diff options
author | Devtools Arcadia <arcadia-devtools@yandex-team.ru> | 2022-02-07 18:08:42 +0300 |
---|---|---|
committer | Devtools Arcadia <arcadia-devtools@mous.vla.yp-c.yandex.net> | 2022-02-07 18:08:42 +0300 |
commit | 1110808a9d39d4b808aef724c861a2e1a38d2a69 (patch) | |
tree | e26c9fed0de5d9873cce7e00bc214573dc2195b7 /contrib/tools/python3/src/Lib/encodings | |
download | ydb-1110808a9d39d4b808aef724c861a2e1a38d2a69.tar.gz |
intermediate changes
ref:cde9a383711a11544ce7e107a78147fb96cc4029
Diffstat (limited to 'contrib/tools/python3/src/Lib/encodings')
122 files changed, 32337 insertions, 0 deletions
diff --git a/contrib/tools/python3/src/Lib/encodings/__init__.py b/contrib/tools/python3/src/Lib/encodings/__init__.py new file mode 100644 index 0000000000..ddd5afdcf2 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/__init__.py @@ -0,0 +1,169 @@ +""" Standard "encodings" Package + + Standard Python encoding modules are stored in this package + directory. + + Codec modules must have names corresponding to normalized encoding + names as defined in the normalize_encoding() function below, e.g. + 'utf-8' must be implemented by the module 'utf_8.py'. + + Each codec module must export the following interface: + + * getregentry() -> codecs.CodecInfo object + The getregentry() API must return a CodecInfo object with encoder, decoder, + incrementalencoder, incrementaldecoder, streamwriter and streamreader + attributes which adhere to the Python Codec Interface Standard. + + In addition, a module may optionally also define the following + APIs which are then used by the package's codec search function: + + * getaliases() -> sequence of encoding name strings to use as aliases + + Alias names returned by getaliases() must be normalized encoding + names as defined by normalize_encoding(). + +Written by Marc-Andre Lemburg (mal@lemburg.com). + +(c) Copyright CNRI, All Rights Reserved. NO WARRANTY. + +"""#" + +import codecs +import sys +from . import aliases + +_cache = {} +_unknown = '--unknown--' +_import_tail = ['*'] +_aliases = aliases.aliases + +class CodecRegistryError(LookupError, SystemError): + pass + +def normalize_encoding(encoding): + + """ Normalize an encoding name. + + Normalization works as follows: all non-alphanumeric + characters except the dot used for Python package names are + collapsed and replaced with a single underscore, e.g. ' -;#' + becomes '_'. Leading and trailing underscores are removed. + + Note that encoding names should be ASCII only. + + """ + if isinstance(encoding, bytes): + encoding = str(encoding, "ascii") + + chars = [] + punct = False + for c in encoding: + if c.isalnum() or c == '.': + if punct and chars: + chars.append('_') + chars.append(c) + punct = False + else: + punct = True + return ''.join(chars) + +def search_function(encoding): + + # Cache lookup + entry = _cache.get(encoding, _unknown) + if entry is not _unknown: + return entry + + # Import the module: + # + # First try to find an alias for the normalized encoding + # name and lookup the module using the aliased name, then try to + # lookup the module using the standard import scheme, i.e. first + # try in the encodings package, then at top-level. + # + norm_encoding = normalize_encoding(encoding) + aliased_encoding = _aliases.get(norm_encoding) or \ + _aliases.get(norm_encoding.replace('.', '_')) + if aliased_encoding is not None: + modnames = [aliased_encoding, + norm_encoding] + else: + modnames = [norm_encoding] + for modname in modnames: + if not modname or '.' in modname: + continue + try: + # Import is absolute to prevent the possibly malicious import of a + # module with side-effects that is not in the 'encodings' package. + mod = __import__('encodings.' + modname, fromlist=_import_tail, + level=0) + except ImportError: + # ImportError may occur because 'encodings.(modname)' does not exist, + # or because it imports a name that does not exist (see mbcs and oem) + pass + else: + break + else: + mod = None + + try: + getregentry = mod.getregentry + except AttributeError: + # Not a codec module + mod = None + + if mod is None: + # Cache misses + _cache[encoding] = None + return None + + # Now ask the module for the registry entry + entry = getregentry() + if not isinstance(entry, codecs.CodecInfo): + if not 4 <= len(entry) <= 7: + raise CodecRegistryError('module "%s" (%s) failed to register' + % (mod.__name__, mod.__file__)) + if not callable(entry[0]) or not callable(entry[1]) or \ + (entry[2] is not None and not callable(entry[2])) or \ + (entry[3] is not None and not callable(entry[3])) or \ + (len(entry) > 4 and entry[4] is not None and not callable(entry[4])) or \ + (len(entry) > 5 and entry[5] is not None and not callable(entry[5])): + raise CodecRegistryError('incompatible codecs in module "%s" (%s)' + % (mod.__name__, mod.__file__)) + if len(entry)<7 or entry[6] is None: + entry += (None,)*(6-len(entry)) + (mod.__name__.split(".", 1)[1],) + entry = codecs.CodecInfo(*entry) + + # Cache the codec registry entry + _cache[encoding] = entry + + # Register its aliases (without overwriting previously registered + # aliases) + try: + codecaliases = mod.getaliases() + except AttributeError: + pass + else: + for alias in codecaliases: + if alias not in _aliases: + _aliases[alias] = modname + + # Return the registry entry + return entry + +# Register the search_function in the Python codec registry +codecs.register(search_function) + +if sys.platform == 'win32': + def _alias_mbcs(encoding): + try: + import _winapi + ansi_code_page = "cp%s" % _winapi.GetACP() + if encoding == ansi_code_page: + import encodings.mbcs + return encodings.mbcs.getregentry() + except ImportError: + # Imports may fail while we are shutting down + pass + + codecs.register(_alias_mbcs) diff --git a/contrib/tools/python3/src/Lib/encodings/aliases.py b/contrib/tools/python3/src/Lib/encodings/aliases.py new file mode 100644 index 0000000000..d85afd6d5c --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/aliases.py @@ -0,0 +1,551 @@ +""" Encoding Aliases Support + + This module is used by the encodings package search function to + map encodings names to module names. + + Note that the search function normalizes the encoding names before + doing the lookup, so the mapping will have to map normalized + encoding names to module names. + + Contents: + + The following aliases dictionary contains mappings of all IANA + character set names for which the Python core library provides + codecs. In addition to these, a few Python specific codec + aliases have also been added. + +""" +aliases = { + + # Please keep this list sorted alphabetically by value ! + + # ascii codec + '646' : 'ascii', + 'ansi_x3.4_1968' : 'ascii', + 'ansi_x3_4_1968' : 'ascii', # some email headers use this non-standard name + 'ansi_x3.4_1986' : 'ascii', + 'cp367' : 'ascii', + 'csascii' : 'ascii', + 'ibm367' : 'ascii', + 'iso646_us' : 'ascii', + 'iso_646.irv_1991' : 'ascii', + 'iso_ir_6' : 'ascii', + 'us' : 'ascii', + 'us_ascii' : 'ascii', + + # base64_codec codec + 'base64' : 'base64_codec', + 'base_64' : 'base64_codec', + + # big5 codec + 'big5_tw' : 'big5', + 'csbig5' : 'big5', + + # big5hkscs codec + 'big5_hkscs' : 'big5hkscs', + 'hkscs' : 'big5hkscs', + + # bz2_codec codec + 'bz2' : 'bz2_codec', + + # cp037 codec + '037' : 'cp037', + 'csibm037' : 'cp037', + 'ebcdic_cp_ca' : 'cp037', + 'ebcdic_cp_nl' : 'cp037', + 'ebcdic_cp_us' : 'cp037', + 'ebcdic_cp_wt' : 'cp037', + 'ibm037' : 'cp037', + 'ibm039' : 'cp037', + + # cp1026 codec + '1026' : 'cp1026', + 'csibm1026' : 'cp1026', + 'ibm1026' : 'cp1026', + + # cp1125 codec + '1125' : 'cp1125', + 'ibm1125' : 'cp1125', + 'cp866u' : 'cp1125', + 'ruscii' : 'cp1125', + + # cp1140 codec + '1140' : 'cp1140', + 'ibm1140' : 'cp1140', + + # cp1250 codec + '1250' : 'cp1250', + 'windows_1250' : 'cp1250', + + # cp1251 codec + '1251' : 'cp1251', + 'windows_1251' : 'cp1251', + + # cp1252 codec + '1252' : 'cp1252', + 'windows_1252' : 'cp1252', + + # cp1253 codec + '1253' : 'cp1253', + 'windows_1253' : 'cp1253', + + # cp1254 codec + '1254' : 'cp1254', + 'windows_1254' : 'cp1254', + + # cp1255 codec + '1255' : 'cp1255', + 'windows_1255' : 'cp1255', + + # cp1256 codec + '1256' : 'cp1256', + 'windows_1256' : 'cp1256', + + # cp1257 codec + '1257' : 'cp1257', + 'windows_1257' : 'cp1257', + + # cp1258 codec + '1258' : 'cp1258', + 'windows_1258' : 'cp1258', + + # cp273 codec + '273' : 'cp273', + 'ibm273' : 'cp273', + 'csibm273' : 'cp273', + + # cp424 codec + '424' : 'cp424', + 'csibm424' : 'cp424', + 'ebcdic_cp_he' : 'cp424', + 'ibm424' : 'cp424', + + # cp437 codec + '437' : 'cp437', + 'cspc8codepage437' : 'cp437', + 'ibm437' : 'cp437', + + # cp500 codec + '500' : 'cp500', + 'csibm500' : 'cp500', + 'ebcdic_cp_be' : 'cp500', + 'ebcdic_cp_ch' : 'cp500', + 'ibm500' : 'cp500', + + # cp775 codec + '775' : 'cp775', + 'cspc775baltic' : 'cp775', + 'ibm775' : 'cp775', + + # cp850 codec + '850' : 'cp850', + 'cspc850multilingual' : 'cp850', + 'ibm850' : 'cp850', + + # cp852 codec + '852' : 'cp852', + 'cspcp852' : 'cp852', + 'ibm852' : 'cp852', + + # cp855 codec + '855' : 'cp855', + 'csibm855' : 'cp855', + 'ibm855' : 'cp855', + + # cp857 codec + '857' : 'cp857', + 'csibm857' : 'cp857', + 'ibm857' : 'cp857', + + # cp858 codec + '858' : 'cp858', + 'csibm858' : 'cp858', + 'ibm858' : 'cp858', + + # cp860 codec + '860' : 'cp860', + 'csibm860' : 'cp860', + 'ibm860' : 'cp860', + + # cp861 codec + '861' : 'cp861', + 'cp_is' : 'cp861', + 'csibm861' : 'cp861', + 'ibm861' : 'cp861', + + # cp862 codec + '862' : 'cp862', + 'cspc862latinhebrew' : 'cp862', + 'ibm862' : 'cp862', + + # cp863 codec + '863' : 'cp863', + 'csibm863' : 'cp863', + 'ibm863' : 'cp863', + + # cp864 codec + '864' : 'cp864', + 'csibm864' : 'cp864', + 'ibm864' : 'cp864', + + # cp865 codec + '865' : 'cp865', + 'csibm865' : 'cp865', + 'ibm865' : 'cp865', + + # cp866 codec + '866' : 'cp866', + 'csibm866' : 'cp866', + 'ibm866' : 'cp866', + + # cp869 codec + '869' : 'cp869', + 'cp_gr' : 'cp869', + 'csibm869' : 'cp869', + 'ibm869' : 'cp869', + + # cp932 codec + '932' : 'cp932', + 'ms932' : 'cp932', + 'mskanji' : 'cp932', + 'ms_kanji' : 'cp932', + + # cp949 codec + '949' : 'cp949', + 'ms949' : 'cp949', + 'uhc' : 'cp949', + + # cp950 codec + '950' : 'cp950', + 'ms950' : 'cp950', + + # euc_jis_2004 codec + 'jisx0213' : 'euc_jis_2004', + 'eucjis2004' : 'euc_jis_2004', + 'euc_jis2004' : 'euc_jis_2004', + + # euc_jisx0213 codec + 'eucjisx0213' : 'euc_jisx0213', + + # euc_jp codec + 'eucjp' : 'euc_jp', + 'ujis' : 'euc_jp', + 'u_jis' : 'euc_jp', + + # euc_kr codec + 'euckr' : 'euc_kr', + 'korean' : 'euc_kr', + 'ksc5601' : 'euc_kr', + 'ks_c_5601' : 'euc_kr', + 'ks_c_5601_1987' : 'euc_kr', + 'ksx1001' : 'euc_kr', + 'ks_x_1001' : 'euc_kr', + + # gb18030 codec + 'gb18030_2000' : 'gb18030', + + # gb2312 codec + 'chinese' : 'gb2312', + 'csiso58gb231280' : 'gb2312', + 'euc_cn' : 'gb2312', + 'euccn' : 'gb2312', + 'eucgb2312_cn' : 'gb2312', + 'gb2312_1980' : 'gb2312', + 'gb2312_80' : 'gb2312', + 'iso_ir_58' : 'gb2312', + + # gbk codec + '936' : 'gbk', + 'cp936' : 'gbk', + 'ms936' : 'gbk', + + # hex_codec codec + 'hex' : 'hex_codec', + + # hp_roman8 codec + 'roman8' : 'hp_roman8', + 'r8' : 'hp_roman8', + 'csHPRoman8' : 'hp_roman8', + 'cp1051' : 'hp_roman8', + 'ibm1051' : 'hp_roman8', + + # hz codec + 'hzgb' : 'hz', + 'hz_gb' : 'hz', + 'hz_gb_2312' : 'hz', + + # iso2022_jp codec + 'csiso2022jp' : 'iso2022_jp', + 'iso2022jp' : 'iso2022_jp', + 'iso_2022_jp' : 'iso2022_jp', + + # iso2022_jp_1 codec + 'iso2022jp_1' : 'iso2022_jp_1', + 'iso_2022_jp_1' : 'iso2022_jp_1', + + # iso2022_jp_2 codec + 'iso2022jp_2' : 'iso2022_jp_2', + 'iso_2022_jp_2' : 'iso2022_jp_2', + + # iso2022_jp_2004 codec + 'iso_2022_jp_2004' : 'iso2022_jp_2004', + 'iso2022jp_2004' : 'iso2022_jp_2004', + + # iso2022_jp_3 codec + 'iso2022jp_3' : 'iso2022_jp_3', + 'iso_2022_jp_3' : 'iso2022_jp_3', + + # iso2022_jp_ext codec + 'iso2022jp_ext' : 'iso2022_jp_ext', + 'iso_2022_jp_ext' : 'iso2022_jp_ext', + + # iso2022_kr codec + 'csiso2022kr' : 'iso2022_kr', + 'iso2022kr' : 'iso2022_kr', + 'iso_2022_kr' : 'iso2022_kr', + + # iso8859_10 codec + 'csisolatin6' : 'iso8859_10', + 'iso_8859_10' : 'iso8859_10', + 'iso_8859_10_1992' : 'iso8859_10', + 'iso_ir_157' : 'iso8859_10', + 'l6' : 'iso8859_10', + 'latin6' : 'iso8859_10', + + # iso8859_11 codec + 'thai' : 'iso8859_11', + 'iso_8859_11' : 'iso8859_11', + 'iso_8859_11_2001' : 'iso8859_11', + + # iso8859_13 codec + 'iso_8859_13' : 'iso8859_13', + 'l7' : 'iso8859_13', + 'latin7' : 'iso8859_13', + + # iso8859_14 codec + 'iso_8859_14' : 'iso8859_14', + 'iso_8859_14_1998' : 'iso8859_14', + 'iso_celtic' : 'iso8859_14', + 'iso_ir_199' : 'iso8859_14', + 'l8' : 'iso8859_14', + 'latin8' : 'iso8859_14', + + # iso8859_15 codec + 'iso_8859_15' : 'iso8859_15', + 'l9' : 'iso8859_15', + 'latin9' : 'iso8859_15', + + # iso8859_16 codec + 'iso_8859_16' : 'iso8859_16', + 'iso_8859_16_2001' : 'iso8859_16', + 'iso_ir_226' : 'iso8859_16', + 'l10' : 'iso8859_16', + 'latin10' : 'iso8859_16', + + # iso8859_2 codec + 'csisolatin2' : 'iso8859_2', + 'iso_8859_2' : 'iso8859_2', + 'iso_8859_2_1987' : 'iso8859_2', + 'iso_ir_101' : 'iso8859_2', + 'l2' : 'iso8859_2', + 'latin2' : 'iso8859_2', + + # iso8859_3 codec + 'csisolatin3' : 'iso8859_3', + 'iso_8859_3' : 'iso8859_3', + 'iso_8859_3_1988' : 'iso8859_3', + 'iso_ir_109' : 'iso8859_3', + 'l3' : 'iso8859_3', + 'latin3' : 'iso8859_3', + + # iso8859_4 codec + 'csisolatin4' : 'iso8859_4', + 'iso_8859_4' : 'iso8859_4', + 'iso_8859_4_1988' : 'iso8859_4', + 'iso_ir_110' : 'iso8859_4', + 'l4' : 'iso8859_4', + 'latin4' : 'iso8859_4', + + # iso8859_5 codec + 'csisolatincyrillic' : 'iso8859_5', + 'cyrillic' : 'iso8859_5', + 'iso_8859_5' : 'iso8859_5', + 'iso_8859_5_1988' : 'iso8859_5', + 'iso_ir_144' : 'iso8859_5', + + # iso8859_6 codec + 'arabic' : 'iso8859_6', + 'asmo_708' : 'iso8859_6', + 'csisolatinarabic' : 'iso8859_6', + 'ecma_114' : 'iso8859_6', + 'iso_8859_6' : 'iso8859_6', + 'iso_8859_6_1987' : 'iso8859_6', + 'iso_ir_127' : 'iso8859_6', + + # iso8859_7 codec + 'csisolatingreek' : 'iso8859_7', + 'ecma_118' : 'iso8859_7', + 'elot_928' : 'iso8859_7', + 'greek' : 'iso8859_7', + 'greek8' : 'iso8859_7', + 'iso_8859_7' : 'iso8859_7', + 'iso_8859_7_1987' : 'iso8859_7', + 'iso_ir_126' : 'iso8859_7', + + # iso8859_8 codec + 'csisolatinhebrew' : 'iso8859_8', + 'hebrew' : 'iso8859_8', + 'iso_8859_8' : 'iso8859_8', + 'iso_8859_8_1988' : 'iso8859_8', + 'iso_ir_138' : 'iso8859_8', + + # iso8859_9 codec + 'csisolatin5' : 'iso8859_9', + 'iso_8859_9' : 'iso8859_9', + 'iso_8859_9_1989' : 'iso8859_9', + 'iso_ir_148' : 'iso8859_9', + 'l5' : 'iso8859_9', + 'latin5' : 'iso8859_9', + + # johab codec + 'cp1361' : 'johab', + 'ms1361' : 'johab', + + # koi8_r codec + 'cskoi8r' : 'koi8_r', + + # kz1048 codec + 'kz_1048' : 'kz1048', + 'rk1048' : 'kz1048', + 'strk1048_2002' : 'kz1048', + + # latin_1 codec + # + # Note that the latin_1 codec is implemented internally in C and a + # lot faster than the charmap codec iso8859_1 which uses the same + # encoding. This is why we discourage the use of the iso8859_1 + # codec and alias it to latin_1 instead. + # + '8859' : 'latin_1', + 'cp819' : 'latin_1', + 'csisolatin1' : 'latin_1', + 'ibm819' : 'latin_1', + 'iso8859' : 'latin_1', + 'iso8859_1' : 'latin_1', + 'iso_8859_1' : 'latin_1', + 'iso_8859_1_1987' : 'latin_1', + 'iso_ir_100' : 'latin_1', + 'l1' : 'latin_1', + 'latin' : 'latin_1', + 'latin1' : 'latin_1', + + # mac_cyrillic codec + 'maccyrillic' : 'mac_cyrillic', + + # mac_greek codec + 'macgreek' : 'mac_greek', + + # mac_iceland codec + 'maciceland' : 'mac_iceland', + + # mac_latin2 codec + 'maccentraleurope' : 'mac_latin2', + 'mac_centeuro' : 'mac_latin2', + 'maclatin2' : 'mac_latin2', + + # mac_roman codec + 'macintosh' : 'mac_roman', + 'macroman' : 'mac_roman', + + # mac_turkish codec + 'macturkish' : 'mac_turkish', + + # mbcs codec + 'ansi' : 'mbcs', + 'dbcs' : 'mbcs', + + # ptcp154 codec + 'csptcp154' : 'ptcp154', + 'pt154' : 'ptcp154', + 'cp154' : 'ptcp154', + 'cyrillic_asian' : 'ptcp154', + + # quopri_codec codec + 'quopri' : 'quopri_codec', + 'quoted_printable' : 'quopri_codec', + 'quotedprintable' : 'quopri_codec', + + # rot_13 codec + 'rot13' : 'rot_13', + + # shift_jis codec + 'csshiftjis' : 'shift_jis', + 'shiftjis' : 'shift_jis', + 'sjis' : 'shift_jis', + 's_jis' : 'shift_jis', + + # shift_jis_2004 codec + 'shiftjis2004' : 'shift_jis_2004', + 'sjis_2004' : 'shift_jis_2004', + 's_jis_2004' : 'shift_jis_2004', + + # shift_jisx0213 codec + 'shiftjisx0213' : 'shift_jisx0213', + 'sjisx0213' : 'shift_jisx0213', + 's_jisx0213' : 'shift_jisx0213', + + # tis_620 codec + 'tis620' : 'tis_620', + 'tis_620_0' : 'tis_620', + 'tis_620_2529_0' : 'tis_620', + 'tis_620_2529_1' : 'tis_620', + 'iso_ir_166' : 'tis_620', + + # utf_16 codec + 'u16' : 'utf_16', + 'utf16' : 'utf_16', + + # utf_16_be codec + 'unicodebigunmarked' : 'utf_16_be', + 'utf_16be' : 'utf_16_be', + + # utf_16_le codec + 'unicodelittleunmarked' : 'utf_16_le', + 'utf_16le' : 'utf_16_le', + + # utf_32 codec + 'u32' : 'utf_32', + 'utf32' : 'utf_32', + + # utf_32_be codec + 'utf_32be' : 'utf_32_be', + + # utf_32_le codec + 'utf_32le' : 'utf_32_le', + + # utf_7 codec + 'u7' : 'utf_7', + 'utf7' : 'utf_7', + 'unicode_1_1_utf_7' : 'utf_7', + + # utf_8 codec + 'u8' : 'utf_8', + 'utf' : 'utf_8', + 'utf8' : 'utf_8', + 'utf8_ucs2' : 'utf_8', + 'utf8_ucs4' : 'utf_8', + 'cp65001' : 'utf_8', + + # uu_codec codec + 'uu' : 'uu_codec', + + # zlib_codec codec + 'zip' : 'zlib_codec', + 'zlib' : 'zlib_codec', + + # temporary mac CJK aliases, will be replaced by proper codecs in 3.1 + 'x_mac_japanese' : 'shift_jis', + 'x_mac_korean' : 'euc_kr', + 'x_mac_simp_chinese' : 'gb2312', + 'x_mac_trad_chinese' : 'big5', +} diff --git a/contrib/tools/python3/src/Lib/encodings/ascii.py b/contrib/tools/python3/src/Lib/encodings/ascii.py new file mode 100644 index 0000000000..2033cde974 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/ascii.py @@ -0,0 +1,50 @@ +""" Python 'ascii' Codec + + +Written by Marc-Andre Lemburg (mal@lemburg.com). + +(c) Copyright CNRI, All Rights Reserved. NO WARRANTY. + +""" +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + # Note: Binding these as C functions will result in the class not + # converting them to methods. This is intended. + encode = codecs.ascii_encode + decode = codecs.ascii_decode + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.ascii_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.ascii_decode(input, self.errors)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +class StreamConverter(StreamWriter,StreamReader): + + encode = codecs.ascii_decode + decode = codecs.ascii_encode + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='ascii', + encode=Codec.encode, + decode=Codec.decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/base64_codec.py b/contrib/tools/python3/src/Lib/encodings/base64_codec.py new file mode 100644 index 0000000000..8e7703b3b6 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/base64_codec.py @@ -0,0 +1,55 @@ +"""Python 'base64_codec' Codec - base64 content transfer encoding. + +This codec de/encodes from bytes to bytes. + +Written by Marc-Andre Lemburg (mal@lemburg.com). +""" + +import codecs +import base64 + +### Codec APIs + +def base64_encode(input, errors='strict'): + assert errors == 'strict' + return (base64.encodebytes(input), len(input)) + +def base64_decode(input, errors='strict'): + assert errors == 'strict' + return (base64.decodebytes(input), len(input)) + +class Codec(codecs.Codec): + def encode(self, input, errors='strict'): + return base64_encode(input, errors) + def decode(self, input, errors='strict'): + return base64_decode(input, errors) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + assert self.errors == 'strict' + return base64.encodebytes(input) + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + assert self.errors == 'strict' + return base64.decodebytes(input) + +class StreamWriter(Codec, codecs.StreamWriter): + charbuffertype = bytes + +class StreamReader(Codec, codecs.StreamReader): + charbuffertype = bytes + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='base64', + encode=base64_encode, + decode=base64_decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + _is_text_encoding=False, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/big5.py b/contrib/tools/python3/src/Lib/encodings/big5.py new file mode 100644 index 0000000000..7adeb0e160 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/big5.py @@ -0,0 +1,39 @@ +# +# big5.py: Python Unicode Codec for BIG5 +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_tw, codecs +import _multibytecodec as mbc + +codec = _codecs_tw.getcodec('big5') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='big5', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/big5hkscs.py b/contrib/tools/python3/src/Lib/encodings/big5hkscs.py new file mode 100644 index 0000000000..350df37baa --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/big5hkscs.py @@ -0,0 +1,39 @@ +# +# big5hkscs.py: Python Unicode Codec for BIG5HKSCS +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_hk, codecs +import _multibytecodec as mbc + +codec = _codecs_hk.getcodec('big5hkscs') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='big5hkscs', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/bz2_codec.py b/contrib/tools/python3/src/Lib/encodings/bz2_codec.py new file mode 100644 index 0000000000..fd9495e341 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/bz2_codec.py @@ -0,0 +1,78 @@ +"""Python 'bz2_codec' Codec - bz2 compression encoding. + +This codec de/encodes from bytes to bytes and is therefore usable with +bytes.transform() and bytes.untransform(). + +Adapted by Raymond Hettinger from zlib_codec.py which was written +by Marc-Andre Lemburg (mal@lemburg.com). +""" + +import codecs +import bz2 # this codec needs the optional bz2 module ! + +### Codec APIs + +def bz2_encode(input, errors='strict'): + assert errors == 'strict' + return (bz2.compress(input), len(input)) + +def bz2_decode(input, errors='strict'): + assert errors == 'strict' + return (bz2.decompress(input), len(input)) + +class Codec(codecs.Codec): + def encode(self, input, errors='strict'): + return bz2_encode(input, errors) + def decode(self, input, errors='strict'): + return bz2_decode(input, errors) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def __init__(self, errors='strict'): + assert errors == 'strict' + self.errors = errors + self.compressobj = bz2.BZ2Compressor() + + def encode(self, input, final=False): + if final: + c = self.compressobj.compress(input) + return c + self.compressobj.flush() + else: + return self.compressobj.compress(input) + + def reset(self): + self.compressobj = bz2.BZ2Compressor() + +class IncrementalDecoder(codecs.IncrementalDecoder): + def __init__(self, errors='strict'): + assert errors == 'strict' + self.errors = errors + self.decompressobj = bz2.BZ2Decompressor() + + def decode(self, input, final=False): + try: + return self.decompressobj.decompress(input) + except EOFError: + return '' + + def reset(self): + self.decompressobj = bz2.BZ2Decompressor() + +class StreamWriter(Codec, codecs.StreamWriter): + charbuffertype = bytes + +class StreamReader(Codec, codecs.StreamReader): + charbuffertype = bytes + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name="bz2", + encode=bz2_encode, + decode=bz2_decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + _is_text_encoding=False, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/charmap.py b/contrib/tools/python3/src/Lib/encodings/charmap.py new file mode 100644 index 0000000000..81189b161a --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/charmap.py @@ -0,0 +1,69 @@ +""" Generic Python Character Mapping Codec. + + Use this codec directly rather than through the automatic + conversion mechanisms supplied by unicode() and .encode(). + + +Written by Marc-Andre Lemburg (mal@lemburg.com). + +(c) Copyright CNRI, All Rights Reserved. NO WARRANTY. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + # Note: Binding these as C functions will result in the class not + # converting them to methods. This is intended. + encode = codecs.charmap_encode + decode = codecs.charmap_decode + +class IncrementalEncoder(codecs.IncrementalEncoder): + def __init__(self, errors='strict', mapping=None): + codecs.IncrementalEncoder.__init__(self, errors) + self.mapping = mapping + + def encode(self, input, final=False): + return codecs.charmap_encode(input, self.errors, self.mapping)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def __init__(self, errors='strict', mapping=None): + codecs.IncrementalDecoder.__init__(self, errors) + self.mapping = mapping + + def decode(self, input, final=False): + return codecs.charmap_decode(input, self.errors, self.mapping)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + + def __init__(self,stream,errors='strict',mapping=None): + codecs.StreamWriter.__init__(self,stream,errors) + self.mapping = mapping + + def encode(self,input,errors='strict'): + return Codec.encode(input,errors,self.mapping) + +class StreamReader(Codec,codecs.StreamReader): + + def __init__(self,stream,errors='strict',mapping=None): + codecs.StreamReader.__init__(self,stream,errors) + self.mapping = mapping + + def decode(self,input,errors='strict'): + return Codec.decode(input,errors,self.mapping) + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='charmap', + encode=Codec.encode, + decode=Codec.decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/cp037.py b/contrib/tools/python3/src/Lib/encodings/cp037.py new file mode 100644 index 0000000000..4edd708f3d --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp037.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec cp037 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP037.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp037', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x9c' # 0x04 -> CONTROL + '\t' # 0x05 -> HORIZONTAL TABULATION + '\x86' # 0x06 -> CONTROL + '\x7f' # 0x07 -> DELETE + '\x97' # 0x08 -> CONTROL + '\x8d' # 0x09 -> CONTROL + '\x8e' # 0x0A -> CONTROL + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x9d' # 0x14 -> CONTROL + '\x85' # 0x15 -> CONTROL + '\x08' # 0x16 -> BACKSPACE + '\x87' # 0x17 -> CONTROL + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x92' # 0x1A -> CONTROL + '\x8f' # 0x1B -> CONTROL + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + '\x80' # 0x20 -> CONTROL + '\x81' # 0x21 -> CONTROL + '\x82' # 0x22 -> CONTROL + '\x83' # 0x23 -> CONTROL + '\x84' # 0x24 -> CONTROL + '\n' # 0x25 -> LINE FEED + '\x17' # 0x26 -> END OF TRANSMISSION BLOCK + '\x1b' # 0x27 -> ESCAPE + '\x88' # 0x28 -> CONTROL + '\x89' # 0x29 -> CONTROL + '\x8a' # 0x2A -> CONTROL + '\x8b' # 0x2B -> CONTROL + '\x8c' # 0x2C -> CONTROL + '\x05' # 0x2D -> ENQUIRY + '\x06' # 0x2E -> ACKNOWLEDGE + '\x07' # 0x2F -> BELL + '\x90' # 0x30 -> CONTROL + '\x91' # 0x31 -> CONTROL + '\x16' # 0x32 -> SYNCHRONOUS IDLE + '\x93' # 0x33 -> CONTROL + '\x94' # 0x34 -> CONTROL + '\x95' # 0x35 -> CONTROL + '\x96' # 0x36 -> CONTROL + '\x04' # 0x37 -> END OF TRANSMISSION + '\x98' # 0x38 -> CONTROL + '\x99' # 0x39 -> CONTROL + '\x9a' # 0x3A -> CONTROL + '\x9b' # 0x3B -> CONTROL + '\x14' # 0x3C -> DEVICE CONTROL FOUR + '\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE + '\x9e' # 0x3E -> CONTROL + '\x1a' # 0x3F -> SUBSTITUTE + ' ' # 0x40 -> SPACE + '\xa0' # 0x41 -> NO-BREAK SPACE + '\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe4' # 0x43 -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE + '\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE + '\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE + '\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe7' # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA + '\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE + '\xa2' # 0x4A -> CENT SIGN + '.' # 0x4B -> FULL STOP + '<' # 0x4C -> LESS-THAN SIGN + '(' # 0x4D -> LEFT PARENTHESIS + '+' # 0x4E -> PLUS SIGN + '|' # 0x4F -> VERTICAL LINE + '&' # 0x50 -> AMPERSAND + '\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE + '\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS + '\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE + '\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE + '\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS + '\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE + '\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN) + '!' # 0x5A -> EXCLAMATION MARK + '$' # 0x5B -> DOLLAR SIGN + '*' # 0x5C -> ASTERISK + ')' # 0x5D -> RIGHT PARENTHESIS + ';' # 0x5E -> SEMICOLON + '\xac' # 0x5F -> NOT SIGN + '-' # 0x60 -> HYPHEN-MINUS + '/' # 0x61 -> SOLIDUS + '\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xc4' # 0x63 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE + '\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE + '\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc7' # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE + '\xa6' # 0x6A -> BROKEN BAR + ',' # 0x6B -> COMMA + '%' # 0x6C -> PERCENT SIGN + '_' # 0x6D -> LOW LINE + '>' # 0x6E -> GREATER-THAN SIGN + '?' # 0x6F -> QUESTION MARK + '\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE + '\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE + '`' # 0x79 -> GRAVE ACCENT + ':' # 0x7A -> COLON + '#' # 0x7B -> NUMBER SIGN + '@' # 0x7C -> COMMERCIAL AT + "'" # 0x7D -> APOSTROPHE + '=' # 0x7E -> EQUALS SIGN + '"' # 0x7F -> QUOTATION MARK + '\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE + 'a' # 0x81 -> LATIN SMALL LETTER A + 'b' # 0x82 -> LATIN SMALL LETTER B + 'c' # 0x83 -> LATIN SMALL LETTER C + 'd' # 0x84 -> LATIN SMALL LETTER D + 'e' # 0x85 -> LATIN SMALL LETTER E + 'f' # 0x86 -> LATIN SMALL LETTER F + 'g' # 0x87 -> LATIN SMALL LETTER G + 'h' # 0x88 -> LATIN SMALL LETTER H + 'i' # 0x89 -> LATIN SMALL LETTER I + '\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xf0' # 0x8C -> LATIN SMALL LETTER ETH (ICELANDIC) + '\xfd' # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE + '\xfe' # 0x8E -> LATIN SMALL LETTER THORN (ICELANDIC) + '\xb1' # 0x8F -> PLUS-MINUS SIGN + '\xb0' # 0x90 -> DEGREE SIGN + 'j' # 0x91 -> LATIN SMALL LETTER J + 'k' # 0x92 -> LATIN SMALL LETTER K + 'l' # 0x93 -> LATIN SMALL LETTER L + 'm' # 0x94 -> LATIN SMALL LETTER M + 'n' # 0x95 -> LATIN SMALL LETTER N + 'o' # 0x96 -> LATIN SMALL LETTER O + 'p' # 0x97 -> LATIN SMALL LETTER P + 'q' # 0x98 -> LATIN SMALL LETTER Q + 'r' # 0x99 -> LATIN SMALL LETTER R + '\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR + '\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR + '\xe6' # 0x9C -> LATIN SMALL LIGATURE AE + '\xb8' # 0x9D -> CEDILLA + '\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE + '\xa4' # 0x9F -> CURRENCY SIGN + '\xb5' # 0xA0 -> MICRO SIGN + '~' # 0xA1 -> TILDE + 's' # 0xA2 -> LATIN SMALL LETTER S + 't' # 0xA3 -> LATIN SMALL LETTER T + 'u' # 0xA4 -> LATIN SMALL LETTER U + 'v' # 0xA5 -> LATIN SMALL LETTER V + 'w' # 0xA6 -> LATIN SMALL LETTER W + 'x' # 0xA7 -> LATIN SMALL LETTER X + 'y' # 0xA8 -> LATIN SMALL LETTER Y + 'z' # 0xA9 -> LATIN SMALL LETTER Z + '\xa1' # 0xAA -> INVERTED EXCLAMATION MARK + '\xbf' # 0xAB -> INVERTED QUESTION MARK + '\xd0' # 0xAC -> LATIN CAPITAL LETTER ETH (ICELANDIC) + '\xdd' # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE + '\xde' # 0xAE -> LATIN CAPITAL LETTER THORN (ICELANDIC) + '\xae' # 0xAF -> REGISTERED SIGN + '^' # 0xB0 -> CIRCUMFLEX ACCENT + '\xa3' # 0xB1 -> POUND SIGN + '\xa5' # 0xB2 -> YEN SIGN + '\xb7' # 0xB3 -> MIDDLE DOT + '\xa9' # 0xB4 -> COPYRIGHT SIGN + '\xa7' # 0xB5 -> SECTION SIGN + '\xb6' # 0xB6 -> PILCROW SIGN + '\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER + '\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF + '\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS + '[' # 0xBA -> LEFT SQUARE BRACKET + ']' # 0xBB -> RIGHT SQUARE BRACKET + '\xaf' # 0xBC -> MACRON + '\xa8' # 0xBD -> DIAERESIS + '\xb4' # 0xBE -> ACUTE ACCENT + '\xd7' # 0xBF -> MULTIPLICATION SIGN + '{' # 0xC0 -> LEFT CURLY BRACKET + 'A' # 0xC1 -> LATIN CAPITAL LETTER A + 'B' # 0xC2 -> LATIN CAPITAL LETTER B + 'C' # 0xC3 -> LATIN CAPITAL LETTER C + 'D' # 0xC4 -> LATIN CAPITAL LETTER D + 'E' # 0xC5 -> LATIN CAPITAL LETTER E + 'F' # 0xC6 -> LATIN CAPITAL LETTER F + 'G' # 0xC7 -> LATIN CAPITAL LETTER G + 'H' # 0xC8 -> LATIN CAPITAL LETTER H + 'I' # 0xC9 -> LATIN CAPITAL LETTER I + '\xad' # 0xCA -> SOFT HYPHEN + '\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf6' # 0xCC -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE + '\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE + '\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE + '}' # 0xD0 -> RIGHT CURLY BRACKET + 'J' # 0xD1 -> LATIN CAPITAL LETTER J + 'K' # 0xD2 -> LATIN CAPITAL LETTER K + 'L' # 0xD3 -> LATIN CAPITAL LETTER L + 'M' # 0xD4 -> LATIN CAPITAL LETTER M + 'N' # 0xD5 -> LATIN CAPITAL LETTER N + 'O' # 0xD6 -> LATIN CAPITAL LETTER O + 'P' # 0xD7 -> LATIN CAPITAL LETTER P + 'Q' # 0xD8 -> LATIN CAPITAL LETTER Q + 'R' # 0xD9 -> LATIN CAPITAL LETTER R + '\xb9' # 0xDA -> SUPERSCRIPT ONE + '\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0xDC -> LATIN SMALL LETTER U WITH DIAERESIS + '\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE + '\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE + '\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS + '\\' # 0xE0 -> REVERSE SOLIDUS + '\xf7' # 0xE1 -> DIVISION SIGN + 'S' # 0xE2 -> LATIN CAPITAL LETTER S + 'T' # 0xE3 -> LATIN CAPITAL LETTER T + 'U' # 0xE4 -> LATIN CAPITAL LETTER U + 'V' # 0xE5 -> LATIN CAPITAL LETTER V + 'W' # 0xE6 -> LATIN CAPITAL LETTER W + 'X' # 0xE7 -> LATIN CAPITAL LETTER X + 'Y' # 0xE8 -> LATIN CAPITAL LETTER Y + 'Z' # 0xE9 -> LATIN CAPITAL LETTER Z + '\xb2' # 0xEA -> SUPERSCRIPT TWO + '\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\xd6' # 0xEC -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE + '\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE + '0' # 0xF0 -> DIGIT ZERO + '1' # 0xF1 -> DIGIT ONE + '2' # 0xF2 -> DIGIT TWO + '3' # 0xF3 -> DIGIT THREE + '4' # 0xF4 -> DIGIT FOUR + '5' # 0xF5 -> DIGIT FIVE + '6' # 0xF6 -> DIGIT SIX + '7' # 0xF7 -> DIGIT SEVEN + '8' # 0xF8 -> DIGIT EIGHT + '9' # 0xF9 -> DIGIT NINE + '\xb3' # 0xFA -> SUPERSCRIPT THREE + '\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xdc' # 0xFC -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE + '\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE + '\x9f' # 0xFF -> CONTROL +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/cp1006.py b/contrib/tools/python3/src/Lib/encodings/cp1006.py new file mode 100644 index 0000000000..a1221c3ef1 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp1006.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec cp1006 generated from 'MAPPINGS/VENDORS/MISC/CP1006.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp1006', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\x80' # 0x80 -> <control> + '\x81' # 0x81 -> <control> + '\x82' # 0x82 -> <control> + '\x83' # 0x83 -> <control> + '\x84' # 0x84 -> <control> + '\x85' # 0x85 -> <control> + '\x86' # 0x86 -> <control> + '\x87' # 0x87 -> <control> + '\x88' # 0x88 -> <control> + '\x89' # 0x89 -> <control> + '\x8a' # 0x8A -> <control> + '\x8b' # 0x8B -> <control> + '\x8c' # 0x8C -> <control> + '\x8d' # 0x8D -> <control> + '\x8e' # 0x8E -> <control> + '\x8f' # 0x8F -> <control> + '\x90' # 0x90 -> <control> + '\x91' # 0x91 -> <control> + '\x92' # 0x92 -> <control> + '\x93' # 0x93 -> <control> + '\x94' # 0x94 -> <control> + '\x95' # 0x95 -> <control> + '\x96' # 0x96 -> <control> + '\x97' # 0x97 -> <control> + '\x98' # 0x98 -> <control> + '\x99' # 0x99 -> <control> + '\x9a' # 0x9A -> <control> + '\x9b' # 0x9B -> <control> + '\x9c' # 0x9C -> <control> + '\x9d' # 0x9D -> <control> + '\x9e' # 0x9E -> <control> + '\x9f' # 0x9F -> <control> + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\u06f0' # 0xA1 -> EXTENDED ARABIC-INDIC DIGIT ZERO + '\u06f1' # 0xA2 -> EXTENDED ARABIC-INDIC DIGIT ONE + '\u06f2' # 0xA3 -> EXTENDED ARABIC-INDIC DIGIT TWO + '\u06f3' # 0xA4 -> EXTENDED ARABIC-INDIC DIGIT THREE + '\u06f4' # 0xA5 -> EXTENDED ARABIC-INDIC DIGIT FOUR + '\u06f5' # 0xA6 -> EXTENDED ARABIC-INDIC DIGIT FIVE + '\u06f6' # 0xA7 -> EXTENDED ARABIC-INDIC DIGIT SIX + '\u06f7' # 0xA8 -> EXTENDED ARABIC-INDIC DIGIT SEVEN + '\u06f8' # 0xA9 -> EXTENDED ARABIC-INDIC DIGIT EIGHT + '\u06f9' # 0xAA -> EXTENDED ARABIC-INDIC DIGIT NINE + '\u060c' # 0xAB -> ARABIC COMMA + '\u061b' # 0xAC -> ARABIC SEMICOLON + '\xad' # 0xAD -> SOFT HYPHEN + '\u061f' # 0xAE -> ARABIC QUESTION MARK + '\ufe81' # 0xAF -> ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM + '\ufe8d' # 0xB0 -> ARABIC LETTER ALEF ISOLATED FORM + '\ufe8e' # 0xB1 -> ARABIC LETTER ALEF FINAL FORM + '\ufe8e' # 0xB2 -> ARABIC LETTER ALEF FINAL FORM + '\ufe8f' # 0xB3 -> ARABIC LETTER BEH ISOLATED FORM + '\ufe91' # 0xB4 -> ARABIC LETTER BEH INITIAL FORM + '\ufb56' # 0xB5 -> ARABIC LETTER PEH ISOLATED FORM + '\ufb58' # 0xB6 -> ARABIC LETTER PEH INITIAL FORM + '\ufe93' # 0xB7 -> ARABIC LETTER TEH MARBUTA ISOLATED FORM + '\ufe95' # 0xB8 -> ARABIC LETTER TEH ISOLATED FORM + '\ufe97' # 0xB9 -> ARABIC LETTER TEH INITIAL FORM + '\ufb66' # 0xBA -> ARABIC LETTER TTEH ISOLATED FORM + '\ufb68' # 0xBB -> ARABIC LETTER TTEH INITIAL FORM + '\ufe99' # 0xBC -> ARABIC LETTER THEH ISOLATED FORM + '\ufe9b' # 0xBD -> ARABIC LETTER THEH INITIAL FORM + '\ufe9d' # 0xBE -> ARABIC LETTER JEEM ISOLATED FORM + '\ufe9f' # 0xBF -> ARABIC LETTER JEEM INITIAL FORM + '\ufb7a' # 0xC0 -> ARABIC LETTER TCHEH ISOLATED FORM + '\ufb7c' # 0xC1 -> ARABIC LETTER TCHEH INITIAL FORM + '\ufea1' # 0xC2 -> ARABIC LETTER HAH ISOLATED FORM + '\ufea3' # 0xC3 -> ARABIC LETTER HAH INITIAL FORM + '\ufea5' # 0xC4 -> ARABIC LETTER KHAH ISOLATED FORM + '\ufea7' # 0xC5 -> ARABIC LETTER KHAH INITIAL FORM + '\ufea9' # 0xC6 -> ARABIC LETTER DAL ISOLATED FORM + '\ufb84' # 0xC7 -> ARABIC LETTER DAHAL ISOLATED FORMN + '\ufeab' # 0xC8 -> ARABIC LETTER THAL ISOLATED FORM + '\ufead' # 0xC9 -> ARABIC LETTER REH ISOLATED FORM + '\ufb8c' # 0xCA -> ARABIC LETTER RREH ISOLATED FORM + '\ufeaf' # 0xCB -> ARABIC LETTER ZAIN ISOLATED FORM + '\ufb8a' # 0xCC -> ARABIC LETTER JEH ISOLATED FORM + '\ufeb1' # 0xCD -> ARABIC LETTER SEEN ISOLATED FORM + '\ufeb3' # 0xCE -> ARABIC LETTER SEEN INITIAL FORM + '\ufeb5' # 0xCF -> ARABIC LETTER SHEEN ISOLATED FORM + '\ufeb7' # 0xD0 -> ARABIC LETTER SHEEN INITIAL FORM + '\ufeb9' # 0xD1 -> ARABIC LETTER SAD ISOLATED FORM + '\ufebb' # 0xD2 -> ARABIC LETTER SAD INITIAL FORM + '\ufebd' # 0xD3 -> ARABIC LETTER DAD ISOLATED FORM + '\ufebf' # 0xD4 -> ARABIC LETTER DAD INITIAL FORM + '\ufec1' # 0xD5 -> ARABIC LETTER TAH ISOLATED FORM + '\ufec5' # 0xD6 -> ARABIC LETTER ZAH ISOLATED FORM + '\ufec9' # 0xD7 -> ARABIC LETTER AIN ISOLATED FORM + '\ufeca' # 0xD8 -> ARABIC LETTER AIN FINAL FORM + '\ufecb' # 0xD9 -> ARABIC LETTER AIN INITIAL FORM + '\ufecc' # 0xDA -> ARABIC LETTER AIN MEDIAL FORM + '\ufecd' # 0xDB -> ARABIC LETTER GHAIN ISOLATED FORM + '\ufece' # 0xDC -> ARABIC LETTER GHAIN FINAL FORM + '\ufecf' # 0xDD -> ARABIC LETTER GHAIN INITIAL FORM + '\ufed0' # 0xDE -> ARABIC LETTER GHAIN MEDIAL FORM + '\ufed1' # 0xDF -> ARABIC LETTER FEH ISOLATED FORM + '\ufed3' # 0xE0 -> ARABIC LETTER FEH INITIAL FORM + '\ufed5' # 0xE1 -> ARABIC LETTER QAF ISOLATED FORM + '\ufed7' # 0xE2 -> ARABIC LETTER QAF INITIAL FORM + '\ufed9' # 0xE3 -> ARABIC LETTER KAF ISOLATED FORM + '\ufedb' # 0xE4 -> ARABIC LETTER KAF INITIAL FORM + '\ufb92' # 0xE5 -> ARABIC LETTER GAF ISOLATED FORM + '\ufb94' # 0xE6 -> ARABIC LETTER GAF INITIAL FORM + '\ufedd' # 0xE7 -> ARABIC LETTER LAM ISOLATED FORM + '\ufedf' # 0xE8 -> ARABIC LETTER LAM INITIAL FORM + '\ufee0' # 0xE9 -> ARABIC LETTER LAM MEDIAL FORM + '\ufee1' # 0xEA -> ARABIC LETTER MEEM ISOLATED FORM + '\ufee3' # 0xEB -> ARABIC LETTER MEEM INITIAL FORM + '\ufb9e' # 0xEC -> ARABIC LETTER NOON GHUNNA ISOLATED FORM + '\ufee5' # 0xED -> ARABIC LETTER NOON ISOLATED FORM + '\ufee7' # 0xEE -> ARABIC LETTER NOON INITIAL FORM + '\ufe85' # 0xEF -> ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM + '\ufeed' # 0xF0 -> ARABIC LETTER WAW ISOLATED FORM + '\ufba6' # 0xF1 -> ARABIC LETTER HEH GOAL ISOLATED FORM + '\ufba8' # 0xF2 -> ARABIC LETTER HEH GOAL INITIAL FORM + '\ufba9' # 0xF3 -> ARABIC LETTER HEH GOAL MEDIAL FORM + '\ufbaa' # 0xF4 -> ARABIC LETTER HEH DOACHASHMEE ISOLATED FORM + '\ufe80' # 0xF5 -> ARABIC LETTER HAMZA ISOLATED FORM + '\ufe89' # 0xF6 -> ARABIC LETTER YEH WITH HAMZA ABOVE ISOLATED FORM + '\ufe8a' # 0xF7 -> ARABIC LETTER YEH WITH HAMZA ABOVE FINAL FORM + '\ufe8b' # 0xF8 -> ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM + '\ufef1' # 0xF9 -> ARABIC LETTER YEH ISOLATED FORM + '\ufef2' # 0xFA -> ARABIC LETTER YEH FINAL FORM + '\ufef3' # 0xFB -> ARABIC LETTER YEH INITIAL FORM + '\ufbb0' # 0xFC -> ARABIC LETTER YEH BARREE WITH HAMZA ABOVE ISOLATED FORM + '\ufbae' # 0xFD -> ARABIC LETTER YEH BARREE ISOLATED FORM + '\ufe7c' # 0xFE -> ARABIC SHADDA ISOLATED FORM + '\ufe7d' # 0xFF -> ARABIC SHADDA MEDIAL FORM +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/cp1026.py b/contrib/tools/python3/src/Lib/encodings/cp1026.py new file mode 100644 index 0000000000..46f71f74da --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp1026.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec cp1026 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP1026.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp1026', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x9c' # 0x04 -> CONTROL + '\t' # 0x05 -> HORIZONTAL TABULATION + '\x86' # 0x06 -> CONTROL + '\x7f' # 0x07 -> DELETE + '\x97' # 0x08 -> CONTROL + '\x8d' # 0x09 -> CONTROL + '\x8e' # 0x0A -> CONTROL + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x9d' # 0x14 -> CONTROL + '\x85' # 0x15 -> CONTROL + '\x08' # 0x16 -> BACKSPACE + '\x87' # 0x17 -> CONTROL + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x92' # 0x1A -> CONTROL + '\x8f' # 0x1B -> CONTROL + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + '\x80' # 0x20 -> CONTROL + '\x81' # 0x21 -> CONTROL + '\x82' # 0x22 -> CONTROL + '\x83' # 0x23 -> CONTROL + '\x84' # 0x24 -> CONTROL + '\n' # 0x25 -> LINE FEED + '\x17' # 0x26 -> END OF TRANSMISSION BLOCK + '\x1b' # 0x27 -> ESCAPE + '\x88' # 0x28 -> CONTROL + '\x89' # 0x29 -> CONTROL + '\x8a' # 0x2A -> CONTROL + '\x8b' # 0x2B -> CONTROL + '\x8c' # 0x2C -> CONTROL + '\x05' # 0x2D -> ENQUIRY + '\x06' # 0x2E -> ACKNOWLEDGE + '\x07' # 0x2F -> BELL + '\x90' # 0x30 -> CONTROL + '\x91' # 0x31 -> CONTROL + '\x16' # 0x32 -> SYNCHRONOUS IDLE + '\x93' # 0x33 -> CONTROL + '\x94' # 0x34 -> CONTROL + '\x95' # 0x35 -> CONTROL + '\x96' # 0x36 -> CONTROL + '\x04' # 0x37 -> END OF TRANSMISSION + '\x98' # 0x38 -> CONTROL + '\x99' # 0x39 -> CONTROL + '\x9a' # 0x3A -> CONTROL + '\x9b' # 0x3B -> CONTROL + '\x14' # 0x3C -> DEVICE CONTROL FOUR + '\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE + '\x9e' # 0x3E -> CONTROL + '\x1a' # 0x3F -> SUBSTITUTE + ' ' # 0x40 -> SPACE + '\xa0' # 0x41 -> NO-BREAK SPACE + '\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe4' # 0x43 -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE + '\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE + '\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE + '\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE + '{' # 0x48 -> LEFT CURLY BRACKET + '\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE + '\xc7' # 0x4A -> LATIN CAPITAL LETTER C WITH CEDILLA + '.' # 0x4B -> FULL STOP + '<' # 0x4C -> LESS-THAN SIGN + '(' # 0x4D -> LEFT PARENTHESIS + '+' # 0x4E -> PLUS SIGN + '!' # 0x4F -> EXCLAMATION MARK + '&' # 0x50 -> AMPERSAND + '\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE + '\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS + '\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE + '\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE + '\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS + '\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE + '\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN) + '\u011e' # 0x5A -> LATIN CAPITAL LETTER G WITH BREVE + '\u0130' # 0x5B -> LATIN CAPITAL LETTER I WITH DOT ABOVE + '*' # 0x5C -> ASTERISK + ')' # 0x5D -> RIGHT PARENTHESIS + ';' # 0x5E -> SEMICOLON + '^' # 0x5F -> CIRCUMFLEX ACCENT + '-' # 0x60 -> HYPHEN-MINUS + '/' # 0x61 -> SOLIDUS + '\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xc4' # 0x63 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE + '\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE + '\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '[' # 0x68 -> LEFT SQUARE BRACKET + '\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE + '\u015f' # 0x6A -> LATIN SMALL LETTER S WITH CEDILLA + ',' # 0x6B -> COMMA + '%' # 0x6C -> PERCENT SIGN + '_' # 0x6D -> LOW LINE + '>' # 0x6E -> GREATER-THAN SIGN + '?' # 0x6F -> QUESTION MARK + '\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE + '\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE + '\u0131' # 0x79 -> LATIN SMALL LETTER DOTLESS I + ':' # 0x7A -> COLON + '\xd6' # 0x7B -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\u015e' # 0x7C -> LATIN CAPITAL LETTER S WITH CEDILLA + "'" # 0x7D -> APOSTROPHE + '=' # 0x7E -> EQUALS SIGN + '\xdc' # 0x7F -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE + 'a' # 0x81 -> LATIN SMALL LETTER A + 'b' # 0x82 -> LATIN SMALL LETTER B + 'c' # 0x83 -> LATIN SMALL LETTER C + 'd' # 0x84 -> LATIN SMALL LETTER D + 'e' # 0x85 -> LATIN SMALL LETTER E + 'f' # 0x86 -> LATIN SMALL LETTER F + 'g' # 0x87 -> LATIN SMALL LETTER G + 'h' # 0x88 -> LATIN SMALL LETTER H + 'i' # 0x89 -> LATIN SMALL LETTER I + '\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '}' # 0x8C -> RIGHT CURLY BRACKET + '`' # 0x8D -> GRAVE ACCENT + '\xa6' # 0x8E -> BROKEN BAR + '\xb1' # 0x8F -> PLUS-MINUS SIGN + '\xb0' # 0x90 -> DEGREE SIGN + 'j' # 0x91 -> LATIN SMALL LETTER J + 'k' # 0x92 -> LATIN SMALL LETTER K + 'l' # 0x93 -> LATIN SMALL LETTER L + 'm' # 0x94 -> LATIN SMALL LETTER M + 'n' # 0x95 -> LATIN SMALL LETTER N + 'o' # 0x96 -> LATIN SMALL LETTER O + 'p' # 0x97 -> LATIN SMALL LETTER P + 'q' # 0x98 -> LATIN SMALL LETTER Q + 'r' # 0x99 -> LATIN SMALL LETTER R + '\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR + '\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR + '\xe6' # 0x9C -> LATIN SMALL LIGATURE AE + '\xb8' # 0x9D -> CEDILLA + '\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE + '\xa4' # 0x9F -> CURRENCY SIGN + '\xb5' # 0xA0 -> MICRO SIGN + '\xf6' # 0xA1 -> LATIN SMALL LETTER O WITH DIAERESIS + 's' # 0xA2 -> LATIN SMALL LETTER S + 't' # 0xA3 -> LATIN SMALL LETTER T + 'u' # 0xA4 -> LATIN SMALL LETTER U + 'v' # 0xA5 -> LATIN SMALL LETTER V + 'w' # 0xA6 -> LATIN SMALL LETTER W + 'x' # 0xA7 -> LATIN SMALL LETTER X + 'y' # 0xA8 -> LATIN SMALL LETTER Y + 'z' # 0xA9 -> LATIN SMALL LETTER Z + '\xa1' # 0xAA -> INVERTED EXCLAMATION MARK + '\xbf' # 0xAB -> INVERTED QUESTION MARK + ']' # 0xAC -> RIGHT SQUARE BRACKET + '$' # 0xAD -> DOLLAR SIGN + '@' # 0xAE -> COMMERCIAL AT + '\xae' # 0xAF -> REGISTERED SIGN + '\xa2' # 0xB0 -> CENT SIGN + '\xa3' # 0xB1 -> POUND SIGN + '\xa5' # 0xB2 -> YEN SIGN + '\xb7' # 0xB3 -> MIDDLE DOT + '\xa9' # 0xB4 -> COPYRIGHT SIGN + '\xa7' # 0xB5 -> SECTION SIGN + '\xb6' # 0xB6 -> PILCROW SIGN + '\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER + '\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF + '\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS + '\xac' # 0xBA -> NOT SIGN + '|' # 0xBB -> VERTICAL LINE + '\xaf' # 0xBC -> MACRON + '\xa8' # 0xBD -> DIAERESIS + '\xb4' # 0xBE -> ACUTE ACCENT + '\xd7' # 0xBF -> MULTIPLICATION SIGN + '\xe7' # 0xC0 -> LATIN SMALL LETTER C WITH CEDILLA + 'A' # 0xC1 -> LATIN CAPITAL LETTER A + 'B' # 0xC2 -> LATIN CAPITAL LETTER B + 'C' # 0xC3 -> LATIN CAPITAL LETTER C + 'D' # 0xC4 -> LATIN CAPITAL LETTER D + 'E' # 0xC5 -> LATIN CAPITAL LETTER E + 'F' # 0xC6 -> LATIN CAPITAL LETTER F + 'G' # 0xC7 -> LATIN CAPITAL LETTER G + 'H' # 0xC8 -> LATIN CAPITAL LETTER H + 'I' # 0xC9 -> LATIN CAPITAL LETTER I + '\xad' # 0xCA -> SOFT HYPHEN + '\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '~' # 0xCC -> TILDE + '\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE + '\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE + '\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE + '\u011f' # 0xD0 -> LATIN SMALL LETTER G WITH BREVE + 'J' # 0xD1 -> LATIN CAPITAL LETTER J + 'K' # 0xD2 -> LATIN CAPITAL LETTER K + 'L' # 0xD3 -> LATIN CAPITAL LETTER L + 'M' # 0xD4 -> LATIN CAPITAL LETTER M + 'N' # 0xD5 -> LATIN CAPITAL LETTER N + 'O' # 0xD6 -> LATIN CAPITAL LETTER O + 'P' # 0xD7 -> LATIN CAPITAL LETTER P + 'Q' # 0xD8 -> LATIN CAPITAL LETTER Q + 'R' # 0xD9 -> LATIN CAPITAL LETTER R + '\xb9' # 0xDA -> SUPERSCRIPT ONE + '\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\\' # 0xDC -> REVERSE SOLIDUS + '\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE + '\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE + '\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS + '\xfc' # 0xE0 -> LATIN SMALL LETTER U WITH DIAERESIS + '\xf7' # 0xE1 -> DIVISION SIGN + 'S' # 0xE2 -> LATIN CAPITAL LETTER S + 'T' # 0xE3 -> LATIN CAPITAL LETTER T + 'U' # 0xE4 -> LATIN CAPITAL LETTER U + 'V' # 0xE5 -> LATIN CAPITAL LETTER V + 'W' # 0xE6 -> LATIN CAPITAL LETTER W + 'X' # 0xE7 -> LATIN CAPITAL LETTER X + 'Y' # 0xE8 -> LATIN CAPITAL LETTER Y + 'Z' # 0xE9 -> LATIN CAPITAL LETTER Z + '\xb2' # 0xEA -> SUPERSCRIPT TWO + '\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '#' # 0xEC -> NUMBER SIGN + '\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE + '\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE + '0' # 0xF0 -> DIGIT ZERO + '1' # 0xF1 -> DIGIT ONE + '2' # 0xF2 -> DIGIT TWO + '3' # 0xF3 -> DIGIT THREE + '4' # 0xF4 -> DIGIT FOUR + '5' # 0xF5 -> DIGIT FIVE + '6' # 0xF6 -> DIGIT SIX + '7' # 0xF7 -> DIGIT SEVEN + '8' # 0xF8 -> DIGIT EIGHT + '9' # 0xF9 -> DIGIT NINE + '\xb3' # 0xFA -> SUPERSCRIPT THREE + '\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '"' # 0xFC -> QUOTATION MARK + '\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE + '\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE + '\x9f' # 0xFF -> CONTROL +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/cp1125.py b/contrib/tools/python3/src/Lib/encodings/cp1125.py new file mode 100644 index 0000000000..b1fd69deb0 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp1125.py @@ -0,0 +1,698 @@ +""" Python Character Mapping Codec for CP1125 + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_map) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp1125', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + +### Decoding Map + +decoding_map = codecs.make_identity_dict(range(256)) +decoding_map.update({ + 0x0080: 0x0410, # CYRILLIC CAPITAL LETTER A + 0x0081: 0x0411, # CYRILLIC CAPITAL LETTER BE + 0x0082: 0x0412, # CYRILLIC CAPITAL LETTER VE + 0x0083: 0x0413, # CYRILLIC CAPITAL LETTER GHE + 0x0084: 0x0414, # CYRILLIC CAPITAL LETTER DE + 0x0085: 0x0415, # CYRILLIC CAPITAL LETTER IE + 0x0086: 0x0416, # CYRILLIC CAPITAL LETTER ZHE + 0x0087: 0x0417, # CYRILLIC CAPITAL LETTER ZE + 0x0088: 0x0418, # CYRILLIC CAPITAL LETTER I + 0x0089: 0x0419, # CYRILLIC CAPITAL LETTER SHORT I + 0x008a: 0x041a, # CYRILLIC CAPITAL LETTER KA + 0x008b: 0x041b, # CYRILLIC CAPITAL LETTER EL + 0x008c: 0x041c, # CYRILLIC CAPITAL LETTER EM + 0x008d: 0x041d, # CYRILLIC CAPITAL LETTER EN + 0x008e: 0x041e, # CYRILLIC CAPITAL LETTER O + 0x008f: 0x041f, # CYRILLIC CAPITAL LETTER PE + 0x0090: 0x0420, # CYRILLIC CAPITAL LETTER ER + 0x0091: 0x0421, # CYRILLIC CAPITAL LETTER ES + 0x0092: 0x0422, # CYRILLIC CAPITAL LETTER TE + 0x0093: 0x0423, # CYRILLIC CAPITAL LETTER U + 0x0094: 0x0424, # CYRILLIC CAPITAL LETTER EF + 0x0095: 0x0425, # CYRILLIC CAPITAL LETTER HA + 0x0096: 0x0426, # CYRILLIC CAPITAL LETTER TSE + 0x0097: 0x0427, # CYRILLIC CAPITAL LETTER CHE + 0x0098: 0x0428, # CYRILLIC CAPITAL LETTER SHA + 0x0099: 0x0429, # CYRILLIC CAPITAL LETTER SHCHA + 0x009a: 0x042a, # CYRILLIC CAPITAL LETTER HARD SIGN + 0x009b: 0x042b, # CYRILLIC CAPITAL LETTER YERU + 0x009c: 0x042c, # CYRILLIC CAPITAL LETTER SOFT SIGN + 0x009d: 0x042d, # CYRILLIC CAPITAL LETTER E + 0x009e: 0x042e, # CYRILLIC CAPITAL LETTER YU + 0x009f: 0x042f, # CYRILLIC CAPITAL LETTER YA + 0x00a0: 0x0430, # CYRILLIC SMALL LETTER A + 0x00a1: 0x0431, # CYRILLIC SMALL LETTER BE + 0x00a2: 0x0432, # CYRILLIC SMALL LETTER VE + 0x00a3: 0x0433, # CYRILLIC SMALL LETTER GHE + 0x00a4: 0x0434, # CYRILLIC SMALL LETTER DE + 0x00a5: 0x0435, # CYRILLIC SMALL LETTER IE + 0x00a6: 0x0436, # CYRILLIC SMALL LETTER ZHE + 0x00a7: 0x0437, # CYRILLIC SMALL LETTER ZE + 0x00a8: 0x0438, # CYRILLIC SMALL LETTER I + 0x00a9: 0x0439, # CYRILLIC SMALL LETTER SHORT I + 0x00aa: 0x043a, # CYRILLIC SMALL LETTER KA + 0x00ab: 0x043b, # CYRILLIC SMALL LETTER EL + 0x00ac: 0x043c, # CYRILLIC SMALL LETTER EM + 0x00ad: 0x043d, # CYRILLIC SMALL LETTER EN + 0x00ae: 0x043e, # CYRILLIC SMALL LETTER O + 0x00af: 0x043f, # CYRILLIC SMALL LETTER PE + 0x00b0: 0x2591, # LIGHT SHADE + 0x00b1: 0x2592, # MEDIUM SHADE + 0x00b2: 0x2593, # DARK SHADE + 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL + 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL + 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL + 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT + 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x00db: 0x2588, # FULL BLOCK + 0x00dc: 0x2584, # LOWER HALF BLOCK + 0x00dd: 0x258c, # LEFT HALF BLOCK + 0x00de: 0x2590, # RIGHT HALF BLOCK + 0x00df: 0x2580, # UPPER HALF BLOCK + 0x00e0: 0x0440, # CYRILLIC SMALL LETTER ER + 0x00e1: 0x0441, # CYRILLIC SMALL LETTER ES + 0x00e2: 0x0442, # CYRILLIC SMALL LETTER TE + 0x00e3: 0x0443, # CYRILLIC SMALL LETTER U + 0x00e4: 0x0444, # CYRILLIC SMALL LETTER EF + 0x00e5: 0x0445, # CYRILLIC SMALL LETTER HA + 0x00e6: 0x0446, # CYRILLIC SMALL LETTER TSE + 0x00e7: 0x0447, # CYRILLIC SMALL LETTER CHE + 0x00e8: 0x0448, # CYRILLIC SMALL LETTER SHA + 0x00e9: 0x0449, # CYRILLIC SMALL LETTER SHCHA + 0x00ea: 0x044a, # CYRILLIC SMALL LETTER HARD SIGN + 0x00eb: 0x044b, # CYRILLIC SMALL LETTER YERU + 0x00ec: 0x044c, # CYRILLIC SMALL LETTER SOFT SIGN + 0x00ed: 0x044d, # CYRILLIC SMALL LETTER E + 0x00ee: 0x044e, # CYRILLIC SMALL LETTER YU + 0x00ef: 0x044f, # CYRILLIC SMALL LETTER YA + 0x00f0: 0x0401, # CYRILLIC CAPITAL LETTER IO + 0x00f1: 0x0451, # CYRILLIC SMALL LETTER IO + 0x00f2: 0x0490, # CYRILLIC CAPITAL LETTER GHE WITH UPTURN + 0x00f3: 0x0491, # CYRILLIC SMALL LETTER GHE WITH UPTURN + 0x00f4: 0x0404, # CYRILLIC CAPITAL LETTER UKRAINIAN IE + 0x00f5: 0x0454, # CYRILLIC SMALL LETTER UKRAINIAN IE + 0x00f6: 0x0406, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + 0x00f7: 0x0456, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + 0x00f8: 0x0407, # CYRILLIC CAPITAL LETTER YI + 0x00f9: 0x0457, # CYRILLIC SMALL LETTER YI + 0x00fa: 0x00b7, # MIDDLE DOT + 0x00fb: 0x221a, # SQUARE ROOT + 0x00fc: 0x2116, # NUMERO SIGN + 0x00fd: 0x00a4, # CURRENCY SIGN + 0x00fe: 0x25a0, # BLACK SQUARE + 0x00ff: 0x00a0, # NO-BREAK SPACE +}) + +### Decoding Table + +decoding_table = ( + '\x00' # 0x0000 -> NULL + '\x01' # 0x0001 -> START OF HEADING + '\x02' # 0x0002 -> START OF TEXT + '\x03' # 0x0003 -> END OF TEXT + '\x04' # 0x0004 -> END OF TRANSMISSION + '\x05' # 0x0005 -> ENQUIRY + '\x06' # 0x0006 -> ACKNOWLEDGE + '\x07' # 0x0007 -> BELL + '\x08' # 0x0008 -> BACKSPACE + '\t' # 0x0009 -> HORIZONTAL TABULATION + '\n' # 0x000a -> LINE FEED + '\x0b' # 0x000b -> VERTICAL TABULATION + '\x0c' # 0x000c -> FORM FEED + '\r' # 0x000d -> CARRIAGE RETURN + '\x0e' # 0x000e -> SHIFT OUT + '\x0f' # 0x000f -> SHIFT IN + '\x10' # 0x0010 -> DATA LINK ESCAPE + '\x11' # 0x0011 -> DEVICE CONTROL ONE + '\x12' # 0x0012 -> DEVICE CONTROL TWO + '\x13' # 0x0013 -> DEVICE CONTROL THREE + '\x14' # 0x0014 -> DEVICE CONTROL FOUR + '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x0016 -> SYNCHRONOUS IDLE + '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK + '\x18' # 0x0018 -> CANCEL + '\x19' # 0x0019 -> END OF MEDIUM + '\x1a' # 0x001a -> SUBSTITUTE + '\x1b' # 0x001b -> ESCAPE + '\x1c' # 0x001c -> FILE SEPARATOR + '\x1d' # 0x001d -> GROUP SEPARATOR + '\x1e' # 0x001e -> RECORD SEPARATOR + '\x1f' # 0x001f -> UNIT SEPARATOR + ' ' # 0x0020 -> SPACE + '!' # 0x0021 -> EXCLAMATION MARK + '"' # 0x0022 -> QUOTATION MARK + '#' # 0x0023 -> NUMBER SIGN + '$' # 0x0024 -> DOLLAR SIGN + '%' # 0x0025 -> PERCENT SIGN + '&' # 0x0026 -> AMPERSAND + "'" # 0x0027 -> APOSTROPHE + '(' # 0x0028 -> LEFT PARENTHESIS + ')' # 0x0029 -> RIGHT PARENTHESIS + '*' # 0x002a -> ASTERISK + '+' # 0x002b -> PLUS SIGN + ',' # 0x002c -> COMMA + '-' # 0x002d -> HYPHEN-MINUS + '.' # 0x002e -> FULL STOP + '/' # 0x002f -> SOLIDUS + '0' # 0x0030 -> DIGIT ZERO + '1' # 0x0031 -> DIGIT ONE + '2' # 0x0032 -> DIGIT TWO + '3' # 0x0033 -> DIGIT THREE + '4' # 0x0034 -> DIGIT FOUR + '5' # 0x0035 -> DIGIT FIVE + '6' # 0x0036 -> DIGIT SIX + '7' # 0x0037 -> DIGIT SEVEN + '8' # 0x0038 -> DIGIT EIGHT + '9' # 0x0039 -> DIGIT NINE + ':' # 0x003a -> COLON + ';' # 0x003b -> SEMICOLON + '<' # 0x003c -> LESS-THAN SIGN + '=' # 0x003d -> EQUALS SIGN + '>' # 0x003e -> GREATER-THAN SIGN + '?' # 0x003f -> QUESTION MARK + '@' # 0x0040 -> COMMERCIAL AT + 'A' # 0x0041 -> LATIN CAPITAL LETTER A + 'B' # 0x0042 -> LATIN CAPITAL LETTER B + 'C' # 0x0043 -> LATIN CAPITAL LETTER C + 'D' # 0x0044 -> LATIN CAPITAL LETTER D + 'E' # 0x0045 -> LATIN CAPITAL LETTER E + 'F' # 0x0046 -> LATIN CAPITAL LETTER F + 'G' # 0x0047 -> LATIN CAPITAL LETTER G + 'H' # 0x0048 -> LATIN CAPITAL LETTER H + 'I' # 0x0049 -> LATIN CAPITAL LETTER I + 'J' # 0x004a -> LATIN CAPITAL LETTER J + 'K' # 0x004b -> LATIN CAPITAL LETTER K + 'L' # 0x004c -> LATIN CAPITAL LETTER L + 'M' # 0x004d -> LATIN CAPITAL LETTER M + 'N' # 0x004e -> LATIN CAPITAL LETTER N + 'O' # 0x004f -> LATIN CAPITAL LETTER O + 'P' # 0x0050 -> LATIN CAPITAL LETTER P + 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q + 'R' # 0x0052 -> LATIN CAPITAL LETTER R + 'S' # 0x0053 -> LATIN CAPITAL LETTER S + 'T' # 0x0054 -> LATIN CAPITAL LETTER T + 'U' # 0x0055 -> LATIN CAPITAL LETTER U + 'V' # 0x0056 -> LATIN CAPITAL LETTER V + 'W' # 0x0057 -> LATIN CAPITAL LETTER W + 'X' # 0x0058 -> LATIN CAPITAL LETTER X + 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y + 'Z' # 0x005a -> LATIN CAPITAL LETTER Z + '[' # 0x005b -> LEFT SQUARE BRACKET + '\\' # 0x005c -> REVERSE SOLIDUS + ']' # 0x005d -> RIGHT SQUARE BRACKET + '^' # 0x005e -> CIRCUMFLEX ACCENT + '_' # 0x005f -> LOW LINE + '`' # 0x0060 -> GRAVE ACCENT + 'a' # 0x0061 -> LATIN SMALL LETTER A + 'b' # 0x0062 -> LATIN SMALL LETTER B + 'c' # 0x0063 -> LATIN SMALL LETTER C + 'd' # 0x0064 -> LATIN SMALL LETTER D + 'e' # 0x0065 -> LATIN SMALL LETTER E + 'f' # 0x0066 -> LATIN SMALL LETTER F + 'g' # 0x0067 -> LATIN SMALL LETTER G + 'h' # 0x0068 -> LATIN SMALL LETTER H + 'i' # 0x0069 -> LATIN SMALL LETTER I + 'j' # 0x006a -> LATIN SMALL LETTER J + 'k' # 0x006b -> LATIN SMALL LETTER K + 'l' # 0x006c -> LATIN SMALL LETTER L + 'm' # 0x006d -> LATIN SMALL LETTER M + 'n' # 0x006e -> LATIN SMALL LETTER N + 'o' # 0x006f -> LATIN SMALL LETTER O + 'p' # 0x0070 -> LATIN SMALL LETTER P + 'q' # 0x0071 -> LATIN SMALL LETTER Q + 'r' # 0x0072 -> LATIN SMALL LETTER R + 's' # 0x0073 -> LATIN SMALL LETTER S + 't' # 0x0074 -> LATIN SMALL LETTER T + 'u' # 0x0075 -> LATIN SMALL LETTER U + 'v' # 0x0076 -> LATIN SMALL LETTER V + 'w' # 0x0077 -> LATIN SMALL LETTER W + 'x' # 0x0078 -> LATIN SMALL LETTER X + 'y' # 0x0079 -> LATIN SMALL LETTER Y + 'z' # 0x007a -> LATIN SMALL LETTER Z + '{' # 0x007b -> LEFT CURLY BRACKET + '|' # 0x007c -> VERTICAL LINE + '}' # 0x007d -> RIGHT CURLY BRACKET + '~' # 0x007e -> TILDE + '\x7f' # 0x007f -> DELETE + '\u0410' # 0x0080 -> CYRILLIC CAPITAL LETTER A + '\u0411' # 0x0081 -> CYRILLIC CAPITAL LETTER BE + '\u0412' # 0x0082 -> CYRILLIC CAPITAL LETTER VE + '\u0413' # 0x0083 -> CYRILLIC CAPITAL LETTER GHE + '\u0414' # 0x0084 -> CYRILLIC CAPITAL LETTER DE + '\u0415' # 0x0085 -> CYRILLIC CAPITAL LETTER IE + '\u0416' # 0x0086 -> CYRILLIC CAPITAL LETTER ZHE + '\u0417' # 0x0087 -> CYRILLIC CAPITAL LETTER ZE + '\u0418' # 0x0088 -> CYRILLIC CAPITAL LETTER I + '\u0419' # 0x0089 -> CYRILLIC CAPITAL LETTER SHORT I + '\u041a' # 0x008a -> CYRILLIC CAPITAL LETTER KA + '\u041b' # 0x008b -> CYRILLIC CAPITAL LETTER EL + '\u041c' # 0x008c -> CYRILLIC CAPITAL LETTER EM + '\u041d' # 0x008d -> CYRILLIC CAPITAL LETTER EN + '\u041e' # 0x008e -> CYRILLIC CAPITAL LETTER O + '\u041f' # 0x008f -> CYRILLIC CAPITAL LETTER PE + '\u0420' # 0x0090 -> CYRILLIC CAPITAL LETTER ER + '\u0421' # 0x0091 -> CYRILLIC CAPITAL LETTER ES + '\u0422' # 0x0092 -> CYRILLIC CAPITAL LETTER TE + '\u0423' # 0x0093 -> CYRILLIC CAPITAL LETTER U + '\u0424' # 0x0094 -> CYRILLIC CAPITAL LETTER EF + '\u0425' # 0x0095 -> CYRILLIC CAPITAL LETTER HA + '\u0426' # 0x0096 -> CYRILLIC CAPITAL LETTER TSE + '\u0427' # 0x0097 -> CYRILLIC CAPITAL LETTER CHE + '\u0428' # 0x0098 -> CYRILLIC CAPITAL LETTER SHA + '\u0429' # 0x0099 -> CYRILLIC CAPITAL LETTER SHCHA + '\u042a' # 0x009a -> CYRILLIC CAPITAL LETTER HARD SIGN + '\u042b' # 0x009b -> CYRILLIC CAPITAL LETTER YERU + '\u042c' # 0x009c -> CYRILLIC CAPITAL LETTER SOFT SIGN + '\u042d' # 0x009d -> CYRILLIC CAPITAL LETTER E + '\u042e' # 0x009e -> CYRILLIC CAPITAL LETTER YU + '\u042f' # 0x009f -> CYRILLIC CAPITAL LETTER YA + '\u0430' # 0x00a0 -> CYRILLIC SMALL LETTER A + '\u0431' # 0x00a1 -> CYRILLIC SMALL LETTER BE + '\u0432' # 0x00a2 -> CYRILLIC SMALL LETTER VE + '\u0433' # 0x00a3 -> CYRILLIC SMALL LETTER GHE + '\u0434' # 0x00a4 -> CYRILLIC SMALL LETTER DE + '\u0435' # 0x00a5 -> CYRILLIC SMALL LETTER IE + '\u0436' # 0x00a6 -> CYRILLIC SMALL LETTER ZHE + '\u0437' # 0x00a7 -> CYRILLIC SMALL LETTER ZE + '\u0438' # 0x00a8 -> CYRILLIC SMALL LETTER I + '\u0439' # 0x00a9 -> CYRILLIC SMALL LETTER SHORT I + '\u043a' # 0x00aa -> CYRILLIC SMALL LETTER KA + '\u043b' # 0x00ab -> CYRILLIC SMALL LETTER EL + '\u043c' # 0x00ac -> CYRILLIC SMALL LETTER EM + '\u043d' # 0x00ad -> CYRILLIC SMALL LETTER EN + '\u043e' # 0x00ae -> CYRILLIC SMALL LETTER O + '\u043f' # 0x00af -> CYRILLIC SMALL LETTER PE + '\u2591' # 0x00b0 -> LIGHT SHADE + '\u2592' # 0x00b1 -> MEDIUM SHADE + '\u2593' # 0x00b2 -> DARK SHADE + '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL + '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT + '\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + '\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + '\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + '\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL + '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT + '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT + '\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + '\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT + '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT + '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL + '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT + '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL + '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + '\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + '\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT + '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL + '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + '\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + '\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + '\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + '\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + '\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + '\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + '\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + '\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + '\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + '\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT + '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT + '\u2588' # 0x00db -> FULL BLOCK + '\u2584' # 0x00dc -> LOWER HALF BLOCK + '\u258c' # 0x00dd -> LEFT HALF BLOCK + '\u2590' # 0x00de -> RIGHT HALF BLOCK + '\u2580' # 0x00df -> UPPER HALF BLOCK + '\u0440' # 0x00e0 -> CYRILLIC SMALL LETTER ER + '\u0441' # 0x00e1 -> CYRILLIC SMALL LETTER ES + '\u0442' # 0x00e2 -> CYRILLIC SMALL LETTER TE + '\u0443' # 0x00e3 -> CYRILLIC SMALL LETTER U + '\u0444' # 0x00e4 -> CYRILLIC SMALL LETTER EF + '\u0445' # 0x00e5 -> CYRILLIC SMALL LETTER HA + '\u0446' # 0x00e6 -> CYRILLIC SMALL LETTER TSE + '\u0447' # 0x00e7 -> CYRILLIC SMALL LETTER CHE + '\u0448' # 0x00e8 -> CYRILLIC SMALL LETTER SHA + '\u0449' # 0x00e9 -> CYRILLIC SMALL LETTER SHCHA + '\u044a' # 0x00ea -> CYRILLIC SMALL LETTER HARD SIGN + '\u044b' # 0x00eb -> CYRILLIC SMALL LETTER YERU + '\u044c' # 0x00ec -> CYRILLIC SMALL LETTER SOFT SIGN + '\u044d' # 0x00ed -> CYRILLIC SMALL LETTER E + '\u044e' # 0x00ee -> CYRILLIC SMALL LETTER YU + '\u044f' # 0x00ef -> CYRILLIC SMALL LETTER YA + '\u0401' # 0x00f0 -> CYRILLIC CAPITAL LETTER IO + '\u0451' # 0x00f1 -> CYRILLIC SMALL LETTER IO + '\u0490' # 0x00f2 -> CYRILLIC CAPITAL LETTER GHE WITH UPTURN + '\u0491' # 0x00f3 -> CYRILLIC SMALL LETTER GHE WITH UPTURN + '\u0404' # 0x00f4 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE + '\u0454' # 0x00f5 -> CYRILLIC SMALL LETTER UKRAINIAN IE + '\u0406' # 0x00f6 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + '\u0456' # 0x00f7 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + '\u0407' # 0x00f8 -> CYRILLIC CAPITAL LETTER YI + '\u0457' # 0x00f9 -> CYRILLIC SMALL LETTER YI + '\xb7' # 0x00fa -> MIDDLE DOT + '\u221a' # 0x00fb -> SQUARE ROOT + '\u2116' # 0x00fc -> NUMERO SIGN + '\xa4' # 0x00fd -> CURRENCY SIGN + '\u25a0' # 0x00fe -> BLACK SQUARE + '\xa0' # 0x00ff -> NO-BREAK SPACE +) + +### Encoding Map + +encoding_map = { + 0x0000: 0x0000, # NULL + 0x0001: 0x0001, # START OF HEADING + 0x0002: 0x0002, # START OF TEXT + 0x0003: 0x0003, # END OF TEXT + 0x0004: 0x0004, # END OF TRANSMISSION + 0x0005: 0x0005, # ENQUIRY + 0x0006: 0x0006, # ACKNOWLEDGE + 0x0007: 0x0007, # BELL + 0x0008: 0x0008, # BACKSPACE + 0x0009: 0x0009, # HORIZONTAL TABULATION + 0x000a: 0x000a, # LINE FEED + 0x000b: 0x000b, # VERTICAL TABULATION + 0x000c: 0x000c, # FORM FEED + 0x000d: 0x000d, # CARRIAGE RETURN + 0x000e: 0x000e, # SHIFT OUT + 0x000f: 0x000f, # SHIFT IN + 0x0010: 0x0010, # DATA LINK ESCAPE + 0x0011: 0x0011, # DEVICE CONTROL ONE + 0x0012: 0x0012, # DEVICE CONTROL TWO + 0x0013: 0x0013, # DEVICE CONTROL THREE + 0x0014: 0x0014, # DEVICE CONTROL FOUR + 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE + 0x0016: 0x0016, # SYNCHRONOUS IDLE + 0x0017: 0x0017, # END OF TRANSMISSION BLOCK + 0x0018: 0x0018, # CANCEL + 0x0019: 0x0019, # END OF MEDIUM + 0x001a: 0x001a, # SUBSTITUTE + 0x001b: 0x001b, # ESCAPE + 0x001c: 0x001c, # FILE SEPARATOR + 0x001d: 0x001d, # GROUP SEPARATOR + 0x001e: 0x001e, # RECORD SEPARATOR + 0x001f: 0x001f, # UNIT SEPARATOR + 0x0020: 0x0020, # SPACE + 0x0021: 0x0021, # EXCLAMATION MARK + 0x0022: 0x0022, # QUOTATION MARK + 0x0023: 0x0023, # NUMBER SIGN + 0x0024: 0x0024, # DOLLAR SIGN + 0x0025: 0x0025, # PERCENT SIGN + 0x0026: 0x0026, # AMPERSAND + 0x0027: 0x0027, # APOSTROPHE + 0x0028: 0x0028, # LEFT PARENTHESIS + 0x0029: 0x0029, # RIGHT PARENTHESIS + 0x002a: 0x002a, # ASTERISK + 0x002b: 0x002b, # PLUS SIGN + 0x002c: 0x002c, # COMMA + 0x002d: 0x002d, # HYPHEN-MINUS + 0x002e: 0x002e, # FULL STOP + 0x002f: 0x002f, # SOLIDUS + 0x0030: 0x0030, # DIGIT ZERO + 0x0031: 0x0031, # DIGIT ONE + 0x0032: 0x0032, # DIGIT TWO + 0x0033: 0x0033, # DIGIT THREE + 0x0034: 0x0034, # DIGIT FOUR + 0x0035: 0x0035, # DIGIT FIVE + 0x0036: 0x0036, # DIGIT SIX + 0x0037: 0x0037, # DIGIT SEVEN + 0x0038: 0x0038, # DIGIT EIGHT + 0x0039: 0x0039, # DIGIT NINE + 0x003a: 0x003a, # COLON + 0x003b: 0x003b, # SEMICOLON + 0x003c: 0x003c, # LESS-THAN SIGN + 0x003d: 0x003d, # EQUALS SIGN + 0x003e: 0x003e, # GREATER-THAN SIGN + 0x003f: 0x003f, # QUESTION MARK + 0x0040: 0x0040, # COMMERCIAL AT + 0x0041: 0x0041, # LATIN CAPITAL LETTER A + 0x0042: 0x0042, # LATIN CAPITAL LETTER B + 0x0043: 0x0043, # LATIN CAPITAL LETTER C + 0x0044: 0x0044, # LATIN CAPITAL LETTER D + 0x0045: 0x0045, # LATIN CAPITAL LETTER E + 0x0046: 0x0046, # LATIN CAPITAL LETTER F + 0x0047: 0x0047, # LATIN CAPITAL LETTER G + 0x0048: 0x0048, # LATIN CAPITAL LETTER H + 0x0049: 0x0049, # LATIN CAPITAL LETTER I + 0x004a: 0x004a, # LATIN CAPITAL LETTER J + 0x004b: 0x004b, # LATIN CAPITAL LETTER K + 0x004c: 0x004c, # LATIN CAPITAL LETTER L + 0x004d: 0x004d, # LATIN CAPITAL LETTER M + 0x004e: 0x004e, # LATIN CAPITAL LETTER N + 0x004f: 0x004f, # LATIN CAPITAL LETTER O + 0x0050: 0x0050, # LATIN CAPITAL LETTER P + 0x0051: 0x0051, # LATIN CAPITAL LETTER Q + 0x0052: 0x0052, # LATIN CAPITAL LETTER R + 0x0053: 0x0053, # LATIN CAPITAL LETTER S + 0x0054: 0x0054, # LATIN CAPITAL LETTER T + 0x0055: 0x0055, # LATIN CAPITAL LETTER U + 0x0056: 0x0056, # LATIN CAPITAL LETTER V + 0x0057: 0x0057, # LATIN CAPITAL LETTER W + 0x0058: 0x0058, # LATIN CAPITAL LETTER X + 0x0059: 0x0059, # LATIN CAPITAL LETTER Y + 0x005a: 0x005a, # LATIN CAPITAL LETTER Z + 0x005b: 0x005b, # LEFT SQUARE BRACKET + 0x005c: 0x005c, # REVERSE SOLIDUS + 0x005d: 0x005d, # RIGHT SQUARE BRACKET + 0x005e: 0x005e, # CIRCUMFLEX ACCENT + 0x005f: 0x005f, # LOW LINE + 0x0060: 0x0060, # GRAVE ACCENT + 0x0061: 0x0061, # LATIN SMALL LETTER A + 0x0062: 0x0062, # LATIN SMALL LETTER B + 0x0063: 0x0063, # LATIN SMALL LETTER C + 0x0064: 0x0064, # LATIN SMALL LETTER D + 0x0065: 0x0065, # LATIN SMALL LETTER E + 0x0066: 0x0066, # LATIN SMALL LETTER F + 0x0067: 0x0067, # LATIN SMALL LETTER G + 0x0068: 0x0068, # LATIN SMALL LETTER H + 0x0069: 0x0069, # LATIN SMALL LETTER I + 0x006a: 0x006a, # LATIN SMALL LETTER J + 0x006b: 0x006b, # LATIN SMALL LETTER K + 0x006c: 0x006c, # LATIN SMALL LETTER L + 0x006d: 0x006d, # LATIN SMALL LETTER M + 0x006e: 0x006e, # LATIN SMALL LETTER N + 0x006f: 0x006f, # LATIN SMALL LETTER O + 0x0070: 0x0070, # LATIN SMALL LETTER P + 0x0071: 0x0071, # LATIN SMALL LETTER Q + 0x0072: 0x0072, # LATIN SMALL LETTER R + 0x0073: 0x0073, # LATIN SMALL LETTER S + 0x0074: 0x0074, # LATIN SMALL LETTER T + 0x0075: 0x0075, # LATIN SMALL LETTER U + 0x0076: 0x0076, # LATIN SMALL LETTER V + 0x0077: 0x0077, # LATIN SMALL LETTER W + 0x0078: 0x0078, # LATIN SMALL LETTER X + 0x0079: 0x0079, # LATIN SMALL LETTER Y + 0x007a: 0x007a, # LATIN SMALL LETTER Z + 0x007b: 0x007b, # LEFT CURLY BRACKET + 0x007c: 0x007c, # VERTICAL LINE + 0x007d: 0x007d, # RIGHT CURLY BRACKET + 0x007e: 0x007e, # TILDE + 0x007f: 0x007f, # DELETE + 0x00a0: 0x00ff, # NO-BREAK SPACE + 0x00a4: 0x00fd, # CURRENCY SIGN + 0x00b7: 0x00fa, # MIDDLE DOT + 0x0401: 0x00f0, # CYRILLIC CAPITAL LETTER IO + 0x0404: 0x00f4, # CYRILLIC CAPITAL LETTER UKRAINIAN IE + 0x0406: 0x00f6, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + 0x0407: 0x00f8, # CYRILLIC CAPITAL LETTER YI + 0x0410: 0x0080, # CYRILLIC CAPITAL LETTER A + 0x0411: 0x0081, # CYRILLIC CAPITAL LETTER BE + 0x0412: 0x0082, # CYRILLIC CAPITAL LETTER VE + 0x0413: 0x0083, # CYRILLIC CAPITAL LETTER GHE + 0x0414: 0x0084, # CYRILLIC CAPITAL LETTER DE + 0x0415: 0x0085, # CYRILLIC CAPITAL LETTER IE + 0x0416: 0x0086, # CYRILLIC CAPITAL LETTER ZHE + 0x0417: 0x0087, # CYRILLIC CAPITAL LETTER ZE + 0x0418: 0x0088, # CYRILLIC CAPITAL LETTER I + 0x0419: 0x0089, # CYRILLIC CAPITAL LETTER SHORT I + 0x041a: 0x008a, # CYRILLIC CAPITAL LETTER KA + 0x041b: 0x008b, # CYRILLIC CAPITAL LETTER EL + 0x041c: 0x008c, # CYRILLIC CAPITAL LETTER EM + 0x041d: 0x008d, # CYRILLIC CAPITAL LETTER EN + 0x041e: 0x008e, # CYRILLIC CAPITAL LETTER O + 0x041f: 0x008f, # CYRILLIC CAPITAL LETTER PE + 0x0420: 0x0090, # CYRILLIC CAPITAL LETTER ER + 0x0421: 0x0091, # CYRILLIC CAPITAL LETTER ES + 0x0422: 0x0092, # CYRILLIC CAPITAL LETTER TE + 0x0423: 0x0093, # CYRILLIC CAPITAL LETTER U + 0x0424: 0x0094, # CYRILLIC CAPITAL LETTER EF + 0x0425: 0x0095, # CYRILLIC CAPITAL LETTER HA + 0x0426: 0x0096, # CYRILLIC CAPITAL LETTER TSE + 0x0427: 0x0097, # CYRILLIC CAPITAL LETTER CHE + 0x0428: 0x0098, # CYRILLIC CAPITAL LETTER SHA + 0x0429: 0x0099, # CYRILLIC CAPITAL LETTER SHCHA + 0x042a: 0x009a, # CYRILLIC CAPITAL LETTER HARD SIGN + 0x042b: 0x009b, # CYRILLIC CAPITAL LETTER YERU + 0x042c: 0x009c, # CYRILLIC CAPITAL LETTER SOFT SIGN + 0x042d: 0x009d, # CYRILLIC CAPITAL LETTER E + 0x042e: 0x009e, # CYRILLIC CAPITAL LETTER YU + 0x042f: 0x009f, # CYRILLIC CAPITAL LETTER YA + 0x0430: 0x00a0, # CYRILLIC SMALL LETTER A + 0x0431: 0x00a1, # CYRILLIC SMALL LETTER BE + 0x0432: 0x00a2, # CYRILLIC SMALL LETTER VE + 0x0433: 0x00a3, # CYRILLIC SMALL LETTER GHE + 0x0434: 0x00a4, # CYRILLIC SMALL LETTER DE + 0x0435: 0x00a5, # CYRILLIC SMALL LETTER IE + 0x0436: 0x00a6, # CYRILLIC SMALL LETTER ZHE + 0x0437: 0x00a7, # CYRILLIC SMALL LETTER ZE + 0x0438: 0x00a8, # CYRILLIC SMALL LETTER I + 0x0439: 0x00a9, # CYRILLIC SMALL LETTER SHORT I + 0x043a: 0x00aa, # CYRILLIC SMALL LETTER KA + 0x043b: 0x00ab, # CYRILLIC SMALL LETTER EL + 0x043c: 0x00ac, # CYRILLIC SMALL LETTER EM + 0x043d: 0x00ad, # CYRILLIC SMALL LETTER EN + 0x043e: 0x00ae, # CYRILLIC SMALL LETTER O + 0x043f: 0x00af, # CYRILLIC SMALL LETTER PE + 0x0440: 0x00e0, # CYRILLIC SMALL LETTER ER + 0x0441: 0x00e1, # CYRILLIC SMALL LETTER ES + 0x0442: 0x00e2, # CYRILLIC SMALL LETTER TE + 0x0443: 0x00e3, # CYRILLIC SMALL LETTER U + 0x0444: 0x00e4, # CYRILLIC SMALL LETTER EF + 0x0445: 0x00e5, # CYRILLIC SMALL LETTER HA + 0x0446: 0x00e6, # CYRILLIC SMALL LETTER TSE + 0x0447: 0x00e7, # CYRILLIC SMALL LETTER CHE + 0x0448: 0x00e8, # CYRILLIC SMALL LETTER SHA + 0x0449: 0x00e9, # CYRILLIC SMALL LETTER SHCHA + 0x044a: 0x00ea, # CYRILLIC SMALL LETTER HARD SIGN + 0x044b: 0x00eb, # CYRILLIC SMALL LETTER YERU + 0x044c: 0x00ec, # CYRILLIC SMALL LETTER SOFT SIGN + 0x044d: 0x00ed, # CYRILLIC SMALL LETTER E + 0x044e: 0x00ee, # CYRILLIC SMALL LETTER YU + 0x044f: 0x00ef, # CYRILLIC SMALL LETTER YA + 0x0451: 0x00f1, # CYRILLIC SMALL LETTER IO + 0x0454: 0x00f5, # CYRILLIC SMALL LETTER UKRAINIAN IE + 0x0456: 0x00f7, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + 0x0457: 0x00f9, # CYRILLIC SMALL LETTER YI + 0x0490: 0x00f2, # CYRILLIC CAPITAL LETTER GHE WITH UPTURN + 0x0491: 0x00f3, # CYRILLIC SMALL LETTER GHE WITH UPTURN + 0x2116: 0x00fc, # NUMERO SIGN + 0x221a: 0x00fb, # SQUARE ROOT + 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL + 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL + 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT + 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL + 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x2580: 0x00df, # UPPER HALF BLOCK + 0x2584: 0x00dc, # LOWER HALF BLOCK + 0x2588: 0x00db, # FULL BLOCK + 0x258c: 0x00dd, # LEFT HALF BLOCK + 0x2590: 0x00de, # RIGHT HALF BLOCK + 0x2591: 0x00b0, # LIGHT SHADE + 0x2592: 0x00b1, # MEDIUM SHADE + 0x2593: 0x00b2, # DARK SHADE + 0x25a0: 0x00fe, # BLACK SQUARE +} diff --git a/contrib/tools/python3/src/Lib/encodings/cp1140.py b/contrib/tools/python3/src/Lib/encodings/cp1140.py new file mode 100644 index 0000000000..0a919d837e --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp1140.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec cp1140 generated from 'python-mappings/CP1140.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp1140', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x9c' # 0x04 -> CONTROL + '\t' # 0x05 -> HORIZONTAL TABULATION + '\x86' # 0x06 -> CONTROL + '\x7f' # 0x07 -> DELETE + '\x97' # 0x08 -> CONTROL + '\x8d' # 0x09 -> CONTROL + '\x8e' # 0x0A -> CONTROL + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x9d' # 0x14 -> CONTROL + '\x85' # 0x15 -> CONTROL + '\x08' # 0x16 -> BACKSPACE + '\x87' # 0x17 -> CONTROL + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x92' # 0x1A -> CONTROL + '\x8f' # 0x1B -> CONTROL + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + '\x80' # 0x20 -> CONTROL + '\x81' # 0x21 -> CONTROL + '\x82' # 0x22 -> CONTROL + '\x83' # 0x23 -> CONTROL + '\x84' # 0x24 -> CONTROL + '\n' # 0x25 -> LINE FEED + '\x17' # 0x26 -> END OF TRANSMISSION BLOCK + '\x1b' # 0x27 -> ESCAPE + '\x88' # 0x28 -> CONTROL + '\x89' # 0x29 -> CONTROL + '\x8a' # 0x2A -> CONTROL + '\x8b' # 0x2B -> CONTROL + '\x8c' # 0x2C -> CONTROL + '\x05' # 0x2D -> ENQUIRY + '\x06' # 0x2E -> ACKNOWLEDGE + '\x07' # 0x2F -> BELL + '\x90' # 0x30 -> CONTROL + '\x91' # 0x31 -> CONTROL + '\x16' # 0x32 -> SYNCHRONOUS IDLE + '\x93' # 0x33 -> CONTROL + '\x94' # 0x34 -> CONTROL + '\x95' # 0x35 -> CONTROL + '\x96' # 0x36 -> CONTROL + '\x04' # 0x37 -> END OF TRANSMISSION + '\x98' # 0x38 -> CONTROL + '\x99' # 0x39 -> CONTROL + '\x9a' # 0x3A -> CONTROL + '\x9b' # 0x3B -> CONTROL + '\x14' # 0x3C -> DEVICE CONTROL FOUR + '\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE + '\x9e' # 0x3E -> CONTROL + '\x1a' # 0x3F -> SUBSTITUTE + ' ' # 0x40 -> SPACE + '\xa0' # 0x41 -> NO-BREAK SPACE + '\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe4' # 0x43 -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE + '\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE + '\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE + '\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe7' # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA + '\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE + '\xa2' # 0x4A -> CENT SIGN + '.' # 0x4B -> FULL STOP + '<' # 0x4C -> LESS-THAN SIGN + '(' # 0x4D -> LEFT PARENTHESIS + '+' # 0x4E -> PLUS SIGN + '|' # 0x4F -> VERTICAL LINE + '&' # 0x50 -> AMPERSAND + '\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE + '\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS + '\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE + '\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE + '\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS + '\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE + '\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN) + '!' # 0x5A -> EXCLAMATION MARK + '$' # 0x5B -> DOLLAR SIGN + '*' # 0x5C -> ASTERISK + ')' # 0x5D -> RIGHT PARENTHESIS + ';' # 0x5E -> SEMICOLON + '\xac' # 0x5F -> NOT SIGN + '-' # 0x60 -> HYPHEN-MINUS + '/' # 0x61 -> SOLIDUS + '\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xc4' # 0x63 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE + '\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE + '\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc7' # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE + '\xa6' # 0x6A -> BROKEN BAR + ',' # 0x6B -> COMMA + '%' # 0x6C -> PERCENT SIGN + '_' # 0x6D -> LOW LINE + '>' # 0x6E -> GREATER-THAN SIGN + '?' # 0x6F -> QUESTION MARK + '\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE + '\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE + '`' # 0x79 -> GRAVE ACCENT + ':' # 0x7A -> COLON + '#' # 0x7B -> NUMBER SIGN + '@' # 0x7C -> COMMERCIAL AT + "'" # 0x7D -> APOSTROPHE + '=' # 0x7E -> EQUALS SIGN + '"' # 0x7F -> QUOTATION MARK + '\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE + 'a' # 0x81 -> LATIN SMALL LETTER A + 'b' # 0x82 -> LATIN SMALL LETTER B + 'c' # 0x83 -> LATIN SMALL LETTER C + 'd' # 0x84 -> LATIN SMALL LETTER D + 'e' # 0x85 -> LATIN SMALL LETTER E + 'f' # 0x86 -> LATIN SMALL LETTER F + 'g' # 0x87 -> LATIN SMALL LETTER G + 'h' # 0x88 -> LATIN SMALL LETTER H + 'i' # 0x89 -> LATIN SMALL LETTER I + '\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xf0' # 0x8C -> LATIN SMALL LETTER ETH (ICELANDIC) + '\xfd' # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE + '\xfe' # 0x8E -> LATIN SMALL LETTER THORN (ICELANDIC) + '\xb1' # 0x8F -> PLUS-MINUS SIGN + '\xb0' # 0x90 -> DEGREE SIGN + 'j' # 0x91 -> LATIN SMALL LETTER J + 'k' # 0x92 -> LATIN SMALL LETTER K + 'l' # 0x93 -> LATIN SMALL LETTER L + 'm' # 0x94 -> LATIN SMALL LETTER M + 'n' # 0x95 -> LATIN SMALL LETTER N + 'o' # 0x96 -> LATIN SMALL LETTER O + 'p' # 0x97 -> LATIN SMALL LETTER P + 'q' # 0x98 -> LATIN SMALL LETTER Q + 'r' # 0x99 -> LATIN SMALL LETTER R + '\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR + '\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR + '\xe6' # 0x9C -> LATIN SMALL LIGATURE AE + '\xb8' # 0x9D -> CEDILLA + '\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE + '\u20ac' # 0x9F -> EURO SIGN + '\xb5' # 0xA0 -> MICRO SIGN + '~' # 0xA1 -> TILDE + 's' # 0xA2 -> LATIN SMALL LETTER S + 't' # 0xA3 -> LATIN SMALL LETTER T + 'u' # 0xA4 -> LATIN SMALL LETTER U + 'v' # 0xA5 -> LATIN SMALL LETTER V + 'w' # 0xA6 -> LATIN SMALL LETTER W + 'x' # 0xA7 -> LATIN SMALL LETTER X + 'y' # 0xA8 -> LATIN SMALL LETTER Y + 'z' # 0xA9 -> LATIN SMALL LETTER Z + '\xa1' # 0xAA -> INVERTED EXCLAMATION MARK + '\xbf' # 0xAB -> INVERTED QUESTION MARK + '\xd0' # 0xAC -> LATIN CAPITAL LETTER ETH (ICELANDIC) + '\xdd' # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE + '\xde' # 0xAE -> LATIN CAPITAL LETTER THORN (ICELANDIC) + '\xae' # 0xAF -> REGISTERED SIGN + '^' # 0xB0 -> CIRCUMFLEX ACCENT + '\xa3' # 0xB1 -> POUND SIGN + '\xa5' # 0xB2 -> YEN SIGN + '\xb7' # 0xB3 -> MIDDLE DOT + '\xa9' # 0xB4 -> COPYRIGHT SIGN + '\xa7' # 0xB5 -> SECTION SIGN + '\xb6' # 0xB6 -> PILCROW SIGN + '\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER + '\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF + '\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS + '[' # 0xBA -> LEFT SQUARE BRACKET + ']' # 0xBB -> RIGHT SQUARE BRACKET + '\xaf' # 0xBC -> MACRON + '\xa8' # 0xBD -> DIAERESIS + '\xb4' # 0xBE -> ACUTE ACCENT + '\xd7' # 0xBF -> MULTIPLICATION SIGN + '{' # 0xC0 -> LEFT CURLY BRACKET + 'A' # 0xC1 -> LATIN CAPITAL LETTER A + 'B' # 0xC2 -> LATIN CAPITAL LETTER B + 'C' # 0xC3 -> LATIN CAPITAL LETTER C + 'D' # 0xC4 -> LATIN CAPITAL LETTER D + 'E' # 0xC5 -> LATIN CAPITAL LETTER E + 'F' # 0xC6 -> LATIN CAPITAL LETTER F + 'G' # 0xC7 -> LATIN CAPITAL LETTER G + 'H' # 0xC8 -> LATIN CAPITAL LETTER H + 'I' # 0xC9 -> LATIN CAPITAL LETTER I + '\xad' # 0xCA -> SOFT HYPHEN + '\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf6' # 0xCC -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE + '\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE + '\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE + '}' # 0xD0 -> RIGHT CURLY BRACKET + 'J' # 0xD1 -> LATIN CAPITAL LETTER J + 'K' # 0xD2 -> LATIN CAPITAL LETTER K + 'L' # 0xD3 -> LATIN CAPITAL LETTER L + 'M' # 0xD4 -> LATIN CAPITAL LETTER M + 'N' # 0xD5 -> LATIN CAPITAL LETTER N + 'O' # 0xD6 -> LATIN CAPITAL LETTER O + 'P' # 0xD7 -> LATIN CAPITAL LETTER P + 'Q' # 0xD8 -> LATIN CAPITAL LETTER Q + 'R' # 0xD9 -> LATIN CAPITAL LETTER R + '\xb9' # 0xDA -> SUPERSCRIPT ONE + '\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0xDC -> LATIN SMALL LETTER U WITH DIAERESIS + '\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE + '\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE + '\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS + '\\' # 0xE0 -> REVERSE SOLIDUS + '\xf7' # 0xE1 -> DIVISION SIGN + 'S' # 0xE2 -> LATIN CAPITAL LETTER S + 'T' # 0xE3 -> LATIN CAPITAL LETTER T + 'U' # 0xE4 -> LATIN CAPITAL LETTER U + 'V' # 0xE5 -> LATIN CAPITAL LETTER V + 'W' # 0xE6 -> LATIN CAPITAL LETTER W + 'X' # 0xE7 -> LATIN CAPITAL LETTER X + 'Y' # 0xE8 -> LATIN CAPITAL LETTER Y + 'Z' # 0xE9 -> LATIN CAPITAL LETTER Z + '\xb2' # 0xEA -> SUPERSCRIPT TWO + '\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\xd6' # 0xEC -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE + '\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE + '0' # 0xF0 -> DIGIT ZERO + '1' # 0xF1 -> DIGIT ONE + '2' # 0xF2 -> DIGIT TWO + '3' # 0xF3 -> DIGIT THREE + '4' # 0xF4 -> DIGIT FOUR + '5' # 0xF5 -> DIGIT FIVE + '6' # 0xF6 -> DIGIT SIX + '7' # 0xF7 -> DIGIT SEVEN + '8' # 0xF8 -> DIGIT EIGHT + '9' # 0xF9 -> DIGIT NINE + '\xb3' # 0xFA -> SUPERSCRIPT THREE + '\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xdc' # 0xFC -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE + '\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE + '\x9f' # 0xFF -> CONTROL +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/cp1250.py b/contrib/tools/python3/src/Lib/encodings/cp1250.py new file mode 100644 index 0000000000..c2c83aaf3e --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp1250.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec cp1250 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1250.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp1250', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\u20ac' # 0x80 -> EURO SIGN + '\ufffe' # 0x81 -> UNDEFINED + '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK + '\ufffe' # 0x83 -> UNDEFINED + '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK + '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS + '\u2020' # 0x86 -> DAGGER + '\u2021' # 0x87 -> DOUBLE DAGGER + '\ufffe' # 0x88 -> UNDEFINED + '\u2030' # 0x89 -> PER MILLE SIGN + '\u0160' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON + '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + '\u015a' # 0x8C -> LATIN CAPITAL LETTER S WITH ACUTE + '\u0164' # 0x8D -> LATIN CAPITAL LETTER T WITH CARON + '\u017d' # 0x8E -> LATIN CAPITAL LETTER Z WITH CARON + '\u0179' # 0x8F -> LATIN CAPITAL LETTER Z WITH ACUTE + '\ufffe' # 0x90 -> UNDEFINED + '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK + '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK + '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK + '\u2022' # 0x95 -> BULLET + '\u2013' # 0x96 -> EN DASH + '\u2014' # 0x97 -> EM DASH + '\ufffe' # 0x98 -> UNDEFINED + '\u2122' # 0x99 -> TRADE MARK SIGN + '\u0161' # 0x9A -> LATIN SMALL LETTER S WITH CARON + '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + '\u015b' # 0x9C -> LATIN SMALL LETTER S WITH ACUTE + '\u0165' # 0x9D -> LATIN SMALL LETTER T WITH CARON + '\u017e' # 0x9E -> LATIN SMALL LETTER Z WITH CARON + '\u017a' # 0x9F -> LATIN SMALL LETTER Z WITH ACUTE + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\u02c7' # 0xA1 -> CARON + '\u02d8' # 0xA2 -> BREVE + '\u0141' # 0xA3 -> LATIN CAPITAL LETTER L WITH STROKE + '\xa4' # 0xA4 -> CURRENCY SIGN + '\u0104' # 0xA5 -> LATIN CAPITAL LETTER A WITH OGONEK + '\xa6' # 0xA6 -> BROKEN BAR + '\xa7' # 0xA7 -> SECTION SIGN + '\xa8' # 0xA8 -> DIAERESIS + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\u015e' # 0xAA -> LATIN CAPITAL LETTER S WITH CEDILLA + '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xac' # 0xAC -> NOT SIGN + '\xad' # 0xAD -> SOFT HYPHEN + '\xae' # 0xAE -> REGISTERED SIGN + '\u017b' # 0xAF -> LATIN CAPITAL LETTER Z WITH DOT ABOVE + '\xb0' # 0xB0 -> DEGREE SIGN + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\u02db' # 0xB2 -> OGONEK + '\u0142' # 0xB3 -> LATIN SMALL LETTER L WITH STROKE + '\xb4' # 0xB4 -> ACUTE ACCENT + '\xb5' # 0xB5 -> MICRO SIGN + '\xb6' # 0xB6 -> PILCROW SIGN + '\xb7' # 0xB7 -> MIDDLE DOT + '\xb8' # 0xB8 -> CEDILLA + '\u0105' # 0xB9 -> LATIN SMALL LETTER A WITH OGONEK + '\u015f' # 0xBA -> LATIN SMALL LETTER S WITH CEDILLA + '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u013d' # 0xBC -> LATIN CAPITAL LETTER L WITH CARON + '\u02dd' # 0xBD -> DOUBLE ACUTE ACCENT + '\u013e' # 0xBE -> LATIN SMALL LETTER L WITH CARON + '\u017c' # 0xBF -> LATIN SMALL LETTER Z WITH DOT ABOVE + '\u0154' # 0xC0 -> LATIN CAPITAL LETTER R WITH ACUTE + '\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\u0102' # 0xC3 -> LATIN CAPITAL LETTER A WITH BREVE + '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\u0139' # 0xC5 -> LATIN CAPITAL LETTER L WITH ACUTE + '\u0106' # 0xC6 -> LATIN CAPITAL LETTER C WITH ACUTE + '\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON + '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + '\u0118' # 0xCA -> LATIN CAPITAL LETTER E WITH OGONEK + '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\u011a' # 0xCC -> LATIN CAPITAL LETTER E WITH CARON + '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\u010e' # 0xCF -> LATIN CAPITAL LETTER D WITH CARON + '\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE + '\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE + '\u0147' # 0xD2 -> LATIN CAPITAL LETTER N WITH CARON + '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\u0150' # 0xD5 -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE + '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xd7' # 0xD7 -> MULTIPLICATION SIGN + '\u0158' # 0xD8 -> LATIN CAPITAL LETTER R WITH CARON + '\u016e' # 0xD9 -> LATIN CAPITAL LETTER U WITH RING ABOVE + '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + '\u0170' # 0xDB -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE + '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE + '\u0162' # 0xDE -> LATIN CAPITAL LETTER T WITH CEDILLA + '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + '\u0155' # 0xE0 -> LATIN SMALL LETTER R WITH ACUTE + '\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\u0103' # 0xE3 -> LATIN SMALL LETTER A WITH BREVE + '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + '\u013a' # 0xE5 -> LATIN SMALL LETTER L WITH ACUTE + '\u0107' # 0xE6 -> LATIN SMALL LETTER C WITH ACUTE + '\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + '\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON + '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + '\u0119' # 0xEA -> LATIN SMALL LETTER E WITH OGONEK + '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + '\u011b' # 0xEC -> LATIN SMALL LETTER E WITH CARON + '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\u010f' # 0xEF -> LATIN SMALL LETTER D WITH CARON + '\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE + '\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE + '\u0148' # 0xF2 -> LATIN SMALL LETTER N WITH CARON + '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\u0151' # 0xF5 -> LATIN SMALL LETTER O WITH DOUBLE ACUTE + '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf7' # 0xF7 -> DIVISION SIGN + '\u0159' # 0xF8 -> LATIN SMALL LETTER R WITH CARON + '\u016f' # 0xF9 -> LATIN SMALL LETTER U WITH RING ABOVE + '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + '\u0171' # 0xFB -> LATIN SMALL LETTER U WITH DOUBLE ACUTE + '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + '\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE + '\u0163' # 0xFE -> LATIN SMALL LETTER T WITH CEDILLA + '\u02d9' # 0xFF -> DOT ABOVE +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/cp1251.py b/contrib/tools/python3/src/Lib/encodings/cp1251.py new file mode 100644 index 0000000000..22bc66002d --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp1251.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec cp1251 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1251.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp1251', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\u0402' # 0x80 -> CYRILLIC CAPITAL LETTER DJE + '\u0403' # 0x81 -> CYRILLIC CAPITAL LETTER GJE + '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK + '\u0453' # 0x83 -> CYRILLIC SMALL LETTER GJE + '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK + '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS + '\u2020' # 0x86 -> DAGGER + '\u2021' # 0x87 -> DOUBLE DAGGER + '\u20ac' # 0x88 -> EURO SIGN + '\u2030' # 0x89 -> PER MILLE SIGN + '\u0409' # 0x8A -> CYRILLIC CAPITAL LETTER LJE + '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + '\u040a' # 0x8C -> CYRILLIC CAPITAL LETTER NJE + '\u040c' # 0x8D -> CYRILLIC CAPITAL LETTER KJE + '\u040b' # 0x8E -> CYRILLIC CAPITAL LETTER TSHE + '\u040f' # 0x8F -> CYRILLIC CAPITAL LETTER DZHE + '\u0452' # 0x90 -> CYRILLIC SMALL LETTER DJE + '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK + '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK + '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK + '\u2022' # 0x95 -> BULLET + '\u2013' # 0x96 -> EN DASH + '\u2014' # 0x97 -> EM DASH + '\ufffe' # 0x98 -> UNDEFINED + '\u2122' # 0x99 -> TRADE MARK SIGN + '\u0459' # 0x9A -> CYRILLIC SMALL LETTER LJE + '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + '\u045a' # 0x9C -> CYRILLIC SMALL LETTER NJE + '\u045c' # 0x9D -> CYRILLIC SMALL LETTER KJE + '\u045b' # 0x9E -> CYRILLIC SMALL LETTER TSHE + '\u045f' # 0x9F -> CYRILLIC SMALL LETTER DZHE + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\u040e' # 0xA1 -> CYRILLIC CAPITAL LETTER SHORT U + '\u045e' # 0xA2 -> CYRILLIC SMALL LETTER SHORT U + '\u0408' # 0xA3 -> CYRILLIC CAPITAL LETTER JE + '\xa4' # 0xA4 -> CURRENCY SIGN + '\u0490' # 0xA5 -> CYRILLIC CAPITAL LETTER GHE WITH UPTURN + '\xa6' # 0xA6 -> BROKEN BAR + '\xa7' # 0xA7 -> SECTION SIGN + '\u0401' # 0xA8 -> CYRILLIC CAPITAL LETTER IO + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\u0404' # 0xAA -> CYRILLIC CAPITAL LETTER UKRAINIAN IE + '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xac' # 0xAC -> NOT SIGN + '\xad' # 0xAD -> SOFT HYPHEN + '\xae' # 0xAE -> REGISTERED SIGN + '\u0407' # 0xAF -> CYRILLIC CAPITAL LETTER YI + '\xb0' # 0xB0 -> DEGREE SIGN + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\u0406' # 0xB2 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + '\u0456' # 0xB3 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + '\u0491' # 0xB4 -> CYRILLIC SMALL LETTER GHE WITH UPTURN + '\xb5' # 0xB5 -> MICRO SIGN + '\xb6' # 0xB6 -> PILCROW SIGN + '\xb7' # 0xB7 -> MIDDLE DOT + '\u0451' # 0xB8 -> CYRILLIC SMALL LETTER IO + '\u2116' # 0xB9 -> NUMERO SIGN + '\u0454' # 0xBA -> CYRILLIC SMALL LETTER UKRAINIAN IE + '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u0458' # 0xBC -> CYRILLIC SMALL LETTER JE + '\u0405' # 0xBD -> CYRILLIC CAPITAL LETTER DZE + '\u0455' # 0xBE -> CYRILLIC SMALL LETTER DZE + '\u0457' # 0xBF -> CYRILLIC SMALL LETTER YI + '\u0410' # 0xC0 -> CYRILLIC CAPITAL LETTER A + '\u0411' # 0xC1 -> CYRILLIC CAPITAL LETTER BE + '\u0412' # 0xC2 -> CYRILLIC CAPITAL LETTER VE + '\u0413' # 0xC3 -> CYRILLIC CAPITAL LETTER GHE + '\u0414' # 0xC4 -> CYRILLIC CAPITAL LETTER DE + '\u0415' # 0xC5 -> CYRILLIC CAPITAL LETTER IE + '\u0416' # 0xC6 -> CYRILLIC CAPITAL LETTER ZHE + '\u0417' # 0xC7 -> CYRILLIC CAPITAL LETTER ZE + '\u0418' # 0xC8 -> CYRILLIC CAPITAL LETTER I + '\u0419' # 0xC9 -> CYRILLIC CAPITAL LETTER SHORT I + '\u041a' # 0xCA -> CYRILLIC CAPITAL LETTER KA + '\u041b' # 0xCB -> CYRILLIC CAPITAL LETTER EL + '\u041c' # 0xCC -> CYRILLIC CAPITAL LETTER EM + '\u041d' # 0xCD -> CYRILLIC CAPITAL LETTER EN + '\u041e' # 0xCE -> CYRILLIC CAPITAL LETTER O + '\u041f' # 0xCF -> CYRILLIC CAPITAL LETTER PE + '\u0420' # 0xD0 -> CYRILLIC CAPITAL LETTER ER + '\u0421' # 0xD1 -> CYRILLIC CAPITAL LETTER ES + '\u0422' # 0xD2 -> CYRILLIC CAPITAL LETTER TE + '\u0423' # 0xD3 -> CYRILLIC CAPITAL LETTER U + '\u0424' # 0xD4 -> CYRILLIC CAPITAL LETTER EF + '\u0425' # 0xD5 -> CYRILLIC CAPITAL LETTER HA + '\u0426' # 0xD6 -> CYRILLIC CAPITAL LETTER TSE + '\u0427' # 0xD7 -> CYRILLIC CAPITAL LETTER CHE + '\u0428' # 0xD8 -> CYRILLIC CAPITAL LETTER SHA + '\u0429' # 0xD9 -> CYRILLIC CAPITAL LETTER SHCHA + '\u042a' # 0xDA -> CYRILLIC CAPITAL LETTER HARD SIGN + '\u042b' # 0xDB -> CYRILLIC CAPITAL LETTER YERU + '\u042c' # 0xDC -> CYRILLIC CAPITAL LETTER SOFT SIGN + '\u042d' # 0xDD -> CYRILLIC CAPITAL LETTER E + '\u042e' # 0xDE -> CYRILLIC CAPITAL LETTER YU + '\u042f' # 0xDF -> CYRILLIC CAPITAL LETTER YA + '\u0430' # 0xE0 -> CYRILLIC SMALL LETTER A + '\u0431' # 0xE1 -> CYRILLIC SMALL LETTER BE + '\u0432' # 0xE2 -> CYRILLIC SMALL LETTER VE + '\u0433' # 0xE3 -> CYRILLIC SMALL LETTER GHE + '\u0434' # 0xE4 -> CYRILLIC SMALL LETTER DE + '\u0435' # 0xE5 -> CYRILLIC SMALL LETTER IE + '\u0436' # 0xE6 -> CYRILLIC SMALL LETTER ZHE + '\u0437' # 0xE7 -> CYRILLIC SMALL LETTER ZE + '\u0438' # 0xE8 -> CYRILLIC SMALL LETTER I + '\u0439' # 0xE9 -> CYRILLIC SMALL LETTER SHORT I + '\u043a' # 0xEA -> CYRILLIC SMALL LETTER KA + '\u043b' # 0xEB -> CYRILLIC SMALL LETTER EL + '\u043c' # 0xEC -> CYRILLIC SMALL LETTER EM + '\u043d' # 0xED -> CYRILLIC SMALL LETTER EN + '\u043e' # 0xEE -> CYRILLIC SMALL LETTER O + '\u043f' # 0xEF -> CYRILLIC SMALL LETTER PE + '\u0440' # 0xF0 -> CYRILLIC SMALL LETTER ER + '\u0441' # 0xF1 -> CYRILLIC SMALL LETTER ES + '\u0442' # 0xF2 -> CYRILLIC SMALL LETTER TE + '\u0443' # 0xF3 -> CYRILLIC SMALL LETTER U + '\u0444' # 0xF4 -> CYRILLIC SMALL LETTER EF + '\u0445' # 0xF5 -> CYRILLIC SMALL LETTER HA + '\u0446' # 0xF6 -> CYRILLIC SMALL LETTER TSE + '\u0447' # 0xF7 -> CYRILLIC SMALL LETTER CHE + '\u0448' # 0xF8 -> CYRILLIC SMALL LETTER SHA + '\u0449' # 0xF9 -> CYRILLIC SMALL LETTER SHCHA + '\u044a' # 0xFA -> CYRILLIC SMALL LETTER HARD SIGN + '\u044b' # 0xFB -> CYRILLIC SMALL LETTER YERU + '\u044c' # 0xFC -> CYRILLIC SMALL LETTER SOFT SIGN + '\u044d' # 0xFD -> CYRILLIC SMALL LETTER E + '\u044e' # 0xFE -> CYRILLIC SMALL LETTER YU + '\u044f' # 0xFF -> CYRILLIC SMALL LETTER YA +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/cp1252.py b/contrib/tools/python3/src/Lib/encodings/cp1252.py new file mode 100644 index 0000000000..c0e8088ea8 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp1252.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec cp1252 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1252.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp1252', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\u20ac' # 0x80 -> EURO SIGN + '\ufffe' # 0x81 -> UNDEFINED + '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK + '\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK + '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK + '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS + '\u2020' # 0x86 -> DAGGER + '\u2021' # 0x87 -> DOUBLE DAGGER + '\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT + '\u2030' # 0x89 -> PER MILLE SIGN + '\u0160' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON + '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + '\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE + '\ufffe' # 0x8D -> UNDEFINED + '\u017d' # 0x8E -> LATIN CAPITAL LETTER Z WITH CARON + '\ufffe' # 0x8F -> UNDEFINED + '\ufffe' # 0x90 -> UNDEFINED + '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK + '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK + '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK + '\u2022' # 0x95 -> BULLET + '\u2013' # 0x96 -> EN DASH + '\u2014' # 0x97 -> EM DASH + '\u02dc' # 0x98 -> SMALL TILDE + '\u2122' # 0x99 -> TRADE MARK SIGN + '\u0161' # 0x9A -> LATIN SMALL LETTER S WITH CARON + '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + '\u0153' # 0x9C -> LATIN SMALL LIGATURE OE + '\ufffe' # 0x9D -> UNDEFINED + '\u017e' # 0x9E -> LATIN SMALL LETTER Z WITH CARON + '\u0178' # 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK + '\xa2' # 0xA2 -> CENT SIGN + '\xa3' # 0xA3 -> POUND SIGN + '\xa4' # 0xA4 -> CURRENCY SIGN + '\xa5' # 0xA5 -> YEN SIGN + '\xa6' # 0xA6 -> BROKEN BAR + '\xa7' # 0xA7 -> SECTION SIGN + '\xa8' # 0xA8 -> DIAERESIS + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR + '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xac' # 0xAC -> NOT SIGN + '\xad' # 0xAD -> SOFT HYPHEN + '\xae' # 0xAE -> REGISTERED SIGN + '\xaf' # 0xAF -> MACRON + '\xb0' # 0xB0 -> DEGREE SIGN + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\xb2' # 0xB2 -> SUPERSCRIPT TWO + '\xb3' # 0xB3 -> SUPERSCRIPT THREE + '\xb4' # 0xB4 -> ACUTE ACCENT + '\xb5' # 0xB5 -> MICRO SIGN + '\xb6' # 0xB6 -> PILCROW SIGN + '\xb7' # 0xB7 -> MIDDLE DOT + '\xb8' # 0xB8 -> CEDILLA + '\xb9' # 0xB9 -> SUPERSCRIPT ONE + '\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR + '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER + '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + '\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS + '\xbf' # 0xBF -> INVERTED QUESTION MARK + '\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE + '\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE + '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE + '\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE + '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH + '\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE + '\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE + '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE + '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xd7' # 0xD7 -> MULTIPLICATION SIGN + '\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE + '\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE + '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + '\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE + '\xde' # 0xDE -> LATIN CAPITAL LETTER THORN + '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + '\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE + '\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE + '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe6' # 0xE6 -> LATIN SMALL LETTER AE + '\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + '\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE + '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + '\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + '\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE + '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS + '\xf0' # 0xF0 -> LATIN SMALL LETTER ETH + '\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE + '\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE + '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE + '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf7' # 0xF7 -> DIVISION SIGN + '\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE + '\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE + '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + '\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + '\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE + '\xfe' # 0xFE -> LATIN SMALL LETTER THORN + '\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/cp1253.py b/contrib/tools/python3/src/Lib/encodings/cp1253.py new file mode 100644 index 0000000000..ec9c0972d1 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp1253.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec cp1253 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1253.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp1253', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\u20ac' # 0x80 -> EURO SIGN + '\ufffe' # 0x81 -> UNDEFINED + '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK + '\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK + '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK + '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS + '\u2020' # 0x86 -> DAGGER + '\u2021' # 0x87 -> DOUBLE DAGGER + '\ufffe' # 0x88 -> UNDEFINED + '\u2030' # 0x89 -> PER MILLE SIGN + '\ufffe' # 0x8A -> UNDEFINED + '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + '\ufffe' # 0x8C -> UNDEFINED + '\ufffe' # 0x8D -> UNDEFINED + '\ufffe' # 0x8E -> UNDEFINED + '\ufffe' # 0x8F -> UNDEFINED + '\ufffe' # 0x90 -> UNDEFINED + '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK + '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK + '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK + '\u2022' # 0x95 -> BULLET + '\u2013' # 0x96 -> EN DASH + '\u2014' # 0x97 -> EM DASH + '\ufffe' # 0x98 -> UNDEFINED + '\u2122' # 0x99 -> TRADE MARK SIGN + '\ufffe' # 0x9A -> UNDEFINED + '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + '\ufffe' # 0x9C -> UNDEFINED + '\ufffe' # 0x9D -> UNDEFINED + '\ufffe' # 0x9E -> UNDEFINED + '\ufffe' # 0x9F -> UNDEFINED + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\u0385' # 0xA1 -> GREEK DIALYTIKA TONOS + '\u0386' # 0xA2 -> GREEK CAPITAL LETTER ALPHA WITH TONOS + '\xa3' # 0xA3 -> POUND SIGN + '\xa4' # 0xA4 -> CURRENCY SIGN + '\xa5' # 0xA5 -> YEN SIGN + '\xa6' # 0xA6 -> BROKEN BAR + '\xa7' # 0xA7 -> SECTION SIGN + '\xa8' # 0xA8 -> DIAERESIS + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\ufffe' # 0xAA -> UNDEFINED + '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xac' # 0xAC -> NOT SIGN + '\xad' # 0xAD -> SOFT HYPHEN + '\xae' # 0xAE -> REGISTERED SIGN + '\u2015' # 0xAF -> HORIZONTAL BAR + '\xb0' # 0xB0 -> DEGREE SIGN + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\xb2' # 0xB2 -> SUPERSCRIPT TWO + '\xb3' # 0xB3 -> SUPERSCRIPT THREE + '\u0384' # 0xB4 -> GREEK TONOS + '\xb5' # 0xB5 -> MICRO SIGN + '\xb6' # 0xB6 -> PILCROW SIGN + '\xb7' # 0xB7 -> MIDDLE DOT + '\u0388' # 0xB8 -> GREEK CAPITAL LETTER EPSILON WITH TONOS + '\u0389' # 0xB9 -> GREEK CAPITAL LETTER ETA WITH TONOS + '\u038a' # 0xBA -> GREEK CAPITAL LETTER IOTA WITH TONOS + '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u038c' # 0xBC -> GREEK CAPITAL LETTER OMICRON WITH TONOS + '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + '\u038e' # 0xBE -> GREEK CAPITAL LETTER UPSILON WITH TONOS + '\u038f' # 0xBF -> GREEK CAPITAL LETTER OMEGA WITH TONOS + '\u0390' # 0xC0 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS + '\u0391' # 0xC1 -> GREEK CAPITAL LETTER ALPHA + '\u0392' # 0xC2 -> GREEK CAPITAL LETTER BETA + '\u0393' # 0xC3 -> GREEK CAPITAL LETTER GAMMA + '\u0394' # 0xC4 -> GREEK CAPITAL LETTER DELTA + '\u0395' # 0xC5 -> GREEK CAPITAL LETTER EPSILON + '\u0396' # 0xC6 -> GREEK CAPITAL LETTER ZETA + '\u0397' # 0xC7 -> GREEK CAPITAL LETTER ETA + '\u0398' # 0xC8 -> GREEK CAPITAL LETTER THETA + '\u0399' # 0xC9 -> GREEK CAPITAL LETTER IOTA + '\u039a' # 0xCA -> GREEK CAPITAL LETTER KAPPA + '\u039b' # 0xCB -> GREEK CAPITAL LETTER LAMDA + '\u039c' # 0xCC -> GREEK CAPITAL LETTER MU + '\u039d' # 0xCD -> GREEK CAPITAL LETTER NU + '\u039e' # 0xCE -> GREEK CAPITAL LETTER XI + '\u039f' # 0xCF -> GREEK CAPITAL LETTER OMICRON + '\u03a0' # 0xD0 -> GREEK CAPITAL LETTER PI + '\u03a1' # 0xD1 -> GREEK CAPITAL LETTER RHO + '\ufffe' # 0xD2 -> UNDEFINED + '\u03a3' # 0xD3 -> GREEK CAPITAL LETTER SIGMA + '\u03a4' # 0xD4 -> GREEK CAPITAL LETTER TAU + '\u03a5' # 0xD5 -> GREEK CAPITAL LETTER UPSILON + '\u03a6' # 0xD6 -> GREEK CAPITAL LETTER PHI + '\u03a7' # 0xD7 -> GREEK CAPITAL LETTER CHI + '\u03a8' # 0xD8 -> GREEK CAPITAL LETTER PSI + '\u03a9' # 0xD9 -> GREEK CAPITAL LETTER OMEGA + '\u03aa' # 0xDA -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA + '\u03ab' # 0xDB -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA + '\u03ac' # 0xDC -> GREEK SMALL LETTER ALPHA WITH TONOS + '\u03ad' # 0xDD -> GREEK SMALL LETTER EPSILON WITH TONOS + '\u03ae' # 0xDE -> GREEK SMALL LETTER ETA WITH TONOS + '\u03af' # 0xDF -> GREEK SMALL LETTER IOTA WITH TONOS + '\u03b0' # 0xE0 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS + '\u03b1' # 0xE1 -> GREEK SMALL LETTER ALPHA + '\u03b2' # 0xE2 -> GREEK SMALL LETTER BETA + '\u03b3' # 0xE3 -> GREEK SMALL LETTER GAMMA + '\u03b4' # 0xE4 -> GREEK SMALL LETTER DELTA + '\u03b5' # 0xE5 -> GREEK SMALL LETTER EPSILON + '\u03b6' # 0xE6 -> GREEK SMALL LETTER ZETA + '\u03b7' # 0xE7 -> GREEK SMALL LETTER ETA + '\u03b8' # 0xE8 -> GREEK SMALL LETTER THETA + '\u03b9' # 0xE9 -> GREEK SMALL LETTER IOTA + '\u03ba' # 0xEA -> GREEK SMALL LETTER KAPPA + '\u03bb' # 0xEB -> GREEK SMALL LETTER LAMDA + '\u03bc' # 0xEC -> GREEK SMALL LETTER MU + '\u03bd' # 0xED -> GREEK SMALL LETTER NU + '\u03be' # 0xEE -> GREEK SMALL LETTER XI + '\u03bf' # 0xEF -> GREEK SMALL LETTER OMICRON + '\u03c0' # 0xF0 -> GREEK SMALL LETTER PI + '\u03c1' # 0xF1 -> GREEK SMALL LETTER RHO + '\u03c2' # 0xF2 -> GREEK SMALL LETTER FINAL SIGMA + '\u03c3' # 0xF3 -> GREEK SMALL LETTER SIGMA + '\u03c4' # 0xF4 -> GREEK SMALL LETTER TAU + '\u03c5' # 0xF5 -> GREEK SMALL LETTER UPSILON + '\u03c6' # 0xF6 -> GREEK SMALL LETTER PHI + '\u03c7' # 0xF7 -> GREEK SMALL LETTER CHI + '\u03c8' # 0xF8 -> GREEK SMALL LETTER PSI + '\u03c9' # 0xF9 -> GREEK SMALL LETTER OMEGA + '\u03ca' # 0xFA -> GREEK SMALL LETTER IOTA WITH DIALYTIKA + '\u03cb' # 0xFB -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA + '\u03cc' # 0xFC -> GREEK SMALL LETTER OMICRON WITH TONOS + '\u03cd' # 0xFD -> GREEK SMALL LETTER UPSILON WITH TONOS + '\u03ce' # 0xFE -> GREEK SMALL LETTER OMEGA WITH TONOS + '\ufffe' # 0xFF -> UNDEFINED +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/cp1254.py b/contrib/tools/python3/src/Lib/encodings/cp1254.py new file mode 100644 index 0000000000..4912327a5b --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp1254.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec cp1254 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1254.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp1254', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\u20ac' # 0x80 -> EURO SIGN + '\ufffe' # 0x81 -> UNDEFINED + '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK + '\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK + '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK + '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS + '\u2020' # 0x86 -> DAGGER + '\u2021' # 0x87 -> DOUBLE DAGGER + '\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT + '\u2030' # 0x89 -> PER MILLE SIGN + '\u0160' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON + '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + '\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE + '\ufffe' # 0x8D -> UNDEFINED + '\ufffe' # 0x8E -> UNDEFINED + '\ufffe' # 0x8F -> UNDEFINED + '\ufffe' # 0x90 -> UNDEFINED + '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK + '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK + '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK + '\u2022' # 0x95 -> BULLET + '\u2013' # 0x96 -> EN DASH + '\u2014' # 0x97 -> EM DASH + '\u02dc' # 0x98 -> SMALL TILDE + '\u2122' # 0x99 -> TRADE MARK SIGN + '\u0161' # 0x9A -> LATIN SMALL LETTER S WITH CARON + '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + '\u0153' # 0x9C -> LATIN SMALL LIGATURE OE + '\ufffe' # 0x9D -> UNDEFINED + '\ufffe' # 0x9E -> UNDEFINED + '\u0178' # 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK + '\xa2' # 0xA2 -> CENT SIGN + '\xa3' # 0xA3 -> POUND SIGN + '\xa4' # 0xA4 -> CURRENCY SIGN + '\xa5' # 0xA5 -> YEN SIGN + '\xa6' # 0xA6 -> BROKEN BAR + '\xa7' # 0xA7 -> SECTION SIGN + '\xa8' # 0xA8 -> DIAERESIS + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR + '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xac' # 0xAC -> NOT SIGN + '\xad' # 0xAD -> SOFT HYPHEN + '\xae' # 0xAE -> REGISTERED SIGN + '\xaf' # 0xAF -> MACRON + '\xb0' # 0xB0 -> DEGREE SIGN + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\xb2' # 0xB2 -> SUPERSCRIPT TWO + '\xb3' # 0xB3 -> SUPERSCRIPT THREE + '\xb4' # 0xB4 -> ACUTE ACCENT + '\xb5' # 0xB5 -> MICRO SIGN + '\xb6' # 0xB6 -> PILCROW SIGN + '\xb7' # 0xB7 -> MIDDLE DOT + '\xb8' # 0xB8 -> CEDILLA + '\xb9' # 0xB9 -> SUPERSCRIPT ONE + '\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR + '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER + '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + '\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS + '\xbf' # 0xBF -> INVERTED QUESTION MARK + '\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE + '\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE + '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE + '\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE + '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\u011e' # 0xD0 -> LATIN CAPITAL LETTER G WITH BREVE + '\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE + '\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE + '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE + '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xd7' # 0xD7 -> MULTIPLICATION SIGN + '\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE + '\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE + '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + '\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\u0130' # 0xDD -> LATIN CAPITAL LETTER I WITH DOT ABOVE + '\u015e' # 0xDE -> LATIN CAPITAL LETTER S WITH CEDILLA + '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + '\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE + '\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE + '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe6' # 0xE6 -> LATIN SMALL LETTER AE + '\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + '\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE + '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + '\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + '\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE + '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS + '\u011f' # 0xF0 -> LATIN SMALL LETTER G WITH BREVE + '\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE + '\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE + '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE + '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf7' # 0xF7 -> DIVISION SIGN + '\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE + '\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE + '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + '\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + '\u0131' # 0xFD -> LATIN SMALL LETTER DOTLESS I + '\u015f' # 0xFE -> LATIN SMALL LETTER S WITH CEDILLA + '\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/cp1255.py b/contrib/tools/python3/src/Lib/encodings/cp1255.py new file mode 100644 index 0000000000..91ce26b9bf --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp1255.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec cp1255 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1255.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp1255', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\u20ac' # 0x80 -> EURO SIGN + '\ufffe' # 0x81 -> UNDEFINED + '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK + '\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK + '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK + '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS + '\u2020' # 0x86 -> DAGGER + '\u2021' # 0x87 -> DOUBLE DAGGER + '\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT + '\u2030' # 0x89 -> PER MILLE SIGN + '\ufffe' # 0x8A -> UNDEFINED + '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + '\ufffe' # 0x8C -> UNDEFINED + '\ufffe' # 0x8D -> UNDEFINED + '\ufffe' # 0x8E -> UNDEFINED + '\ufffe' # 0x8F -> UNDEFINED + '\ufffe' # 0x90 -> UNDEFINED + '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK + '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK + '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK + '\u2022' # 0x95 -> BULLET + '\u2013' # 0x96 -> EN DASH + '\u2014' # 0x97 -> EM DASH + '\u02dc' # 0x98 -> SMALL TILDE + '\u2122' # 0x99 -> TRADE MARK SIGN + '\ufffe' # 0x9A -> UNDEFINED + '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + '\ufffe' # 0x9C -> UNDEFINED + '\ufffe' # 0x9D -> UNDEFINED + '\ufffe' # 0x9E -> UNDEFINED + '\ufffe' # 0x9F -> UNDEFINED + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK + '\xa2' # 0xA2 -> CENT SIGN + '\xa3' # 0xA3 -> POUND SIGN + '\u20aa' # 0xA4 -> NEW SHEQEL SIGN + '\xa5' # 0xA5 -> YEN SIGN + '\xa6' # 0xA6 -> BROKEN BAR + '\xa7' # 0xA7 -> SECTION SIGN + '\xa8' # 0xA8 -> DIAERESIS + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\xd7' # 0xAA -> MULTIPLICATION SIGN + '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xac' # 0xAC -> NOT SIGN + '\xad' # 0xAD -> SOFT HYPHEN + '\xae' # 0xAE -> REGISTERED SIGN + '\xaf' # 0xAF -> MACRON + '\xb0' # 0xB0 -> DEGREE SIGN + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\xb2' # 0xB2 -> SUPERSCRIPT TWO + '\xb3' # 0xB3 -> SUPERSCRIPT THREE + '\xb4' # 0xB4 -> ACUTE ACCENT + '\xb5' # 0xB5 -> MICRO SIGN + '\xb6' # 0xB6 -> PILCROW SIGN + '\xb7' # 0xB7 -> MIDDLE DOT + '\xb8' # 0xB8 -> CEDILLA + '\xb9' # 0xB9 -> SUPERSCRIPT ONE + '\xf7' # 0xBA -> DIVISION SIGN + '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER + '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + '\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS + '\xbf' # 0xBF -> INVERTED QUESTION MARK + '\u05b0' # 0xC0 -> HEBREW POINT SHEVA + '\u05b1' # 0xC1 -> HEBREW POINT HATAF SEGOL + '\u05b2' # 0xC2 -> HEBREW POINT HATAF PATAH + '\u05b3' # 0xC3 -> HEBREW POINT HATAF QAMATS + '\u05b4' # 0xC4 -> HEBREW POINT HIRIQ + '\u05b5' # 0xC5 -> HEBREW POINT TSERE + '\u05b6' # 0xC6 -> HEBREW POINT SEGOL + '\u05b7' # 0xC7 -> HEBREW POINT PATAH + '\u05b8' # 0xC8 -> HEBREW POINT QAMATS + '\u05b9' # 0xC9 -> HEBREW POINT HOLAM + '\ufffe' # 0xCA -> UNDEFINED + '\u05bb' # 0xCB -> HEBREW POINT QUBUTS + '\u05bc' # 0xCC -> HEBREW POINT DAGESH OR MAPIQ + '\u05bd' # 0xCD -> HEBREW POINT METEG + '\u05be' # 0xCE -> HEBREW PUNCTUATION MAQAF + '\u05bf' # 0xCF -> HEBREW POINT RAFE + '\u05c0' # 0xD0 -> HEBREW PUNCTUATION PASEQ + '\u05c1' # 0xD1 -> HEBREW POINT SHIN DOT + '\u05c2' # 0xD2 -> HEBREW POINT SIN DOT + '\u05c3' # 0xD3 -> HEBREW PUNCTUATION SOF PASUQ + '\u05f0' # 0xD4 -> HEBREW LIGATURE YIDDISH DOUBLE VAV + '\u05f1' # 0xD5 -> HEBREW LIGATURE YIDDISH VAV YOD + '\u05f2' # 0xD6 -> HEBREW LIGATURE YIDDISH DOUBLE YOD + '\u05f3' # 0xD7 -> HEBREW PUNCTUATION GERESH + '\u05f4' # 0xD8 -> HEBREW PUNCTUATION GERSHAYIM + '\ufffe' # 0xD9 -> UNDEFINED + '\ufffe' # 0xDA -> UNDEFINED + '\ufffe' # 0xDB -> UNDEFINED + '\ufffe' # 0xDC -> UNDEFINED + '\ufffe' # 0xDD -> UNDEFINED + '\ufffe' # 0xDE -> UNDEFINED + '\ufffe' # 0xDF -> UNDEFINED + '\u05d0' # 0xE0 -> HEBREW LETTER ALEF + '\u05d1' # 0xE1 -> HEBREW LETTER BET + '\u05d2' # 0xE2 -> HEBREW LETTER GIMEL + '\u05d3' # 0xE3 -> HEBREW LETTER DALET + '\u05d4' # 0xE4 -> HEBREW LETTER HE + '\u05d5' # 0xE5 -> HEBREW LETTER VAV + '\u05d6' # 0xE6 -> HEBREW LETTER ZAYIN + '\u05d7' # 0xE7 -> HEBREW LETTER HET + '\u05d8' # 0xE8 -> HEBREW LETTER TET + '\u05d9' # 0xE9 -> HEBREW LETTER YOD + '\u05da' # 0xEA -> HEBREW LETTER FINAL KAF + '\u05db' # 0xEB -> HEBREW LETTER KAF + '\u05dc' # 0xEC -> HEBREW LETTER LAMED + '\u05dd' # 0xED -> HEBREW LETTER FINAL MEM + '\u05de' # 0xEE -> HEBREW LETTER MEM + '\u05df' # 0xEF -> HEBREW LETTER FINAL NUN + '\u05e0' # 0xF0 -> HEBREW LETTER NUN + '\u05e1' # 0xF1 -> HEBREW LETTER SAMEKH + '\u05e2' # 0xF2 -> HEBREW LETTER AYIN + '\u05e3' # 0xF3 -> HEBREW LETTER FINAL PE + '\u05e4' # 0xF4 -> HEBREW LETTER PE + '\u05e5' # 0xF5 -> HEBREW LETTER FINAL TSADI + '\u05e6' # 0xF6 -> HEBREW LETTER TSADI + '\u05e7' # 0xF7 -> HEBREW LETTER QOF + '\u05e8' # 0xF8 -> HEBREW LETTER RESH + '\u05e9' # 0xF9 -> HEBREW LETTER SHIN + '\u05ea' # 0xFA -> HEBREW LETTER TAV + '\ufffe' # 0xFB -> UNDEFINED + '\ufffe' # 0xFC -> UNDEFINED + '\u200e' # 0xFD -> LEFT-TO-RIGHT MARK + '\u200f' # 0xFE -> RIGHT-TO-LEFT MARK + '\ufffe' # 0xFF -> UNDEFINED +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/cp1256.py b/contrib/tools/python3/src/Lib/encodings/cp1256.py new file mode 100644 index 0000000000..fd6afab52c --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp1256.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec cp1256 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1256.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp1256', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\u20ac' # 0x80 -> EURO SIGN + '\u067e' # 0x81 -> ARABIC LETTER PEH + '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK + '\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK + '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK + '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS + '\u2020' # 0x86 -> DAGGER + '\u2021' # 0x87 -> DOUBLE DAGGER + '\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT + '\u2030' # 0x89 -> PER MILLE SIGN + '\u0679' # 0x8A -> ARABIC LETTER TTEH + '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + '\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE + '\u0686' # 0x8D -> ARABIC LETTER TCHEH + '\u0698' # 0x8E -> ARABIC LETTER JEH + '\u0688' # 0x8F -> ARABIC LETTER DDAL + '\u06af' # 0x90 -> ARABIC LETTER GAF + '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK + '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK + '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK + '\u2022' # 0x95 -> BULLET + '\u2013' # 0x96 -> EN DASH + '\u2014' # 0x97 -> EM DASH + '\u06a9' # 0x98 -> ARABIC LETTER KEHEH + '\u2122' # 0x99 -> TRADE MARK SIGN + '\u0691' # 0x9A -> ARABIC LETTER RREH + '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + '\u0153' # 0x9C -> LATIN SMALL LIGATURE OE + '\u200c' # 0x9D -> ZERO WIDTH NON-JOINER + '\u200d' # 0x9E -> ZERO WIDTH JOINER + '\u06ba' # 0x9F -> ARABIC LETTER NOON GHUNNA + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\u060c' # 0xA1 -> ARABIC COMMA + '\xa2' # 0xA2 -> CENT SIGN + '\xa3' # 0xA3 -> POUND SIGN + '\xa4' # 0xA4 -> CURRENCY SIGN + '\xa5' # 0xA5 -> YEN SIGN + '\xa6' # 0xA6 -> BROKEN BAR + '\xa7' # 0xA7 -> SECTION SIGN + '\xa8' # 0xA8 -> DIAERESIS + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\u06be' # 0xAA -> ARABIC LETTER HEH DOACHASHMEE + '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xac' # 0xAC -> NOT SIGN + '\xad' # 0xAD -> SOFT HYPHEN + '\xae' # 0xAE -> REGISTERED SIGN + '\xaf' # 0xAF -> MACRON + '\xb0' # 0xB0 -> DEGREE SIGN + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\xb2' # 0xB2 -> SUPERSCRIPT TWO + '\xb3' # 0xB3 -> SUPERSCRIPT THREE + '\xb4' # 0xB4 -> ACUTE ACCENT + '\xb5' # 0xB5 -> MICRO SIGN + '\xb6' # 0xB6 -> PILCROW SIGN + '\xb7' # 0xB7 -> MIDDLE DOT + '\xb8' # 0xB8 -> CEDILLA + '\xb9' # 0xB9 -> SUPERSCRIPT ONE + '\u061b' # 0xBA -> ARABIC SEMICOLON + '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER + '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + '\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS + '\u061f' # 0xBF -> ARABIC QUESTION MARK + '\u06c1' # 0xC0 -> ARABIC LETTER HEH GOAL + '\u0621' # 0xC1 -> ARABIC LETTER HAMZA + '\u0622' # 0xC2 -> ARABIC LETTER ALEF WITH MADDA ABOVE + '\u0623' # 0xC3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE + '\u0624' # 0xC4 -> ARABIC LETTER WAW WITH HAMZA ABOVE + '\u0625' # 0xC5 -> ARABIC LETTER ALEF WITH HAMZA BELOW + '\u0626' # 0xC6 -> ARABIC LETTER YEH WITH HAMZA ABOVE + '\u0627' # 0xC7 -> ARABIC LETTER ALEF + '\u0628' # 0xC8 -> ARABIC LETTER BEH + '\u0629' # 0xC9 -> ARABIC LETTER TEH MARBUTA + '\u062a' # 0xCA -> ARABIC LETTER TEH + '\u062b' # 0xCB -> ARABIC LETTER THEH + '\u062c' # 0xCC -> ARABIC LETTER JEEM + '\u062d' # 0xCD -> ARABIC LETTER HAH + '\u062e' # 0xCE -> ARABIC LETTER KHAH + '\u062f' # 0xCF -> ARABIC LETTER DAL + '\u0630' # 0xD0 -> ARABIC LETTER THAL + '\u0631' # 0xD1 -> ARABIC LETTER REH + '\u0632' # 0xD2 -> ARABIC LETTER ZAIN + '\u0633' # 0xD3 -> ARABIC LETTER SEEN + '\u0634' # 0xD4 -> ARABIC LETTER SHEEN + '\u0635' # 0xD5 -> ARABIC LETTER SAD + '\u0636' # 0xD6 -> ARABIC LETTER DAD + '\xd7' # 0xD7 -> MULTIPLICATION SIGN + '\u0637' # 0xD8 -> ARABIC LETTER TAH + '\u0638' # 0xD9 -> ARABIC LETTER ZAH + '\u0639' # 0xDA -> ARABIC LETTER AIN + '\u063a' # 0xDB -> ARABIC LETTER GHAIN + '\u0640' # 0xDC -> ARABIC TATWEEL + '\u0641' # 0xDD -> ARABIC LETTER FEH + '\u0642' # 0xDE -> ARABIC LETTER QAF + '\u0643' # 0xDF -> ARABIC LETTER KAF + '\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE + '\u0644' # 0xE1 -> ARABIC LETTER LAM + '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\u0645' # 0xE3 -> ARABIC LETTER MEEM + '\u0646' # 0xE4 -> ARABIC LETTER NOON + '\u0647' # 0xE5 -> ARABIC LETTER HEH + '\u0648' # 0xE6 -> ARABIC LETTER WAW + '\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + '\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE + '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + '\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + '\u0649' # 0xEC -> ARABIC LETTER ALEF MAKSURA + '\u064a' # 0xED -> ARABIC LETTER YEH + '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS + '\u064b' # 0xF0 -> ARABIC FATHATAN + '\u064c' # 0xF1 -> ARABIC DAMMATAN + '\u064d' # 0xF2 -> ARABIC KASRATAN + '\u064e' # 0xF3 -> ARABIC FATHA + '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\u064f' # 0xF5 -> ARABIC DAMMA + '\u0650' # 0xF6 -> ARABIC KASRA + '\xf7' # 0xF7 -> DIVISION SIGN + '\u0651' # 0xF8 -> ARABIC SHADDA + '\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE + '\u0652' # 0xFA -> ARABIC SUKUN + '\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + '\u200e' # 0xFD -> LEFT-TO-RIGHT MARK + '\u200f' # 0xFE -> RIGHT-TO-LEFT MARK + '\u06d2' # 0xFF -> ARABIC LETTER YEH BARREE +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/cp1257.py b/contrib/tools/python3/src/Lib/encodings/cp1257.py new file mode 100644 index 0000000000..9ebc90d509 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp1257.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec cp1257 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1257.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp1257', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\u20ac' # 0x80 -> EURO SIGN + '\ufffe' # 0x81 -> UNDEFINED + '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK + '\ufffe' # 0x83 -> UNDEFINED + '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK + '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS + '\u2020' # 0x86 -> DAGGER + '\u2021' # 0x87 -> DOUBLE DAGGER + '\ufffe' # 0x88 -> UNDEFINED + '\u2030' # 0x89 -> PER MILLE SIGN + '\ufffe' # 0x8A -> UNDEFINED + '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + '\ufffe' # 0x8C -> UNDEFINED + '\xa8' # 0x8D -> DIAERESIS + '\u02c7' # 0x8E -> CARON + '\xb8' # 0x8F -> CEDILLA + '\ufffe' # 0x90 -> UNDEFINED + '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK + '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK + '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK + '\u2022' # 0x95 -> BULLET + '\u2013' # 0x96 -> EN DASH + '\u2014' # 0x97 -> EM DASH + '\ufffe' # 0x98 -> UNDEFINED + '\u2122' # 0x99 -> TRADE MARK SIGN + '\ufffe' # 0x9A -> UNDEFINED + '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + '\ufffe' # 0x9C -> UNDEFINED + '\xaf' # 0x9D -> MACRON + '\u02db' # 0x9E -> OGONEK + '\ufffe' # 0x9F -> UNDEFINED + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\ufffe' # 0xA1 -> UNDEFINED + '\xa2' # 0xA2 -> CENT SIGN + '\xa3' # 0xA3 -> POUND SIGN + '\xa4' # 0xA4 -> CURRENCY SIGN + '\ufffe' # 0xA5 -> UNDEFINED + '\xa6' # 0xA6 -> BROKEN BAR + '\xa7' # 0xA7 -> SECTION SIGN + '\xd8' # 0xA8 -> LATIN CAPITAL LETTER O WITH STROKE + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\u0156' # 0xAA -> LATIN CAPITAL LETTER R WITH CEDILLA + '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xac' # 0xAC -> NOT SIGN + '\xad' # 0xAD -> SOFT HYPHEN + '\xae' # 0xAE -> REGISTERED SIGN + '\xc6' # 0xAF -> LATIN CAPITAL LETTER AE + '\xb0' # 0xB0 -> DEGREE SIGN + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\xb2' # 0xB2 -> SUPERSCRIPT TWO + '\xb3' # 0xB3 -> SUPERSCRIPT THREE + '\xb4' # 0xB4 -> ACUTE ACCENT + '\xb5' # 0xB5 -> MICRO SIGN + '\xb6' # 0xB6 -> PILCROW SIGN + '\xb7' # 0xB7 -> MIDDLE DOT + '\xf8' # 0xB8 -> LATIN SMALL LETTER O WITH STROKE + '\xb9' # 0xB9 -> SUPERSCRIPT ONE + '\u0157' # 0xBA -> LATIN SMALL LETTER R WITH CEDILLA + '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER + '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + '\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS + '\xe6' # 0xBF -> LATIN SMALL LETTER AE + '\u0104' # 0xC0 -> LATIN CAPITAL LETTER A WITH OGONEK + '\u012e' # 0xC1 -> LATIN CAPITAL LETTER I WITH OGONEK + '\u0100' # 0xC2 -> LATIN CAPITAL LETTER A WITH MACRON + '\u0106' # 0xC3 -> LATIN CAPITAL LETTER C WITH ACUTE + '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\u0118' # 0xC6 -> LATIN CAPITAL LETTER E WITH OGONEK + '\u0112' # 0xC7 -> LATIN CAPITAL LETTER E WITH MACRON + '\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON + '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + '\u0179' # 0xCA -> LATIN CAPITAL LETTER Z WITH ACUTE + '\u0116' # 0xCB -> LATIN CAPITAL LETTER E WITH DOT ABOVE + '\u0122' # 0xCC -> LATIN CAPITAL LETTER G WITH CEDILLA + '\u0136' # 0xCD -> LATIN CAPITAL LETTER K WITH CEDILLA + '\u012a' # 0xCE -> LATIN CAPITAL LETTER I WITH MACRON + '\u013b' # 0xCF -> LATIN CAPITAL LETTER L WITH CEDILLA + '\u0160' # 0xD0 -> LATIN CAPITAL LETTER S WITH CARON + '\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE + '\u0145' # 0xD2 -> LATIN CAPITAL LETTER N WITH CEDILLA + '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + '\u014c' # 0xD4 -> LATIN CAPITAL LETTER O WITH MACRON + '\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE + '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xd7' # 0xD7 -> MULTIPLICATION SIGN + '\u0172' # 0xD8 -> LATIN CAPITAL LETTER U WITH OGONEK + '\u0141' # 0xD9 -> LATIN CAPITAL LETTER L WITH STROKE + '\u015a' # 0xDA -> LATIN CAPITAL LETTER S WITH ACUTE + '\u016a' # 0xDB -> LATIN CAPITAL LETTER U WITH MACRON + '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\u017b' # 0xDD -> LATIN CAPITAL LETTER Z WITH DOT ABOVE + '\u017d' # 0xDE -> LATIN CAPITAL LETTER Z WITH CARON + '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + '\u0105' # 0xE0 -> LATIN SMALL LETTER A WITH OGONEK + '\u012f' # 0xE1 -> LATIN SMALL LETTER I WITH OGONEK + '\u0101' # 0xE2 -> LATIN SMALL LETTER A WITH MACRON + '\u0107' # 0xE3 -> LATIN SMALL LETTER C WITH ACUTE + '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + '\u0119' # 0xE6 -> LATIN SMALL LETTER E WITH OGONEK + '\u0113' # 0xE7 -> LATIN SMALL LETTER E WITH MACRON + '\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON + '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + '\u017a' # 0xEA -> LATIN SMALL LETTER Z WITH ACUTE + '\u0117' # 0xEB -> LATIN SMALL LETTER E WITH DOT ABOVE + '\u0123' # 0xEC -> LATIN SMALL LETTER G WITH CEDILLA + '\u0137' # 0xED -> LATIN SMALL LETTER K WITH CEDILLA + '\u012b' # 0xEE -> LATIN SMALL LETTER I WITH MACRON + '\u013c' # 0xEF -> LATIN SMALL LETTER L WITH CEDILLA + '\u0161' # 0xF0 -> LATIN SMALL LETTER S WITH CARON + '\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE + '\u0146' # 0xF2 -> LATIN SMALL LETTER N WITH CEDILLA + '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + '\u014d' # 0xF4 -> LATIN SMALL LETTER O WITH MACRON + '\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE + '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf7' # 0xF7 -> DIVISION SIGN + '\u0173' # 0xF8 -> LATIN SMALL LETTER U WITH OGONEK + '\u0142' # 0xF9 -> LATIN SMALL LETTER L WITH STROKE + '\u015b' # 0xFA -> LATIN SMALL LETTER S WITH ACUTE + '\u016b' # 0xFB -> LATIN SMALL LETTER U WITH MACRON + '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + '\u017c' # 0xFD -> LATIN SMALL LETTER Z WITH DOT ABOVE + '\u017e' # 0xFE -> LATIN SMALL LETTER Z WITH CARON + '\u02d9' # 0xFF -> DOT ABOVE +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/cp1258.py b/contrib/tools/python3/src/Lib/encodings/cp1258.py new file mode 100644 index 0000000000..784378a836 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp1258.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec cp1258 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1258.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp1258', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\u20ac' # 0x80 -> EURO SIGN + '\ufffe' # 0x81 -> UNDEFINED + '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK + '\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK + '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK + '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS + '\u2020' # 0x86 -> DAGGER + '\u2021' # 0x87 -> DOUBLE DAGGER + '\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT + '\u2030' # 0x89 -> PER MILLE SIGN + '\ufffe' # 0x8A -> UNDEFINED + '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + '\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE + '\ufffe' # 0x8D -> UNDEFINED + '\ufffe' # 0x8E -> UNDEFINED + '\ufffe' # 0x8F -> UNDEFINED + '\ufffe' # 0x90 -> UNDEFINED + '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK + '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK + '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK + '\u2022' # 0x95 -> BULLET + '\u2013' # 0x96 -> EN DASH + '\u2014' # 0x97 -> EM DASH + '\u02dc' # 0x98 -> SMALL TILDE + '\u2122' # 0x99 -> TRADE MARK SIGN + '\ufffe' # 0x9A -> UNDEFINED + '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + '\u0153' # 0x9C -> LATIN SMALL LIGATURE OE + '\ufffe' # 0x9D -> UNDEFINED + '\ufffe' # 0x9E -> UNDEFINED + '\u0178' # 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK + '\xa2' # 0xA2 -> CENT SIGN + '\xa3' # 0xA3 -> POUND SIGN + '\xa4' # 0xA4 -> CURRENCY SIGN + '\xa5' # 0xA5 -> YEN SIGN + '\xa6' # 0xA6 -> BROKEN BAR + '\xa7' # 0xA7 -> SECTION SIGN + '\xa8' # 0xA8 -> DIAERESIS + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR + '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xac' # 0xAC -> NOT SIGN + '\xad' # 0xAD -> SOFT HYPHEN + '\xae' # 0xAE -> REGISTERED SIGN + '\xaf' # 0xAF -> MACRON + '\xb0' # 0xB0 -> DEGREE SIGN + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\xb2' # 0xB2 -> SUPERSCRIPT TWO + '\xb3' # 0xB3 -> SUPERSCRIPT THREE + '\xb4' # 0xB4 -> ACUTE ACCENT + '\xb5' # 0xB5 -> MICRO SIGN + '\xb6' # 0xB6 -> PILCROW SIGN + '\xb7' # 0xB7 -> MIDDLE DOT + '\xb8' # 0xB8 -> CEDILLA + '\xb9' # 0xB9 -> SUPERSCRIPT ONE + '\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR + '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER + '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + '\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS + '\xbf' # 0xBF -> INVERTED QUESTION MARK + '\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE + '\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\u0102' # 0xC3 -> LATIN CAPITAL LETTER A WITH BREVE + '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE + '\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\u0300' # 0xCC -> COMBINING GRAVE ACCENT + '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE + '\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE + '\u0309' # 0xD2 -> COMBINING HOOK ABOVE + '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\u01a0' # 0xD5 -> LATIN CAPITAL LETTER O WITH HORN + '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xd7' # 0xD7 -> MULTIPLICATION SIGN + '\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE + '\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE + '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + '\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\u01af' # 0xDD -> LATIN CAPITAL LETTER U WITH HORN + '\u0303' # 0xDE -> COMBINING TILDE + '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + '\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE + '\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\u0103' # 0xE3 -> LATIN SMALL LETTER A WITH BREVE + '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe6' # 0xE6 -> LATIN SMALL LETTER AE + '\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + '\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE + '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + '\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + '\u0301' # 0xEC -> COMBINING ACUTE ACCENT + '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS + '\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE + '\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE + '\u0323' # 0xF2 -> COMBINING DOT BELOW + '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\u01a1' # 0xF5 -> LATIN SMALL LETTER O WITH HORN + '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf7' # 0xF7 -> DIVISION SIGN + '\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE + '\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE + '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + '\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + '\u01b0' # 0xFD -> LATIN SMALL LETTER U WITH HORN + '\u20ab' # 0xFE -> DONG SIGN + '\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/cp273.py b/contrib/tools/python3/src/Lib/encodings/cp273.py new file mode 100644 index 0000000000..69c6d778c5 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp273.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec cp273 generated from 'python-mappings/CP273.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp273', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL (NUL) + '\x01' # 0x01 -> START OF HEADING (SOH) + '\x02' # 0x02 -> START OF TEXT (STX) + '\x03' # 0x03 -> END OF TEXT (ETX) + '\x9c' # 0x04 -> STRING TERMINATOR (ST) + '\t' # 0x05 -> CHARACTER TABULATION (HT) + '\x86' # 0x06 -> START OF SELECTED AREA (SSA) + '\x7f' # 0x07 -> DELETE (DEL) + '\x97' # 0x08 -> END OF GUARDED AREA (EPA) + '\x8d' # 0x09 -> REVERSE LINE FEED (RI) + '\x8e' # 0x0A -> SINGLE-SHIFT TWO (SS2) + '\x0b' # 0x0B -> LINE TABULATION (VT) + '\x0c' # 0x0C -> FORM FEED (FF) + '\r' # 0x0D -> CARRIAGE RETURN (CR) + '\x0e' # 0x0E -> SHIFT OUT (SO) + '\x0f' # 0x0F -> SHIFT IN (SI) + '\x10' # 0x10 -> DATALINK ESCAPE (DLE) + '\x11' # 0x11 -> DEVICE CONTROL ONE (DC1) + '\x12' # 0x12 -> DEVICE CONTROL TWO (DC2) + '\x13' # 0x13 -> DEVICE CONTROL THREE (DC3) + '\x9d' # 0x14 -> OPERATING SYSTEM COMMAND (OSC) + '\x85' # 0x15 -> NEXT LINE (NEL) + '\x08' # 0x16 -> BACKSPACE (BS) + '\x87' # 0x17 -> END OF SELECTED AREA (ESA) + '\x18' # 0x18 -> CANCEL (CAN) + '\x19' # 0x19 -> END OF MEDIUM (EM) + '\x92' # 0x1A -> PRIVATE USE TWO (PU2) + '\x8f' # 0x1B -> SINGLE-SHIFT THREE (SS3) + '\x1c' # 0x1C -> FILE SEPARATOR (IS4) + '\x1d' # 0x1D -> GROUP SEPARATOR (IS3) + '\x1e' # 0x1E -> RECORD SEPARATOR (IS2) + '\x1f' # 0x1F -> UNIT SEPARATOR (IS1) + '\x80' # 0x20 -> PADDING CHARACTER (PAD) + '\x81' # 0x21 -> HIGH OCTET PRESET (HOP) + '\x82' # 0x22 -> BREAK PERMITTED HERE (BPH) + '\x83' # 0x23 -> NO BREAK HERE (NBH) + '\x84' # 0x24 -> INDEX (IND) + '\n' # 0x25 -> LINE FEED (LF) + '\x17' # 0x26 -> END OF TRANSMISSION BLOCK (ETB) + '\x1b' # 0x27 -> ESCAPE (ESC) + '\x88' # 0x28 -> CHARACTER TABULATION SET (HTS) + '\x89' # 0x29 -> CHARACTER TABULATION WITH JUSTIFICATION (HTJ) + '\x8a' # 0x2A -> LINE TABULATION SET (VTS) + '\x8b' # 0x2B -> PARTIAL LINE FORWARD (PLD) + '\x8c' # 0x2C -> PARTIAL LINE BACKWARD (PLU) + '\x05' # 0x2D -> ENQUIRY (ENQ) + '\x06' # 0x2E -> ACKNOWLEDGE (ACK) + '\x07' # 0x2F -> BELL (BEL) + '\x90' # 0x30 -> DEVICE CONTROL STRING (DCS) + '\x91' # 0x31 -> PRIVATE USE ONE (PU1) + '\x16' # 0x32 -> SYNCHRONOUS IDLE (SYN) + '\x93' # 0x33 -> SET TRANSMIT STATE (STS) + '\x94' # 0x34 -> CANCEL CHARACTER (CCH) + '\x95' # 0x35 -> MESSAGE WAITING (MW) + '\x96' # 0x36 -> START OF GUARDED AREA (SPA) + '\x04' # 0x37 -> END OF TRANSMISSION (EOT) + '\x98' # 0x38 -> START OF STRING (SOS) + '\x99' # 0x39 -> SINGLE GRAPHIC CHARACTER INTRODUCER (SGCI) + '\x9a' # 0x3A -> SINGLE CHARACTER INTRODUCER (SCI) + '\x9b' # 0x3B -> CONTROL SEQUENCE INTRODUCER (CSI) + '\x14' # 0x3C -> DEVICE CONTROL FOUR (DC4) + '\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE (NAK) + '\x9e' # 0x3E -> PRIVACY MESSAGE (PM) + '\x1a' # 0x3F -> SUBSTITUTE (SUB) + ' ' # 0x40 -> SPACE + '\xa0' # 0x41 -> NO-BREAK SPACE + '\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '{' # 0x43 -> LEFT CURLY BRACKET + '\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE + '\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE + '\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE + '\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe7' # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA + '\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE + '\xc4' # 0x4A -> LATIN CAPITAL LETTER A WITH DIAERESIS + '.' # 0x4B -> FULL STOP + '<' # 0x4C -> LESS-THAN SIGN + '(' # 0x4D -> LEFT PARENTHESIS + '+' # 0x4E -> PLUS SIGN + '!' # 0x4F -> EXCLAMATION MARK + '&' # 0x50 -> AMPERSAND + '\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE + '\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS + '\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE + '\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE + '\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS + '\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE + '~' # 0x59 -> TILDE + '\xdc' # 0x5A -> LATIN CAPITAL LETTER U WITH DIAERESIS + '$' # 0x5B -> DOLLAR SIGN + '*' # 0x5C -> ASTERISK + ')' # 0x5D -> RIGHT PARENTHESIS + ';' # 0x5E -> SEMICOLON + '^' # 0x5F -> CIRCUMFLEX ACCENT + '-' # 0x60 -> HYPHEN-MINUS + '/' # 0x61 -> SOLIDUS + '\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '[' # 0x63 -> LEFT SQUARE BRACKET + '\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE + '\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE + '\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc7' # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE + '\xf6' # 0x6A -> LATIN SMALL LETTER O WITH DIAERESIS + ',' # 0x6B -> COMMA + '%' # 0x6C -> PERCENT SIGN + '_' # 0x6D -> LOW LINE + '>' # 0x6E -> GREATER-THAN SIGN + '?' # 0x6F -> QUESTION MARK + '\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE + '\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE + '`' # 0x79 -> GRAVE ACCENT + ':' # 0x7A -> COLON + '#' # 0x7B -> NUMBER SIGN + '\xa7' # 0x7C -> SECTION SIGN + "'" # 0x7D -> APOSTROPHE + '=' # 0x7E -> EQUALS SIGN + '"' # 0x7F -> QUOTATION MARK + '\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE + 'a' # 0x81 -> LATIN SMALL LETTER A + 'b' # 0x82 -> LATIN SMALL LETTER B + 'c' # 0x83 -> LATIN SMALL LETTER C + 'd' # 0x84 -> LATIN SMALL LETTER D + 'e' # 0x85 -> LATIN SMALL LETTER E + 'f' # 0x86 -> LATIN SMALL LETTER F + 'g' # 0x87 -> LATIN SMALL LETTER G + 'h' # 0x88 -> LATIN SMALL LETTER H + 'i' # 0x89 -> LATIN SMALL LETTER I + '\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xf0' # 0x8C -> LATIN SMALL LETTER ETH (Icelandic) + '\xfd' # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE + '\xfe' # 0x8E -> LATIN SMALL LETTER THORN (Icelandic) + '\xb1' # 0x8F -> PLUS-MINUS SIGN + '\xb0' # 0x90 -> DEGREE SIGN + 'j' # 0x91 -> LATIN SMALL LETTER J + 'k' # 0x92 -> LATIN SMALL LETTER K + 'l' # 0x93 -> LATIN SMALL LETTER L + 'm' # 0x94 -> LATIN SMALL LETTER M + 'n' # 0x95 -> LATIN SMALL LETTER N + 'o' # 0x96 -> LATIN SMALL LETTER O + 'p' # 0x97 -> LATIN SMALL LETTER P + 'q' # 0x98 -> LATIN SMALL LETTER Q + 'r' # 0x99 -> LATIN SMALL LETTER R + '\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR + '\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR + '\xe6' # 0x9C -> LATIN SMALL LETTER AE + '\xb8' # 0x9D -> CEDILLA + '\xc6' # 0x9E -> LATIN CAPITAL LETTER AE + '\xa4' # 0x9F -> CURRENCY SIGN + '\xb5' # 0xA0 -> MICRO SIGN + '\xdf' # 0xA1 -> LATIN SMALL LETTER SHARP S (German) + 's' # 0xA2 -> LATIN SMALL LETTER S + 't' # 0xA3 -> LATIN SMALL LETTER T + 'u' # 0xA4 -> LATIN SMALL LETTER U + 'v' # 0xA5 -> LATIN SMALL LETTER V + 'w' # 0xA6 -> LATIN SMALL LETTER W + 'x' # 0xA7 -> LATIN SMALL LETTER X + 'y' # 0xA8 -> LATIN SMALL LETTER Y + 'z' # 0xA9 -> LATIN SMALL LETTER Z + '\xa1' # 0xAA -> INVERTED EXCLAMATION MARK + '\xbf' # 0xAB -> INVERTED QUESTION MARK + '\xd0' # 0xAC -> LATIN CAPITAL LETTER ETH (Icelandic) + '\xdd' # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE + '\xde' # 0xAE -> LATIN CAPITAL LETTER THORN (Icelandic) + '\xae' # 0xAF -> REGISTERED SIGN + '\xa2' # 0xB0 -> CENT SIGN + '\xa3' # 0xB1 -> POUND SIGN + '\xa5' # 0xB2 -> YEN SIGN + '\xb7' # 0xB3 -> MIDDLE DOT + '\xa9' # 0xB4 -> COPYRIGHT SIGN + '@' # 0xB5 -> COMMERCIAL AT + '\xb6' # 0xB6 -> PILCROW SIGN + '\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER + '\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF + '\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS + '\xac' # 0xBA -> NOT SIGN + '|' # 0xBB -> VERTICAL LINE + '\u203e' # 0xBC -> OVERLINE + '\xa8' # 0xBD -> DIAERESIS + '\xb4' # 0xBE -> ACUTE ACCENT + '\xd7' # 0xBF -> MULTIPLICATION SIGN + '\xe4' # 0xC0 -> LATIN SMALL LETTER A WITH DIAERESIS + 'A' # 0xC1 -> LATIN CAPITAL LETTER A + 'B' # 0xC2 -> LATIN CAPITAL LETTER B + 'C' # 0xC3 -> LATIN CAPITAL LETTER C + 'D' # 0xC4 -> LATIN CAPITAL LETTER D + 'E' # 0xC5 -> LATIN CAPITAL LETTER E + 'F' # 0xC6 -> LATIN CAPITAL LETTER F + 'G' # 0xC7 -> LATIN CAPITAL LETTER G + 'H' # 0xC8 -> LATIN CAPITAL LETTER H + 'I' # 0xC9 -> LATIN CAPITAL LETTER I + '\xad' # 0xCA -> SOFT HYPHEN + '\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xa6' # 0xCC -> BROKEN BAR + '\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE + '\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE + '\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE + '\xfc' # 0xD0 -> LATIN SMALL LETTER U WITH DIAERESIS + 'J' # 0xD1 -> LATIN CAPITAL LETTER J + 'K' # 0xD2 -> LATIN CAPITAL LETTER K + 'L' # 0xD3 -> LATIN CAPITAL LETTER L + 'M' # 0xD4 -> LATIN CAPITAL LETTER M + 'N' # 0xD5 -> LATIN CAPITAL LETTER N + 'O' # 0xD6 -> LATIN CAPITAL LETTER O + 'P' # 0xD7 -> LATIN CAPITAL LETTER P + 'Q' # 0xD8 -> LATIN CAPITAL LETTER Q + 'R' # 0xD9 -> LATIN CAPITAL LETTER R + '\xb9' # 0xDA -> SUPERSCRIPT ONE + '\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '}' # 0xDC -> RIGHT CURLY BRACKET + '\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE + '\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE + '\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS + '\xd6' # 0xE0 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xf7' # 0xE1 -> DIVISION SIGN + 'S' # 0xE2 -> LATIN CAPITAL LETTER S + 'T' # 0xE3 -> LATIN CAPITAL LETTER T + 'U' # 0xE4 -> LATIN CAPITAL LETTER U + 'V' # 0xE5 -> LATIN CAPITAL LETTER V + 'W' # 0xE6 -> LATIN CAPITAL LETTER W + 'X' # 0xE7 -> LATIN CAPITAL LETTER X + 'Y' # 0xE8 -> LATIN CAPITAL LETTER Y + 'Z' # 0xE9 -> LATIN CAPITAL LETTER Z + '\xb2' # 0xEA -> SUPERSCRIPT TWO + '\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\\' # 0xEC -> REVERSE SOLIDUS + '\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE + '\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE + '0' # 0xF0 -> DIGIT ZERO + '1' # 0xF1 -> DIGIT ONE + '2' # 0xF2 -> DIGIT TWO + '3' # 0xF3 -> DIGIT THREE + '4' # 0xF4 -> DIGIT FOUR + '5' # 0xF5 -> DIGIT FIVE + '6' # 0xF6 -> DIGIT SIX + '7' # 0xF7 -> DIGIT SEVEN + '8' # 0xF8 -> DIGIT EIGHT + '9' # 0xF9 -> DIGIT NINE + '\xb3' # 0xFA -> SUPERSCRIPT THREE + '\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + ']' # 0xFC -> RIGHT SQUARE BRACKET + '\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE + '\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE + '\x9f' # 0xFF -> APPLICATION PROGRAM COMMAND (APC) +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/cp424.py b/contrib/tools/python3/src/Lib/encodings/cp424.py new file mode 100644 index 0000000000..6753daf122 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp424.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec cp424 generated from 'MAPPINGS/VENDORS/MISC/CP424.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp424', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x9c' # 0x04 -> SELECT + '\t' # 0x05 -> HORIZONTAL TABULATION + '\x86' # 0x06 -> REQUIRED NEW LINE + '\x7f' # 0x07 -> DELETE + '\x97' # 0x08 -> GRAPHIC ESCAPE + '\x8d' # 0x09 -> SUPERSCRIPT + '\x8e' # 0x0A -> REPEAT + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x9d' # 0x14 -> RESTORE/ENABLE PRESENTATION + '\x85' # 0x15 -> NEW LINE + '\x08' # 0x16 -> BACKSPACE + '\x87' # 0x17 -> PROGRAM OPERATOR COMMUNICATION + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x92' # 0x1A -> UNIT BACK SPACE + '\x8f' # 0x1B -> CUSTOMER USE ONE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + '\x80' # 0x20 -> DIGIT SELECT + '\x81' # 0x21 -> START OF SIGNIFICANCE + '\x82' # 0x22 -> FIELD SEPARATOR + '\x83' # 0x23 -> WORD UNDERSCORE + '\x84' # 0x24 -> BYPASS OR INHIBIT PRESENTATION + '\n' # 0x25 -> LINE FEED + '\x17' # 0x26 -> END OF TRANSMISSION BLOCK + '\x1b' # 0x27 -> ESCAPE + '\x88' # 0x28 -> SET ATTRIBUTE + '\x89' # 0x29 -> START FIELD EXTENDED + '\x8a' # 0x2A -> SET MODE OR SWITCH + '\x8b' # 0x2B -> CONTROL SEQUENCE PREFIX + '\x8c' # 0x2C -> MODIFY FIELD ATTRIBUTE + '\x05' # 0x2D -> ENQUIRY + '\x06' # 0x2E -> ACKNOWLEDGE + '\x07' # 0x2F -> BELL + '\x90' # 0x30 -> <reserved> + '\x91' # 0x31 -> <reserved> + '\x16' # 0x32 -> SYNCHRONOUS IDLE + '\x93' # 0x33 -> INDEX RETURN + '\x94' # 0x34 -> PRESENTATION POSITION + '\x95' # 0x35 -> TRANSPARENT + '\x96' # 0x36 -> NUMERIC BACKSPACE + '\x04' # 0x37 -> END OF TRANSMISSION + '\x98' # 0x38 -> SUBSCRIPT + '\x99' # 0x39 -> INDENT TABULATION + '\x9a' # 0x3A -> REVERSE FORM FEED + '\x9b' # 0x3B -> CUSTOMER USE THREE + '\x14' # 0x3C -> DEVICE CONTROL FOUR + '\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE + '\x9e' # 0x3E -> <reserved> + '\x1a' # 0x3F -> SUBSTITUTE + ' ' # 0x40 -> SPACE + '\u05d0' # 0x41 -> HEBREW LETTER ALEF + '\u05d1' # 0x42 -> HEBREW LETTER BET + '\u05d2' # 0x43 -> HEBREW LETTER GIMEL + '\u05d3' # 0x44 -> HEBREW LETTER DALET + '\u05d4' # 0x45 -> HEBREW LETTER HE + '\u05d5' # 0x46 -> HEBREW LETTER VAV + '\u05d6' # 0x47 -> HEBREW LETTER ZAYIN + '\u05d7' # 0x48 -> HEBREW LETTER HET + '\u05d8' # 0x49 -> HEBREW LETTER TET + '\xa2' # 0x4A -> CENT SIGN + '.' # 0x4B -> FULL STOP + '<' # 0x4C -> LESS-THAN SIGN + '(' # 0x4D -> LEFT PARENTHESIS + '+' # 0x4E -> PLUS SIGN + '|' # 0x4F -> VERTICAL LINE + '&' # 0x50 -> AMPERSAND + '\u05d9' # 0x51 -> HEBREW LETTER YOD + '\u05da' # 0x52 -> HEBREW LETTER FINAL KAF + '\u05db' # 0x53 -> HEBREW LETTER KAF + '\u05dc' # 0x54 -> HEBREW LETTER LAMED + '\u05dd' # 0x55 -> HEBREW LETTER FINAL MEM + '\u05de' # 0x56 -> HEBREW LETTER MEM + '\u05df' # 0x57 -> HEBREW LETTER FINAL NUN + '\u05e0' # 0x58 -> HEBREW LETTER NUN + '\u05e1' # 0x59 -> HEBREW LETTER SAMEKH + '!' # 0x5A -> EXCLAMATION MARK + '$' # 0x5B -> DOLLAR SIGN + '*' # 0x5C -> ASTERISK + ')' # 0x5D -> RIGHT PARENTHESIS + ';' # 0x5E -> SEMICOLON + '\xac' # 0x5F -> NOT SIGN + '-' # 0x60 -> HYPHEN-MINUS + '/' # 0x61 -> SOLIDUS + '\u05e2' # 0x62 -> HEBREW LETTER AYIN + '\u05e3' # 0x63 -> HEBREW LETTER FINAL PE + '\u05e4' # 0x64 -> HEBREW LETTER PE + '\u05e5' # 0x65 -> HEBREW LETTER FINAL TSADI + '\u05e6' # 0x66 -> HEBREW LETTER TSADI + '\u05e7' # 0x67 -> HEBREW LETTER QOF + '\u05e8' # 0x68 -> HEBREW LETTER RESH + '\u05e9' # 0x69 -> HEBREW LETTER SHIN + '\xa6' # 0x6A -> BROKEN BAR + ',' # 0x6B -> COMMA + '%' # 0x6C -> PERCENT SIGN + '_' # 0x6D -> LOW LINE + '>' # 0x6E -> GREATER-THAN SIGN + '?' # 0x6F -> QUESTION MARK + '\ufffe' # 0x70 -> UNDEFINED + '\u05ea' # 0x71 -> HEBREW LETTER TAV + '\ufffe' # 0x72 -> UNDEFINED + '\ufffe' # 0x73 -> UNDEFINED + '\xa0' # 0x74 -> NO-BREAK SPACE + '\ufffe' # 0x75 -> UNDEFINED + '\ufffe' # 0x76 -> UNDEFINED + '\ufffe' # 0x77 -> UNDEFINED + '\u2017' # 0x78 -> DOUBLE LOW LINE + '`' # 0x79 -> GRAVE ACCENT + ':' # 0x7A -> COLON + '#' # 0x7B -> NUMBER SIGN + '@' # 0x7C -> COMMERCIAL AT + "'" # 0x7D -> APOSTROPHE + '=' # 0x7E -> EQUALS SIGN + '"' # 0x7F -> QUOTATION MARK + '\ufffe' # 0x80 -> UNDEFINED + 'a' # 0x81 -> LATIN SMALL LETTER A + 'b' # 0x82 -> LATIN SMALL LETTER B + 'c' # 0x83 -> LATIN SMALL LETTER C + 'd' # 0x84 -> LATIN SMALL LETTER D + 'e' # 0x85 -> LATIN SMALL LETTER E + 'f' # 0x86 -> LATIN SMALL LETTER F + 'g' # 0x87 -> LATIN SMALL LETTER G + 'h' # 0x88 -> LATIN SMALL LETTER H + 'i' # 0x89 -> LATIN SMALL LETTER I + '\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\ufffe' # 0x8C -> UNDEFINED + '\ufffe' # 0x8D -> UNDEFINED + '\ufffe' # 0x8E -> UNDEFINED + '\xb1' # 0x8F -> PLUS-MINUS SIGN + '\xb0' # 0x90 -> DEGREE SIGN + 'j' # 0x91 -> LATIN SMALL LETTER J + 'k' # 0x92 -> LATIN SMALL LETTER K + 'l' # 0x93 -> LATIN SMALL LETTER L + 'm' # 0x94 -> LATIN SMALL LETTER M + 'n' # 0x95 -> LATIN SMALL LETTER N + 'o' # 0x96 -> LATIN SMALL LETTER O + 'p' # 0x97 -> LATIN SMALL LETTER P + 'q' # 0x98 -> LATIN SMALL LETTER Q + 'r' # 0x99 -> LATIN SMALL LETTER R + '\ufffe' # 0x9A -> UNDEFINED + '\ufffe' # 0x9B -> UNDEFINED + '\ufffe' # 0x9C -> UNDEFINED + '\xb8' # 0x9D -> CEDILLA + '\ufffe' # 0x9E -> UNDEFINED + '\xa4' # 0x9F -> CURRENCY SIGN + '\xb5' # 0xA0 -> MICRO SIGN + '~' # 0xA1 -> TILDE + 's' # 0xA2 -> LATIN SMALL LETTER S + 't' # 0xA3 -> LATIN SMALL LETTER T + 'u' # 0xA4 -> LATIN SMALL LETTER U + 'v' # 0xA5 -> LATIN SMALL LETTER V + 'w' # 0xA6 -> LATIN SMALL LETTER W + 'x' # 0xA7 -> LATIN SMALL LETTER X + 'y' # 0xA8 -> LATIN SMALL LETTER Y + 'z' # 0xA9 -> LATIN SMALL LETTER Z + '\ufffe' # 0xAA -> UNDEFINED + '\ufffe' # 0xAB -> UNDEFINED + '\ufffe' # 0xAC -> UNDEFINED + '\ufffe' # 0xAD -> UNDEFINED + '\ufffe' # 0xAE -> UNDEFINED + '\xae' # 0xAF -> REGISTERED SIGN + '^' # 0xB0 -> CIRCUMFLEX ACCENT + '\xa3' # 0xB1 -> POUND SIGN + '\xa5' # 0xB2 -> YEN SIGN + '\xb7' # 0xB3 -> MIDDLE DOT + '\xa9' # 0xB4 -> COPYRIGHT SIGN + '\xa7' # 0xB5 -> SECTION SIGN + '\xb6' # 0xB6 -> PILCROW SIGN + '\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER + '\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF + '\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS + '[' # 0xBA -> LEFT SQUARE BRACKET + ']' # 0xBB -> RIGHT SQUARE BRACKET + '\xaf' # 0xBC -> MACRON + '\xa8' # 0xBD -> DIAERESIS + '\xb4' # 0xBE -> ACUTE ACCENT + '\xd7' # 0xBF -> MULTIPLICATION SIGN + '{' # 0xC0 -> LEFT CURLY BRACKET + 'A' # 0xC1 -> LATIN CAPITAL LETTER A + 'B' # 0xC2 -> LATIN CAPITAL LETTER B + 'C' # 0xC3 -> LATIN CAPITAL LETTER C + 'D' # 0xC4 -> LATIN CAPITAL LETTER D + 'E' # 0xC5 -> LATIN CAPITAL LETTER E + 'F' # 0xC6 -> LATIN CAPITAL LETTER F + 'G' # 0xC7 -> LATIN CAPITAL LETTER G + 'H' # 0xC8 -> LATIN CAPITAL LETTER H + 'I' # 0xC9 -> LATIN CAPITAL LETTER I + '\xad' # 0xCA -> SOFT HYPHEN + '\ufffe' # 0xCB -> UNDEFINED + '\ufffe' # 0xCC -> UNDEFINED + '\ufffe' # 0xCD -> UNDEFINED + '\ufffe' # 0xCE -> UNDEFINED + '\ufffe' # 0xCF -> UNDEFINED + '}' # 0xD0 -> RIGHT CURLY BRACKET + 'J' # 0xD1 -> LATIN CAPITAL LETTER J + 'K' # 0xD2 -> LATIN CAPITAL LETTER K + 'L' # 0xD3 -> LATIN CAPITAL LETTER L + 'M' # 0xD4 -> LATIN CAPITAL LETTER M + 'N' # 0xD5 -> LATIN CAPITAL LETTER N + 'O' # 0xD6 -> LATIN CAPITAL LETTER O + 'P' # 0xD7 -> LATIN CAPITAL LETTER P + 'Q' # 0xD8 -> LATIN CAPITAL LETTER Q + 'R' # 0xD9 -> LATIN CAPITAL LETTER R + '\xb9' # 0xDA -> SUPERSCRIPT ONE + '\ufffe' # 0xDB -> UNDEFINED + '\ufffe' # 0xDC -> UNDEFINED + '\ufffe' # 0xDD -> UNDEFINED + '\ufffe' # 0xDE -> UNDEFINED + '\ufffe' # 0xDF -> UNDEFINED + '\\' # 0xE0 -> REVERSE SOLIDUS + '\xf7' # 0xE1 -> DIVISION SIGN + 'S' # 0xE2 -> LATIN CAPITAL LETTER S + 'T' # 0xE3 -> LATIN CAPITAL LETTER T + 'U' # 0xE4 -> LATIN CAPITAL LETTER U + 'V' # 0xE5 -> LATIN CAPITAL LETTER V + 'W' # 0xE6 -> LATIN CAPITAL LETTER W + 'X' # 0xE7 -> LATIN CAPITAL LETTER X + 'Y' # 0xE8 -> LATIN CAPITAL LETTER Y + 'Z' # 0xE9 -> LATIN CAPITAL LETTER Z + '\xb2' # 0xEA -> SUPERSCRIPT TWO + '\ufffe' # 0xEB -> UNDEFINED + '\ufffe' # 0xEC -> UNDEFINED + '\ufffe' # 0xED -> UNDEFINED + '\ufffe' # 0xEE -> UNDEFINED + '\ufffe' # 0xEF -> UNDEFINED + '0' # 0xF0 -> DIGIT ZERO + '1' # 0xF1 -> DIGIT ONE + '2' # 0xF2 -> DIGIT TWO + '3' # 0xF3 -> DIGIT THREE + '4' # 0xF4 -> DIGIT FOUR + '5' # 0xF5 -> DIGIT FIVE + '6' # 0xF6 -> DIGIT SIX + '7' # 0xF7 -> DIGIT SEVEN + '8' # 0xF8 -> DIGIT EIGHT + '9' # 0xF9 -> DIGIT NINE + '\xb3' # 0xFA -> SUPERSCRIPT THREE + '\ufffe' # 0xFB -> UNDEFINED + '\ufffe' # 0xFC -> UNDEFINED + '\ufffe' # 0xFD -> UNDEFINED + '\ufffe' # 0xFE -> UNDEFINED + '\x9f' # 0xFF -> EIGHT ONES +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/cp437.py b/contrib/tools/python3/src/Lib/encodings/cp437.py new file mode 100644 index 0000000000..b6c75e2ca1 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp437.py @@ -0,0 +1,698 @@ +""" Python Character Mapping Codec cp437 generated from 'VENDORS/MICSFT/PC/CP437.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_map) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp437', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + +### Decoding Map + +decoding_map = codecs.make_identity_dict(range(256)) +decoding_map.update({ + 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS + 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE + 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE + 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE + 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA + 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS + 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE + 0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS + 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x008d: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE + 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE + 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE + 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE + 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE + 0x0098: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x009b: 0x00a2, # CENT SIGN + 0x009c: 0x00a3, # POUND SIGN + 0x009d: 0x00a5, # YEN SIGN + 0x009e: 0x20a7, # PESETA SIGN + 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK + 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE + 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE + 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE + 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE + 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE + 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE + 0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR + 0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR + 0x00a8: 0x00bf, # INVERTED QUESTION MARK + 0x00a9: 0x2310, # REVERSED NOT SIGN + 0x00aa: 0x00ac, # NOT SIGN + 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF + 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER + 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK + 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00b0: 0x2591, # LIGHT SHADE + 0x00b1: 0x2592, # MEDIUM SHADE + 0x00b2: 0x2593, # DARK SHADE + 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL + 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL + 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL + 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT + 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x00db: 0x2588, # FULL BLOCK + 0x00dc: 0x2584, # LOWER HALF BLOCK + 0x00dd: 0x258c, # LEFT HALF BLOCK + 0x00de: 0x2590, # RIGHT HALF BLOCK + 0x00df: 0x2580, # UPPER HALF BLOCK + 0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA + 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S + 0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA + 0x00e3: 0x03c0, # GREEK SMALL LETTER PI + 0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA + 0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA + 0x00e6: 0x00b5, # MICRO SIGN + 0x00e7: 0x03c4, # GREEK SMALL LETTER TAU + 0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI + 0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA + 0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA + 0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA + 0x00ec: 0x221e, # INFINITY + 0x00ed: 0x03c6, # GREEK SMALL LETTER PHI + 0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON + 0x00ef: 0x2229, # INTERSECTION + 0x00f0: 0x2261, # IDENTICAL TO + 0x00f1: 0x00b1, # PLUS-MINUS SIGN + 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO + 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO + 0x00f4: 0x2320, # TOP HALF INTEGRAL + 0x00f5: 0x2321, # BOTTOM HALF INTEGRAL + 0x00f6: 0x00f7, # DIVISION SIGN + 0x00f7: 0x2248, # ALMOST EQUAL TO + 0x00f8: 0x00b0, # DEGREE SIGN + 0x00f9: 0x2219, # BULLET OPERATOR + 0x00fa: 0x00b7, # MIDDLE DOT + 0x00fb: 0x221a, # SQUARE ROOT + 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N + 0x00fd: 0x00b2, # SUPERSCRIPT TWO + 0x00fe: 0x25a0, # BLACK SQUARE + 0x00ff: 0x00a0, # NO-BREAK SPACE +}) + +### Decoding Table + +decoding_table = ( + '\x00' # 0x0000 -> NULL + '\x01' # 0x0001 -> START OF HEADING + '\x02' # 0x0002 -> START OF TEXT + '\x03' # 0x0003 -> END OF TEXT + '\x04' # 0x0004 -> END OF TRANSMISSION + '\x05' # 0x0005 -> ENQUIRY + '\x06' # 0x0006 -> ACKNOWLEDGE + '\x07' # 0x0007 -> BELL + '\x08' # 0x0008 -> BACKSPACE + '\t' # 0x0009 -> HORIZONTAL TABULATION + '\n' # 0x000a -> LINE FEED + '\x0b' # 0x000b -> VERTICAL TABULATION + '\x0c' # 0x000c -> FORM FEED + '\r' # 0x000d -> CARRIAGE RETURN + '\x0e' # 0x000e -> SHIFT OUT + '\x0f' # 0x000f -> SHIFT IN + '\x10' # 0x0010 -> DATA LINK ESCAPE + '\x11' # 0x0011 -> DEVICE CONTROL ONE + '\x12' # 0x0012 -> DEVICE CONTROL TWO + '\x13' # 0x0013 -> DEVICE CONTROL THREE + '\x14' # 0x0014 -> DEVICE CONTROL FOUR + '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x0016 -> SYNCHRONOUS IDLE + '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK + '\x18' # 0x0018 -> CANCEL + '\x19' # 0x0019 -> END OF MEDIUM + '\x1a' # 0x001a -> SUBSTITUTE + '\x1b' # 0x001b -> ESCAPE + '\x1c' # 0x001c -> FILE SEPARATOR + '\x1d' # 0x001d -> GROUP SEPARATOR + '\x1e' # 0x001e -> RECORD SEPARATOR + '\x1f' # 0x001f -> UNIT SEPARATOR + ' ' # 0x0020 -> SPACE + '!' # 0x0021 -> EXCLAMATION MARK + '"' # 0x0022 -> QUOTATION MARK + '#' # 0x0023 -> NUMBER SIGN + '$' # 0x0024 -> DOLLAR SIGN + '%' # 0x0025 -> PERCENT SIGN + '&' # 0x0026 -> AMPERSAND + "'" # 0x0027 -> APOSTROPHE + '(' # 0x0028 -> LEFT PARENTHESIS + ')' # 0x0029 -> RIGHT PARENTHESIS + '*' # 0x002a -> ASTERISK + '+' # 0x002b -> PLUS SIGN + ',' # 0x002c -> COMMA + '-' # 0x002d -> HYPHEN-MINUS + '.' # 0x002e -> FULL STOP + '/' # 0x002f -> SOLIDUS + '0' # 0x0030 -> DIGIT ZERO + '1' # 0x0031 -> DIGIT ONE + '2' # 0x0032 -> DIGIT TWO + '3' # 0x0033 -> DIGIT THREE + '4' # 0x0034 -> DIGIT FOUR + '5' # 0x0035 -> DIGIT FIVE + '6' # 0x0036 -> DIGIT SIX + '7' # 0x0037 -> DIGIT SEVEN + '8' # 0x0038 -> DIGIT EIGHT + '9' # 0x0039 -> DIGIT NINE + ':' # 0x003a -> COLON + ';' # 0x003b -> SEMICOLON + '<' # 0x003c -> LESS-THAN SIGN + '=' # 0x003d -> EQUALS SIGN + '>' # 0x003e -> GREATER-THAN SIGN + '?' # 0x003f -> QUESTION MARK + '@' # 0x0040 -> COMMERCIAL AT + 'A' # 0x0041 -> LATIN CAPITAL LETTER A + 'B' # 0x0042 -> LATIN CAPITAL LETTER B + 'C' # 0x0043 -> LATIN CAPITAL LETTER C + 'D' # 0x0044 -> LATIN CAPITAL LETTER D + 'E' # 0x0045 -> LATIN CAPITAL LETTER E + 'F' # 0x0046 -> LATIN CAPITAL LETTER F + 'G' # 0x0047 -> LATIN CAPITAL LETTER G + 'H' # 0x0048 -> LATIN CAPITAL LETTER H + 'I' # 0x0049 -> LATIN CAPITAL LETTER I + 'J' # 0x004a -> LATIN CAPITAL LETTER J + 'K' # 0x004b -> LATIN CAPITAL LETTER K + 'L' # 0x004c -> LATIN CAPITAL LETTER L + 'M' # 0x004d -> LATIN CAPITAL LETTER M + 'N' # 0x004e -> LATIN CAPITAL LETTER N + 'O' # 0x004f -> LATIN CAPITAL LETTER O + 'P' # 0x0050 -> LATIN CAPITAL LETTER P + 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q + 'R' # 0x0052 -> LATIN CAPITAL LETTER R + 'S' # 0x0053 -> LATIN CAPITAL LETTER S + 'T' # 0x0054 -> LATIN CAPITAL LETTER T + 'U' # 0x0055 -> LATIN CAPITAL LETTER U + 'V' # 0x0056 -> LATIN CAPITAL LETTER V + 'W' # 0x0057 -> LATIN CAPITAL LETTER W + 'X' # 0x0058 -> LATIN CAPITAL LETTER X + 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y + 'Z' # 0x005a -> LATIN CAPITAL LETTER Z + '[' # 0x005b -> LEFT SQUARE BRACKET + '\\' # 0x005c -> REVERSE SOLIDUS + ']' # 0x005d -> RIGHT SQUARE BRACKET + '^' # 0x005e -> CIRCUMFLEX ACCENT + '_' # 0x005f -> LOW LINE + '`' # 0x0060 -> GRAVE ACCENT + 'a' # 0x0061 -> LATIN SMALL LETTER A + 'b' # 0x0062 -> LATIN SMALL LETTER B + 'c' # 0x0063 -> LATIN SMALL LETTER C + 'd' # 0x0064 -> LATIN SMALL LETTER D + 'e' # 0x0065 -> LATIN SMALL LETTER E + 'f' # 0x0066 -> LATIN SMALL LETTER F + 'g' # 0x0067 -> LATIN SMALL LETTER G + 'h' # 0x0068 -> LATIN SMALL LETTER H + 'i' # 0x0069 -> LATIN SMALL LETTER I + 'j' # 0x006a -> LATIN SMALL LETTER J + 'k' # 0x006b -> LATIN SMALL LETTER K + 'l' # 0x006c -> LATIN SMALL LETTER L + 'm' # 0x006d -> LATIN SMALL LETTER M + 'n' # 0x006e -> LATIN SMALL LETTER N + 'o' # 0x006f -> LATIN SMALL LETTER O + 'p' # 0x0070 -> LATIN SMALL LETTER P + 'q' # 0x0071 -> LATIN SMALL LETTER Q + 'r' # 0x0072 -> LATIN SMALL LETTER R + 's' # 0x0073 -> LATIN SMALL LETTER S + 't' # 0x0074 -> LATIN SMALL LETTER T + 'u' # 0x0075 -> LATIN SMALL LETTER U + 'v' # 0x0076 -> LATIN SMALL LETTER V + 'w' # 0x0077 -> LATIN SMALL LETTER W + 'x' # 0x0078 -> LATIN SMALL LETTER X + 'y' # 0x0079 -> LATIN SMALL LETTER Y + 'z' # 0x007a -> LATIN SMALL LETTER Z + '{' # 0x007b -> LEFT CURLY BRACKET + '|' # 0x007c -> VERTICAL LINE + '}' # 0x007d -> RIGHT CURLY BRACKET + '~' # 0x007e -> TILDE + '\x7f' # 0x007f -> DELETE + '\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS + '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE + '\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE + '\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA + '\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS + '\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE + '\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS + '\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xec' # 0x008d -> LATIN SMALL LETTER I WITH GRAVE + '\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE + '\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE + '\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE + '\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE + '\xff' # 0x0098 -> LATIN SMALL LETTER Y WITH DIAERESIS + '\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xa2' # 0x009b -> CENT SIGN + '\xa3' # 0x009c -> POUND SIGN + '\xa5' # 0x009d -> YEN SIGN + '\u20a7' # 0x009e -> PESETA SIGN + '\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK + '\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE + '\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE + '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE + '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE + '\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE + '\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE + '\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR + '\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR + '\xbf' # 0x00a8 -> INVERTED QUESTION MARK + '\u2310' # 0x00a9 -> REVERSED NOT SIGN + '\xac' # 0x00aa -> NOT SIGN + '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF + '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER + '\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK + '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u2591' # 0x00b0 -> LIGHT SHADE + '\u2592' # 0x00b1 -> MEDIUM SHADE + '\u2593' # 0x00b2 -> DARK SHADE + '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL + '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT + '\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + '\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + '\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + '\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL + '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT + '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT + '\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + '\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT + '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT + '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL + '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT + '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL + '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + '\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + '\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT + '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL + '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + '\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + '\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + '\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + '\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + '\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + '\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + '\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + '\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + '\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + '\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT + '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT + '\u2588' # 0x00db -> FULL BLOCK + '\u2584' # 0x00dc -> LOWER HALF BLOCK + '\u258c' # 0x00dd -> LEFT HALF BLOCK + '\u2590' # 0x00de -> RIGHT HALF BLOCK + '\u2580' # 0x00df -> UPPER HALF BLOCK + '\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA + '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S + '\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA + '\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI + '\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA + '\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA + '\xb5' # 0x00e6 -> MICRO SIGN + '\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU + '\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI + '\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA + '\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA + '\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA + '\u221e' # 0x00ec -> INFINITY + '\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI + '\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON + '\u2229' # 0x00ef -> INTERSECTION + '\u2261' # 0x00f0 -> IDENTICAL TO + '\xb1' # 0x00f1 -> PLUS-MINUS SIGN + '\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO + '\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO + '\u2320' # 0x00f4 -> TOP HALF INTEGRAL + '\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL + '\xf7' # 0x00f6 -> DIVISION SIGN + '\u2248' # 0x00f7 -> ALMOST EQUAL TO + '\xb0' # 0x00f8 -> DEGREE SIGN + '\u2219' # 0x00f9 -> BULLET OPERATOR + '\xb7' # 0x00fa -> MIDDLE DOT + '\u221a' # 0x00fb -> SQUARE ROOT + '\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N + '\xb2' # 0x00fd -> SUPERSCRIPT TWO + '\u25a0' # 0x00fe -> BLACK SQUARE + '\xa0' # 0x00ff -> NO-BREAK SPACE +) + +### Encoding Map + +encoding_map = { + 0x0000: 0x0000, # NULL + 0x0001: 0x0001, # START OF HEADING + 0x0002: 0x0002, # START OF TEXT + 0x0003: 0x0003, # END OF TEXT + 0x0004: 0x0004, # END OF TRANSMISSION + 0x0005: 0x0005, # ENQUIRY + 0x0006: 0x0006, # ACKNOWLEDGE + 0x0007: 0x0007, # BELL + 0x0008: 0x0008, # BACKSPACE + 0x0009: 0x0009, # HORIZONTAL TABULATION + 0x000a: 0x000a, # LINE FEED + 0x000b: 0x000b, # VERTICAL TABULATION + 0x000c: 0x000c, # FORM FEED + 0x000d: 0x000d, # CARRIAGE RETURN + 0x000e: 0x000e, # SHIFT OUT + 0x000f: 0x000f, # SHIFT IN + 0x0010: 0x0010, # DATA LINK ESCAPE + 0x0011: 0x0011, # DEVICE CONTROL ONE + 0x0012: 0x0012, # DEVICE CONTROL TWO + 0x0013: 0x0013, # DEVICE CONTROL THREE + 0x0014: 0x0014, # DEVICE CONTROL FOUR + 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE + 0x0016: 0x0016, # SYNCHRONOUS IDLE + 0x0017: 0x0017, # END OF TRANSMISSION BLOCK + 0x0018: 0x0018, # CANCEL + 0x0019: 0x0019, # END OF MEDIUM + 0x001a: 0x001a, # SUBSTITUTE + 0x001b: 0x001b, # ESCAPE + 0x001c: 0x001c, # FILE SEPARATOR + 0x001d: 0x001d, # GROUP SEPARATOR + 0x001e: 0x001e, # RECORD SEPARATOR + 0x001f: 0x001f, # UNIT SEPARATOR + 0x0020: 0x0020, # SPACE + 0x0021: 0x0021, # EXCLAMATION MARK + 0x0022: 0x0022, # QUOTATION MARK + 0x0023: 0x0023, # NUMBER SIGN + 0x0024: 0x0024, # DOLLAR SIGN + 0x0025: 0x0025, # PERCENT SIGN + 0x0026: 0x0026, # AMPERSAND + 0x0027: 0x0027, # APOSTROPHE + 0x0028: 0x0028, # LEFT PARENTHESIS + 0x0029: 0x0029, # RIGHT PARENTHESIS + 0x002a: 0x002a, # ASTERISK + 0x002b: 0x002b, # PLUS SIGN + 0x002c: 0x002c, # COMMA + 0x002d: 0x002d, # HYPHEN-MINUS + 0x002e: 0x002e, # FULL STOP + 0x002f: 0x002f, # SOLIDUS + 0x0030: 0x0030, # DIGIT ZERO + 0x0031: 0x0031, # DIGIT ONE + 0x0032: 0x0032, # DIGIT TWO + 0x0033: 0x0033, # DIGIT THREE + 0x0034: 0x0034, # DIGIT FOUR + 0x0035: 0x0035, # DIGIT FIVE + 0x0036: 0x0036, # DIGIT SIX + 0x0037: 0x0037, # DIGIT SEVEN + 0x0038: 0x0038, # DIGIT EIGHT + 0x0039: 0x0039, # DIGIT NINE + 0x003a: 0x003a, # COLON + 0x003b: 0x003b, # SEMICOLON + 0x003c: 0x003c, # LESS-THAN SIGN + 0x003d: 0x003d, # EQUALS SIGN + 0x003e: 0x003e, # GREATER-THAN SIGN + 0x003f: 0x003f, # QUESTION MARK + 0x0040: 0x0040, # COMMERCIAL AT + 0x0041: 0x0041, # LATIN CAPITAL LETTER A + 0x0042: 0x0042, # LATIN CAPITAL LETTER B + 0x0043: 0x0043, # LATIN CAPITAL LETTER C + 0x0044: 0x0044, # LATIN CAPITAL LETTER D + 0x0045: 0x0045, # LATIN CAPITAL LETTER E + 0x0046: 0x0046, # LATIN CAPITAL LETTER F + 0x0047: 0x0047, # LATIN CAPITAL LETTER G + 0x0048: 0x0048, # LATIN CAPITAL LETTER H + 0x0049: 0x0049, # LATIN CAPITAL LETTER I + 0x004a: 0x004a, # LATIN CAPITAL LETTER J + 0x004b: 0x004b, # LATIN CAPITAL LETTER K + 0x004c: 0x004c, # LATIN CAPITAL LETTER L + 0x004d: 0x004d, # LATIN CAPITAL LETTER M + 0x004e: 0x004e, # LATIN CAPITAL LETTER N + 0x004f: 0x004f, # LATIN CAPITAL LETTER O + 0x0050: 0x0050, # LATIN CAPITAL LETTER P + 0x0051: 0x0051, # LATIN CAPITAL LETTER Q + 0x0052: 0x0052, # LATIN CAPITAL LETTER R + 0x0053: 0x0053, # LATIN CAPITAL LETTER S + 0x0054: 0x0054, # LATIN CAPITAL LETTER T + 0x0055: 0x0055, # LATIN CAPITAL LETTER U + 0x0056: 0x0056, # LATIN CAPITAL LETTER V + 0x0057: 0x0057, # LATIN CAPITAL LETTER W + 0x0058: 0x0058, # LATIN CAPITAL LETTER X + 0x0059: 0x0059, # LATIN CAPITAL LETTER Y + 0x005a: 0x005a, # LATIN CAPITAL LETTER Z + 0x005b: 0x005b, # LEFT SQUARE BRACKET + 0x005c: 0x005c, # REVERSE SOLIDUS + 0x005d: 0x005d, # RIGHT SQUARE BRACKET + 0x005e: 0x005e, # CIRCUMFLEX ACCENT + 0x005f: 0x005f, # LOW LINE + 0x0060: 0x0060, # GRAVE ACCENT + 0x0061: 0x0061, # LATIN SMALL LETTER A + 0x0062: 0x0062, # LATIN SMALL LETTER B + 0x0063: 0x0063, # LATIN SMALL LETTER C + 0x0064: 0x0064, # LATIN SMALL LETTER D + 0x0065: 0x0065, # LATIN SMALL LETTER E + 0x0066: 0x0066, # LATIN SMALL LETTER F + 0x0067: 0x0067, # LATIN SMALL LETTER G + 0x0068: 0x0068, # LATIN SMALL LETTER H + 0x0069: 0x0069, # LATIN SMALL LETTER I + 0x006a: 0x006a, # LATIN SMALL LETTER J + 0x006b: 0x006b, # LATIN SMALL LETTER K + 0x006c: 0x006c, # LATIN SMALL LETTER L + 0x006d: 0x006d, # LATIN SMALL LETTER M + 0x006e: 0x006e, # LATIN SMALL LETTER N + 0x006f: 0x006f, # LATIN SMALL LETTER O + 0x0070: 0x0070, # LATIN SMALL LETTER P + 0x0071: 0x0071, # LATIN SMALL LETTER Q + 0x0072: 0x0072, # LATIN SMALL LETTER R + 0x0073: 0x0073, # LATIN SMALL LETTER S + 0x0074: 0x0074, # LATIN SMALL LETTER T + 0x0075: 0x0075, # LATIN SMALL LETTER U + 0x0076: 0x0076, # LATIN SMALL LETTER V + 0x0077: 0x0077, # LATIN SMALL LETTER W + 0x0078: 0x0078, # LATIN SMALL LETTER X + 0x0079: 0x0079, # LATIN SMALL LETTER Y + 0x007a: 0x007a, # LATIN SMALL LETTER Z + 0x007b: 0x007b, # LEFT CURLY BRACKET + 0x007c: 0x007c, # VERTICAL LINE + 0x007d: 0x007d, # RIGHT CURLY BRACKET + 0x007e: 0x007e, # TILDE + 0x007f: 0x007f, # DELETE + 0x00a0: 0x00ff, # NO-BREAK SPACE + 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK + 0x00a2: 0x009b, # CENT SIGN + 0x00a3: 0x009c, # POUND SIGN + 0x00a5: 0x009d, # YEN SIGN + 0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR + 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00ac: 0x00aa, # NOT SIGN + 0x00b0: 0x00f8, # DEGREE SIGN + 0x00b1: 0x00f1, # PLUS-MINUS SIGN + 0x00b2: 0x00fd, # SUPERSCRIPT TWO + 0x00b5: 0x00e6, # MICRO SIGN + 0x00b7: 0x00fa, # MIDDLE DOT + 0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR + 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER + 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF + 0x00bf: 0x00a8, # INVERTED QUESTION MARK + 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE + 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE + 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S + 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE + 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE + 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE + 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA + 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE + 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE + 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00ec: 0x008d, # LATIN SMALL LETTER I WITH GRAVE + 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE + 0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE + 0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE + 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE + 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00f7: 0x00f6, # DIVISION SIGN + 0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE + 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE + 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00ff: 0x0098, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK + 0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA + 0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA + 0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA + 0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI + 0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA + 0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA + 0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA + 0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON + 0x03c0: 0x00e3, # GREEK SMALL LETTER PI + 0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA + 0x03c4: 0x00e7, # GREEK SMALL LETTER TAU + 0x03c6: 0x00ed, # GREEK SMALL LETTER PHI + 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N + 0x20a7: 0x009e, # PESETA SIGN + 0x2219: 0x00f9, # BULLET OPERATOR + 0x221a: 0x00fb, # SQUARE ROOT + 0x221e: 0x00ec, # INFINITY + 0x2229: 0x00ef, # INTERSECTION + 0x2248: 0x00f7, # ALMOST EQUAL TO + 0x2261: 0x00f0, # IDENTICAL TO + 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO + 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO + 0x2310: 0x00a9, # REVERSED NOT SIGN + 0x2320: 0x00f4, # TOP HALF INTEGRAL + 0x2321: 0x00f5, # BOTTOM HALF INTEGRAL + 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL + 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL + 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT + 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL + 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x2580: 0x00df, # UPPER HALF BLOCK + 0x2584: 0x00dc, # LOWER HALF BLOCK + 0x2588: 0x00db, # FULL BLOCK + 0x258c: 0x00dd, # LEFT HALF BLOCK + 0x2590: 0x00de, # RIGHT HALF BLOCK + 0x2591: 0x00b0, # LIGHT SHADE + 0x2592: 0x00b1, # MEDIUM SHADE + 0x2593: 0x00b2, # DARK SHADE + 0x25a0: 0x00fe, # BLACK SQUARE +} diff --git a/contrib/tools/python3/src/Lib/encodings/cp500.py b/contrib/tools/python3/src/Lib/encodings/cp500.py new file mode 100644 index 0000000000..5f61535f82 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp500.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec cp500 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP500.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp500', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x9c' # 0x04 -> CONTROL + '\t' # 0x05 -> HORIZONTAL TABULATION + '\x86' # 0x06 -> CONTROL + '\x7f' # 0x07 -> DELETE + '\x97' # 0x08 -> CONTROL + '\x8d' # 0x09 -> CONTROL + '\x8e' # 0x0A -> CONTROL + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x9d' # 0x14 -> CONTROL + '\x85' # 0x15 -> CONTROL + '\x08' # 0x16 -> BACKSPACE + '\x87' # 0x17 -> CONTROL + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x92' # 0x1A -> CONTROL + '\x8f' # 0x1B -> CONTROL + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + '\x80' # 0x20 -> CONTROL + '\x81' # 0x21 -> CONTROL + '\x82' # 0x22 -> CONTROL + '\x83' # 0x23 -> CONTROL + '\x84' # 0x24 -> CONTROL + '\n' # 0x25 -> LINE FEED + '\x17' # 0x26 -> END OF TRANSMISSION BLOCK + '\x1b' # 0x27 -> ESCAPE + '\x88' # 0x28 -> CONTROL + '\x89' # 0x29 -> CONTROL + '\x8a' # 0x2A -> CONTROL + '\x8b' # 0x2B -> CONTROL + '\x8c' # 0x2C -> CONTROL + '\x05' # 0x2D -> ENQUIRY + '\x06' # 0x2E -> ACKNOWLEDGE + '\x07' # 0x2F -> BELL + '\x90' # 0x30 -> CONTROL + '\x91' # 0x31 -> CONTROL + '\x16' # 0x32 -> SYNCHRONOUS IDLE + '\x93' # 0x33 -> CONTROL + '\x94' # 0x34 -> CONTROL + '\x95' # 0x35 -> CONTROL + '\x96' # 0x36 -> CONTROL + '\x04' # 0x37 -> END OF TRANSMISSION + '\x98' # 0x38 -> CONTROL + '\x99' # 0x39 -> CONTROL + '\x9a' # 0x3A -> CONTROL + '\x9b' # 0x3B -> CONTROL + '\x14' # 0x3C -> DEVICE CONTROL FOUR + '\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE + '\x9e' # 0x3E -> CONTROL + '\x1a' # 0x3F -> SUBSTITUTE + ' ' # 0x40 -> SPACE + '\xa0' # 0x41 -> NO-BREAK SPACE + '\xe2' # 0x42 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe4' # 0x43 -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe0' # 0x44 -> LATIN SMALL LETTER A WITH GRAVE + '\xe1' # 0x45 -> LATIN SMALL LETTER A WITH ACUTE + '\xe3' # 0x46 -> LATIN SMALL LETTER A WITH TILDE + '\xe5' # 0x47 -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe7' # 0x48 -> LATIN SMALL LETTER C WITH CEDILLA + '\xf1' # 0x49 -> LATIN SMALL LETTER N WITH TILDE + '[' # 0x4A -> LEFT SQUARE BRACKET + '.' # 0x4B -> FULL STOP + '<' # 0x4C -> LESS-THAN SIGN + '(' # 0x4D -> LEFT PARENTHESIS + '+' # 0x4E -> PLUS SIGN + '!' # 0x4F -> EXCLAMATION MARK + '&' # 0x50 -> AMPERSAND + '\xe9' # 0x51 -> LATIN SMALL LETTER E WITH ACUTE + '\xea' # 0x52 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0x53 -> LATIN SMALL LETTER E WITH DIAERESIS + '\xe8' # 0x54 -> LATIN SMALL LETTER E WITH GRAVE + '\xed' # 0x55 -> LATIN SMALL LETTER I WITH ACUTE + '\xee' # 0x56 -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0x57 -> LATIN SMALL LETTER I WITH DIAERESIS + '\xec' # 0x58 -> LATIN SMALL LETTER I WITH GRAVE + '\xdf' # 0x59 -> LATIN SMALL LETTER SHARP S (GERMAN) + ']' # 0x5A -> RIGHT SQUARE BRACKET + '$' # 0x5B -> DOLLAR SIGN + '*' # 0x5C -> ASTERISK + ')' # 0x5D -> RIGHT PARENTHESIS + ';' # 0x5E -> SEMICOLON + '^' # 0x5F -> CIRCUMFLEX ACCENT + '-' # 0x60 -> HYPHEN-MINUS + '/' # 0x61 -> SOLIDUS + '\xc2' # 0x62 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xc4' # 0x63 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc0' # 0x64 -> LATIN CAPITAL LETTER A WITH GRAVE + '\xc1' # 0x65 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc3' # 0x66 -> LATIN CAPITAL LETTER A WITH TILDE + '\xc5' # 0x67 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc7' # 0x68 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xd1' # 0x69 -> LATIN CAPITAL LETTER N WITH TILDE + '\xa6' # 0x6A -> BROKEN BAR + ',' # 0x6B -> COMMA + '%' # 0x6C -> PERCENT SIGN + '_' # 0x6D -> LOW LINE + '>' # 0x6E -> GREATER-THAN SIGN + '?' # 0x6F -> QUESTION MARK + '\xf8' # 0x70 -> LATIN SMALL LETTER O WITH STROKE + '\xc9' # 0x71 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xca' # 0x72 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xcb' # 0x73 -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xc8' # 0x74 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xcd' # 0x75 -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0x76 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0x77 -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\xcc' # 0x78 -> LATIN CAPITAL LETTER I WITH GRAVE + '`' # 0x79 -> GRAVE ACCENT + ':' # 0x7A -> COLON + '#' # 0x7B -> NUMBER SIGN + '@' # 0x7C -> COMMERCIAL AT + "'" # 0x7D -> APOSTROPHE + '=' # 0x7E -> EQUALS SIGN + '"' # 0x7F -> QUOTATION MARK + '\xd8' # 0x80 -> LATIN CAPITAL LETTER O WITH STROKE + 'a' # 0x81 -> LATIN SMALL LETTER A + 'b' # 0x82 -> LATIN SMALL LETTER B + 'c' # 0x83 -> LATIN SMALL LETTER C + 'd' # 0x84 -> LATIN SMALL LETTER D + 'e' # 0x85 -> LATIN SMALL LETTER E + 'f' # 0x86 -> LATIN SMALL LETTER F + 'g' # 0x87 -> LATIN SMALL LETTER G + 'h' # 0x88 -> LATIN SMALL LETTER H + 'i' # 0x89 -> LATIN SMALL LETTER I + '\xab' # 0x8A -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0x8B -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xf0' # 0x8C -> LATIN SMALL LETTER ETH (ICELANDIC) + '\xfd' # 0x8D -> LATIN SMALL LETTER Y WITH ACUTE + '\xfe' # 0x8E -> LATIN SMALL LETTER THORN (ICELANDIC) + '\xb1' # 0x8F -> PLUS-MINUS SIGN + '\xb0' # 0x90 -> DEGREE SIGN + 'j' # 0x91 -> LATIN SMALL LETTER J + 'k' # 0x92 -> LATIN SMALL LETTER K + 'l' # 0x93 -> LATIN SMALL LETTER L + 'm' # 0x94 -> LATIN SMALL LETTER M + 'n' # 0x95 -> LATIN SMALL LETTER N + 'o' # 0x96 -> LATIN SMALL LETTER O + 'p' # 0x97 -> LATIN SMALL LETTER P + 'q' # 0x98 -> LATIN SMALL LETTER Q + 'r' # 0x99 -> LATIN SMALL LETTER R + '\xaa' # 0x9A -> FEMININE ORDINAL INDICATOR + '\xba' # 0x9B -> MASCULINE ORDINAL INDICATOR + '\xe6' # 0x9C -> LATIN SMALL LIGATURE AE + '\xb8' # 0x9D -> CEDILLA + '\xc6' # 0x9E -> LATIN CAPITAL LIGATURE AE + '\xa4' # 0x9F -> CURRENCY SIGN + '\xb5' # 0xA0 -> MICRO SIGN + '~' # 0xA1 -> TILDE + 's' # 0xA2 -> LATIN SMALL LETTER S + 't' # 0xA3 -> LATIN SMALL LETTER T + 'u' # 0xA4 -> LATIN SMALL LETTER U + 'v' # 0xA5 -> LATIN SMALL LETTER V + 'w' # 0xA6 -> LATIN SMALL LETTER W + 'x' # 0xA7 -> LATIN SMALL LETTER X + 'y' # 0xA8 -> LATIN SMALL LETTER Y + 'z' # 0xA9 -> LATIN SMALL LETTER Z + '\xa1' # 0xAA -> INVERTED EXCLAMATION MARK + '\xbf' # 0xAB -> INVERTED QUESTION MARK + '\xd0' # 0xAC -> LATIN CAPITAL LETTER ETH (ICELANDIC) + '\xdd' # 0xAD -> LATIN CAPITAL LETTER Y WITH ACUTE + '\xde' # 0xAE -> LATIN CAPITAL LETTER THORN (ICELANDIC) + '\xae' # 0xAF -> REGISTERED SIGN + '\xa2' # 0xB0 -> CENT SIGN + '\xa3' # 0xB1 -> POUND SIGN + '\xa5' # 0xB2 -> YEN SIGN + '\xb7' # 0xB3 -> MIDDLE DOT + '\xa9' # 0xB4 -> COPYRIGHT SIGN + '\xa7' # 0xB5 -> SECTION SIGN + '\xb6' # 0xB6 -> PILCROW SIGN + '\xbc' # 0xB7 -> VULGAR FRACTION ONE QUARTER + '\xbd' # 0xB8 -> VULGAR FRACTION ONE HALF + '\xbe' # 0xB9 -> VULGAR FRACTION THREE QUARTERS + '\xac' # 0xBA -> NOT SIGN + '|' # 0xBB -> VERTICAL LINE + '\xaf' # 0xBC -> MACRON + '\xa8' # 0xBD -> DIAERESIS + '\xb4' # 0xBE -> ACUTE ACCENT + '\xd7' # 0xBF -> MULTIPLICATION SIGN + '{' # 0xC0 -> LEFT CURLY BRACKET + 'A' # 0xC1 -> LATIN CAPITAL LETTER A + 'B' # 0xC2 -> LATIN CAPITAL LETTER B + 'C' # 0xC3 -> LATIN CAPITAL LETTER C + 'D' # 0xC4 -> LATIN CAPITAL LETTER D + 'E' # 0xC5 -> LATIN CAPITAL LETTER E + 'F' # 0xC6 -> LATIN CAPITAL LETTER F + 'G' # 0xC7 -> LATIN CAPITAL LETTER G + 'H' # 0xC8 -> LATIN CAPITAL LETTER H + 'I' # 0xC9 -> LATIN CAPITAL LETTER I + '\xad' # 0xCA -> SOFT HYPHEN + '\xf4' # 0xCB -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf6' # 0xCC -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf2' # 0xCD -> LATIN SMALL LETTER O WITH GRAVE + '\xf3' # 0xCE -> LATIN SMALL LETTER O WITH ACUTE + '\xf5' # 0xCF -> LATIN SMALL LETTER O WITH TILDE + '}' # 0xD0 -> RIGHT CURLY BRACKET + 'J' # 0xD1 -> LATIN CAPITAL LETTER J + 'K' # 0xD2 -> LATIN CAPITAL LETTER K + 'L' # 0xD3 -> LATIN CAPITAL LETTER L + 'M' # 0xD4 -> LATIN CAPITAL LETTER M + 'N' # 0xD5 -> LATIN CAPITAL LETTER N + 'O' # 0xD6 -> LATIN CAPITAL LETTER O + 'P' # 0xD7 -> LATIN CAPITAL LETTER P + 'Q' # 0xD8 -> LATIN CAPITAL LETTER Q + 'R' # 0xD9 -> LATIN CAPITAL LETTER R + '\xb9' # 0xDA -> SUPERSCRIPT ONE + '\xfb' # 0xDB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0xDC -> LATIN SMALL LETTER U WITH DIAERESIS + '\xf9' # 0xDD -> LATIN SMALL LETTER U WITH GRAVE + '\xfa' # 0xDE -> LATIN SMALL LETTER U WITH ACUTE + '\xff' # 0xDF -> LATIN SMALL LETTER Y WITH DIAERESIS + '\\' # 0xE0 -> REVERSE SOLIDUS + '\xf7' # 0xE1 -> DIVISION SIGN + 'S' # 0xE2 -> LATIN CAPITAL LETTER S + 'T' # 0xE3 -> LATIN CAPITAL LETTER T + 'U' # 0xE4 -> LATIN CAPITAL LETTER U + 'V' # 0xE5 -> LATIN CAPITAL LETTER V + 'W' # 0xE6 -> LATIN CAPITAL LETTER W + 'X' # 0xE7 -> LATIN CAPITAL LETTER X + 'Y' # 0xE8 -> LATIN CAPITAL LETTER Y + 'Z' # 0xE9 -> LATIN CAPITAL LETTER Z + '\xb2' # 0xEA -> SUPERSCRIPT TWO + '\xd4' # 0xEB -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\xd6' # 0xEC -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xd2' # 0xED -> LATIN CAPITAL LETTER O WITH GRAVE + '\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd5' # 0xEF -> LATIN CAPITAL LETTER O WITH TILDE + '0' # 0xF0 -> DIGIT ZERO + '1' # 0xF1 -> DIGIT ONE + '2' # 0xF2 -> DIGIT TWO + '3' # 0xF3 -> DIGIT THREE + '4' # 0xF4 -> DIGIT FOUR + '5' # 0xF5 -> DIGIT FIVE + '6' # 0xF6 -> DIGIT SIX + '7' # 0xF7 -> DIGIT SEVEN + '8' # 0xF8 -> DIGIT EIGHT + '9' # 0xF9 -> DIGIT NINE + '\xb3' # 0xFA -> SUPERSCRIPT THREE + '\xdb' # 0xFB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xdc' # 0xFC -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xd9' # 0xFD -> LATIN CAPITAL LETTER U WITH GRAVE + '\xda' # 0xFE -> LATIN CAPITAL LETTER U WITH ACUTE + '\x9f' # 0xFF -> CONTROL +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/cp720.py b/contrib/tools/python3/src/Lib/encodings/cp720.py new file mode 100644 index 0000000000..96d609616c --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp720.py @@ -0,0 +1,309 @@ +"""Python Character Mapping Codec cp720 generated on Windows: +Vista 6.0.6002 SP2 Multiprocessor Free with the command: + python Tools/unicode/genwincodec.py 720 +"""#" + + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp720', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> CONTROL CHARACTER + '\x01' # 0x01 -> CONTROL CHARACTER + '\x02' # 0x02 -> CONTROL CHARACTER + '\x03' # 0x03 -> CONTROL CHARACTER + '\x04' # 0x04 -> CONTROL CHARACTER + '\x05' # 0x05 -> CONTROL CHARACTER + '\x06' # 0x06 -> CONTROL CHARACTER + '\x07' # 0x07 -> CONTROL CHARACTER + '\x08' # 0x08 -> CONTROL CHARACTER + '\t' # 0x09 -> CONTROL CHARACTER + '\n' # 0x0A -> CONTROL CHARACTER + '\x0b' # 0x0B -> CONTROL CHARACTER + '\x0c' # 0x0C -> CONTROL CHARACTER + '\r' # 0x0D -> CONTROL CHARACTER + '\x0e' # 0x0E -> CONTROL CHARACTER + '\x0f' # 0x0F -> CONTROL CHARACTER + '\x10' # 0x10 -> CONTROL CHARACTER + '\x11' # 0x11 -> CONTROL CHARACTER + '\x12' # 0x12 -> CONTROL CHARACTER + '\x13' # 0x13 -> CONTROL CHARACTER + '\x14' # 0x14 -> CONTROL CHARACTER + '\x15' # 0x15 -> CONTROL CHARACTER + '\x16' # 0x16 -> CONTROL CHARACTER + '\x17' # 0x17 -> CONTROL CHARACTER + '\x18' # 0x18 -> CONTROL CHARACTER + '\x19' # 0x19 -> CONTROL CHARACTER + '\x1a' # 0x1A -> CONTROL CHARACTER + '\x1b' # 0x1B -> CONTROL CHARACTER + '\x1c' # 0x1C -> CONTROL CHARACTER + '\x1d' # 0x1D -> CONTROL CHARACTER + '\x1e' # 0x1E -> CONTROL CHARACTER + '\x1f' # 0x1F -> CONTROL CHARACTER + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> CONTROL CHARACTER + '\x80' + '\x81' + '\xe9' # 0x82 -> LATIN SMALL LETTER E WITH ACUTE + '\xe2' # 0x83 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\x84' + '\xe0' # 0x85 -> LATIN SMALL LETTER A WITH GRAVE + '\x86' + '\xe7' # 0x87 -> LATIN SMALL LETTER C WITH CEDILLA + '\xea' # 0x88 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0x89 -> LATIN SMALL LETTER E WITH DIAERESIS + '\xe8' # 0x8A -> LATIN SMALL LETTER E WITH GRAVE + '\xef' # 0x8B -> LATIN SMALL LETTER I WITH DIAERESIS + '\xee' # 0x8C -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\x8d' + '\x8e' + '\x8f' + '\x90' + '\u0651' # 0x91 -> ARABIC SHADDA + '\u0652' # 0x92 -> ARABIC SUKUN + '\xf4' # 0x93 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xa4' # 0x94 -> CURRENCY SIGN + '\u0640' # 0x95 -> ARABIC TATWEEL + '\xfb' # 0x96 -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xf9' # 0x97 -> LATIN SMALL LETTER U WITH GRAVE + '\u0621' # 0x98 -> ARABIC LETTER HAMZA + '\u0622' # 0x99 -> ARABIC LETTER ALEF WITH MADDA ABOVE + '\u0623' # 0x9A -> ARABIC LETTER ALEF WITH HAMZA ABOVE + '\u0624' # 0x9B -> ARABIC LETTER WAW WITH HAMZA ABOVE + '\xa3' # 0x9C -> POUND SIGN + '\u0625' # 0x9D -> ARABIC LETTER ALEF WITH HAMZA BELOW + '\u0626' # 0x9E -> ARABIC LETTER YEH WITH HAMZA ABOVE + '\u0627' # 0x9F -> ARABIC LETTER ALEF + '\u0628' # 0xA0 -> ARABIC LETTER BEH + '\u0629' # 0xA1 -> ARABIC LETTER TEH MARBUTA + '\u062a' # 0xA2 -> ARABIC LETTER TEH + '\u062b' # 0xA3 -> ARABIC LETTER THEH + '\u062c' # 0xA4 -> ARABIC LETTER JEEM + '\u062d' # 0xA5 -> ARABIC LETTER HAH + '\u062e' # 0xA6 -> ARABIC LETTER KHAH + '\u062f' # 0xA7 -> ARABIC LETTER DAL + '\u0630' # 0xA8 -> ARABIC LETTER THAL + '\u0631' # 0xA9 -> ARABIC LETTER REH + '\u0632' # 0xAA -> ARABIC LETTER ZAIN + '\u0633' # 0xAB -> ARABIC LETTER SEEN + '\u0634' # 0xAC -> ARABIC LETTER SHEEN + '\u0635' # 0xAD -> ARABIC LETTER SAD + '\xab' # 0xAE -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0xAF -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u2591' # 0xB0 -> LIGHT SHADE + '\u2592' # 0xB1 -> MEDIUM SHADE + '\u2593' # 0xB2 -> DARK SHADE + '\u2502' # 0xB3 -> BOX DRAWINGS LIGHT VERTICAL + '\u2524' # 0xB4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT + '\u2561' # 0xB5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + '\u2562' # 0xB6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + '\u2556' # 0xB7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + '\u2555' # 0xB8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + '\u2563' # 0xB9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + '\u2551' # 0xBA -> BOX DRAWINGS DOUBLE VERTICAL + '\u2557' # 0xBB -> BOX DRAWINGS DOUBLE DOWN AND LEFT + '\u255d' # 0xBC -> BOX DRAWINGS DOUBLE UP AND LEFT + '\u255c' # 0xBD -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + '\u255b' # 0xBE -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + '\u2510' # 0xBF -> BOX DRAWINGS LIGHT DOWN AND LEFT + '\u2514' # 0xC0 -> BOX DRAWINGS LIGHT UP AND RIGHT + '\u2534' # 0xC1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL + '\u252c' # 0xC2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + '\u251c' # 0xC3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT + '\u2500' # 0xC4 -> BOX DRAWINGS LIGHT HORIZONTAL + '\u253c' # 0xC5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + '\u255e' # 0xC6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + '\u255f' # 0xC7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + '\u255a' # 0xC8 -> BOX DRAWINGS DOUBLE UP AND RIGHT + '\u2554' # 0xC9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + '\u2569' # 0xCA -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + '\u2566' # 0xCB -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + '\u2560' # 0xCC -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + '\u2550' # 0xCD -> BOX DRAWINGS DOUBLE HORIZONTAL + '\u256c' # 0xCE -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + '\u2567' # 0xCF -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + '\u2568' # 0xD0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + '\u2564' # 0xD1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + '\u2565' # 0xD2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + '\u2559' # 0xD3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + '\u2558' # 0xD4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + '\u2552' # 0xD5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + '\u2553' # 0xD6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + '\u256b' # 0xD7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + '\u256a' # 0xD8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + '\u2518' # 0xD9 -> BOX DRAWINGS LIGHT UP AND LEFT + '\u250c' # 0xDA -> BOX DRAWINGS LIGHT DOWN AND RIGHT + '\u2588' # 0xDB -> FULL BLOCK + '\u2584' # 0xDC -> LOWER HALF BLOCK + '\u258c' # 0xDD -> LEFT HALF BLOCK + '\u2590' # 0xDE -> RIGHT HALF BLOCK + '\u2580' # 0xDF -> UPPER HALF BLOCK + '\u0636' # 0xE0 -> ARABIC LETTER DAD + '\u0637' # 0xE1 -> ARABIC LETTER TAH + '\u0638' # 0xE2 -> ARABIC LETTER ZAH + '\u0639' # 0xE3 -> ARABIC LETTER AIN + '\u063a' # 0xE4 -> ARABIC LETTER GHAIN + '\u0641' # 0xE5 -> ARABIC LETTER FEH + '\xb5' # 0xE6 -> MICRO SIGN + '\u0642' # 0xE7 -> ARABIC LETTER QAF + '\u0643' # 0xE8 -> ARABIC LETTER KAF + '\u0644' # 0xE9 -> ARABIC LETTER LAM + '\u0645' # 0xEA -> ARABIC LETTER MEEM + '\u0646' # 0xEB -> ARABIC LETTER NOON + '\u0647' # 0xEC -> ARABIC LETTER HEH + '\u0648' # 0xED -> ARABIC LETTER WAW + '\u0649' # 0xEE -> ARABIC LETTER ALEF MAKSURA + '\u064a' # 0xEF -> ARABIC LETTER YEH + '\u2261' # 0xF0 -> IDENTICAL TO + '\u064b' # 0xF1 -> ARABIC FATHATAN + '\u064c' # 0xF2 -> ARABIC DAMMATAN + '\u064d' # 0xF3 -> ARABIC KASRATAN + '\u064e' # 0xF4 -> ARABIC FATHA + '\u064f' # 0xF5 -> ARABIC DAMMA + '\u0650' # 0xF6 -> ARABIC KASRA + '\u2248' # 0xF7 -> ALMOST EQUAL TO + '\xb0' # 0xF8 -> DEGREE SIGN + '\u2219' # 0xF9 -> BULLET OPERATOR + '\xb7' # 0xFA -> MIDDLE DOT + '\u221a' # 0xFB -> SQUARE ROOT + '\u207f' # 0xFC -> SUPERSCRIPT LATIN SMALL LETTER N + '\xb2' # 0xFD -> SUPERSCRIPT TWO + '\u25a0' # 0xFE -> BLACK SQUARE + '\xa0' # 0xFF -> NO-BREAK SPACE +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/cp737.py b/contrib/tools/python3/src/Lib/encodings/cp737.py new file mode 100644 index 0000000000..9685bae75b --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp737.py @@ -0,0 +1,698 @@ +""" Python Character Mapping Codec cp737 generated from 'VENDORS/MICSFT/PC/CP737.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_map) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp737', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + +### Decoding Map + +decoding_map = codecs.make_identity_dict(range(256)) +decoding_map.update({ + 0x0080: 0x0391, # GREEK CAPITAL LETTER ALPHA + 0x0081: 0x0392, # GREEK CAPITAL LETTER BETA + 0x0082: 0x0393, # GREEK CAPITAL LETTER GAMMA + 0x0083: 0x0394, # GREEK CAPITAL LETTER DELTA + 0x0084: 0x0395, # GREEK CAPITAL LETTER EPSILON + 0x0085: 0x0396, # GREEK CAPITAL LETTER ZETA + 0x0086: 0x0397, # GREEK CAPITAL LETTER ETA + 0x0087: 0x0398, # GREEK CAPITAL LETTER THETA + 0x0088: 0x0399, # GREEK CAPITAL LETTER IOTA + 0x0089: 0x039a, # GREEK CAPITAL LETTER KAPPA + 0x008a: 0x039b, # GREEK CAPITAL LETTER LAMDA + 0x008b: 0x039c, # GREEK CAPITAL LETTER MU + 0x008c: 0x039d, # GREEK CAPITAL LETTER NU + 0x008d: 0x039e, # GREEK CAPITAL LETTER XI + 0x008e: 0x039f, # GREEK CAPITAL LETTER OMICRON + 0x008f: 0x03a0, # GREEK CAPITAL LETTER PI + 0x0090: 0x03a1, # GREEK CAPITAL LETTER RHO + 0x0091: 0x03a3, # GREEK CAPITAL LETTER SIGMA + 0x0092: 0x03a4, # GREEK CAPITAL LETTER TAU + 0x0093: 0x03a5, # GREEK CAPITAL LETTER UPSILON + 0x0094: 0x03a6, # GREEK CAPITAL LETTER PHI + 0x0095: 0x03a7, # GREEK CAPITAL LETTER CHI + 0x0096: 0x03a8, # GREEK CAPITAL LETTER PSI + 0x0097: 0x03a9, # GREEK CAPITAL LETTER OMEGA + 0x0098: 0x03b1, # GREEK SMALL LETTER ALPHA + 0x0099: 0x03b2, # GREEK SMALL LETTER BETA + 0x009a: 0x03b3, # GREEK SMALL LETTER GAMMA + 0x009b: 0x03b4, # GREEK SMALL LETTER DELTA + 0x009c: 0x03b5, # GREEK SMALL LETTER EPSILON + 0x009d: 0x03b6, # GREEK SMALL LETTER ZETA + 0x009e: 0x03b7, # GREEK SMALL LETTER ETA + 0x009f: 0x03b8, # GREEK SMALL LETTER THETA + 0x00a0: 0x03b9, # GREEK SMALL LETTER IOTA + 0x00a1: 0x03ba, # GREEK SMALL LETTER KAPPA + 0x00a2: 0x03bb, # GREEK SMALL LETTER LAMDA + 0x00a3: 0x03bc, # GREEK SMALL LETTER MU + 0x00a4: 0x03bd, # GREEK SMALL LETTER NU + 0x00a5: 0x03be, # GREEK SMALL LETTER XI + 0x00a6: 0x03bf, # GREEK SMALL LETTER OMICRON + 0x00a7: 0x03c0, # GREEK SMALL LETTER PI + 0x00a8: 0x03c1, # GREEK SMALL LETTER RHO + 0x00a9: 0x03c3, # GREEK SMALL LETTER SIGMA + 0x00aa: 0x03c2, # GREEK SMALL LETTER FINAL SIGMA + 0x00ab: 0x03c4, # GREEK SMALL LETTER TAU + 0x00ac: 0x03c5, # GREEK SMALL LETTER UPSILON + 0x00ad: 0x03c6, # GREEK SMALL LETTER PHI + 0x00ae: 0x03c7, # GREEK SMALL LETTER CHI + 0x00af: 0x03c8, # GREEK SMALL LETTER PSI + 0x00b0: 0x2591, # LIGHT SHADE + 0x00b1: 0x2592, # MEDIUM SHADE + 0x00b2: 0x2593, # DARK SHADE + 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL + 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL + 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL + 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT + 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x00db: 0x2588, # FULL BLOCK + 0x00dc: 0x2584, # LOWER HALF BLOCK + 0x00dd: 0x258c, # LEFT HALF BLOCK + 0x00de: 0x2590, # RIGHT HALF BLOCK + 0x00df: 0x2580, # UPPER HALF BLOCK + 0x00e0: 0x03c9, # GREEK SMALL LETTER OMEGA + 0x00e1: 0x03ac, # GREEK SMALL LETTER ALPHA WITH TONOS + 0x00e2: 0x03ad, # GREEK SMALL LETTER EPSILON WITH TONOS + 0x00e3: 0x03ae, # GREEK SMALL LETTER ETA WITH TONOS + 0x00e4: 0x03ca, # GREEK SMALL LETTER IOTA WITH DIALYTIKA + 0x00e5: 0x03af, # GREEK SMALL LETTER IOTA WITH TONOS + 0x00e6: 0x03cc, # GREEK SMALL LETTER OMICRON WITH TONOS + 0x00e7: 0x03cd, # GREEK SMALL LETTER UPSILON WITH TONOS + 0x00e8: 0x03cb, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA + 0x00e9: 0x03ce, # GREEK SMALL LETTER OMEGA WITH TONOS + 0x00ea: 0x0386, # GREEK CAPITAL LETTER ALPHA WITH TONOS + 0x00eb: 0x0388, # GREEK CAPITAL LETTER EPSILON WITH TONOS + 0x00ec: 0x0389, # GREEK CAPITAL LETTER ETA WITH TONOS + 0x00ed: 0x038a, # GREEK CAPITAL LETTER IOTA WITH TONOS + 0x00ee: 0x038c, # GREEK CAPITAL LETTER OMICRON WITH TONOS + 0x00ef: 0x038e, # GREEK CAPITAL LETTER UPSILON WITH TONOS + 0x00f0: 0x038f, # GREEK CAPITAL LETTER OMEGA WITH TONOS + 0x00f1: 0x00b1, # PLUS-MINUS SIGN + 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO + 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO + 0x00f4: 0x03aa, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA + 0x00f5: 0x03ab, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA + 0x00f6: 0x00f7, # DIVISION SIGN + 0x00f7: 0x2248, # ALMOST EQUAL TO + 0x00f8: 0x00b0, # DEGREE SIGN + 0x00f9: 0x2219, # BULLET OPERATOR + 0x00fa: 0x00b7, # MIDDLE DOT + 0x00fb: 0x221a, # SQUARE ROOT + 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N + 0x00fd: 0x00b2, # SUPERSCRIPT TWO + 0x00fe: 0x25a0, # BLACK SQUARE + 0x00ff: 0x00a0, # NO-BREAK SPACE +}) + +### Decoding Table + +decoding_table = ( + '\x00' # 0x0000 -> NULL + '\x01' # 0x0001 -> START OF HEADING + '\x02' # 0x0002 -> START OF TEXT + '\x03' # 0x0003 -> END OF TEXT + '\x04' # 0x0004 -> END OF TRANSMISSION + '\x05' # 0x0005 -> ENQUIRY + '\x06' # 0x0006 -> ACKNOWLEDGE + '\x07' # 0x0007 -> BELL + '\x08' # 0x0008 -> BACKSPACE + '\t' # 0x0009 -> HORIZONTAL TABULATION + '\n' # 0x000a -> LINE FEED + '\x0b' # 0x000b -> VERTICAL TABULATION + '\x0c' # 0x000c -> FORM FEED + '\r' # 0x000d -> CARRIAGE RETURN + '\x0e' # 0x000e -> SHIFT OUT + '\x0f' # 0x000f -> SHIFT IN + '\x10' # 0x0010 -> DATA LINK ESCAPE + '\x11' # 0x0011 -> DEVICE CONTROL ONE + '\x12' # 0x0012 -> DEVICE CONTROL TWO + '\x13' # 0x0013 -> DEVICE CONTROL THREE + '\x14' # 0x0014 -> DEVICE CONTROL FOUR + '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x0016 -> SYNCHRONOUS IDLE + '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK + '\x18' # 0x0018 -> CANCEL + '\x19' # 0x0019 -> END OF MEDIUM + '\x1a' # 0x001a -> SUBSTITUTE + '\x1b' # 0x001b -> ESCAPE + '\x1c' # 0x001c -> FILE SEPARATOR + '\x1d' # 0x001d -> GROUP SEPARATOR + '\x1e' # 0x001e -> RECORD SEPARATOR + '\x1f' # 0x001f -> UNIT SEPARATOR + ' ' # 0x0020 -> SPACE + '!' # 0x0021 -> EXCLAMATION MARK + '"' # 0x0022 -> QUOTATION MARK + '#' # 0x0023 -> NUMBER SIGN + '$' # 0x0024 -> DOLLAR SIGN + '%' # 0x0025 -> PERCENT SIGN + '&' # 0x0026 -> AMPERSAND + "'" # 0x0027 -> APOSTROPHE + '(' # 0x0028 -> LEFT PARENTHESIS + ')' # 0x0029 -> RIGHT PARENTHESIS + '*' # 0x002a -> ASTERISK + '+' # 0x002b -> PLUS SIGN + ',' # 0x002c -> COMMA + '-' # 0x002d -> HYPHEN-MINUS + '.' # 0x002e -> FULL STOP + '/' # 0x002f -> SOLIDUS + '0' # 0x0030 -> DIGIT ZERO + '1' # 0x0031 -> DIGIT ONE + '2' # 0x0032 -> DIGIT TWO + '3' # 0x0033 -> DIGIT THREE + '4' # 0x0034 -> DIGIT FOUR + '5' # 0x0035 -> DIGIT FIVE + '6' # 0x0036 -> DIGIT SIX + '7' # 0x0037 -> DIGIT SEVEN + '8' # 0x0038 -> DIGIT EIGHT + '9' # 0x0039 -> DIGIT NINE + ':' # 0x003a -> COLON + ';' # 0x003b -> SEMICOLON + '<' # 0x003c -> LESS-THAN SIGN + '=' # 0x003d -> EQUALS SIGN + '>' # 0x003e -> GREATER-THAN SIGN + '?' # 0x003f -> QUESTION MARK + '@' # 0x0040 -> COMMERCIAL AT + 'A' # 0x0041 -> LATIN CAPITAL LETTER A + 'B' # 0x0042 -> LATIN CAPITAL LETTER B + 'C' # 0x0043 -> LATIN CAPITAL LETTER C + 'D' # 0x0044 -> LATIN CAPITAL LETTER D + 'E' # 0x0045 -> LATIN CAPITAL LETTER E + 'F' # 0x0046 -> LATIN CAPITAL LETTER F + 'G' # 0x0047 -> LATIN CAPITAL LETTER G + 'H' # 0x0048 -> LATIN CAPITAL LETTER H + 'I' # 0x0049 -> LATIN CAPITAL LETTER I + 'J' # 0x004a -> LATIN CAPITAL LETTER J + 'K' # 0x004b -> LATIN CAPITAL LETTER K + 'L' # 0x004c -> LATIN CAPITAL LETTER L + 'M' # 0x004d -> LATIN CAPITAL LETTER M + 'N' # 0x004e -> LATIN CAPITAL LETTER N + 'O' # 0x004f -> LATIN CAPITAL LETTER O + 'P' # 0x0050 -> LATIN CAPITAL LETTER P + 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q + 'R' # 0x0052 -> LATIN CAPITAL LETTER R + 'S' # 0x0053 -> LATIN CAPITAL LETTER S + 'T' # 0x0054 -> LATIN CAPITAL LETTER T + 'U' # 0x0055 -> LATIN CAPITAL LETTER U + 'V' # 0x0056 -> LATIN CAPITAL LETTER V + 'W' # 0x0057 -> LATIN CAPITAL LETTER W + 'X' # 0x0058 -> LATIN CAPITAL LETTER X + 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y + 'Z' # 0x005a -> LATIN CAPITAL LETTER Z + '[' # 0x005b -> LEFT SQUARE BRACKET + '\\' # 0x005c -> REVERSE SOLIDUS + ']' # 0x005d -> RIGHT SQUARE BRACKET + '^' # 0x005e -> CIRCUMFLEX ACCENT + '_' # 0x005f -> LOW LINE + '`' # 0x0060 -> GRAVE ACCENT + 'a' # 0x0061 -> LATIN SMALL LETTER A + 'b' # 0x0062 -> LATIN SMALL LETTER B + 'c' # 0x0063 -> LATIN SMALL LETTER C + 'd' # 0x0064 -> LATIN SMALL LETTER D + 'e' # 0x0065 -> LATIN SMALL LETTER E + 'f' # 0x0066 -> LATIN SMALL LETTER F + 'g' # 0x0067 -> LATIN SMALL LETTER G + 'h' # 0x0068 -> LATIN SMALL LETTER H + 'i' # 0x0069 -> LATIN SMALL LETTER I + 'j' # 0x006a -> LATIN SMALL LETTER J + 'k' # 0x006b -> LATIN SMALL LETTER K + 'l' # 0x006c -> LATIN SMALL LETTER L + 'm' # 0x006d -> LATIN SMALL LETTER M + 'n' # 0x006e -> LATIN SMALL LETTER N + 'o' # 0x006f -> LATIN SMALL LETTER O + 'p' # 0x0070 -> LATIN SMALL LETTER P + 'q' # 0x0071 -> LATIN SMALL LETTER Q + 'r' # 0x0072 -> LATIN SMALL LETTER R + 's' # 0x0073 -> LATIN SMALL LETTER S + 't' # 0x0074 -> LATIN SMALL LETTER T + 'u' # 0x0075 -> LATIN SMALL LETTER U + 'v' # 0x0076 -> LATIN SMALL LETTER V + 'w' # 0x0077 -> LATIN SMALL LETTER W + 'x' # 0x0078 -> LATIN SMALL LETTER X + 'y' # 0x0079 -> LATIN SMALL LETTER Y + 'z' # 0x007a -> LATIN SMALL LETTER Z + '{' # 0x007b -> LEFT CURLY BRACKET + '|' # 0x007c -> VERTICAL LINE + '}' # 0x007d -> RIGHT CURLY BRACKET + '~' # 0x007e -> TILDE + '\x7f' # 0x007f -> DELETE + '\u0391' # 0x0080 -> GREEK CAPITAL LETTER ALPHA + '\u0392' # 0x0081 -> GREEK CAPITAL LETTER BETA + '\u0393' # 0x0082 -> GREEK CAPITAL LETTER GAMMA + '\u0394' # 0x0083 -> GREEK CAPITAL LETTER DELTA + '\u0395' # 0x0084 -> GREEK CAPITAL LETTER EPSILON + '\u0396' # 0x0085 -> GREEK CAPITAL LETTER ZETA + '\u0397' # 0x0086 -> GREEK CAPITAL LETTER ETA + '\u0398' # 0x0087 -> GREEK CAPITAL LETTER THETA + '\u0399' # 0x0088 -> GREEK CAPITAL LETTER IOTA + '\u039a' # 0x0089 -> GREEK CAPITAL LETTER KAPPA + '\u039b' # 0x008a -> GREEK CAPITAL LETTER LAMDA + '\u039c' # 0x008b -> GREEK CAPITAL LETTER MU + '\u039d' # 0x008c -> GREEK CAPITAL LETTER NU + '\u039e' # 0x008d -> GREEK CAPITAL LETTER XI + '\u039f' # 0x008e -> GREEK CAPITAL LETTER OMICRON + '\u03a0' # 0x008f -> GREEK CAPITAL LETTER PI + '\u03a1' # 0x0090 -> GREEK CAPITAL LETTER RHO + '\u03a3' # 0x0091 -> GREEK CAPITAL LETTER SIGMA + '\u03a4' # 0x0092 -> GREEK CAPITAL LETTER TAU + '\u03a5' # 0x0093 -> GREEK CAPITAL LETTER UPSILON + '\u03a6' # 0x0094 -> GREEK CAPITAL LETTER PHI + '\u03a7' # 0x0095 -> GREEK CAPITAL LETTER CHI + '\u03a8' # 0x0096 -> GREEK CAPITAL LETTER PSI + '\u03a9' # 0x0097 -> GREEK CAPITAL LETTER OMEGA + '\u03b1' # 0x0098 -> GREEK SMALL LETTER ALPHA + '\u03b2' # 0x0099 -> GREEK SMALL LETTER BETA + '\u03b3' # 0x009a -> GREEK SMALL LETTER GAMMA + '\u03b4' # 0x009b -> GREEK SMALL LETTER DELTA + '\u03b5' # 0x009c -> GREEK SMALL LETTER EPSILON + '\u03b6' # 0x009d -> GREEK SMALL LETTER ZETA + '\u03b7' # 0x009e -> GREEK SMALL LETTER ETA + '\u03b8' # 0x009f -> GREEK SMALL LETTER THETA + '\u03b9' # 0x00a0 -> GREEK SMALL LETTER IOTA + '\u03ba' # 0x00a1 -> GREEK SMALL LETTER KAPPA + '\u03bb' # 0x00a2 -> GREEK SMALL LETTER LAMDA + '\u03bc' # 0x00a3 -> GREEK SMALL LETTER MU + '\u03bd' # 0x00a4 -> GREEK SMALL LETTER NU + '\u03be' # 0x00a5 -> GREEK SMALL LETTER XI + '\u03bf' # 0x00a6 -> GREEK SMALL LETTER OMICRON + '\u03c0' # 0x00a7 -> GREEK SMALL LETTER PI + '\u03c1' # 0x00a8 -> GREEK SMALL LETTER RHO + '\u03c3' # 0x00a9 -> GREEK SMALL LETTER SIGMA + '\u03c2' # 0x00aa -> GREEK SMALL LETTER FINAL SIGMA + '\u03c4' # 0x00ab -> GREEK SMALL LETTER TAU + '\u03c5' # 0x00ac -> GREEK SMALL LETTER UPSILON + '\u03c6' # 0x00ad -> GREEK SMALL LETTER PHI + '\u03c7' # 0x00ae -> GREEK SMALL LETTER CHI + '\u03c8' # 0x00af -> GREEK SMALL LETTER PSI + '\u2591' # 0x00b0 -> LIGHT SHADE + '\u2592' # 0x00b1 -> MEDIUM SHADE + '\u2593' # 0x00b2 -> DARK SHADE + '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL + '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT + '\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + '\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + '\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + '\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL + '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT + '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT + '\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + '\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT + '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT + '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL + '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT + '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL + '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + '\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + '\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT + '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL + '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + '\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + '\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + '\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + '\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + '\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + '\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + '\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + '\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + '\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + '\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT + '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT + '\u2588' # 0x00db -> FULL BLOCK + '\u2584' # 0x00dc -> LOWER HALF BLOCK + '\u258c' # 0x00dd -> LEFT HALF BLOCK + '\u2590' # 0x00de -> RIGHT HALF BLOCK + '\u2580' # 0x00df -> UPPER HALF BLOCK + '\u03c9' # 0x00e0 -> GREEK SMALL LETTER OMEGA + '\u03ac' # 0x00e1 -> GREEK SMALL LETTER ALPHA WITH TONOS + '\u03ad' # 0x00e2 -> GREEK SMALL LETTER EPSILON WITH TONOS + '\u03ae' # 0x00e3 -> GREEK SMALL LETTER ETA WITH TONOS + '\u03ca' # 0x00e4 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA + '\u03af' # 0x00e5 -> GREEK SMALL LETTER IOTA WITH TONOS + '\u03cc' # 0x00e6 -> GREEK SMALL LETTER OMICRON WITH TONOS + '\u03cd' # 0x00e7 -> GREEK SMALL LETTER UPSILON WITH TONOS + '\u03cb' # 0x00e8 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA + '\u03ce' # 0x00e9 -> GREEK SMALL LETTER OMEGA WITH TONOS + '\u0386' # 0x00ea -> GREEK CAPITAL LETTER ALPHA WITH TONOS + '\u0388' # 0x00eb -> GREEK CAPITAL LETTER EPSILON WITH TONOS + '\u0389' # 0x00ec -> GREEK CAPITAL LETTER ETA WITH TONOS + '\u038a' # 0x00ed -> GREEK CAPITAL LETTER IOTA WITH TONOS + '\u038c' # 0x00ee -> GREEK CAPITAL LETTER OMICRON WITH TONOS + '\u038e' # 0x00ef -> GREEK CAPITAL LETTER UPSILON WITH TONOS + '\u038f' # 0x00f0 -> GREEK CAPITAL LETTER OMEGA WITH TONOS + '\xb1' # 0x00f1 -> PLUS-MINUS SIGN + '\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO + '\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO + '\u03aa' # 0x00f4 -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA + '\u03ab' # 0x00f5 -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA + '\xf7' # 0x00f6 -> DIVISION SIGN + '\u2248' # 0x00f7 -> ALMOST EQUAL TO + '\xb0' # 0x00f8 -> DEGREE SIGN + '\u2219' # 0x00f9 -> BULLET OPERATOR + '\xb7' # 0x00fa -> MIDDLE DOT + '\u221a' # 0x00fb -> SQUARE ROOT + '\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N + '\xb2' # 0x00fd -> SUPERSCRIPT TWO + '\u25a0' # 0x00fe -> BLACK SQUARE + '\xa0' # 0x00ff -> NO-BREAK SPACE +) + +### Encoding Map + +encoding_map = { + 0x0000: 0x0000, # NULL + 0x0001: 0x0001, # START OF HEADING + 0x0002: 0x0002, # START OF TEXT + 0x0003: 0x0003, # END OF TEXT + 0x0004: 0x0004, # END OF TRANSMISSION + 0x0005: 0x0005, # ENQUIRY + 0x0006: 0x0006, # ACKNOWLEDGE + 0x0007: 0x0007, # BELL + 0x0008: 0x0008, # BACKSPACE + 0x0009: 0x0009, # HORIZONTAL TABULATION + 0x000a: 0x000a, # LINE FEED + 0x000b: 0x000b, # VERTICAL TABULATION + 0x000c: 0x000c, # FORM FEED + 0x000d: 0x000d, # CARRIAGE RETURN + 0x000e: 0x000e, # SHIFT OUT + 0x000f: 0x000f, # SHIFT IN + 0x0010: 0x0010, # DATA LINK ESCAPE + 0x0011: 0x0011, # DEVICE CONTROL ONE + 0x0012: 0x0012, # DEVICE CONTROL TWO + 0x0013: 0x0013, # DEVICE CONTROL THREE + 0x0014: 0x0014, # DEVICE CONTROL FOUR + 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE + 0x0016: 0x0016, # SYNCHRONOUS IDLE + 0x0017: 0x0017, # END OF TRANSMISSION BLOCK + 0x0018: 0x0018, # CANCEL + 0x0019: 0x0019, # END OF MEDIUM + 0x001a: 0x001a, # SUBSTITUTE + 0x001b: 0x001b, # ESCAPE + 0x001c: 0x001c, # FILE SEPARATOR + 0x001d: 0x001d, # GROUP SEPARATOR + 0x001e: 0x001e, # RECORD SEPARATOR + 0x001f: 0x001f, # UNIT SEPARATOR + 0x0020: 0x0020, # SPACE + 0x0021: 0x0021, # EXCLAMATION MARK + 0x0022: 0x0022, # QUOTATION MARK + 0x0023: 0x0023, # NUMBER SIGN + 0x0024: 0x0024, # DOLLAR SIGN + 0x0025: 0x0025, # PERCENT SIGN + 0x0026: 0x0026, # AMPERSAND + 0x0027: 0x0027, # APOSTROPHE + 0x0028: 0x0028, # LEFT PARENTHESIS + 0x0029: 0x0029, # RIGHT PARENTHESIS + 0x002a: 0x002a, # ASTERISK + 0x002b: 0x002b, # PLUS SIGN + 0x002c: 0x002c, # COMMA + 0x002d: 0x002d, # HYPHEN-MINUS + 0x002e: 0x002e, # FULL STOP + 0x002f: 0x002f, # SOLIDUS + 0x0030: 0x0030, # DIGIT ZERO + 0x0031: 0x0031, # DIGIT ONE + 0x0032: 0x0032, # DIGIT TWO + 0x0033: 0x0033, # DIGIT THREE + 0x0034: 0x0034, # DIGIT FOUR + 0x0035: 0x0035, # DIGIT FIVE + 0x0036: 0x0036, # DIGIT SIX + 0x0037: 0x0037, # DIGIT SEVEN + 0x0038: 0x0038, # DIGIT EIGHT + 0x0039: 0x0039, # DIGIT NINE + 0x003a: 0x003a, # COLON + 0x003b: 0x003b, # SEMICOLON + 0x003c: 0x003c, # LESS-THAN SIGN + 0x003d: 0x003d, # EQUALS SIGN + 0x003e: 0x003e, # GREATER-THAN SIGN + 0x003f: 0x003f, # QUESTION MARK + 0x0040: 0x0040, # COMMERCIAL AT + 0x0041: 0x0041, # LATIN CAPITAL LETTER A + 0x0042: 0x0042, # LATIN CAPITAL LETTER B + 0x0043: 0x0043, # LATIN CAPITAL LETTER C + 0x0044: 0x0044, # LATIN CAPITAL LETTER D + 0x0045: 0x0045, # LATIN CAPITAL LETTER E + 0x0046: 0x0046, # LATIN CAPITAL LETTER F + 0x0047: 0x0047, # LATIN CAPITAL LETTER G + 0x0048: 0x0048, # LATIN CAPITAL LETTER H + 0x0049: 0x0049, # LATIN CAPITAL LETTER I + 0x004a: 0x004a, # LATIN CAPITAL LETTER J + 0x004b: 0x004b, # LATIN CAPITAL LETTER K + 0x004c: 0x004c, # LATIN CAPITAL LETTER L + 0x004d: 0x004d, # LATIN CAPITAL LETTER M + 0x004e: 0x004e, # LATIN CAPITAL LETTER N + 0x004f: 0x004f, # LATIN CAPITAL LETTER O + 0x0050: 0x0050, # LATIN CAPITAL LETTER P + 0x0051: 0x0051, # LATIN CAPITAL LETTER Q + 0x0052: 0x0052, # LATIN CAPITAL LETTER R + 0x0053: 0x0053, # LATIN CAPITAL LETTER S + 0x0054: 0x0054, # LATIN CAPITAL LETTER T + 0x0055: 0x0055, # LATIN CAPITAL LETTER U + 0x0056: 0x0056, # LATIN CAPITAL LETTER V + 0x0057: 0x0057, # LATIN CAPITAL LETTER W + 0x0058: 0x0058, # LATIN CAPITAL LETTER X + 0x0059: 0x0059, # LATIN CAPITAL LETTER Y + 0x005a: 0x005a, # LATIN CAPITAL LETTER Z + 0x005b: 0x005b, # LEFT SQUARE BRACKET + 0x005c: 0x005c, # REVERSE SOLIDUS + 0x005d: 0x005d, # RIGHT SQUARE BRACKET + 0x005e: 0x005e, # CIRCUMFLEX ACCENT + 0x005f: 0x005f, # LOW LINE + 0x0060: 0x0060, # GRAVE ACCENT + 0x0061: 0x0061, # LATIN SMALL LETTER A + 0x0062: 0x0062, # LATIN SMALL LETTER B + 0x0063: 0x0063, # LATIN SMALL LETTER C + 0x0064: 0x0064, # LATIN SMALL LETTER D + 0x0065: 0x0065, # LATIN SMALL LETTER E + 0x0066: 0x0066, # LATIN SMALL LETTER F + 0x0067: 0x0067, # LATIN SMALL LETTER G + 0x0068: 0x0068, # LATIN SMALL LETTER H + 0x0069: 0x0069, # LATIN SMALL LETTER I + 0x006a: 0x006a, # LATIN SMALL LETTER J + 0x006b: 0x006b, # LATIN SMALL LETTER K + 0x006c: 0x006c, # LATIN SMALL LETTER L + 0x006d: 0x006d, # LATIN SMALL LETTER M + 0x006e: 0x006e, # LATIN SMALL LETTER N + 0x006f: 0x006f, # LATIN SMALL LETTER O + 0x0070: 0x0070, # LATIN SMALL LETTER P + 0x0071: 0x0071, # LATIN SMALL LETTER Q + 0x0072: 0x0072, # LATIN SMALL LETTER R + 0x0073: 0x0073, # LATIN SMALL LETTER S + 0x0074: 0x0074, # LATIN SMALL LETTER T + 0x0075: 0x0075, # LATIN SMALL LETTER U + 0x0076: 0x0076, # LATIN SMALL LETTER V + 0x0077: 0x0077, # LATIN SMALL LETTER W + 0x0078: 0x0078, # LATIN SMALL LETTER X + 0x0079: 0x0079, # LATIN SMALL LETTER Y + 0x007a: 0x007a, # LATIN SMALL LETTER Z + 0x007b: 0x007b, # LEFT CURLY BRACKET + 0x007c: 0x007c, # VERTICAL LINE + 0x007d: 0x007d, # RIGHT CURLY BRACKET + 0x007e: 0x007e, # TILDE + 0x007f: 0x007f, # DELETE + 0x00a0: 0x00ff, # NO-BREAK SPACE + 0x00b0: 0x00f8, # DEGREE SIGN + 0x00b1: 0x00f1, # PLUS-MINUS SIGN + 0x00b2: 0x00fd, # SUPERSCRIPT TWO + 0x00b7: 0x00fa, # MIDDLE DOT + 0x00f7: 0x00f6, # DIVISION SIGN + 0x0386: 0x00ea, # GREEK CAPITAL LETTER ALPHA WITH TONOS + 0x0388: 0x00eb, # GREEK CAPITAL LETTER EPSILON WITH TONOS + 0x0389: 0x00ec, # GREEK CAPITAL LETTER ETA WITH TONOS + 0x038a: 0x00ed, # GREEK CAPITAL LETTER IOTA WITH TONOS + 0x038c: 0x00ee, # GREEK CAPITAL LETTER OMICRON WITH TONOS + 0x038e: 0x00ef, # GREEK CAPITAL LETTER UPSILON WITH TONOS + 0x038f: 0x00f0, # GREEK CAPITAL LETTER OMEGA WITH TONOS + 0x0391: 0x0080, # GREEK CAPITAL LETTER ALPHA + 0x0392: 0x0081, # GREEK CAPITAL LETTER BETA + 0x0393: 0x0082, # GREEK CAPITAL LETTER GAMMA + 0x0394: 0x0083, # GREEK CAPITAL LETTER DELTA + 0x0395: 0x0084, # GREEK CAPITAL LETTER EPSILON + 0x0396: 0x0085, # GREEK CAPITAL LETTER ZETA + 0x0397: 0x0086, # GREEK CAPITAL LETTER ETA + 0x0398: 0x0087, # GREEK CAPITAL LETTER THETA + 0x0399: 0x0088, # GREEK CAPITAL LETTER IOTA + 0x039a: 0x0089, # GREEK CAPITAL LETTER KAPPA + 0x039b: 0x008a, # GREEK CAPITAL LETTER LAMDA + 0x039c: 0x008b, # GREEK CAPITAL LETTER MU + 0x039d: 0x008c, # GREEK CAPITAL LETTER NU + 0x039e: 0x008d, # GREEK CAPITAL LETTER XI + 0x039f: 0x008e, # GREEK CAPITAL LETTER OMICRON + 0x03a0: 0x008f, # GREEK CAPITAL LETTER PI + 0x03a1: 0x0090, # GREEK CAPITAL LETTER RHO + 0x03a3: 0x0091, # GREEK CAPITAL LETTER SIGMA + 0x03a4: 0x0092, # GREEK CAPITAL LETTER TAU + 0x03a5: 0x0093, # GREEK CAPITAL LETTER UPSILON + 0x03a6: 0x0094, # GREEK CAPITAL LETTER PHI + 0x03a7: 0x0095, # GREEK CAPITAL LETTER CHI + 0x03a8: 0x0096, # GREEK CAPITAL LETTER PSI + 0x03a9: 0x0097, # GREEK CAPITAL LETTER OMEGA + 0x03aa: 0x00f4, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA + 0x03ab: 0x00f5, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA + 0x03ac: 0x00e1, # GREEK SMALL LETTER ALPHA WITH TONOS + 0x03ad: 0x00e2, # GREEK SMALL LETTER EPSILON WITH TONOS + 0x03ae: 0x00e3, # GREEK SMALL LETTER ETA WITH TONOS + 0x03af: 0x00e5, # GREEK SMALL LETTER IOTA WITH TONOS + 0x03b1: 0x0098, # GREEK SMALL LETTER ALPHA + 0x03b2: 0x0099, # GREEK SMALL LETTER BETA + 0x03b3: 0x009a, # GREEK SMALL LETTER GAMMA + 0x03b4: 0x009b, # GREEK SMALL LETTER DELTA + 0x03b5: 0x009c, # GREEK SMALL LETTER EPSILON + 0x03b6: 0x009d, # GREEK SMALL LETTER ZETA + 0x03b7: 0x009e, # GREEK SMALL LETTER ETA + 0x03b8: 0x009f, # GREEK SMALL LETTER THETA + 0x03b9: 0x00a0, # GREEK SMALL LETTER IOTA + 0x03ba: 0x00a1, # GREEK SMALL LETTER KAPPA + 0x03bb: 0x00a2, # GREEK SMALL LETTER LAMDA + 0x03bc: 0x00a3, # GREEK SMALL LETTER MU + 0x03bd: 0x00a4, # GREEK SMALL LETTER NU + 0x03be: 0x00a5, # GREEK SMALL LETTER XI + 0x03bf: 0x00a6, # GREEK SMALL LETTER OMICRON + 0x03c0: 0x00a7, # GREEK SMALL LETTER PI + 0x03c1: 0x00a8, # GREEK SMALL LETTER RHO + 0x03c2: 0x00aa, # GREEK SMALL LETTER FINAL SIGMA + 0x03c3: 0x00a9, # GREEK SMALL LETTER SIGMA + 0x03c4: 0x00ab, # GREEK SMALL LETTER TAU + 0x03c5: 0x00ac, # GREEK SMALL LETTER UPSILON + 0x03c6: 0x00ad, # GREEK SMALL LETTER PHI + 0x03c7: 0x00ae, # GREEK SMALL LETTER CHI + 0x03c8: 0x00af, # GREEK SMALL LETTER PSI + 0x03c9: 0x00e0, # GREEK SMALL LETTER OMEGA + 0x03ca: 0x00e4, # GREEK SMALL LETTER IOTA WITH DIALYTIKA + 0x03cb: 0x00e8, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA + 0x03cc: 0x00e6, # GREEK SMALL LETTER OMICRON WITH TONOS + 0x03cd: 0x00e7, # GREEK SMALL LETTER UPSILON WITH TONOS + 0x03ce: 0x00e9, # GREEK SMALL LETTER OMEGA WITH TONOS + 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N + 0x2219: 0x00f9, # BULLET OPERATOR + 0x221a: 0x00fb, # SQUARE ROOT + 0x2248: 0x00f7, # ALMOST EQUAL TO + 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO + 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO + 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL + 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL + 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT + 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL + 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x2580: 0x00df, # UPPER HALF BLOCK + 0x2584: 0x00dc, # LOWER HALF BLOCK + 0x2588: 0x00db, # FULL BLOCK + 0x258c: 0x00dd, # LEFT HALF BLOCK + 0x2590: 0x00de, # RIGHT HALF BLOCK + 0x2591: 0x00b0, # LIGHT SHADE + 0x2592: 0x00b1, # MEDIUM SHADE + 0x2593: 0x00b2, # DARK SHADE + 0x25a0: 0x00fe, # BLACK SQUARE +} diff --git a/contrib/tools/python3/src/Lib/encodings/cp775.py b/contrib/tools/python3/src/Lib/encodings/cp775.py new file mode 100644 index 0000000000..fe06e7bc3b --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp775.py @@ -0,0 +1,697 @@ +""" Python Character Mapping Codec cp775 generated from 'VENDORS/MICSFT/PC/CP775.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_map) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp775', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) +### Decoding Map + +decoding_map = codecs.make_identity_dict(range(256)) +decoding_map.update({ + 0x0080: 0x0106, # LATIN CAPITAL LETTER C WITH ACUTE + 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS + 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE + 0x0083: 0x0101, # LATIN SMALL LETTER A WITH MACRON + 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x0085: 0x0123, # LATIN SMALL LETTER G WITH CEDILLA + 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE + 0x0087: 0x0107, # LATIN SMALL LETTER C WITH ACUTE + 0x0088: 0x0142, # LATIN SMALL LETTER L WITH STROKE + 0x0089: 0x0113, # LATIN SMALL LETTER E WITH MACRON + 0x008a: 0x0156, # LATIN CAPITAL LETTER R WITH CEDILLA + 0x008b: 0x0157, # LATIN SMALL LETTER R WITH CEDILLA + 0x008c: 0x012b, # LATIN SMALL LETTER I WITH MACRON + 0x008d: 0x0179, # LATIN CAPITAL LETTER Z WITH ACUTE + 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE + 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE + 0x0093: 0x014d, # LATIN SMALL LETTER O WITH MACRON + 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x0095: 0x0122, # LATIN CAPITAL LETTER G WITH CEDILLA + 0x0096: 0x00a2, # CENT SIGN + 0x0097: 0x015a, # LATIN CAPITAL LETTER S WITH ACUTE + 0x0098: 0x015b, # LATIN SMALL LETTER S WITH ACUTE + 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE + 0x009c: 0x00a3, # POUND SIGN + 0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE + 0x009e: 0x00d7, # MULTIPLICATION SIGN + 0x009f: 0x00a4, # CURRENCY SIGN + 0x00a0: 0x0100, # LATIN CAPITAL LETTER A WITH MACRON + 0x00a1: 0x012a, # LATIN CAPITAL LETTER I WITH MACRON + 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE + 0x00a3: 0x017b, # LATIN CAPITAL LETTER Z WITH DOT ABOVE + 0x00a4: 0x017c, # LATIN SMALL LETTER Z WITH DOT ABOVE + 0x00a5: 0x017a, # LATIN SMALL LETTER Z WITH ACUTE + 0x00a6: 0x201d, # RIGHT DOUBLE QUOTATION MARK + 0x00a7: 0x00a6, # BROKEN BAR + 0x00a8: 0x00a9, # COPYRIGHT SIGN + 0x00a9: 0x00ae, # REGISTERED SIGN + 0x00aa: 0x00ac, # NOT SIGN + 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF + 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER + 0x00ad: 0x0141, # LATIN CAPITAL LETTER L WITH STROKE + 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00b0: 0x2591, # LIGHT SHADE + 0x00b1: 0x2592, # MEDIUM SHADE + 0x00b2: 0x2593, # DARK SHADE + 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL + 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x00b5: 0x0104, # LATIN CAPITAL LETTER A WITH OGONEK + 0x00b6: 0x010c, # LATIN CAPITAL LETTER C WITH CARON + 0x00b7: 0x0118, # LATIN CAPITAL LETTER E WITH OGONEK + 0x00b8: 0x0116, # LATIN CAPITAL LETTER E WITH DOT ABOVE + 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL + 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x00bd: 0x012e, # LATIN CAPITAL LETTER I WITH OGONEK + 0x00be: 0x0160, # LATIN CAPITAL LETTER S WITH CARON + 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL + 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x00c6: 0x0172, # LATIN CAPITAL LETTER U WITH OGONEK + 0x00c7: 0x016a, # LATIN CAPITAL LETTER U WITH MACRON + 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x00cf: 0x017d, # LATIN CAPITAL LETTER Z WITH CARON + 0x00d0: 0x0105, # LATIN SMALL LETTER A WITH OGONEK + 0x00d1: 0x010d, # LATIN SMALL LETTER C WITH CARON + 0x00d2: 0x0119, # LATIN SMALL LETTER E WITH OGONEK + 0x00d3: 0x0117, # LATIN SMALL LETTER E WITH DOT ABOVE + 0x00d4: 0x012f, # LATIN SMALL LETTER I WITH OGONEK + 0x00d5: 0x0161, # LATIN SMALL LETTER S WITH CARON + 0x00d6: 0x0173, # LATIN SMALL LETTER U WITH OGONEK + 0x00d7: 0x016b, # LATIN SMALL LETTER U WITH MACRON + 0x00d8: 0x017e, # LATIN SMALL LETTER Z WITH CARON + 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT + 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x00db: 0x2588, # FULL BLOCK + 0x00dc: 0x2584, # LOWER HALF BLOCK + 0x00dd: 0x258c, # LEFT HALF BLOCK + 0x00de: 0x2590, # RIGHT HALF BLOCK + 0x00df: 0x2580, # UPPER HALF BLOCK + 0x00e0: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S (GERMAN) + 0x00e2: 0x014c, # LATIN CAPITAL LETTER O WITH MACRON + 0x00e3: 0x0143, # LATIN CAPITAL LETTER N WITH ACUTE + 0x00e4: 0x00f5, # LATIN SMALL LETTER O WITH TILDE + 0x00e5: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE + 0x00e6: 0x00b5, # MICRO SIGN + 0x00e7: 0x0144, # LATIN SMALL LETTER N WITH ACUTE + 0x00e8: 0x0136, # LATIN CAPITAL LETTER K WITH CEDILLA + 0x00e9: 0x0137, # LATIN SMALL LETTER K WITH CEDILLA + 0x00ea: 0x013b, # LATIN CAPITAL LETTER L WITH CEDILLA + 0x00eb: 0x013c, # LATIN SMALL LETTER L WITH CEDILLA + 0x00ec: 0x0146, # LATIN SMALL LETTER N WITH CEDILLA + 0x00ed: 0x0112, # LATIN CAPITAL LETTER E WITH MACRON + 0x00ee: 0x0145, # LATIN CAPITAL LETTER N WITH CEDILLA + 0x00ef: 0x2019, # RIGHT SINGLE QUOTATION MARK + 0x00f0: 0x00ad, # SOFT HYPHEN + 0x00f1: 0x00b1, # PLUS-MINUS SIGN + 0x00f2: 0x201c, # LEFT DOUBLE QUOTATION MARK + 0x00f3: 0x00be, # VULGAR FRACTION THREE QUARTERS + 0x00f4: 0x00b6, # PILCROW SIGN + 0x00f5: 0x00a7, # SECTION SIGN + 0x00f6: 0x00f7, # DIVISION SIGN + 0x00f7: 0x201e, # DOUBLE LOW-9 QUOTATION MARK + 0x00f8: 0x00b0, # DEGREE SIGN + 0x00f9: 0x2219, # BULLET OPERATOR + 0x00fa: 0x00b7, # MIDDLE DOT + 0x00fb: 0x00b9, # SUPERSCRIPT ONE + 0x00fc: 0x00b3, # SUPERSCRIPT THREE + 0x00fd: 0x00b2, # SUPERSCRIPT TWO + 0x00fe: 0x25a0, # BLACK SQUARE + 0x00ff: 0x00a0, # NO-BREAK SPACE +}) + +### Decoding Table + +decoding_table = ( + '\x00' # 0x0000 -> NULL + '\x01' # 0x0001 -> START OF HEADING + '\x02' # 0x0002 -> START OF TEXT + '\x03' # 0x0003 -> END OF TEXT + '\x04' # 0x0004 -> END OF TRANSMISSION + '\x05' # 0x0005 -> ENQUIRY + '\x06' # 0x0006 -> ACKNOWLEDGE + '\x07' # 0x0007 -> BELL + '\x08' # 0x0008 -> BACKSPACE + '\t' # 0x0009 -> HORIZONTAL TABULATION + '\n' # 0x000a -> LINE FEED + '\x0b' # 0x000b -> VERTICAL TABULATION + '\x0c' # 0x000c -> FORM FEED + '\r' # 0x000d -> CARRIAGE RETURN + '\x0e' # 0x000e -> SHIFT OUT + '\x0f' # 0x000f -> SHIFT IN + '\x10' # 0x0010 -> DATA LINK ESCAPE + '\x11' # 0x0011 -> DEVICE CONTROL ONE + '\x12' # 0x0012 -> DEVICE CONTROL TWO + '\x13' # 0x0013 -> DEVICE CONTROL THREE + '\x14' # 0x0014 -> DEVICE CONTROL FOUR + '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x0016 -> SYNCHRONOUS IDLE + '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK + '\x18' # 0x0018 -> CANCEL + '\x19' # 0x0019 -> END OF MEDIUM + '\x1a' # 0x001a -> SUBSTITUTE + '\x1b' # 0x001b -> ESCAPE + '\x1c' # 0x001c -> FILE SEPARATOR + '\x1d' # 0x001d -> GROUP SEPARATOR + '\x1e' # 0x001e -> RECORD SEPARATOR + '\x1f' # 0x001f -> UNIT SEPARATOR + ' ' # 0x0020 -> SPACE + '!' # 0x0021 -> EXCLAMATION MARK + '"' # 0x0022 -> QUOTATION MARK + '#' # 0x0023 -> NUMBER SIGN + '$' # 0x0024 -> DOLLAR SIGN + '%' # 0x0025 -> PERCENT SIGN + '&' # 0x0026 -> AMPERSAND + "'" # 0x0027 -> APOSTROPHE + '(' # 0x0028 -> LEFT PARENTHESIS + ')' # 0x0029 -> RIGHT PARENTHESIS + '*' # 0x002a -> ASTERISK + '+' # 0x002b -> PLUS SIGN + ',' # 0x002c -> COMMA + '-' # 0x002d -> HYPHEN-MINUS + '.' # 0x002e -> FULL STOP + '/' # 0x002f -> SOLIDUS + '0' # 0x0030 -> DIGIT ZERO + '1' # 0x0031 -> DIGIT ONE + '2' # 0x0032 -> DIGIT TWO + '3' # 0x0033 -> DIGIT THREE + '4' # 0x0034 -> DIGIT FOUR + '5' # 0x0035 -> DIGIT FIVE + '6' # 0x0036 -> DIGIT SIX + '7' # 0x0037 -> DIGIT SEVEN + '8' # 0x0038 -> DIGIT EIGHT + '9' # 0x0039 -> DIGIT NINE + ':' # 0x003a -> COLON + ';' # 0x003b -> SEMICOLON + '<' # 0x003c -> LESS-THAN SIGN + '=' # 0x003d -> EQUALS SIGN + '>' # 0x003e -> GREATER-THAN SIGN + '?' # 0x003f -> QUESTION MARK + '@' # 0x0040 -> COMMERCIAL AT + 'A' # 0x0041 -> LATIN CAPITAL LETTER A + 'B' # 0x0042 -> LATIN CAPITAL LETTER B + 'C' # 0x0043 -> LATIN CAPITAL LETTER C + 'D' # 0x0044 -> LATIN CAPITAL LETTER D + 'E' # 0x0045 -> LATIN CAPITAL LETTER E + 'F' # 0x0046 -> LATIN CAPITAL LETTER F + 'G' # 0x0047 -> LATIN CAPITAL LETTER G + 'H' # 0x0048 -> LATIN CAPITAL LETTER H + 'I' # 0x0049 -> LATIN CAPITAL LETTER I + 'J' # 0x004a -> LATIN CAPITAL LETTER J + 'K' # 0x004b -> LATIN CAPITAL LETTER K + 'L' # 0x004c -> LATIN CAPITAL LETTER L + 'M' # 0x004d -> LATIN CAPITAL LETTER M + 'N' # 0x004e -> LATIN CAPITAL LETTER N + 'O' # 0x004f -> LATIN CAPITAL LETTER O + 'P' # 0x0050 -> LATIN CAPITAL LETTER P + 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q + 'R' # 0x0052 -> LATIN CAPITAL LETTER R + 'S' # 0x0053 -> LATIN CAPITAL LETTER S + 'T' # 0x0054 -> LATIN CAPITAL LETTER T + 'U' # 0x0055 -> LATIN CAPITAL LETTER U + 'V' # 0x0056 -> LATIN CAPITAL LETTER V + 'W' # 0x0057 -> LATIN CAPITAL LETTER W + 'X' # 0x0058 -> LATIN CAPITAL LETTER X + 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y + 'Z' # 0x005a -> LATIN CAPITAL LETTER Z + '[' # 0x005b -> LEFT SQUARE BRACKET + '\\' # 0x005c -> REVERSE SOLIDUS + ']' # 0x005d -> RIGHT SQUARE BRACKET + '^' # 0x005e -> CIRCUMFLEX ACCENT + '_' # 0x005f -> LOW LINE + '`' # 0x0060 -> GRAVE ACCENT + 'a' # 0x0061 -> LATIN SMALL LETTER A + 'b' # 0x0062 -> LATIN SMALL LETTER B + 'c' # 0x0063 -> LATIN SMALL LETTER C + 'd' # 0x0064 -> LATIN SMALL LETTER D + 'e' # 0x0065 -> LATIN SMALL LETTER E + 'f' # 0x0066 -> LATIN SMALL LETTER F + 'g' # 0x0067 -> LATIN SMALL LETTER G + 'h' # 0x0068 -> LATIN SMALL LETTER H + 'i' # 0x0069 -> LATIN SMALL LETTER I + 'j' # 0x006a -> LATIN SMALL LETTER J + 'k' # 0x006b -> LATIN SMALL LETTER K + 'l' # 0x006c -> LATIN SMALL LETTER L + 'm' # 0x006d -> LATIN SMALL LETTER M + 'n' # 0x006e -> LATIN SMALL LETTER N + 'o' # 0x006f -> LATIN SMALL LETTER O + 'p' # 0x0070 -> LATIN SMALL LETTER P + 'q' # 0x0071 -> LATIN SMALL LETTER Q + 'r' # 0x0072 -> LATIN SMALL LETTER R + 's' # 0x0073 -> LATIN SMALL LETTER S + 't' # 0x0074 -> LATIN SMALL LETTER T + 'u' # 0x0075 -> LATIN SMALL LETTER U + 'v' # 0x0076 -> LATIN SMALL LETTER V + 'w' # 0x0077 -> LATIN SMALL LETTER W + 'x' # 0x0078 -> LATIN SMALL LETTER X + 'y' # 0x0079 -> LATIN SMALL LETTER Y + 'z' # 0x007a -> LATIN SMALL LETTER Z + '{' # 0x007b -> LEFT CURLY BRACKET + '|' # 0x007c -> VERTICAL LINE + '}' # 0x007d -> RIGHT CURLY BRACKET + '~' # 0x007e -> TILDE + '\x7f' # 0x007f -> DELETE + '\u0106' # 0x0080 -> LATIN CAPITAL LETTER C WITH ACUTE + '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS + '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE + '\u0101' # 0x0083 -> LATIN SMALL LETTER A WITH MACRON + '\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS + '\u0123' # 0x0085 -> LATIN SMALL LETTER G WITH CEDILLA + '\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE + '\u0107' # 0x0087 -> LATIN SMALL LETTER C WITH ACUTE + '\u0142' # 0x0088 -> LATIN SMALL LETTER L WITH STROKE + '\u0113' # 0x0089 -> LATIN SMALL LETTER E WITH MACRON + '\u0156' # 0x008a -> LATIN CAPITAL LETTER R WITH CEDILLA + '\u0157' # 0x008b -> LATIN SMALL LETTER R WITH CEDILLA + '\u012b' # 0x008c -> LATIN SMALL LETTER I WITH MACRON + '\u0179' # 0x008d -> LATIN CAPITAL LETTER Z WITH ACUTE + '\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE + '\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE + '\u014d' # 0x0093 -> LATIN SMALL LETTER O WITH MACRON + '\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS + '\u0122' # 0x0095 -> LATIN CAPITAL LETTER G WITH CEDILLA + '\xa2' # 0x0096 -> CENT SIGN + '\u015a' # 0x0097 -> LATIN CAPITAL LETTER S WITH ACUTE + '\u015b' # 0x0098 -> LATIN SMALL LETTER S WITH ACUTE + '\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE + '\xa3' # 0x009c -> POUND SIGN + '\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE + '\xd7' # 0x009e -> MULTIPLICATION SIGN + '\xa4' # 0x009f -> CURRENCY SIGN + '\u0100' # 0x00a0 -> LATIN CAPITAL LETTER A WITH MACRON + '\u012a' # 0x00a1 -> LATIN CAPITAL LETTER I WITH MACRON + '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE + '\u017b' # 0x00a3 -> LATIN CAPITAL LETTER Z WITH DOT ABOVE + '\u017c' # 0x00a4 -> LATIN SMALL LETTER Z WITH DOT ABOVE + '\u017a' # 0x00a5 -> LATIN SMALL LETTER Z WITH ACUTE + '\u201d' # 0x00a6 -> RIGHT DOUBLE QUOTATION MARK + '\xa6' # 0x00a7 -> BROKEN BAR + '\xa9' # 0x00a8 -> COPYRIGHT SIGN + '\xae' # 0x00a9 -> REGISTERED SIGN + '\xac' # 0x00aa -> NOT SIGN + '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF + '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER + '\u0141' # 0x00ad -> LATIN CAPITAL LETTER L WITH STROKE + '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u2591' # 0x00b0 -> LIGHT SHADE + '\u2592' # 0x00b1 -> MEDIUM SHADE + '\u2593' # 0x00b2 -> DARK SHADE + '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL + '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT + '\u0104' # 0x00b5 -> LATIN CAPITAL LETTER A WITH OGONEK + '\u010c' # 0x00b6 -> LATIN CAPITAL LETTER C WITH CARON + '\u0118' # 0x00b7 -> LATIN CAPITAL LETTER E WITH OGONEK + '\u0116' # 0x00b8 -> LATIN CAPITAL LETTER E WITH DOT ABOVE + '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL + '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT + '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT + '\u012e' # 0x00bd -> LATIN CAPITAL LETTER I WITH OGONEK + '\u0160' # 0x00be -> LATIN CAPITAL LETTER S WITH CARON + '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT + '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT + '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL + '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT + '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL + '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + '\u0172' # 0x00c6 -> LATIN CAPITAL LETTER U WITH OGONEK + '\u016a' # 0x00c7 -> LATIN CAPITAL LETTER U WITH MACRON + '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT + '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL + '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + '\u017d' # 0x00cf -> LATIN CAPITAL LETTER Z WITH CARON + '\u0105' # 0x00d0 -> LATIN SMALL LETTER A WITH OGONEK + '\u010d' # 0x00d1 -> LATIN SMALL LETTER C WITH CARON + '\u0119' # 0x00d2 -> LATIN SMALL LETTER E WITH OGONEK + '\u0117' # 0x00d3 -> LATIN SMALL LETTER E WITH DOT ABOVE + '\u012f' # 0x00d4 -> LATIN SMALL LETTER I WITH OGONEK + '\u0161' # 0x00d5 -> LATIN SMALL LETTER S WITH CARON + '\u0173' # 0x00d6 -> LATIN SMALL LETTER U WITH OGONEK + '\u016b' # 0x00d7 -> LATIN SMALL LETTER U WITH MACRON + '\u017e' # 0x00d8 -> LATIN SMALL LETTER Z WITH CARON + '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT + '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT + '\u2588' # 0x00db -> FULL BLOCK + '\u2584' # 0x00dc -> LOWER HALF BLOCK + '\u258c' # 0x00dd -> LEFT HALF BLOCK + '\u2590' # 0x00de -> RIGHT HALF BLOCK + '\u2580' # 0x00df -> UPPER HALF BLOCK + '\xd3' # 0x00e0 -> LATIN CAPITAL LETTER O WITH ACUTE + '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S (GERMAN) + '\u014c' # 0x00e2 -> LATIN CAPITAL LETTER O WITH MACRON + '\u0143' # 0x00e3 -> LATIN CAPITAL LETTER N WITH ACUTE + '\xf5' # 0x00e4 -> LATIN SMALL LETTER O WITH TILDE + '\xd5' # 0x00e5 -> LATIN CAPITAL LETTER O WITH TILDE + '\xb5' # 0x00e6 -> MICRO SIGN + '\u0144' # 0x00e7 -> LATIN SMALL LETTER N WITH ACUTE + '\u0136' # 0x00e8 -> LATIN CAPITAL LETTER K WITH CEDILLA + '\u0137' # 0x00e9 -> LATIN SMALL LETTER K WITH CEDILLA + '\u013b' # 0x00ea -> LATIN CAPITAL LETTER L WITH CEDILLA + '\u013c' # 0x00eb -> LATIN SMALL LETTER L WITH CEDILLA + '\u0146' # 0x00ec -> LATIN SMALL LETTER N WITH CEDILLA + '\u0112' # 0x00ed -> LATIN CAPITAL LETTER E WITH MACRON + '\u0145' # 0x00ee -> LATIN CAPITAL LETTER N WITH CEDILLA + '\u2019' # 0x00ef -> RIGHT SINGLE QUOTATION MARK + '\xad' # 0x00f0 -> SOFT HYPHEN + '\xb1' # 0x00f1 -> PLUS-MINUS SIGN + '\u201c' # 0x00f2 -> LEFT DOUBLE QUOTATION MARK + '\xbe' # 0x00f3 -> VULGAR FRACTION THREE QUARTERS + '\xb6' # 0x00f4 -> PILCROW SIGN + '\xa7' # 0x00f5 -> SECTION SIGN + '\xf7' # 0x00f6 -> DIVISION SIGN + '\u201e' # 0x00f7 -> DOUBLE LOW-9 QUOTATION MARK + '\xb0' # 0x00f8 -> DEGREE SIGN + '\u2219' # 0x00f9 -> BULLET OPERATOR + '\xb7' # 0x00fa -> MIDDLE DOT + '\xb9' # 0x00fb -> SUPERSCRIPT ONE + '\xb3' # 0x00fc -> SUPERSCRIPT THREE + '\xb2' # 0x00fd -> SUPERSCRIPT TWO + '\u25a0' # 0x00fe -> BLACK SQUARE + '\xa0' # 0x00ff -> NO-BREAK SPACE +) + +### Encoding Map + +encoding_map = { + 0x0000: 0x0000, # NULL + 0x0001: 0x0001, # START OF HEADING + 0x0002: 0x0002, # START OF TEXT + 0x0003: 0x0003, # END OF TEXT + 0x0004: 0x0004, # END OF TRANSMISSION + 0x0005: 0x0005, # ENQUIRY + 0x0006: 0x0006, # ACKNOWLEDGE + 0x0007: 0x0007, # BELL + 0x0008: 0x0008, # BACKSPACE + 0x0009: 0x0009, # HORIZONTAL TABULATION + 0x000a: 0x000a, # LINE FEED + 0x000b: 0x000b, # VERTICAL TABULATION + 0x000c: 0x000c, # FORM FEED + 0x000d: 0x000d, # CARRIAGE RETURN + 0x000e: 0x000e, # SHIFT OUT + 0x000f: 0x000f, # SHIFT IN + 0x0010: 0x0010, # DATA LINK ESCAPE + 0x0011: 0x0011, # DEVICE CONTROL ONE + 0x0012: 0x0012, # DEVICE CONTROL TWO + 0x0013: 0x0013, # DEVICE CONTROL THREE + 0x0014: 0x0014, # DEVICE CONTROL FOUR + 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE + 0x0016: 0x0016, # SYNCHRONOUS IDLE + 0x0017: 0x0017, # END OF TRANSMISSION BLOCK + 0x0018: 0x0018, # CANCEL + 0x0019: 0x0019, # END OF MEDIUM + 0x001a: 0x001a, # SUBSTITUTE + 0x001b: 0x001b, # ESCAPE + 0x001c: 0x001c, # FILE SEPARATOR + 0x001d: 0x001d, # GROUP SEPARATOR + 0x001e: 0x001e, # RECORD SEPARATOR + 0x001f: 0x001f, # UNIT SEPARATOR + 0x0020: 0x0020, # SPACE + 0x0021: 0x0021, # EXCLAMATION MARK + 0x0022: 0x0022, # QUOTATION MARK + 0x0023: 0x0023, # NUMBER SIGN + 0x0024: 0x0024, # DOLLAR SIGN + 0x0025: 0x0025, # PERCENT SIGN + 0x0026: 0x0026, # AMPERSAND + 0x0027: 0x0027, # APOSTROPHE + 0x0028: 0x0028, # LEFT PARENTHESIS + 0x0029: 0x0029, # RIGHT PARENTHESIS + 0x002a: 0x002a, # ASTERISK + 0x002b: 0x002b, # PLUS SIGN + 0x002c: 0x002c, # COMMA + 0x002d: 0x002d, # HYPHEN-MINUS + 0x002e: 0x002e, # FULL STOP + 0x002f: 0x002f, # SOLIDUS + 0x0030: 0x0030, # DIGIT ZERO + 0x0031: 0x0031, # DIGIT ONE + 0x0032: 0x0032, # DIGIT TWO + 0x0033: 0x0033, # DIGIT THREE + 0x0034: 0x0034, # DIGIT FOUR + 0x0035: 0x0035, # DIGIT FIVE + 0x0036: 0x0036, # DIGIT SIX + 0x0037: 0x0037, # DIGIT SEVEN + 0x0038: 0x0038, # DIGIT EIGHT + 0x0039: 0x0039, # DIGIT NINE + 0x003a: 0x003a, # COLON + 0x003b: 0x003b, # SEMICOLON + 0x003c: 0x003c, # LESS-THAN SIGN + 0x003d: 0x003d, # EQUALS SIGN + 0x003e: 0x003e, # GREATER-THAN SIGN + 0x003f: 0x003f, # QUESTION MARK + 0x0040: 0x0040, # COMMERCIAL AT + 0x0041: 0x0041, # LATIN CAPITAL LETTER A + 0x0042: 0x0042, # LATIN CAPITAL LETTER B + 0x0043: 0x0043, # LATIN CAPITAL LETTER C + 0x0044: 0x0044, # LATIN CAPITAL LETTER D + 0x0045: 0x0045, # LATIN CAPITAL LETTER E + 0x0046: 0x0046, # LATIN CAPITAL LETTER F + 0x0047: 0x0047, # LATIN CAPITAL LETTER G + 0x0048: 0x0048, # LATIN CAPITAL LETTER H + 0x0049: 0x0049, # LATIN CAPITAL LETTER I + 0x004a: 0x004a, # LATIN CAPITAL LETTER J + 0x004b: 0x004b, # LATIN CAPITAL LETTER K + 0x004c: 0x004c, # LATIN CAPITAL LETTER L + 0x004d: 0x004d, # LATIN CAPITAL LETTER M + 0x004e: 0x004e, # LATIN CAPITAL LETTER N + 0x004f: 0x004f, # LATIN CAPITAL LETTER O + 0x0050: 0x0050, # LATIN CAPITAL LETTER P + 0x0051: 0x0051, # LATIN CAPITAL LETTER Q + 0x0052: 0x0052, # LATIN CAPITAL LETTER R + 0x0053: 0x0053, # LATIN CAPITAL LETTER S + 0x0054: 0x0054, # LATIN CAPITAL LETTER T + 0x0055: 0x0055, # LATIN CAPITAL LETTER U + 0x0056: 0x0056, # LATIN CAPITAL LETTER V + 0x0057: 0x0057, # LATIN CAPITAL LETTER W + 0x0058: 0x0058, # LATIN CAPITAL LETTER X + 0x0059: 0x0059, # LATIN CAPITAL LETTER Y + 0x005a: 0x005a, # LATIN CAPITAL LETTER Z + 0x005b: 0x005b, # LEFT SQUARE BRACKET + 0x005c: 0x005c, # REVERSE SOLIDUS + 0x005d: 0x005d, # RIGHT SQUARE BRACKET + 0x005e: 0x005e, # CIRCUMFLEX ACCENT + 0x005f: 0x005f, # LOW LINE + 0x0060: 0x0060, # GRAVE ACCENT + 0x0061: 0x0061, # LATIN SMALL LETTER A + 0x0062: 0x0062, # LATIN SMALL LETTER B + 0x0063: 0x0063, # LATIN SMALL LETTER C + 0x0064: 0x0064, # LATIN SMALL LETTER D + 0x0065: 0x0065, # LATIN SMALL LETTER E + 0x0066: 0x0066, # LATIN SMALL LETTER F + 0x0067: 0x0067, # LATIN SMALL LETTER G + 0x0068: 0x0068, # LATIN SMALL LETTER H + 0x0069: 0x0069, # LATIN SMALL LETTER I + 0x006a: 0x006a, # LATIN SMALL LETTER J + 0x006b: 0x006b, # LATIN SMALL LETTER K + 0x006c: 0x006c, # LATIN SMALL LETTER L + 0x006d: 0x006d, # LATIN SMALL LETTER M + 0x006e: 0x006e, # LATIN SMALL LETTER N + 0x006f: 0x006f, # LATIN SMALL LETTER O + 0x0070: 0x0070, # LATIN SMALL LETTER P + 0x0071: 0x0071, # LATIN SMALL LETTER Q + 0x0072: 0x0072, # LATIN SMALL LETTER R + 0x0073: 0x0073, # LATIN SMALL LETTER S + 0x0074: 0x0074, # LATIN SMALL LETTER T + 0x0075: 0x0075, # LATIN SMALL LETTER U + 0x0076: 0x0076, # LATIN SMALL LETTER V + 0x0077: 0x0077, # LATIN SMALL LETTER W + 0x0078: 0x0078, # LATIN SMALL LETTER X + 0x0079: 0x0079, # LATIN SMALL LETTER Y + 0x007a: 0x007a, # LATIN SMALL LETTER Z + 0x007b: 0x007b, # LEFT CURLY BRACKET + 0x007c: 0x007c, # VERTICAL LINE + 0x007d: 0x007d, # RIGHT CURLY BRACKET + 0x007e: 0x007e, # TILDE + 0x007f: 0x007f, # DELETE + 0x00a0: 0x00ff, # NO-BREAK SPACE + 0x00a2: 0x0096, # CENT SIGN + 0x00a3: 0x009c, # POUND SIGN + 0x00a4: 0x009f, # CURRENCY SIGN + 0x00a6: 0x00a7, # BROKEN BAR + 0x00a7: 0x00f5, # SECTION SIGN + 0x00a9: 0x00a8, # COPYRIGHT SIGN + 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00ac: 0x00aa, # NOT SIGN + 0x00ad: 0x00f0, # SOFT HYPHEN + 0x00ae: 0x00a9, # REGISTERED SIGN + 0x00b0: 0x00f8, # DEGREE SIGN + 0x00b1: 0x00f1, # PLUS-MINUS SIGN + 0x00b2: 0x00fd, # SUPERSCRIPT TWO + 0x00b3: 0x00fc, # SUPERSCRIPT THREE + 0x00b5: 0x00e6, # MICRO SIGN + 0x00b6: 0x00f4, # PILCROW SIGN + 0x00b7: 0x00fa, # MIDDLE DOT + 0x00b9: 0x00fb, # SUPERSCRIPT ONE + 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER + 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF + 0x00be: 0x00f3, # VULGAR FRACTION THREE QUARTERS + 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE + 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00d3: 0x00e0, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00d5: 0x00e5, # LATIN CAPITAL LETTER O WITH TILDE + 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00d7: 0x009e, # MULTIPLICATION SIGN + 0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE + 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S (GERMAN) + 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE + 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE + 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE + 0x00f5: 0x00e4, # LATIN SMALL LETTER O WITH TILDE + 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00f7: 0x00f6, # DIVISION SIGN + 0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE + 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS + 0x0100: 0x00a0, # LATIN CAPITAL LETTER A WITH MACRON + 0x0101: 0x0083, # LATIN SMALL LETTER A WITH MACRON + 0x0104: 0x00b5, # LATIN CAPITAL LETTER A WITH OGONEK + 0x0105: 0x00d0, # LATIN SMALL LETTER A WITH OGONEK + 0x0106: 0x0080, # LATIN CAPITAL LETTER C WITH ACUTE + 0x0107: 0x0087, # LATIN SMALL LETTER C WITH ACUTE + 0x010c: 0x00b6, # LATIN CAPITAL LETTER C WITH CARON + 0x010d: 0x00d1, # LATIN SMALL LETTER C WITH CARON + 0x0112: 0x00ed, # LATIN CAPITAL LETTER E WITH MACRON + 0x0113: 0x0089, # LATIN SMALL LETTER E WITH MACRON + 0x0116: 0x00b8, # LATIN CAPITAL LETTER E WITH DOT ABOVE + 0x0117: 0x00d3, # LATIN SMALL LETTER E WITH DOT ABOVE + 0x0118: 0x00b7, # LATIN CAPITAL LETTER E WITH OGONEK + 0x0119: 0x00d2, # LATIN SMALL LETTER E WITH OGONEK + 0x0122: 0x0095, # LATIN CAPITAL LETTER G WITH CEDILLA + 0x0123: 0x0085, # LATIN SMALL LETTER G WITH CEDILLA + 0x012a: 0x00a1, # LATIN CAPITAL LETTER I WITH MACRON + 0x012b: 0x008c, # LATIN SMALL LETTER I WITH MACRON + 0x012e: 0x00bd, # LATIN CAPITAL LETTER I WITH OGONEK + 0x012f: 0x00d4, # LATIN SMALL LETTER I WITH OGONEK + 0x0136: 0x00e8, # LATIN CAPITAL LETTER K WITH CEDILLA + 0x0137: 0x00e9, # LATIN SMALL LETTER K WITH CEDILLA + 0x013b: 0x00ea, # LATIN CAPITAL LETTER L WITH CEDILLA + 0x013c: 0x00eb, # LATIN SMALL LETTER L WITH CEDILLA + 0x0141: 0x00ad, # LATIN CAPITAL LETTER L WITH STROKE + 0x0142: 0x0088, # LATIN SMALL LETTER L WITH STROKE + 0x0143: 0x00e3, # LATIN CAPITAL LETTER N WITH ACUTE + 0x0144: 0x00e7, # LATIN SMALL LETTER N WITH ACUTE + 0x0145: 0x00ee, # LATIN CAPITAL LETTER N WITH CEDILLA + 0x0146: 0x00ec, # LATIN SMALL LETTER N WITH CEDILLA + 0x014c: 0x00e2, # LATIN CAPITAL LETTER O WITH MACRON + 0x014d: 0x0093, # LATIN SMALL LETTER O WITH MACRON + 0x0156: 0x008a, # LATIN CAPITAL LETTER R WITH CEDILLA + 0x0157: 0x008b, # LATIN SMALL LETTER R WITH CEDILLA + 0x015a: 0x0097, # LATIN CAPITAL LETTER S WITH ACUTE + 0x015b: 0x0098, # LATIN SMALL LETTER S WITH ACUTE + 0x0160: 0x00be, # LATIN CAPITAL LETTER S WITH CARON + 0x0161: 0x00d5, # LATIN SMALL LETTER S WITH CARON + 0x016a: 0x00c7, # LATIN CAPITAL LETTER U WITH MACRON + 0x016b: 0x00d7, # LATIN SMALL LETTER U WITH MACRON + 0x0172: 0x00c6, # LATIN CAPITAL LETTER U WITH OGONEK + 0x0173: 0x00d6, # LATIN SMALL LETTER U WITH OGONEK + 0x0179: 0x008d, # LATIN CAPITAL LETTER Z WITH ACUTE + 0x017a: 0x00a5, # LATIN SMALL LETTER Z WITH ACUTE + 0x017b: 0x00a3, # LATIN CAPITAL LETTER Z WITH DOT ABOVE + 0x017c: 0x00a4, # LATIN SMALL LETTER Z WITH DOT ABOVE + 0x017d: 0x00cf, # LATIN CAPITAL LETTER Z WITH CARON + 0x017e: 0x00d8, # LATIN SMALL LETTER Z WITH CARON + 0x2019: 0x00ef, # RIGHT SINGLE QUOTATION MARK + 0x201c: 0x00f2, # LEFT DOUBLE QUOTATION MARK + 0x201d: 0x00a6, # RIGHT DOUBLE QUOTATION MARK + 0x201e: 0x00f7, # DOUBLE LOW-9 QUOTATION MARK + 0x2219: 0x00f9, # BULLET OPERATOR + 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL + 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL + 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT + 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL + 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x2580: 0x00df, # UPPER HALF BLOCK + 0x2584: 0x00dc, # LOWER HALF BLOCK + 0x2588: 0x00db, # FULL BLOCK + 0x258c: 0x00dd, # LEFT HALF BLOCK + 0x2590: 0x00de, # RIGHT HALF BLOCK + 0x2591: 0x00b0, # LIGHT SHADE + 0x2592: 0x00b1, # MEDIUM SHADE + 0x2593: 0x00b2, # DARK SHADE + 0x25a0: 0x00fe, # BLACK SQUARE +} diff --git a/contrib/tools/python3/src/Lib/encodings/cp850.py b/contrib/tools/python3/src/Lib/encodings/cp850.py new file mode 100644 index 0000000000..f98aef99fb --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp850.py @@ -0,0 +1,698 @@ +""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP850.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_map) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp850', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + +### Decoding Map + +decoding_map = codecs.make_identity_dict(range(256)) +decoding_map.update({ + 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS + 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE + 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE + 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE + 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA + 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS + 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE + 0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS + 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x008d: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE + 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE + 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE + 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE + 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE + 0x0098: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE + 0x009c: 0x00a3, # POUND SIGN + 0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE + 0x009e: 0x00d7, # MULTIPLICATION SIGN + 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK + 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE + 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE + 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE + 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE + 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE + 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE + 0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR + 0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR + 0x00a8: 0x00bf, # INVERTED QUESTION MARK + 0x00a9: 0x00ae, # REGISTERED SIGN + 0x00aa: 0x00ac, # NOT SIGN + 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF + 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER + 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK + 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00b0: 0x2591, # LIGHT SHADE + 0x00b1: 0x2592, # MEDIUM SHADE + 0x00b2: 0x2593, # DARK SHADE + 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL + 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x00b5: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00b6: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00b7: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00b8: 0x00a9, # COPYRIGHT SIGN + 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL + 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x00bd: 0x00a2, # CENT SIGN + 0x00be: 0x00a5, # YEN SIGN + 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL + 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x00c6: 0x00e3, # LATIN SMALL LETTER A WITH TILDE + 0x00c7: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE + 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x00cf: 0x00a4, # CURRENCY SIGN + 0x00d0: 0x00f0, # LATIN SMALL LETTER ETH + 0x00d1: 0x00d0, # LATIN CAPITAL LETTER ETH + 0x00d2: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00d3: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00d4: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00d5: 0x0131, # LATIN SMALL LETTER DOTLESS I + 0x00d6: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00d7: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00d8: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT + 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x00db: 0x2588, # FULL BLOCK + 0x00dc: 0x2584, # LOWER HALF BLOCK + 0x00dd: 0x00a6, # BROKEN BAR + 0x00de: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00df: 0x2580, # UPPER HALF BLOCK + 0x00e0: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S + 0x00e2: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00e3: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00e4: 0x00f5, # LATIN SMALL LETTER O WITH TILDE + 0x00e5: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE + 0x00e6: 0x00b5, # MICRO SIGN + 0x00e7: 0x00fe, # LATIN SMALL LETTER THORN + 0x00e8: 0x00de, # LATIN CAPITAL LETTER THORN + 0x00e9: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00ea: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00eb: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00ec: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE + 0x00ed: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE + 0x00ee: 0x00af, # MACRON + 0x00ef: 0x00b4, # ACUTE ACCENT + 0x00f0: 0x00ad, # SOFT HYPHEN + 0x00f1: 0x00b1, # PLUS-MINUS SIGN + 0x00f2: 0x2017, # DOUBLE LOW LINE + 0x00f3: 0x00be, # VULGAR FRACTION THREE QUARTERS + 0x00f4: 0x00b6, # PILCROW SIGN + 0x00f5: 0x00a7, # SECTION SIGN + 0x00f6: 0x00f7, # DIVISION SIGN + 0x00f7: 0x00b8, # CEDILLA + 0x00f8: 0x00b0, # DEGREE SIGN + 0x00f9: 0x00a8, # DIAERESIS + 0x00fa: 0x00b7, # MIDDLE DOT + 0x00fb: 0x00b9, # SUPERSCRIPT ONE + 0x00fc: 0x00b3, # SUPERSCRIPT THREE + 0x00fd: 0x00b2, # SUPERSCRIPT TWO + 0x00fe: 0x25a0, # BLACK SQUARE + 0x00ff: 0x00a0, # NO-BREAK SPACE +}) + +### Decoding Table + +decoding_table = ( + '\x00' # 0x0000 -> NULL + '\x01' # 0x0001 -> START OF HEADING + '\x02' # 0x0002 -> START OF TEXT + '\x03' # 0x0003 -> END OF TEXT + '\x04' # 0x0004 -> END OF TRANSMISSION + '\x05' # 0x0005 -> ENQUIRY + '\x06' # 0x0006 -> ACKNOWLEDGE + '\x07' # 0x0007 -> BELL + '\x08' # 0x0008 -> BACKSPACE + '\t' # 0x0009 -> HORIZONTAL TABULATION + '\n' # 0x000a -> LINE FEED + '\x0b' # 0x000b -> VERTICAL TABULATION + '\x0c' # 0x000c -> FORM FEED + '\r' # 0x000d -> CARRIAGE RETURN + '\x0e' # 0x000e -> SHIFT OUT + '\x0f' # 0x000f -> SHIFT IN + '\x10' # 0x0010 -> DATA LINK ESCAPE + '\x11' # 0x0011 -> DEVICE CONTROL ONE + '\x12' # 0x0012 -> DEVICE CONTROL TWO + '\x13' # 0x0013 -> DEVICE CONTROL THREE + '\x14' # 0x0014 -> DEVICE CONTROL FOUR + '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x0016 -> SYNCHRONOUS IDLE + '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK + '\x18' # 0x0018 -> CANCEL + '\x19' # 0x0019 -> END OF MEDIUM + '\x1a' # 0x001a -> SUBSTITUTE + '\x1b' # 0x001b -> ESCAPE + '\x1c' # 0x001c -> FILE SEPARATOR + '\x1d' # 0x001d -> GROUP SEPARATOR + '\x1e' # 0x001e -> RECORD SEPARATOR + '\x1f' # 0x001f -> UNIT SEPARATOR + ' ' # 0x0020 -> SPACE + '!' # 0x0021 -> EXCLAMATION MARK + '"' # 0x0022 -> QUOTATION MARK + '#' # 0x0023 -> NUMBER SIGN + '$' # 0x0024 -> DOLLAR SIGN + '%' # 0x0025 -> PERCENT SIGN + '&' # 0x0026 -> AMPERSAND + "'" # 0x0027 -> APOSTROPHE + '(' # 0x0028 -> LEFT PARENTHESIS + ')' # 0x0029 -> RIGHT PARENTHESIS + '*' # 0x002a -> ASTERISK + '+' # 0x002b -> PLUS SIGN + ',' # 0x002c -> COMMA + '-' # 0x002d -> HYPHEN-MINUS + '.' # 0x002e -> FULL STOP + '/' # 0x002f -> SOLIDUS + '0' # 0x0030 -> DIGIT ZERO + '1' # 0x0031 -> DIGIT ONE + '2' # 0x0032 -> DIGIT TWO + '3' # 0x0033 -> DIGIT THREE + '4' # 0x0034 -> DIGIT FOUR + '5' # 0x0035 -> DIGIT FIVE + '6' # 0x0036 -> DIGIT SIX + '7' # 0x0037 -> DIGIT SEVEN + '8' # 0x0038 -> DIGIT EIGHT + '9' # 0x0039 -> DIGIT NINE + ':' # 0x003a -> COLON + ';' # 0x003b -> SEMICOLON + '<' # 0x003c -> LESS-THAN SIGN + '=' # 0x003d -> EQUALS SIGN + '>' # 0x003e -> GREATER-THAN SIGN + '?' # 0x003f -> QUESTION MARK + '@' # 0x0040 -> COMMERCIAL AT + 'A' # 0x0041 -> LATIN CAPITAL LETTER A + 'B' # 0x0042 -> LATIN CAPITAL LETTER B + 'C' # 0x0043 -> LATIN CAPITAL LETTER C + 'D' # 0x0044 -> LATIN CAPITAL LETTER D + 'E' # 0x0045 -> LATIN CAPITAL LETTER E + 'F' # 0x0046 -> LATIN CAPITAL LETTER F + 'G' # 0x0047 -> LATIN CAPITAL LETTER G + 'H' # 0x0048 -> LATIN CAPITAL LETTER H + 'I' # 0x0049 -> LATIN CAPITAL LETTER I + 'J' # 0x004a -> LATIN CAPITAL LETTER J + 'K' # 0x004b -> LATIN CAPITAL LETTER K + 'L' # 0x004c -> LATIN CAPITAL LETTER L + 'M' # 0x004d -> LATIN CAPITAL LETTER M + 'N' # 0x004e -> LATIN CAPITAL LETTER N + 'O' # 0x004f -> LATIN CAPITAL LETTER O + 'P' # 0x0050 -> LATIN CAPITAL LETTER P + 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q + 'R' # 0x0052 -> LATIN CAPITAL LETTER R + 'S' # 0x0053 -> LATIN CAPITAL LETTER S + 'T' # 0x0054 -> LATIN CAPITAL LETTER T + 'U' # 0x0055 -> LATIN CAPITAL LETTER U + 'V' # 0x0056 -> LATIN CAPITAL LETTER V + 'W' # 0x0057 -> LATIN CAPITAL LETTER W + 'X' # 0x0058 -> LATIN CAPITAL LETTER X + 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y + 'Z' # 0x005a -> LATIN CAPITAL LETTER Z + '[' # 0x005b -> LEFT SQUARE BRACKET + '\\' # 0x005c -> REVERSE SOLIDUS + ']' # 0x005d -> RIGHT SQUARE BRACKET + '^' # 0x005e -> CIRCUMFLEX ACCENT + '_' # 0x005f -> LOW LINE + '`' # 0x0060 -> GRAVE ACCENT + 'a' # 0x0061 -> LATIN SMALL LETTER A + 'b' # 0x0062 -> LATIN SMALL LETTER B + 'c' # 0x0063 -> LATIN SMALL LETTER C + 'd' # 0x0064 -> LATIN SMALL LETTER D + 'e' # 0x0065 -> LATIN SMALL LETTER E + 'f' # 0x0066 -> LATIN SMALL LETTER F + 'g' # 0x0067 -> LATIN SMALL LETTER G + 'h' # 0x0068 -> LATIN SMALL LETTER H + 'i' # 0x0069 -> LATIN SMALL LETTER I + 'j' # 0x006a -> LATIN SMALL LETTER J + 'k' # 0x006b -> LATIN SMALL LETTER K + 'l' # 0x006c -> LATIN SMALL LETTER L + 'm' # 0x006d -> LATIN SMALL LETTER M + 'n' # 0x006e -> LATIN SMALL LETTER N + 'o' # 0x006f -> LATIN SMALL LETTER O + 'p' # 0x0070 -> LATIN SMALL LETTER P + 'q' # 0x0071 -> LATIN SMALL LETTER Q + 'r' # 0x0072 -> LATIN SMALL LETTER R + 's' # 0x0073 -> LATIN SMALL LETTER S + 't' # 0x0074 -> LATIN SMALL LETTER T + 'u' # 0x0075 -> LATIN SMALL LETTER U + 'v' # 0x0076 -> LATIN SMALL LETTER V + 'w' # 0x0077 -> LATIN SMALL LETTER W + 'x' # 0x0078 -> LATIN SMALL LETTER X + 'y' # 0x0079 -> LATIN SMALL LETTER Y + 'z' # 0x007a -> LATIN SMALL LETTER Z + '{' # 0x007b -> LEFT CURLY BRACKET + '|' # 0x007c -> VERTICAL LINE + '}' # 0x007d -> RIGHT CURLY BRACKET + '~' # 0x007e -> TILDE + '\x7f' # 0x007f -> DELETE + '\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS + '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE + '\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE + '\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA + '\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS + '\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE + '\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS + '\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xec' # 0x008d -> LATIN SMALL LETTER I WITH GRAVE + '\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE + '\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE + '\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE + '\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE + '\xff' # 0x0098 -> LATIN SMALL LETTER Y WITH DIAERESIS + '\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE + '\xa3' # 0x009c -> POUND SIGN + '\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE + '\xd7' # 0x009e -> MULTIPLICATION SIGN + '\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK + '\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE + '\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE + '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE + '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE + '\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE + '\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE + '\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR + '\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR + '\xbf' # 0x00a8 -> INVERTED QUESTION MARK + '\xae' # 0x00a9 -> REGISTERED SIGN + '\xac' # 0x00aa -> NOT SIGN + '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF + '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER + '\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK + '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u2591' # 0x00b0 -> LIGHT SHADE + '\u2592' # 0x00b1 -> MEDIUM SHADE + '\u2593' # 0x00b2 -> DARK SHADE + '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL + '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT + '\xc1' # 0x00b5 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc2' # 0x00b6 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xc0' # 0x00b7 -> LATIN CAPITAL LETTER A WITH GRAVE + '\xa9' # 0x00b8 -> COPYRIGHT SIGN + '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL + '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT + '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT + '\xa2' # 0x00bd -> CENT SIGN + '\xa5' # 0x00be -> YEN SIGN + '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT + '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT + '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL + '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT + '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL + '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + '\xe3' # 0x00c6 -> LATIN SMALL LETTER A WITH TILDE + '\xc3' # 0x00c7 -> LATIN CAPITAL LETTER A WITH TILDE + '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT + '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL + '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + '\xa4' # 0x00cf -> CURRENCY SIGN + '\xf0' # 0x00d0 -> LATIN SMALL LETTER ETH + '\xd0' # 0x00d1 -> LATIN CAPITAL LETTER ETH + '\xca' # 0x00d2 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xcb' # 0x00d3 -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xc8' # 0x00d4 -> LATIN CAPITAL LETTER E WITH GRAVE + '\u0131' # 0x00d5 -> LATIN SMALL LETTER DOTLESS I + '\xcd' # 0x00d6 -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0x00d7 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0x00d8 -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT + '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT + '\u2588' # 0x00db -> FULL BLOCK + '\u2584' # 0x00dc -> LOWER HALF BLOCK + '\xa6' # 0x00dd -> BROKEN BAR + '\xcc' # 0x00de -> LATIN CAPITAL LETTER I WITH GRAVE + '\u2580' # 0x00df -> UPPER HALF BLOCK + '\xd3' # 0x00e0 -> LATIN CAPITAL LETTER O WITH ACUTE + '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S + '\xd4' # 0x00e2 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\xd2' # 0x00e3 -> LATIN CAPITAL LETTER O WITH GRAVE + '\xf5' # 0x00e4 -> LATIN SMALL LETTER O WITH TILDE + '\xd5' # 0x00e5 -> LATIN CAPITAL LETTER O WITH TILDE + '\xb5' # 0x00e6 -> MICRO SIGN + '\xfe' # 0x00e7 -> LATIN SMALL LETTER THORN + '\xde' # 0x00e8 -> LATIN CAPITAL LETTER THORN + '\xda' # 0x00e9 -> LATIN CAPITAL LETTER U WITH ACUTE + '\xdb' # 0x00ea -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xd9' # 0x00eb -> LATIN CAPITAL LETTER U WITH GRAVE + '\xfd' # 0x00ec -> LATIN SMALL LETTER Y WITH ACUTE + '\xdd' # 0x00ed -> LATIN CAPITAL LETTER Y WITH ACUTE + '\xaf' # 0x00ee -> MACRON + '\xb4' # 0x00ef -> ACUTE ACCENT + '\xad' # 0x00f0 -> SOFT HYPHEN + '\xb1' # 0x00f1 -> PLUS-MINUS SIGN + '\u2017' # 0x00f2 -> DOUBLE LOW LINE + '\xbe' # 0x00f3 -> VULGAR FRACTION THREE QUARTERS + '\xb6' # 0x00f4 -> PILCROW SIGN + '\xa7' # 0x00f5 -> SECTION SIGN + '\xf7' # 0x00f6 -> DIVISION SIGN + '\xb8' # 0x00f7 -> CEDILLA + '\xb0' # 0x00f8 -> DEGREE SIGN + '\xa8' # 0x00f9 -> DIAERESIS + '\xb7' # 0x00fa -> MIDDLE DOT + '\xb9' # 0x00fb -> SUPERSCRIPT ONE + '\xb3' # 0x00fc -> SUPERSCRIPT THREE + '\xb2' # 0x00fd -> SUPERSCRIPT TWO + '\u25a0' # 0x00fe -> BLACK SQUARE + '\xa0' # 0x00ff -> NO-BREAK SPACE +) + +### Encoding Map + +encoding_map = { + 0x0000: 0x0000, # NULL + 0x0001: 0x0001, # START OF HEADING + 0x0002: 0x0002, # START OF TEXT + 0x0003: 0x0003, # END OF TEXT + 0x0004: 0x0004, # END OF TRANSMISSION + 0x0005: 0x0005, # ENQUIRY + 0x0006: 0x0006, # ACKNOWLEDGE + 0x0007: 0x0007, # BELL + 0x0008: 0x0008, # BACKSPACE + 0x0009: 0x0009, # HORIZONTAL TABULATION + 0x000a: 0x000a, # LINE FEED + 0x000b: 0x000b, # VERTICAL TABULATION + 0x000c: 0x000c, # FORM FEED + 0x000d: 0x000d, # CARRIAGE RETURN + 0x000e: 0x000e, # SHIFT OUT + 0x000f: 0x000f, # SHIFT IN + 0x0010: 0x0010, # DATA LINK ESCAPE + 0x0011: 0x0011, # DEVICE CONTROL ONE + 0x0012: 0x0012, # DEVICE CONTROL TWO + 0x0013: 0x0013, # DEVICE CONTROL THREE + 0x0014: 0x0014, # DEVICE CONTROL FOUR + 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE + 0x0016: 0x0016, # SYNCHRONOUS IDLE + 0x0017: 0x0017, # END OF TRANSMISSION BLOCK + 0x0018: 0x0018, # CANCEL + 0x0019: 0x0019, # END OF MEDIUM + 0x001a: 0x001a, # SUBSTITUTE + 0x001b: 0x001b, # ESCAPE + 0x001c: 0x001c, # FILE SEPARATOR + 0x001d: 0x001d, # GROUP SEPARATOR + 0x001e: 0x001e, # RECORD SEPARATOR + 0x001f: 0x001f, # UNIT SEPARATOR + 0x0020: 0x0020, # SPACE + 0x0021: 0x0021, # EXCLAMATION MARK + 0x0022: 0x0022, # QUOTATION MARK + 0x0023: 0x0023, # NUMBER SIGN + 0x0024: 0x0024, # DOLLAR SIGN + 0x0025: 0x0025, # PERCENT SIGN + 0x0026: 0x0026, # AMPERSAND + 0x0027: 0x0027, # APOSTROPHE + 0x0028: 0x0028, # LEFT PARENTHESIS + 0x0029: 0x0029, # RIGHT PARENTHESIS + 0x002a: 0x002a, # ASTERISK + 0x002b: 0x002b, # PLUS SIGN + 0x002c: 0x002c, # COMMA + 0x002d: 0x002d, # HYPHEN-MINUS + 0x002e: 0x002e, # FULL STOP + 0x002f: 0x002f, # SOLIDUS + 0x0030: 0x0030, # DIGIT ZERO + 0x0031: 0x0031, # DIGIT ONE + 0x0032: 0x0032, # DIGIT TWO + 0x0033: 0x0033, # DIGIT THREE + 0x0034: 0x0034, # DIGIT FOUR + 0x0035: 0x0035, # DIGIT FIVE + 0x0036: 0x0036, # DIGIT SIX + 0x0037: 0x0037, # DIGIT SEVEN + 0x0038: 0x0038, # DIGIT EIGHT + 0x0039: 0x0039, # DIGIT NINE + 0x003a: 0x003a, # COLON + 0x003b: 0x003b, # SEMICOLON + 0x003c: 0x003c, # LESS-THAN SIGN + 0x003d: 0x003d, # EQUALS SIGN + 0x003e: 0x003e, # GREATER-THAN SIGN + 0x003f: 0x003f, # QUESTION MARK + 0x0040: 0x0040, # COMMERCIAL AT + 0x0041: 0x0041, # LATIN CAPITAL LETTER A + 0x0042: 0x0042, # LATIN CAPITAL LETTER B + 0x0043: 0x0043, # LATIN CAPITAL LETTER C + 0x0044: 0x0044, # LATIN CAPITAL LETTER D + 0x0045: 0x0045, # LATIN CAPITAL LETTER E + 0x0046: 0x0046, # LATIN CAPITAL LETTER F + 0x0047: 0x0047, # LATIN CAPITAL LETTER G + 0x0048: 0x0048, # LATIN CAPITAL LETTER H + 0x0049: 0x0049, # LATIN CAPITAL LETTER I + 0x004a: 0x004a, # LATIN CAPITAL LETTER J + 0x004b: 0x004b, # LATIN CAPITAL LETTER K + 0x004c: 0x004c, # LATIN CAPITAL LETTER L + 0x004d: 0x004d, # LATIN CAPITAL LETTER M + 0x004e: 0x004e, # LATIN CAPITAL LETTER N + 0x004f: 0x004f, # LATIN CAPITAL LETTER O + 0x0050: 0x0050, # LATIN CAPITAL LETTER P + 0x0051: 0x0051, # LATIN CAPITAL LETTER Q + 0x0052: 0x0052, # LATIN CAPITAL LETTER R + 0x0053: 0x0053, # LATIN CAPITAL LETTER S + 0x0054: 0x0054, # LATIN CAPITAL LETTER T + 0x0055: 0x0055, # LATIN CAPITAL LETTER U + 0x0056: 0x0056, # LATIN CAPITAL LETTER V + 0x0057: 0x0057, # LATIN CAPITAL LETTER W + 0x0058: 0x0058, # LATIN CAPITAL LETTER X + 0x0059: 0x0059, # LATIN CAPITAL LETTER Y + 0x005a: 0x005a, # LATIN CAPITAL LETTER Z + 0x005b: 0x005b, # LEFT SQUARE BRACKET + 0x005c: 0x005c, # REVERSE SOLIDUS + 0x005d: 0x005d, # RIGHT SQUARE BRACKET + 0x005e: 0x005e, # CIRCUMFLEX ACCENT + 0x005f: 0x005f, # LOW LINE + 0x0060: 0x0060, # GRAVE ACCENT + 0x0061: 0x0061, # LATIN SMALL LETTER A + 0x0062: 0x0062, # LATIN SMALL LETTER B + 0x0063: 0x0063, # LATIN SMALL LETTER C + 0x0064: 0x0064, # LATIN SMALL LETTER D + 0x0065: 0x0065, # LATIN SMALL LETTER E + 0x0066: 0x0066, # LATIN SMALL LETTER F + 0x0067: 0x0067, # LATIN SMALL LETTER G + 0x0068: 0x0068, # LATIN SMALL LETTER H + 0x0069: 0x0069, # LATIN SMALL LETTER I + 0x006a: 0x006a, # LATIN SMALL LETTER J + 0x006b: 0x006b, # LATIN SMALL LETTER K + 0x006c: 0x006c, # LATIN SMALL LETTER L + 0x006d: 0x006d, # LATIN SMALL LETTER M + 0x006e: 0x006e, # LATIN SMALL LETTER N + 0x006f: 0x006f, # LATIN SMALL LETTER O + 0x0070: 0x0070, # LATIN SMALL LETTER P + 0x0071: 0x0071, # LATIN SMALL LETTER Q + 0x0072: 0x0072, # LATIN SMALL LETTER R + 0x0073: 0x0073, # LATIN SMALL LETTER S + 0x0074: 0x0074, # LATIN SMALL LETTER T + 0x0075: 0x0075, # LATIN SMALL LETTER U + 0x0076: 0x0076, # LATIN SMALL LETTER V + 0x0077: 0x0077, # LATIN SMALL LETTER W + 0x0078: 0x0078, # LATIN SMALL LETTER X + 0x0079: 0x0079, # LATIN SMALL LETTER Y + 0x007a: 0x007a, # LATIN SMALL LETTER Z + 0x007b: 0x007b, # LEFT CURLY BRACKET + 0x007c: 0x007c, # VERTICAL LINE + 0x007d: 0x007d, # RIGHT CURLY BRACKET + 0x007e: 0x007e, # TILDE + 0x007f: 0x007f, # DELETE + 0x00a0: 0x00ff, # NO-BREAK SPACE + 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK + 0x00a2: 0x00bd, # CENT SIGN + 0x00a3: 0x009c, # POUND SIGN + 0x00a4: 0x00cf, # CURRENCY SIGN + 0x00a5: 0x00be, # YEN SIGN + 0x00a6: 0x00dd, # BROKEN BAR + 0x00a7: 0x00f5, # SECTION SIGN + 0x00a8: 0x00f9, # DIAERESIS + 0x00a9: 0x00b8, # COPYRIGHT SIGN + 0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR + 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00ac: 0x00aa, # NOT SIGN + 0x00ad: 0x00f0, # SOFT HYPHEN + 0x00ae: 0x00a9, # REGISTERED SIGN + 0x00af: 0x00ee, # MACRON + 0x00b0: 0x00f8, # DEGREE SIGN + 0x00b1: 0x00f1, # PLUS-MINUS SIGN + 0x00b2: 0x00fd, # SUPERSCRIPT TWO + 0x00b3: 0x00fc, # SUPERSCRIPT THREE + 0x00b4: 0x00ef, # ACUTE ACCENT + 0x00b5: 0x00e6, # MICRO SIGN + 0x00b6: 0x00f4, # PILCROW SIGN + 0x00b7: 0x00fa, # MIDDLE DOT + 0x00b8: 0x00f7, # CEDILLA + 0x00b9: 0x00fb, # SUPERSCRIPT ONE + 0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR + 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER + 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF + 0x00be: 0x00f3, # VULGAR FRACTION THREE QUARTERS + 0x00bf: 0x00a8, # INVERTED QUESTION MARK + 0x00c0: 0x00b7, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00c1: 0x00b5, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00c2: 0x00b6, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00c3: 0x00c7, # LATIN CAPITAL LETTER A WITH TILDE + 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE + 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00c8: 0x00d4, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00ca: 0x00d2, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00cb: 0x00d3, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00cc: 0x00de, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00cd: 0x00d6, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00ce: 0x00d7, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00cf: 0x00d8, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00d0: 0x00d1, # LATIN CAPITAL LETTER ETH + 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE + 0x00d2: 0x00e3, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00d3: 0x00e0, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00d4: 0x00e2, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00d5: 0x00e5, # LATIN CAPITAL LETTER O WITH TILDE + 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00d7: 0x009e, # MULTIPLICATION SIGN + 0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE + 0x00d9: 0x00eb, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00da: 0x00e9, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00db: 0x00ea, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00dd: 0x00ed, # LATIN CAPITAL LETTER Y WITH ACUTE + 0x00de: 0x00e8, # LATIN CAPITAL LETTER THORN + 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S + 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE + 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE + 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00e3: 0x00c6, # LATIN SMALL LETTER A WITH TILDE + 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE + 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA + 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE + 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE + 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00ec: 0x008d, # LATIN SMALL LETTER I WITH GRAVE + 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE + 0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00f0: 0x00d0, # LATIN SMALL LETTER ETH + 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE + 0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE + 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE + 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00f5: 0x00e4, # LATIN SMALL LETTER O WITH TILDE + 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00f7: 0x00f6, # DIVISION SIGN + 0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE + 0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE + 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE + 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00fd: 0x00ec, # LATIN SMALL LETTER Y WITH ACUTE + 0x00fe: 0x00e7, # LATIN SMALL LETTER THORN + 0x00ff: 0x0098, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x0131: 0x00d5, # LATIN SMALL LETTER DOTLESS I + 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK + 0x2017: 0x00f2, # DOUBLE LOW LINE + 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL + 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL + 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT + 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL + 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x2580: 0x00df, # UPPER HALF BLOCK + 0x2584: 0x00dc, # LOWER HALF BLOCK + 0x2588: 0x00db, # FULL BLOCK + 0x2591: 0x00b0, # LIGHT SHADE + 0x2592: 0x00b1, # MEDIUM SHADE + 0x2593: 0x00b2, # DARK SHADE + 0x25a0: 0x00fe, # BLACK SQUARE +} diff --git a/contrib/tools/python3/src/Lib/encodings/cp852.py b/contrib/tools/python3/src/Lib/encodings/cp852.py new file mode 100644 index 0000000000..34d8a0ea5a --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp852.py @@ -0,0 +1,698 @@ +""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP852.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_map) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp852', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + +### Decoding Map + +decoding_map = codecs.make_identity_dict(range(256)) +decoding_map.update({ + 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS + 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE + 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x0085: 0x016f, # LATIN SMALL LETTER U WITH RING ABOVE + 0x0086: 0x0107, # LATIN SMALL LETTER C WITH ACUTE + 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA + 0x0088: 0x0142, # LATIN SMALL LETTER L WITH STROKE + 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS + 0x008a: 0x0150, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE + 0x008b: 0x0151, # LATIN SMALL LETTER O WITH DOUBLE ACUTE + 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x008d: 0x0179, # LATIN CAPITAL LETTER Z WITH ACUTE + 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x008f: 0x0106, # LATIN CAPITAL LETTER C WITH ACUTE + 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x0091: 0x0139, # LATIN CAPITAL LETTER L WITH ACUTE + 0x0092: 0x013a, # LATIN SMALL LETTER L WITH ACUTE + 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x0095: 0x013d, # LATIN CAPITAL LETTER L WITH CARON + 0x0096: 0x013e, # LATIN SMALL LETTER L WITH CARON + 0x0097: 0x015a, # LATIN CAPITAL LETTER S WITH ACUTE + 0x0098: 0x015b, # LATIN SMALL LETTER S WITH ACUTE + 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x009b: 0x0164, # LATIN CAPITAL LETTER T WITH CARON + 0x009c: 0x0165, # LATIN SMALL LETTER T WITH CARON + 0x009d: 0x0141, # LATIN CAPITAL LETTER L WITH STROKE + 0x009e: 0x00d7, # MULTIPLICATION SIGN + 0x009f: 0x010d, # LATIN SMALL LETTER C WITH CARON + 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE + 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE + 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE + 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE + 0x00a4: 0x0104, # LATIN CAPITAL LETTER A WITH OGONEK + 0x00a5: 0x0105, # LATIN SMALL LETTER A WITH OGONEK + 0x00a6: 0x017d, # LATIN CAPITAL LETTER Z WITH CARON + 0x00a7: 0x017e, # LATIN SMALL LETTER Z WITH CARON + 0x00a8: 0x0118, # LATIN CAPITAL LETTER E WITH OGONEK + 0x00a9: 0x0119, # LATIN SMALL LETTER E WITH OGONEK + 0x00aa: 0x00ac, # NOT SIGN + 0x00ab: 0x017a, # LATIN SMALL LETTER Z WITH ACUTE + 0x00ac: 0x010c, # LATIN CAPITAL LETTER C WITH CARON + 0x00ad: 0x015f, # LATIN SMALL LETTER S WITH CEDILLA + 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00b0: 0x2591, # LIGHT SHADE + 0x00b1: 0x2592, # MEDIUM SHADE + 0x00b2: 0x2593, # DARK SHADE + 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL + 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x00b5: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00b6: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00b7: 0x011a, # LATIN CAPITAL LETTER E WITH CARON + 0x00b8: 0x015e, # LATIN CAPITAL LETTER S WITH CEDILLA + 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL + 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x00bd: 0x017b, # LATIN CAPITAL LETTER Z WITH DOT ABOVE + 0x00be: 0x017c, # LATIN SMALL LETTER Z WITH DOT ABOVE + 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL + 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x00c6: 0x0102, # LATIN CAPITAL LETTER A WITH BREVE + 0x00c7: 0x0103, # LATIN SMALL LETTER A WITH BREVE + 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x00cf: 0x00a4, # CURRENCY SIGN + 0x00d0: 0x0111, # LATIN SMALL LETTER D WITH STROKE + 0x00d1: 0x0110, # LATIN CAPITAL LETTER D WITH STROKE + 0x00d2: 0x010e, # LATIN CAPITAL LETTER D WITH CARON + 0x00d3: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00d4: 0x010f, # LATIN SMALL LETTER D WITH CARON + 0x00d5: 0x0147, # LATIN CAPITAL LETTER N WITH CARON + 0x00d6: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00d7: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00d8: 0x011b, # LATIN SMALL LETTER E WITH CARON + 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT + 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x00db: 0x2588, # FULL BLOCK + 0x00dc: 0x2584, # LOWER HALF BLOCK + 0x00dd: 0x0162, # LATIN CAPITAL LETTER T WITH CEDILLA + 0x00de: 0x016e, # LATIN CAPITAL LETTER U WITH RING ABOVE + 0x00df: 0x2580, # UPPER HALF BLOCK + 0x00e0: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S + 0x00e2: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00e3: 0x0143, # LATIN CAPITAL LETTER N WITH ACUTE + 0x00e4: 0x0144, # LATIN SMALL LETTER N WITH ACUTE + 0x00e5: 0x0148, # LATIN SMALL LETTER N WITH CARON + 0x00e6: 0x0160, # LATIN CAPITAL LETTER S WITH CARON + 0x00e7: 0x0161, # LATIN SMALL LETTER S WITH CARON + 0x00e8: 0x0154, # LATIN CAPITAL LETTER R WITH ACUTE + 0x00e9: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00ea: 0x0155, # LATIN SMALL LETTER R WITH ACUTE + 0x00eb: 0x0170, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE + 0x00ec: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE + 0x00ed: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE + 0x00ee: 0x0163, # LATIN SMALL LETTER T WITH CEDILLA + 0x00ef: 0x00b4, # ACUTE ACCENT + 0x00f0: 0x00ad, # SOFT HYPHEN + 0x00f1: 0x02dd, # DOUBLE ACUTE ACCENT + 0x00f2: 0x02db, # OGONEK + 0x00f3: 0x02c7, # CARON + 0x00f4: 0x02d8, # BREVE + 0x00f5: 0x00a7, # SECTION SIGN + 0x00f6: 0x00f7, # DIVISION SIGN + 0x00f7: 0x00b8, # CEDILLA + 0x00f8: 0x00b0, # DEGREE SIGN + 0x00f9: 0x00a8, # DIAERESIS + 0x00fa: 0x02d9, # DOT ABOVE + 0x00fb: 0x0171, # LATIN SMALL LETTER U WITH DOUBLE ACUTE + 0x00fc: 0x0158, # LATIN CAPITAL LETTER R WITH CARON + 0x00fd: 0x0159, # LATIN SMALL LETTER R WITH CARON + 0x00fe: 0x25a0, # BLACK SQUARE + 0x00ff: 0x00a0, # NO-BREAK SPACE +}) + +### Decoding Table + +decoding_table = ( + '\x00' # 0x0000 -> NULL + '\x01' # 0x0001 -> START OF HEADING + '\x02' # 0x0002 -> START OF TEXT + '\x03' # 0x0003 -> END OF TEXT + '\x04' # 0x0004 -> END OF TRANSMISSION + '\x05' # 0x0005 -> ENQUIRY + '\x06' # 0x0006 -> ACKNOWLEDGE + '\x07' # 0x0007 -> BELL + '\x08' # 0x0008 -> BACKSPACE + '\t' # 0x0009 -> HORIZONTAL TABULATION + '\n' # 0x000a -> LINE FEED + '\x0b' # 0x000b -> VERTICAL TABULATION + '\x0c' # 0x000c -> FORM FEED + '\r' # 0x000d -> CARRIAGE RETURN + '\x0e' # 0x000e -> SHIFT OUT + '\x0f' # 0x000f -> SHIFT IN + '\x10' # 0x0010 -> DATA LINK ESCAPE + '\x11' # 0x0011 -> DEVICE CONTROL ONE + '\x12' # 0x0012 -> DEVICE CONTROL TWO + '\x13' # 0x0013 -> DEVICE CONTROL THREE + '\x14' # 0x0014 -> DEVICE CONTROL FOUR + '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x0016 -> SYNCHRONOUS IDLE + '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK + '\x18' # 0x0018 -> CANCEL + '\x19' # 0x0019 -> END OF MEDIUM + '\x1a' # 0x001a -> SUBSTITUTE + '\x1b' # 0x001b -> ESCAPE + '\x1c' # 0x001c -> FILE SEPARATOR + '\x1d' # 0x001d -> GROUP SEPARATOR + '\x1e' # 0x001e -> RECORD SEPARATOR + '\x1f' # 0x001f -> UNIT SEPARATOR + ' ' # 0x0020 -> SPACE + '!' # 0x0021 -> EXCLAMATION MARK + '"' # 0x0022 -> QUOTATION MARK + '#' # 0x0023 -> NUMBER SIGN + '$' # 0x0024 -> DOLLAR SIGN + '%' # 0x0025 -> PERCENT SIGN + '&' # 0x0026 -> AMPERSAND + "'" # 0x0027 -> APOSTROPHE + '(' # 0x0028 -> LEFT PARENTHESIS + ')' # 0x0029 -> RIGHT PARENTHESIS + '*' # 0x002a -> ASTERISK + '+' # 0x002b -> PLUS SIGN + ',' # 0x002c -> COMMA + '-' # 0x002d -> HYPHEN-MINUS + '.' # 0x002e -> FULL STOP + '/' # 0x002f -> SOLIDUS + '0' # 0x0030 -> DIGIT ZERO + '1' # 0x0031 -> DIGIT ONE + '2' # 0x0032 -> DIGIT TWO + '3' # 0x0033 -> DIGIT THREE + '4' # 0x0034 -> DIGIT FOUR + '5' # 0x0035 -> DIGIT FIVE + '6' # 0x0036 -> DIGIT SIX + '7' # 0x0037 -> DIGIT SEVEN + '8' # 0x0038 -> DIGIT EIGHT + '9' # 0x0039 -> DIGIT NINE + ':' # 0x003a -> COLON + ';' # 0x003b -> SEMICOLON + '<' # 0x003c -> LESS-THAN SIGN + '=' # 0x003d -> EQUALS SIGN + '>' # 0x003e -> GREATER-THAN SIGN + '?' # 0x003f -> QUESTION MARK + '@' # 0x0040 -> COMMERCIAL AT + 'A' # 0x0041 -> LATIN CAPITAL LETTER A + 'B' # 0x0042 -> LATIN CAPITAL LETTER B + 'C' # 0x0043 -> LATIN CAPITAL LETTER C + 'D' # 0x0044 -> LATIN CAPITAL LETTER D + 'E' # 0x0045 -> LATIN CAPITAL LETTER E + 'F' # 0x0046 -> LATIN CAPITAL LETTER F + 'G' # 0x0047 -> LATIN CAPITAL LETTER G + 'H' # 0x0048 -> LATIN CAPITAL LETTER H + 'I' # 0x0049 -> LATIN CAPITAL LETTER I + 'J' # 0x004a -> LATIN CAPITAL LETTER J + 'K' # 0x004b -> LATIN CAPITAL LETTER K + 'L' # 0x004c -> LATIN CAPITAL LETTER L + 'M' # 0x004d -> LATIN CAPITAL LETTER M + 'N' # 0x004e -> LATIN CAPITAL LETTER N + 'O' # 0x004f -> LATIN CAPITAL LETTER O + 'P' # 0x0050 -> LATIN CAPITAL LETTER P + 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q + 'R' # 0x0052 -> LATIN CAPITAL LETTER R + 'S' # 0x0053 -> LATIN CAPITAL LETTER S + 'T' # 0x0054 -> LATIN CAPITAL LETTER T + 'U' # 0x0055 -> LATIN CAPITAL LETTER U + 'V' # 0x0056 -> LATIN CAPITAL LETTER V + 'W' # 0x0057 -> LATIN CAPITAL LETTER W + 'X' # 0x0058 -> LATIN CAPITAL LETTER X + 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y + 'Z' # 0x005a -> LATIN CAPITAL LETTER Z + '[' # 0x005b -> LEFT SQUARE BRACKET + '\\' # 0x005c -> REVERSE SOLIDUS + ']' # 0x005d -> RIGHT SQUARE BRACKET + '^' # 0x005e -> CIRCUMFLEX ACCENT + '_' # 0x005f -> LOW LINE + '`' # 0x0060 -> GRAVE ACCENT + 'a' # 0x0061 -> LATIN SMALL LETTER A + 'b' # 0x0062 -> LATIN SMALL LETTER B + 'c' # 0x0063 -> LATIN SMALL LETTER C + 'd' # 0x0064 -> LATIN SMALL LETTER D + 'e' # 0x0065 -> LATIN SMALL LETTER E + 'f' # 0x0066 -> LATIN SMALL LETTER F + 'g' # 0x0067 -> LATIN SMALL LETTER G + 'h' # 0x0068 -> LATIN SMALL LETTER H + 'i' # 0x0069 -> LATIN SMALL LETTER I + 'j' # 0x006a -> LATIN SMALL LETTER J + 'k' # 0x006b -> LATIN SMALL LETTER K + 'l' # 0x006c -> LATIN SMALL LETTER L + 'm' # 0x006d -> LATIN SMALL LETTER M + 'n' # 0x006e -> LATIN SMALL LETTER N + 'o' # 0x006f -> LATIN SMALL LETTER O + 'p' # 0x0070 -> LATIN SMALL LETTER P + 'q' # 0x0071 -> LATIN SMALL LETTER Q + 'r' # 0x0072 -> LATIN SMALL LETTER R + 's' # 0x0073 -> LATIN SMALL LETTER S + 't' # 0x0074 -> LATIN SMALL LETTER T + 'u' # 0x0075 -> LATIN SMALL LETTER U + 'v' # 0x0076 -> LATIN SMALL LETTER V + 'w' # 0x0077 -> LATIN SMALL LETTER W + 'x' # 0x0078 -> LATIN SMALL LETTER X + 'y' # 0x0079 -> LATIN SMALL LETTER Y + 'z' # 0x007a -> LATIN SMALL LETTER Z + '{' # 0x007b -> LEFT CURLY BRACKET + '|' # 0x007c -> VERTICAL LINE + '}' # 0x007d -> RIGHT CURLY BRACKET + '~' # 0x007e -> TILDE + '\x7f' # 0x007f -> DELETE + '\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS + '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE + '\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS + '\u016f' # 0x0085 -> LATIN SMALL LETTER U WITH RING ABOVE + '\u0107' # 0x0086 -> LATIN SMALL LETTER C WITH ACUTE + '\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA + '\u0142' # 0x0088 -> LATIN SMALL LETTER L WITH STROKE + '\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS + '\u0150' # 0x008a -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE + '\u0151' # 0x008b -> LATIN SMALL LETTER O WITH DOUBLE ACUTE + '\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\u0179' # 0x008d -> LATIN CAPITAL LETTER Z WITH ACUTE + '\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\u0106' # 0x008f -> LATIN CAPITAL LETTER C WITH ACUTE + '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE + '\u0139' # 0x0091 -> LATIN CAPITAL LETTER L WITH ACUTE + '\u013a' # 0x0092 -> LATIN SMALL LETTER L WITH ACUTE + '\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS + '\u013d' # 0x0095 -> LATIN CAPITAL LETTER L WITH CARON + '\u013e' # 0x0096 -> LATIN SMALL LETTER L WITH CARON + '\u015a' # 0x0097 -> LATIN CAPITAL LETTER S WITH ACUTE + '\u015b' # 0x0098 -> LATIN SMALL LETTER S WITH ACUTE + '\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\u0164' # 0x009b -> LATIN CAPITAL LETTER T WITH CARON + '\u0165' # 0x009c -> LATIN SMALL LETTER T WITH CARON + '\u0141' # 0x009d -> LATIN CAPITAL LETTER L WITH STROKE + '\xd7' # 0x009e -> MULTIPLICATION SIGN + '\u010d' # 0x009f -> LATIN SMALL LETTER C WITH CARON + '\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE + '\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE + '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE + '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE + '\u0104' # 0x00a4 -> LATIN CAPITAL LETTER A WITH OGONEK + '\u0105' # 0x00a5 -> LATIN SMALL LETTER A WITH OGONEK + '\u017d' # 0x00a6 -> LATIN CAPITAL LETTER Z WITH CARON + '\u017e' # 0x00a7 -> LATIN SMALL LETTER Z WITH CARON + '\u0118' # 0x00a8 -> LATIN CAPITAL LETTER E WITH OGONEK + '\u0119' # 0x00a9 -> LATIN SMALL LETTER E WITH OGONEK + '\xac' # 0x00aa -> NOT SIGN + '\u017a' # 0x00ab -> LATIN SMALL LETTER Z WITH ACUTE + '\u010c' # 0x00ac -> LATIN CAPITAL LETTER C WITH CARON + '\u015f' # 0x00ad -> LATIN SMALL LETTER S WITH CEDILLA + '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u2591' # 0x00b0 -> LIGHT SHADE + '\u2592' # 0x00b1 -> MEDIUM SHADE + '\u2593' # 0x00b2 -> DARK SHADE + '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL + '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT + '\xc1' # 0x00b5 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc2' # 0x00b6 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\u011a' # 0x00b7 -> LATIN CAPITAL LETTER E WITH CARON + '\u015e' # 0x00b8 -> LATIN CAPITAL LETTER S WITH CEDILLA + '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL + '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT + '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT + '\u017b' # 0x00bd -> LATIN CAPITAL LETTER Z WITH DOT ABOVE + '\u017c' # 0x00be -> LATIN SMALL LETTER Z WITH DOT ABOVE + '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT + '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT + '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL + '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT + '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL + '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + '\u0102' # 0x00c6 -> LATIN CAPITAL LETTER A WITH BREVE + '\u0103' # 0x00c7 -> LATIN SMALL LETTER A WITH BREVE + '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT + '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL + '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + '\xa4' # 0x00cf -> CURRENCY SIGN + '\u0111' # 0x00d0 -> LATIN SMALL LETTER D WITH STROKE + '\u0110' # 0x00d1 -> LATIN CAPITAL LETTER D WITH STROKE + '\u010e' # 0x00d2 -> LATIN CAPITAL LETTER D WITH CARON + '\xcb' # 0x00d3 -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\u010f' # 0x00d4 -> LATIN SMALL LETTER D WITH CARON + '\u0147' # 0x00d5 -> LATIN CAPITAL LETTER N WITH CARON + '\xcd' # 0x00d6 -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0x00d7 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\u011b' # 0x00d8 -> LATIN SMALL LETTER E WITH CARON + '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT + '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT + '\u2588' # 0x00db -> FULL BLOCK + '\u2584' # 0x00dc -> LOWER HALF BLOCK + '\u0162' # 0x00dd -> LATIN CAPITAL LETTER T WITH CEDILLA + '\u016e' # 0x00de -> LATIN CAPITAL LETTER U WITH RING ABOVE + '\u2580' # 0x00df -> UPPER HALF BLOCK + '\xd3' # 0x00e0 -> LATIN CAPITAL LETTER O WITH ACUTE + '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S + '\xd4' # 0x00e2 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\u0143' # 0x00e3 -> LATIN CAPITAL LETTER N WITH ACUTE + '\u0144' # 0x00e4 -> LATIN SMALL LETTER N WITH ACUTE + '\u0148' # 0x00e5 -> LATIN SMALL LETTER N WITH CARON + '\u0160' # 0x00e6 -> LATIN CAPITAL LETTER S WITH CARON + '\u0161' # 0x00e7 -> LATIN SMALL LETTER S WITH CARON + '\u0154' # 0x00e8 -> LATIN CAPITAL LETTER R WITH ACUTE + '\xda' # 0x00e9 -> LATIN CAPITAL LETTER U WITH ACUTE + '\u0155' # 0x00ea -> LATIN SMALL LETTER R WITH ACUTE + '\u0170' # 0x00eb -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE + '\xfd' # 0x00ec -> LATIN SMALL LETTER Y WITH ACUTE + '\xdd' # 0x00ed -> LATIN CAPITAL LETTER Y WITH ACUTE + '\u0163' # 0x00ee -> LATIN SMALL LETTER T WITH CEDILLA + '\xb4' # 0x00ef -> ACUTE ACCENT + '\xad' # 0x00f0 -> SOFT HYPHEN + '\u02dd' # 0x00f1 -> DOUBLE ACUTE ACCENT + '\u02db' # 0x00f2 -> OGONEK + '\u02c7' # 0x00f3 -> CARON + '\u02d8' # 0x00f4 -> BREVE + '\xa7' # 0x00f5 -> SECTION SIGN + '\xf7' # 0x00f6 -> DIVISION SIGN + '\xb8' # 0x00f7 -> CEDILLA + '\xb0' # 0x00f8 -> DEGREE SIGN + '\xa8' # 0x00f9 -> DIAERESIS + '\u02d9' # 0x00fa -> DOT ABOVE + '\u0171' # 0x00fb -> LATIN SMALL LETTER U WITH DOUBLE ACUTE + '\u0158' # 0x00fc -> LATIN CAPITAL LETTER R WITH CARON + '\u0159' # 0x00fd -> LATIN SMALL LETTER R WITH CARON + '\u25a0' # 0x00fe -> BLACK SQUARE + '\xa0' # 0x00ff -> NO-BREAK SPACE +) + +### Encoding Map + +encoding_map = { + 0x0000: 0x0000, # NULL + 0x0001: 0x0001, # START OF HEADING + 0x0002: 0x0002, # START OF TEXT + 0x0003: 0x0003, # END OF TEXT + 0x0004: 0x0004, # END OF TRANSMISSION + 0x0005: 0x0005, # ENQUIRY + 0x0006: 0x0006, # ACKNOWLEDGE + 0x0007: 0x0007, # BELL + 0x0008: 0x0008, # BACKSPACE + 0x0009: 0x0009, # HORIZONTAL TABULATION + 0x000a: 0x000a, # LINE FEED + 0x000b: 0x000b, # VERTICAL TABULATION + 0x000c: 0x000c, # FORM FEED + 0x000d: 0x000d, # CARRIAGE RETURN + 0x000e: 0x000e, # SHIFT OUT + 0x000f: 0x000f, # SHIFT IN + 0x0010: 0x0010, # DATA LINK ESCAPE + 0x0011: 0x0011, # DEVICE CONTROL ONE + 0x0012: 0x0012, # DEVICE CONTROL TWO + 0x0013: 0x0013, # DEVICE CONTROL THREE + 0x0014: 0x0014, # DEVICE CONTROL FOUR + 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE + 0x0016: 0x0016, # SYNCHRONOUS IDLE + 0x0017: 0x0017, # END OF TRANSMISSION BLOCK + 0x0018: 0x0018, # CANCEL + 0x0019: 0x0019, # END OF MEDIUM + 0x001a: 0x001a, # SUBSTITUTE + 0x001b: 0x001b, # ESCAPE + 0x001c: 0x001c, # FILE SEPARATOR + 0x001d: 0x001d, # GROUP SEPARATOR + 0x001e: 0x001e, # RECORD SEPARATOR + 0x001f: 0x001f, # UNIT SEPARATOR + 0x0020: 0x0020, # SPACE + 0x0021: 0x0021, # EXCLAMATION MARK + 0x0022: 0x0022, # QUOTATION MARK + 0x0023: 0x0023, # NUMBER SIGN + 0x0024: 0x0024, # DOLLAR SIGN + 0x0025: 0x0025, # PERCENT SIGN + 0x0026: 0x0026, # AMPERSAND + 0x0027: 0x0027, # APOSTROPHE + 0x0028: 0x0028, # LEFT PARENTHESIS + 0x0029: 0x0029, # RIGHT PARENTHESIS + 0x002a: 0x002a, # ASTERISK + 0x002b: 0x002b, # PLUS SIGN + 0x002c: 0x002c, # COMMA + 0x002d: 0x002d, # HYPHEN-MINUS + 0x002e: 0x002e, # FULL STOP + 0x002f: 0x002f, # SOLIDUS + 0x0030: 0x0030, # DIGIT ZERO + 0x0031: 0x0031, # DIGIT ONE + 0x0032: 0x0032, # DIGIT TWO + 0x0033: 0x0033, # DIGIT THREE + 0x0034: 0x0034, # DIGIT FOUR + 0x0035: 0x0035, # DIGIT FIVE + 0x0036: 0x0036, # DIGIT SIX + 0x0037: 0x0037, # DIGIT SEVEN + 0x0038: 0x0038, # DIGIT EIGHT + 0x0039: 0x0039, # DIGIT NINE + 0x003a: 0x003a, # COLON + 0x003b: 0x003b, # SEMICOLON + 0x003c: 0x003c, # LESS-THAN SIGN + 0x003d: 0x003d, # EQUALS SIGN + 0x003e: 0x003e, # GREATER-THAN SIGN + 0x003f: 0x003f, # QUESTION MARK + 0x0040: 0x0040, # COMMERCIAL AT + 0x0041: 0x0041, # LATIN CAPITAL LETTER A + 0x0042: 0x0042, # LATIN CAPITAL LETTER B + 0x0043: 0x0043, # LATIN CAPITAL LETTER C + 0x0044: 0x0044, # LATIN CAPITAL LETTER D + 0x0045: 0x0045, # LATIN CAPITAL LETTER E + 0x0046: 0x0046, # LATIN CAPITAL LETTER F + 0x0047: 0x0047, # LATIN CAPITAL LETTER G + 0x0048: 0x0048, # LATIN CAPITAL LETTER H + 0x0049: 0x0049, # LATIN CAPITAL LETTER I + 0x004a: 0x004a, # LATIN CAPITAL LETTER J + 0x004b: 0x004b, # LATIN CAPITAL LETTER K + 0x004c: 0x004c, # LATIN CAPITAL LETTER L + 0x004d: 0x004d, # LATIN CAPITAL LETTER M + 0x004e: 0x004e, # LATIN CAPITAL LETTER N + 0x004f: 0x004f, # LATIN CAPITAL LETTER O + 0x0050: 0x0050, # LATIN CAPITAL LETTER P + 0x0051: 0x0051, # LATIN CAPITAL LETTER Q + 0x0052: 0x0052, # LATIN CAPITAL LETTER R + 0x0053: 0x0053, # LATIN CAPITAL LETTER S + 0x0054: 0x0054, # LATIN CAPITAL LETTER T + 0x0055: 0x0055, # LATIN CAPITAL LETTER U + 0x0056: 0x0056, # LATIN CAPITAL LETTER V + 0x0057: 0x0057, # LATIN CAPITAL LETTER W + 0x0058: 0x0058, # LATIN CAPITAL LETTER X + 0x0059: 0x0059, # LATIN CAPITAL LETTER Y + 0x005a: 0x005a, # LATIN CAPITAL LETTER Z + 0x005b: 0x005b, # LEFT SQUARE BRACKET + 0x005c: 0x005c, # REVERSE SOLIDUS + 0x005d: 0x005d, # RIGHT SQUARE BRACKET + 0x005e: 0x005e, # CIRCUMFLEX ACCENT + 0x005f: 0x005f, # LOW LINE + 0x0060: 0x0060, # GRAVE ACCENT + 0x0061: 0x0061, # LATIN SMALL LETTER A + 0x0062: 0x0062, # LATIN SMALL LETTER B + 0x0063: 0x0063, # LATIN SMALL LETTER C + 0x0064: 0x0064, # LATIN SMALL LETTER D + 0x0065: 0x0065, # LATIN SMALL LETTER E + 0x0066: 0x0066, # LATIN SMALL LETTER F + 0x0067: 0x0067, # LATIN SMALL LETTER G + 0x0068: 0x0068, # LATIN SMALL LETTER H + 0x0069: 0x0069, # LATIN SMALL LETTER I + 0x006a: 0x006a, # LATIN SMALL LETTER J + 0x006b: 0x006b, # LATIN SMALL LETTER K + 0x006c: 0x006c, # LATIN SMALL LETTER L + 0x006d: 0x006d, # LATIN SMALL LETTER M + 0x006e: 0x006e, # LATIN SMALL LETTER N + 0x006f: 0x006f, # LATIN SMALL LETTER O + 0x0070: 0x0070, # LATIN SMALL LETTER P + 0x0071: 0x0071, # LATIN SMALL LETTER Q + 0x0072: 0x0072, # LATIN SMALL LETTER R + 0x0073: 0x0073, # LATIN SMALL LETTER S + 0x0074: 0x0074, # LATIN SMALL LETTER T + 0x0075: 0x0075, # LATIN SMALL LETTER U + 0x0076: 0x0076, # LATIN SMALL LETTER V + 0x0077: 0x0077, # LATIN SMALL LETTER W + 0x0078: 0x0078, # LATIN SMALL LETTER X + 0x0079: 0x0079, # LATIN SMALL LETTER Y + 0x007a: 0x007a, # LATIN SMALL LETTER Z + 0x007b: 0x007b, # LEFT CURLY BRACKET + 0x007c: 0x007c, # VERTICAL LINE + 0x007d: 0x007d, # RIGHT CURLY BRACKET + 0x007e: 0x007e, # TILDE + 0x007f: 0x007f, # DELETE + 0x00a0: 0x00ff, # NO-BREAK SPACE + 0x00a4: 0x00cf, # CURRENCY SIGN + 0x00a7: 0x00f5, # SECTION SIGN + 0x00a8: 0x00f9, # DIAERESIS + 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00ac: 0x00aa, # NOT SIGN + 0x00ad: 0x00f0, # SOFT HYPHEN + 0x00b0: 0x00f8, # DEGREE SIGN + 0x00b4: 0x00ef, # ACUTE ACCENT + 0x00b8: 0x00f7, # CEDILLA + 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00c1: 0x00b5, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00c2: 0x00b6, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00cb: 0x00d3, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00cd: 0x00d6, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00ce: 0x00d7, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00d3: 0x00e0, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00d4: 0x00e2, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00d7: 0x009e, # MULTIPLICATION SIGN + 0x00da: 0x00e9, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00dd: 0x00ed, # LATIN CAPITAL LETTER Y WITH ACUTE + 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S + 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE + 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA + 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE + 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE + 0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE + 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00f7: 0x00f6, # DIVISION SIGN + 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE + 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00fd: 0x00ec, # LATIN SMALL LETTER Y WITH ACUTE + 0x0102: 0x00c6, # LATIN CAPITAL LETTER A WITH BREVE + 0x0103: 0x00c7, # LATIN SMALL LETTER A WITH BREVE + 0x0104: 0x00a4, # LATIN CAPITAL LETTER A WITH OGONEK + 0x0105: 0x00a5, # LATIN SMALL LETTER A WITH OGONEK + 0x0106: 0x008f, # LATIN CAPITAL LETTER C WITH ACUTE + 0x0107: 0x0086, # LATIN SMALL LETTER C WITH ACUTE + 0x010c: 0x00ac, # LATIN CAPITAL LETTER C WITH CARON + 0x010d: 0x009f, # LATIN SMALL LETTER C WITH CARON + 0x010e: 0x00d2, # LATIN CAPITAL LETTER D WITH CARON + 0x010f: 0x00d4, # LATIN SMALL LETTER D WITH CARON + 0x0110: 0x00d1, # LATIN CAPITAL LETTER D WITH STROKE + 0x0111: 0x00d0, # LATIN SMALL LETTER D WITH STROKE + 0x0118: 0x00a8, # LATIN CAPITAL LETTER E WITH OGONEK + 0x0119: 0x00a9, # LATIN SMALL LETTER E WITH OGONEK + 0x011a: 0x00b7, # LATIN CAPITAL LETTER E WITH CARON + 0x011b: 0x00d8, # LATIN SMALL LETTER E WITH CARON + 0x0139: 0x0091, # LATIN CAPITAL LETTER L WITH ACUTE + 0x013a: 0x0092, # LATIN SMALL LETTER L WITH ACUTE + 0x013d: 0x0095, # LATIN CAPITAL LETTER L WITH CARON + 0x013e: 0x0096, # LATIN SMALL LETTER L WITH CARON + 0x0141: 0x009d, # LATIN CAPITAL LETTER L WITH STROKE + 0x0142: 0x0088, # LATIN SMALL LETTER L WITH STROKE + 0x0143: 0x00e3, # LATIN CAPITAL LETTER N WITH ACUTE + 0x0144: 0x00e4, # LATIN SMALL LETTER N WITH ACUTE + 0x0147: 0x00d5, # LATIN CAPITAL LETTER N WITH CARON + 0x0148: 0x00e5, # LATIN SMALL LETTER N WITH CARON + 0x0150: 0x008a, # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE + 0x0151: 0x008b, # LATIN SMALL LETTER O WITH DOUBLE ACUTE + 0x0154: 0x00e8, # LATIN CAPITAL LETTER R WITH ACUTE + 0x0155: 0x00ea, # LATIN SMALL LETTER R WITH ACUTE + 0x0158: 0x00fc, # LATIN CAPITAL LETTER R WITH CARON + 0x0159: 0x00fd, # LATIN SMALL LETTER R WITH CARON + 0x015a: 0x0097, # LATIN CAPITAL LETTER S WITH ACUTE + 0x015b: 0x0098, # LATIN SMALL LETTER S WITH ACUTE + 0x015e: 0x00b8, # LATIN CAPITAL LETTER S WITH CEDILLA + 0x015f: 0x00ad, # LATIN SMALL LETTER S WITH CEDILLA + 0x0160: 0x00e6, # LATIN CAPITAL LETTER S WITH CARON + 0x0161: 0x00e7, # LATIN SMALL LETTER S WITH CARON + 0x0162: 0x00dd, # LATIN CAPITAL LETTER T WITH CEDILLA + 0x0163: 0x00ee, # LATIN SMALL LETTER T WITH CEDILLA + 0x0164: 0x009b, # LATIN CAPITAL LETTER T WITH CARON + 0x0165: 0x009c, # LATIN SMALL LETTER T WITH CARON + 0x016e: 0x00de, # LATIN CAPITAL LETTER U WITH RING ABOVE + 0x016f: 0x0085, # LATIN SMALL LETTER U WITH RING ABOVE + 0x0170: 0x00eb, # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE + 0x0171: 0x00fb, # LATIN SMALL LETTER U WITH DOUBLE ACUTE + 0x0179: 0x008d, # LATIN CAPITAL LETTER Z WITH ACUTE + 0x017a: 0x00ab, # LATIN SMALL LETTER Z WITH ACUTE + 0x017b: 0x00bd, # LATIN CAPITAL LETTER Z WITH DOT ABOVE + 0x017c: 0x00be, # LATIN SMALL LETTER Z WITH DOT ABOVE + 0x017d: 0x00a6, # LATIN CAPITAL LETTER Z WITH CARON + 0x017e: 0x00a7, # LATIN SMALL LETTER Z WITH CARON + 0x02c7: 0x00f3, # CARON + 0x02d8: 0x00f4, # BREVE + 0x02d9: 0x00fa, # DOT ABOVE + 0x02db: 0x00f2, # OGONEK + 0x02dd: 0x00f1, # DOUBLE ACUTE ACCENT + 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL + 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL + 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT + 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL + 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x2580: 0x00df, # UPPER HALF BLOCK + 0x2584: 0x00dc, # LOWER HALF BLOCK + 0x2588: 0x00db, # FULL BLOCK + 0x2591: 0x00b0, # LIGHT SHADE + 0x2592: 0x00b1, # MEDIUM SHADE + 0x2593: 0x00b2, # DARK SHADE + 0x25a0: 0x00fe, # BLACK SQUARE +} diff --git a/contrib/tools/python3/src/Lib/encodings/cp855.py b/contrib/tools/python3/src/Lib/encodings/cp855.py new file mode 100644 index 0000000000..4fe9210697 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp855.py @@ -0,0 +1,698 @@ +""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP855.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_map) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp855', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + +### Decoding Map + +decoding_map = codecs.make_identity_dict(range(256)) +decoding_map.update({ + 0x0080: 0x0452, # CYRILLIC SMALL LETTER DJE + 0x0081: 0x0402, # CYRILLIC CAPITAL LETTER DJE + 0x0082: 0x0453, # CYRILLIC SMALL LETTER GJE + 0x0083: 0x0403, # CYRILLIC CAPITAL LETTER GJE + 0x0084: 0x0451, # CYRILLIC SMALL LETTER IO + 0x0085: 0x0401, # CYRILLIC CAPITAL LETTER IO + 0x0086: 0x0454, # CYRILLIC SMALL LETTER UKRAINIAN IE + 0x0087: 0x0404, # CYRILLIC CAPITAL LETTER UKRAINIAN IE + 0x0088: 0x0455, # CYRILLIC SMALL LETTER DZE + 0x0089: 0x0405, # CYRILLIC CAPITAL LETTER DZE + 0x008a: 0x0456, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + 0x008b: 0x0406, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + 0x008c: 0x0457, # CYRILLIC SMALL LETTER YI + 0x008d: 0x0407, # CYRILLIC CAPITAL LETTER YI + 0x008e: 0x0458, # CYRILLIC SMALL LETTER JE + 0x008f: 0x0408, # CYRILLIC CAPITAL LETTER JE + 0x0090: 0x0459, # CYRILLIC SMALL LETTER LJE + 0x0091: 0x0409, # CYRILLIC CAPITAL LETTER LJE + 0x0092: 0x045a, # CYRILLIC SMALL LETTER NJE + 0x0093: 0x040a, # CYRILLIC CAPITAL LETTER NJE + 0x0094: 0x045b, # CYRILLIC SMALL LETTER TSHE + 0x0095: 0x040b, # CYRILLIC CAPITAL LETTER TSHE + 0x0096: 0x045c, # CYRILLIC SMALL LETTER KJE + 0x0097: 0x040c, # CYRILLIC CAPITAL LETTER KJE + 0x0098: 0x045e, # CYRILLIC SMALL LETTER SHORT U + 0x0099: 0x040e, # CYRILLIC CAPITAL LETTER SHORT U + 0x009a: 0x045f, # CYRILLIC SMALL LETTER DZHE + 0x009b: 0x040f, # CYRILLIC CAPITAL LETTER DZHE + 0x009c: 0x044e, # CYRILLIC SMALL LETTER YU + 0x009d: 0x042e, # CYRILLIC CAPITAL LETTER YU + 0x009e: 0x044a, # CYRILLIC SMALL LETTER HARD SIGN + 0x009f: 0x042a, # CYRILLIC CAPITAL LETTER HARD SIGN + 0x00a0: 0x0430, # CYRILLIC SMALL LETTER A + 0x00a1: 0x0410, # CYRILLIC CAPITAL LETTER A + 0x00a2: 0x0431, # CYRILLIC SMALL LETTER BE + 0x00a3: 0x0411, # CYRILLIC CAPITAL LETTER BE + 0x00a4: 0x0446, # CYRILLIC SMALL LETTER TSE + 0x00a5: 0x0426, # CYRILLIC CAPITAL LETTER TSE + 0x00a6: 0x0434, # CYRILLIC SMALL LETTER DE + 0x00a7: 0x0414, # CYRILLIC CAPITAL LETTER DE + 0x00a8: 0x0435, # CYRILLIC SMALL LETTER IE + 0x00a9: 0x0415, # CYRILLIC CAPITAL LETTER IE + 0x00aa: 0x0444, # CYRILLIC SMALL LETTER EF + 0x00ab: 0x0424, # CYRILLIC CAPITAL LETTER EF + 0x00ac: 0x0433, # CYRILLIC SMALL LETTER GHE + 0x00ad: 0x0413, # CYRILLIC CAPITAL LETTER GHE + 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00b0: 0x2591, # LIGHT SHADE + 0x00b1: 0x2592, # MEDIUM SHADE + 0x00b2: 0x2593, # DARK SHADE + 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL + 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x00b5: 0x0445, # CYRILLIC SMALL LETTER HA + 0x00b6: 0x0425, # CYRILLIC CAPITAL LETTER HA + 0x00b7: 0x0438, # CYRILLIC SMALL LETTER I + 0x00b8: 0x0418, # CYRILLIC CAPITAL LETTER I + 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL + 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x00bd: 0x0439, # CYRILLIC SMALL LETTER SHORT I + 0x00be: 0x0419, # CYRILLIC CAPITAL LETTER SHORT I + 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL + 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x00c6: 0x043a, # CYRILLIC SMALL LETTER KA + 0x00c7: 0x041a, # CYRILLIC CAPITAL LETTER KA + 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x00cf: 0x00a4, # CURRENCY SIGN + 0x00d0: 0x043b, # CYRILLIC SMALL LETTER EL + 0x00d1: 0x041b, # CYRILLIC CAPITAL LETTER EL + 0x00d2: 0x043c, # CYRILLIC SMALL LETTER EM + 0x00d3: 0x041c, # CYRILLIC CAPITAL LETTER EM + 0x00d4: 0x043d, # CYRILLIC SMALL LETTER EN + 0x00d5: 0x041d, # CYRILLIC CAPITAL LETTER EN + 0x00d6: 0x043e, # CYRILLIC SMALL LETTER O + 0x00d7: 0x041e, # CYRILLIC CAPITAL LETTER O + 0x00d8: 0x043f, # CYRILLIC SMALL LETTER PE + 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT + 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x00db: 0x2588, # FULL BLOCK + 0x00dc: 0x2584, # LOWER HALF BLOCK + 0x00dd: 0x041f, # CYRILLIC CAPITAL LETTER PE + 0x00de: 0x044f, # CYRILLIC SMALL LETTER YA + 0x00df: 0x2580, # UPPER HALF BLOCK + 0x00e0: 0x042f, # CYRILLIC CAPITAL LETTER YA + 0x00e1: 0x0440, # CYRILLIC SMALL LETTER ER + 0x00e2: 0x0420, # CYRILLIC CAPITAL LETTER ER + 0x00e3: 0x0441, # CYRILLIC SMALL LETTER ES + 0x00e4: 0x0421, # CYRILLIC CAPITAL LETTER ES + 0x00e5: 0x0442, # CYRILLIC SMALL LETTER TE + 0x00e6: 0x0422, # CYRILLIC CAPITAL LETTER TE + 0x00e7: 0x0443, # CYRILLIC SMALL LETTER U + 0x00e8: 0x0423, # CYRILLIC CAPITAL LETTER U + 0x00e9: 0x0436, # CYRILLIC SMALL LETTER ZHE + 0x00ea: 0x0416, # CYRILLIC CAPITAL LETTER ZHE + 0x00eb: 0x0432, # CYRILLIC SMALL LETTER VE + 0x00ec: 0x0412, # CYRILLIC CAPITAL LETTER VE + 0x00ed: 0x044c, # CYRILLIC SMALL LETTER SOFT SIGN + 0x00ee: 0x042c, # CYRILLIC CAPITAL LETTER SOFT SIGN + 0x00ef: 0x2116, # NUMERO SIGN + 0x00f0: 0x00ad, # SOFT HYPHEN + 0x00f1: 0x044b, # CYRILLIC SMALL LETTER YERU + 0x00f2: 0x042b, # CYRILLIC CAPITAL LETTER YERU + 0x00f3: 0x0437, # CYRILLIC SMALL LETTER ZE + 0x00f4: 0x0417, # CYRILLIC CAPITAL LETTER ZE + 0x00f5: 0x0448, # CYRILLIC SMALL LETTER SHA + 0x00f6: 0x0428, # CYRILLIC CAPITAL LETTER SHA + 0x00f7: 0x044d, # CYRILLIC SMALL LETTER E + 0x00f8: 0x042d, # CYRILLIC CAPITAL LETTER E + 0x00f9: 0x0449, # CYRILLIC SMALL LETTER SHCHA + 0x00fa: 0x0429, # CYRILLIC CAPITAL LETTER SHCHA + 0x00fb: 0x0447, # CYRILLIC SMALL LETTER CHE + 0x00fc: 0x0427, # CYRILLIC CAPITAL LETTER CHE + 0x00fd: 0x00a7, # SECTION SIGN + 0x00fe: 0x25a0, # BLACK SQUARE + 0x00ff: 0x00a0, # NO-BREAK SPACE +}) + +### Decoding Table + +decoding_table = ( + '\x00' # 0x0000 -> NULL + '\x01' # 0x0001 -> START OF HEADING + '\x02' # 0x0002 -> START OF TEXT + '\x03' # 0x0003 -> END OF TEXT + '\x04' # 0x0004 -> END OF TRANSMISSION + '\x05' # 0x0005 -> ENQUIRY + '\x06' # 0x0006 -> ACKNOWLEDGE + '\x07' # 0x0007 -> BELL + '\x08' # 0x0008 -> BACKSPACE + '\t' # 0x0009 -> HORIZONTAL TABULATION + '\n' # 0x000a -> LINE FEED + '\x0b' # 0x000b -> VERTICAL TABULATION + '\x0c' # 0x000c -> FORM FEED + '\r' # 0x000d -> CARRIAGE RETURN + '\x0e' # 0x000e -> SHIFT OUT + '\x0f' # 0x000f -> SHIFT IN + '\x10' # 0x0010 -> DATA LINK ESCAPE + '\x11' # 0x0011 -> DEVICE CONTROL ONE + '\x12' # 0x0012 -> DEVICE CONTROL TWO + '\x13' # 0x0013 -> DEVICE CONTROL THREE + '\x14' # 0x0014 -> DEVICE CONTROL FOUR + '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x0016 -> SYNCHRONOUS IDLE + '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK + '\x18' # 0x0018 -> CANCEL + '\x19' # 0x0019 -> END OF MEDIUM + '\x1a' # 0x001a -> SUBSTITUTE + '\x1b' # 0x001b -> ESCAPE + '\x1c' # 0x001c -> FILE SEPARATOR + '\x1d' # 0x001d -> GROUP SEPARATOR + '\x1e' # 0x001e -> RECORD SEPARATOR + '\x1f' # 0x001f -> UNIT SEPARATOR + ' ' # 0x0020 -> SPACE + '!' # 0x0021 -> EXCLAMATION MARK + '"' # 0x0022 -> QUOTATION MARK + '#' # 0x0023 -> NUMBER SIGN + '$' # 0x0024 -> DOLLAR SIGN + '%' # 0x0025 -> PERCENT SIGN + '&' # 0x0026 -> AMPERSAND + "'" # 0x0027 -> APOSTROPHE + '(' # 0x0028 -> LEFT PARENTHESIS + ')' # 0x0029 -> RIGHT PARENTHESIS + '*' # 0x002a -> ASTERISK + '+' # 0x002b -> PLUS SIGN + ',' # 0x002c -> COMMA + '-' # 0x002d -> HYPHEN-MINUS + '.' # 0x002e -> FULL STOP + '/' # 0x002f -> SOLIDUS + '0' # 0x0030 -> DIGIT ZERO + '1' # 0x0031 -> DIGIT ONE + '2' # 0x0032 -> DIGIT TWO + '3' # 0x0033 -> DIGIT THREE + '4' # 0x0034 -> DIGIT FOUR + '5' # 0x0035 -> DIGIT FIVE + '6' # 0x0036 -> DIGIT SIX + '7' # 0x0037 -> DIGIT SEVEN + '8' # 0x0038 -> DIGIT EIGHT + '9' # 0x0039 -> DIGIT NINE + ':' # 0x003a -> COLON + ';' # 0x003b -> SEMICOLON + '<' # 0x003c -> LESS-THAN SIGN + '=' # 0x003d -> EQUALS SIGN + '>' # 0x003e -> GREATER-THAN SIGN + '?' # 0x003f -> QUESTION MARK + '@' # 0x0040 -> COMMERCIAL AT + 'A' # 0x0041 -> LATIN CAPITAL LETTER A + 'B' # 0x0042 -> LATIN CAPITAL LETTER B + 'C' # 0x0043 -> LATIN CAPITAL LETTER C + 'D' # 0x0044 -> LATIN CAPITAL LETTER D + 'E' # 0x0045 -> LATIN CAPITAL LETTER E + 'F' # 0x0046 -> LATIN CAPITAL LETTER F + 'G' # 0x0047 -> LATIN CAPITAL LETTER G + 'H' # 0x0048 -> LATIN CAPITAL LETTER H + 'I' # 0x0049 -> LATIN CAPITAL LETTER I + 'J' # 0x004a -> LATIN CAPITAL LETTER J + 'K' # 0x004b -> LATIN CAPITAL LETTER K + 'L' # 0x004c -> LATIN CAPITAL LETTER L + 'M' # 0x004d -> LATIN CAPITAL LETTER M + 'N' # 0x004e -> LATIN CAPITAL LETTER N + 'O' # 0x004f -> LATIN CAPITAL LETTER O + 'P' # 0x0050 -> LATIN CAPITAL LETTER P + 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q + 'R' # 0x0052 -> LATIN CAPITAL LETTER R + 'S' # 0x0053 -> LATIN CAPITAL LETTER S + 'T' # 0x0054 -> LATIN CAPITAL LETTER T + 'U' # 0x0055 -> LATIN CAPITAL LETTER U + 'V' # 0x0056 -> LATIN CAPITAL LETTER V + 'W' # 0x0057 -> LATIN CAPITAL LETTER W + 'X' # 0x0058 -> LATIN CAPITAL LETTER X + 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y + 'Z' # 0x005a -> LATIN CAPITAL LETTER Z + '[' # 0x005b -> LEFT SQUARE BRACKET + '\\' # 0x005c -> REVERSE SOLIDUS + ']' # 0x005d -> RIGHT SQUARE BRACKET + '^' # 0x005e -> CIRCUMFLEX ACCENT + '_' # 0x005f -> LOW LINE + '`' # 0x0060 -> GRAVE ACCENT + 'a' # 0x0061 -> LATIN SMALL LETTER A + 'b' # 0x0062 -> LATIN SMALL LETTER B + 'c' # 0x0063 -> LATIN SMALL LETTER C + 'd' # 0x0064 -> LATIN SMALL LETTER D + 'e' # 0x0065 -> LATIN SMALL LETTER E + 'f' # 0x0066 -> LATIN SMALL LETTER F + 'g' # 0x0067 -> LATIN SMALL LETTER G + 'h' # 0x0068 -> LATIN SMALL LETTER H + 'i' # 0x0069 -> LATIN SMALL LETTER I + 'j' # 0x006a -> LATIN SMALL LETTER J + 'k' # 0x006b -> LATIN SMALL LETTER K + 'l' # 0x006c -> LATIN SMALL LETTER L + 'm' # 0x006d -> LATIN SMALL LETTER M + 'n' # 0x006e -> LATIN SMALL LETTER N + 'o' # 0x006f -> LATIN SMALL LETTER O + 'p' # 0x0070 -> LATIN SMALL LETTER P + 'q' # 0x0071 -> LATIN SMALL LETTER Q + 'r' # 0x0072 -> LATIN SMALL LETTER R + 's' # 0x0073 -> LATIN SMALL LETTER S + 't' # 0x0074 -> LATIN SMALL LETTER T + 'u' # 0x0075 -> LATIN SMALL LETTER U + 'v' # 0x0076 -> LATIN SMALL LETTER V + 'w' # 0x0077 -> LATIN SMALL LETTER W + 'x' # 0x0078 -> LATIN SMALL LETTER X + 'y' # 0x0079 -> LATIN SMALL LETTER Y + 'z' # 0x007a -> LATIN SMALL LETTER Z + '{' # 0x007b -> LEFT CURLY BRACKET + '|' # 0x007c -> VERTICAL LINE + '}' # 0x007d -> RIGHT CURLY BRACKET + '~' # 0x007e -> TILDE + '\x7f' # 0x007f -> DELETE + '\u0452' # 0x0080 -> CYRILLIC SMALL LETTER DJE + '\u0402' # 0x0081 -> CYRILLIC CAPITAL LETTER DJE + '\u0453' # 0x0082 -> CYRILLIC SMALL LETTER GJE + '\u0403' # 0x0083 -> CYRILLIC CAPITAL LETTER GJE + '\u0451' # 0x0084 -> CYRILLIC SMALL LETTER IO + '\u0401' # 0x0085 -> CYRILLIC CAPITAL LETTER IO + '\u0454' # 0x0086 -> CYRILLIC SMALL LETTER UKRAINIAN IE + '\u0404' # 0x0087 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE + '\u0455' # 0x0088 -> CYRILLIC SMALL LETTER DZE + '\u0405' # 0x0089 -> CYRILLIC CAPITAL LETTER DZE + '\u0456' # 0x008a -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + '\u0406' # 0x008b -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + '\u0457' # 0x008c -> CYRILLIC SMALL LETTER YI + '\u0407' # 0x008d -> CYRILLIC CAPITAL LETTER YI + '\u0458' # 0x008e -> CYRILLIC SMALL LETTER JE + '\u0408' # 0x008f -> CYRILLIC CAPITAL LETTER JE + '\u0459' # 0x0090 -> CYRILLIC SMALL LETTER LJE + '\u0409' # 0x0091 -> CYRILLIC CAPITAL LETTER LJE + '\u045a' # 0x0092 -> CYRILLIC SMALL LETTER NJE + '\u040a' # 0x0093 -> CYRILLIC CAPITAL LETTER NJE + '\u045b' # 0x0094 -> CYRILLIC SMALL LETTER TSHE + '\u040b' # 0x0095 -> CYRILLIC CAPITAL LETTER TSHE + '\u045c' # 0x0096 -> CYRILLIC SMALL LETTER KJE + '\u040c' # 0x0097 -> CYRILLIC CAPITAL LETTER KJE + '\u045e' # 0x0098 -> CYRILLIC SMALL LETTER SHORT U + '\u040e' # 0x0099 -> CYRILLIC CAPITAL LETTER SHORT U + '\u045f' # 0x009a -> CYRILLIC SMALL LETTER DZHE + '\u040f' # 0x009b -> CYRILLIC CAPITAL LETTER DZHE + '\u044e' # 0x009c -> CYRILLIC SMALL LETTER YU + '\u042e' # 0x009d -> CYRILLIC CAPITAL LETTER YU + '\u044a' # 0x009e -> CYRILLIC SMALL LETTER HARD SIGN + '\u042a' # 0x009f -> CYRILLIC CAPITAL LETTER HARD SIGN + '\u0430' # 0x00a0 -> CYRILLIC SMALL LETTER A + '\u0410' # 0x00a1 -> CYRILLIC CAPITAL LETTER A + '\u0431' # 0x00a2 -> CYRILLIC SMALL LETTER BE + '\u0411' # 0x00a3 -> CYRILLIC CAPITAL LETTER BE + '\u0446' # 0x00a4 -> CYRILLIC SMALL LETTER TSE + '\u0426' # 0x00a5 -> CYRILLIC CAPITAL LETTER TSE + '\u0434' # 0x00a6 -> CYRILLIC SMALL LETTER DE + '\u0414' # 0x00a7 -> CYRILLIC CAPITAL LETTER DE + '\u0435' # 0x00a8 -> CYRILLIC SMALL LETTER IE + '\u0415' # 0x00a9 -> CYRILLIC CAPITAL LETTER IE + '\u0444' # 0x00aa -> CYRILLIC SMALL LETTER EF + '\u0424' # 0x00ab -> CYRILLIC CAPITAL LETTER EF + '\u0433' # 0x00ac -> CYRILLIC SMALL LETTER GHE + '\u0413' # 0x00ad -> CYRILLIC CAPITAL LETTER GHE + '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u2591' # 0x00b0 -> LIGHT SHADE + '\u2592' # 0x00b1 -> MEDIUM SHADE + '\u2593' # 0x00b2 -> DARK SHADE + '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL + '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT + '\u0445' # 0x00b5 -> CYRILLIC SMALL LETTER HA + '\u0425' # 0x00b6 -> CYRILLIC CAPITAL LETTER HA + '\u0438' # 0x00b7 -> CYRILLIC SMALL LETTER I + '\u0418' # 0x00b8 -> CYRILLIC CAPITAL LETTER I + '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL + '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT + '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT + '\u0439' # 0x00bd -> CYRILLIC SMALL LETTER SHORT I + '\u0419' # 0x00be -> CYRILLIC CAPITAL LETTER SHORT I + '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT + '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT + '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL + '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT + '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL + '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + '\u043a' # 0x00c6 -> CYRILLIC SMALL LETTER KA + '\u041a' # 0x00c7 -> CYRILLIC CAPITAL LETTER KA + '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT + '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL + '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + '\xa4' # 0x00cf -> CURRENCY SIGN + '\u043b' # 0x00d0 -> CYRILLIC SMALL LETTER EL + '\u041b' # 0x00d1 -> CYRILLIC CAPITAL LETTER EL + '\u043c' # 0x00d2 -> CYRILLIC SMALL LETTER EM + '\u041c' # 0x00d3 -> CYRILLIC CAPITAL LETTER EM + '\u043d' # 0x00d4 -> CYRILLIC SMALL LETTER EN + '\u041d' # 0x00d5 -> CYRILLIC CAPITAL LETTER EN + '\u043e' # 0x00d6 -> CYRILLIC SMALL LETTER O + '\u041e' # 0x00d7 -> CYRILLIC CAPITAL LETTER O + '\u043f' # 0x00d8 -> CYRILLIC SMALL LETTER PE + '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT + '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT + '\u2588' # 0x00db -> FULL BLOCK + '\u2584' # 0x00dc -> LOWER HALF BLOCK + '\u041f' # 0x00dd -> CYRILLIC CAPITAL LETTER PE + '\u044f' # 0x00de -> CYRILLIC SMALL LETTER YA + '\u2580' # 0x00df -> UPPER HALF BLOCK + '\u042f' # 0x00e0 -> CYRILLIC CAPITAL LETTER YA + '\u0440' # 0x00e1 -> CYRILLIC SMALL LETTER ER + '\u0420' # 0x00e2 -> CYRILLIC CAPITAL LETTER ER + '\u0441' # 0x00e3 -> CYRILLIC SMALL LETTER ES + '\u0421' # 0x00e4 -> CYRILLIC CAPITAL LETTER ES + '\u0442' # 0x00e5 -> CYRILLIC SMALL LETTER TE + '\u0422' # 0x00e6 -> CYRILLIC CAPITAL LETTER TE + '\u0443' # 0x00e7 -> CYRILLIC SMALL LETTER U + '\u0423' # 0x00e8 -> CYRILLIC CAPITAL LETTER U + '\u0436' # 0x00e9 -> CYRILLIC SMALL LETTER ZHE + '\u0416' # 0x00ea -> CYRILLIC CAPITAL LETTER ZHE + '\u0432' # 0x00eb -> CYRILLIC SMALL LETTER VE + '\u0412' # 0x00ec -> CYRILLIC CAPITAL LETTER VE + '\u044c' # 0x00ed -> CYRILLIC SMALL LETTER SOFT SIGN + '\u042c' # 0x00ee -> CYRILLIC CAPITAL LETTER SOFT SIGN + '\u2116' # 0x00ef -> NUMERO SIGN + '\xad' # 0x00f0 -> SOFT HYPHEN + '\u044b' # 0x00f1 -> CYRILLIC SMALL LETTER YERU + '\u042b' # 0x00f2 -> CYRILLIC CAPITAL LETTER YERU + '\u0437' # 0x00f3 -> CYRILLIC SMALL LETTER ZE + '\u0417' # 0x00f4 -> CYRILLIC CAPITAL LETTER ZE + '\u0448' # 0x00f5 -> CYRILLIC SMALL LETTER SHA + '\u0428' # 0x00f6 -> CYRILLIC CAPITAL LETTER SHA + '\u044d' # 0x00f7 -> CYRILLIC SMALL LETTER E + '\u042d' # 0x00f8 -> CYRILLIC CAPITAL LETTER E + '\u0449' # 0x00f9 -> CYRILLIC SMALL LETTER SHCHA + '\u0429' # 0x00fa -> CYRILLIC CAPITAL LETTER SHCHA + '\u0447' # 0x00fb -> CYRILLIC SMALL LETTER CHE + '\u0427' # 0x00fc -> CYRILLIC CAPITAL LETTER CHE + '\xa7' # 0x00fd -> SECTION SIGN + '\u25a0' # 0x00fe -> BLACK SQUARE + '\xa0' # 0x00ff -> NO-BREAK SPACE +) + +### Encoding Map + +encoding_map = { + 0x0000: 0x0000, # NULL + 0x0001: 0x0001, # START OF HEADING + 0x0002: 0x0002, # START OF TEXT + 0x0003: 0x0003, # END OF TEXT + 0x0004: 0x0004, # END OF TRANSMISSION + 0x0005: 0x0005, # ENQUIRY + 0x0006: 0x0006, # ACKNOWLEDGE + 0x0007: 0x0007, # BELL + 0x0008: 0x0008, # BACKSPACE + 0x0009: 0x0009, # HORIZONTAL TABULATION + 0x000a: 0x000a, # LINE FEED + 0x000b: 0x000b, # VERTICAL TABULATION + 0x000c: 0x000c, # FORM FEED + 0x000d: 0x000d, # CARRIAGE RETURN + 0x000e: 0x000e, # SHIFT OUT + 0x000f: 0x000f, # SHIFT IN + 0x0010: 0x0010, # DATA LINK ESCAPE + 0x0011: 0x0011, # DEVICE CONTROL ONE + 0x0012: 0x0012, # DEVICE CONTROL TWO + 0x0013: 0x0013, # DEVICE CONTROL THREE + 0x0014: 0x0014, # DEVICE CONTROL FOUR + 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE + 0x0016: 0x0016, # SYNCHRONOUS IDLE + 0x0017: 0x0017, # END OF TRANSMISSION BLOCK + 0x0018: 0x0018, # CANCEL + 0x0019: 0x0019, # END OF MEDIUM + 0x001a: 0x001a, # SUBSTITUTE + 0x001b: 0x001b, # ESCAPE + 0x001c: 0x001c, # FILE SEPARATOR + 0x001d: 0x001d, # GROUP SEPARATOR + 0x001e: 0x001e, # RECORD SEPARATOR + 0x001f: 0x001f, # UNIT SEPARATOR + 0x0020: 0x0020, # SPACE + 0x0021: 0x0021, # EXCLAMATION MARK + 0x0022: 0x0022, # QUOTATION MARK + 0x0023: 0x0023, # NUMBER SIGN + 0x0024: 0x0024, # DOLLAR SIGN + 0x0025: 0x0025, # PERCENT SIGN + 0x0026: 0x0026, # AMPERSAND + 0x0027: 0x0027, # APOSTROPHE + 0x0028: 0x0028, # LEFT PARENTHESIS + 0x0029: 0x0029, # RIGHT PARENTHESIS + 0x002a: 0x002a, # ASTERISK + 0x002b: 0x002b, # PLUS SIGN + 0x002c: 0x002c, # COMMA + 0x002d: 0x002d, # HYPHEN-MINUS + 0x002e: 0x002e, # FULL STOP + 0x002f: 0x002f, # SOLIDUS + 0x0030: 0x0030, # DIGIT ZERO + 0x0031: 0x0031, # DIGIT ONE + 0x0032: 0x0032, # DIGIT TWO + 0x0033: 0x0033, # DIGIT THREE + 0x0034: 0x0034, # DIGIT FOUR + 0x0035: 0x0035, # DIGIT FIVE + 0x0036: 0x0036, # DIGIT SIX + 0x0037: 0x0037, # DIGIT SEVEN + 0x0038: 0x0038, # DIGIT EIGHT + 0x0039: 0x0039, # DIGIT NINE + 0x003a: 0x003a, # COLON + 0x003b: 0x003b, # SEMICOLON + 0x003c: 0x003c, # LESS-THAN SIGN + 0x003d: 0x003d, # EQUALS SIGN + 0x003e: 0x003e, # GREATER-THAN SIGN + 0x003f: 0x003f, # QUESTION MARK + 0x0040: 0x0040, # COMMERCIAL AT + 0x0041: 0x0041, # LATIN CAPITAL LETTER A + 0x0042: 0x0042, # LATIN CAPITAL LETTER B + 0x0043: 0x0043, # LATIN CAPITAL LETTER C + 0x0044: 0x0044, # LATIN CAPITAL LETTER D + 0x0045: 0x0045, # LATIN CAPITAL LETTER E + 0x0046: 0x0046, # LATIN CAPITAL LETTER F + 0x0047: 0x0047, # LATIN CAPITAL LETTER G + 0x0048: 0x0048, # LATIN CAPITAL LETTER H + 0x0049: 0x0049, # LATIN CAPITAL LETTER I + 0x004a: 0x004a, # LATIN CAPITAL LETTER J + 0x004b: 0x004b, # LATIN CAPITAL LETTER K + 0x004c: 0x004c, # LATIN CAPITAL LETTER L + 0x004d: 0x004d, # LATIN CAPITAL LETTER M + 0x004e: 0x004e, # LATIN CAPITAL LETTER N + 0x004f: 0x004f, # LATIN CAPITAL LETTER O + 0x0050: 0x0050, # LATIN CAPITAL LETTER P + 0x0051: 0x0051, # LATIN CAPITAL LETTER Q + 0x0052: 0x0052, # LATIN CAPITAL LETTER R + 0x0053: 0x0053, # LATIN CAPITAL LETTER S + 0x0054: 0x0054, # LATIN CAPITAL LETTER T + 0x0055: 0x0055, # LATIN CAPITAL LETTER U + 0x0056: 0x0056, # LATIN CAPITAL LETTER V + 0x0057: 0x0057, # LATIN CAPITAL LETTER W + 0x0058: 0x0058, # LATIN CAPITAL LETTER X + 0x0059: 0x0059, # LATIN CAPITAL LETTER Y + 0x005a: 0x005a, # LATIN CAPITAL LETTER Z + 0x005b: 0x005b, # LEFT SQUARE BRACKET + 0x005c: 0x005c, # REVERSE SOLIDUS + 0x005d: 0x005d, # RIGHT SQUARE BRACKET + 0x005e: 0x005e, # CIRCUMFLEX ACCENT + 0x005f: 0x005f, # LOW LINE + 0x0060: 0x0060, # GRAVE ACCENT + 0x0061: 0x0061, # LATIN SMALL LETTER A + 0x0062: 0x0062, # LATIN SMALL LETTER B + 0x0063: 0x0063, # LATIN SMALL LETTER C + 0x0064: 0x0064, # LATIN SMALL LETTER D + 0x0065: 0x0065, # LATIN SMALL LETTER E + 0x0066: 0x0066, # LATIN SMALL LETTER F + 0x0067: 0x0067, # LATIN SMALL LETTER G + 0x0068: 0x0068, # LATIN SMALL LETTER H + 0x0069: 0x0069, # LATIN SMALL LETTER I + 0x006a: 0x006a, # LATIN SMALL LETTER J + 0x006b: 0x006b, # LATIN SMALL LETTER K + 0x006c: 0x006c, # LATIN SMALL LETTER L + 0x006d: 0x006d, # LATIN SMALL LETTER M + 0x006e: 0x006e, # LATIN SMALL LETTER N + 0x006f: 0x006f, # LATIN SMALL LETTER O + 0x0070: 0x0070, # LATIN SMALL LETTER P + 0x0071: 0x0071, # LATIN SMALL LETTER Q + 0x0072: 0x0072, # LATIN SMALL LETTER R + 0x0073: 0x0073, # LATIN SMALL LETTER S + 0x0074: 0x0074, # LATIN SMALL LETTER T + 0x0075: 0x0075, # LATIN SMALL LETTER U + 0x0076: 0x0076, # LATIN SMALL LETTER V + 0x0077: 0x0077, # LATIN SMALL LETTER W + 0x0078: 0x0078, # LATIN SMALL LETTER X + 0x0079: 0x0079, # LATIN SMALL LETTER Y + 0x007a: 0x007a, # LATIN SMALL LETTER Z + 0x007b: 0x007b, # LEFT CURLY BRACKET + 0x007c: 0x007c, # VERTICAL LINE + 0x007d: 0x007d, # RIGHT CURLY BRACKET + 0x007e: 0x007e, # TILDE + 0x007f: 0x007f, # DELETE + 0x00a0: 0x00ff, # NO-BREAK SPACE + 0x00a4: 0x00cf, # CURRENCY SIGN + 0x00a7: 0x00fd, # SECTION SIGN + 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00ad: 0x00f0, # SOFT HYPHEN + 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x0401: 0x0085, # CYRILLIC CAPITAL LETTER IO + 0x0402: 0x0081, # CYRILLIC CAPITAL LETTER DJE + 0x0403: 0x0083, # CYRILLIC CAPITAL LETTER GJE + 0x0404: 0x0087, # CYRILLIC CAPITAL LETTER UKRAINIAN IE + 0x0405: 0x0089, # CYRILLIC CAPITAL LETTER DZE + 0x0406: 0x008b, # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + 0x0407: 0x008d, # CYRILLIC CAPITAL LETTER YI + 0x0408: 0x008f, # CYRILLIC CAPITAL LETTER JE + 0x0409: 0x0091, # CYRILLIC CAPITAL LETTER LJE + 0x040a: 0x0093, # CYRILLIC CAPITAL LETTER NJE + 0x040b: 0x0095, # CYRILLIC CAPITAL LETTER TSHE + 0x040c: 0x0097, # CYRILLIC CAPITAL LETTER KJE + 0x040e: 0x0099, # CYRILLIC CAPITAL LETTER SHORT U + 0x040f: 0x009b, # CYRILLIC CAPITAL LETTER DZHE + 0x0410: 0x00a1, # CYRILLIC CAPITAL LETTER A + 0x0411: 0x00a3, # CYRILLIC CAPITAL LETTER BE + 0x0412: 0x00ec, # CYRILLIC CAPITAL LETTER VE + 0x0413: 0x00ad, # CYRILLIC CAPITAL LETTER GHE + 0x0414: 0x00a7, # CYRILLIC CAPITAL LETTER DE + 0x0415: 0x00a9, # CYRILLIC CAPITAL LETTER IE + 0x0416: 0x00ea, # CYRILLIC CAPITAL LETTER ZHE + 0x0417: 0x00f4, # CYRILLIC CAPITAL LETTER ZE + 0x0418: 0x00b8, # CYRILLIC CAPITAL LETTER I + 0x0419: 0x00be, # CYRILLIC CAPITAL LETTER SHORT I + 0x041a: 0x00c7, # CYRILLIC CAPITAL LETTER KA + 0x041b: 0x00d1, # CYRILLIC CAPITAL LETTER EL + 0x041c: 0x00d3, # CYRILLIC CAPITAL LETTER EM + 0x041d: 0x00d5, # CYRILLIC CAPITAL LETTER EN + 0x041e: 0x00d7, # CYRILLIC CAPITAL LETTER O + 0x041f: 0x00dd, # CYRILLIC CAPITAL LETTER PE + 0x0420: 0x00e2, # CYRILLIC CAPITAL LETTER ER + 0x0421: 0x00e4, # CYRILLIC CAPITAL LETTER ES + 0x0422: 0x00e6, # CYRILLIC CAPITAL LETTER TE + 0x0423: 0x00e8, # CYRILLIC CAPITAL LETTER U + 0x0424: 0x00ab, # CYRILLIC CAPITAL LETTER EF + 0x0425: 0x00b6, # CYRILLIC CAPITAL LETTER HA + 0x0426: 0x00a5, # CYRILLIC CAPITAL LETTER TSE + 0x0427: 0x00fc, # CYRILLIC CAPITAL LETTER CHE + 0x0428: 0x00f6, # CYRILLIC CAPITAL LETTER SHA + 0x0429: 0x00fa, # CYRILLIC CAPITAL LETTER SHCHA + 0x042a: 0x009f, # CYRILLIC CAPITAL LETTER HARD SIGN + 0x042b: 0x00f2, # CYRILLIC CAPITAL LETTER YERU + 0x042c: 0x00ee, # CYRILLIC CAPITAL LETTER SOFT SIGN + 0x042d: 0x00f8, # CYRILLIC CAPITAL LETTER E + 0x042e: 0x009d, # CYRILLIC CAPITAL LETTER YU + 0x042f: 0x00e0, # CYRILLIC CAPITAL LETTER YA + 0x0430: 0x00a0, # CYRILLIC SMALL LETTER A + 0x0431: 0x00a2, # CYRILLIC SMALL LETTER BE + 0x0432: 0x00eb, # CYRILLIC SMALL LETTER VE + 0x0433: 0x00ac, # CYRILLIC SMALL LETTER GHE + 0x0434: 0x00a6, # CYRILLIC SMALL LETTER DE + 0x0435: 0x00a8, # CYRILLIC SMALL LETTER IE + 0x0436: 0x00e9, # CYRILLIC SMALL LETTER ZHE + 0x0437: 0x00f3, # CYRILLIC SMALL LETTER ZE + 0x0438: 0x00b7, # CYRILLIC SMALL LETTER I + 0x0439: 0x00bd, # CYRILLIC SMALL LETTER SHORT I + 0x043a: 0x00c6, # CYRILLIC SMALL LETTER KA + 0x043b: 0x00d0, # CYRILLIC SMALL LETTER EL + 0x043c: 0x00d2, # CYRILLIC SMALL LETTER EM + 0x043d: 0x00d4, # CYRILLIC SMALL LETTER EN + 0x043e: 0x00d6, # CYRILLIC SMALL LETTER O + 0x043f: 0x00d8, # CYRILLIC SMALL LETTER PE + 0x0440: 0x00e1, # CYRILLIC SMALL LETTER ER + 0x0441: 0x00e3, # CYRILLIC SMALL LETTER ES + 0x0442: 0x00e5, # CYRILLIC SMALL LETTER TE + 0x0443: 0x00e7, # CYRILLIC SMALL LETTER U + 0x0444: 0x00aa, # CYRILLIC SMALL LETTER EF + 0x0445: 0x00b5, # CYRILLIC SMALL LETTER HA + 0x0446: 0x00a4, # CYRILLIC SMALL LETTER TSE + 0x0447: 0x00fb, # CYRILLIC SMALL LETTER CHE + 0x0448: 0x00f5, # CYRILLIC SMALL LETTER SHA + 0x0449: 0x00f9, # CYRILLIC SMALL LETTER SHCHA + 0x044a: 0x009e, # CYRILLIC SMALL LETTER HARD SIGN + 0x044b: 0x00f1, # CYRILLIC SMALL LETTER YERU + 0x044c: 0x00ed, # CYRILLIC SMALL LETTER SOFT SIGN + 0x044d: 0x00f7, # CYRILLIC SMALL LETTER E + 0x044e: 0x009c, # CYRILLIC SMALL LETTER YU + 0x044f: 0x00de, # CYRILLIC SMALL LETTER YA + 0x0451: 0x0084, # CYRILLIC SMALL LETTER IO + 0x0452: 0x0080, # CYRILLIC SMALL LETTER DJE + 0x0453: 0x0082, # CYRILLIC SMALL LETTER GJE + 0x0454: 0x0086, # CYRILLIC SMALL LETTER UKRAINIAN IE + 0x0455: 0x0088, # CYRILLIC SMALL LETTER DZE + 0x0456: 0x008a, # CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + 0x0457: 0x008c, # CYRILLIC SMALL LETTER YI + 0x0458: 0x008e, # CYRILLIC SMALL LETTER JE + 0x0459: 0x0090, # CYRILLIC SMALL LETTER LJE + 0x045a: 0x0092, # CYRILLIC SMALL LETTER NJE + 0x045b: 0x0094, # CYRILLIC SMALL LETTER TSHE + 0x045c: 0x0096, # CYRILLIC SMALL LETTER KJE + 0x045e: 0x0098, # CYRILLIC SMALL LETTER SHORT U + 0x045f: 0x009a, # CYRILLIC SMALL LETTER DZHE + 0x2116: 0x00ef, # NUMERO SIGN + 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL + 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL + 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT + 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL + 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x2580: 0x00df, # UPPER HALF BLOCK + 0x2584: 0x00dc, # LOWER HALF BLOCK + 0x2588: 0x00db, # FULL BLOCK + 0x2591: 0x00b0, # LIGHT SHADE + 0x2592: 0x00b1, # MEDIUM SHADE + 0x2593: 0x00b2, # DARK SHADE + 0x25a0: 0x00fe, # BLACK SQUARE +} diff --git a/contrib/tools/python3/src/Lib/encodings/cp856.py b/contrib/tools/python3/src/Lib/encodings/cp856.py new file mode 100644 index 0000000000..cacbfb2f80 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp856.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec cp856 generated from 'MAPPINGS/VENDORS/MISC/CP856.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp856', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\u05d0' # 0x80 -> HEBREW LETTER ALEF + '\u05d1' # 0x81 -> HEBREW LETTER BET + '\u05d2' # 0x82 -> HEBREW LETTER GIMEL + '\u05d3' # 0x83 -> HEBREW LETTER DALET + '\u05d4' # 0x84 -> HEBREW LETTER HE + '\u05d5' # 0x85 -> HEBREW LETTER VAV + '\u05d6' # 0x86 -> HEBREW LETTER ZAYIN + '\u05d7' # 0x87 -> HEBREW LETTER HET + '\u05d8' # 0x88 -> HEBREW LETTER TET + '\u05d9' # 0x89 -> HEBREW LETTER YOD + '\u05da' # 0x8A -> HEBREW LETTER FINAL KAF + '\u05db' # 0x8B -> HEBREW LETTER KAF + '\u05dc' # 0x8C -> HEBREW LETTER LAMED + '\u05dd' # 0x8D -> HEBREW LETTER FINAL MEM + '\u05de' # 0x8E -> HEBREW LETTER MEM + '\u05df' # 0x8F -> HEBREW LETTER FINAL NUN + '\u05e0' # 0x90 -> HEBREW LETTER NUN + '\u05e1' # 0x91 -> HEBREW LETTER SAMEKH + '\u05e2' # 0x92 -> HEBREW LETTER AYIN + '\u05e3' # 0x93 -> HEBREW LETTER FINAL PE + '\u05e4' # 0x94 -> HEBREW LETTER PE + '\u05e5' # 0x95 -> HEBREW LETTER FINAL TSADI + '\u05e6' # 0x96 -> HEBREW LETTER TSADI + '\u05e7' # 0x97 -> HEBREW LETTER QOF + '\u05e8' # 0x98 -> HEBREW LETTER RESH + '\u05e9' # 0x99 -> HEBREW LETTER SHIN + '\u05ea' # 0x9A -> HEBREW LETTER TAV + '\ufffe' # 0x9B -> UNDEFINED + '\xa3' # 0x9C -> POUND SIGN + '\ufffe' # 0x9D -> UNDEFINED + '\xd7' # 0x9E -> MULTIPLICATION SIGN + '\ufffe' # 0x9F -> UNDEFINED + '\ufffe' # 0xA0 -> UNDEFINED + '\ufffe' # 0xA1 -> UNDEFINED + '\ufffe' # 0xA2 -> UNDEFINED + '\ufffe' # 0xA3 -> UNDEFINED + '\ufffe' # 0xA4 -> UNDEFINED + '\ufffe' # 0xA5 -> UNDEFINED + '\ufffe' # 0xA6 -> UNDEFINED + '\ufffe' # 0xA7 -> UNDEFINED + '\ufffe' # 0xA8 -> UNDEFINED + '\xae' # 0xA9 -> REGISTERED SIGN + '\xac' # 0xAA -> NOT SIGN + '\xbd' # 0xAB -> VULGAR FRACTION ONE HALF + '\xbc' # 0xAC -> VULGAR FRACTION ONE QUARTER + '\ufffe' # 0xAD -> UNDEFINED + '\xab' # 0xAE -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0xAF -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u2591' # 0xB0 -> LIGHT SHADE + '\u2592' # 0xB1 -> MEDIUM SHADE + '\u2593' # 0xB2 -> DARK SHADE + '\u2502' # 0xB3 -> BOX DRAWINGS LIGHT VERTICAL + '\u2524' # 0xB4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT + '\ufffe' # 0xB5 -> UNDEFINED + '\ufffe' # 0xB6 -> UNDEFINED + '\ufffe' # 0xB7 -> UNDEFINED + '\xa9' # 0xB8 -> COPYRIGHT SIGN + '\u2563' # 0xB9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + '\u2551' # 0xBA -> BOX DRAWINGS DOUBLE VERTICAL + '\u2557' # 0xBB -> BOX DRAWINGS DOUBLE DOWN AND LEFT + '\u255d' # 0xBC -> BOX DRAWINGS DOUBLE UP AND LEFT + '\xa2' # 0xBD -> CENT SIGN + '\xa5' # 0xBE -> YEN SIGN + '\u2510' # 0xBF -> BOX DRAWINGS LIGHT DOWN AND LEFT + '\u2514' # 0xC0 -> BOX DRAWINGS LIGHT UP AND RIGHT + '\u2534' # 0xC1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL + '\u252c' # 0xC2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + '\u251c' # 0xC3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT + '\u2500' # 0xC4 -> BOX DRAWINGS LIGHT HORIZONTAL + '\u253c' # 0xC5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + '\ufffe' # 0xC6 -> UNDEFINED + '\ufffe' # 0xC7 -> UNDEFINED + '\u255a' # 0xC8 -> BOX DRAWINGS DOUBLE UP AND RIGHT + '\u2554' # 0xC9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + '\u2569' # 0xCA -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + '\u2566' # 0xCB -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + '\u2560' # 0xCC -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + '\u2550' # 0xCD -> BOX DRAWINGS DOUBLE HORIZONTAL + '\u256c' # 0xCE -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + '\xa4' # 0xCF -> CURRENCY SIGN + '\ufffe' # 0xD0 -> UNDEFINED + '\ufffe' # 0xD1 -> UNDEFINED + '\ufffe' # 0xD2 -> UNDEFINED + '\ufffe' # 0xD3 -> UNDEFINEDS + '\ufffe' # 0xD4 -> UNDEFINED + '\ufffe' # 0xD5 -> UNDEFINED + '\ufffe' # 0xD6 -> UNDEFINEDE + '\ufffe' # 0xD7 -> UNDEFINED + '\ufffe' # 0xD8 -> UNDEFINED + '\u2518' # 0xD9 -> BOX DRAWINGS LIGHT UP AND LEFT + '\u250c' # 0xDA -> BOX DRAWINGS LIGHT DOWN AND RIGHT + '\u2588' # 0xDB -> FULL BLOCK + '\u2584' # 0xDC -> LOWER HALF BLOCK + '\xa6' # 0xDD -> BROKEN BAR + '\ufffe' # 0xDE -> UNDEFINED + '\u2580' # 0xDF -> UPPER HALF BLOCK + '\ufffe' # 0xE0 -> UNDEFINED + '\ufffe' # 0xE1 -> UNDEFINED + '\ufffe' # 0xE2 -> UNDEFINED + '\ufffe' # 0xE3 -> UNDEFINED + '\ufffe' # 0xE4 -> UNDEFINED + '\ufffe' # 0xE5 -> UNDEFINED + '\xb5' # 0xE6 -> MICRO SIGN + '\ufffe' # 0xE7 -> UNDEFINED + '\ufffe' # 0xE8 -> UNDEFINED + '\ufffe' # 0xE9 -> UNDEFINED + '\ufffe' # 0xEA -> UNDEFINED + '\ufffe' # 0xEB -> UNDEFINED + '\ufffe' # 0xEC -> UNDEFINED + '\ufffe' # 0xED -> UNDEFINED + '\xaf' # 0xEE -> MACRON + '\xb4' # 0xEF -> ACUTE ACCENT + '\xad' # 0xF0 -> SOFT HYPHEN + '\xb1' # 0xF1 -> PLUS-MINUS SIGN + '\u2017' # 0xF2 -> DOUBLE LOW LINE + '\xbe' # 0xF3 -> VULGAR FRACTION THREE QUARTERS + '\xb6' # 0xF4 -> PILCROW SIGN + '\xa7' # 0xF5 -> SECTION SIGN + '\xf7' # 0xF6 -> DIVISION SIGN + '\xb8' # 0xF7 -> CEDILLA + '\xb0' # 0xF8 -> DEGREE SIGN + '\xa8' # 0xF9 -> DIAERESIS + '\xb7' # 0xFA -> MIDDLE DOT + '\xb9' # 0xFB -> SUPERSCRIPT ONE + '\xb3' # 0xFC -> SUPERSCRIPT THREE + '\xb2' # 0xFD -> SUPERSCRIPT TWO + '\u25a0' # 0xFE -> BLACK SQUARE + '\xa0' # 0xFF -> NO-BREAK SPACE +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/cp857.py b/contrib/tools/python3/src/Lib/encodings/cp857.py new file mode 100644 index 0000000000..741b059b9a --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp857.py @@ -0,0 +1,694 @@ +""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP857.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_map) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp857', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + +### Decoding Map + +decoding_map = codecs.make_identity_dict(range(256)) +decoding_map.update({ + 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS + 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE + 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE + 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE + 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA + 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS + 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE + 0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS + 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x008d: 0x0131, # LATIN SMALL LETTER DOTLESS I + 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE + 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE + 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE + 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE + 0x0098: 0x0130, # LATIN CAPITAL LETTER I WITH DOT ABOVE + 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE + 0x009c: 0x00a3, # POUND SIGN + 0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE + 0x009e: 0x015e, # LATIN CAPITAL LETTER S WITH CEDILLA + 0x009f: 0x015f, # LATIN SMALL LETTER S WITH CEDILLA + 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE + 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE + 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE + 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE + 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE + 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE + 0x00a6: 0x011e, # LATIN CAPITAL LETTER G WITH BREVE + 0x00a7: 0x011f, # LATIN SMALL LETTER G WITH BREVE + 0x00a8: 0x00bf, # INVERTED QUESTION MARK + 0x00a9: 0x00ae, # REGISTERED SIGN + 0x00aa: 0x00ac, # NOT SIGN + 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF + 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER + 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK + 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00b0: 0x2591, # LIGHT SHADE + 0x00b1: 0x2592, # MEDIUM SHADE + 0x00b2: 0x2593, # DARK SHADE + 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL + 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x00b5: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00b6: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00b7: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00b8: 0x00a9, # COPYRIGHT SIGN + 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL + 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x00bd: 0x00a2, # CENT SIGN + 0x00be: 0x00a5, # YEN SIGN + 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL + 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x00c6: 0x00e3, # LATIN SMALL LETTER A WITH TILDE + 0x00c7: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE + 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x00cf: 0x00a4, # CURRENCY SIGN + 0x00d0: 0x00ba, # MASCULINE ORDINAL INDICATOR + 0x00d1: 0x00aa, # FEMININE ORDINAL INDICATOR + 0x00d2: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00d3: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00d4: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00d5: None, # UNDEFINED + 0x00d6: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00d7: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00d8: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT + 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x00db: 0x2588, # FULL BLOCK + 0x00dc: 0x2584, # LOWER HALF BLOCK + 0x00dd: 0x00a6, # BROKEN BAR + 0x00de: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00df: 0x2580, # UPPER HALF BLOCK + 0x00e0: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S + 0x00e2: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00e3: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00e4: 0x00f5, # LATIN SMALL LETTER O WITH TILDE + 0x00e5: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE + 0x00e6: 0x00b5, # MICRO SIGN + 0x00e7: None, # UNDEFINED + 0x00e8: 0x00d7, # MULTIPLICATION SIGN + 0x00e9: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00ea: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00eb: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00ed: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x00ee: 0x00af, # MACRON + 0x00ef: 0x00b4, # ACUTE ACCENT + 0x00f0: 0x00ad, # SOFT HYPHEN + 0x00f1: 0x00b1, # PLUS-MINUS SIGN + 0x00f2: None, # UNDEFINED + 0x00f3: 0x00be, # VULGAR FRACTION THREE QUARTERS + 0x00f4: 0x00b6, # PILCROW SIGN + 0x00f5: 0x00a7, # SECTION SIGN + 0x00f6: 0x00f7, # DIVISION SIGN + 0x00f7: 0x00b8, # CEDILLA + 0x00f8: 0x00b0, # DEGREE SIGN + 0x00f9: 0x00a8, # DIAERESIS + 0x00fa: 0x00b7, # MIDDLE DOT + 0x00fb: 0x00b9, # SUPERSCRIPT ONE + 0x00fc: 0x00b3, # SUPERSCRIPT THREE + 0x00fd: 0x00b2, # SUPERSCRIPT TWO + 0x00fe: 0x25a0, # BLACK SQUARE + 0x00ff: 0x00a0, # NO-BREAK SPACE +}) + +### Decoding Table + +decoding_table = ( + '\x00' # 0x0000 -> NULL + '\x01' # 0x0001 -> START OF HEADING + '\x02' # 0x0002 -> START OF TEXT + '\x03' # 0x0003 -> END OF TEXT + '\x04' # 0x0004 -> END OF TRANSMISSION + '\x05' # 0x0005 -> ENQUIRY + '\x06' # 0x0006 -> ACKNOWLEDGE + '\x07' # 0x0007 -> BELL + '\x08' # 0x0008 -> BACKSPACE + '\t' # 0x0009 -> HORIZONTAL TABULATION + '\n' # 0x000a -> LINE FEED + '\x0b' # 0x000b -> VERTICAL TABULATION + '\x0c' # 0x000c -> FORM FEED + '\r' # 0x000d -> CARRIAGE RETURN + '\x0e' # 0x000e -> SHIFT OUT + '\x0f' # 0x000f -> SHIFT IN + '\x10' # 0x0010 -> DATA LINK ESCAPE + '\x11' # 0x0011 -> DEVICE CONTROL ONE + '\x12' # 0x0012 -> DEVICE CONTROL TWO + '\x13' # 0x0013 -> DEVICE CONTROL THREE + '\x14' # 0x0014 -> DEVICE CONTROL FOUR + '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x0016 -> SYNCHRONOUS IDLE + '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK + '\x18' # 0x0018 -> CANCEL + '\x19' # 0x0019 -> END OF MEDIUM + '\x1a' # 0x001a -> SUBSTITUTE + '\x1b' # 0x001b -> ESCAPE + '\x1c' # 0x001c -> FILE SEPARATOR + '\x1d' # 0x001d -> GROUP SEPARATOR + '\x1e' # 0x001e -> RECORD SEPARATOR + '\x1f' # 0x001f -> UNIT SEPARATOR + ' ' # 0x0020 -> SPACE + '!' # 0x0021 -> EXCLAMATION MARK + '"' # 0x0022 -> QUOTATION MARK + '#' # 0x0023 -> NUMBER SIGN + '$' # 0x0024 -> DOLLAR SIGN + '%' # 0x0025 -> PERCENT SIGN + '&' # 0x0026 -> AMPERSAND + "'" # 0x0027 -> APOSTROPHE + '(' # 0x0028 -> LEFT PARENTHESIS + ')' # 0x0029 -> RIGHT PARENTHESIS + '*' # 0x002a -> ASTERISK + '+' # 0x002b -> PLUS SIGN + ',' # 0x002c -> COMMA + '-' # 0x002d -> HYPHEN-MINUS + '.' # 0x002e -> FULL STOP + '/' # 0x002f -> SOLIDUS + '0' # 0x0030 -> DIGIT ZERO + '1' # 0x0031 -> DIGIT ONE + '2' # 0x0032 -> DIGIT TWO + '3' # 0x0033 -> DIGIT THREE + '4' # 0x0034 -> DIGIT FOUR + '5' # 0x0035 -> DIGIT FIVE + '6' # 0x0036 -> DIGIT SIX + '7' # 0x0037 -> DIGIT SEVEN + '8' # 0x0038 -> DIGIT EIGHT + '9' # 0x0039 -> DIGIT NINE + ':' # 0x003a -> COLON + ';' # 0x003b -> SEMICOLON + '<' # 0x003c -> LESS-THAN SIGN + '=' # 0x003d -> EQUALS SIGN + '>' # 0x003e -> GREATER-THAN SIGN + '?' # 0x003f -> QUESTION MARK + '@' # 0x0040 -> COMMERCIAL AT + 'A' # 0x0041 -> LATIN CAPITAL LETTER A + 'B' # 0x0042 -> LATIN CAPITAL LETTER B + 'C' # 0x0043 -> LATIN CAPITAL LETTER C + 'D' # 0x0044 -> LATIN CAPITAL LETTER D + 'E' # 0x0045 -> LATIN CAPITAL LETTER E + 'F' # 0x0046 -> LATIN CAPITAL LETTER F + 'G' # 0x0047 -> LATIN CAPITAL LETTER G + 'H' # 0x0048 -> LATIN CAPITAL LETTER H + 'I' # 0x0049 -> LATIN CAPITAL LETTER I + 'J' # 0x004a -> LATIN CAPITAL LETTER J + 'K' # 0x004b -> LATIN CAPITAL LETTER K + 'L' # 0x004c -> LATIN CAPITAL LETTER L + 'M' # 0x004d -> LATIN CAPITAL LETTER M + 'N' # 0x004e -> LATIN CAPITAL LETTER N + 'O' # 0x004f -> LATIN CAPITAL LETTER O + 'P' # 0x0050 -> LATIN CAPITAL LETTER P + 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q + 'R' # 0x0052 -> LATIN CAPITAL LETTER R + 'S' # 0x0053 -> LATIN CAPITAL LETTER S + 'T' # 0x0054 -> LATIN CAPITAL LETTER T + 'U' # 0x0055 -> LATIN CAPITAL LETTER U + 'V' # 0x0056 -> LATIN CAPITAL LETTER V + 'W' # 0x0057 -> LATIN CAPITAL LETTER W + 'X' # 0x0058 -> LATIN CAPITAL LETTER X + 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y + 'Z' # 0x005a -> LATIN CAPITAL LETTER Z + '[' # 0x005b -> LEFT SQUARE BRACKET + '\\' # 0x005c -> REVERSE SOLIDUS + ']' # 0x005d -> RIGHT SQUARE BRACKET + '^' # 0x005e -> CIRCUMFLEX ACCENT + '_' # 0x005f -> LOW LINE + '`' # 0x0060 -> GRAVE ACCENT + 'a' # 0x0061 -> LATIN SMALL LETTER A + 'b' # 0x0062 -> LATIN SMALL LETTER B + 'c' # 0x0063 -> LATIN SMALL LETTER C + 'd' # 0x0064 -> LATIN SMALL LETTER D + 'e' # 0x0065 -> LATIN SMALL LETTER E + 'f' # 0x0066 -> LATIN SMALL LETTER F + 'g' # 0x0067 -> LATIN SMALL LETTER G + 'h' # 0x0068 -> LATIN SMALL LETTER H + 'i' # 0x0069 -> LATIN SMALL LETTER I + 'j' # 0x006a -> LATIN SMALL LETTER J + 'k' # 0x006b -> LATIN SMALL LETTER K + 'l' # 0x006c -> LATIN SMALL LETTER L + 'm' # 0x006d -> LATIN SMALL LETTER M + 'n' # 0x006e -> LATIN SMALL LETTER N + 'o' # 0x006f -> LATIN SMALL LETTER O + 'p' # 0x0070 -> LATIN SMALL LETTER P + 'q' # 0x0071 -> LATIN SMALL LETTER Q + 'r' # 0x0072 -> LATIN SMALL LETTER R + 's' # 0x0073 -> LATIN SMALL LETTER S + 't' # 0x0074 -> LATIN SMALL LETTER T + 'u' # 0x0075 -> LATIN SMALL LETTER U + 'v' # 0x0076 -> LATIN SMALL LETTER V + 'w' # 0x0077 -> LATIN SMALL LETTER W + 'x' # 0x0078 -> LATIN SMALL LETTER X + 'y' # 0x0079 -> LATIN SMALL LETTER Y + 'z' # 0x007a -> LATIN SMALL LETTER Z + '{' # 0x007b -> LEFT CURLY BRACKET + '|' # 0x007c -> VERTICAL LINE + '}' # 0x007d -> RIGHT CURLY BRACKET + '~' # 0x007e -> TILDE + '\x7f' # 0x007f -> DELETE + '\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS + '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE + '\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE + '\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA + '\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS + '\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE + '\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS + '\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\u0131' # 0x008d -> LATIN SMALL LETTER DOTLESS I + '\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE + '\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE + '\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE + '\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE + '\u0130' # 0x0098 -> LATIN CAPITAL LETTER I WITH DOT ABOVE + '\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE + '\xa3' # 0x009c -> POUND SIGN + '\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE + '\u015e' # 0x009e -> LATIN CAPITAL LETTER S WITH CEDILLA + '\u015f' # 0x009f -> LATIN SMALL LETTER S WITH CEDILLA + '\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE + '\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE + '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE + '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE + '\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE + '\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE + '\u011e' # 0x00a6 -> LATIN CAPITAL LETTER G WITH BREVE + '\u011f' # 0x00a7 -> LATIN SMALL LETTER G WITH BREVE + '\xbf' # 0x00a8 -> INVERTED QUESTION MARK + '\xae' # 0x00a9 -> REGISTERED SIGN + '\xac' # 0x00aa -> NOT SIGN + '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF + '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER + '\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK + '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u2591' # 0x00b0 -> LIGHT SHADE + '\u2592' # 0x00b1 -> MEDIUM SHADE + '\u2593' # 0x00b2 -> DARK SHADE + '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL + '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT + '\xc1' # 0x00b5 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc2' # 0x00b6 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xc0' # 0x00b7 -> LATIN CAPITAL LETTER A WITH GRAVE + '\xa9' # 0x00b8 -> COPYRIGHT SIGN + '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL + '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT + '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT + '\xa2' # 0x00bd -> CENT SIGN + '\xa5' # 0x00be -> YEN SIGN + '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT + '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT + '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL + '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT + '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL + '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + '\xe3' # 0x00c6 -> LATIN SMALL LETTER A WITH TILDE + '\xc3' # 0x00c7 -> LATIN CAPITAL LETTER A WITH TILDE + '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT + '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL + '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + '\xa4' # 0x00cf -> CURRENCY SIGN + '\xba' # 0x00d0 -> MASCULINE ORDINAL INDICATOR + '\xaa' # 0x00d1 -> FEMININE ORDINAL INDICATOR + '\xca' # 0x00d2 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xcb' # 0x00d3 -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xc8' # 0x00d4 -> LATIN CAPITAL LETTER E WITH GRAVE + '\ufffe' # 0x00d5 -> UNDEFINED + '\xcd' # 0x00d6 -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0x00d7 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0x00d8 -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT + '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT + '\u2588' # 0x00db -> FULL BLOCK + '\u2584' # 0x00dc -> LOWER HALF BLOCK + '\xa6' # 0x00dd -> BROKEN BAR + '\xcc' # 0x00de -> LATIN CAPITAL LETTER I WITH GRAVE + '\u2580' # 0x00df -> UPPER HALF BLOCK + '\xd3' # 0x00e0 -> LATIN CAPITAL LETTER O WITH ACUTE + '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S + '\xd4' # 0x00e2 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\xd2' # 0x00e3 -> LATIN CAPITAL LETTER O WITH GRAVE + '\xf5' # 0x00e4 -> LATIN SMALL LETTER O WITH TILDE + '\xd5' # 0x00e5 -> LATIN CAPITAL LETTER O WITH TILDE + '\xb5' # 0x00e6 -> MICRO SIGN + '\ufffe' # 0x00e7 -> UNDEFINED + '\xd7' # 0x00e8 -> MULTIPLICATION SIGN + '\xda' # 0x00e9 -> LATIN CAPITAL LETTER U WITH ACUTE + '\xdb' # 0x00ea -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xd9' # 0x00eb -> LATIN CAPITAL LETTER U WITH GRAVE + '\xec' # 0x00ec -> LATIN SMALL LETTER I WITH GRAVE + '\xff' # 0x00ed -> LATIN SMALL LETTER Y WITH DIAERESIS + '\xaf' # 0x00ee -> MACRON + '\xb4' # 0x00ef -> ACUTE ACCENT + '\xad' # 0x00f0 -> SOFT HYPHEN + '\xb1' # 0x00f1 -> PLUS-MINUS SIGN + '\ufffe' # 0x00f2 -> UNDEFINED + '\xbe' # 0x00f3 -> VULGAR FRACTION THREE QUARTERS + '\xb6' # 0x00f4 -> PILCROW SIGN + '\xa7' # 0x00f5 -> SECTION SIGN + '\xf7' # 0x00f6 -> DIVISION SIGN + '\xb8' # 0x00f7 -> CEDILLA + '\xb0' # 0x00f8 -> DEGREE SIGN + '\xa8' # 0x00f9 -> DIAERESIS + '\xb7' # 0x00fa -> MIDDLE DOT + '\xb9' # 0x00fb -> SUPERSCRIPT ONE + '\xb3' # 0x00fc -> SUPERSCRIPT THREE + '\xb2' # 0x00fd -> SUPERSCRIPT TWO + '\u25a0' # 0x00fe -> BLACK SQUARE + '\xa0' # 0x00ff -> NO-BREAK SPACE +) + +### Encoding Map + +encoding_map = { + 0x0000: 0x0000, # NULL + 0x0001: 0x0001, # START OF HEADING + 0x0002: 0x0002, # START OF TEXT + 0x0003: 0x0003, # END OF TEXT + 0x0004: 0x0004, # END OF TRANSMISSION + 0x0005: 0x0005, # ENQUIRY + 0x0006: 0x0006, # ACKNOWLEDGE + 0x0007: 0x0007, # BELL + 0x0008: 0x0008, # BACKSPACE + 0x0009: 0x0009, # HORIZONTAL TABULATION + 0x000a: 0x000a, # LINE FEED + 0x000b: 0x000b, # VERTICAL TABULATION + 0x000c: 0x000c, # FORM FEED + 0x000d: 0x000d, # CARRIAGE RETURN + 0x000e: 0x000e, # SHIFT OUT + 0x000f: 0x000f, # SHIFT IN + 0x0010: 0x0010, # DATA LINK ESCAPE + 0x0011: 0x0011, # DEVICE CONTROL ONE + 0x0012: 0x0012, # DEVICE CONTROL TWO + 0x0013: 0x0013, # DEVICE CONTROL THREE + 0x0014: 0x0014, # DEVICE CONTROL FOUR + 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE + 0x0016: 0x0016, # SYNCHRONOUS IDLE + 0x0017: 0x0017, # END OF TRANSMISSION BLOCK + 0x0018: 0x0018, # CANCEL + 0x0019: 0x0019, # END OF MEDIUM + 0x001a: 0x001a, # SUBSTITUTE + 0x001b: 0x001b, # ESCAPE + 0x001c: 0x001c, # FILE SEPARATOR + 0x001d: 0x001d, # GROUP SEPARATOR + 0x001e: 0x001e, # RECORD SEPARATOR + 0x001f: 0x001f, # UNIT SEPARATOR + 0x0020: 0x0020, # SPACE + 0x0021: 0x0021, # EXCLAMATION MARK + 0x0022: 0x0022, # QUOTATION MARK + 0x0023: 0x0023, # NUMBER SIGN + 0x0024: 0x0024, # DOLLAR SIGN + 0x0025: 0x0025, # PERCENT SIGN + 0x0026: 0x0026, # AMPERSAND + 0x0027: 0x0027, # APOSTROPHE + 0x0028: 0x0028, # LEFT PARENTHESIS + 0x0029: 0x0029, # RIGHT PARENTHESIS + 0x002a: 0x002a, # ASTERISK + 0x002b: 0x002b, # PLUS SIGN + 0x002c: 0x002c, # COMMA + 0x002d: 0x002d, # HYPHEN-MINUS + 0x002e: 0x002e, # FULL STOP + 0x002f: 0x002f, # SOLIDUS + 0x0030: 0x0030, # DIGIT ZERO + 0x0031: 0x0031, # DIGIT ONE + 0x0032: 0x0032, # DIGIT TWO + 0x0033: 0x0033, # DIGIT THREE + 0x0034: 0x0034, # DIGIT FOUR + 0x0035: 0x0035, # DIGIT FIVE + 0x0036: 0x0036, # DIGIT SIX + 0x0037: 0x0037, # DIGIT SEVEN + 0x0038: 0x0038, # DIGIT EIGHT + 0x0039: 0x0039, # DIGIT NINE + 0x003a: 0x003a, # COLON + 0x003b: 0x003b, # SEMICOLON + 0x003c: 0x003c, # LESS-THAN SIGN + 0x003d: 0x003d, # EQUALS SIGN + 0x003e: 0x003e, # GREATER-THAN SIGN + 0x003f: 0x003f, # QUESTION MARK + 0x0040: 0x0040, # COMMERCIAL AT + 0x0041: 0x0041, # LATIN CAPITAL LETTER A + 0x0042: 0x0042, # LATIN CAPITAL LETTER B + 0x0043: 0x0043, # LATIN CAPITAL LETTER C + 0x0044: 0x0044, # LATIN CAPITAL LETTER D + 0x0045: 0x0045, # LATIN CAPITAL LETTER E + 0x0046: 0x0046, # LATIN CAPITAL LETTER F + 0x0047: 0x0047, # LATIN CAPITAL LETTER G + 0x0048: 0x0048, # LATIN CAPITAL LETTER H + 0x0049: 0x0049, # LATIN CAPITAL LETTER I + 0x004a: 0x004a, # LATIN CAPITAL LETTER J + 0x004b: 0x004b, # LATIN CAPITAL LETTER K + 0x004c: 0x004c, # LATIN CAPITAL LETTER L + 0x004d: 0x004d, # LATIN CAPITAL LETTER M + 0x004e: 0x004e, # LATIN CAPITAL LETTER N + 0x004f: 0x004f, # LATIN CAPITAL LETTER O + 0x0050: 0x0050, # LATIN CAPITAL LETTER P + 0x0051: 0x0051, # LATIN CAPITAL LETTER Q + 0x0052: 0x0052, # LATIN CAPITAL LETTER R + 0x0053: 0x0053, # LATIN CAPITAL LETTER S + 0x0054: 0x0054, # LATIN CAPITAL LETTER T + 0x0055: 0x0055, # LATIN CAPITAL LETTER U + 0x0056: 0x0056, # LATIN CAPITAL LETTER V + 0x0057: 0x0057, # LATIN CAPITAL LETTER W + 0x0058: 0x0058, # LATIN CAPITAL LETTER X + 0x0059: 0x0059, # LATIN CAPITAL LETTER Y + 0x005a: 0x005a, # LATIN CAPITAL LETTER Z + 0x005b: 0x005b, # LEFT SQUARE BRACKET + 0x005c: 0x005c, # REVERSE SOLIDUS + 0x005d: 0x005d, # RIGHT SQUARE BRACKET + 0x005e: 0x005e, # CIRCUMFLEX ACCENT + 0x005f: 0x005f, # LOW LINE + 0x0060: 0x0060, # GRAVE ACCENT + 0x0061: 0x0061, # LATIN SMALL LETTER A + 0x0062: 0x0062, # LATIN SMALL LETTER B + 0x0063: 0x0063, # LATIN SMALL LETTER C + 0x0064: 0x0064, # LATIN SMALL LETTER D + 0x0065: 0x0065, # LATIN SMALL LETTER E + 0x0066: 0x0066, # LATIN SMALL LETTER F + 0x0067: 0x0067, # LATIN SMALL LETTER G + 0x0068: 0x0068, # LATIN SMALL LETTER H + 0x0069: 0x0069, # LATIN SMALL LETTER I + 0x006a: 0x006a, # LATIN SMALL LETTER J + 0x006b: 0x006b, # LATIN SMALL LETTER K + 0x006c: 0x006c, # LATIN SMALL LETTER L + 0x006d: 0x006d, # LATIN SMALL LETTER M + 0x006e: 0x006e, # LATIN SMALL LETTER N + 0x006f: 0x006f, # LATIN SMALL LETTER O + 0x0070: 0x0070, # LATIN SMALL LETTER P + 0x0071: 0x0071, # LATIN SMALL LETTER Q + 0x0072: 0x0072, # LATIN SMALL LETTER R + 0x0073: 0x0073, # LATIN SMALL LETTER S + 0x0074: 0x0074, # LATIN SMALL LETTER T + 0x0075: 0x0075, # LATIN SMALL LETTER U + 0x0076: 0x0076, # LATIN SMALL LETTER V + 0x0077: 0x0077, # LATIN SMALL LETTER W + 0x0078: 0x0078, # LATIN SMALL LETTER X + 0x0079: 0x0079, # LATIN SMALL LETTER Y + 0x007a: 0x007a, # LATIN SMALL LETTER Z + 0x007b: 0x007b, # LEFT CURLY BRACKET + 0x007c: 0x007c, # VERTICAL LINE + 0x007d: 0x007d, # RIGHT CURLY BRACKET + 0x007e: 0x007e, # TILDE + 0x007f: 0x007f, # DELETE + 0x00a0: 0x00ff, # NO-BREAK SPACE + 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK + 0x00a2: 0x00bd, # CENT SIGN + 0x00a3: 0x009c, # POUND SIGN + 0x00a4: 0x00cf, # CURRENCY SIGN + 0x00a5: 0x00be, # YEN SIGN + 0x00a6: 0x00dd, # BROKEN BAR + 0x00a7: 0x00f5, # SECTION SIGN + 0x00a8: 0x00f9, # DIAERESIS + 0x00a9: 0x00b8, # COPYRIGHT SIGN + 0x00aa: 0x00d1, # FEMININE ORDINAL INDICATOR + 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00ac: 0x00aa, # NOT SIGN + 0x00ad: 0x00f0, # SOFT HYPHEN + 0x00ae: 0x00a9, # REGISTERED SIGN + 0x00af: 0x00ee, # MACRON + 0x00b0: 0x00f8, # DEGREE SIGN + 0x00b1: 0x00f1, # PLUS-MINUS SIGN + 0x00b2: 0x00fd, # SUPERSCRIPT TWO + 0x00b3: 0x00fc, # SUPERSCRIPT THREE + 0x00b4: 0x00ef, # ACUTE ACCENT + 0x00b5: 0x00e6, # MICRO SIGN + 0x00b6: 0x00f4, # PILCROW SIGN + 0x00b7: 0x00fa, # MIDDLE DOT + 0x00b8: 0x00f7, # CEDILLA + 0x00b9: 0x00fb, # SUPERSCRIPT ONE + 0x00ba: 0x00d0, # MASCULINE ORDINAL INDICATOR + 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER + 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF + 0x00be: 0x00f3, # VULGAR FRACTION THREE QUARTERS + 0x00bf: 0x00a8, # INVERTED QUESTION MARK + 0x00c0: 0x00b7, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00c1: 0x00b5, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00c2: 0x00b6, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00c3: 0x00c7, # LATIN CAPITAL LETTER A WITH TILDE + 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE + 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00c8: 0x00d4, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00ca: 0x00d2, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00cb: 0x00d3, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00cc: 0x00de, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00cd: 0x00d6, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00ce: 0x00d7, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00cf: 0x00d8, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE + 0x00d2: 0x00e3, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00d3: 0x00e0, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00d4: 0x00e2, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00d5: 0x00e5, # LATIN CAPITAL LETTER O WITH TILDE + 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00d7: 0x00e8, # MULTIPLICATION SIGN + 0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE + 0x00d9: 0x00eb, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00da: 0x00e9, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00db: 0x00ea, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S + 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE + 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE + 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00e3: 0x00c6, # LATIN SMALL LETTER A WITH TILDE + 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE + 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA + 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE + 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE + 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00ec: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE + 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE + 0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE + 0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE + 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE + 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00f5: 0x00e4, # LATIN SMALL LETTER O WITH TILDE + 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00f7: 0x00f6, # DIVISION SIGN + 0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE + 0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE + 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE + 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00ff: 0x00ed, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x011e: 0x00a6, # LATIN CAPITAL LETTER G WITH BREVE + 0x011f: 0x00a7, # LATIN SMALL LETTER G WITH BREVE + 0x0130: 0x0098, # LATIN CAPITAL LETTER I WITH DOT ABOVE + 0x0131: 0x008d, # LATIN SMALL LETTER DOTLESS I + 0x015e: 0x009e, # LATIN CAPITAL LETTER S WITH CEDILLA + 0x015f: 0x009f, # LATIN SMALL LETTER S WITH CEDILLA + 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL + 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL + 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT + 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL + 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x2580: 0x00df, # UPPER HALF BLOCK + 0x2584: 0x00dc, # LOWER HALF BLOCK + 0x2588: 0x00db, # FULL BLOCK + 0x2591: 0x00b0, # LIGHT SHADE + 0x2592: 0x00b1, # MEDIUM SHADE + 0x2593: 0x00b2, # DARK SHADE + 0x25a0: 0x00fe, # BLACK SQUARE +} diff --git a/contrib/tools/python3/src/Lib/encodings/cp858.py b/contrib/tools/python3/src/Lib/encodings/cp858.py new file mode 100644 index 0000000000..7579f52538 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp858.py @@ -0,0 +1,698 @@ +""" Python Character Mapping Codec for CP858, modified from cp850. + +""" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_map) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp858', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + +### Decoding Map + +decoding_map = codecs.make_identity_dict(range(256)) +decoding_map.update({ + 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS + 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE + 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE + 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE + 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA + 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS + 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE + 0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS + 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x008d: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE + 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE + 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE + 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE + 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE + 0x0098: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE + 0x009c: 0x00a3, # POUND SIGN + 0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE + 0x009e: 0x00d7, # MULTIPLICATION SIGN + 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK + 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE + 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE + 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE + 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE + 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE + 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE + 0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR + 0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR + 0x00a8: 0x00bf, # INVERTED QUESTION MARK + 0x00a9: 0x00ae, # REGISTERED SIGN + 0x00aa: 0x00ac, # NOT SIGN + 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF + 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER + 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK + 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00b0: 0x2591, # LIGHT SHADE + 0x00b1: 0x2592, # MEDIUM SHADE + 0x00b2: 0x2593, # DARK SHADE + 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL + 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x00b5: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00b6: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00b7: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00b8: 0x00a9, # COPYRIGHT SIGN + 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL + 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x00bd: 0x00a2, # CENT SIGN + 0x00be: 0x00a5, # YEN SIGN + 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL + 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x00c6: 0x00e3, # LATIN SMALL LETTER A WITH TILDE + 0x00c7: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE + 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x00cf: 0x00a4, # CURRENCY SIGN + 0x00d0: 0x00f0, # LATIN SMALL LETTER ETH + 0x00d1: 0x00d0, # LATIN CAPITAL LETTER ETH + 0x00d2: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00d3: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00d4: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00d5: 0x20ac, # EURO SIGN + 0x00d6: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00d7: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00d8: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT + 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x00db: 0x2588, # FULL BLOCK + 0x00dc: 0x2584, # LOWER HALF BLOCK + 0x00dd: 0x00a6, # BROKEN BAR + 0x00de: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00df: 0x2580, # UPPER HALF BLOCK + 0x00e0: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S + 0x00e2: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00e3: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00e4: 0x00f5, # LATIN SMALL LETTER O WITH TILDE + 0x00e5: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE + 0x00e6: 0x00b5, # MICRO SIGN + 0x00e7: 0x00fe, # LATIN SMALL LETTER THORN + 0x00e8: 0x00de, # LATIN CAPITAL LETTER THORN + 0x00e9: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00ea: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00eb: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00ec: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE + 0x00ed: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE + 0x00ee: 0x00af, # MACRON + 0x00ef: 0x00b4, # ACUTE ACCENT + 0x00f0: 0x00ad, # SOFT HYPHEN + 0x00f1: 0x00b1, # PLUS-MINUS SIGN + 0x00f2: 0x2017, # DOUBLE LOW LINE + 0x00f3: 0x00be, # VULGAR FRACTION THREE QUARTERS + 0x00f4: 0x00b6, # PILCROW SIGN + 0x00f5: 0x00a7, # SECTION SIGN + 0x00f6: 0x00f7, # DIVISION SIGN + 0x00f7: 0x00b8, # CEDILLA + 0x00f8: 0x00b0, # DEGREE SIGN + 0x00f9: 0x00a8, # DIAERESIS + 0x00fa: 0x00b7, # MIDDLE DOT + 0x00fb: 0x00b9, # SUPERSCRIPT ONE + 0x00fc: 0x00b3, # SUPERSCRIPT THREE + 0x00fd: 0x00b2, # SUPERSCRIPT TWO + 0x00fe: 0x25a0, # BLACK SQUARE + 0x00ff: 0x00a0, # NO-BREAK SPACE +}) + +### Decoding Table + +decoding_table = ( + '\x00' # 0x0000 -> NULL + '\x01' # 0x0001 -> START OF HEADING + '\x02' # 0x0002 -> START OF TEXT + '\x03' # 0x0003 -> END OF TEXT + '\x04' # 0x0004 -> END OF TRANSMISSION + '\x05' # 0x0005 -> ENQUIRY + '\x06' # 0x0006 -> ACKNOWLEDGE + '\x07' # 0x0007 -> BELL + '\x08' # 0x0008 -> BACKSPACE + '\t' # 0x0009 -> HORIZONTAL TABULATION + '\n' # 0x000a -> LINE FEED + '\x0b' # 0x000b -> VERTICAL TABULATION + '\x0c' # 0x000c -> FORM FEED + '\r' # 0x000d -> CARRIAGE RETURN + '\x0e' # 0x000e -> SHIFT OUT + '\x0f' # 0x000f -> SHIFT IN + '\x10' # 0x0010 -> DATA LINK ESCAPE + '\x11' # 0x0011 -> DEVICE CONTROL ONE + '\x12' # 0x0012 -> DEVICE CONTROL TWO + '\x13' # 0x0013 -> DEVICE CONTROL THREE + '\x14' # 0x0014 -> DEVICE CONTROL FOUR + '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x0016 -> SYNCHRONOUS IDLE + '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK + '\x18' # 0x0018 -> CANCEL + '\x19' # 0x0019 -> END OF MEDIUM + '\x1a' # 0x001a -> SUBSTITUTE + '\x1b' # 0x001b -> ESCAPE + '\x1c' # 0x001c -> FILE SEPARATOR + '\x1d' # 0x001d -> GROUP SEPARATOR + '\x1e' # 0x001e -> RECORD SEPARATOR + '\x1f' # 0x001f -> UNIT SEPARATOR + ' ' # 0x0020 -> SPACE + '!' # 0x0021 -> EXCLAMATION MARK + '"' # 0x0022 -> QUOTATION MARK + '#' # 0x0023 -> NUMBER SIGN + '$' # 0x0024 -> DOLLAR SIGN + '%' # 0x0025 -> PERCENT SIGN + '&' # 0x0026 -> AMPERSAND + "'" # 0x0027 -> APOSTROPHE + '(' # 0x0028 -> LEFT PARENTHESIS + ')' # 0x0029 -> RIGHT PARENTHESIS + '*' # 0x002a -> ASTERISK + '+' # 0x002b -> PLUS SIGN + ',' # 0x002c -> COMMA + '-' # 0x002d -> HYPHEN-MINUS + '.' # 0x002e -> FULL STOP + '/' # 0x002f -> SOLIDUS + '0' # 0x0030 -> DIGIT ZERO + '1' # 0x0031 -> DIGIT ONE + '2' # 0x0032 -> DIGIT TWO + '3' # 0x0033 -> DIGIT THREE + '4' # 0x0034 -> DIGIT FOUR + '5' # 0x0035 -> DIGIT FIVE + '6' # 0x0036 -> DIGIT SIX + '7' # 0x0037 -> DIGIT SEVEN + '8' # 0x0038 -> DIGIT EIGHT + '9' # 0x0039 -> DIGIT NINE + ':' # 0x003a -> COLON + ';' # 0x003b -> SEMICOLON + '<' # 0x003c -> LESS-THAN SIGN + '=' # 0x003d -> EQUALS SIGN + '>' # 0x003e -> GREATER-THAN SIGN + '?' # 0x003f -> QUESTION MARK + '@' # 0x0040 -> COMMERCIAL AT + 'A' # 0x0041 -> LATIN CAPITAL LETTER A + 'B' # 0x0042 -> LATIN CAPITAL LETTER B + 'C' # 0x0043 -> LATIN CAPITAL LETTER C + 'D' # 0x0044 -> LATIN CAPITAL LETTER D + 'E' # 0x0045 -> LATIN CAPITAL LETTER E + 'F' # 0x0046 -> LATIN CAPITAL LETTER F + 'G' # 0x0047 -> LATIN CAPITAL LETTER G + 'H' # 0x0048 -> LATIN CAPITAL LETTER H + 'I' # 0x0049 -> LATIN CAPITAL LETTER I + 'J' # 0x004a -> LATIN CAPITAL LETTER J + 'K' # 0x004b -> LATIN CAPITAL LETTER K + 'L' # 0x004c -> LATIN CAPITAL LETTER L + 'M' # 0x004d -> LATIN CAPITAL LETTER M + 'N' # 0x004e -> LATIN CAPITAL LETTER N + 'O' # 0x004f -> LATIN CAPITAL LETTER O + 'P' # 0x0050 -> LATIN CAPITAL LETTER P + 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q + 'R' # 0x0052 -> LATIN CAPITAL LETTER R + 'S' # 0x0053 -> LATIN CAPITAL LETTER S + 'T' # 0x0054 -> LATIN CAPITAL LETTER T + 'U' # 0x0055 -> LATIN CAPITAL LETTER U + 'V' # 0x0056 -> LATIN CAPITAL LETTER V + 'W' # 0x0057 -> LATIN CAPITAL LETTER W + 'X' # 0x0058 -> LATIN CAPITAL LETTER X + 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y + 'Z' # 0x005a -> LATIN CAPITAL LETTER Z + '[' # 0x005b -> LEFT SQUARE BRACKET + '\\' # 0x005c -> REVERSE SOLIDUS + ']' # 0x005d -> RIGHT SQUARE BRACKET + '^' # 0x005e -> CIRCUMFLEX ACCENT + '_' # 0x005f -> LOW LINE + '`' # 0x0060 -> GRAVE ACCENT + 'a' # 0x0061 -> LATIN SMALL LETTER A + 'b' # 0x0062 -> LATIN SMALL LETTER B + 'c' # 0x0063 -> LATIN SMALL LETTER C + 'd' # 0x0064 -> LATIN SMALL LETTER D + 'e' # 0x0065 -> LATIN SMALL LETTER E + 'f' # 0x0066 -> LATIN SMALL LETTER F + 'g' # 0x0067 -> LATIN SMALL LETTER G + 'h' # 0x0068 -> LATIN SMALL LETTER H + 'i' # 0x0069 -> LATIN SMALL LETTER I + 'j' # 0x006a -> LATIN SMALL LETTER J + 'k' # 0x006b -> LATIN SMALL LETTER K + 'l' # 0x006c -> LATIN SMALL LETTER L + 'm' # 0x006d -> LATIN SMALL LETTER M + 'n' # 0x006e -> LATIN SMALL LETTER N + 'o' # 0x006f -> LATIN SMALL LETTER O + 'p' # 0x0070 -> LATIN SMALL LETTER P + 'q' # 0x0071 -> LATIN SMALL LETTER Q + 'r' # 0x0072 -> LATIN SMALL LETTER R + 's' # 0x0073 -> LATIN SMALL LETTER S + 't' # 0x0074 -> LATIN SMALL LETTER T + 'u' # 0x0075 -> LATIN SMALL LETTER U + 'v' # 0x0076 -> LATIN SMALL LETTER V + 'w' # 0x0077 -> LATIN SMALL LETTER W + 'x' # 0x0078 -> LATIN SMALL LETTER X + 'y' # 0x0079 -> LATIN SMALL LETTER Y + 'z' # 0x007a -> LATIN SMALL LETTER Z + '{' # 0x007b -> LEFT CURLY BRACKET + '|' # 0x007c -> VERTICAL LINE + '}' # 0x007d -> RIGHT CURLY BRACKET + '~' # 0x007e -> TILDE + '\x7f' # 0x007f -> DELETE + '\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS + '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE + '\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE + '\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA + '\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS + '\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE + '\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS + '\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xec' # 0x008d -> LATIN SMALL LETTER I WITH GRAVE + '\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE + '\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE + '\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE + '\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE + '\xff' # 0x0098 -> LATIN SMALL LETTER Y WITH DIAERESIS + '\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE + '\xa3' # 0x009c -> POUND SIGN + '\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE + '\xd7' # 0x009e -> MULTIPLICATION SIGN + '\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK + '\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE + '\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE + '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE + '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE + '\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE + '\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE + '\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR + '\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR + '\xbf' # 0x00a8 -> INVERTED QUESTION MARK + '\xae' # 0x00a9 -> REGISTERED SIGN + '\xac' # 0x00aa -> NOT SIGN + '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF + '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER + '\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK + '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u2591' # 0x00b0 -> LIGHT SHADE + '\u2592' # 0x00b1 -> MEDIUM SHADE + '\u2593' # 0x00b2 -> DARK SHADE + '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL + '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT + '\xc1' # 0x00b5 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc2' # 0x00b6 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xc0' # 0x00b7 -> LATIN CAPITAL LETTER A WITH GRAVE + '\xa9' # 0x00b8 -> COPYRIGHT SIGN + '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL + '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT + '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT + '\xa2' # 0x00bd -> CENT SIGN + '\xa5' # 0x00be -> YEN SIGN + '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT + '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT + '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL + '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT + '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL + '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + '\xe3' # 0x00c6 -> LATIN SMALL LETTER A WITH TILDE + '\xc3' # 0x00c7 -> LATIN CAPITAL LETTER A WITH TILDE + '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT + '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL + '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + '\xa4' # 0x00cf -> CURRENCY SIGN + '\xf0' # 0x00d0 -> LATIN SMALL LETTER ETH + '\xd0' # 0x00d1 -> LATIN CAPITAL LETTER ETH + '\xca' # 0x00d2 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xcb' # 0x00d3 -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xc8' # 0x00d4 -> LATIN CAPITAL LETTER E WITH GRAVE + '\u20ac' # 0x00d5 -> EURO SIGN + '\xcd' # 0x00d6 -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0x00d7 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0x00d8 -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT + '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT + '\u2588' # 0x00db -> FULL BLOCK + '\u2584' # 0x00dc -> LOWER HALF BLOCK + '\xa6' # 0x00dd -> BROKEN BAR + '\xcc' # 0x00de -> LATIN CAPITAL LETTER I WITH GRAVE + '\u2580' # 0x00df -> UPPER HALF BLOCK + '\xd3' # 0x00e0 -> LATIN CAPITAL LETTER O WITH ACUTE + '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S + '\xd4' # 0x00e2 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\xd2' # 0x00e3 -> LATIN CAPITAL LETTER O WITH GRAVE + '\xf5' # 0x00e4 -> LATIN SMALL LETTER O WITH TILDE + '\xd5' # 0x00e5 -> LATIN CAPITAL LETTER O WITH TILDE + '\xb5' # 0x00e6 -> MICRO SIGN + '\xfe' # 0x00e7 -> LATIN SMALL LETTER THORN + '\xde' # 0x00e8 -> LATIN CAPITAL LETTER THORN + '\xda' # 0x00e9 -> LATIN CAPITAL LETTER U WITH ACUTE + '\xdb' # 0x00ea -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xd9' # 0x00eb -> LATIN CAPITAL LETTER U WITH GRAVE + '\xfd' # 0x00ec -> LATIN SMALL LETTER Y WITH ACUTE + '\xdd' # 0x00ed -> LATIN CAPITAL LETTER Y WITH ACUTE + '\xaf' # 0x00ee -> MACRON + '\xb4' # 0x00ef -> ACUTE ACCENT + '\xad' # 0x00f0 -> SOFT HYPHEN + '\xb1' # 0x00f1 -> PLUS-MINUS SIGN + '\u2017' # 0x00f2 -> DOUBLE LOW LINE + '\xbe' # 0x00f3 -> VULGAR FRACTION THREE QUARTERS + '\xb6' # 0x00f4 -> PILCROW SIGN + '\xa7' # 0x00f5 -> SECTION SIGN + '\xf7' # 0x00f6 -> DIVISION SIGN + '\xb8' # 0x00f7 -> CEDILLA + '\xb0' # 0x00f8 -> DEGREE SIGN + '\xa8' # 0x00f9 -> DIAERESIS + '\xb7' # 0x00fa -> MIDDLE DOT + '\xb9' # 0x00fb -> SUPERSCRIPT ONE + '\xb3' # 0x00fc -> SUPERSCRIPT THREE + '\xb2' # 0x00fd -> SUPERSCRIPT TWO + '\u25a0' # 0x00fe -> BLACK SQUARE + '\xa0' # 0x00ff -> NO-BREAK SPACE +) + +### Encoding Map + +encoding_map = { + 0x0000: 0x0000, # NULL + 0x0001: 0x0001, # START OF HEADING + 0x0002: 0x0002, # START OF TEXT + 0x0003: 0x0003, # END OF TEXT + 0x0004: 0x0004, # END OF TRANSMISSION + 0x0005: 0x0005, # ENQUIRY + 0x0006: 0x0006, # ACKNOWLEDGE + 0x0007: 0x0007, # BELL + 0x0008: 0x0008, # BACKSPACE + 0x0009: 0x0009, # HORIZONTAL TABULATION + 0x000a: 0x000a, # LINE FEED + 0x000b: 0x000b, # VERTICAL TABULATION + 0x000c: 0x000c, # FORM FEED + 0x000d: 0x000d, # CARRIAGE RETURN + 0x000e: 0x000e, # SHIFT OUT + 0x000f: 0x000f, # SHIFT IN + 0x0010: 0x0010, # DATA LINK ESCAPE + 0x0011: 0x0011, # DEVICE CONTROL ONE + 0x0012: 0x0012, # DEVICE CONTROL TWO + 0x0013: 0x0013, # DEVICE CONTROL THREE + 0x0014: 0x0014, # DEVICE CONTROL FOUR + 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE + 0x0016: 0x0016, # SYNCHRONOUS IDLE + 0x0017: 0x0017, # END OF TRANSMISSION BLOCK + 0x0018: 0x0018, # CANCEL + 0x0019: 0x0019, # END OF MEDIUM + 0x001a: 0x001a, # SUBSTITUTE + 0x001b: 0x001b, # ESCAPE + 0x001c: 0x001c, # FILE SEPARATOR + 0x001d: 0x001d, # GROUP SEPARATOR + 0x001e: 0x001e, # RECORD SEPARATOR + 0x001f: 0x001f, # UNIT SEPARATOR + 0x0020: 0x0020, # SPACE + 0x0021: 0x0021, # EXCLAMATION MARK + 0x0022: 0x0022, # QUOTATION MARK + 0x0023: 0x0023, # NUMBER SIGN + 0x0024: 0x0024, # DOLLAR SIGN + 0x0025: 0x0025, # PERCENT SIGN + 0x0026: 0x0026, # AMPERSAND + 0x0027: 0x0027, # APOSTROPHE + 0x0028: 0x0028, # LEFT PARENTHESIS + 0x0029: 0x0029, # RIGHT PARENTHESIS + 0x002a: 0x002a, # ASTERISK + 0x002b: 0x002b, # PLUS SIGN + 0x002c: 0x002c, # COMMA + 0x002d: 0x002d, # HYPHEN-MINUS + 0x002e: 0x002e, # FULL STOP + 0x002f: 0x002f, # SOLIDUS + 0x0030: 0x0030, # DIGIT ZERO + 0x0031: 0x0031, # DIGIT ONE + 0x0032: 0x0032, # DIGIT TWO + 0x0033: 0x0033, # DIGIT THREE + 0x0034: 0x0034, # DIGIT FOUR + 0x0035: 0x0035, # DIGIT FIVE + 0x0036: 0x0036, # DIGIT SIX + 0x0037: 0x0037, # DIGIT SEVEN + 0x0038: 0x0038, # DIGIT EIGHT + 0x0039: 0x0039, # DIGIT NINE + 0x003a: 0x003a, # COLON + 0x003b: 0x003b, # SEMICOLON + 0x003c: 0x003c, # LESS-THAN SIGN + 0x003d: 0x003d, # EQUALS SIGN + 0x003e: 0x003e, # GREATER-THAN SIGN + 0x003f: 0x003f, # QUESTION MARK + 0x0040: 0x0040, # COMMERCIAL AT + 0x0041: 0x0041, # LATIN CAPITAL LETTER A + 0x0042: 0x0042, # LATIN CAPITAL LETTER B + 0x0043: 0x0043, # LATIN CAPITAL LETTER C + 0x0044: 0x0044, # LATIN CAPITAL LETTER D + 0x0045: 0x0045, # LATIN CAPITAL LETTER E + 0x0046: 0x0046, # LATIN CAPITAL LETTER F + 0x0047: 0x0047, # LATIN CAPITAL LETTER G + 0x0048: 0x0048, # LATIN CAPITAL LETTER H + 0x0049: 0x0049, # LATIN CAPITAL LETTER I + 0x004a: 0x004a, # LATIN CAPITAL LETTER J + 0x004b: 0x004b, # LATIN CAPITAL LETTER K + 0x004c: 0x004c, # LATIN CAPITAL LETTER L + 0x004d: 0x004d, # LATIN CAPITAL LETTER M + 0x004e: 0x004e, # LATIN CAPITAL LETTER N + 0x004f: 0x004f, # LATIN CAPITAL LETTER O + 0x0050: 0x0050, # LATIN CAPITAL LETTER P + 0x0051: 0x0051, # LATIN CAPITAL LETTER Q + 0x0052: 0x0052, # LATIN CAPITAL LETTER R + 0x0053: 0x0053, # LATIN CAPITAL LETTER S + 0x0054: 0x0054, # LATIN CAPITAL LETTER T + 0x0055: 0x0055, # LATIN CAPITAL LETTER U + 0x0056: 0x0056, # LATIN CAPITAL LETTER V + 0x0057: 0x0057, # LATIN CAPITAL LETTER W + 0x0058: 0x0058, # LATIN CAPITAL LETTER X + 0x0059: 0x0059, # LATIN CAPITAL LETTER Y + 0x005a: 0x005a, # LATIN CAPITAL LETTER Z + 0x005b: 0x005b, # LEFT SQUARE BRACKET + 0x005c: 0x005c, # REVERSE SOLIDUS + 0x005d: 0x005d, # RIGHT SQUARE BRACKET + 0x005e: 0x005e, # CIRCUMFLEX ACCENT + 0x005f: 0x005f, # LOW LINE + 0x0060: 0x0060, # GRAVE ACCENT + 0x0061: 0x0061, # LATIN SMALL LETTER A + 0x0062: 0x0062, # LATIN SMALL LETTER B + 0x0063: 0x0063, # LATIN SMALL LETTER C + 0x0064: 0x0064, # LATIN SMALL LETTER D + 0x0065: 0x0065, # LATIN SMALL LETTER E + 0x0066: 0x0066, # LATIN SMALL LETTER F + 0x0067: 0x0067, # LATIN SMALL LETTER G + 0x0068: 0x0068, # LATIN SMALL LETTER H + 0x0069: 0x0069, # LATIN SMALL LETTER I + 0x006a: 0x006a, # LATIN SMALL LETTER J + 0x006b: 0x006b, # LATIN SMALL LETTER K + 0x006c: 0x006c, # LATIN SMALL LETTER L + 0x006d: 0x006d, # LATIN SMALL LETTER M + 0x006e: 0x006e, # LATIN SMALL LETTER N + 0x006f: 0x006f, # LATIN SMALL LETTER O + 0x0070: 0x0070, # LATIN SMALL LETTER P + 0x0071: 0x0071, # LATIN SMALL LETTER Q + 0x0072: 0x0072, # LATIN SMALL LETTER R + 0x0073: 0x0073, # LATIN SMALL LETTER S + 0x0074: 0x0074, # LATIN SMALL LETTER T + 0x0075: 0x0075, # LATIN SMALL LETTER U + 0x0076: 0x0076, # LATIN SMALL LETTER V + 0x0077: 0x0077, # LATIN SMALL LETTER W + 0x0078: 0x0078, # LATIN SMALL LETTER X + 0x0079: 0x0079, # LATIN SMALL LETTER Y + 0x007a: 0x007a, # LATIN SMALL LETTER Z + 0x007b: 0x007b, # LEFT CURLY BRACKET + 0x007c: 0x007c, # VERTICAL LINE + 0x007d: 0x007d, # RIGHT CURLY BRACKET + 0x007e: 0x007e, # TILDE + 0x007f: 0x007f, # DELETE + 0x00a0: 0x00ff, # NO-BREAK SPACE + 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK + 0x00a2: 0x00bd, # CENT SIGN + 0x00a3: 0x009c, # POUND SIGN + 0x00a4: 0x00cf, # CURRENCY SIGN + 0x00a5: 0x00be, # YEN SIGN + 0x00a6: 0x00dd, # BROKEN BAR + 0x00a7: 0x00f5, # SECTION SIGN + 0x00a8: 0x00f9, # DIAERESIS + 0x00a9: 0x00b8, # COPYRIGHT SIGN + 0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR + 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00ac: 0x00aa, # NOT SIGN + 0x00ad: 0x00f0, # SOFT HYPHEN + 0x00ae: 0x00a9, # REGISTERED SIGN + 0x00af: 0x00ee, # MACRON + 0x00b0: 0x00f8, # DEGREE SIGN + 0x00b1: 0x00f1, # PLUS-MINUS SIGN + 0x00b2: 0x00fd, # SUPERSCRIPT TWO + 0x00b3: 0x00fc, # SUPERSCRIPT THREE + 0x00b4: 0x00ef, # ACUTE ACCENT + 0x00b5: 0x00e6, # MICRO SIGN + 0x00b6: 0x00f4, # PILCROW SIGN + 0x00b7: 0x00fa, # MIDDLE DOT + 0x00b8: 0x00f7, # CEDILLA + 0x00b9: 0x00fb, # SUPERSCRIPT ONE + 0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR + 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER + 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF + 0x00be: 0x00f3, # VULGAR FRACTION THREE QUARTERS + 0x00bf: 0x00a8, # INVERTED QUESTION MARK + 0x00c0: 0x00b7, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00c1: 0x00b5, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00c2: 0x00b6, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00c3: 0x00c7, # LATIN CAPITAL LETTER A WITH TILDE + 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE + 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00c8: 0x00d4, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00ca: 0x00d2, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00cb: 0x00d3, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00cc: 0x00de, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00cd: 0x00d6, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00ce: 0x00d7, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00cf: 0x00d8, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00d0: 0x00d1, # LATIN CAPITAL LETTER ETH + 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE + 0x00d2: 0x00e3, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00d3: 0x00e0, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00d4: 0x00e2, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00d5: 0x00e5, # LATIN CAPITAL LETTER O WITH TILDE + 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00d7: 0x009e, # MULTIPLICATION SIGN + 0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE + 0x00d9: 0x00eb, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00da: 0x00e9, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00db: 0x00ea, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00dd: 0x00ed, # LATIN CAPITAL LETTER Y WITH ACUTE + 0x00de: 0x00e8, # LATIN CAPITAL LETTER THORN + 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S + 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE + 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE + 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00e3: 0x00c6, # LATIN SMALL LETTER A WITH TILDE + 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE + 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA + 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE + 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE + 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00ec: 0x008d, # LATIN SMALL LETTER I WITH GRAVE + 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE + 0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00f0: 0x00d0, # LATIN SMALL LETTER ETH + 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE + 0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE + 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE + 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00f5: 0x00e4, # LATIN SMALL LETTER O WITH TILDE + 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00f7: 0x00f6, # DIVISION SIGN + 0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE + 0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE + 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE + 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00fd: 0x00ec, # LATIN SMALL LETTER Y WITH ACUTE + 0x00fe: 0x00e7, # LATIN SMALL LETTER THORN + 0x00ff: 0x0098, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x20ac: 0x00d5, # EURO SIGN + 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK + 0x2017: 0x00f2, # DOUBLE LOW LINE + 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL + 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL + 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT + 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL + 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x2580: 0x00df, # UPPER HALF BLOCK + 0x2584: 0x00dc, # LOWER HALF BLOCK + 0x2588: 0x00db, # FULL BLOCK + 0x2591: 0x00b0, # LIGHT SHADE + 0x2592: 0x00b1, # MEDIUM SHADE + 0x2593: 0x00b2, # DARK SHADE + 0x25a0: 0x00fe, # BLACK SQUARE +} diff --git a/contrib/tools/python3/src/Lib/encodings/cp860.py b/contrib/tools/python3/src/Lib/encodings/cp860.py new file mode 100644 index 0000000000..65903e7464 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp860.py @@ -0,0 +1,698 @@ +""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP860.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_map) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp860', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + +### Decoding Map + +decoding_map = codecs.make_identity_dict(range(256)) +decoding_map.update({ + 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS + 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE + 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x0084: 0x00e3, # LATIN SMALL LETTER A WITH TILDE + 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE + 0x0086: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE + 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA + 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x0089: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE + 0x008b: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE + 0x008c: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x008d: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE + 0x008e: 0x00c3, # LATIN CAPITAL LETTER A WITH TILDE + 0x008f: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x0091: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE + 0x0092: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE + 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x0094: 0x00f5, # LATIN SMALL LETTER O WITH TILDE + 0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE + 0x0096: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE + 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE + 0x0098: 0x00cc, # LATIN CAPITAL LETTER I WITH GRAVE + 0x0099: 0x00d5, # LATIN CAPITAL LETTER O WITH TILDE + 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x009b: 0x00a2, # CENT SIGN + 0x009c: 0x00a3, # POUND SIGN + 0x009d: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE + 0x009e: 0x20a7, # PESETA SIGN + 0x009f: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE + 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE + 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE + 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE + 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE + 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE + 0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR + 0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR + 0x00a8: 0x00bf, # INVERTED QUESTION MARK + 0x00a9: 0x00d2, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00aa: 0x00ac, # NOT SIGN + 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF + 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER + 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK + 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00b0: 0x2591, # LIGHT SHADE + 0x00b1: 0x2592, # MEDIUM SHADE + 0x00b2: 0x2593, # DARK SHADE + 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL + 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL + 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL + 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT + 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x00db: 0x2588, # FULL BLOCK + 0x00dc: 0x2584, # LOWER HALF BLOCK + 0x00dd: 0x258c, # LEFT HALF BLOCK + 0x00de: 0x2590, # RIGHT HALF BLOCK + 0x00df: 0x2580, # UPPER HALF BLOCK + 0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA + 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S + 0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA + 0x00e3: 0x03c0, # GREEK SMALL LETTER PI + 0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA + 0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA + 0x00e6: 0x00b5, # MICRO SIGN + 0x00e7: 0x03c4, # GREEK SMALL LETTER TAU + 0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI + 0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA + 0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA + 0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA + 0x00ec: 0x221e, # INFINITY + 0x00ed: 0x03c6, # GREEK SMALL LETTER PHI + 0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON + 0x00ef: 0x2229, # INTERSECTION + 0x00f0: 0x2261, # IDENTICAL TO + 0x00f1: 0x00b1, # PLUS-MINUS SIGN + 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO + 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO + 0x00f4: 0x2320, # TOP HALF INTEGRAL + 0x00f5: 0x2321, # BOTTOM HALF INTEGRAL + 0x00f6: 0x00f7, # DIVISION SIGN + 0x00f7: 0x2248, # ALMOST EQUAL TO + 0x00f8: 0x00b0, # DEGREE SIGN + 0x00f9: 0x2219, # BULLET OPERATOR + 0x00fa: 0x00b7, # MIDDLE DOT + 0x00fb: 0x221a, # SQUARE ROOT + 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N + 0x00fd: 0x00b2, # SUPERSCRIPT TWO + 0x00fe: 0x25a0, # BLACK SQUARE + 0x00ff: 0x00a0, # NO-BREAK SPACE +}) + +### Decoding Table + +decoding_table = ( + '\x00' # 0x0000 -> NULL + '\x01' # 0x0001 -> START OF HEADING + '\x02' # 0x0002 -> START OF TEXT + '\x03' # 0x0003 -> END OF TEXT + '\x04' # 0x0004 -> END OF TRANSMISSION + '\x05' # 0x0005 -> ENQUIRY + '\x06' # 0x0006 -> ACKNOWLEDGE + '\x07' # 0x0007 -> BELL + '\x08' # 0x0008 -> BACKSPACE + '\t' # 0x0009 -> HORIZONTAL TABULATION + '\n' # 0x000a -> LINE FEED + '\x0b' # 0x000b -> VERTICAL TABULATION + '\x0c' # 0x000c -> FORM FEED + '\r' # 0x000d -> CARRIAGE RETURN + '\x0e' # 0x000e -> SHIFT OUT + '\x0f' # 0x000f -> SHIFT IN + '\x10' # 0x0010 -> DATA LINK ESCAPE + '\x11' # 0x0011 -> DEVICE CONTROL ONE + '\x12' # 0x0012 -> DEVICE CONTROL TWO + '\x13' # 0x0013 -> DEVICE CONTROL THREE + '\x14' # 0x0014 -> DEVICE CONTROL FOUR + '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x0016 -> SYNCHRONOUS IDLE + '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK + '\x18' # 0x0018 -> CANCEL + '\x19' # 0x0019 -> END OF MEDIUM + '\x1a' # 0x001a -> SUBSTITUTE + '\x1b' # 0x001b -> ESCAPE + '\x1c' # 0x001c -> FILE SEPARATOR + '\x1d' # 0x001d -> GROUP SEPARATOR + '\x1e' # 0x001e -> RECORD SEPARATOR + '\x1f' # 0x001f -> UNIT SEPARATOR + ' ' # 0x0020 -> SPACE + '!' # 0x0021 -> EXCLAMATION MARK + '"' # 0x0022 -> QUOTATION MARK + '#' # 0x0023 -> NUMBER SIGN + '$' # 0x0024 -> DOLLAR SIGN + '%' # 0x0025 -> PERCENT SIGN + '&' # 0x0026 -> AMPERSAND + "'" # 0x0027 -> APOSTROPHE + '(' # 0x0028 -> LEFT PARENTHESIS + ')' # 0x0029 -> RIGHT PARENTHESIS + '*' # 0x002a -> ASTERISK + '+' # 0x002b -> PLUS SIGN + ',' # 0x002c -> COMMA + '-' # 0x002d -> HYPHEN-MINUS + '.' # 0x002e -> FULL STOP + '/' # 0x002f -> SOLIDUS + '0' # 0x0030 -> DIGIT ZERO + '1' # 0x0031 -> DIGIT ONE + '2' # 0x0032 -> DIGIT TWO + '3' # 0x0033 -> DIGIT THREE + '4' # 0x0034 -> DIGIT FOUR + '5' # 0x0035 -> DIGIT FIVE + '6' # 0x0036 -> DIGIT SIX + '7' # 0x0037 -> DIGIT SEVEN + '8' # 0x0038 -> DIGIT EIGHT + '9' # 0x0039 -> DIGIT NINE + ':' # 0x003a -> COLON + ';' # 0x003b -> SEMICOLON + '<' # 0x003c -> LESS-THAN SIGN + '=' # 0x003d -> EQUALS SIGN + '>' # 0x003e -> GREATER-THAN SIGN + '?' # 0x003f -> QUESTION MARK + '@' # 0x0040 -> COMMERCIAL AT + 'A' # 0x0041 -> LATIN CAPITAL LETTER A + 'B' # 0x0042 -> LATIN CAPITAL LETTER B + 'C' # 0x0043 -> LATIN CAPITAL LETTER C + 'D' # 0x0044 -> LATIN CAPITAL LETTER D + 'E' # 0x0045 -> LATIN CAPITAL LETTER E + 'F' # 0x0046 -> LATIN CAPITAL LETTER F + 'G' # 0x0047 -> LATIN CAPITAL LETTER G + 'H' # 0x0048 -> LATIN CAPITAL LETTER H + 'I' # 0x0049 -> LATIN CAPITAL LETTER I + 'J' # 0x004a -> LATIN CAPITAL LETTER J + 'K' # 0x004b -> LATIN CAPITAL LETTER K + 'L' # 0x004c -> LATIN CAPITAL LETTER L + 'M' # 0x004d -> LATIN CAPITAL LETTER M + 'N' # 0x004e -> LATIN CAPITAL LETTER N + 'O' # 0x004f -> LATIN CAPITAL LETTER O + 'P' # 0x0050 -> LATIN CAPITAL LETTER P + 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q + 'R' # 0x0052 -> LATIN CAPITAL LETTER R + 'S' # 0x0053 -> LATIN CAPITAL LETTER S + 'T' # 0x0054 -> LATIN CAPITAL LETTER T + 'U' # 0x0055 -> LATIN CAPITAL LETTER U + 'V' # 0x0056 -> LATIN CAPITAL LETTER V + 'W' # 0x0057 -> LATIN CAPITAL LETTER W + 'X' # 0x0058 -> LATIN CAPITAL LETTER X + 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y + 'Z' # 0x005a -> LATIN CAPITAL LETTER Z + '[' # 0x005b -> LEFT SQUARE BRACKET + '\\' # 0x005c -> REVERSE SOLIDUS + ']' # 0x005d -> RIGHT SQUARE BRACKET + '^' # 0x005e -> CIRCUMFLEX ACCENT + '_' # 0x005f -> LOW LINE + '`' # 0x0060 -> GRAVE ACCENT + 'a' # 0x0061 -> LATIN SMALL LETTER A + 'b' # 0x0062 -> LATIN SMALL LETTER B + 'c' # 0x0063 -> LATIN SMALL LETTER C + 'd' # 0x0064 -> LATIN SMALL LETTER D + 'e' # 0x0065 -> LATIN SMALL LETTER E + 'f' # 0x0066 -> LATIN SMALL LETTER F + 'g' # 0x0067 -> LATIN SMALL LETTER G + 'h' # 0x0068 -> LATIN SMALL LETTER H + 'i' # 0x0069 -> LATIN SMALL LETTER I + 'j' # 0x006a -> LATIN SMALL LETTER J + 'k' # 0x006b -> LATIN SMALL LETTER K + 'l' # 0x006c -> LATIN SMALL LETTER L + 'm' # 0x006d -> LATIN SMALL LETTER M + 'n' # 0x006e -> LATIN SMALL LETTER N + 'o' # 0x006f -> LATIN SMALL LETTER O + 'p' # 0x0070 -> LATIN SMALL LETTER P + 'q' # 0x0071 -> LATIN SMALL LETTER Q + 'r' # 0x0072 -> LATIN SMALL LETTER R + 's' # 0x0073 -> LATIN SMALL LETTER S + 't' # 0x0074 -> LATIN SMALL LETTER T + 'u' # 0x0075 -> LATIN SMALL LETTER U + 'v' # 0x0076 -> LATIN SMALL LETTER V + 'w' # 0x0077 -> LATIN SMALL LETTER W + 'x' # 0x0078 -> LATIN SMALL LETTER X + 'y' # 0x0079 -> LATIN SMALL LETTER Y + 'z' # 0x007a -> LATIN SMALL LETTER Z + '{' # 0x007b -> LEFT CURLY BRACKET + '|' # 0x007c -> VERTICAL LINE + '}' # 0x007d -> RIGHT CURLY BRACKET + '~' # 0x007e -> TILDE + '\x7f' # 0x007f -> DELETE + '\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS + '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE + '\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe3' # 0x0084 -> LATIN SMALL LETTER A WITH TILDE + '\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE + '\xc1' # 0x0086 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA + '\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xca' # 0x0089 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE + '\xcd' # 0x008b -> LATIN CAPITAL LETTER I WITH ACUTE + '\xd4' # 0x008c -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\xec' # 0x008d -> LATIN SMALL LETTER I WITH GRAVE + '\xc3' # 0x008e -> LATIN CAPITAL LETTER A WITH TILDE + '\xc2' # 0x008f -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xc0' # 0x0091 -> LATIN CAPITAL LETTER A WITH GRAVE + '\xc8' # 0x0092 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf5' # 0x0094 -> LATIN SMALL LETTER O WITH TILDE + '\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE + '\xda' # 0x0096 -> LATIN CAPITAL LETTER U WITH ACUTE + '\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE + '\xcc' # 0x0098 -> LATIN CAPITAL LETTER I WITH GRAVE + '\xd5' # 0x0099 -> LATIN CAPITAL LETTER O WITH TILDE + '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xa2' # 0x009b -> CENT SIGN + '\xa3' # 0x009c -> POUND SIGN + '\xd9' # 0x009d -> LATIN CAPITAL LETTER U WITH GRAVE + '\u20a7' # 0x009e -> PESETA SIGN + '\xd3' # 0x009f -> LATIN CAPITAL LETTER O WITH ACUTE + '\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE + '\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE + '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE + '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE + '\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE + '\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE + '\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR + '\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR + '\xbf' # 0x00a8 -> INVERTED QUESTION MARK + '\xd2' # 0x00a9 -> LATIN CAPITAL LETTER O WITH GRAVE + '\xac' # 0x00aa -> NOT SIGN + '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF + '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER + '\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK + '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u2591' # 0x00b0 -> LIGHT SHADE + '\u2592' # 0x00b1 -> MEDIUM SHADE + '\u2593' # 0x00b2 -> DARK SHADE + '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL + '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT + '\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + '\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + '\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + '\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL + '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT + '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT + '\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + '\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT + '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT + '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL + '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT + '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL + '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + '\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + '\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT + '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL + '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + '\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + '\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + '\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + '\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + '\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + '\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + '\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + '\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + '\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + '\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT + '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT + '\u2588' # 0x00db -> FULL BLOCK + '\u2584' # 0x00dc -> LOWER HALF BLOCK + '\u258c' # 0x00dd -> LEFT HALF BLOCK + '\u2590' # 0x00de -> RIGHT HALF BLOCK + '\u2580' # 0x00df -> UPPER HALF BLOCK + '\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA + '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S + '\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA + '\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI + '\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA + '\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA + '\xb5' # 0x00e6 -> MICRO SIGN + '\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU + '\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI + '\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA + '\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA + '\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA + '\u221e' # 0x00ec -> INFINITY + '\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI + '\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON + '\u2229' # 0x00ef -> INTERSECTION + '\u2261' # 0x00f0 -> IDENTICAL TO + '\xb1' # 0x00f1 -> PLUS-MINUS SIGN + '\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO + '\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO + '\u2320' # 0x00f4 -> TOP HALF INTEGRAL + '\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL + '\xf7' # 0x00f6 -> DIVISION SIGN + '\u2248' # 0x00f7 -> ALMOST EQUAL TO + '\xb0' # 0x00f8 -> DEGREE SIGN + '\u2219' # 0x00f9 -> BULLET OPERATOR + '\xb7' # 0x00fa -> MIDDLE DOT + '\u221a' # 0x00fb -> SQUARE ROOT + '\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N + '\xb2' # 0x00fd -> SUPERSCRIPT TWO + '\u25a0' # 0x00fe -> BLACK SQUARE + '\xa0' # 0x00ff -> NO-BREAK SPACE +) + +### Encoding Map + +encoding_map = { + 0x0000: 0x0000, # NULL + 0x0001: 0x0001, # START OF HEADING + 0x0002: 0x0002, # START OF TEXT + 0x0003: 0x0003, # END OF TEXT + 0x0004: 0x0004, # END OF TRANSMISSION + 0x0005: 0x0005, # ENQUIRY + 0x0006: 0x0006, # ACKNOWLEDGE + 0x0007: 0x0007, # BELL + 0x0008: 0x0008, # BACKSPACE + 0x0009: 0x0009, # HORIZONTAL TABULATION + 0x000a: 0x000a, # LINE FEED + 0x000b: 0x000b, # VERTICAL TABULATION + 0x000c: 0x000c, # FORM FEED + 0x000d: 0x000d, # CARRIAGE RETURN + 0x000e: 0x000e, # SHIFT OUT + 0x000f: 0x000f, # SHIFT IN + 0x0010: 0x0010, # DATA LINK ESCAPE + 0x0011: 0x0011, # DEVICE CONTROL ONE + 0x0012: 0x0012, # DEVICE CONTROL TWO + 0x0013: 0x0013, # DEVICE CONTROL THREE + 0x0014: 0x0014, # DEVICE CONTROL FOUR + 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE + 0x0016: 0x0016, # SYNCHRONOUS IDLE + 0x0017: 0x0017, # END OF TRANSMISSION BLOCK + 0x0018: 0x0018, # CANCEL + 0x0019: 0x0019, # END OF MEDIUM + 0x001a: 0x001a, # SUBSTITUTE + 0x001b: 0x001b, # ESCAPE + 0x001c: 0x001c, # FILE SEPARATOR + 0x001d: 0x001d, # GROUP SEPARATOR + 0x001e: 0x001e, # RECORD SEPARATOR + 0x001f: 0x001f, # UNIT SEPARATOR + 0x0020: 0x0020, # SPACE + 0x0021: 0x0021, # EXCLAMATION MARK + 0x0022: 0x0022, # QUOTATION MARK + 0x0023: 0x0023, # NUMBER SIGN + 0x0024: 0x0024, # DOLLAR SIGN + 0x0025: 0x0025, # PERCENT SIGN + 0x0026: 0x0026, # AMPERSAND + 0x0027: 0x0027, # APOSTROPHE + 0x0028: 0x0028, # LEFT PARENTHESIS + 0x0029: 0x0029, # RIGHT PARENTHESIS + 0x002a: 0x002a, # ASTERISK + 0x002b: 0x002b, # PLUS SIGN + 0x002c: 0x002c, # COMMA + 0x002d: 0x002d, # HYPHEN-MINUS + 0x002e: 0x002e, # FULL STOP + 0x002f: 0x002f, # SOLIDUS + 0x0030: 0x0030, # DIGIT ZERO + 0x0031: 0x0031, # DIGIT ONE + 0x0032: 0x0032, # DIGIT TWO + 0x0033: 0x0033, # DIGIT THREE + 0x0034: 0x0034, # DIGIT FOUR + 0x0035: 0x0035, # DIGIT FIVE + 0x0036: 0x0036, # DIGIT SIX + 0x0037: 0x0037, # DIGIT SEVEN + 0x0038: 0x0038, # DIGIT EIGHT + 0x0039: 0x0039, # DIGIT NINE + 0x003a: 0x003a, # COLON + 0x003b: 0x003b, # SEMICOLON + 0x003c: 0x003c, # LESS-THAN SIGN + 0x003d: 0x003d, # EQUALS SIGN + 0x003e: 0x003e, # GREATER-THAN SIGN + 0x003f: 0x003f, # QUESTION MARK + 0x0040: 0x0040, # COMMERCIAL AT + 0x0041: 0x0041, # LATIN CAPITAL LETTER A + 0x0042: 0x0042, # LATIN CAPITAL LETTER B + 0x0043: 0x0043, # LATIN CAPITAL LETTER C + 0x0044: 0x0044, # LATIN CAPITAL LETTER D + 0x0045: 0x0045, # LATIN CAPITAL LETTER E + 0x0046: 0x0046, # LATIN CAPITAL LETTER F + 0x0047: 0x0047, # LATIN CAPITAL LETTER G + 0x0048: 0x0048, # LATIN CAPITAL LETTER H + 0x0049: 0x0049, # LATIN CAPITAL LETTER I + 0x004a: 0x004a, # LATIN CAPITAL LETTER J + 0x004b: 0x004b, # LATIN CAPITAL LETTER K + 0x004c: 0x004c, # LATIN CAPITAL LETTER L + 0x004d: 0x004d, # LATIN CAPITAL LETTER M + 0x004e: 0x004e, # LATIN CAPITAL LETTER N + 0x004f: 0x004f, # LATIN CAPITAL LETTER O + 0x0050: 0x0050, # LATIN CAPITAL LETTER P + 0x0051: 0x0051, # LATIN CAPITAL LETTER Q + 0x0052: 0x0052, # LATIN CAPITAL LETTER R + 0x0053: 0x0053, # LATIN CAPITAL LETTER S + 0x0054: 0x0054, # LATIN CAPITAL LETTER T + 0x0055: 0x0055, # LATIN CAPITAL LETTER U + 0x0056: 0x0056, # LATIN CAPITAL LETTER V + 0x0057: 0x0057, # LATIN CAPITAL LETTER W + 0x0058: 0x0058, # LATIN CAPITAL LETTER X + 0x0059: 0x0059, # LATIN CAPITAL LETTER Y + 0x005a: 0x005a, # LATIN CAPITAL LETTER Z + 0x005b: 0x005b, # LEFT SQUARE BRACKET + 0x005c: 0x005c, # REVERSE SOLIDUS + 0x005d: 0x005d, # RIGHT SQUARE BRACKET + 0x005e: 0x005e, # CIRCUMFLEX ACCENT + 0x005f: 0x005f, # LOW LINE + 0x0060: 0x0060, # GRAVE ACCENT + 0x0061: 0x0061, # LATIN SMALL LETTER A + 0x0062: 0x0062, # LATIN SMALL LETTER B + 0x0063: 0x0063, # LATIN SMALL LETTER C + 0x0064: 0x0064, # LATIN SMALL LETTER D + 0x0065: 0x0065, # LATIN SMALL LETTER E + 0x0066: 0x0066, # LATIN SMALL LETTER F + 0x0067: 0x0067, # LATIN SMALL LETTER G + 0x0068: 0x0068, # LATIN SMALL LETTER H + 0x0069: 0x0069, # LATIN SMALL LETTER I + 0x006a: 0x006a, # LATIN SMALL LETTER J + 0x006b: 0x006b, # LATIN SMALL LETTER K + 0x006c: 0x006c, # LATIN SMALL LETTER L + 0x006d: 0x006d, # LATIN SMALL LETTER M + 0x006e: 0x006e, # LATIN SMALL LETTER N + 0x006f: 0x006f, # LATIN SMALL LETTER O + 0x0070: 0x0070, # LATIN SMALL LETTER P + 0x0071: 0x0071, # LATIN SMALL LETTER Q + 0x0072: 0x0072, # LATIN SMALL LETTER R + 0x0073: 0x0073, # LATIN SMALL LETTER S + 0x0074: 0x0074, # LATIN SMALL LETTER T + 0x0075: 0x0075, # LATIN SMALL LETTER U + 0x0076: 0x0076, # LATIN SMALL LETTER V + 0x0077: 0x0077, # LATIN SMALL LETTER W + 0x0078: 0x0078, # LATIN SMALL LETTER X + 0x0079: 0x0079, # LATIN SMALL LETTER Y + 0x007a: 0x007a, # LATIN SMALL LETTER Z + 0x007b: 0x007b, # LEFT CURLY BRACKET + 0x007c: 0x007c, # VERTICAL LINE + 0x007d: 0x007d, # RIGHT CURLY BRACKET + 0x007e: 0x007e, # TILDE + 0x007f: 0x007f, # DELETE + 0x00a0: 0x00ff, # NO-BREAK SPACE + 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK + 0x00a2: 0x009b, # CENT SIGN + 0x00a3: 0x009c, # POUND SIGN + 0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR + 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00ac: 0x00aa, # NOT SIGN + 0x00b0: 0x00f8, # DEGREE SIGN + 0x00b1: 0x00f1, # PLUS-MINUS SIGN + 0x00b2: 0x00fd, # SUPERSCRIPT TWO + 0x00b5: 0x00e6, # MICRO SIGN + 0x00b7: 0x00fa, # MIDDLE DOT + 0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR + 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER + 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF + 0x00bf: 0x00a8, # INVERTED QUESTION MARK + 0x00c0: 0x0091, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00c1: 0x0086, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00c2: 0x008f, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00c3: 0x008e, # LATIN CAPITAL LETTER A WITH TILDE + 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00c8: 0x0092, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00ca: 0x0089, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00cc: 0x0098, # LATIN CAPITAL LETTER I WITH GRAVE + 0x00cd: 0x008b, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE + 0x00d2: 0x00a9, # LATIN CAPITAL LETTER O WITH GRAVE + 0x00d3: 0x009f, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00d4: 0x008c, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00d5: 0x0099, # LATIN CAPITAL LETTER O WITH TILDE + 0x00d9: 0x009d, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00da: 0x0096, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S + 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE + 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE + 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00e3: 0x0084, # LATIN SMALL LETTER A WITH TILDE + 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA + 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE + 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE + 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00ec: 0x008d, # LATIN SMALL LETTER I WITH GRAVE + 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE + 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE + 0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE + 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE + 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00f5: 0x0094, # LATIN SMALL LETTER O WITH TILDE + 0x00f7: 0x00f6, # DIVISION SIGN + 0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE + 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE + 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS + 0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA + 0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA + 0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA + 0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI + 0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA + 0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA + 0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA + 0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON + 0x03c0: 0x00e3, # GREEK SMALL LETTER PI + 0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA + 0x03c4: 0x00e7, # GREEK SMALL LETTER TAU + 0x03c6: 0x00ed, # GREEK SMALL LETTER PHI + 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N + 0x20a7: 0x009e, # PESETA SIGN + 0x2219: 0x00f9, # BULLET OPERATOR + 0x221a: 0x00fb, # SQUARE ROOT + 0x221e: 0x00ec, # INFINITY + 0x2229: 0x00ef, # INTERSECTION + 0x2248: 0x00f7, # ALMOST EQUAL TO + 0x2261: 0x00f0, # IDENTICAL TO + 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO + 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO + 0x2320: 0x00f4, # TOP HALF INTEGRAL + 0x2321: 0x00f5, # BOTTOM HALF INTEGRAL + 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL + 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL + 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT + 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL + 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x2580: 0x00df, # UPPER HALF BLOCK + 0x2584: 0x00dc, # LOWER HALF BLOCK + 0x2588: 0x00db, # FULL BLOCK + 0x258c: 0x00dd, # LEFT HALF BLOCK + 0x2590: 0x00de, # RIGHT HALF BLOCK + 0x2591: 0x00b0, # LIGHT SHADE + 0x2592: 0x00b1, # MEDIUM SHADE + 0x2593: 0x00b2, # DARK SHADE + 0x25a0: 0x00fe, # BLACK SQUARE +} diff --git a/contrib/tools/python3/src/Lib/encodings/cp861.py b/contrib/tools/python3/src/Lib/encodings/cp861.py new file mode 100644 index 0000000000..860a05fa3f --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp861.py @@ -0,0 +1,698 @@ +""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP861.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_map) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp861', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + +### Decoding Map + +decoding_map = codecs.make_identity_dict(range(256)) +decoding_map.update({ + 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS + 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE + 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE + 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE + 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA + 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS + 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE + 0x008b: 0x00d0, # LATIN CAPITAL LETTER ETH + 0x008c: 0x00f0, # LATIN SMALL LETTER ETH + 0x008d: 0x00de, # LATIN CAPITAL LETTER THORN + 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE + 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE + 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x0095: 0x00fe, # LATIN SMALL LETTER THORN + 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x0097: 0x00dd, # LATIN CAPITAL LETTER Y WITH ACUTE + 0x0098: 0x00fd, # LATIN SMALL LETTER Y WITH ACUTE + 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE + 0x009c: 0x00a3, # POUND SIGN + 0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE + 0x009e: 0x20a7, # PESETA SIGN + 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK + 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE + 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE + 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE + 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE + 0x00a4: 0x00c1, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00a5: 0x00cd, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00a6: 0x00d3, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00a7: 0x00da, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00a8: 0x00bf, # INVERTED QUESTION MARK + 0x00a9: 0x2310, # REVERSED NOT SIGN + 0x00aa: 0x00ac, # NOT SIGN + 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF + 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER + 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK + 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00b0: 0x2591, # LIGHT SHADE + 0x00b1: 0x2592, # MEDIUM SHADE + 0x00b2: 0x2593, # DARK SHADE + 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL + 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL + 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL + 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT + 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x00db: 0x2588, # FULL BLOCK + 0x00dc: 0x2584, # LOWER HALF BLOCK + 0x00dd: 0x258c, # LEFT HALF BLOCK + 0x00de: 0x2590, # RIGHT HALF BLOCK + 0x00df: 0x2580, # UPPER HALF BLOCK + 0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA + 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S + 0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA + 0x00e3: 0x03c0, # GREEK SMALL LETTER PI + 0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA + 0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA + 0x00e6: 0x00b5, # MICRO SIGN + 0x00e7: 0x03c4, # GREEK SMALL LETTER TAU + 0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI + 0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA + 0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA + 0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA + 0x00ec: 0x221e, # INFINITY + 0x00ed: 0x03c6, # GREEK SMALL LETTER PHI + 0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON + 0x00ef: 0x2229, # INTERSECTION + 0x00f0: 0x2261, # IDENTICAL TO + 0x00f1: 0x00b1, # PLUS-MINUS SIGN + 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO + 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO + 0x00f4: 0x2320, # TOP HALF INTEGRAL + 0x00f5: 0x2321, # BOTTOM HALF INTEGRAL + 0x00f6: 0x00f7, # DIVISION SIGN + 0x00f7: 0x2248, # ALMOST EQUAL TO + 0x00f8: 0x00b0, # DEGREE SIGN + 0x00f9: 0x2219, # BULLET OPERATOR + 0x00fa: 0x00b7, # MIDDLE DOT + 0x00fb: 0x221a, # SQUARE ROOT + 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N + 0x00fd: 0x00b2, # SUPERSCRIPT TWO + 0x00fe: 0x25a0, # BLACK SQUARE + 0x00ff: 0x00a0, # NO-BREAK SPACE +}) + +### Decoding Table + +decoding_table = ( + '\x00' # 0x0000 -> NULL + '\x01' # 0x0001 -> START OF HEADING + '\x02' # 0x0002 -> START OF TEXT + '\x03' # 0x0003 -> END OF TEXT + '\x04' # 0x0004 -> END OF TRANSMISSION + '\x05' # 0x0005 -> ENQUIRY + '\x06' # 0x0006 -> ACKNOWLEDGE + '\x07' # 0x0007 -> BELL + '\x08' # 0x0008 -> BACKSPACE + '\t' # 0x0009 -> HORIZONTAL TABULATION + '\n' # 0x000a -> LINE FEED + '\x0b' # 0x000b -> VERTICAL TABULATION + '\x0c' # 0x000c -> FORM FEED + '\r' # 0x000d -> CARRIAGE RETURN + '\x0e' # 0x000e -> SHIFT OUT + '\x0f' # 0x000f -> SHIFT IN + '\x10' # 0x0010 -> DATA LINK ESCAPE + '\x11' # 0x0011 -> DEVICE CONTROL ONE + '\x12' # 0x0012 -> DEVICE CONTROL TWO + '\x13' # 0x0013 -> DEVICE CONTROL THREE + '\x14' # 0x0014 -> DEVICE CONTROL FOUR + '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x0016 -> SYNCHRONOUS IDLE + '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK + '\x18' # 0x0018 -> CANCEL + '\x19' # 0x0019 -> END OF MEDIUM + '\x1a' # 0x001a -> SUBSTITUTE + '\x1b' # 0x001b -> ESCAPE + '\x1c' # 0x001c -> FILE SEPARATOR + '\x1d' # 0x001d -> GROUP SEPARATOR + '\x1e' # 0x001e -> RECORD SEPARATOR + '\x1f' # 0x001f -> UNIT SEPARATOR + ' ' # 0x0020 -> SPACE + '!' # 0x0021 -> EXCLAMATION MARK + '"' # 0x0022 -> QUOTATION MARK + '#' # 0x0023 -> NUMBER SIGN + '$' # 0x0024 -> DOLLAR SIGN + '%' # 0x0025 -> PERCENT SIGN + '&' # 0x0026 -> AMPERSAND + "'" # 0x0027 -> APOSTROPHE + '(' # 0x0028 -> LEFT PARENTHESIS + ')' # 0x0029 -> RIGHT PARENTHESIS + '*' # 0x002a -> ASTERISK + '+' # 0x002b -> PLUS SIGN + ',' # 0x002c -> COMMA + '-' # 0x002d -> HYPHEN-MINUS + '.' # 0x002e -> FULL STOP + '/' # 0x002f -> SOLIDUS + '0' # 0x0030 -> DIGIT ZERO + '1' # 0x0031 -> DIGIT ONE + '2' # 0x0032 -> DIGIT TWO + '3' # 0x0033 -> DIGIT THREE + '4' # 0x0034 -> DIGIT FOUR + '5' # 0x0035 -> DIGIT FIVE + '6' # 0x0036 -> DIGIT SIX + '7' # 0x0037 -> DIGIT SEVEN + '8' # 0x0038 -> DIGIT EIGHT + '9' # 0x0039 -> DIGIT NINE + ':' # 0x003a -> COLON + ';' # 0x003b -> SEMICOLON + '<' # 0x003c -> LESS-THAN SIGN + '=' # 0x003d -> EQUALS SIGN + '>' # 0x003e -> GREATER-THAN SIGN + '?' # 0x003f -> QUESTION MARK + '@' # 0x0040 -> COMMERCIAL AT + 'A' # 0x0041 -> LATIN CAPITAL LETTER A + 'B' # 0x0042 -> LATIN CAPITAL LETTER B + 'C' # 0x0043 -> LATIN CAPITAL LETTER C + 'D' # 0x0044 -> LATIN CAPITAL LETTER D + 'E' # 0x0045 -> LATIN CAPITAL LETTER E + 'F' # 0x0046 -> LATIN CAPITAL LETTER F + 'G' # 0x0047 -> LATIN CAPITAL LETTER G + 'H' # 0x0048 -> LATIN CAPITAL LETTER H + 'I' # 0x0049 -> LATIN CAPITAL LETTER I + 'J' # 0x004a -> LATIN CAPITAL LETTER J + 'K' # 0x004b -> LATIN CAPITAL LETTER K + 'L' # 0x004c -> LATIN CAPITAL LETTER L + 'M' # 0x004d -> LATIN CAPITAL LETTER M + 'N' # 0x004e -> LATIN CAPITAL LETTER N + 'O' # 0x004f -> LATIN CAPITAL LETTER O + 'P' # 0x0050 -> LATIN CAPITAL LETTER P + 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q + 'R' # 0x0052 -> LATIN CAPITAL LETTER R + 'S' # 0x0053 -> LATIN CAPITAL LETTER S + 'T' # 0x0054 -> LATIN CAPITAL LETTER T + 'U' # 0x0055 -> LATIN CAPITAL LETTER U + 'V' # 0x0056 -> LATIN CAPITAL LETTER V + 'W' # 0x0057 -> LATIN CAPITAL LETTER W + 'X' # 0x0058 -> LATIN CAPITAL LETTER X + 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y + 'Z' # 0x005a -> LATIN CAPITAL LETTER Z + '[' # 0x005b -> LEFT SQUARE BRACKET + '\\' # 0x005c -> REVERSE SOLIDUS + ']' # 0x005d -> RIGHT SQUARE BRACKET + '^' # 0x005e -> CIRCUMFLEX ACCENT + '_' # 0x005f -> LOW LINE + '`' # 0x0060 -> GRAVE ACCENT + 'a' # 0x0061 -> LATIN SMALL LETTER A + 'b' # 0x0062 -> LATIN SMALL LETTER B + 'c' # 0x0063 -> LATIN SMALL LETTER C + 'd' # 0x0064 -> LATIN SMALL LETTER D + 'e' # 0x0065 -> LATIN SMALL LETTER E + 'f' # 0x0066 -> LATIN SMALL LETTER F + 'g' # 0x0067 -> LATIN SMALL LETTER G + 'h' # 0x0068 -> LATIN SMALL LETTER H + 'i' # 0x0069 -> LATIN SMALL LETTER I + 'j' # 0x006a -> LATIN SMALL LETTER J + 'k' # 0x006b -> LATIN SMALL LETTER K + 'l' # 0x006c -> LATIN SMALL LETTER L + 'm' # 0x006d -> LATIN SMALL LETTER M + 'n' # 0x006e -> LATIN SMALL LETTER N + 'o' # 0x006f -> LATIN SMALL LETTER O + 'p' # 0x0070 -> LATIN SMALL LETTER P + 'q' # 0x0071 -> LATIN SMALL LETTER Q + 'r' # 0x0072 -> LATIN SMALL LETTER R + 's' # 0x0073 -> LATIN SMALL LETTER S + 't' # 0x0074 -> LATIN SMALL LETTER T + 'u' # 0x0075 -> LATIN SMALL LETTER U + 'v' # 0x0076 -> LATIN SMALL LETTER V + 'w' # 0x0077 -> LATIN SMALL LETTER W + 'x' # 0x0078 -> LATIN SMALL LETTER X + 'y' # 0x0079 -> LATIN SMALL LETTER Y + 'z' # 0x007a -> LATIN SMALL LETTER Z + '{' # 0x007b -> LEFT CURLY BRACKET + '|' # 0x007c -> VERTICAL LINE + '}' # 0x007d -> RIGHT CURLY BRACKET + '~' # 0x007e -> TILDE + '\x7f' # 0x007f -> DELETE + '\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS + '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE + '\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE + '\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA + '\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS + '\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE + '\xd0' # 0x008b -> LATIN CAPITAL LETTER ETH + '\xf0' # 0x008c -> LATIN SMALL LETTER ETH + '\xde' # 0x008d -> LATIN CAPITAL LETTER THORN + '\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE + '\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE + '\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS + '\xfe' # 0x0095 -> LATIN SMALL LETTER THORN + '\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xdd' # 0x0097 -> LATIN CAPITAL LETTER Y WITH ACUTE + '\xfd' # 0x0098 -> LATIN SMALL LETTER Y WITH ACUTE + '\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE + '\xa3' # 0x009c -> POUND SIGN + '\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE + '\u20a7' # 0x009e -> PESETA SIGN + '\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK + '\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE + '\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE + '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE + '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE + '\xc1' # 0x00a4 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xcd' # 0x00a5 -> LATIN CAPITAL LETTER I WITH ACUTE + '\xd3' # 0x00a6 -> LATIN CAPITAL LETTER O WITH ACUTE + '\xda' # 0x00a7 -> LATIN CAPITAL LETTER U WITH ACUTE + '\xbf' # 0x00a8 -> INVERTED QUESTION MARK + '\u2310' # 0x00a9 -> REVERSED NOT SIGN + '\xac' # 0x00aa -> NOT SIGN + '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF + '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER + '\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK + '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u2591' # 0x00b0 -> LIGHT SHADE + '\u2592' # 0x00b1 -> MEDIUM SHADE + '\u2593' # 0x00b2 -> DARK SHADE + '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL + '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT + '\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + '\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + '\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + '\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL + '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT + '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT + '\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + '\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT + '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT + '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL + '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT + '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL + '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + '\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + '\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT + '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL + '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + '\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + '\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + '\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + '\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + '\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + '\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + '\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + '\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + '\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + '\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT + '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT + '\u2588' # 0x00db -> FULL BLOCK + '\u2584' # 0x00dc -> LOWER HALF BLOCK + '\u258c' # 0x00dd -> LEFT HALF BLOCK + '\u2590' # 0x00de -> RIGHT HALF BLOCK + '\u2580' # 0x00df -> UPPER HALF BLOCK + '\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA + '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S + '\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA + '\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI + '\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA + '\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA + '\xb5' # 0x00e6 -> MICRO SIGN + '\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU + '\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI + '\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA + '\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA + '\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA + '\u221e' # 0x00ec -> INFINITY + '\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI + '\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON + '\u2229' # 0x00ef -> INTERSECTION + '\u2261' # 0x00f0 -> IDENTICAL TO + '\xb1' # 0x00f1 -> PLUS-MINUS SIGN + '\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO + '\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO + '\u2320' # 0x00f4 -> TOP HALF INTEGRAL + '\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL + '\xf7' # 0x00f6 -> DIVISION SIGN + '\u2248' # 0x00f7 -> ALMOST EQUAL TO + '\xb0' # 0x00f8 -> DEGREE SIGN + '\u2219' # 0x00f9 -> BULLET OPERATOR + '\xb7' # 0x00fa -> MIDDLE DOT + '\u221a' # 0x00fb -> SQUARE ROOT + '\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N + '\xb2' # 0x00fd -> SUPERSCRIPT TWO + '\u25a0' # 0x00fe -> BLACK SQUARE + '\xa0' # 0x00ff -> NO-BREAK SPACE +) + +### Encoding Map + +encoding_map = { + 0x0000: 0x0000, # NULL + 0x0001: 0x0001, # START OF HEADING + 0x0002: 0x0002, # START OF TEXT + 0x0003: 0x0003, # END OF TEXT + 0x0004: 0x0004, # END OF TRANSMISSION + 0x0005: 0x0005, # ENQUIRY + 0x0006: 0x0006, # ACKNOWLEDGE + 0x0007: 0x0007, # BELL + 0x0008: 0x0008, # BACKSPACE + 0x0009: 0x0009, # HORIZONTAL TABULATION + 0x000a: 0x000a, # LINE FEED + 0x000b: 0x000b, # VERTICAL TABULATION + 0x000c: 0x000c, # FORM FEED + 0x000d: 0x000d, # CARRIAGE RETURN + 0x000e: 0x000e, # SHIFT OUT + 0x000f: 0x000f, # SHIFT IN + 0x0010: 0x0010, # DATA LINK ESCAPE + 0x0011: 0x0011, # DEVICE CONTROL ONE + 0x0012: 0x0012, # DEVICE CONTROL TWO + 0x0013: 0x0013, # DEVICE CONTROL THREE + 0x0014: 0x0014, # DEVICE CONTROL FOUR + 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE + 0x0016: 0x0016, # SYNCHRONOUS IDLE + 0x0017: 0x0017, # END OF TRANSMISSION BLOCK + 0x0018: 0x0018, # CANCEL + 0x0019: 0x0019, # END OF MEDIUM + 0x001a: 0x001a, # SUBSTITUTE + 0x001b: 0x001b, # ESCAPE + 0x001c: 0x001c, # FILE SEPARATOR + 0x001d: 0x001d, # GROUP SEPARATOR + 0x001e: 0x001e, # RECORD SEPARATOR + 0x001f: 0x001f, # UNIT SEPARATOR + 0x0020: 0x0020, # SPACE + 0x0021: 0x0021, # EXCLAMATION MARK + 0x0022: 0x0022, # QUOTATION MARK + 0x0023: 0x0023, # NUMBER SIGN + 0x0024: 0x0024, # DOLLAR SIGN + 0x0025: 0x0025, # PERCENT SIGN + 0x0026: 0x0026, # AMPERSAND + 0x0027: 0x0027, # APOSTROPHE + 0x0028: 0x0028, # LEFT PARENTHESIS + 0x0029: 0x0029, # RIGHT PARENTHESIS + 0x002a: 0x002a, # ASTERISK + 0x002b: 0x002b, # PLUS SIGN + 0x002c: 0x002c, # COMMA + 0x002d: 0x002d, # HYPHEN-MINUS + 0x002e: 0x002e, # FULL STOP + 0x002f: 0x002f, # SOLIDUS + 0x0030: 0x0030, # DIGIT ZERO + 0x0031: 0x0031, # DIGIT ONE + 0x0032: 0x0032, # DIGIT TWO + 0x0033: 0x0033, # DIGIT THREE + 0x0034: 0x0034, # DIGIT FOUR + 0x0035: 0x0035, # DIGIT FIVE + 0x0036: 0x0036, # DIGIT SIX + 0x0037: 0x0037, # DIGIT SEVEN + 0x0038: 0x0038, # DIGIT EIGHT + 0x0039: 0x0039, # DIGIT NINE + 0x003a: 0x003a, # COLON + 0x003b: 0x003b, # SEMICOLON + 0x003c: 0x003c, # LESS-THAN SIGN + 0x003d: 0x003d, # EQUALS SIGN + 0x003e: 0x003e, # GREATER-THAN SIGN + 0x003f: 0x003f, # QUESTION MARK + 0x0040: 0x0040, # COMMERCIAL AT + 0x0041: 0x0041, # LATIN CAPITAL LETTER A + 0x0042: 0x0042, # LATIN CAPITAL LETTER B + 0x0043: 0x0043, # LATIN CAPITAL LETTER C + 0x0044: 0x0044, # LATIN CAPITAL LETTER D + 0x0045: 0x0045, # LATIN CAPITAL LETTER E + 0x0046: 0x0046, # LATIN CAPITAL LETTER F + 0x0047: 0x0047, # LATIN CAPITAL LETTER G + 0x0048: 0x0048, # LATIN CAPITAL LETTER H + 0x0049: 0x0049, # LATIN CAPITAL LETTER I + 0x004a: 0x004a, # LATIN CAPITAL LETTER J + 0x004b: 0x004b, # LATIN CAPITAL LETTER K + 0x004c: 0x004c, # LATIN CAPITAL LETTER L + 0x004d: 0x004d, # LATIN CAPITAL LETTER M + 0x004e: 0x004e, # LATIN CAPITAL LETTER N + 0x004f: 0x004f, # LATIN CAPITAL LETTER O + 0x0050: 0x0050, # LATIN CAPITAL LETTER P + 0x0051: 0x0051, # LATIN CAPITAL LETTER Q + 0x0052: 0x0052, # LATIN CAPITAL LETTER R + 0x0053: 0x0053, # LATIN CAPITAL LETTER S + 0x0054: 0x0054, # LATIN CAPITAL LETTER T + 0x0055: 0x0055, # LATIN CAPITAL LETTER U + 0x0056: 0x0056, # LATIN CAPITAL LETTER V + 0x0057: 0x0057, # LATIN CAPITAL LETTER W + 0x0058: 0x0058, # LATIN CAPITAL LETTER X + 0x0059: 0x0059, # LATIN CAPITAL LETTER Y + 0x005a: 0x005a, # LATIN CAPITAL LETTER Z + 0x005b: 0x005b, # LEFT SQUARE BRACKET + 0x005c: 0x005c, # REVERSE SOLIDUS + 0x005d: 0x005d, # RIGHT SQUARE BRACKET + 0x005e: 0x005e, # CIRCUMFLEX ACCENT + 0x005f: 0x005f, # LOW LINE + 0x0060: 0x0060, # GRAVE ACCENT + 0x0061: 0x0061, # LATIN SMALL LETTER A + 0x0062: 0x0062, # LATIN SMALL LETTER B + 0x0063: 0x0063, # LATIN SMALL LETTER C + 0x0064: 0x0064, # LATIN SMALL LETTER D + 0x0065: 0x0065, # LATIN SMALL LETTER E + 0x0066: 0x0066, # LATIN SMALL LETTER F + 0x0067: 0x0067, # LATIN SMALL LETTER G + 0x0068: 0x0068, # LATIN SMALL LETTER H + 0x0069: 0x0069, # LATIN SMALL LETTER I + 0x006a: 0x006a, # LATIN SMALL LETTER J + 0x006b: 0x006b, # LATIN SMALL LETTER K + 0x006c: 0x006c, # LATIN SMALL LETTER L + 0x006d: 0x006d, # LATIN SMALL LETTER M + 0x006e: 0x006e, # LATIN SMALL LETTER N + 0x006f: 0x006f, # LATIN SMALL LETTER O + 0x0070: 0x0070, # LATIN SMALL LETTER P + 0x0071: 0x0071, # LATIN SMALL LETTER Q + 0x0072: 0x0072, # LATIN SMALL LETTER R + 0x0073: 0x0073, # LATIN SMALL LETTER S + 0x0074: 0x0074, # LATIN SMALL LETTER T + 0x0075: 0x0075, # LATIN SMALL LETTER U + 0x0076: 0x0076, # LATIN SMALL LETTER V + 0x0077: 0x0077, # LATIN SMALL LETTER W + 0x0078: 0x0078, # LATIN SMALL LETTER X + 0x0079: 0x0079, # LATIN SMALL LETTER Y + 0x007a: 0x007a, # LATIN SMALL LETTER Z + 0x007b: 0x007b, # LEFT CURLY BRACKET + 0x007c: 0x007c, # VERTICAL LINE + 0x007d: 0x007d, # RIGHT CURLY BRACKET + 0x007e: 0x007e, # TILDE + 0x007f: 0x007f, # DELETE + 0x00a0: 0x00ff, # NO-BREAK SPACE + 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK + 0x00a3: 0x009c, # POUND SIGN + 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00ac: 0x00aa, # NOT SIGN + 0x00b0: 0x00f8, # DEGREE SIGN + 0x00b1: 0x00f1, # PLUS-MINUS SIGN + 0x00b2: 0x00fd, # SUPERSCRIPT TWO + 0x00b5: 0x00e6, # MICRO SIGN + 0x00b7: 0x00fa, # MIDDLE DOT + 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER + 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF + 0x00bf: 0x00a8, # INVERTED QUESTION MARK + 0x00c1: 0x00a4, # LATIN CAPITAL LETTER A WITH ACUTE + 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE + 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00cd: 0x00a5, # LATIN CAPITAL LETTER I WITH ACUTE + 0x00d0: 0x008b, # LATIN CAPITAL LETTER ETH + 0x00d3: 0x00a6, # LATIN CAPITAL LETTER O WITH ACUTE + 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE + 0x00da: 0x00a7, # LATIN CAPITAL LETTER U WITH ACUTE + 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00dd: 0x0097, # LATIN CAPITAL LETTER Y WITH ACUTE + 0x00de: 0x008d, # LATIN CAPITAL LETTER THORN + 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S + 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE + 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE + 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE + 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA + 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE + 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE + 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE + 0x00f0: 0x008c, # LATIN SMALL LETTER ETH + 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE + 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00f7: 0x00f6, # DIVISION SIGN + 0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE + 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE + 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00fd: 0x0098, # LATIN SMALL LETTER Y WITH ACUTE + 0x00fe: 0x0095, # LATIN SMALL LETTER THORN + 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK + 0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA + 0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA + 0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA + 0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI + 0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA + 0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA + 0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA + 0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON + 0x03c0: 0x00e3, # GREEK SMALL LETTER PI + 0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA + 0x03c4: 0x00e7, # GREEK SMALL LETTER TAU + 0x03c6: 0x00ed, # GREEK SMALL LETTER PHI + 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N + 0x20a7: 0x009e, # PESETA SIGN + 0x2219: 0x00f9, # BULLET OPERATOR + 0x221a: 0x00fb, # SQUARE ROOT + 0x221e: 0x00ec, # INFINITY + 0x2229: 0x00ef, # INTERSECTION + 0x2248: 0x00f7, # ALMOST EQUAL TO + 0x2261: 0x00f0, # IDENTICAL TO + 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO + 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO + 0x2310: 0x00a9, # REVERSED NOT SIGN + 0x2320: 0x00f4, # TOP HALF INTEGRAL + 0x2321: 0x00f5, # BOTTOM HALF INTEGRAL + 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL + 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL + 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT + 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL + 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x2580: 0x00df, # UPPER HALF BLOCK + 0x2584: 0x00dc, # LOWER HALF BLOCK + 0x2588: 0x00db, # FULL BLOCK + 0x258c: 0x00dd, # LEFT HALF BLOCK + 0x2590: 0x00de, # RIGHT HALF BLOCK + 0x2591: 0x00b0, # LIGHT SHADE + 0x2592: 0x00b1, # MEDIUM SHADE + 0x2593: 0x00b2, # DARK SHADE + 0x25a0: 0x00fe, # BLACK SQUARE +} diff --git a/contrib/tools/python3/src/Lib/encodings/cp862.py b/contrib/tools/python3/src/Lib/encodings/cp862.py new file mode 100644 index 0000000000..3df22f997b --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp862.py @@ -0,0 +1,698 @@ +""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP862.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_map) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp862', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + +### Decoding Map + +decoding_map = codecs.make_identity_dict(range(256)) +decoding_map.update({ + 0x0080: 0x05d0, # HEBREW LETTER ALEF + 0x0081: 0x05d1, # HEBREW LETTER BET + 0x0082: 0x05d2, # HEBREW LETTER GIMEL + 0x0083: 0x05d3, # HEBREW LETTER DALET + 0x0084: 0x05d4, # HEBREW LETTER HE + 0x0085: 0x05d5, # HEBREW LETTER VAV + 0x0086: 0x05d6, # HEBREW LETTER ZAYIN + 0x0087: 0x05d7, # HEBREW LETTER HET + 0x0088: 0x05d8, # HEBREW LETTER TET + 0x0089: 0x05d9, # HEBREW LETTER YOD + 0x008a: 0x05da, # HEBREW LETTER FINAL KAF + 0x008b: 0x05db, # HEBREW LETTER KAF + 0x008c: 0x05dc, # HEBREW LETTER LAMED + 0x008d: 0x05dd, # HEBREW LETTER FINAL MEM + 0x008e: 0x05de, # HEBREW LETTER MEM + 0x008f: 0x05df, # HEBREW LETTER FINAL NUN + 0x0090: 0x05e0, # HEBREW LETTER NUN + 0x0091: 0x05e1, # HEBREW LETTER SAMEKH + 0x0092: 0x05e2, # HEBREW LETTER AYIN + 0x0093: 0x05e3, # HEBREW LETTER FINAL PE + 0x0094: 0x05e4, # HEBREW LETTER PE + 0x0095: 0x05e5, # HEBREW LETTER FINAL TSADI + 0x0096: 0x05e6, # HEBREW LETTER TSADI + 0x0097: 0x05e7, # HEBREW LETTER QOF + 0x0098: 0x05e8, # HEBREW LETTER RESH + 0x0099: 0x05e9, # HEBREW LETTER SHIN + 0x009a: 0x05ea, # HEBREW LETTER TAV + 0x009b: 0x00a2, # CENT SIGN + 0x009c: 0x00a3, # POUND SIGN + 0x009d: 0x00a5, # YEN SIGN + 0x009e: 0x20a7, # PESETA SIGN + 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK + 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE + 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE + 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE + 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE + 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE + 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE + 0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR + 0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR + 0x00a8: 0x00bf, # INVERTED QUESTION MARK + 0x00a9: 0x2310, # REVERSED NOT SIGN + 0x00aa: 0x00ac, # NOT SIGN + 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF + 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER + 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK + 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00b0: 0x2591, # LIGHT SHADE + 0x00b1: 0x2592, # MEDIUM SHADE + 0x00b2: 0x2593, # DARK SHADE + 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL + 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL + 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL + 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT + 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x00db: 0x2588, # FULL BLOCK + 0x00dc: 0x2584, # LOWER HALF BLOCK + 0x00dd: 0x258c, # LEFT HALF BLOCK + 0x00de: 0x2590, # RIGHT HALF BLOCK + 0x00df: 0x2580, # UPPER HALF BLOCK + 0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA + 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S (GERMAN) + 0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA + 0x00e3: 0x03c0, # GREEK SMALL LETTER PI + 0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA + 0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA + 0x00e6: 0x00b5, # MICRO SIGN + 0x00e7: 0x03c4, # GREEK SMALL LETTER TAU + 0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI + 0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA + 0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA + 0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA + 0x00ec: 0x221e, # INFINITY + 0x00ed: 0x03c6, # GREEK SMALL LETTER PHI + 0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON + 0x00ef: 0x2229, # INTERSECTION + 0x00f0: 0x2261, # IDENTICAL TO + 0x00f1: 0x00b1, # PLUS-MINUS SIGN + 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO + 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO + 0x00f4: 0x2320, # TOP HALF INTEGRAL + 0x00f5: 0x2321, # BOTTOM HALF INTEGRAL + 0x00f6: 0x00f7, # DIVISION SIGN + 0x00f7: 0x2248, # ALMOST EQUAL TO + 0x00f8: 0x00b0, # DEGREE SIGN + 0x00f9: 0x2219, # BULLET OPERATOR + 0x00fa: 0x00b7, # MIDDLE DOT + 0x00fb: 0x221a, # SQUARE ROOT + 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N + 0x00fd: 0x00b2, # SUPERSCRIPT TWO + 0x00fe: 0x25a0, # BLACK SQUARE + 0x00ff: 0x00a0, # NO-BREAK SPACE +}) + +### Decoding Table + +decoding_table = ( + '\x00' # 0x0000 -> NULL + '\x01' # 0x0001 -> START OF HEADING + '\x02' # 0x0002 -> START OF TEXT + '\x03' # 0x0003 -> END OF TEXT + '\x04' # 0x0004 -> END OF TRANSMISSION + '\x05' # 0x0005 -> ENQUIRY + '\x06' # 0x0006 -> ACKNOWLEDGE + '\x07' # 0x0007 -> BELL + '\x08' # 0x0008 -> BACKSPACE + '\t' # 0x0009 -> HORIZONTAL TABULATION + '\n' # 0x000a -> LINE FEED + '\x0b' # 0x000b -> VERTICAL TABULATION + '\x0c' # 0x000c -> FORM FEED + '\r' # 0x000d -> CARRIAGE RETURN + '\x0e' # 0x000e -> SHIFT OUT + '\x0f' # 0x000f -> SHIFT IN + '\x10' # 0x0010 -> DATA LINK ESCAPE + '\x11' # 0x0011 -> DEVICE CONTROL ONE + '\x12' # 0x0012 -> DEVICE CONTROL TWO + '\x13' # 0x0013 -> DEVICE CONTROL THREE + '\x14' # 0x0014 -> DEVICE CONTROL FOUR + '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x0016 -> SYNCHRONOUS IDLE + '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK + '\x18' # 0x0018 -> CANCEL + '\x19' # 0x0019 -> END OF MEDIUM + '\x1a' # 0x001a -> SUBSTITUTE + '\x1b' # 0x001b -> ESCAPE + '\x1c' # 0x001c -> FILE SEPARATOR + '\x1d' # 0x001d -> GROUP SEPARATOR + '\x1e' # 0x001e -> RECORD SEPARATOR + '\x1f' # 0x001f -> UNIT SEPARATOR + ' ' # 0x0020 -> SPACE + '!' # 0x0021 -> EXCLAMATION MARK + '"' # 0x0022 -> QUOTATION MARK + '#' # 0x0023 -> NUMBER SIGN + '$' # 0x0024 -> DOLLAR SIGN + '%' # 0x0025 -> PERCENT SIGN + '&' # 0x0026 -> AMPERSAND + "'" # 0x0027 -> APOSTROPHE + '(' # 0x0028 -> LEFT PARENTHESIS + ')' # 0x0029 -> RIGHT PARENTHESIS + '*' # 0x002a -> ASTERISK + '+' # 0x002b -> PLUS SIGN + ',' # 0x002c -> COMMA + '-' # 0x002d -> HYPHEN-MINUS + '.' # 0x002e -> FULL STOP + '/' # 0x002f -> SOLIDUS + '0' # 0x0030 -> DIGIT ZERO + '1' # 0x0031 -> DIGIT ONE + '2' # 0x0032 -> DIGIT TWO + '3' # 0x0033 -> DIGIT THREE + '4' # 0x0034 -> DIGIT FOUR + '5' # 0x0035 -> DIGIT FIVE + '6' # 0x0036 -> DIGIT SIX + '7' # 0x0037 -> DIGIT SEVEN + '8' # 0x0038 -> DIGIT EIGHT + '9' # 0x0039 -> DIGIT NINE + ':' # 0x003a -> COLON + ';' # 0x003b -> SEMICOLON + '<' # 0x003c -> LESS-THAN SIGN + '=' # 0x003d -> EQUALS SIGN + '>' # 0x003e -> GREATER-THAN SIGN + '?' # 0x003f -> QUESTION MARK + '@' # 0x0040 -> COMMERCIAL AT + 'A' # 0x0041 -> LATIN CAPITAL LETTER A + 'B' # 0x0042 -> LATIN CAPITAL LETTER B + 'C' # 0x0043 -> LATIN CAPITAL LETTER C + 'D' # 0x0044 -> LATIN CAPITAL LETTER D + 'E' # 0x0045 -> LATIN CAPITAL LETTER E + 'F' # 0x0046 -> LATIN CAPITAL LETTER F + 'G' # 0x0047 -> LATIN CAPITAL LETTER G + 'H' # 0x0048 -> LATIN CAPITAL LETTER H + 'I' # 0x0049 -> LATIN CAPITAL LETTER I + 'J' # 0x004a -> LATIN CAPITAL LETTER J + 'K' # 0x004b -> LATIN CAPITAL LETTER K + 'L' # 0x004c -> LATIN CAPITAL LETTER L + 'M' # 0x004d -> LATIN CAPITAL LETTER M + 'N' # 0x004e -> LATIN CAPITAL LETTER N + 'O' # 0x004f -> LATIN CAPITAL LETTER O + 'P' # 0x0050 -> LATIN CAPITAL LETTER P + 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q + 'R' # 0x0052 -> LATIN CAPITAL LETTER R + 'S' # 0x0053 -> LATIN CAPITAL LETTER S + 'T' # 0x0054 -> LATIN CAPITAL LETTER T + 'U' # 0x0055 -> LATIN CAPITAL LETTER U + 'V' # 0x0056 -> LATIN CAPITAL LETTER V + 'W' # 0x0057 -> LATIN CAPITAL LETTER W + 'X' # 0x0058 -> LATIN CAPITAL LETTER X + 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y + 'Z' # 0x005a -> LATIN CAPITAL LETTER Z + '[' # 0x005b -> LEFT SQUARE BRACKET + '\\' # 0x005c -> REVERSE SOLIDUS + ']' # 0x005d -> RIGHT SQUARE BRACKET + '^' # 0x005e -> CIRCUMFLEX ACCENT + '_' # 0x005f -> LOW LINE + '`' # 0x0060 -> GRAVE ACCENT + 'a' # 0x0061 -> LATIN SMALL LETTER A + 'b' # 0x0062 -> LATIN SMALL LETTER B + 'c' # 0x0063 -> LATIN SMALL LETTER C + 'd' # 0x0064 -> LATIN SMALL LETTER D + 'e' # 0x0065 -> LATIN SMALL LETTER E + 'f' # 0x0066 -> LATIN SMALL LETTER F + 'g' # 0x0067 -> LATIN SMALL LETTER G + 'h' # 0x0068 -> LATIN SMALL LETTER H + 'i' # 0x0069 -> LATIN SMALL LETTER I + 'j' # 0x006a -> LATIN SMALL LETTER J + 'k' # 0x006b -> LATIN SMALL LETTER K + 'l' # 0x006c -> LATIN SMALL LETTER L + 'm' # 0x006d -> LATIN SMALL LETTER M + 'n' # 0x006e -> LATIN SMALL LETTER N + 'o' # 0x006f -> LATIN SMALL LETTER O + 'p' # 0x0070 -> LATIN SMALL LETTER P + 'q' # 0x0071 -> LATIN SMALL LETTER Q + 'r' # 0x0072 -> LATIN SMALL LETTER R + 's' # 0x0073 -> LATIN SMALL LETTER S + 't' # 0x0074 -> LATIN SMALL LETTER T + 'u' # 0x0075 -> LATIN SMALL LETTER U + 'v' # 0x0076 -> LATIN SMALL LETTER V + 'w' # 0x0077 -> LATIN SMALL LETTER W + 'x' # 0x0078 -> LATIN SMALL LETTER X + 'y' # 0x0079 -> LATIN SMALL LETTER Y + 'z' # 0x007a -> LATIN SMALL LETTER Z + '{' # 0x007b -> LEFT CURLY BRACKET + '|' # 0x007c -> VERTICAL LINE + '}' # 0x007d -> RIGHT CURLY BRACKET + '~' # 0x007e -> TILDE + '\x7f' # 0x007f -> DELETE + '\u05d0' # 0x0080 -> HEBREW LETTER ALEF + '\u05d1' # 0x0081 -> HEBREW LETTER BET + '\u05d2' # 0x0082 -> HEBREW LETTER GIMEL + '\u05d3' # 0x0083 -> HEBREW LETTER DALET + '\u05d4' # 0x0084 -> HEBREW LETTER HE + '\u05d5' # 0x0085 -> HEBREW LETTER VAV + '\u05d6' # 0x0086 -> HEBREW LETTER ZAYIN + '\u05d7' # 0x0087 -> HEBREW LETTER HET + '\u05d8' # 0x0088 -> HEBREW LETTER TET + '\u05d9' # 0x0089 -> HEBREW LETTER YOD + '\u05da' # 0x008a -> HEBREW LETTER FINAL KAF + '\u05db' # 0x008b -> HEBREW LETTER KAF + '\u05dc' # 0x008c -> HEBREW LETTER LAMED + '\u05dd' # 0x008d -> HEBREW LETTER FINAL MEM + '\u05de' # 0x008e -> HEBREW LETTER MEM + '\u05df' # 0x008f -> HEBREW LETTER FINAL NUN + '\u05e0' # 0x0090 -> HEBREW LETTER NUN + '\u05e1' # 0x0091 -> HEBREW LETTER SAMEKH + '\u05e2' # 0x0092 -> HEBREW LETTER AYIN + '\u05e3' # 0x0093 -> HEBREW LETTER FINAL PE + '\u05e4' # 0x0094 -> HEBREW LETTER PE + '\u05e5' # 0x0095 -> HEBREW LETTER FINAL TSADI + '\u05e6' # 0x0096 -> HEBREW LETTER TSADI + '\u05e7' # 0x0097 -> HEBREW LETTER QOF + '\u05e8' # 0x0098 -> HEBREW LETTER RESH + '\u05e9' # 0x0099 -> HEBREW LETTER SHIN + '\u05ea' # 0x009a -> HEBREW LETTER TAV + '\xa2' # 0x009b -> CENT SIGN + '\xa3' # 0x009c -> POUND SIGN + '\xa5' # 0x009d -> YEN SIGN + '\u20a7' # 0x009e -> PESETA SIGN + '\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK + '\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE + '\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE + '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE + '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE + '\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE + '\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE + '\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR + '\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR + '\xbf' # 0x00a8 -> INVERTED QUESTION MARK + '\u2310' # 0x00a9 -> REVERSED NOT SIGN + '\xac' # 0x00aa -> NOT SIGN + '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF + '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER + '\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK + '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u2591' # 0x00b0 -> LIGHT SHADE + '\u2592' # 0x00b1 -> MEDIUM SHADE + '\u2593' # 0x00b2 -> DARK SHADE + '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL + '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT + '\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + '\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + '\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + '\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL + '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT + '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT + '\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + '\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT + '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT + '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL + '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT + '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL + '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + '\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + '\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT + '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL + '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + '\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + '\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + '\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + '\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + '\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + '\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + '\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + '\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + '\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + '\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT + '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT + '\u2588' # 0x00db -> FULL BLOCK + '\u2584' # 0x00dc -> LOWER HALF BLOCK + '\u258c' # 0x00dd -> LEFT HALF BLOCK + '\u2590' # 0x00de -> RIGHT HALF BLOCK + '\u2580' # 0x00df -> UPPER HALF BLOCK + '\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA + '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S (GERMAN) + '\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA + '\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI + '\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA + '\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA + '\xb5' # 0x00e6 -> MICRO SIGN + '\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU + '\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI + '\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA + '\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA + '\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA + '\u221e' # 0x00ec -> INFINITY + '\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI + '\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON + '\u2229' # 0x00ef -> INTERSECTION + '\u2261' # 0x00f0 -> IDENTICAL TO + '\xb1' # 0x00f1 -> PLUS-MINUS SIGN + '\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO + '\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO + '\u2320' # 0x00f4 -> TOP HALF INTEGRAL + '\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL + '\xf7' # 0x00f6 -> DIVISION SIGN + '\u2248' # 0x00f7 -> ALMOST EQUAL TO + '\xb0' # 0x00f8 -> DEGREE SIGN + '\u2219' # 0x00f9 -> BULLET OPERATOR + '\xb7' # 0x00fa -> MIDDLE DOT + '\u221a' # 0x00fb -> SQUARE ROOT + '\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N + '\xb2' # 0x00fd -> SUPERSCRIPT TWO + '\u25a0' # 0x00fe -> BLACK SQUARE + '\xa0' # 0x00ff -> NO-BREAK SPACE +) + +### Encoding Map + +encoding_map = { + 0x0000: 0x0000, # NULL + 0x0001: 0x0001, # START OF HEADING + 0x0002: 0x0002, # START OF TEXT + 0x0003: 0x0003, # END OF TEXT + 0x0004: 0x0004, # END OF TRANSMISSION + 0x0005: 0x0005, # ENQUIRY + 0x0006: 0x0006, # ACKNOWLEDGE + 0x0007: 0x0007, # BELL + 0x0008: 0x0008, # BACKSPACE + 0x0009: 0x0009, # HORIZONTAL TABULATION + 0x000a: 0x000a, # LINE FEED + 0x000b: 0x000b, # VERTICAL TABULATION + 0x000c: 0x000c, # FORM FEED + 0x000d: 0x000d, # CARRIAGE RETURN + 0x000e: 0x000e, # SHIFT OUT + 0x000f: 0x000f, # SHIFT IN + 0x0010: 0x0010, # DATA LINK ESCAPE + 0x0011: 0x0011, # DEVICE CONTROL ONE + 0x0012: 0x0012, # DEVICE CONTROL TWO + 0x0013: 0x0013, # DEVICE CONTROL THREE + 0x0014: 0x0014, # DEVICE CONTROL FOUR + 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE + 0x0016: 0x0016, # SYNCHRONOUS IDLE + 0x0017: 0x0017, # END OF TRANSMISSION BLOCK + 0x0018: 0x0018, # CANCEL + 0x0019: 0x0019, # END OF MEDIUM + 0x001a: 0x001a, # SUBSTITUTE + 0x001b: 0x001b, # ESCAPE + 0x001c: 0x001c, # FILE SEPARATOR + 0x001d: 0x001d, # GROUP SEPARATOR + 0x001e: 0x001e, # RECORD SEPARATOR + 0x001f: 0x001f, # UNIT SEPARATOR + 0x0020: 0x0020, # SPACE + 0x0021: 0x0021, # EXCLAMATION MARK + 0x0022: 0x0022, # QUOTATION MARK + 0x0023: 0x0023, # NUMBER SIGN + 0x0024: 0x0024, # DOLLAR SIGN + 0x0025: 0x0025, # PERCENT SIGN + 0x0026: 0x0026, # AMPERSAND + 0x0027: 0x0027, # APOSTROPHE + 0x0028: 0x0028, # LEFT PARENTHESIS + 0x0029: 0x0029, # RIGHT PARENTHESIS + 0x002a: 0x002a, # ASTERISK + 0x002b: 0x002b, # PLUS SIGN + 0x002c: 0x002c, # COMMA + 0x002d: 0x002d, # HYPHEN-MINUS + 0x002e: 0x002e, # FULL STOP + 0x002f: 0x002f, # SOLIDUS + 0x0030: 0x0030, # DIGIT ZERO + 0x0031: 0x0031, # DIGIT ONE + 0x0032: 0x0032, # DIGIT TWO + 0x0033: 0x0033, # DIGIT THREE + 0x0034: 0x0034, # DIGIT FOUR + 0x0035: 0x0035, # DIGIT FIVE + 0x0036: 0x0036, # DIGIT SIX + 0x0037: 0x0037, # DIGIT SEVEN + 0x0038: 0x0038, # DIGIT EIGHT + 0x0039: 0x0039, # DIGIT NINE + 0x003a: 0x003a, # COLON + 0x003b: 0x003b, # SEMICOLON + 0x003c: 0x003c, # LESS-THAN SIGN + 0x003d: 0x003d, # EQUALS SIGN + 0x003e: 0x003e, # GREATER-THAN SIGN + 0x003f: 0x003f, # QUESTION MARK + 0x0040: 0x0040, # COMMERCIAL AT + 0x0041: 0x0041, # LATIN CAPITAL LETTER A + 0x0042: 0x0042, # LATIN CAPITAL LETTER B + 0x0043: 0x0043, # LATIN CAPITAL LETTER C + 0x0044: 0x0044, # LATIN CAPITAL LETTER D + 0x0045: 0x0045, # LATIN CAPITAL LETTER E + 0x0046: 0x0046, # LATIN CAPITAL LETTER F + 0x0047: 0x0047, # LATIN CAPITAL LETTER G + 0x0048: 0x0048, # LATIN CAPITAL LETTER H + 0x0049: 0x0049, # LATIN CAPITAL LETTER I + 0x004a: 0x004a, # LATIN CAPITAL LETTER J + 0x004b: 0x004b, # LATIN CAPITAL LETTER K + 0x004c: 0x004c, # LATIN CAPITAL LETTER L + 0x004d: 0x004d, # LATIN CAPITAL LETTER M + 0x004e: 0x004e, # LATIN CAPITAL LETTER N + 0x004f: 0x004f, # LATIN CAPITAL LETTER O + 0x0050: 0x0050, # LATIN CAPITAL LETTER P + 0x0051: 0x0051, # LATIN CAPITAL LETTER Q + 0x0052: 0x0052, # LATIN CAPITAL LETTER R + 0x0053: 0x0053, # LATIN CAPITAL LETTER S + 0x0054: 0x0054, # LATIN CAPITAL LETTER T + 0x0055: 0x0055, # LATIN CAPITAL LETTER U + 0x0056: 0x0056, # LATIN CAPITAL LETTER V + 0x0057: 0x0057, # LATIN CAPITAL LETTER W + 0x0058: 0x0058, # LATIN CAPITAL LETTER X + 0x0059: 0x0059, # LATIN CAPITAL LETTER Y + 0x005a: 0x005a, # LATIN CAPITAL LETTER Z + 0x005b: 0x005b, # LEFT SQUARE BRACKET + 0x005c: 0x005c, # REVERSE SOLIDUS + 0x005d: 0x005d, # RIGHT SQUARE BRACKET + 0x005e: 0x005e, # CIRCUMFLEX ACCENT + 0x005f: 0x005f, # LOW LINE + 0x0060: 0x0060, # GRAVE ACCENT + 0x0061: 0x0061, # LATIN SMALL LETTER A + 0x0062: 0x0062, # LATIN SMALL LETTER B + 0x0063: 0x0063, # LATIN SMALL LETTER C + 0x0064: 0x0064, # LATIN SMALL LETTER D + 0x0065: 0x0065, # LATIN SMALL LETTER E + 0x0066: 0x0066, # LATIN SMALL LETTER F + 0x0067: 0x0067, # LATIN SMALL LETTER G + 0x0068: 0x0068, # LATIN SMALL LETTER H + 0x0069: 0x0069, # LATIN SMALL LETTER I + 0x006a: 0x006a, # LATIN SMALL LETTER J + 0x006b: 0x006b, # LATIN SMALL LETTER K + 0x006c: 0x006c, # LATIN SMALL LETTER L + 0x006d: 0x006d, # LATIN SMALL LETTER M + 0x006e: 0x006e, # LATIN SMALL LETTER N + 0x006f: 0x006f, # LATIN SMALL LETTER O + 0x0070: 0x0070, # LATIN SMALL LETTER P + 0x0071: 0x0071, # LATIN SMALL LETTER Q + 0x0072: 0x0072, # LATIN SMALL LETTER R + 0x0073: 0x0073, # LATIN SMALL LETTER S + 0x0074: 0x0074, # LATIN SMALL LETTER T + 0x0075: 0x0075, # LATIN SMALL LETTER U + 0x0076: 0x0076, # LATIN SMALL LETTER V + 0x0077: 0x0077, # LATIN SMALL LETTER W + 0x0078: 0x0078, # LATIN SMALL LETTER X + 0x0079: 0x0079, # LATIN SMALL LETTER Y + 0x007a: 0x007a, # LATIN SMALL LETTER Z + 0x007b: 0x007b, # LEFT CURLY BRACKET + 0x007c: 0x007c, # VERTICAL LINE + 0x007d: 0x007d, # RIGHT CURLY BRACKET + 0x007e: 0x007e, # TILDE + 0x007f: 0x007f, # DELETE + 0x00a0: 0x00ff, # NO-BREAK SPACE + 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK + 0x00a2: 0x009b, # CENT SIGN + 0x00a3: 0x009c, # POUND SIGN + 0x00a5: 0x009d, # YEN SIGN + 0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR + 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00ac: 0x00aa, # NOT SIGN + 0x00b0: 0x00f8, # DEGREE SIGN + 0x00b1: 0x00f1, # PLUS-MINUS SIGN + 0x00b2: 0x00fd, # SUPERSCRIPT TWO + 0x00b5: 0x00e6, # MICRO SIGN + 0x00b7: 0x00fa, # MIDDLE DOT + 0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR + 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER + 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF + 0x00bf: 0x00a8, # INVERTED QUESTION MARK + 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE + 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S (GERMAN) + 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE + 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE + 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE + 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE + 0x00f7: 0x00f6, # DIVISION SIGN + 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE + 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK + 0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA + 0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA + 0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA + 0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI + 0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA + 0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA + 0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA + 0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON + 0x03c0: 0x00e3, # GREEK SMALL LETTER PI + 0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA + 0x03c4: 0x00e7, # GREEK SMALL LETTER TAU + 0x03c6: 0x00ed, # GREEK SMALL LETTER PHI + 0x05d0: 0x0080, # HEBREW LETTER ALEF + 0x05d1: 0x0081, # HEBREW LETTER BET + 0x05d2: 0x0082, # HEBREW LETTER GIMEL + 0x05d3: 0x0083, # HEBREW LETTER DALET + 0x05d4: 0x0084, # HEBREW LETTER HE + 0x05d5: 0x0085, # HEBREW LETTER VAV + 0x05d6: 0x0086, # HEBREW LETTER ZAYIN + 0x05d7: 0x0087, # HEBREW LETTER HET + 0x05d8: 0x0088, # HEBREW LETTER TET + 0x05d9: 0x0089, # HEBREW LETTER YOD + 0x05da: 0x008a, # HEBREW LETTER FINAL KAF + 0x05db: 0x008b, # HEBREW LETTER KAF + 0x05dc: 0x008c, # HEBREW LETTER LAMED + 0x05dd: 0x008d, # HEBREW LETTER FINAL MEM + 0x05de: 0x008e, # HEBREW LETTER MEM + 0x05df: 0x008f, # HEBREW LETTER FINAL NUN + 0x05e0: 0x0090, # HEBREW LETTER NUN + 0x05e1: 0x0091, # HEBREW LETTER SAMEKH + 0x05e2: 0x0092, # HEBREW LETTER AYIN + 0x05e3: 0x0093, # HEBREW LETTER FINAL PE + 0x05e4: 0x0094, # HEBREW LETTER PE + 0x05e5: 0x0095, # HEBREW LETTER FINAL TSADI + 0x05e6: 0x0096, # HEBREW LETTER TSADI + 0x05e7: 0x0097, # HEBREW LETTER QOF + 0x05e8: 0x0098, # HEBREW LETTER RESH + 0x05e9: 0x0099, # HEBREW LETTER SHIN + 0x05ea: 0x009a, # HEBREW LETTER TAV + 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N + 0x20a7: 0x009e, # PESETA SIGN + 0x2219: 0x00f9, # BULLET OPERATOR + 0x221a: 0x00fb, # SQUARE ROOT + 0x221e: 0x00ec, # INFINITY + 0x2229: 0x00ef, # INTERSECTION + 0x2248: 0x00f7, # ALMOST EQUAL TO + 0x2261: 0x00f0, # IDENTICAL TO + 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO + 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO + 0x2310: 0x00a9, # REVERSED NOT SIGN + 0x2320: 0x00f4, # TOP HALF INTEGRAL + 0x2321: 0x00f5, # BOTTOM HALF INTEGRAL + 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL + 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL + 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT + 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL + 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x2580: 0x00df, # UPPER HALF BLOCK + 0x2584: 0x00dc, # LOWER HALF BLOCK + 0x2588: 0x00db, # FULL BLOCK + 0x258c: 0x00dd, # LEFT HALF BLOCK + 0x2590: 0x00de, # RIGHT HALF BLOCK + 0x2591: 0x00b0, # LIGHT SHADE + 0x2592: 0x00b1, # MEDIUM SHADE + 0x2593: 0x00b2, # DARK SHADE + 0x25a0: 0x00fe, # BLACK SQUARE +} diff --git a/contrib/tools/python3/src/Lib/encodings/cp863.py b/contrib/tools/python3/src/Lib/encodings/cp863.py new file mode 100644 index 0000000000..764180b623 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp863.py @@ -0,0 +1,698 @@ +""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP863.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_map) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp863', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + +### Decoding Map + +decoding_map = codecs.make_identity_dict(range(256)) +decoding_map.update({ + 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS + 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE + 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x0084: 0x00c2, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE + 0x0086: 0x00b6, # PILCROW SIGN + 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA + 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS + 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE + 0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS + 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x008d: 0x2017, # DOUBLE LOW LINE + 0x008e: 0x00c0, # LATIN CAPITAL LETTER A WITH GRAVE + 0x008f: 0x00a7, # SECTION SIGN + 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x0091: 0x00c8, # LATIN CAPITAL LETTER E WITH GRAVE + 0x0092: 0x00ca, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x0094: 0x00cb, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x0095: 0x00cf, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE + 0x0098: 0x00a4, # CURRENCY SIGN + 0x0099: 0x00d4, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x009b: 0x00a2, # CENT SIGN + 0x009c: 0x00a3, # POUND SIGN + 0x009d: 0x00d9, # LATIN CAPITAL LETTER U WITH GRAVE + 0x009e: 0x00db, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK + 0x00a0: 0x00a6, # BROKEN BAR + 0x00a1: 0x00b4, # ACUTE ACCENT + 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE + 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE + 0x00a4: 0x00a8, # DIAERESIS + 0x00a5: 0x00b8, # CEDILLA + 0x00a6: 0x00b3, # SUPERSCRIPT THREE + 0x00a7: 0x00af, # MACRON + 0x00a8: 0x00ce, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00a9: 0x2310, # REVERSED NOT SIGN + 0x00aa: 0x00ac, # NOT SIGN + 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF + 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER + 0x00ad: 0x00be, # VULGAR FRACTION THREE QUARTERS + 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00b0: 0x2591, # LIGHT SHADE + 0x00b1: 0x2592, # MEDIUM SHADE + 0x00b2: 0x2593, # DARK SHADE + 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL + 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL + 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL + 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT + 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x00db: 0x2588, # FULL BLOCK + 0x00dc: 0x2584, # LOWER HALF BLOCK + 0x00dd: 0x258c, # LEFT HALF BLOCK + 0x00de: 0x2590, # RIGHT HALF BLOCK + 0x00df: 0x2580, # UPPER HALF BLOCK + 0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA + 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S + 0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA + 0x00e3: 0x03c0, # GREEK SMALL LETTER PI + 0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA + 0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA + 0x00e6: 0x00b5, # MICRO SIGN + 0x00e7: 0x03c4, # GREEK SMALL LETTER TAU + 0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI + 0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA + 0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA + 0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA + 0x00ec: 0x221e, # INFINITY + 0x00ed: 0x03c6, # GREEK SMALL LETTER PHI + 0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON + 0x00ef: 0x2229, # INTERSECTION + 0x00f0: 0x2261, # IDENTICAL TO + 0x00f1: 0x00b1, # PLUS-MINUS SIGN + 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO + 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO + 0x00f4: 0x2320, # TOP HALF INTEGRAL + 0x00f5: 0x2321, # BOTTOM HALF INTEGRAL + 0x00f6: 0x00f7, # DIVISION SIGN + 0x00f7: 0x2248, # ALMOST EQUAL TO + 0x00f8: 0x00b0, # DEGREE SIGN + 0x00f9: 0x2219, # BULLET OPERATOR + 0x00fa: 0x00b7, # MIDDLE DOT + 0x00fb: 0x221a, # SQUARE ROOT + 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N + 0x00fd: 0x00b2, # SUPERSCRIPT TWO + 0x00fe: 0x25a0, # BLACK SQUARE + 0x00ff: 0x00a0, # NO-BREAK SPACE +}) + +### Decoding Table + +decoding_table = ( + '\x00' # 0x0000 -> NULL + '\x01' # 0x0001 -> START OF HEADING + '\x02' # 0x0002 -> START OF TEXT + '\x03' # 0x0003 -> END OF TEXT + '\x04' # 0x0004 -> END OF TRANSMISSION + '\x05' # 0x0005 -> ENQUIRY + '\x06' # 0x0006 -> ACKNOWLEDGE + '\x07' # 0x0007 -> BELL + '\x08' # 0x0008 -> BACKSPACE + '\t' # 0x0009 -> HORIZONTAL TABULATION + '\n' # 0x000a -> LINE FEED + '\x0b' # 0x000b -> VERTICAL TABULATION + '\x0c' # 0x000c -> FORM FEED + '\r' # 0x000d -> CARRIAGE RETURN + '\x0e' # 0x000e -> SHIFT OUT + '\x0f' # 0x000f -> SHIFT IN + '\x10' # 0x0010 -> DATA LINK ESCAPE + '\x11' # 0x0011 -> DEVICE CONTROL ONE + '\x12' # 0x0012 -> DEVICE CONTROL TWO + '\x13' # 0x0013 -> DEVICE CONTROL THREE + '\x14' # 0x0014 -> DEVICE CONTROL FOUR + '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x0016 -> SYNCHRONOUS IDLE + '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK + '\x18' # 0x0018 -> CANCEL + '\x19' # 0x0019 -> END OF MEDIUM + '\x1a' # 0x001a -> SUBSTITUTE + '\x1b' # 0x001b -> ESCAPE + '\x1c' # 0x001c -> FILE SEPARATOR + '\x1d' # 0x001d -> GROUP SEPARATOR + '\x1e' # 0x001e -> RECORD SEPARATOR + '\x1f' # 0x001f -> UNIT SEPARATOR + ' ' # 0x0020 -> SPACE + '!' # 0x0021 -> EXCLAMATION MARK + '"' # 0x0022 -> QUOTATION MARK + '#' # 0x0023 -> NUMBER SIGN + '$' # 0x0024 -> DOLLAR SIGN + '%' # 0x0025 -> PERCENT SIGN + '&' # 0x0026 -> AMPERSAND + "'" # 0x0027 -> APOSTROPHE + '(' # 0x0028 -> LEFT PARENTHESIS + ')' # 0x0029 -> RIGHT PARENTHESIS + '*' # 0x002a -> ASTERISK + '+' # 0x002b -> PLUS SIGN + ',' # 0x002c -> COMMA + '-' # 0x002d -> HYPHEN-MINUS + '.' # 0x002e -> FULL STOP + '/' # 0x002f -> SOLIDUS + '0' # 0x0030 -> DIGIT ZERO + '1' # 0x0031 -> DIGIT ONE + '2' # 0x0032 -> DIGIT TWO + '3' # 0x0033 -> DIGIT THREE + '4' # 0x0034 -> DIGIT FOUR + '5' # 0x0035 -> DIGIT FIVE + '6' # 0x0036 -> DIGIT SIX + '7' # 0x0037 -> DIGIT SEVEN + '8' # 0x0038 -> DIGIT EIGHT + '9' # 0x0039 -> DIGIT NINE + ':' # 0x003a -> COLON + ';' # 0x003b -> SEMICOLON + '<' # 0x003c -> LESS-THAN SIGN + '=' # 0x003d -> EQUALS SIGN + '>' # 0x003e -> GREATER-THAN SIGN + '?' # 0x003f -> QUESTION MARK + '@' # 0x0040 -> COMMERCIAL AT + 'A' # 0x0041 -> LATIN CAPITAL LETTER A + 'B' # 0x0042 -> LATIN CAPITAL LETTER B + 'C' # 0x0043 -> LATIN CAPITAL LETTER C + 'D' # 0x0044 -> LATIN CAPITAL LETTER D + 'E' # 0x0045 -> LATIN CAPITAL LETTER E + 'F' # 0x0046 -> LATIN CAPITAL LETTER F + 'G' # 0x0047 -> LATIN CAPITAL LETTER G + 'H' # 0x0048 -> LATIN CAPITAL LETTER H + 'I' # 0x0049 -> LATIN CAPITAL LETTER I + 'J' # 0x004a -> LATIN CAPITAL LETTER J + 'K' # 0x004b -> LATIN CAPITAL LETTER K + 'L' # 0x004c -> LATIN CAPITAL LETTER L + 'M' # 0x004d -> LATIN CAPITAL LETTER M + 'N' # 0x004e -> LATIN CAPITAL LETTER N + 'O' # 0x004f -> LATIN CAPITAL LETTER O + 'P' # 0x0050 -> LATIN CAPITAL LETTER P + 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q + 'R' # 0x0052 -> LATIN CAPITAL LETTER R + 'S' # 0x0053 -> LATIN CAPITAL LETTER S + 'T' # 0x0054 -> LATIN CAPITAL LETTER T + 'U' # 0x0055 -> LATIN CAPITAL LETTER U + 'V' # 0x0056 -> LATIN CAPITAL LETTER V + 'W' # 0x0057 -> LATIN CAPITAL LETTER W + 'X' # 0x0058 -> LATIN CAPITAL LETTER X + 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y + 'Z' # 0x005a -> LATIN CAPITAL LETTER Z + '[' # 0x005b -> LEFT SQUARE BRACKET + '\\' # 0x005c -> REVERSE SOLIDUS + ']' # 0x005d -> RIGHT SQUARE BRACKET + '^' # 0x005e -> CIRCUMFLEX ACCENT + '_' # 0x005f -> LOW LINE + '`' # 0x0060 -> GRAVE ACCENT + 'a' # 0x0061 -> LATIN SMALL LETTER A + 'b' # 0x0062 -> LATIN SMALL LETTER B + 'c' # 0x0063 -> LATIN SMALL LETTER C + 'd' # 0x0064 -> LATIN SMALL LETTER D + 'e' # 0x0065 -> LATIN SMALL LETTER E + 'f' # 0x0066 -> LATIN SMALL LETTER F + 'g' # 0x0067 -> LATIN SMALL LETTER G + 'h' # 0x0068 -> LATIN SMALL LETTER H + 'i' # 0x0069 -> LATIN SMALL LETTER I + 'j' # 0x006a -> LATIN SMALL LETTER J + 'k' # 0x006b -> LATIN SMALL LETTER K + 'l' # 0x006c -> LATIN SMALL LETTER L + 'm' # 0x006d -> LATIN SMALL LETTER M + 'n' # 0x006e -> LATIN SMALL LETTER N + 'o' # 0x006f -> LATIN SMALL LETTER O + 'p' # 0x0070 -> LATIN SMALL LETTER P + 'q' # 0x0071 -> LATIN SMALL LETTER Q + 'r' # 0x0072 -> LATIN SMALL LETTER R + 's' # 0x0073 -> LATIN SMALL LETTER S + 't' # 0x0074 -> LATIN SMALL LETTER T + 'u' # 0x0075 -> LATIN SMALL LETTER U + 'v' # 0x0076 -> LATIN SMALL LETTER V + 'w' # 0x0077 -> LATIN SMALL LETTER W + 'x' # 0x0078 -> LATIN SMALL LETTER X + 'y' # 0x0079 -> LATIN SMALL LETTER Y + 'z' # 0x007a -> LATIN SMALL LETTER Z + '{' # 0x007b -> LEFT CURLY BRACKET + '|' # 0x007c -> VERTICAL LINE + '}' # 0x007d -> RIGHT CURLY BRACKET + '~' # 0x007e -> TILDE + '\x7f' # 0x007f -> DELETE + '\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS + '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE + '\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xc2' # 0x0084 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE + '\xb6' # 0x0086 -> PILCROW SIGN + '\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA + '\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS + '\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE + '\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS + '\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\u2017' # 0x008d -> DOUBLE LOW LINE + '\xc0' # 0x008e -> LATIN CAPITAL LETTER A WITH GRAVE + '\xa7' # 0x008f -> SECTION SIGN + '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xc8' # 0x0091 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xca' # 0x0092 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xcb' # 0x0094 -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xcf' # 0x0095 -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE + '\xa4' # 0x0098 -> CURRENCY SIGN + '\xd4' # 0x0099 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xa2' # 0x009b -> CENT SIGN + '\xa3' # 0x009c -> POUND SIGN + '\xd9' # 0x009d -> LATIN CAPITAL LETTER U WITH GRAVE + '\xdb' # 0x009e -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK + '\xa6' # 0x00a0 -> BROKEN BAR + '\xb4' # 0x00a1 -> ACUTE ACCENT + '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE + '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE + '\xa8' # 0x00a4 -> DIAERESIS + '\xb8' # 0x00a5 -> CEDILLA + '\xb3' # 0x00a6 -> SUPERSCRIPT THREE + '\xaf' # 0x00a7 -> MACRON + '\xce' # 0x00a8 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\u2310' # 0x00a9 -> REVERSED NOT SIGN + '\xac' # 0x00aa -> NOT SIGN + '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF + '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER + '\xbe' # 0x00ad -> VULGAR FRACTION THREE QUARTERS + '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u2591' # 0x00b0 -> LIGHT SHADE + '\u2592' # 0x00b1 -> MEDIUM SHADE + '\u2593' # 0x00b2 -> DARK SHADE + '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL + '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT + '\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + '\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + '\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + '\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL + '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT + '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT + '\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + '\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT + '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT + '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL + '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT + '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL + '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + '\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + '\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT + '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL + '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + '\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + '\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + '\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + '\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + '\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + '\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + '\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + '\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + '\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + '\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT + '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT + '\u2588' # 0x00db -> FULL BLOCK + '\u2584' # 0x00dc -> LOWER HALF BLOCK + '\u258c' # 0x00dd -> LEFT HALF BLOCK + '\u2590' # 0x00de -> RIGHT HALF BLOCK + '\u2580' # 0x00df -> UPPER HALF BLOCK + '\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA + '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S + '\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA + '\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI + '\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA + '\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA + '\xb5' # 0x00e6 -> MICRO SIGN + '\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU + '\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI + '\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA + '\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA + '\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA + '\u221e' # 0x00ec -> INFINITY + '\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI + '\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON + '\u2229' # 0x00ef -> INTERSECTION + '\u2261' # 0x00f0 -> IDENTICAL TO + '\xb1' # 0x00f1 -> PLUS-MINUS SIGN + '\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO + '\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO + '\u2320' # 0x00f4 -> TOP HALF INTEGRAL + '\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL + '\xf7' # 0x00f6 -> DIVISION SIGN + '\u2248' # 0x00f7 -> ALMOST EQUAL TO + '\xb0' # 0x00f8 -> DEGREE SIGN + '\u2219' # 0x00f9 -> BULLET OPERATOR + '\xb7' # 0x00fa -> MIDDLE DOT + '\u221a' # 0x00fb -> SQUARE ROOT + '\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N + '\xb2' # 0x00fd -> SUPERSCRIPT TWO + '\u25a0' # 0x00fe -> BLACK SQUARE + '\xa0' # 0x00ff -> NO-BREAK SPACE +) + +### Encoding Map + +encoding_map = { + 0x0000: 0x0000, # NULL + 0x0001: 0x0001, # START OF HEADING + 0x0002: 0x0002, # START OF TEXT + 0x0003: 0x0003, # END OF TEXT + 0x0004: 0x0004, # END OF TRANSMISSION + 0x0005: 0x0005, # ENQUIRY + 0x0006: 0x0006, # ACKNOWLEDGE + 0x0007: 0x0007, # BELL + 0x0008: 0x0008, # BACKSPACE + 0x0009: 0x0009, # HORIZONTAL TABULATION + 0x000a: 0x000a, # LINE FEED + 0x000b: 0x000b, # VERTICAL TABULATION + 0x000c: 0x000c, # FORM FEED + 0x000d: 0x000d, # CARRIAGE RETURN + 0x000e: 0x000e, # SHIFT OUT + 0x000f: 0x000f, # SHIFT IN + 0x0010: 0x0010, # DATA LINK ESCAPE + 0x0011: 0x0011, # DEVICE CONTROL ONE + 0x0012: 0x0012, # DEVICE CONTROL TWO + 0x0013: 0x0013, # DEVICE CONTROL THREE + 0x0014: 0x0014, # DEVICE CONTROL FOUR + 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE + 0x0016: 0x0016, # SYNCHRONOUS IDLE + 0x0017: 0x0017, # END OF TRANSMISSION BLOCK + 0x0018: 0x0018, # CANCEL + 0x0019: 0x0019, # END OF MEDIUM + 0x001a: 0x001a, # SUBSTITUTE + 0x001b: 0x001b, # ESCAPE + 0x001c: 0x001c, # FILE SEPARATOR + 0x001d: 0x001d, # GROUP SEPARATOR + 0x001e: 0x001e, # RECORD SEPARATOR + 0x001f: 0x001f, # UNIT SEPARATOR + 0x0020: 0x0020, # SPACE + 0x0021: 0x0021, # EXCLAMATION MARK + 0x0022: 0x0022, # QUOTATION MARK + 0x0023: 0x0023, # NUMBER SIGN + 0x0024: 0x0024, # DOLLAR SIGN + 0x0025: 0x0025, # PERCENT SIGN + 0x0026: 0x0026, # AMPERSAND + 0x0027: 0x0027, # APOSTROPHE + 0x0028: 0x0028, # LEFT PARENTHESIS + 0x0029: 0x0029, # RIGHT PARENTHESIS + 0x002a: 0x002a, # ASTERISK + 0x002b: 0x002b, # PLUS SIGN + 0x002c: 0x002c, # COMMA + 0x002d: 0x002d, # HYPHEN-MINUS + 0x002e: 0x002e, # FULL STOP + 0x002f: 0x002f, # SOLIDUS + 0x0030: 0x0030, # DIGIT ZERO + 0x0031: 0x0031, # DIGIT ONE + 0x0032: 0x0032, # DIGIT TWO + 0x0033: 0x0033, # DIGIT THREE + 0x0034: 0x0034, # DIGIT FOUR + 0x0035: 0x0035, # DIGIT FIVE + 0x0036: 0x0036, # DIGIT SIX + 0x0037: 0x0037, # DIGIT SEVEN + 0x0038: 0x0038, # DIGIT EIGHT + 0x0039: 0x0039, # DIGIT NINE + 0x003a: 0x003a, # COLON + 0x003b: 0x003b, # SEMICOLON + 0x003c: 0x003c, # LESS-THAN SIGN + 0x003d: 0x003d, # EQUALS SIGN + 0x003e: 0x003e, # GREATER-THAN SIGN + 0x003f: 0x003f, # QUESTION MARK + 0x0040: 0x0040, # COMMERCIAL AT + 0x0041: 0x0041, # LATIN CAPITAL LETTER A + 0x0042: 0x0042, # LATIN CAPITAL LETTER B + 0x0043: 0x0043, # LATIN CAPITAL LETTER C + 0x0044: 0x0044, # LATIN CAPITAL LETTER D + 0x0045: 0x0045, # LATIN CAPITAL LETTER E + 0x0046: 0x0046, # LATIN CAPITAL LETTER F + 0x0047: 0x0047, # LATIN CAPITAL LETTER G + 0x0048: 0x0048, # LATIN CAPITAL LETTER H + 0x0049: 0x0049, # LATIN CAPITAL LETTER I + 0x004a: 0x004a, # LATIN CAPITAL LETTER J + 0x004b: 0x004b, # LATIN CAPITAL LETTER K + 0x004c: 0x004c, # LATIN CAPITAL LETTER L + 0x004d: 0x004d, # LATIN CAPITAL LETTER M + 0x004e: 0x004e, # LATIN CAPITAL LETTER N + 0x004f: 0x004f, # LATIN CAPITAL LETTER O + 0x0050: 0x0050, # LATIN CAPITAL LETTER P + 0x0051: 0x0051, # LATIN CAPITAL LETTER Q + 0x0052: 0x0052, # LATIN CAPITAL LETTER R + 0x0053: 0x0053, # LATIN CAPITAL LETTER S + 0x0054: 0x0054, # LATIN CAPITAL LETTER T + 0x0055: 0x0055, # LATIN CAPITAL LETTER U + 0x0056: 0x0056, # LATIN CAPITAL LETTER V + 0x0057: 0x0057, # LATIN CAPITAL LETTER W + 0x0058: 0x0058, # LATIN CAPITAL LETTER X + 0x0059: 0x0059, # LATIN CAPITAL LETTER Y + 0x005a: 0x005a, # LATIN CAPITAL LETTER Z + 0x005b: 0x005b, # LEFT SQUARE BRACKET + 0x005c: 0x005c, # REVERSE SOLIDUS + 0x005d: 0x005d, # RIGHT SQUARE BRACKET + 0x005e: 0x005e, # CIRCUMFLEX ACCENT + 0x005f: 0x005f, # LOW LINE + 0x0060: 0x0060, # GRAVE ACCENT + 0x0061: 0x0061, # LATIN SMALL LETTER A + 0x0062: 0x0062, # LATIN SMALL LETTER B + 0x0063: 0x0063, # LATIN SMALL LETTER C + 0x0064: 0x0064, # LATIN SMALL LETTER D + 0x0065: 0x0065, # LATIN SMALL LETTER E + 0x0066: 0x0066, # LATIN SMALL LETTER F + 0x0067: 0x0067, # LATIN SMALL LETTER G + 0x0068: 0x0068, # LATIN SMALL LETTER H + 0x0069: 0x0069, # LATIN SMALL LETTER I + 0x006a: 0x006a, # LATIN SMALL LETTER J + 0x006b: 0x006b, # LATIN SMALL LETTER K + 0x006c: 0x006c, # LATIN SMALL LETTER L + 0x006d: 0x006d, # LATIN SMALL LETTER M + 0x006e: 0x006e, # LATIN SMALL LETTER N + 0x006f: 0x006f, # LATIN SMALL LETTER O + 0x0070: 0x0070, # LATIN SMALL LETTER P + 0x0071: 0x0071, # LATIN SMALL LETTER Q + 0x0072: 0x0072, # LATIN SMALL LETTER R + 0x0073: 0x0073, # LATIN SMALL LETTER S + 0x0074: 0x0074, # LATIN SMALL LETTER T + 0x0075: 0x0075, # LATIN SMALL LETTER U + 0x0076: 0x0076, # LATIN SMALL LETTER V + 0x0077: 0x0077, # LATIN SMALL LETTER W + 0x0078: 0x0078, # LATIN SMALL LETTER X + 0x0079: 0x0079, # LATIN SMALL LETTER Y + 0x007a: 0x007a, # LATIN SMALL LETTER Z + 0x007b: 0x007b, # LEFT CURLY BRACKET + 0x007c: 0x007c, # VERTICAL LINE + 0x007d: 0x007d, # RIGHT CURLY BRACKET + 0x007e: 0x007e, # TILDE + 0x007f: 0x007f, # DELETE + 0x00a0: 0x00ff, # NO-BREAK SPACE + 0x00a2: 0x009b, # CENT SIGN + 0x00a3: 0x009c, # POUND SIGN + 0x00a4: 0x0098, # CURRENCY SIGN + 0x00a6: 0x00a0, # BROKEN BAR + 0x00a7: 0x008f, # SECTION SIGN + 0x00a8: 0x00a4, # DIAERESIS + 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00ac: 0x00aa, # NOT SIGN + 0x00af: 0x00a7, # MACRON + 0x00b0: 0x00f8, # DEGREE SIGN + 0x00b1: 0x00f1, # PLUS-MINUS SIGN + 0x00b2: 0x00fd, # SUPERSCRIPT TWO + 0x00b3: 0x00a6, # SUPERSCRIPT THREE + 0x00b4: 0x00a1, # ACUTE ACCENT + 0x00b5: 0x00e6, # MICRO SIGN + 0x00b6: 0x0086, # PILCROW SIGN + 0x00b7: 0x00fa, # MIDDLE DOT + 0x00b8: 0x00a5, # CEDILLA + 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER + 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF + 0x00be: 0x00ad, # VULGAR FRACTION THREE QUARTERS + 0x00c0: 0x008e, # LATIN CAPITAL LETTER A WITH GRAVE + 0x00c2: 0x0084, # LATIN CAPITAL LETTER A WITH CIRCUMFLEX + 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00c8: 0x0091, # LATIN CAPITAL LETTER E WITH GRAVE + 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00ca: 0x0092, # LATIN CAPITAL LETTER E WITH CIRCUMFLEX + 0x00cb: 0x0094, # LATIN CAPITAL LETTER E WITH DIAERESIS + 0x00ce: 0x00a8, # LATIN CAPITAL LETTER I WITH CIRCUMFLEX + 0x00cf: 0x0095, # LATIN CAPITAL LETTER I WITH DIAERESIS + 0x00d4: 0x0099, # LATIN CAPITAL LETTER O WITH CIRCUMFLEX + 0x00d9: 0x009d, # LATIN CAPITAL LETTER U WITH GRAVE + 0x00db: 0x009e, # LATIN CAPITAL LETTER U WITH CIRCUMFLEX + 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S + 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE + 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA + 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE + 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE + 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE + 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00f7: 0x00f6, # DIVISION SIGN + 0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE + 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE + 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS + 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK + 0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA + 0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA + 0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA + 0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI + 0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA + 0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA + 0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA + 0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON + 0x03c0: 0x00e3, # GREEK SMALL LETTER PI + 0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA + 0x03c4: 0x00e7, # GREEK SMALL LETTER TAU + 0x03c6: 0x00ed, # GREEK SMALL LETTER PHI + 0x2017: 0x008d, # DOUBLE LOW LINE + 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N + 0x2219: 0x00f9, # BULLET OPERATOR + 0x221a: 0x00fb, # SQUARE ROOT + 0x221e: 0x00ec, # INFINITY + 0x2229: 0x00ef, # INTERSECTION + 0x2248: 0x00f7, # ALMOST EQUAL TO + 0x2261: 0x00f0, # IDENTICAL TO + 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO + 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO + 0x2310: 0x00a9, # REVERSED NOT SIGN + 0x2320: 0x00f4, # TOP HALF INTEGRAL + 0x2321: 0x00f5, # BOTTOM HALF INTEGRAL + 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL + 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL + 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT + 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL + 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x2580: 0x00df, # UPPER HALF BLOCK + 0x2584: 0x00dc, # LOWER HALF BLOCK + 0x2588: 0x00db, # FULL BLOCK + 0x258c: 0x00dd, # LEFT HALF BLOCK + 0x2590: 0x00de, # RIGHT HALF BLOCK + 0x2591: 0x00b0, # LIGHT SHADE + 0x2592: 0x00b1, # MEDIUM SHADE + 0x2593: 0x00b2, # DARK SHADE + 0x25a0: 0x00fe, # BLACK SQUARE +} diff --git a/contrib/tools/python3/src/Lib/encodings/cp864.py b/contrib/tools/python3/src/Lib/encodings/cp864.py new file mode 100644 index 0000000000..53df482dcd --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp864.py @@ -0,0 +1,690 @@ +""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP864.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_map) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp864', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + +### Decoding Map + +decoding_map = codecs.make_identity_dict(range(256)) +decoding_map.update({ + 0x0025: 0x066a, # ARABIC PERCENT SIGN + 0x0080: 0x00b0, # DEGREE SIGN + 0x0081: 0x00b7, # MIDDLE DOT + 0x0082: 0x2219, # BULLET OPERATOR + 0x0083: 0x221a, # SQUARE ROOT + 0x0084: 0x2592, # MEDIUM SHADE + 0x0085: 0x2500, # FORMS LIGHT HORIZONTAL + 0x0086: 0x2502, # FORMS LIGHT VERTICAL + 0x0087: 0x253c, # FORMS LIGHT VERTICAL AND HORIZONTAL + 0x0088: 0x2524, # FORMS LIGHT VERTICAL AND LEFT + 0x0089: 0x252c, # FORMS LIGHT DOWN AND HORIZONTAL + 0x008a: 0x251c, # FORMS LIGHT VERTICAL AND RIGHT + 0x008b: 0x2534, # FORMS LIGHT UP AND HORIZONTAL + 0x008c: 0x2510, # FORMS LIGHT DOWN AND LEFT + 0x008d: 0x250c, # FORMS LIGHT DOWN AND RIGHT + 0x008e: 0x2514, # FORMS LIGHT UP AND RIGHT + 0x008f: 0x2518, # FORMS LIGHT UP AND LEFT + 0x0090: 0x03b2, # GREEK SMALL BETA + 0x0091: 0x221e, # INFINITY + 0x0092: 0x03c6, # GREEK SMALL PHI + 0x0093: 0x00b1, # PLUS-OR-MINUS SIGN + 0x0094: 0x00bd, # FRACTION 1/2 + 0x0095: 0x00bc, # FRACTION 1/4 + 0x0096: 0x2248, # ALMOST EQUAL TO + 0x0097: 0x00ab, # LEFT POINTING GUILLEMET + 0x0098: 0x00bb, # RIGHT POINTING GUILLEMET + 0x0099: 0xfef7, # ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE ISOLATED FORM + 0x009a: 0xfef8, # ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE FINAL FORM + 0x009b: None, # UNDEFINED + 0x009c: None, # UNDEFINED + 0x009d: 0xfefb, # ARABIC LIGATURE LAM WITH ALEF ISOLATED FORM + 0x009e: 0xfefc, # ARABIC LIGATURE LAM WITH ALEF FINAL FORM + 0x009f: None, # UNDEFINED + 0x00a1: 0x00ad, # SOFT HYPHEN + 0x00a2: 0xfe82, # ARABIC LETTER ALEF WITH MADDA ABOVE FINAL FORM + 0x00a5: 0xfe84, # ARABIC LETTER ALEF WITH HAMZA ABOVE FINAL FORM + 0x00a6: None, # UNDEFINED + 0x00a7: None, # UNDEFINED + 0x00a8: 0xfe8e, # ARABIC LETTER ALEF FINAL FORM + 0x00a9: 0xfe8f, # ARABIC LETTER BEH ISOLATED FORM + 0x00aa: 0xfe95, # ARABIC LETTER TEH ISOLATED FORM + 0x00ab: 0xfe99, # ARABIC LETTER THEH ISOLATED FORM + 0x00ac: 0x060c, # ARABIC COMMA + 0x00ad: 0xfe9d, # ARABIC LETTER JEEM ISOLATED FORM + 0x00ae: 0xfea1, # ARABIC LETTER HAH ISOLATED FORM + 0x00af: 0xfea5, # ARABIC LETTER KHAH ISOLATED FORM + 0x00b0: 0x0660, # ARABIC-INDIC DIGIT ZERO + 0x00b1: 0x0661, # ARABIC-INDIC DIGIT ONE + 0x00b2: 0x0662, # ARABIC-INDIC DIGIT TWO + 0x00b3: 0x0663, # ARABIC-INDIC DIGIT THREE + 0x00b4: 0x0664, # ARABIC-INDIC DIGIT FOUR + 0x00b5: 0x0665, # ARABIC-INDIC DIGIT FIVE + 0x00b6: 0x0666, # ARABIC-INDIC DIGIT SIX + 0x00b7: 0x0667, # ARABIC-INDIC DIGIT SEVEN + 0x00b8: 0x0668, # ARABIC-INDIC DIGIT EIGHT + 0x00b9: 0x0669, # ARABIC-INDIC DIGIT NINE + 0x00ba: 0xfed1, # ARABIC LETTER FEH ISOLATED FORM + 0x00bb: 0x061b, # ARABIC SEMICOLON + 0x00bc: 0xfeb1, # ARABIC LETTER SEEN ISOLATED FORM + 0x00bd: 0xfeb5, # ARABIC LETTER SHEEN ISOLATED FORM + 0x00be: 0xfeb9, # ARABIC LETTER SAD ISOLATED FORM + 0x00bf: 0x061f, # ARABIC QUESTION MARK + 0x00c0: 0x00a2, # CENT SIGN + 0x00c1: 0xfe80, # ARABIC LETTER HAMZA ISOLATED FORM + 0x00c2: 0xfe81, # ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM + 0x00c3: 0xfe83, # ARABIC LETTER ALEF WITH HAMZA ABOVE ISOLATED FORM + 0x00c4: 0xfe85, # ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM + 0x00c5: 0xfeca, # ARABIC LETTER AIN FINAL FORM + 0x00c6: 0xfe8b, # ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM + 0x00c7: 0xfe8d, # ARABIC LETTER ALEF ISOLATED FORM + 0x00c8: 0xfe91, # ARABIC LETTER BEH INITIAL FORM + 0x00c9: 0xfe93, # ARABIC LETTER TEH MARBUTA ISOLATED FORM + 0x00ca: 0xfe97, # ARABIC LETTER TEH INITIAL FORM + 0x00cb: 0xfe9b, # ARABIC LETTER THEH INITIAL FORM + 0x00cc: 0xfe9f, # ARABIC LETTER JEEM INITIAL FORM + 0x00cd: 0xfea3, # ARABIC LETTER HAH INITIAL FORM + 0x00ce: 0xfea7, # ARABIC LETTER KHAH INITIAL FORM + 0x00cf: 0xfea9, # ARABIC LETTER DAL ISOLATED FORM + 0x00d0: 0xfeab, # ARABIC LETTER THAL ISOLATED FORM + 0x00d1: 0xfead, # ARABIC LETTER REH ISOLATED FORM + 0x00d2: 0xfeaf, # ARABIC LETTER ZAIN ISOLATED FORM + 0x00d3: 0xfeb3, # ARABIC LETTER SEEN INITIAL FORM + 0x00d4: 0xfeb7, # ARABIC LETTER SHEEN INITIAL FORM + 0x00d5: 0xfebb, # ARABIC LETTER SAD INITIAL FORM + 0x00d6: 0xfebf, # ARABIC LETTER DAD INITIAL FORM + 0x00d7: 0xfec1, # ARABIC LETTER TAH ISOLATED FORM + 0x00d8: 0xfec5, # ARABIC LETTER ZAH ISOLATED FORM + 0x00d9: 0xfecb, # ARABIC LETTER AIN INITIAL FORM + 0x00da: 0xfecf, # ARABIC LETTER GHAIN INITIAL FORM + 0x00db: 0x00a6, # BROKEN VERTICAL BAR + 0x00dc: 0x00ac, # NOT SIGN + 0x00dd: 0x00f7, # DIVISION SIGN + 0x00de: 0x00d7, # MULTIPLICATION SIGN + 0x00df: 0xfec9, # ARABIC LETTER AIN ISOLATED FORM + 0x00e0: 0x0640, # ARABIC TATWEEL + 0x00e1: 0xfed3, # ARABIC LETTER FEH INITIAL FORM + 0x00e2: 0xfed7, # ARABIC LETTER QAF INITIAL FORM + 0x00e3: 0xfedb, # ARABIC LETTER KAF INITIAL FORM + 0x00e4: 0xfedf, # ARABIC LETTER LAM INITIAL FORM + 0x00e5: 0xfee3, # ARABIC LETTER MEEM INITIAL FORM + 0x00e6: 0xfee7, # ARABIC LETTER NOON INITIAL FORM + 0x00e7: 0xfeeb, # ARABIC LETTER HEH INITIAL FORM + 0x00e8: 0xfeed, # ARABIC LETTER WAW ISOLATED FORM + 0x00e9: 0xfeef, # ARABIC LETTER ALEF MAKSURA ISOLATED FORM + 0x00ea: 0xfef3, # ARABIC LETTER YEH INITIAL FORM + 0x00eb: 0xfebd, # ARABIC LETTER DAD ISOLATED FORM + 0x00ec: 0xfecc, # ARABIC LETTER AIN MEDIAL FORM + 0x00ed: 0xfece, # ARABIC LETTER GHAIN FINAL FORM + 0x00ee: 0xfecd, # ARABIC LETTER GHAIN ISOLATED FORM + 0x00ef: 0xfee1, # ARABIC LETTER MEEM ISOLATED FORM + 0x00f0: 0xfe7d, # ARABIC SHADDA MEDIAL FORM + 0x00f1: 0x0651, # ARABIC SHADDAH + 0x00f2: 0xfee5, # ARABIC LETTER NOON ISOLATED FORM + 0x00f3: 0xfee9, # ARABIC LETTER HEH ISOLATED FORM + 0x00f4: 0xfeec, # ARABIC LETTER HEH MEDIAL FORM + 0x00f5: 0xfef0, # ARABIC LETTER ALEF MAKSURA FINAL FORM + 0x00f6: 0xfef2, # ARABIC LETTER YEH FINAL FORM + 0x00f7: 0xfed0, # ARABIC LETTER GHAIN MEDIAL FORM + 0x00f8: 0xfed5, # ARABIC LETTER QAF ISOLATED FORM + 0x00f9: 0xfef5, # ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE ISOLATED FORM + 0x00fa: 0xfef6, # ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE FINAL FORM + 0x00fb: 0xfedd, # ARABIC LETTER LAM ISOLATED FORM + 0x00fc: 0xfed9, # ARABIC LETTER KAF ISOLATED FORM + 0x00fd: 0xfef1, # ARABIC LETTER YEH ISOLATED FORM + 0x00fe: 0x25a0, # BLACK SQUARE + 0x00ff: None, # UNDEFINED +}) + +### Decoding Table + +decoding_table = ( + '\x00' # 0x0000 -> NULL + '\x01' # 0x0001 -> START OF HEADING + '\x02' # 0x0002 -> START OF TEXT + '\x03' # 0x0003 -> END OF TEXT + '\x04' # 0x0004 -> END OF TRANSMISSION + '\x05' # 0x0005 -> ENQUIRY + '\x06' # 0x0006 -> ACKNOWLEDGE + '\x07' # 0x0007 -> BELL + '\x08' # 0x0008 -> BACKSPACE + '\t' # 0x0009 -> HORIZONTAL TABULATION + '\n' # 0x000a -> LINE FEED + '\x0b' # 0x000b -> VERTICAL TABULATION + '\x0c' # 0x000c -> FORM FEED + '\r' # 0x000d -> CARRIAGE RETURN + '\x0e' # 0x000e -> SHIFT OUT + '\x0f' # 0x000f -> SHIFT IN + '\x10' # 0x0010 -> DATA LINK ESCAPE + '\x11' # 0x0011 -> DEVICE CONTROL ONE + '\x12' # 0x0012 -> DEVICE CONTROL TWO + '\x13' # 0x0013 -> DEVICE CONTROL THREE + '\x14' # 0x0014 -> DEVICE CONTROL FOUR + '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x0016 -> SYNCHRONOUS IDLE + '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK + '\x18' # 0x0018 -> CANCEL + '\x19' # 0x0019 -> END OF MEDIUM + '\x1a' # 0x001a -> SUBSTITUTE + '\x1b' # 0x001b -> ESCAPE + '\x1c' # 0x001c -> FILE SEPARATOR + '\x1d' # 0x001d -> GROUP SEPARATOR + '\x1e' # 0x001e -> RECORD SEPARATOR + '\x1f' # 0x001f -> UNIT SEPARATOR + ' ' # 0x0020 -> SPACE + '!' # 0x0021 -> EXCLAMATION MARK + '"' # 0x0022 -> QUOTATION MARK + '#' # 0x0023 -> NUMBER SIGN + '$' # 0x0024 -> DOLLAR SIGN + '\u066a' # 0x0025 -> ARABIC PERCENT SIGN + '&' # 0x0026 -> AMPERSAND + "'" # 0x0027 -> APOSTROPHE + '(' # 0x0028 -> LEFT PARENTHESIS + ')' # 0x0029 -> RIGHT PARENTHESIS + '*' # 0x002a -> ASTERISK + '+' # 0x002b -> PLUS SIGN + ',' # 0x002c -> COMMA + '-' # 0x002d -> HYPHEN-MINUS + '.' # 0x002e -> FULL STOP + '/' # 0x002f -> SOLIDUS + '0' # 0x0030 -> DIGIT ZERO + '1' # 0x0031 -> DIGIT ONE + '2' # 0x0032 -> DIGIT TWO + '3' # 0x0033 -> DIGIT THREE + '4' # 0x0034 -> DIGIT FOUR + '5' # 0x0035 -> DIGIT FIVE + '6' # 0x0036 -> DIGIT SIX + '7' # 0x0037 -> DIGIT SEVEN + '8' # 0x0038 -> DIGIT EIGHT + '9' # 0x0039 -> DIGIT NINE + ':' # 0x003a -> COLON + ';' # 0x003b -> SEMICOLON + '<' # 0x003c -> LESS-THAN SIGN + '=' # 0x003d -> EQUALS SIGN + '>' # 0x003e -> GREATER-THAN SIGN + '?' # 0x003f -> QUESTION MARK + '@' # 0x0040 -> COMMERCIAL AT + 'A' # 0x0041 -> LATIN CAPITAL LETTER A + 'B' # 0x0042 -> LATIN CAPITAL LETTER B + 'C' # 0x0043 -> LATIN CAPITAL LETTER C + 'D' # 0x0044 -> LATIN CAPITAL LETTER D + 'E' # 0x0045 -> LATIN CAPITAL LETTER E + 'F' # 0x0046 -> LATIN CAPITAL LETTER F + 'G' # 0x0047 -> LATIN CAPITAL LETTER G + 'H' # 0x0048 -> LATIN CAPITAL LETTER H + 'I' # 0x0049 -> LATIN CAPITAL LETTER I + 'J' # 0x004a -> LATIN CAPITAL LETTER J + 'K' # 0x004b -> LATIN CAPITAL LETTER K + 'L' # 0x004c -> LATIN CAPITAL LETTER L + 'M' # 0x004d -> LATIN CAPITAL LETTER M + 'N' # 0x004e -> LATIN CAPITAL LETTER N + 'O' # 0x004f -> LATIN CAPITAL LETTER O + 'P' # 0x0050 -> LATIN CAPITAL LETTER P + 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q + 'R' # 0x0052 -> LATIN CAPITAL LETTER R + 'S' # 0x0053 -> LATIN CAPITAL LETTER S + 'T' # 0x0054 -> LATIN CAPITAL LETTER T + 'U' # 0x0055 -> LATIN CAPITAL LETTER U + 'V' # 0x0056 -> LATIN CAPITAL LETTER V + 'W' # 0x0057 -> LATIN CAPITAL LETTER W + 'X' # 0x0058 -> LATIN CAPITAL LETTER X + 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y + 'Z' # 0x005a -> LATIN CAPITAL LETTER Z + '[' # 0x005b -> LEFT SQUARE BRACKET + '\\' # 0x005c -> REVERSE SOLIDUS + ']' # 0x005d -> RIGHT SQUARE BRACKET + '^' # 0x005e -> CIRCUMFLEX ACCENT + '_' # 0x005f -> LOW LINE + '`' # 0x0060 -> GRAVE ACCENT + 'a' # 0x0061 -> LATIN SMALL LETTER A + 'b' # 0x0062 -> LATIN SMALL LETTER B + 'c' # 0x0063 -> LATIN SMALL LETTER C + 'd' # 0x0064 -> LATIN SMALL LETTER D + 'e' # 0x0065 -> LATIN SMALL LETTER E + 'f' # 0x0066 -> LATIN SMALL LETTER F + 'g' # 0x0067 -> LATIN SMALL LETTER G + 'h' # 0x0068 -> LATIN SMALL LETTER H + 'i' # 0x0069 -> LATIN SMALL LETTER I + 'j' # 0x006a -> LATIN SMALL LETTER J + 'k' # 0x006b -> LATIN SMALL LETTER K + 'l' # 0x006c -> LATIN SMALL LETTER L + 'm' # 0x006d -> LATIN SMALL LETTER M + 'n' # 0x006e -> LATIN SMALL LETTER N + 'o' # 0x006f -> LATIN SMALL LETTER O + 'p' # 0x0070 -> LATIN SMALL LETTER P + 'q' # 0x0071 -> LATIN SMALL LETTER Q + 'r' # 0x0072 -> LATIN SMALL LETTER R + 's' # 0x0073 -> LATIN SMALL LETTER S + 't' # 0x0074 -> LATIN SMALL LETTER T + 'u' # 0x0075 -> LATIN SMALL LETTER U + 'v' # 0x0076 -> LATIN SMALL LETTER V + 'w' # 0x0077 -> LATIN SMALL LETTER W + 'x' # 0x0078 -> LATIN SMALL LETTER X + 'y' # 0x0079 -> LATIN SMALL LETTER Y + 'z' # 0x007a -> LATIN SMALL LETTER Z + '{' # 0x007b -> LEFT CURLY BRACKET + '|' # 0x007c -> VERTICAL LINE + '}' # 0x007d -> RIGHT CURLY BRACKET + '~' # 0x007e -> TILDE + '\x7f' # 0x007f -> DELETE + '\xb0' # 0x0080 -> DEGREE SIGN + '\xb7' # 0x0081 -> MIDDLE DOT + '\u2219' # 0x0082 -> BULLET OPERATOR + '\u221a' # 0x0083 -> SQUARE ROOT + '\u2592' # 0x0084 -> MEDIUM SHADE + '\u2500' # 0x0085 -> FORMS LIGHT HORIZONTAL + '\u2502' # 0x0086 -> FORMS LIGHT VERTICAL + '\u253c' # 0x0087 -> FORMS LIGHT VERTICAL AND HORIZONTAL + '\u2524' # 0x0088 -> FORMS LIGHT VERTICAL AND LEFT + '\u252c' # 0x0089 -> FORMS LIGHT DOWN AND HORIZONTAL + '\u251c' # 0x008a -> FORMS LIGHT VERTICAL AND RIGHT + '\u2534' # 0x008b -> FORMS LIGHT UP AND HORIZONTAL + '\u2510' # 0x008c -> FORMS LIGHT DOWN AND LEFT + '\u250c' # 0x008d -> FORMS LIGHT DOWN AND RIGHT + '\u2514' # 0x008e -> FORMS LIGHT UP AND RIGHT + '\u2518' # 0x008f -> FORMS LIGHT UP AND LEFT + '\u03b2' # 0x0090 -> GREEK SMALL BETA + '\u221e' # 0x0091 -> INFINITY + '\u03c6' # 0x0092 -> GREEK SMALL PHI + '\xb1' # 0x0093 -> PLUS-OR-MINUS SIGN + '\xbd' # 0x0094 -> FRACTION 1/2 + '\xbc' # 0x0095 -> FRACTION 1/4 + '\u2248' # 0x0096 -> ALMOST EQUAL TO + '\xab' # 0x0097 -> LEFT POINTING GUILLEMET + '\xbb' # 0x0098 -> RIGHT POINTING GUILLEMET + '\ufef7' # 0x0099 -> ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE ISOLATED FORM + '\ufef8' # 0x009a -> ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE FINAL FORM + '\ufffe' # 0x009b -> UNDEFINED + '\ufffe' # 0x009c -> UNDEFINED + '\ufefb' # 0x009d -> ARABIC LIGATURE LAM WITH ALEF ISOLATED FORM + '\ufefc' # 0x009e -> ARABIC LIGATURE LAM WITH ALEF FINAL FORM + '\ufffe' # 0x009f -> UNDEFINED + '\xa0' # 0x00a0 -> NON-BREAKING SPACE + '\xad' # 0x00a1 -> SOFT HYPHEN + '\ufe82' # 0x00a2 -> ARABIC LETTER ALEF WITH MADDA ABOVE FINAL FORM + '\xa3' # 0x00a3 -> POUND SIGN + '\xa4' # 0x00a4 -> CURRENCY SIGN + '\ufe84' # 0x00a5 -> ARABIC LETTER ALEF WITH HAMZA ABOVE FINAL FORM + '\ufffe' # 0x00a6 -> UNDEFINED + '\ufffe' # 0x00a7 -> UNDEFINED + '\ufe8e' # 0x00a8 -> ARABIC LETTER ALEF FINAL FORM + '\ufe8f' # 0x00a9 -> ARABIC LETTER BEH ISOLATED FORM + '\ufe95' # 0x00aa -> ARABIC LETTER TEH ISOLATED FORM + '\ufe99' # 0x00ab -> ARABIC LETTER THEH ISOLATED FORM + '\u060c' # 0x00ac -> ARABIC COMMA + '\ufe9d' # 0x00ad -> ARABIC LETTER JEEM ISOLATED FORM + '\ufea1' # 0x00ae -> ARABIC LETTER HAH ISOLATED FORM + '\ufea5' # 0x00af -> ARABIC LETTER KHAH ISOLATED FORM + '\u0660' # 0x00b0 -> ARABIC-INDIC DIGIT ZERO + '\u0661' # 0x00b1 -> ARABIC-INDIC DIGIT ONE + '\u0662' # 0x00b2 -> ARABIC-INDIC DIGIT TWO + '\u0663' # 0x00b3 -> ARABIC-INDIC DIGIT THREE + '\u0664' # 0x00b4 -> ARABIC-INDIC DIGIT FOUR + '\u0665' # 0x00b5 -> ARABIC-INDIC DIGIT FIVE + '\u0666' # 0x00b6 -> ARABIC-INDIC DIGIT SIX + '\u0667' # 0x00b7 -> ARABIC-INDIC DIGIT SEVEN + '\u0668' # 0x00b8 -> ARABIC-INDIC DIGIT EIGHT + '\u0669' # 0x00b9 -> ARABIC-INDIC DIGIT NINE + '\ufed1' # 0x00ba -> ARABIC LETTER FEH ISOLATED FORM + '\u061b' # 0x00bb -> ARABIC SEMICOLON + '\ufeb1' # 0x00bc -> ARABIC LETTER SEEN ISOLATED FORM + '\ufeb5' # 0x00bd -> ARABIC LETTER SHEEN ISOLATED FORM + '\ufeb9' # 0x00be -> ARABIC LETTER SAD ISOLATED FORM + '\u061f' # 0x00bf -> ARABIC QUESTION MARK + '\xa2' # 0x00c0 -> CENT SIGN + '\ufe80' # 0x00c1 -> ARABIC LETTER HAMZA ISOLATED FORM + '\ufe81' # 0x00c2 -> ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM + '\ufe83' # 0x00c3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE ISOLATED FORM + '\ufe85' # 0x00c4 -> ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM + '\ufeca' # 0x00c5 -> ARABIC LETTER AIN FINAL FORM + '\ufe8b' # 0x00c6 -> ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM + '\ufe8d' # 0x00c7 -> ARABIC LETTER ALEF ISOLATED FORM + '\ufe91' # 0x00c8 -> ARABIC LETTER BEH INITIAL FORM + '\ufe93' # 0x00c9 -> ARABIC LETTER TEH MARBUTA ISOLATED FORM + '\ufe97' # 0x00ca -> ARABIC LETTER TEH INITIAL FORM + '\ufe9b' # 0x00cb -> ARABIC LETTER THEH INITIAL FORM + '\ufe9f' # 0x00cc -> ARABIC LETTER JEEM INITIAL FORM + '\ufea3' # 0x00cd -> ARABIC LETTER HAH INITIAL FORM + '\ufea7' # 0x00ce -> ARABIC LETTER KHAH INITIAL FORM + '\ufea9' # 0x00cf -> ARABIC LETTER DAL ISOLATED FORM + '\ufeab' # 0x00d0 -> ARABIC LETTER THAL ISOLATED FORM + '\ufead' # 0x00d1 -> ARABIC LETTER REH ISOLATED FORM + '\ufeaf' # 0x00d2 -> ARABIC LETTER ZAIN ISOLATED FORM + '\ufeb3' # 0x00d3 -> ARABIC LETTER SEEN INITIAL FORM + '\ufeb7' # 0x00d4 -> ARABIC LETTER SHEEN INITIAL FORM + '\ufebb' # 0x00d5 -> ARABIC LETTER SAD INITIAL FORM + '\ufebf' # 0x00d6 -> ARABIC LETTER DAD INITIAL FORM + '\ufec1' # 0x00d7 -> ARABIC LETTER TAH ISOLATED FORM + '\ufec5' # 0x00d8 -> ARABIC LETTER ZAH ISOLATED FORM + '\ufecb' # 0x00d9 -> ARABIC LETTER AIN INITIAL FORM + '\ufecf' # 0x00da -> ARABIC LETTER GHAIN INITIAL FORM + '\xa6' # 0x00db -> BROKEN VERTICAL BAR + '\xac' # 0x00dc -> NOT SIGN + '\xf7' # 0x00dd -> DIVISION SIGN + '\xd7' # 0x00de -> MULTIPLICATION SIGN + '\ufec9' # 0x00df -> ARABIC LETTER AIN ISOLATED FORM + '\u0640' # 0x00e0 -> ARABIC TATWEEL + '\ufed3' # 0x00e1 -> ARABIC LETTER FEH INITIAL FORM + '\ufed7' # 0x00e2 -> ARABIC LETTER QAF INITIAL FORM + '\ufedb' # 0x00e3 -> ARABIC LETTER KAF INITIAL FORM + '\ufedf' # 0x00e4 -> ARABIC LETTER LAM INITIAL FORM + '\ufee3' # 0x00e5 -> ARABIC LETTER MEEM INITIAL FORM + '\ufee7' # 0x00e6 -> ARABIC LETTER NOON INITIAL FORM + '\ufeeb' # 0x00e7 -> ARABIC LETTER HEH INITIAL FORM + '\ufeed' # 0x00e8 -> ARABIC LETTER WAW ISOLATED FORM + '\ufeef' # 0x00e9 -> ARABIC LETTER ALEF MAKSURA ISOLATED FORM + '\ufef3' # 0x00ea -> ARABIC LETTER YEH INITIAL FORM + '\ufebd' # 0x00eb -> ARABIC LETTER DAD ISOLATED FORM + '\ufecc' # 0x00ec -> ARABIC LETTER AIN MEDIAL FORM + '\ufece' # 0x00ed -> ARABIC LETTER GHAIN FINAL FORM + '\ufecd' # 0x00ee -> ARABIC LETTER GHAIN ISOLATED FORM + '\ufee1' # 0x00ef -> ARABIC LETTER MEEM ISOLATED FORM + '\ufe7d' # 0x00f0 -> ARABIC SHADDA MEDIAL FORM + '\u0651' # 0x00f1 -> ARABIC SHADDAH + '\ufee5' # 0x00f2 -> ARABIC LETTER NOON ISOLATED FORM + '\ufee9' # 0x00f3 -> ARABIC LETTER HEH ISOLATED FORM + '\ufeec' # 0x00f4 -> ARABIC LETTER HEH MEDIAL FORM + '\ufef0' # 0x00f5 -> ARABIC LETTER ALEF MAKSURA FINAL FORM + '\ufef2' # 0x00f6 -> ARABIC LETTER YEH FINAL FORM + '\ufed0' # 0x00f7 -> ARABIC LETTER GHAIN MEDIAL FORM + '\ufed5' # 0x00f8 -> ARABIC LETTER QAF ISOLATED FORM + '\ufef5' # 0x00f9 -> ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE ISOLATED FORM + '\ufef6' # 0x00fa -> ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE FINAL FORM + '\ufedd' # 0x00fb -> ARABIC LETTER LAM ISOLATED FORM + '\ufed9' # 0x00fc -> ARABIC LETTER KAF ISOLATED FORM + '\ufef1' # 0x00fd -> ARABIC LETTER YEH ISOLATED FORM + '\u25a0' # 0x00fe -> BLACK SQUARE + '\ufffe' # 0x00ff -> UNDEFINED +) + +### Encoding Map + +encoding_map = { + 0x0000: 0x0000, # NULL + 0x0001: 0x0001, # START OF HEADING + 0x0002: 0x0002, # START OF TEXT + 0x0003: 0x0003, # END OF TEXT + 0x0004: 0x0004, # END OF TRANSMISSION + 0x0005: 0x0005, # ENQUIRY + 0x0006: 0x0006, # ACKNOWLEDGE + 0x0007: 0x0007, # BELL + 0x0008: 0x0008, # BACKSPACE + 0x0009: 0x0009, # HORIZONTAL TABULATION + 0x000a: 0x000a, # LINE FEED + 0x000b: 0x000b, # VERTICAL TABULATION + 0x000c: 0x000c, # FORM FEED + 0x000d: 0x000d, # CARRIAGE RETURN + 0x000e: 0x000e, # SHIFT OUT + 0x000f: 0x000f, # SHIFT IN + 0x0010: 0x0010, # DATA LINK ESCAPE + 0x0011: 0x0011, # DEVICE CONTROL ONE + 0x0012: 0x0012, # DEVICE CONTROL TWO + 0x0013: 0x0013, # DEVICE CONTROL THREE + 0x0014: 0x0014, # DEVICE CONTROL FOUR + 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE + 0x0016: 0x0016, # SYNCHRONOUS IDLE + 0x0017: 0x0017, # END OF TRANSMISSION BLOCK + 0x0018: 0x0018, # CANCEL + 0x0019: 0x0019, # END OF MEDIUM + 0x001a: 0x001a, # SUBSTITUTE + 0x001b: 0x001b, # ESCAPE + 0x001c: 0x001c, # FILE SEPARATOR + 0x001d: 0x001d, # GROUP SEPARATOR + 0x001e: 0x001e, # RECORD SEPARATOR + 0x001f: 0x001f, # UNIT SEPARATOR + 0x0020: 0x0020, # SPACE + 0x0021: 0x0021, # EXCLAMATION MARK + 0x0022: 0x0022, # QUOTATION MARK + 0x0023: 0x0023, # NUMBER SIGN + 0x0024: 0x0024, # DOLLAR SIGN + 0x0026: 0x0026, # AMPERSAND + 0x0027: 0x0027, # APOSTROPHE + 0x0028: 0x0028, # LEFT PARENTHESIS + 0x0029: 0x0029, # RIGHT PARENTHESIS + 0x002a: 0x002a, # ASTERISK + 0x002b: 0x002b, # PLUS SIGN + 0x002c: 0x002c, # COMMA + 0x002d: 0x002d, # HYPHEN-MINUS + 0x002e: 0x002e, # FULL STOP + 0x002f: 0x002f, # SOLIDUS + 0x0030: 0x0030, # DIGIT ZERO + 0x0031: 0x0031, # DIGIT ONE + 0x0032: 0x0032, # DIGIT TWO + 0x0033: 0x0033, # DIGIT THREE + 0x0034: 0x0034, # DIGIT FOUR + 0x0035: 0x0035, # DIGIT FIVE + 0x0036: 0x0036, # DIGIT SIX + 0x0037: 0x0037, # DIGIT SEVEN + 0x0038: 0x0038, # DIGIT EIGHT + 0x0039: 0x0039, # DIGIT NINE + 0x003a: 0x003a, # COLON + 0x003b: 0x003b, # SEMICOLON + 0x003c: 0x003c, # LESS-THAN SIGN + 0x003d: 0x003d, # EQUALS SIGN + 0x003e: 0x003e, # GREATER-THAN SIGN + 0x003f: 0x003f, # QUESTION MARK + 0x0040: 0x0040, # COMMERCIAL AT + 0x0041: 0x0041, # LATIN CAPITAL LETTER A + 0x0042: 0x0042, # LATIN CAPITAL LETTER B + 0x0043: 0x0043, # LATIN CAPITAL LETTER C + 0x0044: 0x0044, # LATIN CAPITAL LETTER D + 0x0045: 0x0045, # LATIN CAPITAL LETTER E + 0x0046: 0x0046, # LATIN CAPITAL LETTER F + 0x0047: 0x0047, # LATIN CAPITAL LETTER G + 0x0048: 0x0048, # LATIN CAPITAL LETTER H + 0x0049: 0x0049, # LATIN CAPITAL LETTER I + 0x004a: 0x004a, # LATIN CAPITAL LETTER J + 0x004b: 0x004b, # LATIN CAPITAL LETTER K + 0x004c: 0x004c, # LATIN CAPITAL LETTER L + 0x004d: 0x004d, # LATIN CAPITAL LETTER M + 0x004e: 0x004e, # LATIN CAPITAL LETTER N + 0x004f: 0x004f, # LATIN CAPITAL LETTER O + 0x0050: 0x0050, # LATIN CAPITAL LETTER P + 0x0051: 0x0051, # LATIN CAPITAL LETTER Q + 0x0052: 0x0052, # LATIN CAPITAL LETTER R + 0x0053: 0x0053, # LATIN CAPITAL LETTER S + 0x0054: 0x0054, # LATIN CAPITAL LETTER T + 0x0055: 0x0055, # LATIN CAPITAL LETTER U + 0x0056: 0x0056, # LATIN CAPITAL LETTER V + 0x0057: 0x0057, # LATIN CAPITAL LETTER W + 0x0058: 0x0058, # LATIN CAPITAL LETTER X + 0x0059: 0x0059, # LATIN CAPITAL LETTER Y + 0x005a: 0x005a, # LATIN CAPITAL LETTER Z + 0x005b: 0x005b, # LEFT SQUARE BRACKET + 0x005c: 0x005c, # REVERSE SOLIDUS + 0x005d: 0x005d, # RIGHT SQUARE BRACKET + 0x005e: 0x005e, # CIRCUMFLEX ACCENT + 0x005f: 0x005f, # LOW LINE + 0x0060: 0x0060, # GRAVE ACCENT + 0x0061: 0x0061, # LATIN SMALL LETTER A + 0x0062: 0x0062, # LATIN SMALL LETTER B + 0x0063: 0x0063, # LATIN SMALL LETTER C + 0x0064: 0x0064, # LATIN SMALL LETTER D + 0x0065: 0x0065, # LATIN SMALL LETTER E + 0x0066: 0x0066, # LATIN SMALL LETTER F + 0x0067: 0x0067, # LATIN SMALL LETTER G + 0x0068: 0x0068, # LATIN SMALL LETTER H + 0x0069: 0x0069, # LATIN SMALL LETTER I + 0x006a: 0x006a, # LATIN SMALL LETTER J + 0x006b: 0x006b, # LATIN SMALL LETTER K + 0x006c: 0x006c, # LATIN SMALL LETTER L + 0x006d: 0x006d, # LATIN SMALL LETTER M + 0x006e: 0x006e, # LATIN SMALL LETTER N + 0x006f: 0x006f, # LATIN SMALL LETTER O + 0x0070: 0x0070, # LATIN SMALL LETTER P + 0x0071: 0x0071, # LATIN SMALL LETTER Q + 0x0072: 0x0072, # LATIN SMALL LETTER R + 0x0073: 0x0073, # LATIN SMALL LETTER S + 0x0074: 0x0074, # LATIN SMALL LETTER T + 0x0075: 0x0075, # LATIN SMALL LETTER U + 0x0076: 0x0076, # LATIN SMALL LETTER V + 0x0077: 0x0077, # LATIN SMALL LETTER W + 0x0078: 0x0078, # LATIN SMALL LETTER X + 0x0079: 0x0079, # LATIN SMALL LETTER Y + 0x007a: 0x007a, # LATIN SMALL LETTER Z + 0x007b: 0x007b, # LEFT CURLY BRACKET + 0x007c: 0x007c, # VERTICAL LINE + 0x007d: 0x007d, # RIGHT CURLY BRACKET + 0x007e: 0x007e, # TILDE + 0x007f: 0x007f, # DELETE + 0x00a0: 0x00a0, # NON-BREAKING SPACE + 0x00a2: 0x00c0, # CENT SIGN + 0x00a3: 0x00a3, # POUND SIGN + 0x00a4: 0x00a4, # CURRENCY SIGN + 0x00a6: 0x00db, # BROKEN VERTICAL BAR + 0x00ab: 0x0097, # LEFT POINTING GUILLEMET + 0x00ac: 0x00dc, # NOT SIGN + 0x00ad: 0x00a1, # SOFT HYPHEN + 0x00b0: 0x0080, # DEGREE SIGN + 0x00b1: 0x0093, # PLUS-OR-MINUS SIGN + 0x00b7: 0x0081, # MIDDLE DOT + 0x00bb: 0x0098, # RIGHT POINTING GUILLEMET + 0x00bc: 0x0095, # FRACTION 1/4 + 0x00bd: 0x0094, # FRACTION 1/2 + 0x00d7: 0x00de, # MULTIPLICATION SIGN + 0x00f7: 0x00dd, # DIVISION SIGN + 0x03b2: 0x0090, # GREEK SMALL BETA + 0x03c6: 0x0092, # GREEK SMALL PHI + 0x060c: 0x00ac, # ARABIC COMMA + 0x061b: 0x00bb, # ARABIC SEMICOLON + 0x061f: 0x00bf, # ARABIC QUESTION MARK + 0x0640: 0x00e0, # ARABIC TATWEEL + 0x0651: 0x00f1, # ARABIC SHADDAH + 0x0660: 0x00b0, # ARABIC-INDIC DIGIT ZERO + 0x0661: 0x00b1, # ARABIC-INDIC DIGIT ONE + 0x0662: 0x00b2, # ARABIC-INDIC DIGIT TWO + 0x0663: 0x00b3, # ARABIC-INDIC DIGIT THREE + 0x0664: 0x00b4, # ARABIC-INDIC DIGIT FOUR + 0x0665: 0x00b5, # ARABIC-INDIC DIGIT FIVE + 0x0666: 0x00b6, # ARABIC-INDIC DIGIT SIX + 0x0667: 0x00b7, # ARABIC-INDIC DIGIT SEVEN + 0x0668: 0x00b8, # ARABIC-INDIC DIGIT EIGHT + 0x0669: 0x00b9, # ARABIC-INDIC DIGIT NINE + 0x066a: 0x0025, # ARABIC PERCENT SIGN + 0x2219: 0x0082, # BULLET OPERATOR + 0x221a: 0x0083, # SQUARE ROOT + 0x221e: 0x0091, # INFINITY + 0x2248: 0x0096, # ALMOST EQUAL TO + 0x2500: 0x0085, # FORMS LIGHT HORIZONTAL + 0x2502: 0x0086, # FORMS LIGHT VERTICAL + 0x250c: 0x008d, # FORMS LIGHT DOWN AND RIGHT + 0x2510: 0x008c, # FORMS LIGHT DOWN AND LEFT + 0x2514: 0x008e, # FORMS LIGHT UP AND RIGHT + 0x2518: 0x008f, # FORMS LIGHT UP AND LEFT + 0x251c: 0x008a, # FORMS LIGHT VERTICAL AND RIGHT + 0x2524: 0x0088, # FORMS LIGHT VERTICAL AND LEFT + 0x252c: 0x0089, # FORMS LIGHT DOWN AND HORIZONTAL + 0x2534: 0x008b, # FORMS LIGHT UP AND HORIZONTAL + 0x253c: 0x0087, # FORMS LIGHT VERTICAL AND HORIZONTAL + 0x2592: 0x0084, # MEDIUM SHADE + 0x25a0: 0x00fe, # BLACK SQUARE + 0xfe7d: 0x00f0, # ARABIC SHADDA MEDIAL FORM + 0xfe80: 0x00c1, # ARABIC LETTER HAMZA ISOLATED FORM + 0xfe81: 0x00c2, # ARABIC LETTER ALEF WITH MADDA ABOVE ISOLATED FORM + 0xfe82: 0x00a2, # ARABIC LETTER ALEF WITH MADDA ABOVE FINAL FORM + 0xfe83: 0x00c3, # ARABIC LETTER ALEF WITH HAMZA ABOVE ISOLATED FORM + 0xfe84: 0x00a5, # ARABIC LETTER ALEF WITH HAMZA ABOVE FINAL FORM + 0xfe85: 0x00c4, # ARABIC LETTER WAW WITH HAMZA ABOVE ISOLATED FORM + 0xfe8b: 0x00c6, # ARABIC LETTER YEH WITH HAMZA ABOVE INITIAL FORM + 0xfe8d: 0x00c7, # ARABIC LETTER ALEF ISOLATED FORM + 0xfe8e: 0x00a8, # ARABIC LETTER ALEF FINAL FORM + 0xfe8f: 0x00a9, # ARABIC LETTER BEH ISOLATED FORM + 0xfe91: 0x00c8, # ARABIC LETTER BEH INITIAL FORM + 0xfe93: 0x00c9, # ARABIC LETTER TEH MARBUTA ISOLATED FORM + 0xfe95: 0x00aa, # ARABIC LETTER TEH ISOLATED FORM + 0xfe97: 0x00ca, # ARABIC LETTER TEH INITIAL FORM + 0xfe99: 0x00ab, # ARABIC LETTER THEH ISOLATED FORM + 0xfe9b: 0x00cb, # ARABIC LETTER THEH INITIAL FORM + 0xfe9d: 0x00ad, # ARABIC LETTER JEEM ISOLATED FORM + 0xfe9f: 0x00cc, # ARABIC LETTER JEEM INITIAL FORM + 0xfea1: 0x00ae, # ARABIC LETTER HAH ISOLATED FORM + 0xfea3: 0x00cd, # ARABIC LETTER HAH INITIAL FORM + 0xfea5: 0x00af, # ARABIC LETTER KHAH ISOLATED FORM + 0xfea7: 0x00ce, # ARABIC LETTER KHAH INITIAL FORM + 0xfea9: 0x00cf, # ARABIC LETTER DAL ISOLATED FORM + 0xfeab: 0x00d0, # ARABIC LETTER THAL ISOLATED FORM + 0xfead: 0x00d1, # ARABIC LETTER REH ISOLATED FORM + 0xfeaf: 0x00d2, # ARABIC LETTER ZAIN ISOLATED FORM + 0xfeb1: 0x00bc, # ARABIC LETTER SEEN ISOLATED FORM + 0xfeb3: 0x00d3, # ARABIC LETTER SEEN INITIAL FORM + 0xfeb5: 0x00bd, # ARABIC LETTER SHEEN ISOLATED FORM + 0xfeb7: 0x00d4, # ARABIC LETTER SHEEN INITIAL FORM + 0xfeb9: 0x00be, # ARABIC LETTER SAD ISOLATED FORM + 0xfebb: 0x00d5, # ARABIC LETTER SAD INITIAL FORM + 0xfebd: 0x00eb, # ARABIC LETTER DAD ISOLATED FORM + 0xfebf: 0x00d6, # ARABIC LETTER DAD INITIAL FORM + 0xfec1: 0x00d7, # ARABIC LETTER TAH ISOLATED FORM + 0xfec5: 0x00d8, # ARABIC LETTER ZAH ISOLATED FORM + 0xfec9: 0x00df, # ARABIC LETTER AIN ISOLATED FORM + 0xfeca: 0x00c5, # ARABIC LETTER AIN FINAL FORM + 0xfecb: 0x00d9, # ARABIC LETTER AIN INITIAL FORM + 0xfecc: 0x00ec, # ARABIC LETTER AIN MEDIAL FORM + 0xfecd: 0x00ee, # ARABIC LETTER GHAIN ISOLATED FORM + 0xfece: 0x00ed, # ARABIC LETTER GHAIN FINAL FORM + 0xfecf: 0x00da, # ARABIC LETTER GHAIN INITIAL FORM + 0xfed0: 0x00f7, # ARABIC LETTER GHAIN MEDIAL FORM + 0xfed1: 0x00ba, # ARABIC LETTER FEH ISOLATED FORM + 0xfed3: 0x00e1, # ARABIC LETTER FEH INITIAL FORM + 0xfed5: 0x00f8, # ARABIC LETTER QAF ISOLATED FORM + 0xfed7: 0x00e2, # ARABIC LETTER QAF INITIAL FORM + 0xfed9: 0x00fc, # ARABIC LETTER KAF ISOLATED FORM + 0xfedb: 0x00e3, # ARABIC LETTER KAF INITIAL FORM + 0xfedd: 0x00fb, # ARABIC LETTER LAM ISOLATED FORM + 0xfedf: 0x00e4, # ARABIC LETTER LAM INITIAL FORM + 0xfee1: 0x00ef, # ARABIC LETTER MEEM ISOLATED FORM + 0xfee3: 0x00e5, # ARABIC LETTER MEEM INITIAL FORM + 0xfee5: 0x00f2, # ARABIC LETTER NOON ISOLATED FORM + 0xfee7: 0x00e6, # ARABIC LETTER NOON INITIAL FORM + 0xfee9: 0x00f3, # ARABIC LETTER HEH ISOLATED FORM + 0xfeeb: 0x00e7, # ARABIC LETTER HEH INITIAL FORM + 0xfeec: 0x00f4, # ARABIC LETTER HEH MEDIAL FORM + 0xfeed: 0x00e8, # ARABIC LETTER WAW ISOLATED FORM + 0xfeef: 0x00e9, # ARABIC LETTER ALEF MAKSURA ISOLATED FORM + 0xfef0: 0x00f5, # ARABIC LETTER ALEF MAKSURA FINAL FORM + 0xfef1: 0x00fd, # ARABIC LETTER YEH ISOLATED FORM + 0xfef2: 0x00f6, # ARABIC LETTER YEH FINAL FORM + 0xfef3: 0x00ea, # ARABIC LETTER YEH INITIAL FORM + 0xfef5: 0x00f9, # ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE ISOLATED FORM + 0xfef6: 0x00fa, # ARABIC LIGATURE LAM WITH ALEF WITH MADDA ABOVE FINAL FORM + 0xfef7: 0x0099, # ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE ISOLATED FORM + 0xfef8: 0x009a, # ARABIC LIGATURE LAM WITH ALEF WITH HAMZA ABOVE FINAL FORM + 0xfefb: 0x009d, # ARABIC LIGATURE LAM WITH ALEF ISOLATED FORM + 0xfefc: 0x009e, # ARABIC LIGATURE LAM WITH ALEF FINAL FORM +} diff --git a/contrib/tools/python3/src/Lib/encodings/cp865.py b/contrib/tools/python3/src/Lib/encodings/cp865.py new file mode 100644 index 0000000000..6726cf3f9e --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp865.py @@ -0,0 +1,698 @@ +""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP865.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_map) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp865', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + +### Decoding Map + +decoding_map = codecs.make_identity_dict(range(256)) +decoding_map.update({ + 0x0080: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x0081: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS + 0x0082: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE + 0x0083: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x0084: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x0085: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE + 0x0086: 0x00e5, # LATIN SMALL LETTER A WITH RING ABOVE + 0x0087: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA + 0x0088: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x0089: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS + 0x008a: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE + 0x008b: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS + 0x008c: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x008d: 0x00ec, # LATIN SMALL LETTER I WITH GRAVE + 0x008e: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x008f: 0x00c5, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x0090: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x0091: 0x00e6, # LATIN SMALL LIGATURE AE + 0x0092: 0x00c6, # LATIN CAPITAL LIGATURE AE + 0x0093: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x0094: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x0095: 0x00f2, # LATIN SMALL LETTER O WITH GRAVE + 0x0096: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x0097: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE + 0x0098: 0x00ff, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x0099: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x009a: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x009b: 0x00f8, # LATIN SMALL LETTER O WITH STROKE + 0x009c: 0x00a3, # POUND SIGN + 0x009d: 0x00d8, # LATIN CAPITAL LETTER O WITH STROKE + 0x009e: 0x20a7, # PESETA SIGN + 0x009f: 0x0192, # LATIN SMALL LETTER F WITH HOOK + 0x00a0: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE + 0x00a1: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE + 0x00a2: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE + 0x00a3: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE + 0x00a4: 0x00f1, # LATIN SMALL LETTER N WITH TILDE + 0x00a5: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE + 0x00a6: 0x00aa, # FEMININE ORDINAL INDICATOR + 0x00a7: 0x00ba, # MASCULINE ORDINAL INDICATOR + 0x00a8: 0x00bf, # INVERTED QUESTION MARK + 0x00a9: 0x2310, # REVERSED NOT SIGN + 0x00aa: 0x00ac, # NOT SIGN + 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF + 0x00ac: 0x00bc, # VULGAR FRACTION ONE QUARTER + 0x00ad: 0x00a1, # INVERTED EXCLAMATION MARK + 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00af: 0x00a4, # CURRENCY SIGN + 0x00b0: 0x2591, # LIGHT SHADE + 0x00b1: 0x2592, # MEDIUM SHADE + 0x00b2: 0x2593, # DARK SHADE + 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL + 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL + 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL + 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT + 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x00db: 0x2588, # FULL BLOCK + 0x00dc: 0x2584, # LOWER HALF BLOCK + 0x00dd: 0x258c, # LEFT HALF BLOCK + 0x00de: 0x2590, # RIGHT HALF BLOCK + 0x00df: 0x2580, # UPPER HALF BLOCK + 0x00e0: 0x03b1, # GREEK SMALL LETTER ALPHA + 0x00e1: 0x00df, # LATIN SMALL LETTER SHARP S + 0x00e2: 0x0393, # GREEK CAPITAL LETTER GAMMA + 0x00e3: 0x03c0, # GREEK SMALL LETTER PI + 0x00e4: 0x03a3, # GREEK CAPITAL LETTER SIGMA + 0x00e5: 0x03c3, # GREEK SMALL LETTER SIGMA + 0x00e6: 0x00b5, # MICRO SIGN + 0x00e7: 0x03c4, # GREEK SMALL LETTER TAU + 0x00e8: 0x03a6, # GREEK CAPITAL LETTER PHI + 0x00e9: 0x0398, # GREEK CAPITAL LETTER THETA + 0x00ea: 0x03a9, # GREEK CAPITAL LETTER OMEGA + 0x00eb: 0x03b4, # GREEK SMALL LETTER DELTA + 0x00ec: 0x221e, # INFINITY + 0x00ed: 0x03c6, # GREEK SMALL LETTER PHI + 0x00ee: 0x03b5, # GREEK SMALL LETTER EPSILON + 0x00ef: 0x2229, # INTERSECTION + 0x00f0: 0x2261, # IDENTICAL TO + 0x00f1: 0x00b1, # PLUS-MINUS SIGN + 0x00f2: 0x2265, # GREATER-THAN OR EQUAL TO + 0x00f3: 0x2264, # LESS-THAN OR EQUAL TO + 0x00f4: 0x2320, # TOP HALF INTEGRAL + 0x00f5: 0x2321, # BOTTOM HALF INTEGRAL + 0x00f6: 0x00f7, # DIVISION SIGN + 0x00f7: 0x2248, # ALMOST EQUAL TO + 0x00f8: 0x00b0, # DEGREE SIGN + 0x00f9: 0x2219, # BULLET OPERATOR + 0x00fa: 0x00b7, # MIDDLE DOT + 0x00fb: 0x221a, # SQUARE ROOT + 0x00fc: 0x207f, # SUPERSCRIPT LATIN SMALL LETTER N + 0x00fd: 0x00b2, # SUPERSCRIPT TWO + 0x00fe: 0x25a0, # BLACK SQUARE + 0x00ff: 0x00a0, # NO-BREAK SPACE +}) + +### Decoding Table + +decoding_table = ( + '\x00' # 0x0000 -> NULL + '\x01' # 0x0001 -> START OF HEADING + '\x02' # 0x0002 -> START OF TEXT + '\x03' # 0x0003 -> END OF TEXT + '\x04' # 0x0004 -> END OF TRANSMISSION + '\x05' # 0x0005 -> ENQUIRY + '\x06' # 0x0006 -> ACKNOWLEDGE + '\x07' # 0x0007 -> BELL + '\x08' # 0x0008 -> BACKSPACE + '\t' # 0x0009 -> HORIZONTAL TABULATION + '\n' # 0x000a -> LINE FEED + '\x0b' # 0x000b -> VERTICAL TABULATION + '\x0c' # 0x000c -> FORM FEED + '\r' # 0x000d -> CARRIAGE RETURN + '\x0e' # 0x000e -> SHIFT OUT + '\x0f' # 0x000f -> SHIFT IN + '\x10' # 0x0010 -> DATA LINK ESCAPE + '\x11' # 0x0011 -> DEVICE CONTROL ONE + '\x12' # 0x0012 -> DEVICE CONTROL TWO + '\x13' # 0x0013 -> DEVICE CONTROL THREE + '\x14' # 0x0014 -> DEVICE CONTROL FOUR + '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x0016 -> SYNCHRONOUS IDLE + '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK + '\x18' # 0x0018 -> CANCEL + '\x19' # 0x0019 -> END OF MEDIUM + '\x1a' # 0x001a -> SUBSTITUTE + '\x1b' # 0x001b -> ESCAPE + '\x1c' # 0x001c -> FILE SEPARATOR + '\x1d' # 0x001d -> GROUP SEPARATOR + '\x1e' # 0x001e -> RECORD SEPARATOR + '\x1f' # 0x001f -> UNIT SEPARATOR + ' ' # 0x0020 -> SPACE + '!' # 0x0021 -> EXCLAMATION MARK + '"' # 0x0022 -> QUOTATION MARK + '#' # 0x0023 -> NUMBER SIGN + '$' # 0x0024 -> DOLLAR SIGN + '%' # 0x0025 -> PERCENT SIGN + '&' # 0x0026 -> AMPERSAND + "'" # 0x0027 -> APOSTROPHE + '(' # 0x0028 -> LEFT PARENTHESIS + ')' # 0x0029 -> RIGHT PARENTHESIS + '*' # 0x002a -> ASTERISK + '+' # 0x002b -> PLUS SIGN + ',' # 0x002c -> COMMA + '-' # 0x002d -> HYPHEN-MINUS + '.' # 0x002e -> FULL STOP + '/' # 0x002f -> SOLIDUS + '0' # 0x0030 -> DIGIT ZERO + '1' # 0x0031 -> DIGIT ONE + '2' # 0x0032 -> DIGIT TWO + '3' # 0x0033 -> DIGIT THREE + '4' # 0x0034 -> DIGIT FOUR + '5' # 0x0035 -> DIGIT FIVE + '6' # 0x0036 -> DIGIT SIX + '7' # 0x0037 -> DIGIT SEVEN + '8' # 0x0038 -> DIGIT EIGHT + '9' # 0x0039 -> DIGIT NINE + ':' # 0x003a -> COLON + ';' # 0x003b -> SEMICOLON + '<' # 0x003c -> LESS-THAN SIGN + '=' # 0x003d -> EQUALS SIGN + '>' # 0x003e -> GREATER-THAN SIGN + '?' # 0x003f -> QUESTION MARK + '@' # 0x0040 -> COMMERCIAL AT + 'A' # 0x0041 -> LATIN CAPITAL LETTER A + 'B' # 0x0042 -> LATIN CAPITAL LETTER B + 'C' # 0x0043 -> LATIN CAPITAL LETTER C + 'D' # 0x0044 -> LATIN CAPITAL LETTER D + 'E' # 0x0045 -> LATIN CAPITAL LETTER E + 'F' # 0x0046 -> LATIN CAPITAL LETTER F + 'G' # 0x0047 -> LATIN CAPITAL LETTER G + 'H' # 0x0048 -> LATIN CAPITAL LETTER H + 'I' # 0x0049 -> LATIN CAPITAL LETTER I + 'J' # 0x004a -> LATIN CAPITAL LETTER J + 'K' # 0x004b -> LATIN CAPITAL LETTER K + 'L' # 0x004c -> LATIN CAPITAL LETTER L + 'M' # 0x004d -> LATIN CAPITAL LETTER M + 'N' # 0x004e -> LATIN CAPITAL LETTER N + 'O' # 0x004f -> LATIN CAPITAL LETTER O + 'P' # 0x0050 -> LATIN CAPITAL LETTER P + 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q + 'R' # 0x0052 -> LATIN CAPITAL LETTER R + 'S' # 0x0053 -> LATIN CAPITAL LETTER S + 'T' # 0x0054 -> LATIN CAPITAL LETTER T + 'U' # 0x0055 -> LATIN CAPITAL LETTER U + 'V' # 0x0056 -> LATIN CAPITAL LETTER V + 'W' # 0x0057 -> LATIN CAPITAL LETTER W + 'X' # 0x0058 -> LATIN CAPITAL LETTER X + 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y + 'Z' # 0x005a -> LATIN CAPITAL LETTER Z + '[' # 0x005b -> LEFT SQUARE BRACKET + '\\' # 0x005c -> REVERSE SOLIDUS + ']' # 0x005d -> RIGHT SQUARE BRACKET + '^' # 0x005e -> CIRCUMFLEX ACCENT + '_' # 0x005f -> LOW LINE + '`' # 0x0060 -> GRAVE ACCENT + 'a' # 0x0061 -> LATIN SMALL LETTER A + 'b' # 0x0062 -> LATIN SMALL LETTER B + 'c' # 0x0063 -> LATIN SMALL LETTER C + 'd' # 0x0064 -> LATIN SMALL LETTER D + 'e' # 0x0065 -> LATIN SMALL LETTER E + 'f' # 0x0066 -> LATIN SMALL LETTER F + 'g' # 0x0067 -> LATIN SMALL LETTER G + 'h' # 0x0068 -> LATIN SMALL LETTER H + 'i' # 0x0069 -> LATIN SMALL LETTER I + 'j' # 0x006a -> LATIN SMALL LETTER J + 'k' # 0x006b -> LATIN SMALL LETTER K + 'l' # 0x006c -> LATIN SMALL LETTER L + 'm' # 0x006d -> LATIN SMALL LETTER M + 'n' # 0x006e -> LATIN SMALL LETTER N + 'o' # 0x006f -> LATIN SMALL LETTER O + 'p' # 0x0070 -> LATIN SMALL LETTER P + 'q' # 0x0071 -> LATIN SMALL LETTER Q + 'r' # 0x0072 -> LATIN SMALL LETTER R + 's' # 0x0073 -> LATIN SMALL LETTER S + 't' # 0x0074 -> LATIN SMALL LETTER T + 'u' # 0x0075 -> LATIN SMALL LETTER U + 'v' # 0x0076 -> LATIN SMALL LETTER V + 'w' # 0x0077 -> LATIN SMALL LETTER W + 'x' # 0x0078 -> LATIN SMALL LETTER X + 'y' # 0x0079 -> LATIN SMALL LETTER Y + 'z' # 0x007a -> LATIN SMALL LETTER Z + '{' # 0x007b -> LEFT CURLY BRACKET + '|' # 0x007c -> VERTICAL LINE + '}' # 0x007d -> RIGHT CURLY BRACKET + '~' # 0x007e -> TILDE + '\x7f' # 0x007f -> DELETE + '\xc7' # 0x0080 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xfc' # 0x0081 -> LATIN SMALL LETTER U WITH DIAERESIS + '\xe9' # 0x0082 -> LATIN SMALL LETTER E WITH ACUTE + '\xe2' # 0x0083 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe4' # 0x0084 -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe0' # 0x0085 -> LATIN SMALL LETTER A WITH GRAVE + '\xe5' # 0x0086 -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe7' # 0x0087 -> LATIN SMALL LETTER C WITH CEDILLA + '\xea' # 0x0088 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0x0089 -> LATIN SMALL LETTER E WITH DIAERESIS + '\xe8' # 0x008a -> LATIN SMALL LETTER E WITH GRAVE + '\xef' # 0x008b -> LATIN SMALL LETTER I WITH DIAERESIS + '\xee' # 0x008c -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xec' # 0x008d -> LATIN SMALL LETTER I WITH GRAVE + '\xc4' # 0x008e -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0x008f -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc9' # 0x0090 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xe6' # 0x0091 -> LATIN SMALL LIGATURE AE + '\xc6' # 0x0092 -> LATIN CAPITAL LIGATURE AE + '\xf4' # 0x0093 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf6' # 0x0094 -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf2' # 0x0095 -> LATIN SMALL LETTER O WITH GRAVE + '\xfb' # 0x0096 -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xf9' # 0x0097 -> LATIN SMALL LETTER U WITH GRAVE + '\xff' # 0x0098 -> LATIN SMALL LETTER Y WITH DIAERESIS + '\xd6' # 0x0099 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xdc' # 0x009a -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xf8' # 0x009b -> LATIN SMALL LETTER O WITH STROKE + '\xa3' # 0x009c -> POUND SIGN + '\xd8' # 0x009d -> LATIN CAPITAL LETTER O WITH STROKE + '\u20a7' # 0x009e -> PESETA SIGN + '\u0192' # 0x009f -> LATIN SMALL LETTER F WITH HOOK + '\xe1' # 0x00a0 -> LATIN SMALL LETTER A WITH ACUTE + '\xed' # 0x00a1 -> LATIN SMALL LETTER I WITH ACUTE + '\xf3' # 0x00a2 -> LATIN SMALL LETTER O WITH ACUTE + '\xfa' # 0x00a3 -> LATIN SMALL LETTER U WITH ACUTE + '\xf1' # 0x00a4 -> LATIN SMALL LETTER N WITH TILDE + '\xd1' # 0x00a5 -> LATIN CAPITAL LETTER N WITH TILDE + '\xaa' # 0x00a6 -> FEMININE ORDINAL INDICATOR + '\xba' # 0x00a7 -> MASCULINE ORDINAL INDICATOR + '\xbf' # 0x00a8 -> INVERTED QUESTION MARK + '\u2310' # 0x00a9 -> REVERSED NOT SIGN + '\xac' # 0x00aa -> NOT SIGN + '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF + '\xbc' # 0x00ac -> VULGAR FRACTION ONE QUARTER + '\xa1' # 0x00ad -> INVERTED EXCLAMATION MARK + '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xa4' # 0x00af -> CURRENCY SIGN + '\u2591' # 0x00b0 -> LIGHT SHADE + '\u2592' # 0x00b1 -> MEDIUM SHADE + '\u2593' # 0x00b2 -> DARK SHADE + '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL + '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT + '\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + '\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + '\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + '\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL + '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT + '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT + '\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + '\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT + '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT + '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL + '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT + '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL + '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + '\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + '\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT + '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL + '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + '\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + '\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + '\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + '\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + '\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + '\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + '\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + '\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + '\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + '\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT + '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT + '\u2588' # 0x00db -> FULL BLOCK + '\u2584' # 0x00dc -> LOWER HALF BLOCK + '\u258c' # 0x00dd -> LEFT HALF BLOCK + '\u2590' # 0x00de -> RIGHT HALF BLOCK + '\u2580' # 0x00df -> UPPER HALF BLOCK + '\u03b1' # 0x00e0 -> GREEK SMALL LETTER ALPHA + '\xdf' # 0x00e1 -> LATIN SMALL LETTER SHARP S + '\u0393' # 0x00e2 -> GREEK CAPITAL LETTER GAMMA + '\u03c0' # 0x00e3 -> GREEK SMALL LETTER PI + '\u03a3' # 0x00e4 -> GREEK CAPITAL LETTER SIGMA + '\u03c3' # 0x00e5 -> GREEK SMALL LETTER SIGMA + '\xb5' # 0x00e6 -> MICRO SIGN + '\u03c4' # 0x00e7 -> GREEK SMALL LETTER TAU + '\u03a6' # 0x00e8 -> GREEK CAPITAL LETTER PHI + '\u0398' # 0x00e9 -> GREEK CAPITAL LETTER THETA + '\u03a9' # 0x00ea -> GREEK CAPITAL LETTER OMEGA + '\u03b4' # 0x00eb -> GREEK SMALL LETTER DELTA + '\u221e' # 0x00ec -> INFINITY + '\u03c6' # 0x00ed -> GREEK SMALL LETTER PHI + '\u03b5' # 0x00ee -> GREEK SMALL LETTER EPSILON + '\u2229' # 0x00ef -> INTERSECTION + '\u2261' # 0x00f0 -> IDENTICAL TO + '\xb1' # 0x00f1 -> PLUS-MINUS SIGN + '\u2265' # 0x00f2 -> GREATER-THAN OR EQUAL TO + '\u2264' # 0x00f3 -> LESS-THAN OR EQUAL TO + '\u2320' # 0x00f4 -> TOP HALF INTEGRAL + '\u2321' # 0x00f5 -> BOTTOM HALF INTEGRAL + '\xf7' # 0x00f6 -> DIVISION SIGN + '\u2248' # 0x00f7 -> ALMOST EQUAL TO + '\xb0' # 0x00f8 -> DEGREE SIGN + '\u2219' # 0x00f9 -> BULLET OPERATOR + '\xb7' # 0x00fa -> MIDDLE DOT + '\u221a' # 0x00fb -> SQUARE ROOT + '\u207f' # 0x00fc -> SUPERSCRIPT LATIN SMALL LETTER N + '\xb2' # 0x00fd -> SUPERSCRIPT TWO + '\u25a0' # 0x00fe -> BLACK SQUARE + '\xa0' # 0x00ff -> NO-BREAK SPACE +) + +### Encoding Map + +encoding_map = { + 0x0000: 0x0000, # NULL + 0x0001: 0x0001, # START OF HEADING + 0x0002: 0x0002, # START OF TEXT + 0x0003: 0x0003, # END OF TEXT + 0x0004: 0x0004, # END OF TRANSMISSION + 0x0005: 0x0005, # ENQUIRY + 0x0006: 0x0006, # ACKNOWLEDGE + 0x0007: 0x0007, # BELL + 0x0008: 0x0008, # BACKSPACE + 0x0009: 0x0009, # HORIZONTAL TABULATION + 0x000a: 0x000a, # LINE FEED + 0x000b: 0x000b, # VERTICAL TABULATION + 0x000c: 0x000c, # FORM FEED + 0x000d: 0x000d, # CARRIAGE RETURN + 0x000e: 0x000e, # SHIFT OUT + 0x000f: 0x000f, # SHIFT IN + 0x0010: 0x0010, # DATA LINK ESCAPE + 0x0011: 0x0011, # DEVICE CONTROL ONE + 0x0012: 0x0012, # DEVICE CONTROL TWO + 0x0013: 0x0013, # DEVICE CONTROL THREE + 0x0014: 0x0014, # DEVICE CONTROL FOUR + 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE + 0x0016: 0x0016, # SYNCHRONOUS IDLE + 0x0017: 0x0017, # END OF TRANSMISSION BLOCK + 0x0018: 0x0018, # CANCEL + 0x0019: 0x0019, # END OF MEDIUM + 0x001a: 0x001a, # SUBSTITUTE + 0x001b: 0x001b, # ESCAPE + 0x001c: 0x001c, # FILE SEPARATOR + 0x001d: 0x001d, # GROUP SEPARATOR + 0x001e: 0x001e, # RECORD SEPARATOR + 0x001f: 0x001f, # UNIT SEPARATOR + 0x0020: 0x0020, # SPACE + 0x0021: 0x0021, # EXCLAMATION MARK + 0x0022: 0x0022, # QUOTATION MARK + 0x0023: 0x0023, # NUMBER SIGN + 0x0024: 0x0024, # DOLLAR SIGN + 0x0025: 0x0025, # PERCENT SIGN + 0x0026: 0x0026, # AMPERSAND + 0x0027: 0x0027, # APOSTROPHE + 0x0028: 0x0028, # LEFT PARENTHESIS + 0x0029: 0x0029, # RIGHT PARENTHESIS + 0x002a: 0x002a, # ASTERISK + 0x002b: 0x002b, # PLUS SIGN + 0x002c: 0x002c, # COMMA + 0x002d: 0x002d, # HYPHEN-MINUS + 0x002e: 0x002e, # FULL STOP + 0x002f: 0x002f, # SOLIDUS + 0x0030: 0x0030, # DIGIT ZERO + 0x0031: 0x0031, # DIGIT ONE + 0x0032: 0x0032, # DIGIT TWO + 0x0033: 0x0033, # DIGIT THREE + 0x0034: 0x0034, # DIGIT FOUR + 0x0035: 0x0035, # DIGIT FIVE + 0x0036: 0x0036, # DIGIT SIX + 0x0037: 0x0037, # DIGIT SEVEN + 0x0038: 0x0038, # DIGIT EIGHT + 0x0039: 0x0039, # DIGIT NINE + 0x003a: 0x003a, # COLON + 0x003b: 0x003b, # SEMICOLON + 0x003c: 0x003c, # LESS-THAN SIGN + 0x003d: 0x003d, # EQUALS SIGN + 0x003e: 0x003e, # GREATER-THAN SIGN + 0x003f: 0x003f, # QUESTION MARK + 0x0040: 0x0040, # COMMERCIAL AT + 0x0041: 0x0041, # LATIN CAPITAL LETTER A + 0x0042: 0x0042, # LATIN CAPITAL LETTER B + 0x0043: 0x0043, # LATIN CAPITAL LETTER C + 0x0044: 0x0044, # LATIN CAPITAL LETTER D + 0x0045: 0x0045, # LATIN CAPITAL LETTER E + 0x0046: 0x0046, # LATIN CAPITAL LETTER F + 0x0047: 0x0047, # LATIN CAPITAL LETTER G + 0x0048: 0x0048, # LATIN CAPITAL LETTER H + 0x0049: 0x0049, # LATIN CAPITAL LETTER I + 0x004a: 0x004a, # LATIN CAPITAL LETTER J + 0x004b: 0x004b, # LATIN CAPITAL LETTER K + 0x004c: 0x004c, # LATIN CAPITAL LETTER L + 0x004d: 0x004d, # LATIN CAPITAL LETTER M + 0x004e: 0x004e, # LATIN CAPITAL LETTER N + 0x004f: 0x004f, # LATIN CAPITAL LETTER O + 0x0050: 0x0050, # LATIN CAPITAL LETTER P + 0x0051: 0x0051, # LATIN CAPITAL LETTER Q + 0x0052: 0x0052, # LATIN CAPITAL LETTER R + 0x0053: 0x0053, # LATIN CAPITAL LETTER S + 0x0054: 0x0054, # LATIN CAPITAL LETTER T + 0x0055: 0x0055, # LATIN CAPITAL LETTER U + 0x0056: 0x0056, # LATIN CAPITAL LETTER V + 0x0057: 0x0057, # LATIN CAPITAL LETTER W + 0x0058: 0x0058, # LATIN CAPITAL LETTER X + 0x0059: 0x0059, # LATIN CAPITAL LETTER Y + 0x005a: 0x005a, # LATIN CAPITAL LETTER Z + 0x005b: 0x005b, # LEFT SQUARE BRACKET + 0x005c: 0x005c, # REVERSE SOLIDUS + 0x005d: 0x005d, # RIGHT SQUARE BRACKET + 0x005e: 0x005e, # CIRCUMFLEX ACCENT + 0x005f: 0x005f, # LOW LINE + 0x0060: 0x0060, # GRAVE ACCENT + 0x0061: 0x0061, # LATIN SMALL LETTER A + 0x0062: 0x0062, # LATIN SMALL LETTER B + 0x0063: 0x0063, # LATIN SMALL LETTER C + 0x0064: 0x0064, # LATIN SMALL LETTER D + 0x0065: 0x0065, # LATIN SMALL LETTER E + 0x0066: 0x0066, # LATIN SMALL LETTER F + 0x0067: 0x0067, # LATIN SMALL LETTER G + 0x0068: 0x0068, # LATIN SMALL LETTER H + 0x0069: 0x0069, # LATIN SMALL LETTER I + 0x006a: 0x006a, # LATIN SMALL LETTER J + 0x006b: 0x006b, # LATIN SMALL LETTER K + 0x006c: 0x006c, # LATIN SMALL LETTER L + 0x006d: 0x006d, # LATIN SMALL LETTER M + 0x006e: 0x006e, # LATIN SMALL LETTER N + 0x006f: 0x006f, # LATIN SMALL LETTER O + 0x0070: 0x0070, # LATIN SMALL LETTER P + 0x0071: 0x0071, # LATIN SMALL LETTER Q + 0x0072: 0x0072, # LATIN SMALL LETTER R + 0x0073: 0x0073, # LATIN SMALL LETTER S + 0x0074: 0x0074, # LATIN SMALL LETTER T + 0x0075: 0x0075, # LATIN SMALL LETTER U + 0x0076: 0x0076, # LATIN SMALL LETTER V + 0x0077: 0x0077, # LATIN SMALL LETTER W + 0x0078: 0x0078, # LATIN SMALL LETTER X + 0x0079: 0x0079, # LATIN SMALL LETTER Y + 0x007a: 0x007a, # LATIN SMALL LETTER Z + 0x007b: 0x007b, # LEFT CURLY BRACKET + 0x007c: 0x007c, # VERTICAL LINE + 0x007d: 0x007d, # RIGHT CURLY BRACKET + 0x007e: 0x007e, # TILDE + 0x007f: 0x007f, # DELETE + 0x00a0: 0x00ff, # NO-BREAK SPACE + 0x00a1: 0x00ad, # INVERTED EXCLAMATION MARK + 0x00a3: 0x009c, # POUND SIGN + 0x00a4: 0x00af, # CURRENCY SIGN + 0x00aa: 0x00a6, # FEMININE ORDINAL INDICATOR + 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00ac: 0x00aa, # NOT SIGN + 0x00b0: 0x00f8, # DEGREE SIGN + 0x00b1: 0x00f1, # PLUS-MINUS SIGN + 0x00b2: 0x00fd, # SUPERSCRIPT TWO + 0x00b5: 0x00e6, # MICRO SIGN + 0x00b7: 0x00fa, # MIDDLE DOT + 0x00ba: 0x00a7, # MASCULINE ORDINAL INDICATOR + 0x00bc: 0x00ac, # VULGAR FRACTION ONE QUARTER + 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF + 0x00bf: 0x00a8, # INVERTED QUESTION MARK + 0x00c4: 0x008e, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00c5: 0x008f, # LATIN CAPITAL LETTER A WITH RING ABOVE + 0x00c6: 0x0092, # LATIN CAPITAL LIGATURE AE + 0x00c7: 0x0080, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00c9: 0x0090, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00d1: 0x00a5, # LATIN CAPITAL LETTER N WITH TILDE + 0x00d6: 0x0099, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00d8: 0x009d, # LATIN CAPITAL LETTER O WITH STROKE + 0x00dc: 0x009a, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00df: 0x00e1, # LATIN SMALL LETTER SHARP S + 0x00e0: 0x0085, # LATIN SMALL LETTER A WITH GRAVE + 0x00e1: 0x00a0, # LATIN SMALL LETTER A WITH ACUTE + 0x00e2: 0x0083, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00e4: 0x0084, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00e5: 0x0086, # LATIN SMALL LETTER A WITH RING ABOVE + 0x00e6: 0x0091, # LATIN SMALL LIGATURE AE + 0x00e7: 0x0087, # LATIN SMALL LETTER C WITH CEDILLA + 0x00e8: 0x008a, # LATIN SMALL LETTER E WITH GRAVE + 0x00e9: 0x0082, # LATIN SMALL LETTER E WITH ACUTE + 0x00ea: 0x0088, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00eb: 0x0089, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00ec: 0x008d, # LATIN SMALL LETTER I WITH GRAVE + 0x00ed: 0x00a1, # LATIN SMALL LETTER I WITH ACUTE + 0x00ee: 0x008c, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00ef: 0x008b, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00f1: 0x00a4, # LATIN SMALL LETTER N WITH TILDE + 0x00f2: 0x0095, # LATIN SMALL LETTER O WITH GRAVE + 0x00f3: 0x00a2, # LATIN SMALL LETTER O WITH ACUTE + 0x00f4: 0x0093, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00f6: 0x0094, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00f7: 0x00f6, # DIVISION SIGN + 0x00f8: 0x009b, # LATIN SMALL LETTER O WITH STROKE + 0x00f9: 0x0097, # LATIN SMALL LETTER U WITH GRAVE + 0x00fa: 0x00a3, # LATIN SMALL LETTER U WITH ACUTE + 0x00fb: 0x0096, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00fc: 0x0081, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00ff: 0x0098, # LATIN SMALL LETTER Y WITH DIAERESIS + 0x0192: 0x009f, # LATIN SMALL LETTER F WITH HOOK + 0x0393: 0x00e2, # GREEK CAPITAL LETTER GAMMA + 0x0398: 0x00e9, # GREEK CAPITAL LETTER THETA + 0x03a3: 0x00e4, # GREEK CAPITAL LETTER SIGMA + 0x03a6: 0x00e8, # GREEK CAPITAL LETTER PHI + 0x03a9: 0x00ea, # GREEK CAPITAL LETTER OMEGA + 0x03b1: 0x00e0, # GREEK SMALL LETTER ALPHA + 0x03b4: 0x00eb, # GREEK SMALL LETTER DELTA + 0x03b5: 0x00ee, # GREEK SMALL LETTER EPSILON + 0x03c0: 0x00e3, # GREEK SMALL LETTER PI + 0x03c3: 0x00e5, # GREEK SMALL LETTER SIGMA + 0x03c4: 0x00e7, # GREEK SMALL LETTER TAU + 0x03c6: 0x00ed, # GREEK SMALL LETTER PHI + 0x207f: 0x00fc, # SUPERSCRIPT LATIN SMALL LETTER N + 0x20a7: 0x009e, # PESETA SIGN + 0x2219: 0x00f9, # BULLET OPERATOR + 0x221a: 0x00fb, # SQUARE ROOT + 0x221e: 0x00ec, # INFINITY + 0x2229: 0x00ef, # INTERSECTION + 0x2248: 0x00f7, # ALMOST EQUAL TO + 0x2261: 0x00f0, # IDENTICAL TO + 0x2264: 0x00f3, # LESS-THAN OR EQUAL TO + 0x2265: 0x00f2, # GREATER-THAN OR EQUAL TO + 0x2310: 0x00a9, # REVERSED NOT SIGN + 0x2320: 0x00f4, # TOP HALF INTEGRAL + 0x2321: 0x00f5, # BOTTOM HALF INTEGRAL + 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL + 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL + 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT + 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL + 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x2580: 0x00df, # UPPER HALF BLOCK + 0x2584: 0x00dc, # LOWER HALF BLOCK + 0x2588: 0x00db, # FULL BLOCK + 0x258c: 0x00dd, # LEFT HALF BLOCK + 0x2590: 0x00de, # RIGHT HALF BLOCK + 0x2591: 0x00b0, # LIGHT SHADE + 0x2592: 0x00b1, # MEDIUM SHADE + 0x2593: 0x00b2, # DARK SHADE + 0x25a0: 0x00fe, # BLACK SQUARE +} diff --git a/contrib/tools/python3/src/Lib/encodings/cp866.py b/contrib/tools/python3/src/Lib/encodings/cp866.py new file mode 100644 index 0000000000..bec7ae39fb --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp866.py @@ -0,0 +1,698 @@ +""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP866.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_map) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp866', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + +### Decoding Map + +decoding_map = codecs.make_identity_dict(range(256)) +decoding_map.update({ + 0x0080: 0x0410, # CYRILLIC CAPITAL LETTER A + 0x0081: 0x0411, # CYRILLIC CAPITAL LETTER BE + 0x0082: 0x0412, # CYRILLIC CAPITAL LETTER VE + 0x0083: 0x0413, # CYRILLIC CAPITAL LETTER GHE + 0x0084: 0x0414, # CYRILLIC CAPITAL LETTER DE + 0x0085: 0x0415, # CYRILLIC CAPITAL LETTER IE + 0x0086: 0x0416, # CYRILLIC CAPITAL LETTER ZHE + 0x0087: 0x0417, # CYRILLIC CAPITAL LETTER ZE + 0x0088: 0x0418, # CYRILLIC CAPITAL LETTER I + 0x0089: 0x0419, # CYRILLIC CAPITAL LETTER SHORT I + 0x008a: 0x041a, # CYRILLIC CAPITAL LETTER KA + 0x008b: 0x041b, # CYRILLIC CAPITAL LETTER EL + 0x008c: 0x041c, # CYRILLIC CAPITAL LETTER EM + 0x008d: 0x041d, # CYRILLIC CAPITAL LETTER EN + 0x008e: 0x041e, # CYRILLIC CAPITAL LETTER O + 0x008f: 0x041f, # CYRILLIC CAPITAL LETTER PE + 0x0090: 0x0420, # CYRILLIC CAPITAL LETTER ER + 0x0091: 0x0421, # CYRILLIC CAPITAL LETTER ES + 0x0092: 0x0422, # CYRILLIC CAPITAL LETTER TE + 0x0093: 0x0423, # CYRILLIC CAPITAL LETTER U + 0x0094: 0x0424, # CYRILLIC CAPITAL LETTER EF + 0x0095: 0x0425, # CYRILLIC CAPITAL LETTER HA + 0x0096: 0x0426, # CYRILLIC CAPITAL LETTER TSE + 0x0097: 0x0427, # CYRILLIC CAPITAL LETTER CHE + 0x0098: 0x0428, # CYRILLIC CAPITAL LETTER SHA + 0x0099: 0x0429, # CYRILLIC CAPITAL LETTER SHCHA + 0x009a: 0x042a, # CYRILLIC CAPITAL LETTER HARD SIGN + 0x009b: 0x042b, # CYRILLIC CAPITAL LETTER YERU + 0x009c: 0x042c, # CYRILLIC CAPITAL LETTER SOFT SIGN + 0x009d: 0x042d, # CYRILLIC CAPITAL LETTER E + 0x009e: 0x042e, # CYRILLIC CAPITAL LETTER YU + 0x009f: 0x042f, # CYRILLIC CAPITAL LETTER YA + 0x00a0: 0x0430, # CYRILLIC SMALL LETTER A + 0x00a1: 0x0431, # CYRILLIC SMALL LETTER BE + 0x00a2: 0x0432, # CYRILLIC SMALL LETTER VE + 0x00a3: 0x0433, # CYRILLIC SMALL LETTER GHE + 0x00a4: 0x0434, # CYRILLIC SMALL LETTER DE + 0x00a5: 0x0435, # CYRILLIC SMALL LETTER IE + 0x00a6: 0x0436, # CYRILLIC SMALL LETTER ZHE + 0x00a7: 0x0437, # CYRILLIC SMALL LETTER ZE + 0x00a8: 0x0438, # CYRILLIC SMALL LETTER I + 0x00a9: 0x0439, # CYRILLIC SMALL LETTER SHORT I + 0x00aa: 0x043a, # CYRILLIC SMALL LETTER KA + 0x00ab: 0x043b, # CYRILLIC SMALL LETTER EL + 0x00ac: 0x043c, # CYRILLIC SMALL LETTER EM + 0x00ad: 0x043d, # CYRILLIC SMALL LETTER EN + 0x00ae: 0x043e, # CYRILLIC SMALL LETTER O + 0x00af: 0x043f, # CYRILLIC SMALL LETTER PE + 0x00b0: 0x2591, # LIGHT SHADE + 0x00b1: 0x2592, # MEDIUM SHADE + 0x00b2: 0x2593, # DARK SHADE + 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL + 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x00b5: 0x2561, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + 0x00b6: 0x2562, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + 0x00b7: 0x2556, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + 0x00b8: 0x2555, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL + 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x00bd: 0x255c, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + 0x00be: 0x255b, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL + 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x00c6: 0x255e, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + 0x00c7: 0x255f, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x00cf: 0x2567, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + 0x00d0: 0x2568, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + 0x00d1: 0x2564, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + 0x00d2: 0x2565, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + 0x00d3: 0x2559, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + 0x00d4: 0x2558, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + 0x00d5: 0x2552, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + 0x00d6: 0x2553, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + 0x00d7: 0x256b, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + 0x00d8: 0x256a, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT + 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x00db: 0x2588, # FULL BLOCK + 0x00dc: 0x2584, # LOWER HALF BLOCK + 0x00dd: 0x258c, # LEFT HALF BLOCK + 0x00de: 0x2590, # RIGHT HALF BLOCK + 0x00df: 0x2580, # UPPER HALF BLOCK + 0x00e0: 0x0440, # CYRILLIC SMALL LETTER ER + 0x00e1: 0x0441, # CYRILLIC SMALL LETTER ES + 0x00e2: 0x0442, # CYRILLIC SMALL LETTER TE + 0x00e3: 0x0443, # CYRILLIC SMALL LETTER U + 0x00e4: 0x0444, # CYRILLIC SMALL LETTER EF + 0x00e5: 0x0445, # CYRILLIC SMALL LETTER HA + 0x00e6: 0x0446, # CYRILLIC SMALL LETTER TSE + 0x00e7: 0x0447, # CYRILLIC SMALL LETTER CHE + 0x00e8: 0x0448, # CYRILLIC SMALL LETTER SHA + 0x00e9: 0x0449, # CYRILLIC SMALL LETTER SHCHA + 0x00ea: 0x044a, # CYRILLIC SMALL LETTER HARD SIGN + 0x00eb: 0x044b, # CYRILLIC SMALL LETTER YERU + 0x00ec: 0x044c, # CYRILLIC SMALL LETTER SOFT SIGN + 0x00ed: 0x044d, # CYRILLIC SMALL LETTER E + 0x00ee: 0x044e, # CYRILLIC SMALL LETTER YU + 0x00ef: 0x044f, # CYRILLIC SMALL LETTER YA + 0x00f0: 0x0401, # CYRILLIC CAPITAL LETTER IO + 0x00f1: 0x0451, # CYRILLIC SMALL LETTER IO + 0x00f2: 0x0404, # CYRILLIC CAPITAL LETTER UKRAINIAN IE + 0x00f3: 0x0454, # CYRILLIC SMALL LETTER UKRAINIAN IE + 0x00f4: 0x0407, # CYRILLIC CAPITAL LETTER YI + 0x00f5: 0x0457, # CYRILLIC SMALL LETTER YI + 0x00f6: 0x040e, # CYRILLIC CAPITAL LETTER SHORT U + 0x00f7: 0x045e, # CYRILLIC SMALL LETTER SHORT U + 0x00f8: 0x00b0, # DEGREE SIGN + 0x00f9: 0x2219, # BULLET OPERATOR + 0x00fa: 0x00b7, # MIDDLE DOT + 0x00fb: 0x221a, # SQUARE ROOT + 0x00fc: 0x2116, # NUMERO SIGN + 0x00fd: 0x00a4, # CURRENCY SIGN + 0x00fe: 0x25a0, # BLACK SQUARE + 0x00ff: 0x00a0, # NO-BREAK SPACE +}) + +### Decoding Table + +decoding_table = ( + '\x00' # 0x0000 -> NULL + '\x01' # 0x0001 -> START OF HEADING + '\x02' # 0x0002 -> START OF TEXT + '\x03' # 0x0003 -> END OF TEXT + '\x04' # 0x0004 -> END OF TRANSMISSION + '\x05' # 0x0005 -> ENQUIRY + '\x06' # 0x0006 -> ACKNOWLEDGE + '\x07' # 0x0007 -> BELL + '\x08' # 0x0008 -> BACKSPACE + '\t' # 0x0009 -> HORIZONTAL TABULATION + '\n' # 0x000a -> LINE FEED + '\x0b' # 0x000b -> VERTICAL TABULATION + '\x0c' # 0x000c -> FORM FEED + '\r' # 0x000d -> CARRIAGE RETURN + '\x0e' # 0x000e -> SHIFT OUT + '\x0f' # 0x000f -> SHIFT IN + '\x10' # 0x0010 -> DATA LINK ESCAPE + '\x11' # 0x0011 -> DEVICE CONTROL ONE + '\x12' # 0x0012 -> DEVICE CONTROL TWO + '\x13' # 0x0013 -> DEVICE CONTROL THREE + '\x14' # 0x0014 -> DEVICE CONTROL FOUR + '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x0016 -> SYNCHRONOUS IDLE + '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK + '\x18' # 0x0018 -> CANCEL + '\x19' # 0x0019 -> END OF MEDIUM + '\x1a' # 0x001a -> SUBSTITUTE + '\x1b' # 0x001b -> ESCAPE + '\x1c' # 0x001c -> FILE SEPARATOR + '\x1d' # 0x001d -> GROUP SEPARATOR + '\x1e' # 0x001e -> RECORD SEPARATOR + '\x1f' # 0x001f -> UNIT SEPARATOR + ' ' # 0x0020 -> SPACE + '!' # 0x0021 -> EXCLAMATION MARK + '"' # 0x0022 -> QUOTATION MARK + '#' # 0x0023 -> NUMBER SIGN + '$' # 0x0024 -> DOLLAR SIGN + '%' # 0x0025 -> PERCENT SIGN + '&' # 0x0026 -> AMPERSAND + "'" # 0x0027 -> APOSTROPHE + '(' # 0x0028 -> LEFT PARENTHESIS + ')' # 0x0029 -> RIGHT PARENTHESIS + '*' # 0x002a -> ASTERISK + '+' # 0x002b -> PLUS SIGN + ',' # 0x002c -> COMMA + '-' # 0x002d -> HYPHEN-MINUS + '.' # 0x002e -> FULL STOP + '/' # 0x002f -> SOLIDUS + '0' # 0x0030 -> DIGIT ZERO + '1' # 0x0031 -> DIGIT ONE + '2' # 0x0032 -> DIGIT TWO + '3' # 0x0033 -> DIGIT THREE + '4' # 0x0034 -> DIGIT FOUR + '5' # 0x0035 -> DIGIT FIVE + '6' # 0x0036 -> DIGIT SIX + '7' # 0x0037 -> DIGIT SEVEN + '8' # 0x0038 -> DIGIT EIGHT + '9' # 0x0039 -> DIGIT NINE + ':' # 0x003a -> COLON + ';' # 0x003b -> SEMICOLON + '<' # 0x003c -> LESS-THAN SIGN + '=' # 0x003d -> EQUALS SIGN + '>' # 0x003e -> GREATER-THAN SIGN + '?' # 0x003f -> QUESTION MARK + '@' # 0x0040 -> COMMERCIAL AT + 'A' # 0x0041 -> LATIN CAPITAL LETTER A + 'B' # 0x0042 -> LATIN CAPITAL LETTER B + 'C' # 0x0043 -> LATIN CAPITAL LETTER C + 'D' # 0x0044 -> LATIN CAPITAL LETTER D + 'E' # 0x0045 -> LATIN CAPITAL LETTER E + 'F' # 0x0046 -> LATIN CAPITAL LETTER F + 'G' # 0x0047 -> LATIN CAPITAL LETTER G + 'H' # 0x0048 -> LATIN CAPITAL LETTER H + 'I' # 0x0049 -> LATIN CAPITAL LETTER I + 'J' # 0x004a -> LATIN CAPITAL LETTER J + 'K' # 0x004b -> LATIN CAPITAL LETTER K + 'L' # 0x004c -> LATIN CAPITAL LETTER L + 'M' # 0x004d -> LATIN CAPITAL LETTER M + 'N' # 0x004e -> LATIN CAPITAL LETTER N + 'O' # 0x004f -> LATIN CAPITAL LETTER O + 'P' # 0x0050 -> LATIN CAPITAL LETTER P + 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q + 'R' # 0x0052 -> LATIN CAPITAL LETTER R + 'S' # 0x0053 -> LATIN CAPITAL LETTER S + 'T' # 0x0054 -> LATIN CAPITAL LETTER T + 'U' # 0x0055 -> LATIN CAPITAL LETTER U + 'V' # 0x0056 -> LATIN CAPITAL LETTER V + 'W' # 0x0057 -> LATIN CAPITAL LETTER W + 'X' # 0x0058 -> LATIN CAPITAL LETTER X + 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y + 'Z' # 0x005a -> LATIN CAPITAL LETTER Z + '[' # 0x005b -> LEFT SQUARE BRACKET + '\\' # 0x005c -> REVERSE SOLIDUS + ']' # 0x005d -> RIGHT SQUARE BRACKET + '^' # 0x005e -> CIRCUMFLEX ACCENT + '_' # 0x005f -> LOW LINE + '`' # 0x0060 -> GRAVE ACCENT + 'a' # 0x0061 -> LATIN SMALL LETTER A + 'b' # 0x0062 -> LATIN SMALL LETTER B + 'c' # 0x0063 -> LATIN SMALL LETTER C + 'd' # 0x0064 -> LATIN SMALL LETTER D + 'e' # 0x0065 -> LATIN SMALL LETTER E + 'f' # 0x0066 -> LATIN SMALL LETTER F + 'g' # 0x0067 -> LATIN SMALL LETTER G + 'h' # 0x0068 -> LATIN SMALL LETTER H + 'i' # 0x0069 -> LATIN SMALL LETTER I + 'j' # 0x006a -> LATIN SMALL LETTER J + 'k' # 0x006b -> LATIN SMALL LETTER K + 'l' # 0x006c -> LATIN SMALL LETTER L + 'm' # 0x006d -> LATIN SMALL LETTER M + 'n' # 0x006e -> LATIN SMALL LETTER N + 'o' # 0x006f -> LATIN SMALL LETTER O + 'p' # 0x0070 -> LATIN SMALL LETTER P + 'q' # 0x0071 -> LATIN SMALL LETTER Q + 'r' # 0x0072 -> LATIN SMALL LETTER R + 's' # 0x0073 -> LATIN SMALL LETTER S + 't' # 0x0074 -> LATIN SMALL LETTER T + 'u' # 0x0075 -> LATIN SMALL LETTER U + 'v' # 0x0076 -> LATIN SMALL LETTER V + 'w' # 0x0077 -> LATIN SMALL LETTER W + 'x' # 0x0078 -> LATIN SMALL LETTER X + 'y' # 0x0079 -> LATIN SMALL LETTER Y + 'z' # 0x007a -> LATIN SMALL LETTER Z + '{' # 0x007b -> LEFT CURLY BRACKET + '|' # 0x007c -> VERTICAL LINE + '}' # 0x007d -> RIGHT CURLY BRACKET + '~' # 0x007e -> TILDE + '\x7f' # 0x007f -> DELETE + '\u0410' # 0x0080 -> CYRILLIC CAPITAL LETTER A + '\u0411' # 0x0081 -> CYRILLIC CAPITAL LETTER BE + '\u0412' # 0x0082 -> CYRILLIC CAPITAL LETTER VE + '\u0413' # 0x0083 -> CYRILLIC CAPITAL LETTER GHE + '\u0414' # 0x0084 -> CYRILLIC CAPITAL LETTER DE + '\u0415' # 0x0085 -> CYRILLIC CAPITAL LETTER IE + '\u0416' # 0x0086 -> CYRILLIC CAPITAL LETTER ZHE + '\u0417' # 0x0087 -> CYRILLIC CAPITAL LETTER ZE + '\u0418' # 0x0088 -> CYRILLIC CAPITAL LETTER I + '\u0419' # 0x0089 -> CYRILLIC CAPITAL LETTER SHORT I + '\u041a' # 0x008a -> CYRILLIC CAPITAL LETTER KA + '\u041b' # 0x008b -> CYRILLIC CAPITAL LETTER EL + '\u041c' # 0x008c -> CYRILLIC CAPITAL LETTER EM + '\u041d' # 0x008d -> CYRILLIC CAPITAL LETTER EN + '\u041e' # 0x008e -> CYRILLIC CAPITAL LETTER O + '\u041f' # 0x008f -> CYRILLIC CAPITAL LETTER PE + '\u0420' # 0x0090 -> CYRILLIC CAPITAL LETTER ER + '\u0421' # 0x0091 -> CYRILLIC CAPITAL LETTER ES + '\u0422' # 0x0092 -> CYRILLIC CAPITAL LETTER TE + '\u0423' # 0x0093 -> CYRILLIC CAPITAL LETTER U + '\u0424' # 0x0094 -> CYRILLIC CAPITAL LETTER EF + '\u0425' # 0x0095 -> CYRILLIC CAPITAL LETTER HA + '\u0426' # 0x0096 -> CYRILLIC CAPITAL LETTER TSE + '\u0427' # 0x0097 -> CYRILLIC CAPITAL LETTER CHE + '\u0428' # 0x0098 -> CYRILLIC CAPITAL LETTER SHA + '\u0429' # 0x0099 -> CYRILLIC CAPITAL LETTER SHCHA + '\u042a' # 0x009a -> CYRILLIC CAPITAL LETTER HARD SIGN + '\u042b' # 0x009b -> CYRILLIC CAPITAL LETTER YERU + '\u042c' # 0x009c -> CYRILLIC CAPITAL LETTER SOFT SIGN + '\u042d' # 0x009d -> CYRILLIC CAPITAL LETTER E + '\u042e' # 0x009e -> CYRILLIC CAPITAL LETTER YU + '\u042f' # 0x009f -> CYRILLIC CAPITAL LETTER YA + '\u0430' # 0x00a0 -> CYRILLIC SMALL LETTER A + '\u0431' # 0x00a1 -> CYRILLIC SMALL LETTER BE + '\u0432' # 0x00a2 -> CYRILLIC SMALL LETTER VE + '\u0433' # 0x00a3 -> CYRILLIC SMALL LETTER GHE + '\u0434' # 0x00a4 -> CYRILLIC SMALL LETTER DE + '\u0435' # 0x00a5 -> CYRILLIC SMALL LETTER IE + '\u0436' # 0x00a6 -> CYRILLIC SMALL LETTER ZHE + '\u0437' # 0x00a7 -> CYRILLIC SMALL LETTER ZE + '\u0438' # 0x00a8 -> CYRILLIC SMALL LETTER I + '\u0439' # 0x00a9 -> CYRILLIC SMALL LETTER SHORT I + '\u043a' # 0x00aa -> CYRILLIC SMALL LETTER KA + '\u043b' # 0x00ab -> CYRILLIC SMALL LETTER EL + '\u043c' # 0x00ac -> CYRILLIC SMALL LETTER EM + '\u043d' # 0x00ad -> CYRILLIC SMALL LETTER EN + '\u043e' # 0x00ae -> CYRILLIC SMALL LETTER O + '\u043f' # 0x00af -> CYRILLIC SMALL LETTER PE + '\u2591' # 0x00b0 -> LIGHT SHADE + '\u2592' # 0x00b1 -> MEDIUM SHADE + '\u2593' # 0x00b2 -> DARK SHADE + '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL + '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT + '\u2561' # 0x00b5 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + '\u2562' # 0x00b6 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + '\u2556' # 0x00b7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + '\u2555' # 0x00b8 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL + '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT + '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT + '\u255c' # 0x00bd -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + '\u255b' # 0x00be -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT + '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT + '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL + '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT + '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL + '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + '\u255e' # 0x00c6 -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + '\u255f' # 0x00c7 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT + '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL + '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + '\u2567' # 0x00cf -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + '\u2568' # 0x00d0 -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + '\u2564' # 0x00d1 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + '\u2565' # 0x00d2 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + '\u2559' # 0x00d3 -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + '\u2558' # 0x00d4 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + '\u2552' # 0x00d5 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + '\u2553' # 0x00d6 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + '\u256b' # 0x00d7 -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + '\u256a' # 0x00d8 -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT + '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT + '\u2588' # 0x00db -> FULL BLOCK + '\u2584' # 0x00dc -> LOWER HALF BLOCK + '\u258c' # 0x00dd -> LEFT HALF BLOCK + '\u2590' # 0x00de -> RIGHT HALF BLOCK + '\u2580' # 0x00df -> UPPER HALF BLOCK + '\u0440' # 0x00e0 -> CYRILLIC SMALL LETTER ER + '\u0441' # 0x00e1 -> CYRILLIC SMALL LETTER ES + '\u0442' # 0x00e2 -> CYRILLIC SMALL LETTER TE + '\u0443' # 0x00e3 -> CYRILLIC SMALL LETTER U + '\u0444' # 0x00e4 -> CYRILLIC SMALL LETTER EF + '\u0445' # 0x00e5 -> CYRILLIC SMALL LETTER HA + '\u0446' # 0x00e6 -> CYRILLIC SMALL LETTER TSE + '\u0447' # 0x00e7 -> CYRILLIC SMALL LETTER CHE + '\u0448' # 0x00e8 -> CYRILLIC SMALL LETTER SHA + '\u0449' # 0x00e9 -> CYRILLIC SMALL LETTER SHCHA + '\u044a' # 0x00ea -> CYRILLIC SMALL LETTER HARD SIGN + '\u044b' # 0x00eb -> CYRILLIC SMALL LETTER YERU + '\u044c' # 0x00ec -> CYRILLIC SMALL LETTER SOFT SIGN + '\u044d' # 0x00ed -> CYRILLIC SMALL LETTER E + '\u044e' # 0x00ee -> CYRILLIC SMALL LETTER YU + '\u044f' # 0x00ef -> CYRILLIC SMALL LETTER YA + '\u0401' # 0x00f0 -> CYRILLIC CAPITAL LETTER IO + '\u0451' # 0x00f1 -> CYRILLIC SMALL LETTER IO + '\u0404' # 0x00f2 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE + '\u0454' # 0x00f3 -> CYRILLIC SMALL LETTER UKRAINIAN IE + '\u0407' # 0x00f4 -> CYRILLIC CAPITAL LETTER YI + '\u0457' # 0x00f5 -> CYRILLIC SMALL LETTER YI + '\u040e' # 0x00f6 -> CYRILLIC CAPITAL LETTER SHORT U + '\u045e' # 0x00f7 -> CYRILLIC SMALL LETTER SHORT U + '\xb0' # 0x00f8 -> DEGREE SIGN + '\u2219' # 0x00f9 -> BULLET OPERATOR + '\xb7' # 0x00fa -> MIDDLE DOT + '\u221a' # 0x00fb -> SQUARE ROOT + '\u2116' # 0x00fc -> NUMERO SIGN + '\xa4' # 0x00fd -> CURRENCY SIGN + '\u25a0' # 0x00fe -> BLACK SQUARE + '\xa0' # 0x00ff -> NO-BREAK SPACE +) + +### Encoding Map + +encoding_map = { + 0x0000: 0x0000, # NULL + 0x0001: 0x0001, # START OF HEADING + 0x0002: 0x0002, # START OF TEXT + 0x0003: 0x0003, # END OF TEXT + 0x0004: 0x0004, # END OF TRANSMISSION + 0x0005: 0x0005, # ENQUIRY + 0x0006: 0x0006, # ACKNOWLEDGE + 0x0007: 0x0007, # BELL + 0x0008: 0x0008, # BACKSPACE + 0x0009: 0x0009, # HORIZONTAL TABULATION + 0x000a: 0x000a, # LINE FEED + 0x000b: 0x000b, # VERTICAL TABULATION + 0x000c: 0x000c, # FORM FEED + 0x000d: 0x000d, # CARRIAGE RETURN + 0x000e: 0x000e, # SHIFT OUT + 0x000f: 0x000f, # SHIFT IN + 0x0010: 0x0010, # DATA LINK ESCAPE + 0x0011: 0x0011, # DEVICE CONTROL ONE + 0x0012: 0x0012, # DEVICE CONTROL TWO + 0x0013: 0x0013, # DEVICE CONTROL THREE + 0x0014: 0x0014, # DEVICE CONTROL FOUR + 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE + 0x0016: 0x0016, # SYNCHRONOUS IDLE + 0x0017: 0x0017, # END OF TRANSMISSION BLOCK + 0x0018: 0x0018, # CANCEL + 0x0019: 0x0019, # END OF MEDIUM + 0x001a: 0x001a, # SUBSTITUTE + 0x001b: 0x001b, # ESCAPE + 0x001c: 0x001c, # FILE SEPARATOR + 0x001d: 0x001d, # GROUP SEPARATOR + 0x001e: 0x001e, # RECORD SEPARATOR + 0x001f: 0x001f, # UNIT SEPARATOR + 0x0020: 0x0020, # SPACE + 0x0021: 0x0021, # EXCLAMATION MARK + 0x0022: 0x0022, # QUOTATION MARK + 0x0023: 0x0023, # NUMBER SIGN + 0x0024: 0x0024, # DOLLAR SIGN + 0x0025: 0x0025, # PERCENT SIGN + 0x0026: 0x0026, # AMPERSAND + 0x0027: 0x0027, # APOSTROPHE + 0x0028: 0x0028, # LEFT PARENTHESIS + 0x0029: 0x0029, # RIGHT PARENTHESIS + 0x002a: 0x002a, # ASTERISK + 0x002b: 0x002b, # PLUS SIGN + 0x002c: 0x002c, # COMMA + 0x002d: 0x002d, # HYPHEN-MINUS + 0x002e: 0x002e, # FULL STOP + 0x002f: 0x002f, # SOLIDUS + 0x0030: 0x0030, # DIGIT ZERO + 0x0031: 0x0031, # DIGIT ONE + 0x0032: 0x0032, # DIGIT TWO + 0x0033: 0x0033, # DIGIT THREE + 0x0034: 0x0034, # DIGIT FOUR + 0x0035: 0x0035, # DIGIT FIVE + 0x0036: 0x0036, # DIGIT SIX + 0x0037: 0x0037, # DIGIT SEVEN + 0x0038: 0x0038, # DIGIT EIGHT + 0x0039: 0x0039, # DIGIT NINE + 0x003a: 0x003a, # COLON + 0x003b: 0x003b, # SEMICOLON + 0x003c: 0x003c, # LESS-THAN SIGN + 0x003d: 0x003d, # EQUALS SIGN + 0x003e: 0x003e, # GREATER-THAN SIGN + 0x003f: 0x003f, # QUESTION MARK + 0x0040: 0x0040, # COMMERCIAL AT + 0x0041: 0x0041, # LATIN CAPITAL LETTER A + 0x0042: 0x0042, # LATIN CAPITAL LETTER B + 0x0043: 0x0043, # LATIN CAPITAL LETTER C + 0x0044: 0x0044, # LATIN CAPITAL LETTER D + 0x0045: 0x0045, # LATIN CAPITAL LETTER E + 0x0046: 0x0046, # LATIN CAPITAL LETTER F + 0x0047: 0x0047, # LATIN CAPITAL LETTER G + 0x0048: 0x0048, # LATIN CAPITAL LETTER H + 0x0049: 0x0049, # LATIN CAPITAL LETTER I + 0x004a: 0x004a, # LATIN CAPITAL LETTER J + 0x004b: 0x004b, # LATIN CAPITAL LETTER K + 0x004c: 0x004c, # LATIN CAPITAL LETTER L + 0x004d: 0x004d, # LATIN CAPITAL LETTER M + 0x004e: 0x004e, # LATIN CAPITAL LETTER N + 0x004f: 0x004f, # LATIN CAPITAL LETTER O + 0x0050: 0x0050, # LATIN CAPITAL LETTER P + 0x0051: 0x0051, # LATIN CAPITAL LETTER Q + 0x0052: 0x0052, # LATIN CAPITAL LETTER R + 0x0053: 0x0053, # LATIN CAPITAL LETTER S + 0x0054: 0x0054, # LATIN CAPITAL LETTER T + 0x0055: 0x0055, # LATIN CAPITAL LETTER U + 0x0056: 0x0056, # LATIN CAPITAL LETTER V + 0x0057: 0x0057, # LATIN CAPITAL LETTER W + 0x0058: 0x0058, # LATIN CAPITAL LETTER X + 0x0059: 0x0059, # LATIN CAPITAL LETTER Y + 0x005a: 0x005a, # LATIN CAPITAL LETTER Z + 0x005b: 0x005b, # LEFT SQUARE BRACKET + 0x005c: 0x005c, # REVERSE SOLIDUS + 0x005d: 0x005d, # RIGHT SQUARE BRACKET + 0x005e: 0x005e, # CIRCUMFLEX ACCENT + 0x005f: 0x005f, # LOW LINE + 0x0060: 0x0060, # GRAVE ACCENT + 0x0061: 0x0061, # LATIN SMALL LETTER A + 0x0062: 0x0062, # LATIN SMALL LETTER B + 0x0063: 0x0063, # LATIN SMALL LETTER C + 0x0064: 0x0064, # LATIN SMALL LETTER D + 0x0065: 0x0065, # LATIN SMALL LETTER E + 0x0066: 0x0066, # LATIN SMALL LETTER F + 0x0067: 0x0067, # LATIN SMALL LETTER G + 0x0068: 0x0068, # LATIN SMALL LETTER H + 0x0069: 0x0069, # LATIN SMALL LETTER I + 0x006a: 0x006a, # LATIN SMALL LETTER J + 0x006b: 0x006b, # LATIN SMALL LETTER K + 0x006c: 0x006c, # LATIN SMALL LETTER L + 0x006d: 0x006d, # LATIN SMALL LETTER M + 0x006e: 0x006e, # LATIN SMALL LETTER N + 0x006f: 0x006f, # LATIN SMALL LETTER O + 0x0070: 0x0070, # LATIN SMALL LETTER P + 0x0071: 0x0071, # LATIN SMALL LETTER Q + 0x0072: 0x0072, # LATIN SMALL LETTER R + 0x0073: 0x0073, # LATIN SMALL LETTER S + 0x0074: 0x0074, # LATIN SMALL LETTER T + 0x0075: 0x0075, # LATIN SMALL LETTER U + 0x0076: 0x0076, # LATIN SMALL LETTER V + 0x0077: 0x0077, # LATIN SMALL LETTER W + 0x0078: 0x0078, # LATIN SMALL LETTER X + 0x0079: 0x0079, # LATIN SMALL LETTER Y + 0x007a: 0x007a, # LATIN SMALL LETTER Z + 0x007b: 0x007b, # LEFT CURLY BRACKET + 0x007c: 0x007c, # VERTICAL LINE + 0x007d: 0x007d, # RIGHT CURLY BRACKET + 0x007e: 0x007e, # TILDE + 0x007f: 0x007f, # DELETE + 0x00a0: 0x00ff, # NO-BREAK SPACE + 0x00a4: 0x00fd, # CURRENCY SIGN + 0x00b0: 0x00f8, # DEGREE SIGN + 0x00b7: 0x00fa, # MIDDLE DOT + 0x0401: 0x00f0, # CYRILLIC CAPITAL LETTER IO + 0x0404: 0x00f2, # CYRILLIC CAPITAL LETTER UKRAINIAN IE + 0x0407: 0x00f4, # CYRILLIC CAPITAL LETTER YI + 0x040e: 0x00f6, # CYRILLIC CAPITAL LETTER SHORT U + 0x0410: 0x0080, # CYRILLIC CAPITAL LETTER A + 0x0411: 0x0081, # CYRILLIC CAPITAL LETTER BE + 0x0412: 0x0082, # CYRILLIC CAPITAL LETTER VE + 0x0413: 0x0083, # CYRILLIC CAPITAL LETTER GHE + 0x0414: 0x0084, # CYRILLIC CAPITAL LETTER DE + 0x0415: 0x0085, # CYRILLIC CAPITAL LETTER IE + 0x0416: 0x0086, # CYRILLIC CAPITAL LETTER ZHE + 0x0417: 0x0087, # CYRILLIC CAPITAL LETTER ZE + 0x0418: 0x0088, # CYRILLIC CAPITAL LETTER I + 0x0419: 0x0089, # CYRILLIC CAPITAL LETTER SHORT I + 0x041a: 0x008a, # CYRILLIC CAPITAL LETTER KA + 0x041b: 0x008b, # CYRILLIC CAPITAL LETTER EL + 0x041c: 0x008c, # CYRILLIC CAPITAL LETTER EM + 0x041d: 0x008d, # CYRILLIC CAPITAL LETTER EN + 0x041e: 0x008e, # CYRILLIC CAPITAL LETTER O + 0x041f: 0x008f, # CYRILLIC CAPITAL LETTER PE + 0x0420: 0x0090, # CYRILLIC CAPITAL LETTER ER + 0x0421: 0x0091, # CYRILLIC CAPITAL LETTER ES + 0x0422: 0x0092, # CYRILLIC CAPITAL LETTER TE + 0x0423: 0x0093, # CYRILLIC CAPITAL LETTER U + 0x0424: 0x0094, # CYRILLIC CAPITAL LETTER EF + 0x0425: 0x0095, # CYRILLIC CAPITAL LETTER HA + 0x0426: 0x0096, # CYRILLIC CAPITAL LETTER TSE + 0x0427: 0x0097, # CYRILLIC CAPITAL LETTER CHE + 0x0428: 0x0098, # CYRILLIC CAPITAL LETTER SHA + 0x0429: 0x0099, # CYRILLIC CAPITAL LETTER SHCHA + 0x042a: 0x009a, # CYRILLIC CAPITAL LETTER HARD SIGN + 0x042b: 0x009b, # CYRILLIC CAPITAL LETTER YERU + 0x042c: 0x009c, # CYRILLIC CAPITAL LETTER SOFT SIGN + 0x042d: 0x009d, # CYRILLIC CAPITAL LETTER E + 0x042e: 0x009e, # CYRILLIC CAPITAL LETTER YU + 0x042f: 0x009f, # CYRILLIC CAPITAL LETTER YA + 0x0430: 0x00a0, # CYRILLIC SMALL LETTER A + 0x0431: 0x00a1, # CYRILLIC SMALL LETTER BE + 0x0432: 0x00a2, # CYRILLIC SMALL LETTER VE + 0x0433: 0x00a3, # CYRILLIC SMALL LETTER GHE + 0x0434: 0x00a4, # CYRILLIC SMALL LETTER DE + 0x0435: 0x00a5, # CYRILLIC SMALL LETTER IE + 0x0436: 0x00a6, # CYRILLIC SMALL LETTER ZHE + 0x0437: 0x00a7, # CYRILLIC SMALL LETTER ZE + 0x0438: 0x00a8, # CYRILLIC SMALL LETTER I + 0x0439: 0x00a9, # CYRILLIC SMALL LETTER SHORT I + 0x043a: 0x00aa, # CYRILLIC SMALL LETTER KA + 0x043b: 0x00ab, # CYRILLIC SMALL LETTER EL + 0x043c: 0x00ac, # CYRILLIC SMALL LETTER EM + 0x043d: 0x00ad, # CYRILLIC SMALL LETTER EN + 0x043e: 0x00ae, # CYRILLIC SMALL LETTER O + 0x043f: 0x00af, # CYRILLIC SMALL LETTER PE + 0x0440: 0x00e0, # CYRILLIC SMALL LETTER ER + 0x0441: 0x00e1, # CYRILLIC SMALL LETTER ES + 0x0442: 0x00e2, # CYRILLIC SMALL LETTER TE + 0x0443: 0x00e3, # CYRILLIC SMALL LETTER U + 0x0444: 0x00e4, # CYRILLIC SMALL LETTER EF + 0x0445: 0x00e5, # CYRILLIC SMALL LETTER HA + 0x0446: 0x00e6, # CYRILLIC SMALL LETTER TSE + 0x0447: 0x00e7, # CYRILLIC SMALL LETTER CHE + 0x0448: 0x00e8, # CYRILLIC SMALL LETTER SHA + 0x0449: 0x00e9, # CYRILLIC SMALL LETTER SHCHA + 0x044a: 0x00ea, # CYRILLIC SMALL LETTER HARD SIGN + 0x044b: 0x00eb, # CYRILLIC SMALL LETTER YERU + 0x044c: 0x00ec, # CYRILLIC SMALL LETTER SOFT SIGN + 0x044d: 0x00ed, # CYRILLIC SMALL LETTER E + 0x044e: 0x00ee, # CYRILLIC SMALL LETTER YU + 0x044f: 0x00ef, # CYRILLIC SMALL LETTER YA + 0x0451: 0x00f1, # CYRILLIC SMALL LETTER IO + 0x0454: 0x00f3, # CYRILLIC SMALL LETTER UKRAINIAN IE + 0x0457: 0x00f5, # CYRILLIC SMALL LETTER YI + 0x045e: 0x00f7, # CYRILLIC SMALL LETTER SHORT U + 0x2116: 0x00fc, # NUMERO SIGN + 0x2219: 0x00f9, # BULLET OPERATOR + 0x221a: 0x00fb, # SQUARE ROOT + 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL + 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL + 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT + 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL + 0x2552: 0x00d5, # BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + 0x2553: 0x00d6, # BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x2555: 0x00b8, # BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + 0x2556: 0x00b7, # BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x2558: 0x00d4, # BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + 0x2559: 0x00d3, # BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x255b: 0x00be, # BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + 0x255c: 0x00bd, # BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x255e: 0x00c6, # BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + 0x255f: 0x00c7, # BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x2561: 0x00b5, # BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + 0x2562: 0x00b6, # BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x2564: 0x00d1, # BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + 0x2565: 0x00d2, # BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x2567: 0x00cf, # BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + 0x2568: 0x00d0, # BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x256a: 0x00d8, # BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + 0x256b: 0x00d7, # BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x2580: 0x00df, # UPPER HALF BLOCK + 0x2584: 0x00dc, # LOWER HALF BLOCK + 0x2588: 0x00db, # FULL BLOCK + 0x258c: 0x00dd, # LEFT HALF BLOCK + 0x2590: 0x00de, # RIGHT HALF BLOCK + 0x2591: 0x00b0, # LIGHT SHADE + 0x2592: 0x00b1, # MEDIUM SHADE + 0x2593: 0x00b2, # DARK SHADE + 0x25a0: 0x00fe, # BLACK SQUARE +} diff --git a/contrib/tools/python3/src/Lib/encodings/cp869.py b/contrib/tools/python3/src/Lib/encodings/cp869.py new file mode 100644 index 0000000000..8d8a29b175 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp869.py @@ -0,0 +1,689 @@ +""" Python Character Mapping Codec generated from 'VENDORS/MICSFT/PC/CP869.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_map) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp869', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + +### Decoding Map + +decoding_map = codecs.make_identity_dict(range(256)) +decoding_map.update({ + 0x0080: None, # UNDEFINED + 0x0081: None, # UNDEFINED + 0x0082: None, # UNDEFINED + 0x0083: None, # UNDEFINED + 0x0084: None, # UNDEFINED + 0x0085: None, # UNDEFINED + 0x0086: 0x0386, # GREEK CAPITAL LETTER ALPHA WITH TONOS + 0x0087: None, # UNDEFINED + 0x0088: 0x00b7, # MIDDLE DOT + 0x0089: 0x00ac, # NOT SIGN + 0x008a: 0x00a6, # BROKEN BAR + 0x008b: 0x2018, # LEFT SINGLE QUOTATION MARK + 0x008c: 0x2019, # RIGHT SINGLE QUOTATION MARK + 0x008d: 0x0388, # GREEK CAPITAL LETTER EPSILON WITH TONOS + 0x008e: 0x2015, # HORIZONTAL BAR + 0x008f: 0x0389, # GREEK CAPITAL LETTER ETA WITH TONOS + 0x0090: 0x038a, # GREEK CAPITAL LETTER IOTA WITH TONOS + 0x0091: 0x03aa, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA + 0x0092: 0x038c, # GREEK CAPITAL LETTER OMICRON WITH TONOS + 0x0093: None, # UNDEFINED + 0x0094: None, # UNDEFINED + 0x0095: 0x038e, # GREEK CAPITAL LETTER UPSILON WITH TONOS + 0x0096: 0x03ab, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA + 0x0097: 0x00a9, # COPYRIGHT SIGN + 0x0098: 0x038f, # GREEK CAPITAL LETTER OMEGA WITH TONOS + 0x0099: 0x00b2, # SUPERSCRIPT TWO + 0x009a: 0x00b3, # SUPERSCRIPT THREE + 0x009b: 0x03ac, # GREEK SMALL LETTER ALPHA WITH TONOS + 0x009c: 0x00a3, # POUND SIGN + 0x009d: 0x03ad, # GREEK SMALL LETTER EPSILON WITH TONOS + 0x009e: 0x03ae, # GREEK SMALL LETTER ETA WITH TONOS + 0x009f: 0x03af, # GREEK SMALL LETTER IOTA WITH TONOS + 0x00a0: 0x03ca, # GREEK SMALL LETTER IOTA WITH DIALYTIKA + 0x00a1: 0x0390, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS + 0x00a2: 0x03cc, # GREEK SMALL LETTER OMICRON WITH TONOS + 0x00a3: 0x03cd, # GREEK SMALL LETTER UPSILON WITH TONOS + 0x00a4: 0x0391, # GREEK CAPITAL LETTER ALPHA + 0x00a5: 0x0392, # GREEK CAPITAL LETTER BETA + 0x00a6: 0x0393, # GREEK CAPITAL LETTER GAMMA + 0x00a7: 0x0394, # GREEK CAPITAL LETTER DELTA + 0x00a8: 0x0395, # GREEK CAPITAL LETTER EPSILON + 0x00a9: 0x0396, # GREEK CAPITAL LETTER ZETA + 0x00aa: 0x0397, # GREEK CAPITAL LETTER ETA + 0x00ab: 0x00bd, # VULGAR FRACTION ONE HALF + 0x00ac: 0x0398, # GREEK CAPITAL LETTER THETA + 0x00ad: 0x0399, # GREEK CAPITAL LETTER IOTA + 0x00ae: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00af: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00b0: 0x2591, # LIGHT SHADE + 0x00b1: 0x2592, # MEDIUM SHADE + 0x00b2: 0x2593, # DARK SHADE + 0x00b3: 0x2502, # BOX DRAWINGS LIGHT VERTICAL + 0x00b4: 0x2524, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x00b5: 0x039a, # GREEK CAPITAL LETTER KAPPA + 0x00b6: 0x039b, # GREEK CAPITAL LETTER LAMDA + 0x00b7: 0x039c, # GREEK CAPITAL LETTER MU + 0x00b8: 0x039d, # GREEK CAPITAL LETTER NU + 0x00b9: 0x2563, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x00ba: 0x2551, # BOX DRAWINGS DOUBLE VERTICAL + 0x00bb: 0x2557, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x00bc: 0x255d, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x00bd: 0x039e, # GREEK CAPITAL LETTER XI + 0x00be: 0x039f, # GREEK CAPITAL LETTER OMICRON + 0x00bf: 0x2510, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x00c0: 0x2514, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x00c1: 0x2534, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x00c2: 0x252c, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x00c3: 0x251c, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x00c4: 0x2500, # BOX DRAWINGS LIGHT HORIZONTAL + 0x00c5: 0x253c, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x00c6: 0x03a0, # GREEK CAPITAL LETTER PI + 0x00c7: 0x03a1, # GREEK CAPITAL LETTER RHO + 0x00c8: 0x255a, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x00c9: 0x2554, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x00ca: 0x2569, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x00cb: 0x2566, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x00cc: 0x2560, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x00cd: 0x2550, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x00ce: 0x256c, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x00cf: 0x03a3, # GREEK CAPITAL LETTER SIGMA + 0x00d0: 0x03a4, # GREEK CAPITAL LETTER TAU + 0x00d1: 0x03a5, # GREEK CAPITAL LETTER UPSILON + 0x00d2: 0x03a6, # GREEK CAPITAL LETTER PHI + 0x00d3: 0x03a7, # GREEK CAPITAL LETTER CHI + 0x00d4: 0x03a8, # GREEK CAPITAL LETTER PSI + 0x00d5: 0x03a9, # GREEK CAPITAL LETTER OMEGA + 0x00d6: 0x03b1, # GREEK SMALL LETTER ALPHA + 0x00d7: 0x03b2, # GREEK SMALL LETTER BETA + 0x00d8: 0x03b3, # GREEK SMALL LETTER GAMMA + 0x00d9: 0x2518, # BOX DRAWINGS LIGHT UP AND LEFT + 0x00da: 0x250c, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x00db: 0x2588, # FULL BLOCK + 0x00dc: 0x2584, # LOWER HALF BLOCK + 0x00dd: 0x03b4, # GREEK SMALL LETTER DELTA + 0x00de: 0x03b5, # GREEK SMALL LETTER EPSILON + 0x00df: 0x2580, # UPPER HALF BLOCK + 0x00e0: 0x03b6, # GREEK SMALL LETTER ZETA + 0x00e1: 0x03b7, # GREEK SMALL LETTER ETA + 0x00e2: 0x03b8, # GREEK SMALL LETTER THETA + 0x00e3: 0x03b9, # GREEK SMALL LETTER IOTA + 0x00e4: 0x03ba, # GREEK SMALL LETTER KAPPA + 0x00e5: 0x03bb, # GREEK SMALL LETTER LAMDA + 0x00e6: 0x03bc, # GREEK SMALL LETTER MU + 0x00e7: 0x03bd, # GREEK SMALL LETTER NU + 0x00e8: 0x03be, # GREEK SMALL LETTER XI + 0x00e9: 0x03bf, # GREEK SMALL LETTER OMICRON + 0x00ea: 0x03c0, # GREEK SMALL LETTER PI + 0x00eb: 0x03c1, # GREEK SMALL LETTER RHO + 0x00ec: 0x03c3, # GREEK SMALL LETTER SIGMA + 0x00ed: 0x03c2, # GREEK SMALL LETTER FINAL SIGMA + 0x00ee: 0x03c4, # GREEK SMALL LETTER TAU + 0x00ef: 0x0384, # GREEK TONOS + 0x00f0: 0x00ad, # SOFT HYPHEN + 0x00f1: 0x00b1, # PLUS-MINUS SIGN + 0x00f2: 0x03c5, # GREEK SMALL LETTER UPSILON + 0x00f3: 0x03c6, # GREEK SMALL LETTER PHI + 0x00f4: 0x03c7, # GREEK SMALL LETTER CHI + 0x00f5: 0x00a7, # SECTION SIGN + 0x00f6: 0x03c8, # GREEK SMALL LETTER PSI + 0x00f7: 0x0385, # GREEK DIALYTIKA TONOS + 0x00f8: 0x00b0, # DEGREE SIGN + 0x00f9: 0x00a8, # DIAERESIS + 0x00fa: 0x03c9, # GREEK SMALL LETTER OMEGA + 0x00fb: 0x03cb, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA + 0x00fc: 0x03b0, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS + 0x00fd: 0x03ce, # GREEK SMALL LETTER OMEGA WITH TONOS + 0x00fe: 0x25a0, # BLACK SQUARE + 0x00ff: 0x00a0, # NO-BREAK SPACE +}) + +### Decoding Table + +decoding_table = ( + '\x00' # 0x0000 -> NULL + '\x01' # 0x0001 -> START OF HEADING + '\x02' # 0x0002 -> START OF TEXT + '\x03' # 0x0003 -> END OF TEXT + '\x04' # 0x0004 -> END OF TRANSMISSION + '\x05' # 0x0005 -> ENQUIRY + '\x06' # 0x0006 -> ACKNOWLEDGE + '\x07' # 0x0007 -> BELL + '\x08' # 0x0008 -> BACKSPACE + '\t' # 0x0009 -> HORIZONTAL TABULATION + '\n' # 0x000a -> LINE FEED + '\x0b' # 0x000b -> VERTICAL TABULATION + '\x0c' # 0x000c -> FORM FEED + '\r' # 0x000d -> CARRIAGE RETURN + '\x0e' # 0x000e -> SHIFT OUT + '\x0f' # 0x000f -> SHIFT IN + '\x10' # 0x0010 -> DATA LINK ESCAPE + '\x11' # 0x0011 -> DEVICE CONTROL ONE + '\x12' # 0x0012 -> DEVICE CONTROL TWO + '\x13' # 0x0013 -> DEVICE CONTROL THREE + '\x14' # 0x0014 -> DEVICE CONTROL FOUR + '\x15' # 0x0015 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x0016 -> SYNCHRONOUS IDLE + '\x17' # 0x0017 -> END OF TRANSMISSION BLOCK + '\x18' # 0x0018 -> CANCEL + '\x19' # 0x0019 -> END OF MEDIUM + '\x1a' # 0x001a -> SUBSTITUTE + '\x1b' # 0x001b -> ESCAPE + '\x1c' # 0x001c -> FILE SEPARATOR + '\x1d' # 0x001d -> GROUP SEPARATOR + '\x1e' # 0x001e -> RECORD SEPARATOR + '\x1f' # 0x001f -> UNIT SEPARATOR + ' ' # 0x0020 -> SPACE + '!' # 0x0021 -> EXCLAMATION MARK + '"' # 0x0022 -> QUOTATION MARK + '#' # 0x0023 -> NUMBER SIGN + '$' # 0x0024 -> DOLLAR SIGN + '%' # 0x0025 -> PERCENT SIGN + '&' # 0x0026 -> AMPERSAND + "'" # 0x0027 -> APOSTROPHE + '(' # 0x0028 -> LEFT PARENTHESIS + ')' # 0x0029 -> RIGHT PARENTHESIS + '*' # 0x002a -> ASTERISK + '+' # 0x002b -> PLUS SIGN + ',' # 0x002c -> COMMA + '-' # 0x002d -> HYPHEN-MINUS + '.' # 0x002e -> FULL STOP + '/' # 0x002f -> SOLIDUS + '0' # 0x0030 -> DIGIT ZERO + '1' # 0x0031 -> DIGIT ONE + '2' # 0x0032 -> DIGIT TWO + '3' # 0x0033 -> DIGIT THREE + '4' # 0x0034 -> DIGIT FOUR + '5' # 0x0035 -> DIGIT FIVE + '6' # 0x0036 -> DIGIT SIX + '7' # 0x0037 -> DIGIT SEVEN + '8' # 0x0038 -> DIGIT EIGHT + '9' # 0x0039 -> DIGIT NINE + ':' # 0x003a -> COLON + ';' # 0x003b -> SEMICOLON + '<' # 0x003c -> LESS-THAN SIGN + '=' # 0x003d -> EQUALS SIGN + '>' # 0x003e -> GREATER-THAN SIGN + '?' # 0x003f -> QUESTION MARK + '@' # 0x0040 -> COMMERCIAL AT + 'A' # 0x0041 -> LATIN CAPITAL LETTER A + 'B' # 0x0042 -> LATIN CAPITAL LETTER B + 'C' # 0x0043 -> LATIN CAPITAL LETTER C + 'D' # 0x0044 -> LATIN CAPITAL LETTER D + 'E' # 0x0045 -> LATIN CAPITAL LETTER E + 'F' # 0x0046 -> LATIN CAPITAL LETTER F + 'G' # 0x0047 -> LATIN CAPITAL LETTER G + 'H' # 0x0048 -> LATIN CAPITAL LETTER H + 'I' # 0x0049 -> LATIN CAPITAL LETTER I + 'J' # 0x004a -> LATIN CAPITAL LETTER J + 'K' # 0x004b -> LATIN CAPITAL LETTER K + 'L' # 0x004c -> LATIN CAPITAL LETTER L + 'M' # 0x004d -> LATIN CAPITAL LETTER M + 'N' # 0x004e -> LATIN CAPITAL LETTER N + 'O' # 0x004f -> LATIN CAPITAL LETTER O + 'P' # 0x0050 -> LATIN CAPITAL LETTER P + 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q + 'R' # 0x0052 -> LATIN CAPITAL LETTER R + 'S' # 0x0053 -> LATIN CAPITAL LETTER S + 'T' # 0x0054 -> LATIN CAPITAL LETTER T + 'U' # 0x0055 -> LATIN CAPITAL LETTER U + 'V' # 0x0056 -> LATIN CAPITAL LETTER V + 'W' # 0x0057 -> LATIN CAPITAL LETTER W + 'X' # 0x0058 -> LATIN CAPITAL LETTER X + 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y + 'Z' # 0x005a -> LATIN CAPITAL LETTER Z + '[' # 0x005b -> LEFT SQUARE BRACKET + '\\' # 0x005c -> REVERSE SOLIDUS + ']' # 0x005d -> RIGHT SQUARE BRACKET + '^' # 0x005e -> CIRCUMFLEX ACCENT + '_' # 0x005f -> LOW LINE + '`' # 0x0060 -> GRAVE ACCENT + 'a' # 0x0061 -> LATIN SMALL LETTER A + 'b' # 0x0062 -> LATIN SMALL LETTER B + 'c' # 0x0063 -> LATIN SMALL LETTER C + 'd' # 0x0064 -> LATIN SMALL LETTER D + 'e' # 0x0065 -> LATIN SMALL LETTER E + 'f' # 0x0066 -> LATIN SMALL LETTER F + 'g' # 0x0067 -> LATIN SMALL LETTER G + 'h' # 0x0068 -> LATIN SMALL LETTER H + 'i' # 0x0069 -> LATIN SMALL LETTER I + 'j' # 0x006a -> LATIN SMALL LETTER J + 'k' # 0x006b -> LATIN SMALL LETTER K + 'l' # 0x006c -> LATIN SMALL LETTER L + 'm' # 0x006d -> LATIN SMALL LETTER M + 'n' # 0x006e -> LATIN SMALL LETTER N + 'o' # 0x006f -> LATIN SMALL LETTER O + 'p' # 0x0070 -> LATIN SMALL LETTER P + 'q' # 0x0071 -> LATIN SMALL LETTER Q + 'r' # 0x0072 -> LATIN SMALL LETTER R + 's' # 0x0073 -> LATIN SMALL LETTER S + 't' # 0x0074 -> LATIN SMALL LETTER T + 'u' # 0x0075 -> LATIN SMALL LETTER U + 'v' # 0x0076 -> LATIN SMALL LETTER V + 'w' # 0x0077 -> LATIN SMALL LETTER W + 'x' # 0x0078 -> LATIN SMALL LETTER X + 'y' # 0x0079 -> LATIN SMALL LETTER Y + 'z' # 0x007a -> LATIN SMALL LETTER Z + '{' # 0x007b -> LEFT CURLY BRACKET + '|' # 0x007c -> VERTICAL LINE + '}' # 0x007d -> RIGHT CURLY BRACKET + '~' # 0x007e -> TILDE + '\x7f' # 0x007f -> DELETE + '\ufffe' # 0x0080 -> UNDEFINED + '\ufffe' # 0x0081 -> UNDEFINED + '\ufffe' # 0x0082 -> UNDEFINED + '\ufffe' # 0x0083 -> UNDEFINED + '\ufffe' # 0x0084 -> UNDEFINED + '\ufffe' # 0x0085 -> UNDEFINED + '\u0386' # 0x0086 -> GREEK CAPITAL LETTER ALPHA WITH TONOS + '\ufffe' # 0x0087 -> UNDEFINED + '\xb7' # 0x0088 -> MIDDLE DOT + '\xac' # 0x0089 -> NOT SIGN + '\xa6' # 0x008a -> BROKEN BAR + '\u2018' # 0x008b -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0x008c -> RIGHT SINGLE QUOTATION MARK + '\u0388' # 0x008d -> GREEK CAPITAL LETTER EPSILON WITH TONOS + '\u2015' # 0x008e -> HORIZONTAL BAR + '\u0389' # 0x008f -> GREEK CAPITAL LETTER ETA WITH TONOS + '\u038a' # 0x0090 -> GREEK CAPITAL LETTER IOTA WITH TONOS + '\u03aa' # 0x0091 -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA + '\u038c' # 0x0092 -> GREEK CAPITAL LETTER OMICRON WITH TONOS + '\ufffe' # 0x0093 -> UNDEFINED + '\ufffe' # 0x0094 -> UNDEFINED + '\u038e' # 0x0095 -> GREEK CAPITAL LETTER UPSILON WITH TONOS + '\u03ab' # 0x0096 -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA + '\xa9' # 0x0097 -> COPYRIGHT SIGN + '\u038f' # 0x0098 -> GREEK CAPITAL LETTER OMEGA WITH TONOS + '\xb2' # 0x0099 -> SUPERSCRIPT TWO + '\xb3' # 0x009a -> SUPERSCRIPT THREE + '\u03ac' # 0x009b -> GREEK SMALL LETTER ALPHA WITH TONOS + '\xa3' # 0x009c -> POUND SIGN + '\u03ad' # 0x009d -> GREEK SMALL LETTER EPSILON WITH TONOS + '\u03ae' # 0x009e -> GREEK SMALL LETTER ETA WITH TONOS + '\u03af' # 0x009f -> GREEK SMALL LETTER IOTA WITH TONOS + '\u03ca' # 0x00a0 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA + '\u0390' # 0x00a1 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS + '\u03cc' # 0x00a2 -> GREEK SMALL LETTER OMICRON WITH TONOS + '\u03cd' # 0x00a3 -> GREEK SMALL LETTER UPSILON WITH TONOS + '\u0391' # 0x00a4 -> GREEK CAPITAL LETTER ALPHA + '\u0392' # 0x00a5 -> GREEK CAPITAL LETTER BETA + '\u0393' # 0x00a6 -> GREEK CAPITAL LETTER GAMMA + '\u0394' # 0x00a7 -> GREEK CAPITAL LETTER DELTA + '\u0395' # 0x00a8 -> GREEK CAPITAL LETTER EPSILON + '\u0396' # 0x00a9 -> GREEK CAPITAL LETTER ZETA + '\u0397' # 0x00aa -> GREEK CAPITAL LETTER ETA + '\xbd' # 0x00ab -> VULGAR FRACTION ONE HALF + '\u0398' # 0x00ac -> GREEK CAPITAL LETTER THETA + '\u0399' # 0x00ad -> GREEK CAPITAL LETTER IOTA + '\xab' # 0x00ae -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0x00af -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u2591' # 0x00b0 -> LIGHT SHADE + '\u2592' # 0x00b1 -> MEDIUM SHADE + '\u2593' # 0x00b2 -> DARK SHADE + '\u2502' # 0x00b3 -> BOX DRAWINGS LIGHT VERTICAL + '\u2524' # 0x00b4 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT + '\u039a' # 0x00b5 -> GREEK CAPITAL LETTER KAPPA + '\u039b' # 0x00b6 -> GREEK CAPITAL LETTER LAMDA + '\u039c' # 0x00b7 -> GREEK CAPITAL LETTER MU + '\u039d' # 0x00b8 -> GREEK CAPITAL LETTER NU + '\u2563' # 0x00b9 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + '\u2551' # 0x00ba -> BOX DRAWINGS DOUBLE VERTICAL + '\u2557' # 0x00bb -> BOX DRAWINGS DOUBLE DOWN AND LEFT + '\u255d' # 0x00bc -> BOX DRAWINGS DOUBLE UP AND LEFT + '\u039e' # 0x00bd -> GREEK CAPITAL LETTER XI + '\u039f' # 0x00be -> GREEK CAPITAL LETTER OMICRON + '\u2510' # 0x00bf -> BOX DRAWINGS LIGHT DOWN AND LEFT + '\u2514' # 0x00c0 -> BOX DRAWINGS LIGHT UP AND RIGHT + '\u2534' # 0x00c1 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL + '\u252c' # 0x00c2 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + '\u251c' # 0x00c3 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT + '\u2500' # 0x00c4 -> BOX DRAWINGS LIGHT HORIZONTAL + '\u253c' # 0x00c5 -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + '\u03a0' # 0x00c6 -> GREEK CAPITAL LETTER PI + '\u03a1' # 0x00c7 -> GREEK CAPITAL LETTER RHO + '\u255a' # 0x00c8 -> BOX DRAWINGS DOUBLE UP AND RIGHT + '\u2554' # 0x00c9 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + '\u2569' # 0x00ca -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + '\u2566' # 0x00cb -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + '\u2560' # 0x00cc -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + '\u2550' # 0x00cd -> BOX DRAWINGS DOUBLE HORIZONTAL + '\u256c' # 0x00ce -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + '\u03a3' # 0x00cf -> GREEK CAPITAL LETTER SIGMA + '\u03a4' # 0x00d0 -> GREEK CAPITAL LETTER TAU + '\u03a5' # 0x00d1 -> GREEK CAPITAL LETTER UPSILON + '\u03a6' # 0x00d2 -> GREEK CAPITAL LETTER PHI + '\u03a7' # 0x00d3 -> GREEK CAPITAL LETTER CHI + '\u03a8' # 0x00d4 -> GREEK CAPITAL LETTER PSI + '\u03a9' # 0x00d5 -> GREEK CAPITAL LETTER OMEGA + '\u03b1' # 0x00d6 -> GREEK SMALL LETTER ALPHA + '\u03b2' # 0x00d7 -> GREEK SMALL LETTER BETA + '\u03b3' # 0x00d8 -> GREEK SMALL LETTER GAMMA + '\u2518' # 0x00d9 -> BOX DRAWINGS LIGHT UP AND LEFT + '\u250c' # 0x00da -> BOX DRAWINGS LIGHT DOWN AND RIGHT + '\u2588' # 0x00db -> FULL BLOCK + '\u2584' # 0x00dc -> LOWER HALF BLOCK + '\u03b4' # 0x00dd -> GREEK SMALL LETTER DELTA + '\u03b5' # 0x00de -> GREEK SMALL LETTER EPSILON + '\u2580' # 0x00df -> UPPER HALF BLOCK + '\u03b6' # 0x00e0 -> GREEK SMALL LETTER ZETA + '\u03b7' # 0x00e1 -> GREEK SMALL LETTER ETA + '\u03b8' # 0x00e2 -> GREEK SMALL LETTER THETA + '\u03b9' # 0x00e3 -> GREEK SMALL LETTER IOTA + '\u03ba' # 0x00e4 -> GREEK SMALL LETTER KAPPA + '\u03bb' # 0x00e5 -> GREEK SMALL LETTER LAMDA + '\u03bc' # 0x00e6 -> GREEK SMALL LETTER MU + '\u03bd' # 0x00e7 -> GREEK SMALL LETTER NU + '\u03be' # 0x00e8 -> GREEK SMALL LETTER XI + '\u03bf' # 0x00e9 -> GREEK SMALL LETTER OMICRON + '\u03c0' # 0x00ea -> GREEK SMALL LETTER PI + '\u03c1' # 0x00eb -> GREEK SMALL LETTER RHO + '\u03c3' # 0x00ec -> GREEK SMALL LETTER SIGMA + '\u03c2' # 0x00ed -> GREEK SMALL LETTER FINAL SIGMA + '\u03c4' # 0x00ee -> GREEK SMALL LETTER TAU + '\u0384' # 0x00ef -> GREEK TONOS + '\xad' # 0x00f0 -> SOFT HYPHEN + '\xb1' # 0x00f1 -> PLUS-MINUS SIGN + '\u03c5' # 0x00f2 -> GREEK SMALL LETTER UPSILON + '\u03c6' # 0x00f3 -> GREEK SMALL LETTER PHI + '\u03c7' # 0x00f4 -> GREEK SMALL LETTER CHI + '\xa7' # 0x00f5 -> SECTION SIGN + '\u03c8' # 0x00f6 -> GREEK SMALL LETTER PSI + '\u0385' # 0x00f7 -> GREEK DIALYTIKA TONOS + '\xb0' # 0x00f8 -> DEGREE SIGN + '\xa8' # 0x00f9 -> DIAERESIS + '\u03c9' # 0x00fa -> GREEK SMALL LETTER OMEGA + '\u03cb' # 0x00fb -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA + '\u03b0' # 0x00fc -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS + '\u03ce' # 0x00fd -> GREEK SMALL LETTER OMEGA WITH TONOS + '\u25a0' # 0x00fe -> BLACK SQUARE + '\xa0' # 0x00ff -> NO-BREAK SPACE +) + +### Encoding Map + +encoding_map = { + 0x0000: 0x0000, # NULL + 0x0001: 0x0001, # START OF HEADING + 0x0002: 0x0002, # START OF TEXT + 0x0003: 0x0003, # END OF TEXT + 0x0004: 0x0004, # END OF TRANSMISSION + 0x0005: 0x0005, # ENQUIRY + 0x0006: 0x0006, # ACKNOWLEDGE + 0x0007: 0x0007, # BELL + 0x0008: 0x0008, # BACKSPACE + 0x0009: 0x0009, # HORIZONTAL TABULATION + 0x000a: 0x000a, # LINE FEED + 0x000b: 0x000b, # VERTICAL TABULATION + 0x000c: 0x000c, # FORM FEED + 0x000d: 0x000d, # CARRIAGE RETURN + 0x000e: 0x000e, # SHIFT OUT + 0x000f: 0x000f, # SHIFT IN + 0x0010: 0x0010, # DATA LINK ESCAPE + 0x0011: 0x0011, # DEVICE CONTROL ONE + 0x0012: 0x0012, # DEVICE CONTROL TWO + 0x0013: 0x0013, # DEVICE CONTROL THREE + 0x0014: 0x0014, # DEVICE CONTROL FOUR + 0x0015: 0x0015, # NEGATIVE ACKNOWLEDGE + 0x0016: 0x0016, # SYNCHRONOUS IDLE + 0x0017: 0x0017, # END OF TRANSMISSION BLOCK + 0x0018: 0x0018, # CANCEL + 0x0019: 0x0019, # END OF MEDIUM + 0x001a: 0x001a, # SUBSTITUTE + 0x001b: 0x001b, # ESCAPE + 0x001c: 0x001c, # FILE SEPARATOR + 0x001d: 0x001d, # GROUP SEPARATOR + 0x001e: 0x001e, # RECORD SEPARATOR + 0x001f: 0x001f, # UNIT SEPARATOR + 0x0020: 0x0020, # SPACE + 0x0021: 0x0021, # EXCLAMATION MARK + 0x0022: 0x0022, # QUOTATION MARK + 0x0023: 0x0023, # NUMBER SIGN + 0x0024: 0x0024, # DOLLAR SIGN + 0x0025: 0x0025, # PERCENT SIGN + 0x0026: 0x0026, # AMPERSAND + 0x0027: 0x0027, # APOSTROPHE + 0x0028: 0x0028, # LEFT PARENTHESIS + 0x0029: 0x0029, # RIGHT PARENTHESIS + 0x002a: 0x002a, # ASTERISK + 0x002b: 0x002b, # PLUS SIGN + 0x002c: 0x002c, # COMMA + 0x002d: 0x002d, # HYPHEN-MINUS + 0x002e: 0x002e, # FULL STOP + 0x002f: 0x002f, # SOLIDUS + 0x0030: 0x0030, # DIGIT ZERO + 0x0031: 0x0031, # DIGIT ONE + 0x0032: 0x0032, # DIGIT TWO + 0x0033: 0x0033, # DIGIT THREE + 0x0034: 0x0034, # DIGIT FOUR + 0x0035: 0x0035, # DIGIT FIVE + 0x0036: 0x0036, # DIGIT SIX + 0x0037: 0x0037, # DIGIT SEVEN + 0x0038: 0x0038, # DIGIT EIGHT + 0x0039: 0x0039, # DIGIT NINE + 0x003a: 0x003a, # COLON + 0x003b: 0x003b, # SEMICOLON + 0x003c: 0x003c, # LESS-THAN SIGN + 0x003d: 0x003d, # EQUALS SIGN + 0x003e: 0x003e, # GREATER-THAN SIGN + 0x003f: 0x003f, # QUESTION MARK + 0x0040: 0x0040, # COMMERCIAL AT + 0x0041: 0x0041, # LATIN CAPITAL LETTER A + 0x0042: 0x0042, # LATIN CAPITAL LETTER B + 0x0043: 0x0043, # LATIN CAPITAL LETTER C + 0x0044: 0x0044, # LATIN CAPITAL LETTER D + 0x0045: 0x0045, # LATIN CAPITAL LETTER E + 0x0046: 0x0046, # LATIN CAPITAL LETTER F + 0x0047: 0x0047, # LATIN CAPITAL LETTER G + 0x0048: 0x0048, # LATIN CAPITAL LETTER H + 0x0049: 0x0049, # LATIN CAPITAL LETTER I + 0x004a: 0x004a, # LATIN CAPITAL LETTER J + 0x004b: 0x004b, # LATIN CAPITAL LETTER K + 0x004c: 0x004c, # LATIN CAPITAL LETTER L + 0x004d: 0x004d, # LATIN CAPITAL LETTER M + 0x004e: 0x004e, # LATIN CAPITAL LETTER N + 0x004f: 0x004f, # LATIN CAPITAL LETTER O + 0x0050: 0x0050, # LATIN CAPITAL LETTER P + 0x0051: 0x0051, # LATIN CAPITAL LETTER Q + 0x0052: 0x0052, # LATIN CAPITAL LETTER R + 0x0053: 0x0053, # LATIN CAPITAL LETTER S + 0x0054: 0x0054, # LATIN CAPITAL LETTER T + 0x0055: 0x0055, # LATIN CAPITAL LETTER U + 0x0056: 0x0056, # LATIN CAPITAL LETTER V + 0x0057: 0x0057, # LATIN CAPITAL LETTER W + 0x0058: 0x0058, # LATIN CAPITAL LETTER X + 0x0059: 0x0059, # LATIN CAPITAL LETTER Y + 0x005a: 0x005a, # LATIN CAPITAL LETTER Z + 0x005b: 0x005b, # LEFT SQUARE BRACKET + 0x005c: 0x005c, # REVERSE SOLIDUS + 0x005d: 0x005d, # RIGHT SQUARE BRACKET + 0x005e: 0x005e, # CIRCUMFLEX ACCENT + 0x005f: 0x005f, # LOW LINE + 0x0060: 0x0060, # GRAVE ACCENT + 0x0061: 0x0061, # LATIN SMALL LETTER A + 0x0062: 0x0062, # LATIN SMALL LETTER B + 0x0063: 0x0063, # LATIN SMALL LETTER C + 0x0064: 0x0064, # LATIN SMALL LETTER D + 0x0065: 0x0065, # LATIN SMALL LETTER E + 0x0066: 0x0066, # LATIN SMALL LETTER F + 0x0067: 0x0067, # LATIN SMALL LETTER G + 0x0068: 0x0068, # LATIN SMALL LETTER H + 0x0069: 0x0069, # LATIN SMALL LETTER I + 0x006a: 0x006a, # LATIN SMALL LETTER J + 0x006b: 0x006b, # LATIN SMALL LETTER K + 0x006c: 0x006c, # LATIN SMALL LETTER L + 0x006d: 0x006d, # LATIN SMALL LETTER M + 0x006e: 0x006e, # LATIN SMALL LETTER N + 0x006f: 0x006f, # LATIN SMALL LETTER O + 0x0070: 0x0070, # LATIN SMALL LETTER P + 0x0071: 0x0071, # LATIN SMALL LETTER Q + 0x0072: 0x0072, # LATIN SMALL LETTER R + 0x0073: 0x0073, # LATIN SMALL LETTER S + 0x0074: 0x0074, # LATIN SMALL LETTER T + 0x0075: 0x0075, # LATIN SMALL LETTER U + 0x0076: 0x0076, # LATIN SMALL LETTER V + 0x0077: 0x0077, # LATIN SMALL LETTER W + 0x0078: 0x0078, # LATIN SMALL LETTER X + 0x0079: 0x0079, # LATIN SMALL LETTER Y + 0x007a: 0x007a, # LATIN SMALL LETTER Z + 0x007b: 0x007b, # LEFT CURLY BRACKET + 0x007c: 0x007c, # VERTICAL LINE + 0x007d: 0x007d, # RIGHT CURLY BRACKET + 0x007e: 0x007e, # TILDE + 0x007f: 0x007f, # DELETE + 0x00a0: 0x00ff, # NO-BREAK SPACE + 0x00a3: 0x009c, # POUND SIGN + 0x00a6: 0x008a, # BROKEN BAR + 0x00a7: 0x00f5, # SECTION SIGN + 0x00a8: 0x00f9, # DIAERESIS + 0x00a9: 0x0097, # COPYRIGHT SIGN + 0x00ab: 0x00ae, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00ac: 0x0089, # NOT SIGN + 0x00ad: 0x00f0, # SOFT HYPHEN + 0x00b0: 0x00f8, # DEGREE SIGN + 0x00b1: 0x00f1, # PLUS-MINUS SIGN + 0x00b2: 0x0099, # SUPERSCRIPT TWO + 0x00b3: 0x009a, # SUPERSCRIPT THREE + 0x00b7: 0x0088, # MIDDLE DOT + 0x00bb: 0x00af, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + 0x00bd: 0x00ab, # VULGAR FRACTION ONE HALF + 0x0384: 0x00ef, # GREEK TONOS + 0x0385: 0x00f7, # GREEK DIALYTIKA TONOS + 0x0386: 0x0086, # GREEK CAPITAL LETTER ALPHA WITH TONOS + 0x0388: 0x008d, # GREEK CAPITAL LETTER EPSILON WITH TONOS + 0x0389: 0x008f, # GREEK CAPITAL LETTER ETA WITH TONOS + 0x038a: 0x0090, # GREEK CAPITAL LETTER IOTA WITH TONOS + 0x038c: 0x0092, # GREEK CAPITAL LETTER OMICRON WITH TONOS + 0x038e: 0x0095, # GREEK CAPITAL LETTER UPSILON WITH TONOS + 0x038f: 0x0098, # GREEK CAPITAL LETTER OMEGA WITH TONOS + 0x0390: 0x00a1, # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS + 0x0391: 0x00a4, # GREEK CAPITAL LETTER ALPHA + 0x0392: 0x00a5, # GREEK CAPITAL LETTER BETA + 0x0393: 0x00a6, # GREEK CAPITAL LETTER GAMMA + 0x0394: 0x00a7, # GREEK CAPITAL LETTER DELTA + 0x0395: 0x00a8, # GREEK CAPITAL LETTER EPSILON + 0x0396: 0x00a9, # GREEK CAPITAL LETTER ZETA + 0x0397: 0x00aa, # GREEK CAPITAL LETTER ETA + 0x0398: 0x00ac, # GREEK CAPITAL LETTER THETA + 0x0399: 0x00ad, # GREEK CAPITAL LETTER IOTA + 0x039a: 0x00b5, # GREEK CAPITAL LETTER KAPPA + 0x039b: 0x00b6, # GREEK CAPITAL LETTER LAMDA + 0x039c: 0x00b7, # GREEK CAPITAL LETTER MU + 0x039d: 0x00b8, # GREEK CAPITAL LETTER NU + 0x039e: 0x00bd, # GREEK CAPITAL LETTER XI + 0x039f: 0x00be, # GREEK CAPITAL LETTER OMICRON + 0x03a0: 0x00c6, # GREEK CAPITAL LETTER PI + 0x03a1: 0x00c7, # GREEK CAPITAL LETTER RHO + 0x03a3: 0x00cf, # GREEK CAPITAL LETTER SIGMA + 0x03a4: 0x00d0, # GREEK CAPITAL LETTER TAU + 0x03a5: 0x00d1, # GREEK CAPITAL LETTER UPSILON + 0x03a6: 0x00d2, # GREEK CAPITAL LETTER PHI + 0x03a7: 0x00d3, # GREEK CAPITAL LETTER CHI + 0x03a8: 0x00d4, # GREEK CAPITAL LETTER PSI + 0x03a9: 0x00d5, # GREEK CAPITAL LETTER OMEGA + 0x03aa: 0x0091, # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA + 0x03ab: 0x0096, # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA + 0x03ac: 0x009b, # GREEK SMALL LETTER ALPHA WITH TONOS + 0x03ad: 0x009d, # GREEK SMALL LETTER EPSILON WITH TONOS + 0x03ae: 0x009e, # GREEK SMALL LETTER ETA WITH TONOS + 0x03af: 0x009f, # GREEK SMALL LETTER IOTA WITH TONOS + 0x03b0: 0x00fc, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS + 0x03b1: 0x00d6, # GREEK SMALL LETTER ALPHA + 0x03b2: 0x00d7, # GREEK SMALL LETTER BETA + 0x03b3: 0x00d8, # GREEK SMALL LETTER GAMMA + 0x03b4: 0x00dd, # GREEK SMALL LETTER DELTA + 0x03b5: 0x00de, # GREEK SMALL LETTER EPSILON + 0x03b6: 0x00e0, # GREEK SMALL LETTER ZETA + 0x03b7: 0x00e1, # GREEK SMALL LETTER ETA + 0x03b8: 0x00e2, # GREEK SMALL LETTER THETA + 0x03b9: 0x00e3, # GREEK SMALL LETTER IOTA + 0x03ba: 0x00e4, # GREEK SMALL LETTER KAPPA + 0x03bb: 0x00e5, # GREEK SMALL LETTER LAMDA + 0x03bc: 0x00e6, # GREEK SMALL LETTER MU + 0x03bd: 0x00e7, # GREEK SMALL LETTER NU + 0x03be: 0x00e8, # GREEK SMALL LETTER XI + 0x03bf: 0x00e9, # GREEK SMALL LETTER OMICRON + 0x03c0: 0x00ea, # GREEK SMALL LETTER PI + 0x03c1: 0x00eb, # GREEK SMALL LETTER RHO + 0x03c2: 0x00ed, # GREEK SMALL LETTER FINAL SIGMA + 0x03c3: 0x00ec, # GREEK SMALL LETTER SIGMA + 0x03c4: 0x00ee, # GREEK SMALL LETTER TAU + 0x03c5: 0x00f2, # GREEK SMALL LETTER UPSILON + 0x03c6: 0x00f3, # GREEK SMALL LETTER PHI + 0x03c7: 0x00f4, # GREEK SMALL LETTER CHI + 0x03c8: 0x00f6, # GREEK SMALL LETTER PSI + 0x03c9: 0x00fa, # GREEK SMALL LETTER OMEGA + 0x03ca: 0x00a0, # GREEK SMALL LETTER IOTA WITH DIALYTIKA + 0x03cb: 0x00fb, # GREEK SMALL LETTER UPSILON WITH DIALYTIKA + 0x03cc: 0x00a2, # GREEK SMALL LETTER OMICRON WITH TONOS + 0x03cd: 0x00a3, # GREEK SMALL LETTER UPSILON WITH TONOS + 0x03ce: 0x00fd, # GREEK SMALL LETTER OMEGA WITH TONOS + 0x2015: 0x008e, # HORIZONTAL BAR + 0x2018: 0x008b, # LEFT SINGLE QUOTATION MARK + 0x2019: 0x008c, # RIGHT SINGLE QUOTATION MARK + 0x2500: 0x00c4, # BOX DRAWINGS LIGHT HORIZONTAL + 0x2502: 0x00b3, # BOX DRAWINGS LIGHT VERTICAL + 0x250c: 0x00da, # BOX DRAWINGS LIGHT DOWN AND RIGHT + 0x2510: 0x00bf, # BOX DRAWINGS LIGHT DOWN AND LEFT + 0x2514: 0x00c0, # BOX DRAWINGS LIGHT UP AND RIGHT + 0x2518: 0x00d9, # BOX DRAWINGS LIGHT UP AND LEFT + 0x251c: 0x00c3, # BOX DRAWINGS LIGHT VERTICAL AND RIGHT + 0x2524: 0x00b4, # BOX DRAWINGS LIGHT VERTICAL AND LEFT + 0x252c: 0x00c2, # BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + 0x2534: 0x00c1, # BOX DRAWINGS LIGHT UP AND HORIZONTAL + 0x253c: 0x00c5, # BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + 0x2550: 0x00cd, # BOX DRAWINGS DOUBLE HORIZONTAL + 0x2551: 0x00ba, # BOX DRAWINGS DOUBLE VERTICAL + 0x2554: 0x00c9, # BOX DRAWINGS DOUBLE DOWN AND RIGHT + 0x2557: 0x00bb, # BOX DRAWINGS DOUBLE DOWN AND LEFT + 0x255a: 0x00c8, # BOX DRAWINGS DOUBLE UP AND RIGHT + 0x255d: 0x00bc, # BOX DRAWINGS DOUBLE UP AND LEFT + 0x2560: 0x00cc, # BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + 0x2563: 0x00b9, # BOX DRAWINGS DOUBLE VERTICAL AND LEFT + 0x2566: 0x00cb, # BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + 0x2569: 0x00ca, # BOX DRAWINGS DOUBLE UP AND HORIZONTAL + 0x256c: 0x00ce, # BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + 0x2580: 0x00df, # UPPER HALF BLOCK + 0x2584: 0x00dc, # LOWER HALF BLOCK + 0x2588: 0x00db, # FULL BLOCK + 0x2591: 0x00b0, # LIGHT SHADE + 0x2592: 0x00b1, # MEDIUM SHADE + 0x2593: 0x00b2, # DARK SHADE + 0x25a0: 0x00fe, # BLACK SQUARE +} diff --git a/contrib/tools/python3/src/Lib/encodings/cp874.py b/contrib/tools/python3/src/Lib/encodings/cp874.py new file mode 100644 index 0000000000..59bfcbc98a --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp874.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec cp874 generated from 'MAPPINGS/VENDORS/MICSFT/WINDOWS/CP874.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp874', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\u20ac' # 0x80 -> EURO SIGN + '\ufffe' # 0x81 -> UNDEFINED + '\ufffe' # 0x82 -> UNDEFINED + '\ufffe' # 0x83 -> UNDEFINED + '\ufffe' # 0x84 -> UNDEFINED + '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS + '\ufffe' # 0x86 -> UNDEFINED + '\ufffe' # 0x87 -> UNDEFINED + '\ufffe' # 0x88 -> UNDEFINED + '\ufffe' # 0x89 -> UNDEFINED + '\ufffe' # 0x8A -> UNDEFINED + '\ufffe' # 0x8B -> UNDEFINED + '\ufffe' # 0x8C -> UNDEFINED + '\ufffe' # 0x8D -> UNDEFINED + '\ufffe' # 0x8E -> UNDEFINED + '\ufffe' # 0x8F -> UNDEFINED + '\ufffe' # 0x90 -> UNDEFINED + '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK + '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK + '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK + '\u2022' # 0x95 -> BULLET + '\u2013' # 0x96 -> EN DASH + '\u2014' # 0x97 -> EM DASH + '\ufffe' # 0x98 -> UNDEFINED + '\ufffe' # 0x99 -> UNDEFINED + '\ufffe' # 0x9A -> UNDEFINED + '\ufffe' # 0x9B -> UNDEFINED + '\ufffe' # 0x9C -> UNDEFINED + '\ufffe' # 0x9D -> UNDEFINED + '\ufffe' # 0x9E -> UNDEFINED + '\ufffe' # 0x9F -> UNDEFINED + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\u0e01' # 0xA1 -> THAI CHARACTER KO KAI + '\u0e02' # 0xA2 -> THAI CHARACTER KHO KHAI + '\u0e03' # 0xA3 -> THAI CHARACTER KHO KHUAT + '\u0e04' # 0xA4 -> THAI CHARACTER KHO KHWAI + '\u0e05' # 0xA5 -> THAI CHARACTER KHO KHON + '\u0e06' # 0xA6 -> THAI CHARACTER KHO RAKHANG + '\u0e07' # 0xA7 -> THAI CHARACTER NGO NGU + '\u0e08' # 0xA8 -> THAI CHARACTER CHO CHAN + '\u0e09' # 0xA9 -> THAI CHARACTER CHO CHING + '\u0e0a' # 0xAA -> THAI CHARACTER CHO CHANG + '\u0e0b' # 0xAB -> THAI CHARACTER SO SO + '\u0e0c' # 0xAC -> THAI CHARACTER CHO CHOE + '\u0e0d' # 0xAD -> THAI CHARACTER YO YING + '\u0e0e' # 0xAE -> THAI CHARACTER DO CHADA + '\u0e0f' # 0xAF -> THAI CHARACTER TO PATAK + '\u0e10' # 0xB0 -> THAI CHARACTER THO THAN + '\u0e11' # 0xB1 -> THAI CHARACTER THO NANGMONTHO + '\u0e12' # 0xB2 -> THAI CHARACTER THO PHUTHAO + '\u0e13' # 0xB3 -> THAI CHARACTER NO NEN + '\u0e14' # 0xB4 -> THAI CHARACTER DO DEK + '\u0e15' # 0xB5 -> THAI CHARACTER TO TAO + '\u0e16' # 0xB6 -> THAI CHARACTER THO THUNG + '\u0e17' # 0xB7 -> THAI CHARACTER THO THAHAN + '\u0e18' # 0xB8 -> THAI CHARACTER THO THONG + '\u0e19' # 0xB9 -> THAI CHARACTER NO NU + '\u0e1a' # 0xBA -> THAI CHARACTER BO BAIMAI + '\u0e1b' # 0xBB -> THAI CHARACTER PO PLA + '\u0e1c' # 0xBC -> THAI CHARACTER PHO PHUNG + '\u0e1d' # 0xBD -> THAI CHARACTER FO FA + '\u0e1e' # 0xBE -> THAI CHARACTER PHO PHAN + '\u0e1f' # 0xBF -> THAI CHARACTER FO FAN + '\u0e20' # 0xC0 -> THAI CHARACTER PHO SAMPHAO + '\u0e21' # 0xC1 -> THAI CHARACTER MO MA + '\u0e22' # 0xC2 -> THAI CHARACTER YO YAK + '\u0e23' # 0xC3 -> THAI CHARACTER RO RUA + '\u0e24' # 0xC4 -> THAI CHARACTER RU + '\u0e25' # 0xC5 -> THAI CHARACTER LO LING + '\u0e26' # 0xC6 -> THAI CHARACTER LU + '\u0e27' # 0xC7 -> THAI CHARACTER WO WAEN + '\u0e28' # 0xC8 -> THAI CHARACTER SO SALA + '\u0e29' # 0xC9 -> THAI CHARACTER SO RUSI + '\u0e2a' # 0xCA -> THAI CHARACTER SO SUA + '\u0e2b' # 0xCB -> THAI CHARACTER HO HIP + '\u0e2c' # 0xCC -> THAI CHARACTER LO CHULA + '\u0e2d' # 0xCD -> THAI CHARACTER O ANG + '\u0e2e' # 0xCE -> THAI CHARACTER HO NOKHUK + '\u0e2f' # 0xCF -> THAI CHARACTER PAIYANNOI + '\u0e30' # 0xD0 -> THAI CHARACTER SARA A + '\u0e31' # 0xD1 -> THAI CHARACTER MAI HAN-AKAT + '\u0e32' # 0xD2 -> THAI CHARACTER SARA AA + '\u0e33' # 0xD3 -> THAI CHARACTER SARA AM + '\u0e34' # 0xD4 -> THAI CHARACTER SARA I + '\u0e35' # 0xD5 -> THAI CHARACTER SARA II + '\u0e36' # 0xD6 -> THAI CHARACTER SARA UE + '\u0e37' # 0xD7 -> THAI CHARACTER SARA UEE + '\u0e38' # 0xD8 -> THAI CHARACTER SARA U + '\u0e39' # 0xD9 -> THAI CHARACTER SARA UU + '\u0e3a' # 0xDA -> THAI CHARACTER PHINTHU + '\ufffe' # 0xDB -> UNDEFINED + '\ufffe' # 0xDC -> UNDEFINED + '\ufffe' # 0xDD -> UNDEFINED + '\ufffe' # 0xDE -> UNDEFINED + '\u0e3f' # 0xDF -> THAI CURRENCY SYMBOL BAHT + '\u0e40' # 0xE0 -> THAI CHARACTER SARA E + '\u0e41' # 0xE1 -> THAI CHARACTER SARA AE + '\u0e42' # 0xE2 -> THAI CHARACTER SARA O + '\u0e43' # 0xE3 -> THAI CHARACTER SARA AI MAIMUAN + '\u0e44' # 0xE4 -> THAI CHARACTER SARA AI MAIMALAI + '\u0e45' # 0xE5 -> THAI CHARACTER LAKKHANGYAO + '\u0e46' # 0xE6 -> THAI CHARACTER MAIYAMOK + '\u0e47' # 0xE7 -> THAI CHARACTER MAITAIKHU + '\u0e48' # 0xE8 -> THAI CHARACTER MAI EK + '\u0e49' # 0xE9 -> THAI CHARACTER MAI THO + '\u0e4a' # 0xEA -> THAI CHARACTER MAI TRI + '\u0e4b' # 0xEB -> THAI CHARACTER MAI CHATTAWA + '\u0e4c' # 0xEC -> THAI CHARACTER THANTHAKHAT + '\u0e4d' # 0xED -> THAI CHARACTER NIKHAHIT + '\u0e4e' # 0xEE -> THAI CHARACTER YAMAKKAN + '\u0e4f' # 0xEF -> THAI CHARACTER FONGMAN + '\u0e50' # 0xF0 -> THAI DIGIT ZERO + '\u0e51' # 0xF1 -> THAI DIGIT ONE + '\u0e52' # 0xF2 -> THAI DIGIT TWO + '\u0e53' # 0xF3 -> THAI DIGIT THREE + '\u0e54' # 0xF4 -> THAI DIGIT FOUR + '\u0e55' # 0xF5 -> THAI DIGIT FIVE + '\u0e56' # 0xF6 -> THAI DIGIT SIX + '\u0e57' # 0xF7 -> THAI DIGIT SEVEN + '\u0e58' # 0xF8 -> THAI DIGIT EIGHT + '\u0e59' # 0xF9 -> THAI DIGIT NINE + '\u0e5a' # 0xFA -> THAI CHARACTER ANGKHANKHU + '\u0e5b' # 0xFB -> THAI CHARACTER KHOMUT + '\ufffe' # 0xFC -> UNDEFINED + '\ufffe' # 0xFD -> UNDEFINED + '\ufffe' # 0xFE -> UNDEFINED + '\ufffe' # 0xFF -> UNDEFINED +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/cp875.py b/contrib/tools/python3/src/Lib/encodings/cp875.py new file mode 100644 index 0000000000..c25a5a43bc --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp875.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec cp875 generated from 'MAPPINGS/VENDORS/MICSFT/EBCDIC/CP875.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='cp875', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x9c' # 0x04 -> CONTROL + '\t' # 0x05 -> HORIZONTAL TABULATION + '\x86' # 0x06 -> CONTROL + '\x7f' # 0x07 -> DELETE + '\x97' # 0x08 -> CONTROL + '\x8d' # 0x09 -> CONTROL + '\x8e' # 0x0A -> CONTROL + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x9d' # 0x14 -> CONTROL + '\x85' # 0x15 -> CONTROL + '\x08' # 0x16 -> BACKSPACE + '\x87' # 0x17 -> CONTROL + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x92' # 0x1A -> CONTROL + '\x8f' # 0x1B -> CONTROL + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + '\x80' # 0x20 -> CONTROL + '\x81' # 0x21 -> CONTROL + '\x82' # 0x22 -> CONTROL + '\x83' # 0x23 -> CONTROL + '\x84' # 0x24 -> CONTROL + '\n' # 0x25 -> LINE FEED + '\x17' # 0x26 -> END OF TRANSMISSION BLOCK + '\x1b' # 0x27 -> ESCAPE + '\x88' # 0x28 -> CONTROL + '\x89' # 0x29 -> CONTROL + '\x8a' # 0x2A -> CONTROL + '\x8b' # 0x2B -> CONTROL + '\x8c' # 0x2C -> CONTROL + '\x05' # 0x2D -> ENQUIRY + '\x06' # 0x2E -> ACKNOWLEDGE + '\x07' # 0x2F -> BELL + '\x90' # 0x30 -> CONTROL + '\x91' # 0x31 -> CONTROL + '\x16' # 0x32 -> SYNCHRONOUS IDLE + '\x93' # 0x33 -> CONTROL + '\x94' # 0x34 -> CONTROL + '\x95' # 0x35 -> CONTROL + '\x96' # 0x36 -> CONTROL + '\x04' # 0x37 -> END OF TRANSMISSION + '\x98' # 0x38 -> CONTROL + '\x99' # 0x39 -> CONTROL + '\x9a' # 0x3A -> CONTROL + '\x9b' # 0x3B -> CONTROL + '\x14' # 0x3C -> DEVICE CONTROL FOUR + '\x15' # 0x3D -> NEGATIVE ACKNOWLEDGE + '\x9e' # 0x3E -> CONTROL + '\x1a' # 0x3F -> SUBSTITUTE + ' ' # 0x40 -> SPACE + '\u0391' # 0x41 -> GREEK CAPITAL LETTER ALPHA + '\u0392' # 0x42 -> GREEK CAPITAL LETTER BETA + '\u0393' # 0x43 -> GREEK CAPITAL LETTER GAMMA + '\u0394' # 0x44 -> GREEK CAPITAL LETTER DELTA + '\u0395' # 0x45 -> GREEK CAPITAL LETTER EPSILON + '\u0396' # 0x46 -> GREEK CAPITAL LETTER ZETA + '\u0397' # 0x47 -> GREEK CAPITAL LETTER ETA + '\u0398' # 0x48 -> GREEK CAPITAL LETTER THETA + '\u0399' # 0x49 -> GREEK CAPITAL LETTER IOTA + '[' # 0x4A -> LEFT SQUARE BRACKET + '.' # 0x4B -> FULL STOP + '<' # 0x4C -> LESS-THAN SIGN + '(' # 0x4D -> LEFT PARENTHESIS + '+' # 0x4E -> PLUS SIGN + '!' # 0x4F -> EXCLAMATION MARK + '&' # 0x50 -> AMPERSAND + '\u039a' # 0x51 -> GREEK CAPITAL LETTER KAPPA + '\u039b' # 0x52 -> GREEK CAPITAL LETTER LAMDA + '\u039c' # 0x53 -> GREEK CAPITAL LETTER MU + '\u039d' # 0x54 -> GREEK CAPITAL LETTER NU + '\u039e' # 0x55 -> GREEK CAPITAL LETTER XI + '\u039f' # 0x56 -> GREEK CAPITAL LETTER OMICRON + '\u03a0' # 0x57 -> GREEK CAPITAL LETTER PI + '\u03a1' # 0x58 -> GREEK CAPITAL LETTER RHO + '\u03a3' # 0x59 -> GREEK CAPITAL LETTER SIGMA + ']' # 0x5A -> RIGHT SQUARE BRACKET + '$' # 0x5B -> DOLLAR SIGN + '*' # 0x5C -> ASTERISK + ')' # 0x5D -> RIGHT PARENTHESIS + ';' # 0x5E -> SEMICOLON + '^' # 0x5F -> CIRCUMFLEX ACCENT + '-' # 0x60 -> HYPHEN-MINUS + '/' # 0x61 -> SOLIDUS + '\u03a4' # 0x62 -> GREEK CAPITAL LETTER TAU + '\u03a5' # 0x63 -> GREEK CAPITAL LETTER UPSILON + '\u03a6' # 0x64 -> GREEK CAPITAL LETTER PHI + '\u03a7' # 0x65 -> GREEK CAPITAL LETTER CHI + '\u03a8' # 0x66 -> GREEK CAPITAL LETTER PSI + '\u03a9' # 0x67 -> GREEK CAPITAL LETTER OMEGA + '\u03aa' # 0x68 -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA + '\u03ab' # 0x69 -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA + '|' # 0x6A -> VERTICAL LINE + ',' # 0x6B -> COMMA + '%' # 0x6C -> PERCENT SIGN + '_' # 0x6D -> LOW LINE + '>' # 0x6E -> GREATER-THAN SIGN + '?' # 0x6F -> QUESTION MARK + '\xa8' # 0x70 -> DIAERESIS + '\u0386' # 0x71 -> GREEK CAPITAL LETTER ALPHA WITH TONOS + '\u0388' # 0x72 -> GREEK CAPITAL LETTER EPSILON WITH TONOS + '\u0389' # 0x73 -> GREEK CAPITAL LETTER ETA WITH TONOS + '\xa0' # 0x74 -> NO-BREAK SPACE + '\u038a' # 0x75 -> GREEK CAPITAL LETTER IOTA WITH TONOS + '\u038c' # 0x76 -> GREEK CAPITAL LETTER OMICRON WITH TONOS + '\u038e' # 0x77 -> GREEK CAPITAL LETTER UPSILON WITH TONOS + '\u038f' # 0x78 -> GREEK CAPITAL LETTER OMEGA WITH TONOS + '`' # 0x79 -> GRAVE ACCENT + ':' # 0x7A -> COLON + '#' # 0x7B -> NUMBER SIGN + '@' # 0x7C -> COMMERCIAL AT + "'" # 0x7D -> APOSTROPHE + '=' # 0x7E -> EQUALS SIGN + '"' # 0x7F -> QUOTATION MARK + '\u0385' # 0x80 -> GREEK DIALYTIKA TONOS + 'a' # 0x81 -> LATIN SMALL LETTER A + 'b' # 0x82 -> LATIN SMALL LETTER B + 'c' # 0x83 -> LATIN SMALL LETTER C + 'd' # 0x84 -> LATIN SMALL LETTER D + 'e' # 0x85 -> LATIN SMALL LETTER E + 'f' # 0x86 -> LATIN SMALL LETTER F + 'g' # 0x87 -> LATIN SMALL LETTER G + 'h' # 0x88 -> LATIN SMALL LETTER H + 'i' # 0x89 -> LATIN SMALL LETTER I + '\u03b1' # 0x8A -> GREEK SMALL LETTER ALPHA + '\u03b2' # 0x8B -> GREEK SMALL LETTER BETA + '\u03b3' # 0x8C -> GREEK SMALL LETTER GAMMA + '\u03b4' # 0x8D -> GREEK SMALL LETTER DELTA + '\u03b5' # 0x8E -> GREEK SMALL LETTER EPSILON + '\u03b6' # 0x8F -> GREEK SMALL LETTER ZETA + '\xb0' # 0x90 -> DEGREE SIGN + 'j' # 0x91 -> LATIN SMALL LETTER J + 'k' # 0x92 -> LATIN SMALL LETTER K + 'l' # 0x93 -> LATIN SMALL LETTER L + 'm' # 0x94 -> LATIN SMALL LETTER M + 'n' # 0x95 -> LATIN SMALL LETTER N + 'o' # 0x96 -> LATIN SMALL LETTER O + 'p' # 0x97 -> LATIN SMALL LETTER P + 'q' # 0x98 -> LATIN SMALL LETTER Q + 'r' # 0x99 -> LATIN SMALL LETTER R + '\u03b7' # 0x9A -> GREEK SMALL LETTER ETA + '\u03b8' # 0x9B -> GREEK SMALL LETTER THETA + '\u03b9' # 0x9C -> GREEK SMALL LETTER IOTA + '\u03ba' # 0x9D -> GREEK SMALL LETTER KAPPA + '\u03bb' # 0x9E -> GREEK SMALL LETTER LAMDA + '\u03bc' # 0x9F -> GREEK SMALL LETTER MU + '\xb4' # 0xA0 -> ACUTE ACCENT + '~' # 0xA1 -> TILDE + 's' # 0xA2 -> LATIN SMALL LETTER S + 't' # 0xA3 -> LATIN SMALL LETTER T + 'u' # 0xA4 -> LATIN SMALL LETTER U + 'v' # 0xA5 -> LATIN SMALL LETTER V + 'w' # 0xA6 -> LATIN SMALL LETTER W + 'x' # 0xA7 -> LATIN SMALL LETTER X + 'y' # 0xA8 -> LATIN SMALL LETTER Y + 'z' # 0xA9 -> LATIN SMALL LETTER Z + '\u03bd' # 0xAA -> GREEK SMALL LETTER NU + '\u03be' # 0xAB -> GREEK SMALL LETTER XI + '\u03bf' # 0xAC -> GREEK SMALL LETTER OMICRON + '\u03c0' # 0xAD -> GREEK SMALL LETTER PI + '\u03c1' # 0xAE -> GREEK SMALL LETTER RHO + '\u03c3' # 0xAF -> GREEK SMALL LETTER SIGMA + '\xa3' # 0xB0 -> POUND SIGN + '\u03ac' # 0xB1 -> GREEK SMALL LETTER ALPHA WITH TONOS + '\u03ad' # 0xB2 -> GREEK SMALL LETTER EPSILON WITH TONOS + '\u03ae' # 0xB3 -> GREEK SMALL LETTER ETA WITH TONOS + '\u03ca' # 0xB4 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA + '\u03af' # 0xB5 -> GREEK SMALL LETTER IOTA WITH TONOS + '\u03cc' # 0xB6 -> GREEK SMALL LETTER OMICRON WITH TONOS + '\u03cd' # 0xB7 -> GREEK SMALL LETTER UPSILON WITH TONOS + '\u03cb' # 0xB8 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA + '\u03ce' # 0xB9 -> GREEK SMALL LETTER OMEGA WITH TONOS + '\u03c2' # 0xBA -> GREEK SMALL LETTER FINAL SIGMA + '\u03c4' # 0xBB -> GREEK SMALL LETTER TAU + '\u03c5' # 0xBC -> GREEK SMALL LETTER UPSILON + '\u03c6' # 0xBD -> GREEK SMALL LETTER PHI + '\u03c7' # 0xBE -> GREEK SMALL LETTER CHI + '\u03c8' # 0xBF -> GREEK SMALL LETTER PSI + '{' # 0xC0 -> LEFT CURLY BRACKET + 'A' # 0xC1 -> LATIN CAPITAL LETTER A + 'B' # 0xC2 -> LATIN CAPITAL LETTER B + 'C' # 0xC3 -> LATIN CAPITAL LETTER C + 'D' # 0xC4 -> LATIN CAPITAL LETTER D + 'E' # 0xC5 -> LATIN CAPITAL LETTER E + 'F' # 0xC6 -> LATIN CAPITAL LETTER F + 'G' # 0xC7 -> LATIN CAPITAL LETTER G + 'H' # 0xC8 -> LATIN CAPITAL LETTER H + 'I' # 0xC9 -> LATIN CAPITAL LETTER I + '\xad' # 0xCA -> SOFT HYPHEN + '\u03c9' # 0xCB -> GREEK SMALL LETTER OMEGA + '\u0390' # 0xCC -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS + '\u03b0' # 0xCD -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS + '\u2018' # 0xCE -> LEFT SINGLE QUOTATION MARK + '\u2015' # 0xCF -> HORIZONTAL BAR + '}' # 0xD0 -> RIGHT CURLY BRACKET + 'J' # 0xD1 -> LATIN CAPITAL LETTER J + 'K' # 0xD2 -> LATIN CAPITAL LETTER K + 'L' # 0xD3 -> LATIN CAPITAL LETTER L + 'M' # 0xD4 -> LATIN CAPITAL LETTER M + 'N' # 0xD5 -> LATIN CAPITAL LETTER N + 'O' # 0xD6 -> LATIN CAPITAL LETTER O + 'P' # 0xD7 -> LATIN CAPITAL LETTER P + 'Q' # 0xD8 -> LATIN CAPITAL LETTER Q + 'R' # 0xD9 -> LATIN CAPITAL LETTER R + '\xb1' # 0xDA -> PLUS-MINUS SIGN + '\xbd' # 0xDB -> VULGAR FRACTION ONE HALF + '\x1a' # 0xDC -> SUBSTITUTE + '\u0387' # 0xDD -> GREEK ANO TELEIA + '\u2019' # 0xDE -> RIGHT SINGLE QUOTATION MARK + '\xa6' # 0xDF -> BROKEN BAR + '\\' # 0xE0 -> REVERSE SOLIDUS + '\x1a' # 0xE1 -> SUBSTITUTE + 'S' # 0xE2 -> LATIN CAPITAL LETTER S + 'T' # 0xE3 -> LATIN CAPITAL LETTER T + 'U' # 0xE4 -> LATIN CAPITAL LETTER U + 'V' # 0xE5 -> LATIN CAPITAL LETTER V + 'W' # 0xE6 -> LATIN CAPITAL LETTER W + 'X' # 0xE7 -> LATIN CAPITAL LETTER X + 'Y' # 0xE8 -> LATIN CAPITAL LETTER Y + 'Z' # 0xE9 -> LATIN CAPITAL LETTER Z + '\xb2' # 0xEA -> SUPERSCRIPT TWO + '\xa7' # 0xEB -> SECTION SIGN + '\x1a' # 0xEC -> SUBSTITUTE + '\x1a' # 0xED -> SUBSTITUTE + '\xab' # 0xEE -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xac' # 0xEF -> NOT SIGN + '0' # 0xF0 -> DIGIT ZERO + '1' # 0xF1 -> DIGIT ONE + '2' # 0xF2 -> DIGIT TWO + '3' # 0xF3 -> DIGIT THREE + '4' # 0xF4 -> DIGIT FOUR + '5' # 0xF5 -> DIGIT FIVE + '6' # 0xF6 -> DIGIT SIX + '7' # 0xF7 -> DIGIT SEVEN + '8' # 0xF8 -> DIGIT EIGHT + '9' # 0xF9 -> DIGIT NINE + '\xb3' # 0xFA -> SUPERSCRIPT THREE + '\xa9' # 0xFB -> COPYRIGHT SIGN + '\x1a' # 0xFC -> SUBSTITUTE + '\x1a' # 0xFD -> SUBSTITUTE + '\xbb' # 0xFE -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\x9f' # 0xFF -> CONTROL +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/cp932.py b/contrib/tools/python3/src/Lib/encodings/cp932.py new file mode 100644 index 0000000000..e01f59b719 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp932.py @@ -0,0 +1,39 @@ +# +# cp932.py: Python Unicode Codec for CP932 +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_jp, codecs +import _multibytecodec as mbc + +codec = _codecs_jp.getcodec('cp932') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='cp932', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/cp949.py b/contrib/tools/python3/src/Lib/encodings/cp949.py new file mode 100644 index 0000000000..627c87125e --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp949.py @@ -0,0 +1,39 @@ +# +# cp949.py: Python Unicode Codec for CP949 +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_kr, codecs +import _multibytecodec as mbc + +codec = _codecs_kr.getcodec('cp949') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='cp949', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/cp950.py b/contrib/tools/python3/src/Lib/encodings/cp950.py new file mode 100644 index 0000000000..39eec5ed0d --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/cp950.py @@ -0,0 +1,39 @@ +# +# cp950.py: Python Unicode Codec for CP950 +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_tw, codecs +import _multibytecodec as mbc + +codec = _codecs_tw.getcodec('cp950') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='cp950', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/euc_jis_2004.py b/contrib/tools/python3/src/Lib/encodings/euc_jis_2004.py new file mode 100644 index 0000000000..72b87aea68 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/euc_jis_2004.py @@ -0,0 +1,39 @@ +# +# euc_jis_2004.py: Python Unicode Codec for EUC_JIS_2004 +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_jp, codecs +import _multibytecodec as mbc + +codec = _codecs_jp.getcodec('euc_jis_2004') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='euc_jis_2004', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/euc_jisx0213.py b/contrib/tools/python3/src/Lib/encodings/euc_jisx0213.py new file mode 100644 index 0000000000..cc47d04112 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/euc_jisx0213.py @@ -0,0 +1,39 @@ +# +# euc_jisx0213.py: Python Unicode Codec for EUC_JISX0213 +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_jp, codecs +import _multibytecodec as mbc + +codec = _codecs_jp.getcodec('euc_jisx0213') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='euc_jisx0213', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/euc_jp.py b/contrib/tools/python3/src/Lib/encodings/euc_jp.py new file mode 100644 index 0000000000..7bcbe4147f --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/euc_jp.py @@ -0,0 +1,39 @@ +# +# euc_jp.py: Python Unicode Codec for EUC_JP +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_jp, codecs +import _multibytecodec as mbc + +codec = _codecs_jp.getcodec('euc_jp') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='euc_jp', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/euc_kr.py b/contrib/tools/python3/src/Lib/encodings/euc_kr.py new file mode 100644 index 0000000000..c1fb1260e8 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/euc_kr.py @@ -0,0 +1,39 @@ +# +# euc_kr.py: Python Unicode Codec for EUC_KR +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_kr, codecs +import _multibytecodec as mbc + +codec = _codecs_kr.getcodec('euc_kr') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='euc_kr', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/gb18030.py b/contrib/tools/python3/src/Lib/encodings/gb18030.py new file mode 100644 index 0000000000..34fb6c366a --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/gb18030.py @@ -0,0 +1,39 @@ +# +# gb18030.py: Python Unicode Codec for GB18030 +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_cn, codecs +import _multibytecodec as mbc + +codec = _codecs_cn.getcodec('gb18030') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='gb18030', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/gb2312.py b/contrib/tools/python3/src/Lib/encodings/gb2312.py new file mode 100644 index 0000000000..3c3b837d61 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/gb2312.py @@ -0,0 +1,39 @@ +# +# gb2312.py: Python Unicode Codec for GB2312 +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_cn, codecs +import _multibytecodec as mbc + +codec = _codecs_cn.getcodec('gb2312') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='gb2312', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/gbk.py b/contrib/tools/python3/src/Lib/encodings/gbk.py new file mode 100644 index 0000000000..1b45db8985 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/gbk.py @@ -0,0 +1,39 @@ +# +# gbk.py: Python Unicode Codec for GBK +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_cn, codecs +import _multibytecodec as mbc + +codec = _codecs_cn.getcodec('gbk') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='gbk', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/hex_codec.py b/contrib/tools/python3/src/Lib/encodings/hex_codec.py new file mode 100644 index 0000000000..9fb1072804 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/hex_codec.py @@ -0,0 +1,55 @@ +"""Python 'hex_codec' Codec - 2-digit hex content transfer encoding. + +This codec de/encodes from bytes to bytes. + +Written by Marc-Andre Lemburg (mal@lemburg.com). +""" + +import codecs +import binascii + +### Codec APIs + +def hex_encode(input, errors='strict'): + assert errors == 'strict' + return (binascii.b2a_hex(input), len(input)) + +def hex_decode(input, errors='strict'): + assert errors == 'strict' + return (binascii.a2b_hex(input), len(input)) + +class Codec(codecs.Codec): + def encode(self, input, errors='strict'): + return hex_encode(input, errors) + def decode(self, input, errors='strict'): + return hex_decode(input, errors) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + assert self.errors == 'strict' + return binascii.b2a_hex(input) + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + assert self.errors == 'strict' + return binascii.a2b_hex(input) + +class StreamWriter(Codec, codecs.StreamWriter): + charbuffertype = bytes + +class StreamReader(Codec, codecs.StreamReader): + charbuffertype = bytes + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='hex', + encode=hex_encode, + decode=hex_decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + _is_text_encoding=False, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/hp_roman8.py b/contrib/tools/python3/src/Lib/encodings/hp_roman8.py new file mode 100644 index 0000000000..58de1033c1 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/hp_roman8.py @@ -0,0 +1,314 @@ +""" Python Character Mapping Codec generated from 'hp_roman8.txt' with gencodec.py. + + Based on data from ftp://dkuug.dk/i18n/charmaps/HP-ROMAN8 (Keld Simonsen) + + Original source: LaserJet IIP Printer User's Manual HP part no + 33471-90901, Hewlet-Packard, June 1989. + + (Used with permission) + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='hp-roman8', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\x80' # 0x80 -> <control> + '\x81' # 0x81 -> <control> + '\x82' # 0x82 -> <control> + '\x83' # 0x83 -> <control> + '\x84' # 0x84 -> <control> + '\x85' # 0x85 -> <control> + '\x86' # 0x86 -> <control> + '\x87' # 0x87 -> <control> + '\x88' # 0x88 -> <control> + '\x89' # 0x89 -> <control> + '\x8a' # 0x8A -> <control> + '\x8b' # 0x8B -> <control> + '\x8c' # 0x8C -> <control> + '\x8d' # 0x8D -> <control> + '\x8e' # 0x8E -> <control> + '\x8f' # 0x8F -> <control> + '\x90' # 0x90 -> <control> + '\x91' # 0x91 -> <control> + '\x92' # 0x92 -> <control> + '\x93' # 0x93 -> <control> + '\x94' # 0x94 -> <control> + '\x95' # 0x95 -> <control> + '\x96' # 0x96 -> <control> + '\x97' # 0x97 -> <control> + '\x98' # 0x98 -> <control> + '\x99' # 0x99 -> <control> + '\x9a' # 0x9A -> <control> + '\x9b' # 0x9B -> <control> + '\x9c' # 0x9C -> <control> + '\x9d' # 0x9D -> <control> + '\x9e' # 0x9E -> <control> + '\x9f' # 0x9F -> <control> + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\xc0' # 0xA1 -> LATIN CAPITAL LETTER A WITH GRAVE + '\xc2' # 0xA2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xc8' # 0xA3 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xca' # 0xA4 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xcb' # 0xA5 -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xce' # 0xA6 -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0xA7 -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\xb4' # 0xA8 -> ACUTE ACCENT + '\u02cb' # 0xA9 -> MODIFIER LETTER GRAVE ACCENT (MANDARIN CHINESE FOURTH TONE) + '\u02c6' # 0xAA -> MODIFIER LETTER CIRCUMFLEX ACCENT + '\xa8' # 0xAB -> DIAERESIS + '\u02dc' # 0xAC -> SMALL TILDE + '\xd9' # 0xAD -> LATIN CAPITAL LETTER U WITH GRAVE + '\xdb' # 0xAE -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\u20a4' # 0xAF -> LIRA SIGN + '\xaf' # 0xB0 -> MACRON + '\xdd' # 0xB1 -> LATIN CAPITAL LETTER Y WITH ACUTE + '\xfd' # 0xB2 -> LATIN SMALL LETTER Y WITH ACUTE + '\xb0' # 0xB3 -> DEGREE SIGN + '\xc7' # 0xB4 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xe7' # 0xB5 -> LATIN SMALL LETTER C WITH CEDILLA + '\xd1' # 0xB6 -> LATIN CAPITAL LETTER N WITH TILDE + '\xf1' # 0xB7 -> LATIN SMALL LETTER N WITH TILDE + '\xa1' # 0xB8 -> INVERTED EXCLAMATION MARK + '\xbf' # 0xB9 -> INVERTED QUESTION MARK + '\xa4' # 0xBA -> CURRENCY SIGN + '\xa3' # 0xBB -> POUND SIGN + '\xa5' # 0xBC -> YEN SIGN + '\xa7' # 0xBD -> SECTION SIGN + '\u0192' # 0xBE -> LATIN SMALL LETTER F WITH HOOK + '\xa2' # 0xBF -> CENT SIGN + '\xe2' # 0xC0 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xea' # 0xC1 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xf4' # 0xC2 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xfb' # 0xC3 -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xe1' # 0xC4 -> LATIN SMALL LETTER A WITH ACUTE + '\xe9' # 0xC5 -> LATIN SMALL LETTER E WITH ACUTE + '\xf3' # 0xC6 -> LATIN SMALL LETTER O WITH ACUTE + '\xfa' # 0xC7 -> LATIN SMALL LETTER U WITH ACUTE + '\xe0' # 0xC8 -> LATIN SMALL LETTER A WITH GRAVE + '\xe8' # 0xC9 -> LATIN SMALL LETTER E WITH GRAVE + '\xf2' # 0xCA -> LATIN SMALL LETTER O WITH GRAVE + '\xf9' # 0xCB -> LATIN SMALL LETTER U WITH GRAVE + '\xe4' # 0xCC -> LATIN SMALL LETTER A WITH DIAERESIS + '\xeb' # 0xCD -> LATIN SMALL LETTER E WITH DIAERESIS + '\xf6' # 0xCE -> LATIN SMALL LETTER O WITH DIAERESIS + '\xfc' # 0xCF -> LATIN SMALL LETTER U WITH DIAERESIS + '\xc5' # 0xD0 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xee' # 0xD1 -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xd8' # 0xD2 -> LATIN CAPITAL LETTER O WITH STROKE + '\xc6' # 0xD3 -> LATIN CAPITAL LETTER AE + '\xe5' # 0xD4 -> LATIN SMALL LETTER A WITH RING ABOVE + '\xed' # 0xD5 -> LATIN SMALL LETTER I WITH ACUTE + '\xf8' # 0xD6 -> LATIN SMALL LETTER O WITH STROKE + '\xe6' # 0xD7 -> LATIN SMALL LETTER AE + '\xc4' # 0xD8 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xec' # 0xD9 -> LATIN SMALL LETTER I WITH GRAVE + '\xd6' # 0xDA -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xdc' # 0xDB -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xc9' # 0xDC -> LATIN CAPITAL LETTER E WITH ACUTE + '\xef' # 0xDD -> LATIN SMALL LETTER I WITH DIAERESIS + '\xdf' # 0xDE -> LATIN SMALL LETTER SHARP S (GERMAN) + '\xd4' # 0xDF -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\xc1' # 0xE0 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc3' # 0xE1 -> LATIN CAPITAL LETTER A WITH TILDE + '\xe3' # 0xE2 -> LATIN SMALL LETTER A WITH TILDE + '\xd0' # 0xE3 -> LATIN CAPITAL LETTER ETH (ICELANDIC) + '\xf0' # 0xE4 -> LATIN SMALL LETTER ETH (ICELANDIC) + '\xcd' # 0xE5 -> LATIN CAPITAL LETTER I WITH ACUTE + '\xcc' # 0xE6 -> LATIN CAPITAL LETTER I WITH GRAVE + '\xd3' # 0xE7 -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd2' # 0xE8 -> LATIN CAPITAL LETTER O WITH GRAVE + '\xd5' # 0xE9 -> LATIN CAPITAL LETTER O WITH TILDE + '\xf5' # 0xEA -> LATIN SMALL LETTER O WITH TILDE + '\u0160' # 0xEB -> LATIN CAPITAL LETTER S WITH CARON + '\u0161' # 0xEC -> LATIN SMALL LETTER S WITH CARON + '\xda' # 0xED -> LATIN CAPITAL LETTER U WITH ACUTE + '\u0178' # 0xEE -> LATIN CAPITAL LETTER Y WITH DIAERESIS + '\xff' # 0xEF -> LATIN SMALL LETTER Y WITH DIAERESIS + '\xde' # 0xF0 -> LATIN CAPITAL LETTER THORN (ICELANDIC) + '\xfe' # 0xF1 -> LATIN SMALL LETTER THORN (ICELANDIC) + '\xb7' # 0xF2 -> MIDDLE DOT + '\xb5' # 0xF3 -> MICRO SIGN + '\xb6' # 0xF4 -> PILCROW SIGN + '\xbe' # 0xF5 -> VULGAR FRACTION THREE QUARTERS + '\u2014' # 0xF6 -> EM DASH + '\xbc' # 0xF7 -> VULGAR FRACTION ONE QUARTER + '\xbd' # 0xF8 -> VULGAR FRACTION ONE HALF + '\xaa' # 0xF9 -> FEMININE ORDINAL INDICATOR + '\xba' # 0xFA -> MASCULINE ORDINAL INDICATOR + '\xab' # 0xFB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u25a0' # 0xFC -> BLACK SQUARE + '\xbb' # 0xFD -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xb1' # 0xFE -> PLUS-MINUS SIGN + '\ufffe' +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/hz.py b/contrib/tools/python3/src/Lib/encodings/hz.py new file mode 100644 index 0000000000..383442a3c9 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/hz.py @@ -0,0 +1,39 @@ +# +# hz.py: Python Unicode Codec for HZ +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_cn, codecs +import _multibytecodec as mbc + +codec = _codecs_cn.getcodec('hz') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='hz', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/idna.py b/contrib/tools/python3/src/Lib/encodings/idna.py new file mode 100644 index 0000000000..ea4058512f --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/idna.py @@ -0,0 +1,309 @@ +# This module implements the RFCs 3490 (IDNA) and 3491 (Nameprep) + +import stringprep, re, codecs +from unicodedata import ucd_3_2_0 as unicodedata + +# IDNA section 3.1 +dots = re.compile("[\u002E\u3002\uFF0E\uFF61]") + +# IDNA section 5 +ace_prefix = b"xn--" +sace_prefix = "xn--" + +# This assumes query strings, so AllowUnassigned is true +def nameprep(label): + # Map + newlabel = [] + for c in label: + if stringprep.in_table_b1(c): + # Map to nothing + continue + newlabel.append(stringprep.map_table_b2(c)) + label = "".join(newlabel) + + # Normalize + label = unicodedata.normalize("NFKC", label) + + # Prohibit + for c in label: + if stringprep.in_table_c12(c) or \ + stringprep.in_table_c22(c) or \ + stringprep.in_table_c3(c) or \ + stringprep.in_table_c4(c) or \ + stringprep.in_table_c5(c) or \ + stringprep.in_table_c6(c) or \ + stringprep.in_table_c7(c) or \ + stringprep.in_table_c8(c) or \ + stringprep.in_table_c9(c): + raise UnicodeError("Invalid character %r" % c) + + # Check bidi + RandAL = [stringprep.in_table_d1(x) for x in label] + for c in RandAL: + if c: + # There is a RandAL char in the string. Must perform further + # tests: + # 1) The characters in section 5.8 MUST be prohibited. + # This is table C.8, which was already checked + # 2) If a string contains any RandALCat character, the string + # MUST NOT contain any LCat character. + if any(stringprep.in_table_d2(x) for x in label): + raise UnicodeError("Violation of BIDI requirement 2") + + # 3) If a string contains any RandALCat character, a + # RandALCat character MUST be the first character of the + # string, and a RandALCat character MUST be the last + # character of the string. + if not RandAL[0] or not RandAL[-1]: + raise UnicodeError("Violation of BIDI requirement 3") + + return label + +def ToASCII(label): + try: + # Step 1: try ASCII + label = label.encode("ascii") + except UnicodeError: + pass + else: + # Skip to step 3: UseSTD3ASCIIRules is false, so + # Skip to step 8. + if 0 < len(label) < 64: + return label + raise UnicodeError("label empty or too long") + + # Step 2: nameprep + label = nameprep(label) + + # Step 3: UseSTD3ASCIIRules is false + # Step 4: try ASCII + try: + label = label.encode("ascii") + except UnicodeError: + pass + else: + # Skip to step 8. + if 0 < len(label) < 64: + return label + raise UnicodeError("label empty or too long") + + # Step 5: Check ACE prefix + if label.startswith(sace_prefix): + raise UnicodeError("Label starts with ACE prefix") + + # Step 6: Encode with PUNYCODE + label = label.encode("punycode") + + # Step 7: Prepend ACE prefix + label = ace_prefix + label + + # Step 8: Check size + if 0 < len(label) < 64: + return label + raise UnicodeError("label empty or too long") + +def ToUnicode(label): + # Step 1: Check for ASCII + if isinstance(label, bytes): + pure_ascii = True + else: + try: + label = label.encode("ascii") + pure_ascii = True + except UnicodeError: + pure_ascii = False + if not pure_ascii: + # Step 2: Perform nameprep + label = nameprep(label) + # It doesn't say this, but apparently, it should be ASCII now + try: + label = label.encode("ascii") + except UnicodeError: + raise UnicodeError("Invalid character in IDN label") + # Step 3: Check for ACE prefix + if not label.startswith(ace_prefix): + return str(label, "ascii") + + # Step 4: Remove ACE prefix + label1 = label[len(ace_prefix):] + + # Step 5: Decode using PUNYCODE + result = label1.decode("punycode") + + # Step 6: Apply ToASCII + label2 = ToASCII(result) + + # Step 7: Compare the result of step 6 with the one of step 3 + # label2 will already be in lower case. + if str(label, "ascii").lower() != str(label2, "ascii"): + raise UnicodeError("IDNA does not round-trip", label, label2) + + # Step 8: return the result of step 5 + return result + +### Codec APIs + +class Codec(codecs.Codec): + def encode(self, input, errors='strict'): + + if errors != 'strict': + # IDNA is quite clear that implementations must be strict + raise UnicodeError("unsupported error handling "+errors) + + if not input: + return b'', 0 + + try: + result = input.encode('ascii') + except UnicodeEncodeError: + pass + else: + # ASCII name: fast path + labels = result.split(b'.') + for label in labels[:-1]: + if not (0 < len(label) < 64): + raise UnicodeError("label empty or too long") + if len(labels[-1]) >= 64: + raise UnicodeError("label too long") + return result, len(input) + + result = bytearray() + labels = dots.split(input) + if labels and not labels[-1]: + trailing_dot = b'.' + del labels[-1] + else: + trailing_dot = b'' + for label in labels: + if result: + # Join with U+002E + result.extend(b'.') + result.extend(ToASCII(label)) + return bytes(result+trailing_dot), len(input) + + def decode(self, input, errors='strict'): + + if errors != 'strict': + raise UnicodeError("Unsupported error handling "+errors) + + if not input: + return "", 0 + + # IDNA allows decoding to operate on Unicode strings, too. + if not isinstance(input, bytes): + # XXX obviously wrong, see #3232 + input = bytes(input) + + if ace_prefix not in input: + # Fast path + try: + return input.decode('ascii'), len(input) + except UnicodeDecodeError: + pass + + labels = input.split(b".") + + if labels and len(labels[-1]) == 0: + trailing_dot = '.' + del labels[-1] + else: + trailing_dot = '' + + result = [] + for label in labels: + result.append(ToUnicode(label)) + + return ".".join(result)+trailing_dot, len(input) + +class IncrementalEncoder(codecs.BufferedIncrementalEncoder): + def _buffer_encode(self, input, errors, final): + if errors != 'strict': + # IDNA is quite clear that implementations must be strict + raise UnicodeError("unsupported error handling "+errors) + + if not input: + return (b'', 0) + + labels = dots.split(input) + trailing_dot = b'' + if labels: + if not labels[-1]: + trailing_dot = b'.' + del labels[-1] + elif not final: + # Keep potentially unfinished label until the next call + del labels[-1] + if labels: + trailing_dot = b'.' + + result = bytearray() + size = 0 + for label in labels: + if size: + # Join with U+002E + result.extend(b'.') + size += 1 + result.extend(ToASCII(label)) + size += len(label) + + result += trailing_dot + size += len(trailing_dot) + return (bytes(result), size) + +class IncrementalDecoder(codecs.BufferedIncrementalDecoder): + def _buffer_decode(self, input, errors, final): + if errors != 'strict': + raise UnicodeError("Unsupported error handling "+errors) + + if not input: + return ("", 0) + + # IDNA allows decoding to operate on Unicode strings, too. + if isinstance(input, str): + labels = dots.split(input) + else: + # Must be ASCII string + input = str(input, "ascii") + labels = input.split(".") + + trailing_dot = '' + if labels: + if not labels[-1]: + trailing_dot = '.' + del labels[-1] + elif not final: + # Keep potentially unfinished label until the next call + del labels[-1] + if labels: + trailing_dot = '.' + + result = [] + size = 0 + for label in labels: + result.append(ToUnicode(label)) + if size: + size += 1 + size += len(label) + + result = ".".join(result) + trailing_dot + size += len(trailing_dot) + return (result, size) + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='idna', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/iso2022_jp.py b/contrib/tools/python3/src/Lib/encodings/iso2022_jp.py new file mode 100644 index 0000000000..ab04060693 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/iso2022_jp.py @@ -0,0 +1,39 @@ +# +# iso2022_jp.py: Python Unicode Codec for ISO2022_JP +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_iso2022, codecs +import _multibytecodec as mbc + +codec = _codecs_iso2022.getcodec('iso2022_jp') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='iso2022_jp', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/iso2022_jp_1.py b/contrib/tools/python3/src/Lib/encodings/iso2022_jp_1.py new file mode 100644 index 0000000000..997044dc37 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/iso2022_jp_1.py @@ -0,0 +1,39 @@ +# +# iso2022_jp_1.py: Python Unicode Codec for ISO2022_JP_1 +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_iso2022, codecs +import _multibytecodec as mbc + +codec = _codecs_iso2022.getcodec('iso2022_jp_1') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='iso2022_jp_1', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/iso2022_jp_2.py b/contrib/tools/python3/src/Lib/encodings/iso2022_jp_2.py new file mode 100644 index 0000000000..9106bf7625 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/iso2022_jp_2.py @@ -0,0 +1,39 @@ +# +# iso2022_jp_2.py: Python Unicode Codec for ISO2022_JP_2 +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_iso2022, codecs +import _multibytecodec as mbc + +codec = _codecs_iso2022.getcodec('iso2022_jp_2') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='iso2022_jp_2', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/iso2022_jp_2004.py b/contrib/tools/python3/src/Lib/encodings/iso2022_jp_2004.py new file mode 100644 index 0000000000..40198bf098 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/iso2022_jp_2004.py @@ -0,0 +1,39 @@ +# +# iso2022_jp_2004.py: Python Unicode Codec for ISO2022_JP_2004 +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_iso2022, codecs +import _multibytecodec as mbc + +codec = _codecs_iso2022.getcodec('iso2022_jp_2004') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='iso2022_jp_2004', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/iso2022_jp_3.py b/contrib/tools/python3/src/Lib/encodings/iso2022_jp_3.py new file mode 100644 index 0000000000..346e08becc --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/iso2022_jp_3.py @@ -0,0 +1,39 @@ +# +# iso2022_jp_3.py: Python Unicode Codec for ISO2022_JP_3 +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_iso2022, codecs +import _multibytecodec as mbc + +codec = _codecs_iso2022.getcodec('iso2022_jp_3') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='iso2022_jp_3', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/iso2022_jp_ext.py b/contrib/tools/python3/src/Lib/encodings/iso2022_jp_ext.py new file mode 100644 index 0000000000..752bab9813 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/iso2022_jp_ext.py @@ -0,0 +1,39 @@ +# +# iso2022_jp_ext.py: Python Unicode Codec for ISO2022_JP_EXT +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_iso2022, codecs +import _multibytecodec as mbc + +codec = _codecs_iso2022.getcodec('iso2022_jp_ext') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='iso2022_jp_ext', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/iso2022_kr.py b/contrib/tools/python3/src/Lib/encodings/iso2022_kr.py new file mode 100644 index 0000000000..bf7018763e --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/iso2022_kr.py @@ -0,0 +1,39 @@ +# +# iso2022_kr.py: Python Unicode Codec for ISO2022_KR +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_iso2022, codecs +import _multibytecodec as mbc + +codec = _codecs_iso2022.getcodec('iso2022_kr') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='iso2022_kr', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/iso8859_1.py b/contrib/tools/python3/src/Lib/encodings/iso8859_1.py new file mode 100644 index 0000000000..8cfc01fe14 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/iso8859_1.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec iso8859_1 generated from 'MAPPINGS/ISO8859/8859-1.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='iso8859-1', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\x80' # 0x80 -> <control> + '\x81' # 0x81 -> <control> + '\x82' # 0x82 -> <control> + '\x83' # 0x83 -> <control> + '\x84' # 0x84 -> <control> + '\x85' # 0x85 -> <control> + '\x86' # 0x86 -> <control> + '\x87' # 0x87 -> <control> + '\x88' # 0x88 -> <control> + '\x89' # 0x89 -> <control> + '\x8a' # 0x8A -> <control> + '\x8b' # 0x8B -> <control> + '\x8c' # 0x8C -> <control> + '\x8d' # 0x8D -> <control> + '\x8e' # 0x8E -> <control> + '\x8f' # 0x8F -> <control> + '\x90' # 0x90 -> <control> + '\x91' # 0x91 -> <control> + '\x92' # 0x92 -> <control> + '\x93' # 0x93 -> <control> + '\x94' # 0x94 -> <control> + '\x95' # 0x95 -> <control> + '\x96' # 0x96 -> <control> + '\x97' # 0x97 -> <control> + '\x98' # 0x98 -> <control> + '\x99' # 0x99 -> <control> + '\x9a' # 0x9A -> <control> + '\x9b' # 0x9B -> <control> + '\x9c' # 0x9C -> <control> + '\x9d' # 0x9D -> <control> + '\x9e' # 0x9E -> <control> + '\x9f' # 0x9F -> <control> + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK + '\xa2' # 0xA2 -> CENT SIGN + '\xa3' # 0xA3 -> POUND SIGN + '\xa4' # 0xA4 -> CURRENCY SIGN + '\xa5' # 0xA5 -> YEN SIGN + '\xa6' # 0xA6 -> BROKEN BAR + '\xa7' # 0xA7 -> SECTION SIGN + '\xa8' # 0xA8 -> DIAERESIS + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR + '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xac' # 0xAC -> NOT SIGN + '\xad' # 0xAD -> SOFT HYPHEN + '\xae' # 0xAE -> REGISTERED SIGN + '\xaf' # 0xAF -> MACRON + '\xb0' # 0xB0 -> DEGREE SIGN + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\xb2' # 0xB2 -> SUPERSCRIPT TWO + '\xb3' # 0xB3 -> SUPERSCRIPT THREE + '\xb4' # 0xB4 -> ACUTE ACCENT + '\xb5' # 0xB5 -> MICRO SIGN + '\xb6' # 0xB6 -> PILCROW SIGN + '\xb7' # 0xB7 -> MIDDLE DOT + '\xb8' # 0xB8 -> CEDILLA + '\xb9' # 0xB9 -> SUPERSCRIPT ONE + '\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR + '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER + '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + '\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS + '\xbf' # 0xBF -> INVERTED QUESTION MARK + '\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE + '\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE + '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE + '\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE + '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH (Icelandic) + '\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE + '\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE + '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE + '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xd7' # 0xD7 -> MULTIPLICATION SIGN + '\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE + '\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE + '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + '\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE + '\xde' # 0xDE -> LATIN CAPITAL LETTER THORN (Icelandic) + '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S (German) + '\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE + '\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE + '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe6' # 0xE6 -> LATIN SMALL LETTER AE + '\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + '\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE + '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + '\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + '\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE + '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS + '\xf0' # 0xF0 -> LATIN SMALL LETTER ETH (Icelandic) + '\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE + '\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE + '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE + '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf7' # 0xF7 -> DIVISION SIGN + '\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE + '\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE + '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + '\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + '\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE + '\xfe' # 0xFE -> LATIN SMALL LETTER THORN (Icelandic) + '\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/iso8859_10.py b/contrib/tools/python3/src/Lib/encodings/iso8859_10.py new file mode 100644 index 0000000000..b4fb0419c4 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/iso8859_10.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec iso8859_10 generated from 'MAPPINGS/ISO8859/8859-10.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='iso8859-10', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\x80' # 0x80 -> <control> + '\x81' # 0x81 -> <control> + '\x82' # 0x82 -> <control> + '\x83' # 0x83 -> <control> + '\x84' # 0x84 -> <control> + '\x85' # 0x85 -> <control> + '\x86' # 0x86 -> <control> + '\x87' # 0x87 -> <control> + '\x88' # 0x88 -> <control> + '\x89' # 0x89 -> <control> + '\x8a' # 0x8A -> <control> + '\x8b' # 0x8B -> <control> + '\x8c' # 0x8C -> <control> + '\x8d' # 0x8D -> <control> + '\x8e' # 0x8E -> <control> + '\x8f' # 0x8F -> <control> + '\x90' # 0x90 -> <control> + '\x91' # 0x91 -> <control> + '\x92' # 0x92 -> <control> + '\x93' # 0x93 -> <control> + '\x94' # 0x94 -> <control> + '\x95' # 0x95 -> <control> + '\x96' # 0x96 -> <control> + '\x97' # 0x97 -> <control> + '\x98' # 0x98 -> <control> + '\x99' # 0x99 -> <control> + '\x9a' # 0x9A -> <control> + '\x9b' # 0x9B -> <control> + '\x9c' # 0x9C -> <control> + '\x9d' # 0x9D -> <control> + '\x9e' # 0x9E -> <control> + '\x9f' # 0x9F -> <control> + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\u0104' # 0xA1 -> LATIN CAPITAL LETTER A WITH OGONEK + '\u0112' # 0xA2 -> LATIN CAPITAL LETTER E WITH MACRON + '\u0122' # 0xA3 -> LATIN CAPITAL LETTER G WITH CEDILLA + '\u012a' # 0xA4 -> LATIN CAPITAL LETTER I WITH MACRON + '\u0128' # 0xA5 -> LATIN CAPITAL LETTER I WITH TILDE + '\u0136' # 0xA6 -> LATIN CAPITAL LETTER K WITH CEDILLA + '\xa7' # 0xA7 -> SECTION SIGN + '\u013b' # 0xA8 -> LATIN CAPITAL LETTER L WITH CEDILLA + '\u0110' # 0xA9 -> LATIN CAPITAL LETTER D WITH STROKE + '\u0160' # 0xAA -> LATIN CAPITAL LETTER S WITH CARON + '\u0166' # 0xAB -> LATIN CAPITAL LETTER T WITH STROKE + '\u017d' # 0xAC -> LATIN CAPITAL LETTER Z WITH CARON + '\xad' # 0xAD -> SOFT HYPHEN + '\u016a' # 0xAE -> LATIN CAPITAL LETTER U WITH MACRON + '\u014a' # 0xAF -> LATIN CAPITAL LETTER ENG + '\xb0' # 0xB0 -> DEGREE SIGN + '\u0105' # 0xB1 -> LATIN SMALL LETTER A WITH OGONEK + '\u0113' # 0xB2 -> LATIN SMALL LETTER E WITH MACRON + '\u0123' # 0xB3 -> LATIN SMALL LETTER G WITH CEDILLA + '\u012b' # 0xB4 -> LATIN SMALL LETTER I WITH MACRON + '\u0129' # 0xB5 -> LATIN SMALL LETTER I WITH TILDE + '\u0137' # 0xB6 -> LATIN SMALL LETTER K WITH CEDILLA + '\xb7' # 0xB7 -> MIDDLE DOT + '\u013c' # 0xB8 -> LATIN SMALL LETTER L WITH CEDILLA + '\u0111' # 0xB9 -> LATIN SMALL LETTER D WITH STROKE + '\u0161' # 0xBA -> LATIN SMALL LETTER S WITH CARON + '\u0167' # 0xBB -> LATIN SMALL LETTER T WITH STROKE + '\u017e' # 0xBC -> LATIN SMALL LETTER Z WITH CARON + '\u2015' # 0xBD -> HORIZONTAL BAR + '\u016b' # 0xBE -> LATIN SMALL LETTER U WITH MACRON + '\u014b' # 0xBF -> LATIN SMALL LETTER ENG + '\u0100' # 0xC0 -> LATIN CAPITAL LETTER A WITH MACRON + '\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE + '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE + '\u012e' # 0xC7 -> LATIN CAPITAL LETTER I WITH OGONEK + '\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON + '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + '\u0118' # 0xCA -> LATIN CAPITAL LETTER E WITH OGONEK + '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\u0116' # 0xCC -> LATIN CAPITAL LETTER E WITH DOT ABOVE + '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH (Icelandic) + '\u0145' # 0xD1 -> LATIN CAPITAL LETTER N WITH CEDILLA + '\u014c' # 0xD2 -> LATIN CAPITAL LETTER O WITH MACRON + '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE + '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\u0168' # 0xD7 -> LATIN CAPITAL LETTER U WITH TILDE + '\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE + '\u0172' # 0xD9 -> LATIN CAPITAL LETTER U WITH OGONEK + '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + '\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE + '\xde' # 0xDE -> LATIN CAPITAL LETTER THORN (Icelandic) + '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S (German) + '\u0101' # 0xE0 -> LATIN SMALL LETTER A WITH MACRON + '\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE + '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe6' # 0xE6 -> LATIN SMALL LETTER AE + '\u012f' # 0xE7 -> LATIN SMALL LETTER I WITH OGONEK + '\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON + '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + '\u0119' # 0xEA -> LATIN SMALL LETTER E WITH OGONEK + '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + '\u0117' # 0xEC -> LATIN SMALL LETTER E WITH DOT ABOVE + '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS + '\xf0' # 0xF0 -> LATIN SMALL LETTER ETH (Icelandic) + '\u0146' # 0xF1 -> LATIN SMALL LETTER N WITH CEDILLA + '\u014d' # 0xF2 -> LATIN SMALL LETTER O WITH MACRON + '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE + '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + '\u0169' # 0xF7 -> LATIN SMALL LETTER U WITH TILDE + '\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE + '\u0173' # 0xF9 -> LATIN SMALL LETTER U WITH OGONEK + '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + '\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + '\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE + '\xfe' # 0xFE -> LATIN SMALL LETTER THORN (Icelandic) + '\u0138' # 0xFF -> LATIN SMALL LETTER KRA +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/iso8859_11.py b/contrib/tools/python3/src/Lib/encodings/iso8859_11.py new file mode 100644 index 0000000000..c7258ecf46 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/iso8859_11.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec iso8859_11 generated from 'MAPPINGS/ISO8859/8859-11.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='iso8859-11', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\x80' # 0x80 -> <control> + '\x81' # 0x81 -> <control> + '\x82' # 0x82 -> <control> + '\x83' # 0x83 -> <control> + '\x84' # 0x84 -> <control> + '\x85' # 0x85 -> <control> + '\x86' # 0x86 -> <control> + '\x87' # 0x87 -> <control> + '\x88' # 0x88 -> <control> + '\x89' # 0x89 -> <control> + '\x8a' # 0x8A -> <control> + '\x8b' # 0x8B -> <control> + '\x8c' # 0x8C -> <control> + '\x8d' # 0x8D -> <control> + '\x8e' # 0x8E -> <control> + '\x8f' # 0x8F -> <control> + '\x90' # 0x90 -> <control> + '\x91' # 0x91 -> <control> + '\x92' # 0x92 -> <control> + '\x93' # 0x93 -> <control> + '\x94' # 0x94 -> <control> + '\x95' # 0x95 -> <control> + '\x96' # 0x96 -> <control> + '\x97' # 0x97 -> <control> + '\x98' # 0x98 -> <control> + '\x99' # 0x99 -> <control> + '\x9a' # 0x9A -> <control> + '\x9b' # 0x9B -> <control> + '\x9c' # 0x9C -> <control> + '\x9d' # 0x9D -> <control> + '\x9e' # 0x9E -> <control> + '\x9f' # 0x9F -> <control> + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\u0e01' # 0xA1 -> THAI CHARACTER KO KAI + '\u0e02' # 0xA2 -> THAI CHARACTER KHO KHAI + '\u0e03' # 0xA3 -> THAI CHARACTER KHO KHUAT + '\u0e04' # 0xA4 -> THAI CHARACTER KHO KHWAI + '\u0e05' # 0xA5 -> THAI CHARACTER KHO KHON + '\u0e06' # 0xA6 -> THAI CHARACTER KHO RAKHANG + '\u0e07' # 0xA7 -> THAI CHARACTER NGO NGU + '\u0e08' # 0xA8 -> THAI CHARACTER CHO CHAN + '\u0e09' # 0xA9 -> THAI CHARACTER CHO CHING + '\u0e0a' # 0xAA -> THAI CHARACTER CHO CHANG + '\u0e0b' # 0xAB -> THAI CHARACTER SO SO + '\u0e0c' # 0xAC -> THAI CHARACTER CHO CHOE + '\u0e0d' # 0xAD -> THAI CHARACTER YO YING + '\u0e0e' # 0xAE -> THAI CHARACTER DO CHADA + '\u0e0f' # 0xAF -> THAI CHARACTER TO PATAK + '\u0e10' # 0xB0 -> THAI CHARACTER THO THAN + '\u0e11' # 0xB1 -> THAI CHARACTER THO NANGMONTHO + '\u0e12' # 0xB2 -> THAI CHARACTER THO PHUTHAO + '\u0e13' # 0xB3 -> THAI CHARACTER NO NEN + '\u0e14' # 0xB4 -> THAI CHARACTER DO DEK + '\u0e15' # 0xB5 -> THAI CHARACTER TO TAO + '\u0e16' # 0xB6 -> THAI CHARACTER THO THUNG + '\u0e17' # 0xB7 -> THAI CHARACTER THO THAHAN + '\u0e18' # 0xB8 -> THAI CHARACTER THO THONG + '\u0e19' # 0xB9 -> THAI CHARACTER NO NU + '\u0e1a' # 0xBA -> THAI CHARACTER BO BAIMAI + '\u0e1b' # 0xBB -> THAI CHARACTER PO PLA + '\u0e1c' # 0xBC -> THAI CHARACTER PHO PHUNG + '\u0e1d' # 0xBD -> THAI CHARACTER FO FA + '\u0e1e' # 0xBE -> THAI CHARACTER PHO PHAN + '\u0e1f' # 0xBF -> THAI CHARACTER FO FAN + '\u0e20' # 0xC0 -> THAI CHARACTER PHO SAMPHAO + '\u0e21' # 0xC1 -> THAI CHARACTER MO MA + '\u0e22' # 0xC2 -> THAI CHARACTER YO YAK + '\u0e23' # 0xC3 -> THAI CHARACTER RO RUA + '\u0e24' # 0xC4 -> THAI CHARACTER RU + '\u0e25' # 0xC5 -> THAI CHARACTER LO LING + '\u0e26' # 0xC6 -> THAI CHARACTER LU + '\u0e27' # 0xC7 -> THAI CHARACTER WO WAEN + '\u0e28' # 0xC8 -> THAI CHARACTER SO SALA + '\u0e29' # 0xC9 -> THAI CHARACTER SO RUSI + '\u0e2a' # 0xCA -> THAI CHARACTER SO SUA + '\u0e2b' # 0xCB -> THAI CHARACTER HO HIP + '\u0e2c' # 0xCC -> THAI CHARACTER LO CHULA + '\u0e2d' # 0xCD -> THAI CHARACTER O ANG + '\u0e2e' # 0xCE -> THAI CHARACTER HO NOKHUK + '\u0e2f' # 0xCF -> THAI CHARACTER PAIYANNOI + '\u0e30' # 0xD0 -> THAI CHARACTER SARA A + '\u0e31' # 0xD1 -> THAI CHARACTER MAI HAN-AKAT + '\u0e32' # 0xD2 -> THAI CHARACTER SARA AA + '\u0e33' # 0xD3 -> THAI CHARACTER SARA AM + '\u0e34' # 0xD4 -> THAI CHARACTER SARA I + '\u0e35' # 0xD5 -> THAI CHARACTER SARA II + '\u0e36' # 0xD6 -> THAI CHARACTER SARA UE + '\u0e37' # 0xD7 -> THAI CHARACTER SARA UEE + '\u0e38' # 0xD8 -> THAI CHARACTER SARA U + '\u0e39' # 0xD9 -> THAI CHARACTER SARA UU + '\u0e3a' # 0xDA -> THAI CHARACTER PHINTHU + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\u0e3f' # 0xDF -> THAI CURRENCY SYMBOL BAHT + '\u0e40' # 0xE0 -> THAI CHARACTER SARA E + '\u0e41' # 0xE1 -> THAI CHARACTER SARA AE + '\u0e42' # 0xE2 -> THAI CHARACTER SARA O + '\u0e43' # 0xE3 -> THAI CHARACTER SARA AI MAIMUAN + '\u0e44' # 0xE4 -> THAI CHARACTER SARA AI MAIMALAI + '\u0e45' # 0xE5 -> THAI CHARACTER LAKKHANGYAO + '\u0e46' # 0xE6 -> THAI CHARACTER MAIYAMOK + '\u0e47' # 0xE7 -> THAI CHARACTER MAITAIKHU + '\u0e48' # 0xE8 -> THAI CHARACTER MAI EK + '\u0e49' # 0xE9 -> THAI CHARACTER MAI THO + '\u0e4a' # 0xEA -> THAI CHARACTER MAI TRI + '\u0e4b' # 0xEB -> THAI CHARACTER MAI CHATTAWA + '\u0e4c' # 0xEC -> THAI CHARACTER THANTHAKHAT + '\u0e4d' # 0xED -> THAI CHARACTER NIKHAHIT + '\u0e4e' # 0xEE -> THAI CHARACTER YAMAKKAN + '\u0e4f' # 0xEF -> THAI CHARACTER FONGMAN + '\u0e50' # 0xF0 -> THAI DIGIT ZERO + '\u0e51' # 0xF1 -> THAI DIGIT ONE + '\u0e52' # 0xF2 -> THAI DIGIT TWO + '\u0e53' # 0xF3 -> THAI DIGIT THREE + '\u0e54' # 0xF4 -> THAI DIGIT FOUR + '\u0e55' # 0xF5 -> THAI DIGIT FIVE + '\u0e56' # 0xF6 -> THAI DIGIT SIX + '\u0e57' # 0xF7 -> THAI DIGIT SEVEN + '\u0e58' # 0xF8 -> THAI DIGIT EIGHT + '\u0e59' # 0xF9 -> THAI DIGIT NINE + '\u0e5a' # 0xFA -> THAI CHARACTER ANGKHANKHU + '\u0e5b' # 0xFB -> THAI CHARACTER KHOMUT + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/iso8859_13.py b/contrib/tools/python3/src/Lib/encodings/iso8859_13.py new file mode 100644 index 0000000000..6f8eab2b82 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/iso8859_13.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec iso8859_13 generated from 'MAPPINGS/ISO8859/8859-13.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='iso8859-13', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\x80' # 0x80 -> <control> + '\x81' # 0x81 -> <control> + '\x82' # 0x82 -> <control> + '\x83' # 0x83 -> <control> + '\x84' # 0x84 -> <control> + '\x85' # 0x85 -> <control> + '\x86' # 0x86 -> <control> + '\x87' # 0x87 -> <control> + '\x88' # 0x88 -> <control> + '\x89' # 0x89 -> <control> + '\x8a' # 0x8A -> <control> + '\x8b' # 0x8B -> <control> + '\x8c' # 0x8C -> <control> + '\x8d' # 0x8D -> <control> + '\x8e' # 0x8E -> <control> + '\x8f' # 0x8F -> <control> + '\x90' # 0x90 -> <control> + '\x91' # 0x91 -> <control> + '\x92' # 0x92 -> <control> + '\x93' # 0x93 -> <control> + '\x94' # 0x94 -> <control> + '\x95' # 0x95 -> <control> + '\x96' # 0x96 -> <control> + '\x97' # 0x97 -> <control> + '\x98' # 0x98 -> <control> + '\x99' # 0x99 -> <control> + '\x9a' # 0x9A -> <control> + '\x9b' # 0x9B -> <control> + '\x9c' # 0x9C -> <control> + '\x9d' # 0x9D -> <control> + '\x9e' # 0x9E -> <control> + '\x9f' # 0x9F -> <control> + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\u201d' # 0xA1 -> RIGHT DOUBLE QUOTATION MARK + '\xa2' # 0xA2 -> CENT SIGN + '\xa3' # 0xA3 -> POUND SIGN + '\xa4' # 0xA4 -> CURRENCY SIGN + '\u201e' # 0xA5 -> DOUBLE LOW-9 QUOTATION MARK + '\xa6' # 0xA6 -> BROKEN BAR + '\xa7' # 0xA7 -> SECTION SIGN + '\xd8' # 0xA8 -> LATIN CAPITAL LETTER O WITH STROKE + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\u0156' # 0xAA -> LATIN CAPITAL LETTER R WITH CEDILLA + '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xac' # 0xAC -> NOT SIGN + '\xad' # 0xAD -> SOFT HYPHEN + '\xae' # 0xAE -> REGISTERED SIGN + '\xc6' # 0xAF -> LATIN CAPITAL LETTER AE + '\xb0' # 0xB0 -> DEGREE SIGN + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\xb2' # 0xB2 -> SUPERSCRIPT TWO + '\xb3' # 0xB3 -> SUPERSCRIPT THREE + '\u201c' # 0xB4 -> LEFT DOUBLE QUOTATION MARK + '\xb5' # 0xB5 -> MICRO SIGN + '\xb6' # 0xB6 -> PILCROW SIGN + '\xb7' # 0xB7 -> MIDDLE DOT + '\xf8' # 0xB8 -> LATIN SMALL LETTER O WITH STROKE + '\xb9' # 0xB9 -> SUPERSCRIPT ONE + '\u0157' # 0xBA -> LATIN SMALL LETTER R WITH CEDILLA + '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER + '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + '\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS + '\xe6' # 0xBF -> LATIN SMALL LETTER AE + '\u0104' # 0xC0 -> LATIN CAPITAL LETTER A WITH OGONEK + '\u012e' # 0xC1 -> LATIN CAPITAL LETTER I WITH OGONEK + '\u0100' # 0xC2 -> LATIN CAPITAL LETTER A WITH MACRON + '\u0106' # 0xC3 -> LATIN CAPITAL LETTER C WITH ACUTE + '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\u0118' # 0xC6 -> LATIN CAPITAL LETTER E WITH OGONEK + '\u0112' # 0xC7 -> LATIN CAPITAL LETTER E WITH MACRON + '\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON + '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + '\u0179' # 0xCA -> LATIN CAPITAL LETTER Z WITH ACUTE + '\u0116' # 0xCB -> LATIN CAPITAL LETTER E WITH DOT ABOVE + '\u0122' # 0xCC -> LATIN CAPITAL LETTER G WITH CEDILLA + '\u0136' # 0xCD -> LATIN CAPITAL LETTER K WITH CEDILLA + '\u012a' # 0xCE -> LATIN CAPITAL LETTER I WITH MACRON + '\u013b' # 0xCF -> LATIN CAPITAL LETTER L WITH CEDILLA + '\u0160' # 0xD0 -> LATIN CAPITAL LETTER S WITH CARON + '\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE + '\u0145' # 0xD2 -> LATIN CAPITAL LETTER N WITH CEDILLA + '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + '\u014c' # 0xD4 -> LATIN CAPITAL LETTER O WITH MACRON + '\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE + '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xd7' # 0xD7 -> MULTIPLICATION SIGN + '\u0172' # 0xD8 -> LATIN CAPITAL LETTER U WITH OGONEK + '\u0141' # 0xD9 -> LATIN CAPITAL LETTER L WITH STROKE + '\u015a' # 0xDA -> LATIN CAPITAL LETTER S WITH ACUTE + '\u016a' # 0xDB -> LATIN CAPITAL LETTER U WITH MACRON + '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\u017b' # 0xDD -> LATIN CAPITAL LETTER Z WITH DOT ABOVE + '\u017d' # 0xDE -> LATIN CAPITAL LETTER Z WITH CARON + '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S (German) + '\u0105' # 0xE0 -> LATIN SMALL LETTER A WITH OGONEK + '\u012f' # 0xE1 -> LATIN SMALL LETTER I WITH OGONEK + '\u0101' # 0xE2 -> LATIN SMALL LETTER A WITH MACRON + '\u0107' # 0xE3 -> LATIN SMALL LETTER C WITH ACUTE + '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + '\u0119' # 0xE6 -> LATIN SMALL LETTER E WITH OGONEK + '\u0113' # 0xE7 -> LATIN SMALL LETTER E WITH MACRON + '\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON + '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + '\u017a' # 0xEA -> LATIN SMALL LETTER Z WITH ACUTE + '\u0117' # 0xEB -> LATIN SMALL LETTER E WITH DOT ABOVE + '\u0123' # 0xEC -> LATIN SMALL LETTER G WITH CEDILLA + '\u0137' # 0xED -> LATIN SMALL LETTER K WITH CEDILLA + '\u012b' # 0xEE -> LATIN SMALL LETTER I WITH MACRON + '\u013c' # 0xEF -> LATIN SMALL LETTER L WITH CEDILLA + '\u0161' # 0xF0 -> LATIN SMALL LETTER S WITH CARON + '\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE + '\u0146' # 0xF2 -> LATIN SMALL LETTER N WITH CEDILLA + '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + '\u014d' # 0xF4 -> LATIN SMALL LETTER O WITH MACRON + '\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE + '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf7' # 0xF7 -> DIVISION SIGN + '\u0173' # 0xF8 -> LATIN SMALL LETTER U WITH OGONEK + '\u0142' # 0xF9 -> LATIN SMALL LETTER L WITH STROKE + '\u015b' # 0xFA -> LATIN SMALL LETTER S WITH ACUTE + '\u016b' # 0xFB -> LATIN SMALL LETTER U WITH MACRON + '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + '\u017c' # 0xFD -> LATIN SMALL LETTER Z WITH DOT ABOVE + '\u017e' # 0xFE -> LATIN SMALL LETTER Z WITH CARON + '\u2019' # 0xFF -> RIGHT SINGLE QUOTATION MARK +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/iso8859_14.py b/contrib/tools/python3/src/Lib/encodings/iso8859_14.py new file mode 100644 index 0000000000..7568d4ee1f --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/iso8859_14.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec iso8859_14 generated from 'MAPPINGS/ISO8859/8859-14.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='iso8859-14', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\x80' # 0x80 -> <control> + '\x81' # 0x81 -> <control> + '\x82' # 0x82 -> <control> + '\x83' # 0x83 -> <control> + '\x84' # 0x84 -> <control> + '\x85' # 0x85 -> <control> + '\x86' # 0x86 -> <control> + '\x87' # 0x87 -> <control> + '\x88' # 0x88 -> <control> + '\x89' # 0x89 -> <control> + '\x8a' # 0x8A -> <control> + '\x8b' # 0x8B -> <control> + '\x8c' # 0x8C -> <control> + '\x8d' # 0x8D -> <control> + '\x8e' # 0x8E -> <control> + '\x8f' # 0x8F -> <control> + '\x90' # 0x90 -> <control> + '\x91' # 0x91 -> <control> + '\x92' # 0x92 -> <control> + '\x93' # 0x93 -> <control> + '\x94' # 0x94 -> <control> + '\x95' # 0x95 -> <control> + '\x96' # 0x96 -> <control> + '\x97' # 0x97 -> <control> + '\x98' # 0x98 -> <control> + '\x99' # 0x99 -> <control> + '\x9a' # 0x9A -> <control> + '\x9b' # 0x9B -> <control> + '\x9c' # 0x9C -> <control> + '\x9d' # 0x9D -> <control> + '\x9e' # 0x9E -> <control> + '\x9f' # 0x9F -> <control> + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\u1e02' # 0xA1 -> LATIN CAPITAL LETTER B WITH DOT ABOVE + '\u1e03' # 0xA2 -> LATIN SMALL LETTER B WITH DOT ABOVE + '\xa3' # 0xA3 -> POUND SIGN + '\u010a' # 0xA4 -> LATIN CAPITAL LETTER C WITH DOT ABOVE + '\u010b' # 0xA5 -> LATIN SMALL LETTER C WITH DOT ABOVE + '\u1e0a' # 0xA6 -> LATIN CAPITAL LETTER D WITH DOT ABOVE + '\xa7' # 0xA7 -> SECTION SIGN + '\u1e80' # 0xA8 -> LATIN CAPITAL LETTER W WITH GRAVE + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\u1e82' # 0xAA -> LATIN CAPITAL LETTER W WITH ACUTE + '\u1e0b' # 0xAB -> LATIN SMALL LETTER D WITH DOT ABOVE + '\u1ef2' # 0xAC -> LATIN CAPITAL LETTER Y WITH GRAVE + '\xad' # 0xAD -> SOFT HYPHEN + '\xae' # 0xAE -> REGISTERED SIGN + '\u0178' # 0xAF -> LATIN CAPITAL LETTER Y WITH DIAERESIS + '\u1e1e' # 0xB0 -> LATIN CAPITAL LETTER F WITH DOT ABOVE + '\u1e1f' # 0xB1 -> LATIN SMALL LETTER F WITH DOT ABOVE + '\u0120' # 0xB2 -> LATIN CAPITAL LETTER G WITH DOT ABOVE + '\u0121' # 0xB3 -> LATIN SMALL LETTER G WITH DOT ABOVE + '\u1e40' # 0xB4 -> LATIN CAPITAL LETTER M WITH DOT ABOVE + '\u1e41' # 0xB5 -> LATIN SMALL LETTER M WITH DOT ABOVE + '\xb6' # 0xB6 -> PILCROW SIGN + '\u1e56' # 0xB7 -> LATIN CAPITAL LETTER P WITH DOT ABOVE + '\u1e81' # 0xB8 -> LATIN SMALL LETTER W WITH GRAVE + '\u1e57' # 0xB9 -> LATIN SMALL LETTER P WITH DOT ABOVE + '\u1e83' # 0xBA -> LATIN SMALL LETTER W WITH ACUTE + '\u1e60' # 0xBB -> LATIN CAPITAL LETTER S WITH DOT ABOVE + '\u1ef3' # 0xBC -> LATIN SMALL LETTER Y WITH GRAVE + '\u1e84' # 0xBD -> LATIN CAPITAL LETTER W WITH DIAERESIS + '\u1e85' # 0xBE -> LATIN SMALL LETTER W WITH DIAERESIS + '\u1e61' # 0xBF -> LATIN SMALL LETTER S WITH DOT ABOVE + '\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE + '\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE + '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE + '\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE + '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\u0174' # 0xD0 -> LATIN CAPITAL LETTER W WITH CIRCUMFLEX + '\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE + '\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE + '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE + '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\u1e6a' # 0xD7 -> LATIN CAPITAL LETTER T WITH DOT ABOVE + '\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE + '\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE + '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + '\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE + '\u0176' # 0xDE -> LATIN CAPITAL LETTER Y WITH CIRCUMFLEX + '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + '\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE + '\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE + '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe6' # 0xE6 -> LATIN SMALL LETTER AE + '\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + '\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE + '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + '\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + '\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE + '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS + '\u0175' # 0xF0 -> LATIN SMALL LETTER W WITH CIRCUMFLEX + '\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE + '\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE + '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE + '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + '\u1e6b' # 0xF7 -> LATIN SMALL LETTER T WITH DOT ABOVE + '\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE + '\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE + '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + '\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + '\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE + '\u0177' # 0xFE -> LATIN SMALL LETTER Y WITH CIRCUMFLEX + '\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/iso8859_15.py b/contrib/tools/python3/src/Lib/encodings/iso8859_15.py new file mode 100644 index 0000000000..43bdecd446 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/iso8859_15.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec iso8859_15 generated from 'MAPPINGS/ISO8859/8859-15.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='iso8859-15', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\x80' # 0x80 -> <control> + '\x81' # 0x81 -> <control> + '\x82' # 0x82 -> <control> + '\x83' # 0x83 -> <control> + '\x84' # 0x84 -> <control> + '\x85' # 0x85 -> <control> + '\x86' # 0x86 -> <control> + '\x87' # 0x87 -> <control> + '\x88' # 0x88 -> <control> + '\x89' # 0x89 -> <control> + '\x8a' # 0x8A -> <control> + '\x8b' # 0x8B -> <control> + '\x8c' # 0x8C -> <control> + '\x8d' # 0x8D -> <control> + '\x8e' # 0x8E -> <control> + '\x8f' # 0x8F -> <control> + '\x90' # 0x90 -> <control> + '\x91' # 0x91 -> <control> + '\x92' # 0x92 -> <control> + '\x93' # 0x93 -> <control> + '\x94' # 0x94 -> <control> + '\x95' # 0x95 -> <control> + '\x96' # 0x96 -> <control> + '\x97' # 0x97 -> <control> + '\x98' # 0x98 -> <control> + '\x99' # 0x99 -> <control> + '\x9a' # 0x9A -> <control> + '\x9b' # 0x9B -> <control> + '\x9c' # 0x9C -> <control> + '\x9d' # 0x9D -> <control> + '\x9e' # 0x9E -> <control> + '\x9f' # 0x9F -> <control> + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK + '\xa2' # 0xA2 -> CENT SIGN + '\xa3' # 0xA3 -> POUND SIGN + '\u20ac' # 0xA4 -> EURO SIGN + '\xa5' # 0xA5 -> YEN SIGN + '\u0160' # 0xA6 -> LATIN CAPITAL LETTER S WITH CARON + '\xa7' # 0xA7 -> SECTION SIGN + '\u0161' # 0xA8 -> LATIN SMALL LETTER S WITH CARON + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR + '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xac' # 0xAC -> NOT SIGN + '\xad' # 0xAD -> SOFT HYPHEN + '\xae' # 0xAE -> REGISTERED SIGN + '\xaf' # 0xAF -> MACRON + '\xb0' # 0xB0 -> DEGREE SIGN + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\xb2' # 0xB2 -> SUPERSCRIPT TWO + '\xb3' # 0xB3 -> SUPERSCRIPT THREE + '\u017d' # 0xB4 -> LATIN CAPITAL LETTER Z WITH CARON + '\xb5' # 0xB5 -> MICRO SIGN + '\xb6' # 0xB6 -> PILCROW SIGN + '\xb7' # 0xB7 -> MIDDLE DOT + '\u017e' # 0xB8 -> LATIN SMALL LETTER Z WITH CARON + '\xb9' # 0xB9 -> SUPERSCRIPT ONE + '\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR + '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u0152' # 0xBC -> LATIN CAPITAL LIGATURE OE + '\u0153' # 0xBD -> LATIN SMALL LIGATURE OE + '\u0178' # 0xBE -> LATIN CAPITAL LETTER Y WITH DIAERESIS + '\xbf' # 0xBF -> INVERTED QUESTION MARK + '\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE + '\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE + '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE + '\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE + '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH + '\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE + '\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE + '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE + '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xd7' # 0xD7 -> MULTIPLICATION SIGN + '\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE + '\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE + '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + '\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE + '\xde' # 0xDE -> LATIN CAPITAL LETTER THORN + '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + '\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE + '\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE + '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe6' # 0xE6 -> LATIN SMALL LETTER AE + '\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + '\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE + '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + '\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + '\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE + '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS + '\xf0' # 0xF0 -> LATIN SMALL LETTER ETH + '\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE + '\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE + '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE + '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf7' # 0xF7 -> DIVISION SIGN + '\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE + '\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE + '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + '\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + '\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE + '\xfe' # 0xFE -> LATIN SMALL LETTER THORN + '\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/iso8859_16.py b/contrib/tools/python3/src/Lib/encodings/iso8859_16.py new file mode 100644 index 0000000000..e70c96e333 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/iso8859_16.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec iso8859_16 generated from 'MAPPINGS/ISO8859/8859-16.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='iso8859-16', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\x80' # 0x80 -> <control> + '\x81' # 0x81 -> <control> + '\x82' # 0x82 -> <control> + '\x83' # 0x83 -> <control> + '\x84' # 0x84 -> <control> + '\x85' # 0x85 -> <control> + '\x86' # 0x86 -> <control> + '\x87' # 0x87 -> <control> + '\x88' # 0x88 -> <control> + '\x89' # 0x89 -> <control> + '\x8a' # 0x8A -> <control> + '\x8b' # 0x8B -> <control> + '\x8c' # 0x8C -> <control> + '\x8d' # 0x8D -> <control> + '\x8e' # 0x8E -> <control> + '\x8f' # 0x8F -> <control> + '\x90' # 0x90 -> <control> + '\x91' # 0x91 -> <control> + '\x92' # 0x92 -> <control> + '\x93' # 0x93 -> <control> + '\x94' # 0x94 -> <control> + '\x95' # 0x95 -> <control> + '\x96' # 0x96 -> <control> + '\x97' # 0x97 -> <control> + '\x98' # 0x98 -> <control> + '\x99' # 0x99 -> <control> + '\x9a' # 0x9A -> <control> + '\x9b' # 0x9B -> <control> + '\x9c' # 0x9C -> <control> + '\x9d' # 0x9D -> <control> + '\x9e' # 0x9E -> <control> + '\x9f' # 0x9F -> <control> + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\u0104' # 0xA1 -> LATIN CAPITAL LETTER A WITH OGONEK + '\u0105' # 0xA2 -> LATIN SMALL LETTER A WITH OGONEK + '\u0141' # 0xA3 -> LATIN CAPITAL LETTER L WITH STROKE + '\u20ac' # 0xA4 -> EURO SIGN + '\u201e' # 0xA5 -> DOUBLE LOW-9 QUOTATION MARK + '\u0160' # 0xA6 -> LATIN CAPITAL LETTER S WITH CARON + '\xa7' # 0xA7 -> SECTION SIGN + '\u0161' # 0xA8 -> LATIN SMALL LETTER S WITH CARON + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\u0218' # 0xAA -> LATIN CAPITAL LETTER S WITH COMMA BELOW + '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u0179' # 0xAC -> LATIN CAPITAL LETTER Z WITH ACUTE + '\xad' # 0xAD -> SOFT HYPHEN + '\u017a' # 0xAE -> LATIN SMALL LETTER Z WITH ACUTE + '\u017b' # 0xAF -> LATIN CAPITAL LETTER Z WITH DOT ABOVE + '\xb0' # 0xB0 -> DEGREE SIGN + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\u010c' # 0xB2 -> LATIN CAPITAL LETTER C WITH CARON + '\u0142' # 0xB3 -> LATIN SMALL LETTER L WITH STROKE + '\u017d' # 0xB4 -> LATIN CAPITAL LETTER Z WITH CARON + '\u201d' # 0xB5 -> RIGHT DOUBLE QUOTATION MARK + '\xb6' # 0xB6 -> PILCROW SIGN + '\xb7' # 0xB7 -> MIDDLE DOT + '\u017e' # 0xB8 -> LATIN SMALL LETTER Z WITH CARON + '\u010d' # 0xB9 -> LATIN SMALL LETTER C WITH CARON + '\u0219' # 0xBA -> LATIN SMALL LETTER S WITH COMMA BELOW + '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u0152' # 0xBC -> LATIN CAPITAL LIGATURE OE + '\u0153' # 0xBD -> LATIN SMALL LIGATURE OE + '\u0178' # 0xBE -> LATIN CAPITAL LETTER Y WITH DIAERESIS + '\u017c' # 0xBF -> LATIN SMALL LETTER Z WITH DOT ABOVE + '\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE + '\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\u0102' # 0xC3 -> LATIN CAPITAL LETTER A WITH BREVE + '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\u0106' # 0xC5 -> LATIN CAPITAL LETTER C WITH ACUTE + '\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE + '\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE + '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE + '\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE + '\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE + '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\u0150' # 0xD5 -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE + '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\u015a' # 0xD7 -> LATIN CAPITAL LETTER S WITH ACUTE + '\u0170' # 0xD8 -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE + '\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE + '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + '\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\u0118' # 0xDD -> LATIN CAPITAL LETTER E WITH OGONEK + '\u021a' # 0xDE -> LATIN CAPITAL LETTER T WITH COMMA BELOW + '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + '\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE + '\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\u0103' # 0xE3 -> LATIN SMALL LETTER A WITH BREVE + '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + '\u0107' # 0xE5 -> LATIN SMALL LETTER C WITH ACUTE + '\xe6' # 0xE6 -> LATIN SMALL LETTER AE + '\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + '\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE + '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + '\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + '\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE + '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS + '\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE + '\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE + '\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE + '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\u0151' # 0xF5 -> LATIN SMALL LETTER O WITH DOUBLE ACUTE + '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + '\u015b' # 0xF7 -> LATIN SMALL LETTER S WITH ACUTE + '\u0171' # 0xF8 -> LATIN SMALL LETTER U WITH DOUBLE ACUTE + '\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE + '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + '\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + '\u0119' # 0xFD -> LATIN SMALL LETTER E WITH OGONEK + '\u021b' # 0xFE -> LATIN SMALL LETTER T WITH COMMA BELOW + '\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/iso8859_2.py b/contrib/tools/python3/src/Lib/encodings/iso8859_2.py new file mode 100644 index 0000000000..3698747b47 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/iso8859_2.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec iso8859_2 generated from 'MAPPINGS/ISO8859/8859-2.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='iso8859-2', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\x80' # 0x80 -> <control> + '\x81' # 0x81 -> <control> + '\x82' # 0x82 -> <control> + '\x83' # 0x83 -> <control> + '\x84' # 0x84 -> <control> + '\x85' # 0x85 -> <control> + '\x86' # 0x86 -> <control> + '\x87' # 0x87 -> <control> + '\x88' # 0x88 -> <control> + '\x89' # 0x89 -> <control> + '\x8a' # 0x8A -> <control> + '\x8b' # 0x8B -> <control> + '\x8c' # 0x8C -> <control> + '\x8d' # 0x8D -> <control> + '\x8e' # 0x8E -> <control> + '\x8f' # 0x8F -> <control> + '\x90' # 0x90 -> <control> + '\x91' # 0x91 -> <control> + '\x92' # 0x92 -> <control> + '\x93' # 0x93 -> <control> + '\x94' # 0x94 -> <control> + '\x95' # 0x95 -> <control> + '\x96' # 0x96 -> <control> + '\x97' # 0x97 -> <control> + '\x98' # 0x98 -> <control> + '\x99' # 0x99 -> <control> + '\x9a' # 0x9A -> <control> + '\x9b' # 0x9B -> <control> + '\x9c' # 0x9C -> <control> + '\x9d' # 0x9D -> <control> + '\x9e' # 0x9E -> <control> + '\x9f' # 0x9F -> <control> + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\u0104' # 0xA1 -> LATIN CAPITAL LETTER A WITH OGONEK + '\u02d8' # 0xA2 -> BREVE + '\u0141' # 0xA3 -> LATIN CAPITAL LETTER L WITH STROKE + '\xa4' # 0xA4 -> CURRENCY SIGN + '\u013d' # 0xA5 -> LATIN CAPITAL LETTER L WITH CARON + '\u015a' # 0xA6 -> LATIN CAPITAL LETTER S WITH ACUTE + '\xa7' # 0xA7 -> SECTION SIGN + '\xa8' # 0xA8 -> DIAERESIS + '\u0160' # 0xA9 -> LATIN CAPITAL LETTER S WITH CARON + '\u015e' # 0xAA -> LATIN CAPITAL LETTER S WITH CEDILLA + '\u0164' # 0xAB -> LATIN CAPITAL LETTER T WITH CARON + '\u0179' # 0xAC -> LATIN CAPITAL LETTER Z WITH ACUTE + '\xad' # 0xAD -> SOFT HYPHEN + '\u017d' # 0xAE -> LATIN CAPITAL LETTER Z WITH CARON + '\u017b' # 0xAF -> LATIN CAPITAL LETTER Z WITH DOT ABOVE + '\xb0' # 0xB0 -> DEGREE SIGN + '\u0105' # 0xB1 -> LATIN SMALL LETTER A WITH OGONEK + '\u02db' # 0xB2 -> OGONEK + '\u0142' # 0xB3 -> LATIN SMALL LETTER L WITH STROKE + '\xb4' # 0xB4 -> ACUTE ACCENT + '\u013e' # 0xB5 -> LATIN SMALL LETTER L WITH CARON + '\u015b' # 0xB6 -> LATIN SMALL LETTER S WITH ACUTE + '\u02c7' # 0xB7 -> CARON + '\xb8' # 0xB8 -> CEDILLA + '\u0161' # 0xB9 -> LATIN SMALL LETTER S WITH CARON + '\u015f' # 0xBA -> LATIN SMALL LETTER S WITH CEDILLA + '\u0165' # 0xBB -> LATIN SMALL LETTER T WITH CARON + '\u017a' # 0xBC -> LATIN SMALL LETTER Z WITH ACUTE + '\u02dd' # 0xBD -> DOUBLE ACUTE ACCENT + '\u017e' # 0xBE -> LATIN SMALL LETTER Z WITH CARON + '\u017c' # 0xBF -> LATIN SMALL LETTER Z WITH DOT ABOVE + '\u0154' # 0xC0 -> LATIN CAPITAL LETTER R WITH ACUTE + '\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\u0102' # 0xC3 -> LATIN CAPITAL LETTER A WITH BREVE + '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\u0139' # 0xC5 -> LATIN CAPITAL LETTER L WITH ACUTE + '\u0106' # 0xC6 -> LATIN CAPITAL LETTER C WITH ACUTE + '\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON + '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + '\u0118' # 0xCA -> LATIN CAPITAL LETTER E WITH OGONEK + '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\u011a' # 0xCC -> LATIN CAPITAL LETTER E WITH CARON + '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\u010e' # 0xCF -> LATIN CAPITAL LETTER D WITH CARON + '\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE + '\u0143' # 0xD1 -> LATIN CAPITAL LETTER N WITH ACUTE + '\u0147' # 0xD2 -> LATIN CAPITAL LETTER N WITH CARON + '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\u0150' # 0xD5 -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE + '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xd7' # 0xD7 -> MULTIPLICATION SIGN + '\u0158' # 0xD8 -> LATIN CAPITAL LETTER R WITH CARON + '\u016e' # 0xD9 -> LATIN CAPITAL LETTER U WITH RING ABOVE + '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + '\u0170' # 0xDB -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE + '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE + '\u0162' # 0xDE -> LATIN CAPITAL LETTER T WITH CEDILLA + '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + '\u0155' # 0xE0 -> LATIN SMALL LETTER R WITH ACUTE + '\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\u0103' # 0xE3 -> LATIN SMALL LETTER A WITH BREVE + '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + '\u013a' # 0xE5 -> LATIN SMALL LETTER L WITH ACUTE + '\u0107' # 0xE6 -> LATIN SMALL LETTER C WITH ACUTE + '\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + '\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON + '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + '\u0119' # 0xEA -> LATIN SMALL LETTER E WITH OGONEK + '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + '\u011b' # 0xEC -> LATIN SMALL LETTER E WITH CARON + '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\u010f' # 0xEF -> LATIN SMALL LETTER D WITH CARON + '\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE + '\u0144' # 0xF1 -> LATIN SMALL LETTER N WITH ACUTE + '\u0148' # 0xF2 -> LATIN SMALL LETTER N WITH CARON + '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\u0151' # 0xF5 -> LATIN SMALL LETTER O WITH DOUBLE ACUTE + '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf7' # 0xF7 -> DIVISION SIGN + '\u0159' # 0xF8 -> LATIN SMALL LETTER R WITH CARON + '\u016f' # 0xF9 -> LATIN SMALL LETTER U WITH RING ABOVE + '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + '\u0171' # 0xFB -> LATIN SMALL LETTER U WITH DOUBLE ACUTE + '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + '\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE + '\u0163' # 0xFE -> LATIN SMALL LETTER T WITH CEDILLA + '\u02d9' # 0xFF -> DOT ABOVE +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/iso8859_3.py b/contrib/tools/python3/src/Lib/encodings/iso8859_3.py new file mode 100644 index 0000000000..96d3063ea6 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/iso8859_3.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec iso8859_3 generated from 'MAPPINGS/ISO8859/8859-3.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='iso8859-3', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\x80' # 0x80 -> <control> + '\x81' # 0x81 -> <control> + '\x82' # 0x82 -> <control> + '\x83' # 0x83 -> <control> + '\x84' # 0x84 -> <control> + '\x85' # 0x85 -> <control> + '\x86' # 0x86 -> <control> + '\x87' # 0x87 -> <control> + '\x88' # 0x88 -> <control> + '\x89' # 0x89 -> <control> + '\x8a' # 0x8A -> <control> + '\x8b' # 0x8B -> <control> + '\x8c' # 0x8C -> <control> + '\x8d' # 0x8D -> <control> + '\x8e' # 0x8E -> <control> + '\x8f' # 0x8F -> <control> + '\x90' # 0x90 -> <control> + '\x91' # 0x91 -> <control> + '\x92' # 0x92 -> <control> + '\x93' # 0x93 -> <control> + '\x94' # 0x94 -> <control> + '\x95' # 0x95 -> <control> + '\x96' # 0x96 -> <control> + '\x97' # 0x97 -> <control> + '\x98' # 0x98 -> <control> + '\x99' # 0x99 -> <control> + '\x9a' # 0x9A -> <control> + '\x9b' # 0x9B -> <control> + '\x9c' # 0x9C -> <control> + '\x9d' # 0x9D -> <control> + '\x9e' # 0x9E -> <control> + '\x9f' # 0x9F -> <control> + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\u0126' # 0xA1 -> LATIN CAPITAL LETTER H WITH STROKE + '\u02d8' # 0xA2 -> BREVE + '\xa3' # 0xA3 -> POUND SIGN + '\xa4' # 0xA4 -> CURRENCY SIGN + '\ufffe' + '\u0124' # 0xA6 -> LATIN CAPITAL LETTER H WITH CIRCUMFLEX + '\xa7' # 0xA7 -> SECTION SIGN + '\xa8' # 0xA8 -> DIAERESIS + '\u0130' # 0xA9 -> LATIN CAPITAL LETTER I WITH DOT ABOVE + '\u015e' # 0xAA -> LATIN CAPITAL LETTER S WITH CEDILLA + '\u011e' # 0xAB -> LATIN CAPITAL LETTER G WITH BREVE + '\u0134' # 0xAC -> LATIN CAPITAL LETTER J WITH CIRCUMFLEX + '\xad' # 0xAD -> SOFT HYPHEN + '\ufffe' + '\u017b' # 0xAF -> LATIN CAPITAL LETTER Z WITH DOT ABOVE + '\xb0' # 0xB0 -> DEGREE SIGN + '\u0127' # 0xB1 -> LATIN SMALL LETTER H WITH STROKE + '\xb2' # 0xB2 -> SUPERSCRIPT TWO + '\xb3' # 0xB3 -> SUPERSCRIPT THREE + '\xb4' # 0xB4 -> ACUTE ACCENT + '\xb5' # 0xB5 -> MICRO SIGN + '\u0125' # 0xB6 -> LATIN SMALL LETTER H WITH CIRCUMFLEX + '\xb7' # 0xB7 -> MIDDLE DOT + '\xb8' # 0xB8 -> CEDILLA + '\u0131' # 0xB9 -> LATIN SMALL LETTER DOTLESS I + '\u015f' # 0xBA -> LATIN SMALL LETTER S WITH CEDILLA + '\u011f' # 0xBB -> LATIN SMALL LETTER G WITH BREVE + '\u0135' # 0xBC -> LATIN SMALL LETTER J WITH CIRCUMFLEX + '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + '\ufffe' + '\u017c' # 0xBF -> LATIN SMALL LETTER Z WITH DOT ABOVE + '\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE + '\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\ufffe' + '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\u010a' # 0xC5 -> LATIN CAPITAL LETTER C WITH DOT ABOVE + '\u0108' # 0xC6 -> LATIN CAPITAL LETTER C WITH CIRCUMFLEX + '\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE + '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\ufffe' + '\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE + '\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE + '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\u0120' # 0xD5 -> LATIN CAPITAL LETTER G WITH DOT ABOVE + '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xd7' # 0xD7 -> MULTIPLICATION SIGN + '\u011c' # 0xD8 -> LATIN CAPITAL LETTER G WITH CIRCUMFLEX + '\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE + '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + '\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\u016c' # 0xDD -> LATIN CAPITAL LETTER U WITH BREVE + '\u015c' # 0xDE -> LATIN CAPITAL LETTER S WITH CIRCUMFLEX + '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + '\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE + '\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\ufffe' + '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + '\u010b' # 0xE5 -> LATIN SMALL LETTER C WITH DOT ABOVE + '\u0109' # 0xE6 -> LATIN SMALL LETTER C WITH CIRCUMFLEX + '\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + '\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE + '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + '\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + '\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE + '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS + '\ufffe' + '\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE + '\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE + '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\u0121' # 0xF5 -> LATIN SMALL LETTER G WITH DOT ABOVE + '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf7' # 0xF7 -> DIVISION SIGN + '\u011d' # 0xF8 -> LATIN SMALL LETTER G WITH CIRCUMFLEX + '\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE + '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + '\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + '\u016d' # 0xFD -> LATIN SMALL LETTER U WITH BREVE + '\u015d' # 0xFE -> LATIN SMALL LETTER S WITH CIRCUMFLEX + '\u02d9' # 0xFF -> DOT ABOVE +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/iso8859_4.py b/contrib/tools/python3/src/Lib/encodings/iso8859_4.py new file mode 100644 index 0000000000..65c1e00f30 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/iso8859_4.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec iso8859_4 generated from 'MAPPINGS/ISO8859/8859-4.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='iso8859-4', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\x80' # 0x80 -> <control> + '\x81' # 0x81 -> <control> + '\x82' # 0x82 -> <control> + '\x83' # 0x83 -> <control> + '\x84' # 0x84 -> <control> + '\x85' # 0x85 -> <control> + '\x86' # 0x86 -> <control> + '\x87' # 0x87 -> <control> + '\x88' # 0x88 -> <control> + '\x89' # 0x89 -> <control> + '\x8a' # 0x8A -> <control> + '\x8b' # 0x8B -> <control> + '\x8c' # 0x8C -> <control> + '\x8d' # 0x8D -> <control> + '\x8e' # 0x8E -> <control> + '\x8f' # 0x8F -> <control> + '\x90' # 0x90 -> <control> + '\x91' # 0x91 -> <control> + '\x92' # 0x92 -> <control> + '\x93' # 0x93 -> <control> + '\x94' # 0x94 -> <control> + '\x95' # 0x95 -> <control> + '\x96' # 0x96 -> <control> + '\x97' # 0x97 -> <control> + '\x98' # 0x98 -> <control> + '\x99' # 0x99 -> <control> + '\x9a' # 0x9A -> <control> + '\x9b' # 0x9B -> <control> + '\x9c' # 0x9C -> <control> + '\x9d' # 0x9D -> <control> + '\x9e' # 0x9E -> <control> + '\x9f' # 0x9F -> <control> + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\u0104' # 0xA1 -> LATIN CAPITAL LETTER A WITH OGONEK + '\u0138' # 0xA2 -> LATIN SMALL LETTER KRA + '\u0156' # 0xA3 -> LATIN CAPITAL LETTER R WITH CEDILLA + '\xa4' # 0xA4 -> CURRENCY SIGN + '\u0128' # 0xA5 -> LATIN CAPITAL LETTER I WITH TILDE + '\u013b' # 0xA6 -> LATIN CAPITAL LETTER L WITH CEDILLA + '\xa7' # 0xA7 -> SECTION SIGN + '\xa8' # 0xA8 -> DIAERESIS + '\u0160' # 0xA9 -> LATIN CAPITAL LETTER S WITH CARON + '\u0112' # 0xAA -> LATIN CAPITAL LETTER E WITH MACRON + '\u0122' # 0xAB -> LATIN CAPITAL LETTER G WITH CEDILLA + '\u0166' # 0xAC -> LATIN CAPITAL LETTER T WITH STROKE + '\xad' # 0xAD -> SOFT HYPHEN + '\u017d' # 0xAE -> LATIN CAPITAL LETTER Z WITH CARON + '\xaf' # 0xAF -> MACRON + '\xb0' # 0xB0 -> DEGREE SIGN + '\u0105' # 0xB1 -> LATIN SMALL LETTER A WITH OGONEK + '\u02db' # 0xB2 -> OGONEK + '\u0157' # 0xB3 -> LATIN SMALL LETTER R WITH CEDILLA + '\xb4' # 0xB4 -> ACUTE ACCENT + '\u0129' # 0xB5 -> LATIN SMALL LETTER I WITH TILDE + '\u013c' # 0xB6 -> LATIN SMALL LETTER L WITH CEDILLA + '\u02c7' # 0xB7 -> CARON + '\xb8' # 0xB8 -> CEDILLA + '\u0161' # 0xB9 -> LATIN SMALL LETTER S WITH CARON + '\u0113' # 0xBA -> LATIN SMALL LETTER E WITH MACRON + '\u0123' # 0xBB -> LATIN SMALL LETTER G WITH CEDILLA + '\u0167' # 0xBC -> LATIN SMALL LETTER T WITH STROKE + '\u014a' # 0xBD -> LATIN CAPITAL LETTER ENG + '\u017e' # 0xBE -> LATIN SMALL LETTER Z WITH CARON + '\u014b' # 0xBF -> LATIN SMALL LETTER ENG + '\u0100' # 0xC0 -> LATIN CAPITAL LETTER A WITH MACRON + '\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE + '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE + '\u012e' # 0xC7 -> LATIN CAPITAL LETTER I WITH OGONEK + '\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON + '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + '\u0118' # 0xCA -> LATIN CAPITAL LETTER E WITH OGONEK + '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\u0116' # 0xCC -> LATIN CAPITAL LETTER E WITH DOT ABOVE + '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\u012a' # 0xCF -> LATIN CAPITAL LETTER I WITH MACRON + '\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE + '\u0145' # 0xD1 -> LATIN CAPITAL LETTER N WITH CEDILLA + '\u014c' # 0xD2 -> LATIN CAPITAL LETTER O WITH MACRON + '\u0136' # 0xD3 -> LATIN CAPITAL LETTER K WITH CEDILLA + '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE + '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xd7' # 0xD7 -> MULTIPLICATION SIGN + '\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE + '\u0172' # 0xD9 -> LATIN CAPITAL LETTER U WITH OGONEK + '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + '\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\u0168' # 0xDD -> LATIN CAPITAL LETTER U WITH TILDE + '\u016a' # 0xDE -> LATIN CAPITAL LETTER U WITH MACRON + '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + '\u0101' # 0xE0 -> LATIN SMALL LETTER A WITH MACRON + '\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE + '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe6' # 0xE6 -> LATIN SMALL LETTER AE + '\u012f' # 0xE7 -> LATIN SMALL LETTER I WITH OGONEK + '\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON + '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + '\u0119' # 0xEA -> LATIN SMALL LETTER E WITH OGONEK + '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + '\u0117' # 0xEC -> LATIN SMALL LETTER E WITH DOT ABOVE + '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\u012b' # 0xEF -> LATIN SMALL LETTER I WITH MACRON + '\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE + '\u0146' # 0xF1 -> LATIN SMALL LETTER N WITH CEDILLA + '\u014d' # 0xF2 -> LATIN SMALL LETTER O WITH MACRON + '\u0137' # 0xF3 -> LATIN SMALL LETTER K WITH CEDILLA + '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE + '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf7' # 0xF7 -> DIVISION SIGN + '\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE + '\u0173' # 0xF9 -> LATIN SMALL LETTER U WITH OGONEK + '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + '\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + '\u0169' # 0xFD -> LATIN SMALL LETTER U WITH TILDE + '\u016b' # 0xFE -> LATIN SMALL LETTER U WITH MACRON + '\u02d9' # 0xFF -> DOT ABOVE +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/iso8859_5.py b/contrib/tools/python3/src/Lib/encodings/iso8859_5.py new file mode 100644 index 0000000000..a3c868a50c --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/iso8859_5.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec iso8859_5 generated from 'MAPPINGS/ISO8859/8859-5.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='iso8859-5', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\x80' # 0x80 -> <control> + '\x81' # 0x81 -> <control> + '\x82' # 0x82 -> <control> + '\x83' # 0x83 -> <control> + '\x84' # 0x84 -> <control> + '\x85' # 0x85 -> <control> + '\x86' # 0x86 -> <control> + '\x87' # 0x87 -> <control> + '\x88' # 0x88 -> <control> + '\x89' # 0x89 -> <control> + '\x8a' # 0x8A -> <control> + '\x8b' # 0x8B -> <control> + '\x8c' # 0x8C -> <control> + '\x8d' # 0x8D -> <control> + '\x8e' # 0x8E -> <control> + '\x8f' # 0x8F -> <control> + '\x90' # 0x90 -> <control> + '\x91' # 0x91 -> <control> + '\x92' # 0x92 -> <control> + '\x93' # 0x93 -> <control> + '\x94' # 0x94 -> <control> + '\x95' # 0x95 -> <control> + '\x96' # 0x96 -> <control> + '\x97' # 0x97 -> <control> + '\x98' # 0x98 -> <control> + '\x99' # 0x99 -> <control> + '\x9a' # 0x9A -> <control> + '\x9b' # 0x9B -> <control> + '\x9c' # 0x9C -> <control> + '\x9d' # 0x9D -> <control> + '\x9e' # 0x9E -> <control> + '\x9f' # 0x9F -> <control> + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\u0401' # 0xA1 -> CYRILLIC CAPITAL LETTER IO + '\u0402' # 0xA2 -> CYRILLIC CAPITAL LETTER DJE + '\u0403' # 0xA3 -> CYRILLIC CAPITAL LETTER GJE + '\u0404' # 0xA4 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE + '\u0405' # 0xA5 -> CYRILLIC CAPITAL LETTER DZE + '\u0406' # 0xA6 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + '\u0407' # 0xA7 -> CYRILLIC CAPITAL LETTER YI + '\u0408' # 0xA8 -> CYRILLIC CAPITAL LETTER JE + '\u0409' # 0xA9 -> CYRILLIC CAPITAL LETTER LJE + '\u040a' # 0xAA -> CYRILLIC CAPITAL LETTER NJE + '\u040b' # 0xAB -> CYRILLIC CAPITAL LETTER TSHE + '\u040c' # 0xAC -> CYRILLIC CAPITAL LETTER KJE + '\xad' # 0xAD -> SOFT HYPHEN + '\u040e' # 0xAE -> CYRILLIC CAPITAL LETTER SHORT U + '\u040f' # 0xAF -> CYRILLIC CAPITAL LETTER DZHE + '\u0410' # 0xB0 -> CYRILLIC CAPITAL LETTER A + '\u0411' # 0xB1 -> CYRILLIC CAPITAL LETTER BE + '\u0412' # 0xB2 -> CYRILLIC CAPITAL LETTER VE + '\u0413' # 0xB3 -> CYRILLIC CAPITAL LETTER GHE + '\u0414' # 0xB4 -> CYRILLIC CAPITAL LETTER DE + '\u0415' # 0xB5 -> CYRILLIC CAPITAL LETTER IE + '\u0416' # 0xB6 -> CYRILLIC CAPITAL LETTER ZHE + '\u0417' # 0xB7 -> CYRILLIC CAPITAL LETTER ZE + '\u0418' # 0xB8 -> CYRILLIC CAPITAL LETTER I + '\u0419' # 0xB9 -> CYRILLIC CAPITAL LETTER SHORT I + '\u041a' # 0xBA -> CYRILLIC CAPITAL LETTER KA + '\u041b' # 0xBB -> CYRILLIC CAPITAL LETTER EL + '\u041c' # 0xBC -> CYRILLIC CAPITAL LETTER EM + '\u041d' # 0xBD -> CYRILLIC CAPITAL LETTER EN + '\u041e' # 0xBE -> CYRILLIC CAPITAL LETTER O + '\u041f' # 0xBF -> CYRILLIC CAPITAL LETTER PE + '\u0420' # 0xC0 -> CYRILLIC CAPITAL LETTER ER + '\u0421' # 0xC1 -> CYRILLIC CAPITAL LETTER ES + '\u0422' # 0xC2 -> CYRILLIC CAPITAL LETTER TE + '\u0423' # 0xC3 -> CYRILLIC CAPITAL LETTER U + '\u0424' # 0xC4 -> CYRILLIC CAPITAL LETTER EF + '\u0425' # 0xC5 -> CYRILLIC CAPITAL LETTER HA + '\u0426' # 0xC6 -> CYRILLIC CAPITAL LETTER TSE + '\u0427' # 0xC7 -> CYRILLIC CAPITAL LETTER CHE + '\u0428' # 0xC8 -> CYRILLIC CAPITAL LETTER SHA + '\u0429' # 0xC9 -> CYRILLIC CAPITAL LETTER SHCHA + '\u042a' # 0xCA -> CYRILLIC CAPITAL LETTER HARD SIGN + '\u042b' # 0xCB -> CYRILLIC CAPITAL LETTER YERU + '\u042c' # 0xCC -> CYRILLIC CAPITAL LETTER SOFT SIGN + '\u042d' # 0xCD -> CYRILLIC CAPITAL LETTER E + '\u042e' # 0xCE -> CYRILLIC CAPITAL LETTER YU + '\u042f' # 0xCF -> CYRILLIC CAPITAL LETTER YA + '\u0430' # 0xD0 -> CYRILLIC SMALL LETTER A + '\u0431' # 0xD1 -> CYRILLIC SMALL LETTER BE + '\u0432' # 0xD2 -> CYRILLIC SMALL LETTER VE + '\u0433' # 0xD3 -> CYRILLIC SMALL LETTER GHE + '\u0434' # 0xD4 -> CYRILLIC SMALL LETTER DE + '\u0435' # 0xD5 -> CYRILLIC SMALL LETTER IE + '\u0436' # 0xD6 -> CYRILLIC SMALL LETTER ZHE + '\u0437' # 0xD7 -> CYRILLIC SMALL LETTER ZE + '\u0438' # 0xD8 -> CYRILLIC SMALL LETTER I + '\u0439' # 0xD9 -> CYRILLIC SMALL LETTER SHORT I + '\u043a' # 0xDA -> CYRILLIC SMALL LETTER KA + '\u043b' # 0xDB -> CYRILLIC SMALL LETTER EL + '\u043c' # 0xDC -> CYRILLIC SMALL LETTER EM + '\u043d' # 0xDD -> CYRILLIC SMALL LETTER EN + '\u043e' # 0xDE -> CYRILLIC SMALL LETTER O + '\u043f' # 0xDF -> CYRILLIC SMALL LETTER PE + '\u0440' # 0xE0 -> CYRILLIC SMALL LETTER ER + '\u0441' # 0xE1 -> CYRILLIC SMALL LETTER ES + '\u0442' # 0xE2 -> CYRILLIC SMALL LETTER TE + '\u0443' # 0xE3 -> CYRILLIC SMALL LETTER U + '\u0444' # 0xE4 -> CYRILLIC SMALL LETTER EF + '\u0445' # 0xE5 -> CYRILLIC SMALL LETTER HA + '\u0446' # 0xE6 -> CYRILLIC SMALL LETTER TSE + '\u0447' # 0xE7 -> CYRILLIC SMALL LETTER CHE + '\u0448' # 0xE8 -> CYRILLIC SMALL LETTER SHA + '\u0449' # 0xE9 -> CYRILLIC SMALL LETTER SHCHA + '\u044a' # 0xEA -> CYRILLIC SMALL LETTER HARD SIGN + '\u044b' # 0xEB -> CYRILLIC SMALL LETTER YERU + '\u044c' # 0xEC -> CYRILLIC SMALL LETTER SOFT SIGN + '\u044d' # 0xED -> CYRILLIC SMALL LETTER E + '\u044e' # 0xEE -> CYRILLIC SMALL LETTER YU + '\u044f' # 0xEF -> CYRILLIC SMALL LETTER YA + '\u2116' # 0xF0 -> NUMERO SIGN + '\u0451' # 0xF1 -> CYRILLIC SMALL LETTER IO + '\u0452' # 0xF2 -> CYRILLIC SMALL LETTER DJE + '\u0453' # 0xF3 -> CYRILLIC SMALL LETTER GJE + '\u0454' # 0xF4 -> CYRILLIC SMALL LETTER UKRAINIAN IE + '\u0455' # 0xF5 -> CYRILLIC SMALL LETTER DZE + '\u0456' # 0xF6 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + '\u0457' # 0xF7 -> CYRILLIC SMALL LETTER YI + '\u0458' # 0xF8 -> CYRILLIC SMALL LETTER JE + '\u0459' # 0xF9 -> CYRILLIC SMALL LETTER LJE + '\u045a' # 0xFA -> CYRILLIC SMALL LETTER NJE + '\u045b' # 0xFB -> CYRILLIC SMALL LETTER TSHE + '\u045c' # 0xFC -> CYRILLIC SMALL LETTER KJE + '\xa7' # 0xFD -> SECTION SIGN + '\u045e' # 0xFE -> CYRILLIC SMALL LETTER SHORT U + '\u045f' # 0xFF -> CYRILLIC SMALL LETTER DZHE +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/iso8859_6.py b/contrib/tools/python3/src/Lib/encodings/iso8859_6.py new file mode 100644 index 0000000000..b02ade6eaf --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/iso8859_6.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec iso8859_6 generated from 'MAPPINGS/ISO8859/8859-6.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='iso8859-6', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\x80' # 0x80 -> <control> + '\x81' # 0x81 -> <control> + '\x82' # 0x82 -> <control> + '\x83' # 0x83 -> <control> + '\x84' # 0x84 -> <control> + '\x85' # 0x85 -> <control> + '\x86' # 0x86 -> <control> + '\x87' # 0x87 -> <control> + '\x88' # 0x88 -> <control> + '\x89' # 0x89 -> <control> + '\x8a' # 0x8A -> <control> + '\x8b' # 0x8B -> <control> + '\x8c' # 0x8C -> <control> + '\x8d' # 0x8D -> <control> + '\x8e' # 0x8E -> <control> + '\x8f' # 0x8F -> <control> + '\x90' # 0x90 -> <control> + '\x91' # 0x91 -> <control> + '\x92' # 0x92 -> <control> + '\x93' # 0x93 -> <control> + '\x94' # 0x94 -> <control> + '\x95' # 0x95 -> <control> + '\x96' # 0x96 -> <control> + '\x97' # 0x97 -> <control> + '\x98' # 0x98 -> <control> + '\x99' # 0x99 -> <control> + '\x9a' # 0x9A -> <control> + '\x9b' # 0x9B -> <control> + '\x9c' # 0x9C -> <control> + '\x9d' # 0x9D -> <control> + '\x9e' # 0x9E -> <control> + '\x9f' # 0x9F -> <control> + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\ufffe' + '\ufffe' + '\ufffe' + '\xa4' # 0xA4 -> CURRENCY SIGN + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\u060c' # 0xAC -> ARABIC COMMA + '\xad' # 0xAD -> SOFT HYPHEN + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\u061b' # 0xBB -> ARABIC SEMICOLON + '\ufffe' + '\ufffe' + '\ufffe' + '\u061f' # 0xBF -> ARABIC QUESTION MARK + '\ufffe' + '\u0621' # 0xC1 -> ARABIC LETTER HAMZA + '\u0622' # 0xC2 -> ARABIC LETTER ALEF WITH MADDA ABOVE + '\u0623' # 0xC3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE + '\u0624' # 0xC4 -> ARABIC LETTER WAW WITH HAMZA ABOVE + '\u0625' # 0xC5 -> ARABIC LETTER ALEF WITH HAMZA BELOW + '\u0626' # 0xC6 -> ARABIC LETTER YEH WITH HAMZA ABOVE + '\u0627' # 0xC7 -> ARABIC LETTER ALEF + '\u0628' # 0xC8 -> ARABIC LETTER BEH + '\u0629' # 0xC9 -> ARABIC LETTER TEH MARBUTA + '\u062a' # 0xCA -> ARABIC LETTER TEH + '\u062b' # 0xCB -> ARABIC LETTER THEH + '\u062c' # 0xCC -> ARABIC LETTER JEEM + '\u062d' # 0xCD -> ARABIC LETTER HAH + '\u062e' # 0xCE -> ARABIC LETTER KHAH + '\u062f' # 0xCF -> ARABIC LETTER DAL + '\u0630' # 0xD0 -> ARABIC LETTER THAL + '\u0631' # 0xD1 -> ARABIC LETTER REH + '\u0632' # 0xD2 -> ARABIC LETTER ZAIN + '\u0633' # 0xD3 -> ARABIC LETTER SEEN + '\u0634' # 0xD4 -> ARABIC LETTER SHEEN + '\u0635' # 0xD5 -> ARABIC LETTER SAD + '\u0636' # 0xD6 -> ARABIC LETTER DAD + '\u0637' # 0xD7 -> ARABIC LETTER TAH + '\u0638' # 0xD8 -> ARABIC LETTER ZAH + '\u0639' # 0xD9 -> ARABIC LETTER AIN + '\u063a' # 0xDA -> ARABIC LETTER GHAIN + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\u0640' # 0xE0 -> ARABIC TATWEEL + '\u0641' # 0xE1 -> ARABIC LETTER FEH + '\u0642' # 0xE2 -> ARABIC LETTER QAF + '\u0643' # 0xE3 -> ARABIC LETTER KAF + '\u0644' # 0xE4 -> ARABIC LETTER LAM + '\u0645' # 0xE5 -> ARABIC LETTER MEEM + '\u0646' # 0xE6 -> ARABIC LETTER NOON + '\u0647' # 0xE7 -> ARABIC LETTER HEH + '\u0648' # 0xE8 -> ARABIC LETTER WAW + '\u0649' # 0xE9 -> ARABIC LETTER ALEF MAKSURA + '\u064a' # 0xEA -> ARABIC LETTER YEH + '\u064b' # 0xEB -> ARABIC FATHATAN + '\u064c' # 0xEC -> ARABIC DAMMATAN + '\u064d' # 0xED -> ARABIC KASRATAN + '\u064e' # 0xEE -> ARABIC FATHA + '\u064f' # 0xEF -> ARABIC DAMMA + '\u0650' # 0xF0 -> ARABIC KASRA + '\u0651' # 0xF1 -> ARABIC SHADDA + '\u0652' # 0xF2 -> ARABIC SUKUN + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/iso8859_7.py b/contrib/tools/python3/src/Lib/encodings/iso8859_7.py new file mode 100644 index 0000000000..d7b39cbc3a --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/iso8859_7.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec iso8859_7 generated from 'MAPPINGS/ISO8859/8859-7.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='iso8859-7', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\x80' # 0x80 -> <control> + '\x81' # 0x81 -> <control> + '\x82' # 0x82 -> <control> + '\x83' # 0x83 -> <control> + '\x84' # 0x84 -> <control> + '\x85' # 0x85 -> <control> + '\x86' # 0x86 -> <control> + '\x87' # 0x87 -> <control> + '\x88' # 0x88 -> <control> + '\x89' # 0x89 -> <control> + '\x8a' # 0x8A -> <control> + '\x8b' # 0x8B -> <control> + '\x8c' # 0x8C -> <control> + '\x8d' # 0x8D -> <control> + '\x8e' # 0x8E -> <control> + '\x8f' # 0x8F -> <control> + '\x90' # 0x90 -> <control> + '\x91' # 0x91 -> <control> + '\x92' # 0x92 -> <control> + '\x93' # 0x93 -> <control> + '\x94' # 0x94 -> <control> + '\x95' # 0x95 -> <control> + '\x96' # 0x96 -> <control> + '\x97' # 0x97 -> <control> + '\x98' # 0x98 -> <control> + '\x99' # 0x99 -> <control> + '\x9a' # 0x9A -> <control> + '\x9b' # 0x9B -> <control> + '\x9c' # 0x9C -> <control> + '\x9d' # 0x9D -> <control> + '\x9e' # 0x9E -> <control> + '\x9f' # 0x9F -> <control> + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\u2018' # 0xA1 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0xA2 -> RIGHT SINGLE QUOTATION MARK + '\xa3' # 0xA3 -> POUND SIGN + '\u20ac' # 0xA4 -> EURO SIGN + '\u20af' # 0xA5 -> DRACHMA SIGN + '\xa6' # 0xA6 -> BROKEN BAR + '\xa7' # 0xA7 -> SECTION SIGN + '\xa8' # 0xA8 -> DIAERESIS + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\u037a' # 0xAA -> GREEK YPOGEGRAMMENI + '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xac' # 0xAC -> NOT SIGN + '\xad' # 0xAD -> SOFT HYPHEN + '\ufffe' + '\u2015' # 0xAF -> HORIZONTAL BAR + '\xb0' # 0xB0 -> DEGREE SIGN + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\xb2' # 0xB2 -> SUPERSCRIPT TWO + '\xb3' # 0xB3 -> SUPERSCRIPT THREE + '\u0384' # 0xB4 -> GREEK TONOS + '\u0385' # 0xB5 -> GREEK DIALYTIKA TONOS + '\u0386' # 0xB6 -> GREEK CAPITAL LETTER ALPHA WITH TONOS + '\xb7' # 0xB7 -> MIDDLE DOT + '\u0388' # 0xB8 -> GREEK CAPITAL LETTER EPSILON WITH TONOS + '\u0389' # 0xB9 -> GREEK CAPITAL LETTER ETA WITH TONOS + '\u038a' # 0xBA -> GREEK CAPITAL LETTER IOTA WITH TONOS + '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u038c' # 0xBC -> GREEK CAPITAL LETTER OMICRON WITH TONOS + '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + '\u038e' # 0xBE -> GREEK CAPITAL LETTER UPSILON WITH TONOS + '\u038f' # 0xBF -> GREEK CAPITAL LETTER OMEGA WITH TONOS + '\u0390' # 0xC0 -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS + '\u0391' # 0xC1 -> GREEK CAPITAL LETTER ALPHA + '\u0392' # 0xC2 -> GREEK CAPITAL LETTER BETA + '\u0393' # 0xC3 -> GREEK CAPITAL LETTER GAMMA + '\u0394' # 0xC4 -> GREEK CAPITAL LETTER DELTA + '\u0395' # 0xC5 -> GREEK CAPITAL LETTER EPSILON + '\u0396' # 0xC6 -> GREEK CAPITAL LETTER ZETA + '\u0397' # 0xC7 -> GREEK CAPITAL LETTER ETA + '\u0398' # 0xC8 -> GREEK CAPITAL LETTER THETA + '\u0399' # 0xC9 -> GREEK CAPITAL LETTER IOTA + '\u039a' # 0xCA -> GREEK CAPITAL LETTER KAPPA + '\u039b' # 0xCB -> GREEK CAPITAL LETTER LAMDA + '\u039c' # 0xCC -> GREEK CAPITAL LETTER MU + '\u039d' # 0xCD -> GREEK CAPITAL LETTER NU + '\u039e' # 0xCE -> GREEK CAPITAL LETTER XI + '\u039f' # 0xCF -> GREEK CAPITAL LETTER OMICRON + '\u03a0' # 0xD0 -> GREEK CAPITAL LETTER PI + '\u03a1' # 0xD1 -> GREEK CAPITAL LETTER RHO + '\ufffe' + '\u03a3' # 0xD3 -> GREEK CAPITAL LETTER SIGMA + '\u03a4' # 0xD4 -> GREEK CAPITAL LETTER TAU + '\u03a5' # 0xD5 -> GREEK CAPITAL LETTER UPSILON + '\u03a6' # 0xD6 -> GREEK CAPITAL LETTER PHI + '\u03a7' # 0xD7 -> GREEK CAPITAL LETTER CHI + '\u03a8' # 0xD8 -> GREEK CAPITAL LETTER PSI + '\u03a9' # 0xD9 -> GREEK CAPITAL LETTER OMEGA + '\u03aa' # 0xDA -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA + '\u03ab' # 0xDB -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA + '\u03ac' # 0xDC -> GREEK SMALL LETTER ALPHA WITH TONOS + '\u03ad' # 0xDD -> GREEK SMALL LETTER EPSILON WITH TONOS + '\u03ae' # 0xDE -> GREEK SMALL LETTER ETA WITH TONOS + '\u03af' # 0xDF -> GREEK SMALL LETTER IOTA WITH TONOS + '\u03b0' # 0xE0 -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS + '\u03b1' # 0xE1 -> GREEK SMALL LETTER ALPHA + '\u03b2' # 0xE2 -> GREEK SMALL LETTER BETA + '\u03b3' # 0xE3 -> GREEK SMALL LETTER GAMMA + '\u03b4' # 0xE4 -> GREEK SMALL LETTER DELTA + '\u03b5' # 0xE5 -> GREEK SMALL LETTER EPSILON + '\u03b6' # 0xE6 -> GREEK SMALL LETTER ZETA + '\u03b7' # 0xE7 -> GREEK SMALL LETTER ETA + '\u03b8' # 0xE8 -> GREEK SMALL LETTER THETA + '\u03b9' # 0xE9 -> GREEK SMALL LETTER IOTA + '\u03ba' # 0xEA -> GREEK SMALL LETTER KAPPA + '\u03bb' # 0xEB -> GREEK SMALL LETTER LAMDA + '\u03bc' # 0xEC -> GREEK SMALL LETTER MU + '\u03bd' # 0xED -> GREEK SMALL LETTER NU + '\u03be' # 0xEE -> GREEK SMALL LETTER XI + '\u03bf' # 0xEF -> GREEK SMALL LETTER OMICRON + '\u03c0' # 0xF0 -> GREEK SMALL LETTER PI + '\u03c1' # 0xF1 -> GREEK SMALL LETTER RHO + '\u03c2' # 0xF2 -> GREEK SMALL LETTER FINAL SIGMA + '\u03c3' # 0xF3 -> GREEK SMALL LETTER SIGMA + '\u03c4' # 0xF4 -> GREEK SMALL LETTER TAU + '\u03c5' # 0xF5 -> GREEK SMALL LETTER UPSILON + '\u03c6' # 0xF6 -> GREEK SMALL LETTER PHI + '\u03c7' # 0xF7 -> GREEK SMALL LETTER CHI + '\u03c8' # 0xF8 -> GREEK SMALL LETTER PSI + '\u03c9' # 0xF9 -> GREEK SMALL LETTER OMEGA + '\u03ca' # 0xFA -> GREEK SMALL LETTER IOTA WITH DIALYTIKA + '\u03cb' # 0xFB -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA + '\u03cc' # 0xFC -> GREEK SMALL LETTER OMICRON WITH TONOS + '\u03cd' # 0xFD -> GREEK SMALL LETTER UPSILON WITH TONOS + '\u03ce' # 0xFE -> GREEK SMALL LETTER OMEGA WITH TONOS + '\ufffe' +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/iso8859_8.py b/contrib/tools/python3/src/Lib/encodings/iso8859_8.py new file mode 100644 index 0000000000..8184902738 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/iso8859_8.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec iso8859_8 generated from 'MAPPINGS/ISO8859/8859-8.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='iso8859-8', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\x80' # 0x80 -> <control> + '\x81' # 0x81 -> <control> + '\x82' # 0x82 -> <control> + '\x83' # 0x83 -> <control> + '\x84' # 0x84 -> <control> + '\x85' # 0x85 -> <control> + '\x86' # 0x86 -> <control> + '\x87' # 0x87 -> <control> + '\x88' # 0x88 -> <control> + '\x89' # 0x89 -> <control> + '\x8a' # 0x8A -> <control> + '\x8b' # 0x8B -> <control> + '\x8c' # 0x8C -> <control> + '\x8d' # 0x8D -> <control> + '\x8e' # 0x8E -> <control> + '\x8f' # 0x8F -> <control> + '\x90' # 0x90 -> <control> + '\x91' # 0x91 -> <control> + '\x92' # 0x92 -> <control> + '\x93' # 0x93 -> <control> + '\x94' # 0x94 -> <control> + '\x95' # 0x95 -> <control> + '\x96' # 0x96 -> <control> + '\x97' # 0x97 -> <control> + '\x98' # 0x98 -> <control> + '\x99' # 0x99 -> <control> + '\x9a' # 0x9A -> <control> + '\x9b' # 0x9B -> <control> + '\x9c' # 0x9C -> <control> + '\x9d' # 0x9D -> <control> + '\x9e' # 0x9E -> <control> + '\x9f' # 0x9F -> <control> + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\ufffe' + '\xa2' # 0xA2 -> CENT SIGN + '\xa3' # 0xA3 -> POUND SIGN + '\xa4' # 0xA4 -> CURRENCY SIGN + '\xa5' # 0xA5 -> YEN SIGN + '\xa6' # 0xA6 -> BROKEN BAR + '\xa7' # 0xA7 -> SECTION SIGN + '\xa8' # 0xA8 -> DIAERESIS + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\xd7' # 0xAA -> MULTIPLICATION SIGN + '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xac' # 0xAC -> NOT SIGN + '\xad' # 0xAD -> SOFT HYPHEN + '\xae' # 0xAE -> REGISTERED SIGN + '\xaf' # 0xAF -> MACRON + '\xb0' # 0xB0 -> DEGREE SIGN + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\xb2' # 0xB2 -> SUPERSCRIPT TWO + '\xb3' # 0xB3 -> SUPERSCRIPT THREE + '\xb4' # 0xB4 -> ACUTE ACCENT + '\xb5' # 0xB5 -> MICRO SIGN + '\xb6' # 0xB6 -> PILCROW SIGN + '\xb7' # 0xB7 -> MIDDLE DOT + '\xb8' # 0xB8 -> CEDILLA + '\xb9' # 0xB9 -> SUPERSCRIPT ONE + '\xf7' # 0xBA -> DIVISION SIGN + '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER + '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + '\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\u2017' # 0xDF -> DOUBLE LOW LINE + '\u05d0' # 0xE0 -> HEBREW LETTER ALEF + '\u05d1' # 0xE1 -> HEBREW LETTER BET + '\u05d2' # 0xE2 -> HEBREW LETTER GIMEL + '\u05d3' # 0xE3 -> HEBREW LETTER DALET + '\u05d4' # 0xE4 -> HEBREW LETTER HE + '\u05d5' # 0xE5 -> HEBREW LETTER VAV + '\u05d6' # 0xE6 -> HEBREW LETTER ZAYIN + '\u05d7' # 0xE7 -> HEBREW LETTER HET + '\u05d8' # 0xE8 -> HEBREW LETTER TET + '\u05d9' # 0xE9 -> HEBREW LETTER YOD + '\u05da' # 0xEA -> HEBREW LETTER FINAL KAF + '\u05db' # 0xEB -> HEBREW LETTER KAF + '\u05dc' # 0xEC -> HEBREW LETTER LAMED + '\u05dd' # 0xED -> HEBREW LETTER FINAL MEM + '\u05de' # 0xEE -> HEBREW LETTER MEM + '\u05df' # 0xEF -> HEBREW LETTER FINAL NUN + '\u05e0' # 0xF0 -> HEBREW LETTER NUN + '\u05e1' # 0xF1 -> HEBREW LETTER SAMEKH + '\u05e2' # 0xF2 -> HEBREW LETTER AYIN + '\u05e3' # 0xF3 -> HEBREW LETTER FINAL PE + '\u05e4' # 0xF4 -> HEBREW LETTER PE + '\u05e5' # 0xF5 -> HEBREW LETTER FINAL TSADI + '\u05e6' # 0xF6 -> HEBREW LETTER TSADI + '\u05e7' # 0xF7 -> HEBREW LETTER QOF + '\u05e8' # 0xF8 -> HEBREW LETTER RESH + '\u05e9' # 0xF9 -> HEBREW LETTER SHIN + '\u05ea' # 0xFA -> HEBREW LETTER TAV + '\ufffe' + '\ufffe' + '\u200e' # 0xFD -> LEFT-TO-RIGHT MARK + '\u200f' # 0xFE -> RIGHT-TO-LEFT MARK + '\ufffe' +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/iso8859_9.py b/contrib/tools/python3/src/Lib/encodings/iso8859_9.py new file mode 100644 index 0000000000..e539fddac6 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/iso8859_9.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec iso8859_9 generated from 'MAPPINGS/ISO8859/8859-9.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='iso8859-9', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\x80' # 0x80 -> <control> + '\x81' # 0x81 -> <control> + '\x82' # 0x82 -> <control> + '\x83' # 0x83 -> <control> + '\x84' # 0x84 -> <control> + '\x85' # 0x85 -> <control> + '\x86' # 0x86 -> <control> + '\x87' # 0x87 -> <control> + '\x88' # 0x88 -> <control> + '\x89' # 0x89 -> <control> + '\x8a' # 0x8A -> <control> + '\x8b' # 0x8B -> <control> + '\x8c' # 0x8C -> <control> + '\x8d' # 0x8D -> <control> + '\x8e' # 0x8E -> <control> + '\x8f' # 0x8F -> <control> + '\x90' # 0x90 -> <control> + '\x91' # 0x91 -> <control> + '\x92' # 0x92 -> <control> + '\x93' # 0x93 -> <control> + '\x94' # 0x94 -> <control> + '\x95' # 0x95 -> <control> + '\x96' # 0x96 -> <control> + '\x97' # 0x97 -> <control> + '\x98' # 0x98 -> <control> + '\x99' # 0x99 -> <control> + '\x9a' # 0x9A -> <control> + '\x9b' # 0x9B -> <control> + '\x9c' # 0x9C -> <control> + '\x9d' # 0x9D -> <control> + '\x9e' # 0x9E -> <control> + '\x9f' # 0x9F -> <control> + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK + '\xa2' # 0xA2 -> CENT SIGN + '\xa3' # 0xA3 -> POUND SIGN + '\xa4' # 0xA4 -> CURRENCY SIGN + '\xa5' # 0xA5 -> YEN SIGN + '\xa6' # 0xA6 -> BROKEN BAR + '\xa7' # 0xA7 -> SECTION SIGN + '\xa8' # 0xA8 -> DIAERESIS + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR + '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xac' # 0xAC -> NOT SIGN + '\xad' # 0xAD -> SOFT HYPHEN + '\xae' # 0xAE -> REGISTERED SIGN + '\xaf' # 0xAF -> MACRON + '\xb0' # 0xB0 -> DEGREE SIGN + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\xb2' # 0xB2 -> SUPERSCRIPT TWO + '\xb3' # 0xB3 -> SUPERSCRIPT THREE + '\xb4' # 0xB4 -> ACUTE ACCENT + '\xb5' # 0xB5 -> MICRO SIGN + '\xb6' # 0xB6 -> PILCROW SIGN + '\xb7' # 0xB7 -> MIDDLE DOT + '\xb8' # 0xB8 -> CEDILLA + '\xb9' # 0xB9 -> SUPERSCRIPT ONE + '\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR + '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER + '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + '\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS + '\xbf' # 0xBF -> INVERTED QUESTION MARK + '\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE + '\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE + '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE + '\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE + '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\u011e' # 0xD0 -> LATIN CAPITAL LETTER G WITH BREVE + '\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE + '\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE + '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE + '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xd7' # 0xD7 -> MULTIPLICATION SIGN + '\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE + '\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE + '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + '\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\u0130' # 0xDD -> LATIN CAPITAL LETTER I WITH DOT ABOVE + '\u015e' # 0xDE -> LATIN CAPITAL LETTER S WITH CEDILLA + '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S + '\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE + '\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE + '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe6' # 0xE6 -> LATIN SMALL LETTER AE + '\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + '\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE + '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + '\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + '\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE + '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS + '\u011f' # 0xF0 -> LATIN SMALL LETTER G WITH BREVE + '\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE + '\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE + '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE + '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf7' # 0xF7 -> DIVISION SIGN + '\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE + '\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE + '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + '\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + '\u0131' # 0xFD -> LATIN SMALL LETTER DOTLESS I + '\u015f' # 0xFE -> LATIN SMALL LETTER S WITH CEDILLA + '\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/johab.py b/contrib/tools/python3/src/Lib/encodings/johab.py new file mode 100644 index 0000000000..512aeeb732 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/johab.py @@ -0,0 +1,39 @@ +# +# johab.py: Python Unicode Codec for JOHAB +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_kr, codecs +import _multibytecodec as mbc + +codec = _codecs_kr.getcodec('johab') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='johab', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/koi8_r.py b/contrib/tools/python3/src/Lib/encodings/koi8_r.py new file mode 100644 index 0000000000..41ddde856e --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/koi8_r.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec koi8_r generated from 'MAPPINGS/VENDORS/MISC/KOI8-R.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='koi8-r', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\u2500' # 0x80 -> BOX DRAWINGS LIGHT HORIZONTAL + '\u2502' # 0x81 -> BOX DRAWINGS LIGHT VERTICAL + '\u250c' # 0x82 -> BOX DRAWINGS LIGHT DOWN AND RIGHT + '\u2510' # 0x83 -> BOX DRAWINGS LIGHT DOWN AND LEFT + '\u2514' # 0x84 -> BOX DRAWINGS LIGHT UP AND RIGHT + '\u2518' # 0x85 -> BOX DRAWINGS LIGHT UP AND LEFT + '\u251c' # 0x86 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT + '\u2524' # 0x87 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT + '\u252c' # 0x88 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + '\u2534' # 0x89 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL + '\u253c' # 0x8A -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + '\u2580' # 0x8B -> UPPER HALF BLOCK + '\u2584' # 0x8C -> LOWER HALF BLOCK + '\u2588' # 0x8D -> FULL BLOCK + '\u258c' # 0x8E -> LEFT HALF BLOCK + '\u2590' # 0x8F -> RIGHT HALF BLOCK + '\u2591' # 0x90 -> LIGHT SHADE + '\u2592' # 0x91 -> MEDIUM SHADE + '\u2593' # 0x92 -> DARK SHADE + '\u2320' # 0x93 -> TOP HALF INTEGRAL + '\u25a0' # 0x94 -> BLACK SQUARE + '\u2219' # 0x95 -> BULLET OPERATOR + '\u221a' # 0x96 -> SQUARE ROOT + '\u2248' # 0x97 -> ALMOST EQUAL TO + '\u2264' # 0x98 -> LESS-THAN OR EQUAL TO + '\u2265' # 0x99 -> GREATER-THAN OR EQUAL TO + '\xa0' # 0x9A -> NO-BREAK SPACE + '\u2321' # 0x9B -> BOTTOM HALF INTEGRAL + '\xb0' # 0x9C -> DEGREE SIGN + '\xb2' # 0x9D -> SUPERSCRIPT TWO + '\xb7' # 0x9E -> MIDDLE DOT + '\xf7' # 0x9F -> DIVISION SIGN + '\u2550' # 0xA0 -> BOX DRAWINGS DOUBLE HORIZONTAL + '\u2551' # 0xA1 -> BOX DRAWINGS DOUBLE VERTICAL + '\u2552' # 0xA2 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + '\u0451' # 0xA3 -> CYRILLIC SMALL LETTER IO + '\u2553' # 0xA4 -> BOX DRAWINGS DOWN DOUBLE AND RIGHT SINGLE + '\u2554' # 0xA5 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + '\u2555' # 0xA6 -> BOX DRAWINGS DOWN SINGLE AND LEFT DOUBLE + '\u2556' # 0xA7 -> BOX DRAWINGS DOWN DOUBLE AND LEFT SINGLE + '\u2557' # 0xA8 -> BOX DRAWINGS DOUBLE DOWN AND LEFT + '\u2558' # 0xA9 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + '\u2559' # 0xAA -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + '\u255a' # 0xAB -> BOX DRAWINGS DOUBLE UP AND RIGHT + '\u255b' # 0xAC -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + '\u255c' # 0xAD -> BOX DRAWINGS UP DOUBLE AND LEFT SINGLE + '\u255d' # 0xAE -> BOX DRAWINGS DOUBLE UP AND LEFT + '\u255e' # 0xAF -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + '\u255f' # 0xB0 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + '\u2560' # 0xB1 -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + '\u2561' # 0xB2 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + '\u0401' # 0xB3 -> CYRILLIC CAPITAL LETTER IO + '\u2562' # 0xB4 -> BOX DRAWINGS VERTICAL DOUBLE AND LEFT SINGLE + '\u2563' # 0xB5 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + '\u2564' # 0xB6 -> BOX DRAWINGS DOWN SINGLE AND HORIZONTAL DOUBLE + '\u2565' # 0xB7 -> BOX DRAWINGS DOWN DOUBLE AND HORIZONTAL SINGLE + '\u2566' # 0xB8 -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + '\u2567' # 0xB9 -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + '\u2568' # 0xBA -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + '\u2569' # 0xBB -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + '\u256a' # 0xBC -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + '\u256b' # 0xBD -> BOX DRAWINGS VERTICAL DOUBLE AND HORIZONTAL SINGLE + '\u256c' # 0xBE -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + '\xa9' # 0xBF -> COPYRIGHT SIGN + '\u044e' # 0xC0 -> CYRILLIC SMALL LETTER YU + '\u0430' # 0xC1 -> CYRILLIC SMALL LETTER A + '\u0431' # 0xC2 -> CYRILLIC SMALL LETTER BE + '\u0446' # 0xC3 -> CYRILLIC SMALL LETTER TSE + '\u0434' # 0xC4 -> CYRILLIC SMALL LETTER DE + '\u0435' # 0xC5 -> CYRILLIC SMALL LETTER IE + '\u0444' # 0xC6 -> CYRILLIC SMALL LETTER EF + '\u0433' # 0xC7 -> CYRILLIC SMALL LETTER GHE + '\u0445' # 0xC8 -> CYRILLIC SMALL LETTER HA + '\u0438' # 0xC9 -> CYRILLIC SMALL LETTER I + '\u0439' # 0xCA -> CYRILLIC SMALL LETTER SHORT I + '\u043a' # 0xCB -> CYRILLIC SMALL LETTER KA + '\u043b' # 0xCC -> CYRILLIC SMALL LETTER EL + '\u043c' # 0xCD -> CYRILLIC SMALL LETTER EM + '\u043d' # 0xCE -> CYRILLIC SMALL LETTER EN + '\u043e' # 0xCF -> CYRILLIC SMALL LETTER O + '\u043f' # 0xD0 -> CYRILLIC SMALL LETTER PE + '\u044f' # 0xD1 -> CYRILLIC SMALL LETTER YA + '\u0440' # 0xD2 -> CYRILLIC SMALL LETTER ER + '\u0441' # 0xD3 -> CYRILLIC SMALL LETTER ES + '\u0442' # 0xD4 -> CYRILLIC SMALL LETTER TE + '\u0443' # 0xD5 -> CYRILLIC SMALL LETTER U + '\u0436' # 0xD6 -> CYRILLIC SMALL LETTER ZHE + '\u0432' # 0xD7 -> CYRILLIC SMALL LETTER VE + '\u044c' # 0xD8 -> CYRILLIC SMALL LETTER SOFT SIGN + '\u044b' # 0xD9 -> CYRILLIC SMALL LETTER YERU + '\u0437' # 0xDA -> CYRILLIC SMALL LETTER ZE + '\u0448' # 0xDB -> CYRILLIC SMALL LETTER SHA + '\u044d' # 0xDC -> CYRILLIC SMALL LETTER E + '\u0449' # 0xDD -> CYRILLIC SMALL LETTER SHCHA + '\u0447' # 0xDE -> CYRILLIC SMALL LETTER CHE + '\u044a' # 0xDF -> CYRILLIC SMALL LETTER HARD SIGN + '\u042e' # 0xE0 -> CYRILLIC CAPITAL LETTER YU + '\u0410' # 0xE1 -> CYRILLIC CAPITAL LETTER A + '\u0411' # 0xE2 -> CYRILLIC CAPITAL LETTER BE + '\u0426' # 0xE3 -> CYRILLIC CAPITAL LETTER TSE + '\u0414' # 0xE4 -> CYRILLIC CAPITAL LETTER DE + '\u0415' # 0xE5 -> CYRILLIC CAPITAL LETTER IE + '\u0424' # 0xE6 -> CYRILLIC CAPITAL LETTER EF + '\u0413' # 0xE7 -> CYRILLIC CAPITAL LETTER GHE + '\u0425' # 0xE8 -> CYRILLIC CAPITAL LETTER HA + '\u0418' # 0xE9 -> CYRILLIC CAPITAL LETTER I + '\u0419' # 0xEA -> CYRILLIC CAPITAL LETTER SHORT I + '\u041a' # 0xEB -> CYRILLIC CAPITAL LETTER KA + '\u041b' # 0xEC -> CYRILLIC CAPITAL LETTER EL + '\u041c' # 0xED -> CYRILLIC CAPITAL LETTER EM + '\u041d' # 0xEE -> CYRILLIC CAPITAL LETTER EN + '\u041e' # 0xEF -> CYRILLIC CAPITAL LETTER O + '\u041f' # 0xF0 -> CYRILLIC CAPITAL LETTER PE + '\u042f' # 0xF1 -> CYRILLIC CAPITAL LETTER YA + '\u0420' # 0xF2 -> CYRILLIC CAPITAL LETTER ER + '\u0421' # 0xF3 -> CYRILLIC CAPITAL LETTER ES + '\u0422' # 0xF4 -> CYRILLIC CAPITAL LETTER TE + '\u0423' # 0xF5 -> CYRILLIC CAPITAL LETTER U + '\u0416' # 0xF6 -> CYRILLIC CAPITAL LETTER ZHE + '\u0412' # 0xF7 -> CYRILLIC CAPITAL LETTER VE + '\u042c' # 0xF8 -> CYRILLIC CAPITAL LETTER SOFT SIGN + '\u042b' # 0xF9 -> CYRILLIC CAPITAL LETTER YERU + '\u0417' # 0xFA -> CYRILLIC CAPITAL LETTER ZE + '\u0428' # 0xFB -> CYRILLIC CAPITAL LETTER SHA + '\u042d' # 0xFC -> CYRILLIC CAPITAL LETTER E + '\u0429' # 0xFD -> CYRILLIC CAPITAL LETTER SHCHA + '\u0427' # 0xFE -> CYRILLIC CAPITAL LETTER CHE + '\u042a' # 0xFF -> CYRILLIC CAPITAL LETTER HARD SIGN +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/koi8_t.py b/contrib/tools/python3/src/Lib/encodings/koi8_t.py new file mode 100644 index 0000000000..b5415ba366 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/koi8_t.py @@ -0,0 +1,308 @@ +""" Python Character Mapping Codec koi8_t +""" +# http://ru.wikipedia.org/wiki/КОИ-8 +# http://www.opensource.apple.com/source/libiconv/libiconv-4/libiconv/tests/KOI8-T.TXT + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='koi8-t', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\u049b' # 0x80 -> CYRILLIC SMALL LETTER KA WITH DESCENDER + '\u0493' # 0x81 -> CYRILLIC SMALL LETTER GHE WITH STROKE + '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK + '\u0492' # 0x83 -> CYRILLIC CAPITAL LETTER GHE WITH STROKE + '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK + '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS + '\u2020' # 0x86 -> DAGGER + '\u2021' # 0x87 -> DOUBLE DAGGER + '\ufffe' # 0x88 -> UNDEFINED + '\u2030' # 0x89 -> PER MILLE SIGN + '\u04b3' # 0x8A -> CYRILLIC SMALL LETTER HA WITH DESCENDER + '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + '\u04b2' # 0x8C -> CYRILLIC CAPITAL LETTER HA WITH DESCENDER + '\u04b7' # 0x8D -> CYRILLIC SMALL LETTER CHE WITH DESCENDER + '\u04b6' # 0x8E -> CYRILLIC CAPITAL LETTER CHE WITH DESCENDER + '\ufffe' # 0x8F -> UNDEFINED + '\u049a' # 0x90 -> CYRILLIC CAPITAL LETTER KA WITH DESCENDER + '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK + '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK + '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK + '\u2022' # 0x95 -> BULLET + '\u2013' # 0x96 -> EN DASH + '\u2014' # 0x97 -> EM DASH + '\ufffe' # 0x98 -> UNDEFINED + '\u2122' # 0x99 -> TRADE MARK SIGN + '\ufffe' # 0x9A -> UNDEFINED + '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + '\ufffe' # 0x9C -> UNDEFINED + '\ufffe' # 0x9D -> UNDEFINED + '\ufffe' # 0x9E -> UNDEFINED + '\ufffe' # 0x9F -> UNDEFINED + '\ufffe' # 0xA0 -> UNDEFINED + '\u04ef' # 0xA1 -> CYRILLIC SMALL LETTER U WITH MACRON + '\u04ee' # 0xA2 -> CYRILLIC CAPITAL LETTER U WITH MACRON + '\u0451' # 0xA3 -> CYRILLIC SMALL LETTER IO + '\xa4' # 0xA4 -> CURRENCY SIGN + '\u04e3' # 0xA5 -> CYRILLIC SMALL LETTER I WITH MACRON + '\xa6' # 0xA6 -> BROKEN BAR + '\xa7' # 0xA7 -> SECTION SIGN + '\ufffe' # 0xA8 -> UNDEFINED + '\ufffe' # 0xA9 -> UNDEFINED + '\ufffe' # 0xAA -> UNDEFINED + '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xac' # 0xAC -> NOT SIGN + '\xad' # 0xAD -> SOFT HYPHEN + '\xae' # 0xAE -> REGISTERED SIGN + '\ufffe' # 0xAF -> UNDEFINED + '\xb0' # 0xB0 -> DEGREE SIGN + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\xb2' # 0xB2 -> SUPERSCRIPT TWO + '\u0401' # 0xB3 -> CYRILLIC CAPITAL LETTER IO + '\ufffe' # 0xB4 -> UNDEFINED + '\u04e2' # 0xB5 -> CYRILLIC CAPITAL LETTER I WITH MACRON + '\xb6' # 0xB6 -> PILCROW SIGN + '\xb7' # 0xB7 -> MIDDLE DOT + '\ufffe' # 0xB8 -> UNDEFINED + '\u2116' # 0xB9 -> NUMERO SIGN + '\ufffe' # 0xBA -> UNDEFINED + '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\ufffe' # 0xBC -> UNDEFINED + '\ufffe' # 0xBD -> UNDEFINED + '\ufffe' # 0xBE -> UNDEFINED + '\xa9' # 0xBF -> COPYRIGHT SIGN + '\u044e' # 0xC0 -> CYRILLIC SMALL LETTER YU + '\u0430' # 0xC1 -> CYRILLIC SMALL LETTER A + '\u0431' # 0xC2 -> CYRILLIC SMALL LETTER BE + '\u0446' # 0xC3 -> CYRILLIC SMALL LETTER TSE + '\u0434' # 0xC4 -> CYRILLIC SMALL LETTER DE + '\u0435' # 0xC5 -> CYRILLIC SMALL LETTER IE + '\u0444' # 0xC6 -> CYRILLIC SMALL LETTER EF + '\u0433' # 0xC7 -> CYRILLIC SMALL LETTER GHE + '\u0445' # 0xC8 -> CYRILLIC SMALL LETTER HA + '\u0438' # 0xC9 -> CYRILLIC SMALL LETTER I + '\u0439' # 0xCA -> CYRILLIC SMALL LETTER SHORT I + '\u043a' # 0xCB -> CYRILLIC SMALL LETTER KA + '\u043b' # 0xCC -> CYRILLIC SMALL LETTER EL + '\u043c' # 0xCD -> CYRILLIC SMALL LETTER EM + '\u043d' # 0xCE -> CYRILLIC SMALL LETTER EN + '\u043e' # 0xCF -> CYRILLIC SMALL LETTER O + '\u043f' # 0xD0 -> CYRILLIC SMALL LETTER PE + '\u044f' # 0xD1 -> CYRILLIC SMALL LETTER YA + '\u0440' # 0xD2 -> CYRILLIC SMALL LETTER ER + '\u0441' # 0xD3 -> CYRILLIC SMALL LETTER ES + '\u0442' # 0xD4 -> CYRILLIC SMALL LETTER TE + '\u0443' # 0xD5 -> CYRILLIC SMALL LETTER U + '\u0436' # 0xD6 -> CYRILLIC SMALL LETTER ZHE + '\u0432' # 0xD7 -> CYRILLIC SMALL LETTER VE + '\u044c' # 0xD8 -> CYRILLIC SMALL LETTER SOFT SIGN + '\u044b' # 0xD9 -> CYRILLIC SMALL LETTER YERU + '\u0437' # 0xDA -> CYRILLIC SMALL LETTER ZE + '\u0448' # 0xDB -> CYRILLIC SMALL LETTER SHA + '\u044d' # 0xDC -> CYRILLIC SMALL LETTER E + '\u0449' # 0xDD -> CYRILLIC SMALL LETTER SHCHA + '\u0447' # 0xDE -> CYRILLIC SMALL LETTER CHE + '\u044a' # 0xDF -> CYRILLIC SMALL LETTER HARD SIGN + '\u042e' # 0xE0 -> CYRILLIC CAPITAL LETTER YU + '\u0410' # 0xE1 -> CYRILLIC CAPITAL LETTER A + '\u0411' # 0xE2 -> CYRILLIC CAPITAL LETTER BE + '\u0426' # 0xE3 -> CYRILLIC CAPITAL LETTER TSE + '\u0414' # 0xE4 -> CYRILLIC CAPITAL LETTER DE + '\u0415' # 0xE5 -> CYRILLIC CAPITAL LETTER IE + '\u0424' # 0xE6 -> CYRILLIC CAPITAL LETTER EF + '\u0413' # 0xE7 -> CYRILLIC CAPITAL LETTER GHE + '\u0425' # 0xE8 -> CYRILLIC CAPITAL LETTER HA + '\u0418' # 0xE9 -> CYRILLIC CAPITAL LETTER I + '\u0419' # 0xEA -> CYRILLIC CAPITAL LETTER SHORT I + '\u041a' # 0xEB -> CYRILLIC CAPITAL LETTER KA + '\u041b' # 0xEC -> CYRILLIC CAPITAL LETTER EL + '\u041c' # 0xED -> CYRILLIC CAPITAL LETTER EM + '\u041d' # 0xEE -> CYRILLIC CAPITAL LETTER EN + '\u041e' # 0xEF -> CYRILLIC CAPITAL LETTER O + '\u041f' # 0xF0 -> CYRILLIC CAPITAL LETTER PE + '\u042f' # 0xF1 -> CYRILLIC CAPITAL LETTER YA + '\u0420' # 0xF2 -> CYRILLIC CAPITAL LETTER ER + '\u0421' # 0xF3 -> CYRILLIC CAPITAL LETTER ES + '\u0422' # 0xF4 -> CYRILLIC CAPITAL LETTER TE + '\u0423' # 0xF5 -> CYRILLIC CAPITAL LETTER U + '\u0416' # 0xF6 -> CYRILLIC CAPITAL LETTER ZHE + '\u0412' # 0xF7 -> CYRILLIC CAPITAL LETTER VE + '\u042c' # 0xF8 -> CYRILLIC CAPITAL LETTER SOFT SIGN + '\u042b' # 0xF9 -> CYRILLIC CAPITAL LETTER YERU + '\u0417' # 0xFA -> CYRILLIC CAPITAL LETTER ZE + '\u0428' # 0xFB -> CYRILLIC CAPITAL LETTER SHA + '\u042d' # 0xFC -> CYRILLIC CAPITAL LETTER E + '\u0429' # 0xFD -> CYRILLIC CAPITAL LETTER SHCHA + '\u0427' # 0xFE -> CYRILLIC CAPITAL LETTER CHE + '\u042a' # 0xFF -> CYRILLIC CAPITAL LETTER HARD SIGN +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/koi8_u.py b/contrib/tools/python3/src/Lib/encodings/koi8_u.py new file mode 100644 index 0000000000..f9e3fae5fa --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/koi8_u.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec koi8_u generated from 'python-mappings/KOI8-U.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='koi8-u', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\u2500' # 0x80 -> BOX DRAWINGS LIGHT HORIZONTAL + '\u2502' # 0x81 -> BOX DRAWINGS LIGHT VERTICAL + '\u250c' # 0x82 -> BOX DRAWINGS LIGHT DOWN AND RIGHT + '\u2510' # 0x83 -> BOX DRAWINGS LIGHT DOWN AND LEFT + '\u2514' # 0x84 -> BOX DRAWINGS LIGHT UP AND RIGHT + '\u2518' # 0x85 -> BOX DRAWINGS LIGHT UP AND LEFT + '\u251c' # 0x86 -> BOX DRAWINGS LIGHT VERTICAL AND RIGHT + '\u2524' # 0x87 -> BOX DRAWINGS LIGHT VERTICAL AND LEFT + '\u252c' # 0x88 -> BOX DRAWINGS LIGHT DOWN AND HORIZONTAL + '\u2534' # 0x89 -> BOX DRAWINGS LIGHT UP AND HORIZONTAL + '\u253c' # 0x8A -> BOX DRAWINGS LIGHT VERTICAL AND HORIZONTAL + '\u2580' # 0x8B -> UPPER HALF BLOCK + '\u2584' # 0x8C -> LOWER HALF BLOCK + '\u2588' # 0x8D -> FULL BLOCK + '\u258c' # 0x8E -> LEFT HALF BLOCK + '\u2590' # 0x8F -> RIGHT HALF BLOCK + '\u2591' # 0x90 -> LIGHT SHADE + '\u2592' # 0x91 -> MEDIUM SHADE + '\u2593' # 0x92 -> DARK SHADE + '\u2320' # 0x93 -> TOP HALF INTEGRAL + '\u25a0' # 0x94 -> BLACK SQUARE + '\u2219' # 0x95 -> BULLET OPERATOR + '\u221a' # 0x96 -> SQUARE ROOT + '\u2248' # 0x97 -> ALMOST EQUAL TO + '\u2264' # 0x98 -> LESS-THAN OR EQUAL TO + '\u2265' # 0x99 -> GREATER-THAN OR EQUAL TO + '\xa0' # 0x9A -> NO-BREAK SPACE + '\u2321' # 0x9B -> BOTTOM HALF INTEGRAL + '\xb0' # 0x9C -> DEGREE SIGN + '\xb2' # 0x9D -> SUPERSCRIPT TWO + '\xb7' # 0x9E -> MIDDLE DOT + '\xf7' # 0x9F -> DIVISION SIGN + '\u2550' # 0xA0 -> BOX DRAWINGS DOUBLE HORIZONTAL + '\u2551' # 0xA1 -> BOX DRAWINGS DOUBLE VERTICAL + '\u2552' # 0xA2 -> BOX DRAWINGS DOWN SINGLE AND RIGHT DOUBLE + '\u0451' # 0xA3 -> CYRILLIC SMALL LETTER IO + '\u0454' # 0xA4 -> CYRILLIC SMALL LETTER UKRAINIAN IE + '\u2554' # 0xA5 -> BOX DRAWINGS DOUBLE DOWN AND RIGHT + '\u0456' # 0xA6 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + '\u0457' # 0xA7 -> CYRILLIC SMALL LETTER YI (UKRAINIAN) + '\u2557' # 0xA8 -> BOX DRAWINGS DOUBLE DOWN AND LEFT + '\u2558' # 0xA9 -> BOX DRAWINGS UP SINGLE AND RIGHT DOUBLE + '\u2559' # 0xAA -> BOX DRAWINGS UP DOUBLE AND RIGHT SINGLE + '\u255a' # 0xAB -> BOX DRAWINGS DOUBLE UP AND RIGHT + '\u255b' # 0xAC -> BOX DRAWINGS UP SINGLE AND LEFT DOUBLE + '\u0491' # 0xAD -> CYRILLIC SMALL LETTER UKRAINIAN GHE WITH UPTURN + '\u255d' # 0xAE -> BOX DRAWINGS DOUBLE UP AND LEFT + '\u255e' # 0xAF -> BOX DRAWINGS VERTICAL SINGLE AND RIGHT DOUBLE + '\u255f' # 0xB0 -> BOX DRAWINGS VERTICAL DOUBLE AND RIGHT SINGLE + '\u2560' # 0xB1 -> BOX DRAWINGS DOUBLE VERTICAL AND RIGHT + '\u2561' # 0xB2 -> BOX DRAWINGS VERTICAL SINGLE AND LEFT DOUBLE + '\u0401' # 0xB3 -> CYRILLIC CAPITAL LETTER IO + '\u0404' # 0xB4 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE + '\u2563' # 0xB5 -> BOX DRAWINGS DOUBLE VERTICAL AND LEFT + '\u0406' # 0xB6 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + '\u0407' # 0xB7 -> CYRILLIC CAPITAL LETTER YI (UKRAINIAN) + '\u2566' # 0xB8 -> BOX DRAWINGS DOUBLE DOWN AND HORIZONTAL + '\u2567' # 0xB9 -> BOX DRAWINGS UP SINGLE AND HORIZONTAL DOUBLE + '\u2568' # 0xBA -> BOX DRAWINGS UP DOUBLE AND HORIZONTAL SINGLE + '\u2569' # 0xBB -> BOX DRAWINGS DOUBLE UP AND HORIZONTAL + '\u256a' # 0xBC -> BOX DRAWINGS VERTICAL SINGLE AND HORIZONTAL DOUBLE + '\u0490' # 0xBD -> CYRILLIC CAPITAL LETTER UKRAINIAN GHE WITH UPTURN + '\u256c' # 0xBE -> BOX DRAWINGS DOUBLE VERTICAL AND HORIZONTAL + '\xa9' # 0xBF -> COPYRIGHT SIGN + '\u044e' # 0xC0 -> CYRILLIC SMALL LETTER YU + '\u0430' # 0xC1 -> CYRILLIC SMALL LETTER A + '\u0431' # 0xC2 -> CYRILLIC SMALL LETTER BE + '\u0446' # 0xC3 -> CYRILLIC SMALL LETTER TSE + '\u0434' # 0xC4 -> CYRILLIC SMALL LETTER DE + '\u0435' # 0xC5 -> CYRILLIC SMALL LETTER IE + '\u0444' # 0xC6 -> CYRILLIC SMALL LETTER EF + '\u0433' # 0xC7 -> CYRILLIC SMALL LETTER GHE + '\u0445' # 0xC8 -> CYRILLIC SMALL LETTER HA + '\u0438' # 0xC9 -> CYRILLIC SMALL LETTER I + '\u0439' # 0xCA -> CYRILLIC SMALL LETTER SHORT I + '\u043a' # 0xCB -> CYRILLIC SMALL LETTER KA + '\u043b' # 0xCC -> CYRILLIC SMALL LETTER EL + '\u043c' # 0xCD -> CYRILLIC SMALL LETTER EM + '\u043d' # 0xCE -> CYRILLIC SMALL LETTER EN + '\u043e' # 0xCF -> CYRILLIC SMALL LETTER O + '\u043f' # 0xD0 -> CYRILLIC SMALL LETTER PE + '\u044f' # 0xD1 -> CYRILLIC SMALL LETTER YA + '\u0440' # 0xD2 -> CYRILLIC SMALL LETTER ER + '\u0441' # 0xD3 -> CYRILLIC SMALL LETTER ES + '\u0442' # 0xD4 -> CYRILLIC SMALL LETTER TE + '\u0443' # 0xD5 -> CYRILLIC SMALL LETTER U + '\u0436' # 0xD6 -> CYRILLIC SMALL LETTER ZHE + '\u0432' # 0xD7 -> CYRILLIC SMALL LETTER VE + '\u044c' # 0xD8 -> CYRILLIC SMALL LETTER SOFT SIGN + '\u044b' # 0xD9 -> CYRILLIC SMALL LETTER YERU + '\u0437' # 0xDA -> CYRILLIC SMALL LETTER ZE + '\u0448' # 0xDB -> CYRILLIC SMALL LETTER SHA + '\u044d' # 0xDC -> CYRILLIC SMALL LETTER E + '\u0449' # 0xDD -> CYRILLIC SMALL LETTER SHCHA + '\u0447' # 0xDE -> CYRILLIC SMALL LETTER CHE + '\u044a' # 0xDF -> CYRILLIC SMALL LETTER HARD SIGN + '\u042e' # 0xE0 -> CYRILLIC CAPITAL LETTER YU + '\u0410' # 0xE1 -> CYRILLIC CAPITAL LETTER A + '\u0411' # 0xE2 -> CYRILLIC CAPITAL LETTER BE + '\u0426' # 0xE3 -> CYRILLIC CAPITAL LETTER TSE + '\u0414' # 0xE4 -> CYRILLIC CAPITAL LETTER DE + '\u0415' # 0xE5 -> CYRILLIC CAPITAL LETTER IE + '\u0424' # 0xE6 -> CYRILLIC CAPITAL LETTER EF + '\u0413' # 0xE7 -> CYRILLIC CAPITAL LETTER GHE + '\u0425' # 0xE8 -> CYRILLIC CAPITAL LETTER HA + '\u0418' # 0xE9 -> CYRILLIC CAPITAL LETTER I + '\u0419' # 0xEA -> CYRILLIC CAPITAL LETTER SHORT I + '\u041a' # 0xEB -> CYRILLIC CAPITAL LETTER KA + '\u041b' # 0xEC -> CYRILLIC CAPITAL LETTER EL + '\u041c' # 0xED -> CYRILLIC CAPITAL LETTER EM + '\u041d' # 0xEE -> CYRILLIC CAPITAL LETTER EN + '\u041e' # 0xEF -> CYRILLIC CAPITAL LETTER O + '\u041f' # 0xF0 -> CYRILLIC CAPITAL LETTER PE + '\u042f' # 0xF1 -> CYRILLIC CAPITAL LETTER YA + '\u0420' # 0xF2 -> CYRILLIC CAPITAL LETTER ER + '\u0421' # 0xF3 -> CYRILLIC CAPITAL LETTER ES + '\u0422' # 0xF4 -> CYRILLIC CAPITAL LETTER TE + '\u0423' # 0xF5 -> CYRILLIC CAPITAL LETTER U + '\u0416' # 0xF6 -> CYRILLIC CAPITAL LETTER ZHE + '\u0412' # 0xF7 -> CYRILLIC CAPITAL LETTER VE + '\u042c' # 0xF8 -> CYRILLIC CAPITAL LETTER SOFT SIGN + '\u042b' # 0xF9 -> CYRILLIC CAPITAL LETTER YERU + '\u0417' # 0xFA -> CYRILLIC CAPITAL LETTER ZE + '\u0428' # 0xFB -> CYRILLIC CAPITAL LETTER SHA + '\u042d' # 0xFC -> CYRILLIC CAPITAL LETTER E + '\u0429' # 0xFD -> CYRILLIC CAPITAL LETTER SHCHA + '\u0427' # 0xFE -> CYRILLIC CAPITAL LETTER CHE + '\u042a' # 0xFF -> CYRILLIC CAPITAL LETTER HARD SIGN +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/kz1048.py b/contrib/tools/python3/src/Lib/encodings/kz1048.py new file mode 100644 index 0000000000..712aee6e93 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/kz1048.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec kz1048 generated from 'MAPPINGS/VENDORS/MISC/KZ1048.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self, input, errors='strict'): + return codecs.charmap_encode(input, errors, encoding_table) + + def decode(self, input, errors='strict'): + return codecs.charmap_decode(input, errors, decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input, self.errors, encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input, self.errors, decoding_table)[0] + +class StreamWriter(Codec, codecs.StreamWriter): + pass + +class StreamReader(Codec, codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='kz1048', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\u0402' # 0x80 -> CYRILLIC CAPITAL LETTER DJE + '\u0403' # 0x81 -> CYRILLIC CAPITAL LETTER GJE + '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK + '\u0453' # 0x83 -> CYRILLIC SMALL LETTER GJE + '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK + '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS + '\u2020' # 0x86 -> DAGGER + '\u2021' # 0x87 -> DOUBLE DAGGER + '\u20ac' # 0x88 -> EURO SIGN + '\u2030' # 0x89 -> PER MILLE SIGN + '\u0409' # 0x8A -> CYRILLIC CAPITAL LETTER LJE + '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + '\u040a' # 0x8C -> CYRILLIC CAPITAL LETTER NJE + '\u049a' # 0x8D -> CYRILLIC CAPITAL LETTER KA WITH DESCENDER + '\u04ba' # 0x8E -> CYRILLIC CAPITAL LETTER SHHA + '\u040f' # 0x8F -> CYRILLIC CAPITAL LETTER DZHE + '\u0452' # 0x90 -> CYRILLIC SMALL LETTER DJE + '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK + '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK + '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK + '\u2022' # 0x95 -> BULLET + '\u2013' # 0x96 -> EN DASH + '\u2014' # 0x97 -> EM DASH + '\ufffe' # 0x98 -> UNDEFINED + '\u2122' # 0x99 -> TRADE MARK SIGN + '\u0459' # 0x9A -> CYRILLIC SMALL LETTER LJE + '\u203a' # 0x9B -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + '\u045a' # 0x9C -> CYRILLIC SMALL LETTER NJE + '\u049b' # 0x9D -> CYRILLIC SMALL LETTER KA WITH DESCENDER + '\u04bb' # 0x9E -> CYRILLIC SMALL LETTER SHHA + '\u045f' # 0x9F -> CYRILLIC SMALL LETTER DZHE + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\u04b0' # 0xA1 -> CYRILLIC CAPITAL LETTER STRAIGHT U WITH STROKE + '\u04b1' # 0xA2 -> CYRILLIC SMALL LETTER STRAIGHT U WITH STROKE + '\u04d8' # 0xA3 -> CYRILLIC CAPITAL LETTER SCHWA + '\xa4' # 0xA4 -> CURRENCY SIGN + '\u04e8' # 0xA5 -> CYRILLIC CAPITAL LETTER BARRED O + '\xa6' # 0xA6 -> BROKEN BAR + '\xa7' # 0xA7 -> SECTION SIGN + '\u0401' # 0xA8 -> CYRILLIC CAPITAL LETTER IO + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\u0492' # 0xAA -> CYRILLIC CAPITAL LETTER GHE WITH STROKE + '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xac' # 0xAC -> NOT SIGN + '\xad' # 0xAD -> SOFT HYPHEN + '\xae' # 0xAE -> REGISTERED SIGN + '\u04ae' # 0xAF -> CYRILLIC CAPITAL LETTER STRAIGHT U + '\xb0' # 0xB0 -> DEGREE SIGN + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\u0406' # 0xB2 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + '\u0456' # 0xB3 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + '\u04e9' # 0xB4 -> CYRILLIC SMALL LETTER BARRED O + '\xb5' # 0xB5 -> MICRO SIGN + '\xb6' # 0xB6 -> PILCROW SIGN + '\xb7' # 0xB7 -> MIDDLE DOT + '\u0451' # 0xB8 -> CYRILLIC SMALL LETTER IO + '\u2116' # 0xB9 -> NUMERO SIGN + '\u0493' # 0xBA -> CYRILLIC SMALL LETTER GHE WITH STROKE + '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u04d9' # 0xBC -> CYRILLIC SMALL LETTER SCHWA + '\u04a2' # 0xBD -> CYRILLIC CAPITAL LETTER EN WITH DESCENDER + '\u04a3' # 0xBE -> CYRILLIC SMALL LETTER EN WITH DESCENDER + '\u04af' # 0xBF -> CYRILLIC SMALL LETTER STRAIGHT U + '\u0410' # 0xC0 -> CYRILLIC CAPITAL LETTER A + '\u0411' # 0xC1 -> CYRILLIC CAPITAL LETTER BE + '\u0412' # 0xC2 -> CYRILLIC CAPITAL LETTER VE + '\u0413' # 0xC3 -> CYRILLIC CAPITAL LETTER GHE + '\u0414' # 0xC4 -> CYRILLIC CAPITAL LETTER DE + '\u0415' # 0xC5 -> CYRILLIC CAPITAL LETTER IE + '\u0416' # 0xC6 -> CYRILLIC CAPITAL LETTER ZHE + '\u0417' # 0xC7 -> CYRILLIC CAPITAL LETTER ZE + '\u0418' # 0xC8 -> CYRILLIC CAPITAL LETTER I + '\u0419' # 0xC9 -> CYRILLIC CAPITAL LETTER SHORT I + '\u041a' # 0xCA -> CYRILLIC CAPITAL LETTER KA + '\u041b' # 0xCB -> CYRILLIC CAPITAL LETTER EL + '\u041c' # 0xCC -> CYRILLIC CAPITAL LETTER EM + '\u041d' # 0xCD -> CYRILLIC CAPITAL LETTER EN + '\u041e' # 0xCE -> CYRILLIC CAPITAL LETTER O + '\u041f' # 0xCF -> CYRILLIC CAPITAL LETTER PE + '\u0420' # 0xD0 -> CYRILLIC CAPITAL LETTER ER + '\u0421' # 0xD1 -> CYRILLIC CAPITAL LETTER ES + '\u0422' # 0xD2 -> CYRILLIC CAPITAL LETTER TE + '\u0423' # 0xD3 -> CYRILLIC CAPITAL LETTER U + '\u0424' # 0xD4 -> CYRILLIC CAPITAL LETTER EF + '\u0425' # 0xD5 -> CYRILLIC CAPITAL LETTER HA + '\u0426' # 0xD6 -> CYRILLIC CAPITAL LETTER TSE + '\u0427' # 0xD7 -> CYRILLIC CAPITAL LETTER CHE + '\u0428' # 0xD8 -> CYRILLIC CAPITAL LETTER SHA + '\u0429' # 0xD9 -> CYRILLIC CAPITAL LETTER SHCHA + '\u042a' # 0xDA -> CYRILLIC CAPITAL LETTER HARD SIGN + '\u042b' # 0xDB -> CYRILLIC CAPITAL LETTER YERU + '\u042c' # 0xDC -> CYRILLIC CAPITAL LETTER SOFT SIGN + '\u042d' # 0xDD -> CYRILLIC CAPITAL LETTER E + '\u042e' # 0xDE -> CYRILLIC CAPITAL LETTER YU + '\u042f' # 0xDF -> CYRILLIC CAPITAL LETTER YA + '\u0430' # 0xE0 -> CYRILLIC SMALL LETTER A + '\u0431' # 0xE1 -> CYRILLIC SMALL LETTER BE + '\u0432' # 0xE2 -> CYRILLIC SMALL LETTER VE + '\u0433' # 0xE3 -> CYRILLIC SMALL LETTER GHE + '\u0434' # 0xE4 -> CYRILLIC SMALL LETTER DE + '\u0435' # 0xE5 -> CYRILLIC SMALL LETTER IE + '\u0436' # 0xE6 -> CYRILLIC SMALL LETTER ZHE + '\u0437' # 0xE7 -> CYRILLIC SMALL LETTER ZE + '\u0438' # 0xE8 -> CYRILLIC SMALL LETTER I + '\u0439' # 0xE9 -> CYRILLIC SMALL LETTER SHORT I + '\u043a' # 0xEA -> CYRILLIC SMALL LETTER KA + '\u043b' # 0xEB -> CYRILLIC SMALL LETTER EL + '\u043c' # 0xEC -> CYRILLIC SMALL LETTER EM + '\u043d' # 0xED -> CYRILLIC SMALL LETTER EN + '\u043e' # 0xEE -> CYRILLIC SMALL LETTER O + '\u043f' # 0xEF -> CYRILLIC SMALL LETTER PE + '\u0440' # 0xF0 -> CYRILLIC SMALL LETTER ER + '\u0441' # 0xF1 -> CYRILLIC SMALL LETTER ES + '\u0442' # 0xF2 -> CYRILLIC SMALL LETTER TE + '\u0443' # 0xF3 -> CYRILLIC SMALL LETTER U + '\u0444' # 0xF4 -> CYRILLIC SMALL LETTER EF + '\u0445' # 0xF5 -> CYRILLIC SMALL LETTER HA + '\u0446' # 0xF6 -> CYRILLIC SMALL LETTER TSE + '\u0447' # 0xF7 -> CYRILLIC SMALL LETTER CHE + '\u0448' # 0xF8 -> CYRILLIC SMALL LETTER SHA + '\u0449' # 0xF9 -> CYRILLIC SMALL LETTER SHCHA + '\u044a' # 0xFA -> CYRILLIC SMALL LETTER HARD SIGN + '\u044b' # 0xFB -> CYRILLIC SMALL LETTER YERU + '\u044c' # 0xFC -> CYRILLIC SMALL LETTER SOFT SIGN + '\u044d' # 0xFD -> CYRILLIC SMALL LETTER E + '\u044e' # 0xFE -> CYRILLIC SMALL LETTER YU + '\u044f' # 0xFF -> CYRILLIC SMALL LETTER YA +) + +### Encoding table +encoding_table = codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/latin_1.py b/contrib/tools/python3/src/Lib/encodings/latin_1.py new file mode 100644 index 0000000000..370160c0cb --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/latin_1.py @@ -0,0 +1,50 @@ +""" Python 'latin-1' Codec + + +Written by Marc-Andre Lemburg (mal@lemburg.com). + +(c) Copyright CNRI, All Rights Reserved. NO WARRANTY. + +""" +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + # Note: Binding these as C functions will result in the class not + # converting them to methods. This is intended. + encode = codecs.latin_1_encode + decode = codecs.latin_1_decode + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.latin_1_encode(input,self.errors)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.latin_1_decode(input,self.errors)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +class StreamConverter(StreamWriter,StreamReader): + + encode = codecs.latin_1_decode + decode = codecs.latin_1_encode + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='iso8859-1', + encode=Codec.encode, + decode=Codec.decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/mac_arabic.py b/contrib/tools/python3/src/Lib/encodings/mac_arabic.py new file mode 100644 index 0000000000..72847e859c --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/mac_arabic.py @@ -0,0 +1,698 @@ +""" Python Character Mapping Codec generated from 'VENDORS/APPLE/ARABIC.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_map) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_map)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='mac-arabic', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + +### Decoding Map + +decoding_map = codecs.make_identity_dict(range(256)) +decoding_map.update({ + 0x0080: 0x00c4, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x0081: 0x00a0, # NO-BREAK SPACE, right-left + 0x0082: 0x00c7, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x0083: 0x00c9, # LATIN CAPITAL LETTER E WITH ACUTE + 0x0084: 0x00d1, # LATIN CAPITAL LETTER N WITH TILDE + 0x0085: 0x00d6, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x0086: 0x00dc, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x0087: 0x00e1, # LATIN SMALL LETTER A WITH ACUTE + 0x0088: 0x00e0, # LATIN SMALL LETTER A WITH GRAVE + 0x0089: 0x00e2, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x008a: 0x00e4, # LATIN SMALL LETTER A WITH DIAERESIS + 0x008b: 0x06ba, # ARABIC LETTER NOON GHUNNA + 0x008c: 0x00ab, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left + 0x008d: 0x00e7, # LATIN SMALL LETTER C WITH CEDILLA + 0x008e: 0x00e9, # LATIN SMALL LETTER E WITH ACUTE + 0x008f: 0x00e8, # LATIN SMALL LETTER E WITH GRAVE + 0x0090: 0x00ea, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x0091: 0x00eb, # LATIN SMALL LETTER E WITH DIAERESIS + 0x0092: 0x00ed, # LATIN SMALL LETTER I WITH ACUTE + 0x0093: 0x2026, # HORIZONTAL ELLIPSIS, right-left + 0x0094: 0x00ee, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x0095: 0x00ef, # LATIN SMALL LETTER I WITH DIAERESIS + 0x0096: 0x00f1, # LATIN SMALL LETTER N WITH TILDE + 0x0097: 0x00f3, # LATIN SMALL LETTER O WITH ACUTE + 0x0098: 0x00bb, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left + 0x0099: 0x00f4, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x009a: 0x00f6, # LATIN SMALL LETTER O WITH DIAERESIS + 0x009b: 0x00f7, # DIVISION SIGN, right-left + 0x009c: 0x00fa, # LATIN SMALL LETTER U WITH ACUTE + 0x009d: 0x00f9, # LATIN SMALL LETTER U WITH GRAVE + 0x009e: 0x00fb, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x009f: 0x00fc, # LATIN SMALL LETTER U WITH DIAERESIS + 0x00a0: 0x0020, # SPACE, right-left + 0x00a1: 0x0021, # EXCLAMATION MARK, right-left + 0x00a2: 0x0022, # QUOTATION MARK, right-left + 0x00a3: 0x0023, # NUMBER SIGN, right-left + 0x00a4: 0x0024, # DOLLAR SIGN, right-left + 0x00a5: 0x066a, # ARABIC PERCENT SIGN + 0x00a6: 0x0026, # AMPERSAND, right-left + 0x00a7: 0x0027, # APOSTROPHE, right-left + 0x00a8: 0x0028, # LEFT PARENTHESIS, right-left + 0x00a9: 0x0029, # RIGHT PARENTHESIS, right-left + 0x00aa: 0x002a, # ASTERISK, right-left + 0x00ab: 0x002b, # PLUS SIGN, right-left + 0x00ac: 0x060c, # ARABIC COMMA + 0x00ad: 0x002d, # HYPHEN-MINUS, right-left + 0x00ae: 0x002e, # FULL STOP, right-left + 0x00af: 0x002f, # SOLIDUS, right-left + 0x00b0: 0x0660, # ARABIC-INDIC DIGIT ZERO, right-left (need override) + 0x00b1: 0x0661, # ARABIC-INDIC DIGIT ONE, right-left (need override) + 0x00b2: 0x0662, # ARABIC-INDIC DIGIT TWO, right-left (need override) + 0x00b3: 0x0663, # ARABIC-INDIC DIGIT THREE, right-left (need override) + 0x00b4: 0x0664, # ARABIC-INDIC DIGIT FOUR, right-left (need override) + 0x00b5: 0x0665, # ARABIC-INDIC DIGIT FIVE, right-left (need override) + 0x00b6: 0x0666, # ARABIC-INDIC DIGIT SIX, right-left (need override) + 0x00b7: 0x0667, # ARABIC-INDIC DIGIT SEVEN, right-left (need override) + 0x00b8: 0x0668, # ARABIC-INDIC DIGIT EIGHT, right-left (need override) + 0x00b9: 0x0669, # ARABIC-INDIC DIGIT NINE, right-left (need override) + 0x00ba: 0x003a, # COLON, right-left + 0x00bb: 0x061b, # ARABIC SEMICOLON + 0x00bc: 0x003c, # LESS-THAN SIGN, right-left + 0x00bd: 0x003d, # EQUALS SIGN, right-left + 0x00be: 0x003e, # GREATER-THAN SIGN, right-left + 0x00bf: 0x061f, # ARABIC QUESTION MARK + 0x00c0: 0x274a, # EIGHT TEARDROP-SPOKED PROPELLER ASTERISK, right-left + 0x00c1: 0x0621, # ARABIC LETTER HAMZA + 0x00c2: 0x0622, # ARABIC LETTER ALEF WITH MADDA ABOVE + 0x00c3: 0x0623, # ARABIC LETTER ALEF WITH HAMZA ABOVE + 0x00c4: 0x0624, # ARABIC LETTER WAW WITH HAMZA ABOVE + 0x00c5: 0x0625, # ARABIC LETTER ALEF WITH HAMZA BELOW + 0x00c6: 0x0626, # ARABIC LETTER YEH WITH HAMZA ABOVE + 0x00c7: 0x0627, # ARABIC LETTER ALEF + 0x00c8: 0x0628, # ARABIC LETTER BEH + 0x00c9: 0x0629, # ARABIC LETTER TEH MARBUTA + 0x00ca: 0x062a, # ARABIC LETTER TEH + 0x00cb: 0x062b, # ARABIC LETTER THEH + 0x00cc: 0x062c, # ARABIC LETTER JEEM + 0x00cd: 0x062d, # ARABIC LETTER HAH + 0x00ce: 0x062e, # ARABIC LETTER KHAH + 0x00cf: 0x062f, # ARABIC LETTER DAL + 0x00d0: 0x0630, # ARABIC LETTER THAL + 0x00d1: 0x0631, # ARABIC LETTER REH + 0x00d2: 0x0632, # ARABIC LETTER ZAIN + 0x00d3: 0x0633, # ARABIC LETTER SEEN + 0x00d4: 0x0634, # ARABIC LETTER SHEEN + 0x00d5: 0x0635, # ARABIC LETTER SAD + 0x00d6: 0x0636, # ARABIC LETTER DAD + 0x00d7: 0x0637, # ARABIC LETTER TAH + 0x00d8: 0x0638, # ARABIC LETTER ZAH + 0x00d9: 0x0639, # ARABIC LETTER AIN + 0x00da: 0x063a, # ARABIC LETTER GHAIN + 0x00db: 0x005b, # LEFT SQUARE BRACKET, right-left + 0x00dc: 0x005c, # REVERSE SOLIDUS, right-left + 0x00dd: 0x005d, # RIGHT SQUARE BRACKET, right-left + 0x00de: 0x005e, # CIRCUMFLEX ACCENT, right-left + 0x00df: 0x005f, # LOW LINE, right-left + 0x00e0: 0x0640, # ARABIC TATWEEL + 0x00e1: 0x0641, # ARABIC LETTER FEH + 0x00e2: 0x0642, # ARABIC LETTER QAF + 0x00e3: 0x0643, # ARABIC LETTER KAF + 0x00e4: 0x0644, # ARABIC LETTER LAM + 0x00e5: 0x0645, # ARABIC LETTER MEEM + 0x00e6: 0x0646, # ARABIC LETTER NOON + 0x00e7: 0x0647, # ARABIC LETTER HEH + 0x00e8: 0x0648, # ARABIC LETTER WAW + 0x00e9: 0x0649, # ARABIC LETTER ALEF MAKSURA + 0x00ea: 0x064a, # ARABIC LETTER YEH + 0x00eb: 0x064b, # ARABIC FATHATAN + 0x00ec: 0x064c, # ARABIC DAMMATAN + 0x00ed: 0x064d, # ARABIC KASRATAN + 0x00ee: 0x064e, # ARABIC FATHA + 0x00ef: 0x064f, # ARABIC DAMMA + 0x00f0: 0x0650, # ARABIC KASRA + 0x00f1: 0x0651, # ARABIC SHADDA + 0x00f2: 0x0652, # ARABIC SUKUN + 0x00f3: 0x067e, # ARABIC LETTER PEH + 0x00f4: 0x0679, # ARABIC LETTER TTEH + 0x00f5: 0x0686, # ARABIC LETTER TCHEH + 0x00f6: 0x06d5, # ARABIC LETTER AE + 0x00f7: 0x06a4, # ARABIC LETTER VEH + 0x00f8: 0x06af, # ARABIC LETTER GAF + 0x00f9: 0x0688, # ARABIC LETTER DDAL + 0x00fa: 0x0691, # ARABIC LETTER RREH + 0x00fb: 0x007b, # LEFT CURLY BRACKET, right-left + 0x00fc: 0x007c, # VERTICAL LINE, right-left + 0x00fd: 0x007d, # RIGHT CURLY BRACKET, right-left + 0x00fe: 0x0698, # ARABIC LETTER JEH + 0x00ff: 0x06d2, # ARABIC LETTER YEH BARREE +}) + +### Decoding Table + +decoding_table = ( + '\x00' # 0x0000 -> CONTROL CHARACTER + '\x01' # 0x0001 -> CONTROL CHARACTER + '\x02' # 0x0002 -> CONTROL CHARACTER + '\x03' # 0x0003 -> CONTROL CHARACTER + '\x04' # 0x0004 -> CONTROL CHARACTER + '\x05' # 0x0005 -> CONTROL CHARACTER + '\x06' # 0x0006 -> CONTROL CHARACTER + '\x07' # 0x0007 -> CONTROL CHARACTER + '\x08' # 0x0008 -> CONTROL CHARACTER + '\t' # 0x0009 -> CONTROL CHARACTER + '\n' # 0x000a -> CONTROL CHARACTER + '\x0b' # 0x000b -> CONTROL CHARACTER + '\x0c' # 0x000c -> CONTROL CHARACTER + '\r' # 0x000d -> CONTROL CHARACTER + '\x0e' # 0x000e -> CONTROL CHARACTER + '\x0f' # 0x000f -> CONTROL CHARACTER + '\x10' # 0x0010 -> CONTROL CHARACTER + '\x11' # 0x0011 -> CONTROL CHARACTER + '\x12' # 0x0012 -> CONTROL CHARACTER + '\x13' # 0x0013 -> CONTROL CHARACTER + '\x14' # 0x0014 -> CONTROL CHARACTER + '\x15' # 0x0015 -> CONTROL CHARACTER + '\x16' # 0x0016 -> CONTROL CHARACTER + '\x17' # 0x0017 -> CONTROL CHARACTER + '\x18' # 0x0018 -> CONTROL CHARACTER + '\x19' # 0x0019 -> CONTROL CHARACTER + '\x1a' # 0x001a -> CONTROL CHARACTER + '\x1b' # 0x001b -> CONTROL CHARACTER + '\x1c' # 0x001c -> CONTROL CHARACTER + '\x1d' # 0x001d -> CONTROL CHARACTER + '\x1e' # 0x001e -> CONTROL CHARACTER + '\x1f' # 0x001f -> CONTROL CHARACTER + ' ' # 0x0020 -> SPACE, left-right + '!' # 0x0021 -> EXCLAMATION MARK, left-right + '"' # 0x0022 -> QUOTATION MARK, left-right + '#' # 0x0023 -> NUMBER SIGN, left-right + '$' # 0x0024 -> DOLLAR SIGN, left-right + '%' # 0x0025 -> PERCENT SIGN, left-right + '&' # 0x0026 -> AMPERSAND, left-right + "'" # 0x0027 -> APOSTROPHE, left-right + '(' # 0x0028 -> LEFT PARENTHESIS, left-right + ')' # 0x0029 -> RIGHT PARENTHESIS, left-right + '*' # 0x002a -> ASTERISK, left-right + '+' # 0x002b -> PLUS SIGN, left-right + ',' # 0x002c -> COMMA, left-right; in Arabic-script context, displayed as 0x066C ARABIC THOUSANDS SEPARATOR + '-' # 0x002d -> HYPHEN-MINUS, left-right + '.' # 0x002e -> FULL STOP, left-right; in Arabic-script context, displayed as 0x066B ARABIC DECIMAL SEPARATOR + '/' # 0x002f -> SOLIDUS, left-right + '0' # 0x0030 -> DIGIT ZERO; in Arabic-script context, displayed as 0x0660 ARABIC-INDIC DIGIT ZERO + '1' # 0x0031 -> DIGIT ONE; in Arabic-script context, displayed as 0x0661 ARABIC-INDIC DIGIT ONE + '2' # 0x0032 -> DIGIT TWO; in Arabic-script context, displayed as 0x0662 ARABIC-INDIC DIGIT TWO + '3' # 0x0033 -> DIGIT THREE; in Arabic-script context, displayed as 0x0663 ARABIC-INDIC DIGIT THREE + '4' # 0x0034 -> DIGIT FOUR; in Arabic-script context, displayed as 0x0664 ARABIC-INDIC DIGIT FOUR + '5' # 0x0035 -> DIGIT FIVE; in Arabic-script context, displayed as 0x0665 ARABIC-INDIC DIGIT FIVE + '6' # 0x0036 -> DIGIT SIX; in Arabic-script context, displayed as 0x0666 ARABIC-INDIC DIGIT SIX + '7' # 0x0037 -> DIGIT SEVEN; in Arabic-script context, displayed as 0x0667 ARABIC-INDIC DIGIT SEVEN + '8' # 0x0038 -> DIGIT EIGHT; in Arabic-script context, displayed as 0x0668 ARABIC-INDIC DIGIT EIGHT + '9' # 0x0039 -> DIGIT NINE; in Arabic-script context, displayed as 0x0669 ARABIC-INDIC DIGIT NINE + ':' # 0x003a -> COLON, left-right + ';' # 0x003b -> SEMICOLON, left-right + '<' # 0x003c -> LESS-THAN SIGN, left-right + '=' # 0x003d -> EQUALS SIGN, left-right + '>' # 0x003e -> GREATER-THAN SIGN, left-right + '?' # 0x003f -> QUESTION MARK, left-right + '@' # 0x0040 -> COMMERCIAL AT + 'A' # 0x0041 -> LATIN CAPITAL LETTER A + 'B' # 0x0042 -> LATIN CAPITAL LETTER B + 'C' # 0x0043 -> LATIN CAPITAL LETTER C + 'D' # 0x0044 -> LATIN CAPITAL LETTER D + 'E' # 0x0045 -> LATIN CAPITAL LETTER E + 'F' # 0x0046 -> LATIN CAPITAL LETTER F + 'G' # 0x0047 -> LATIN CAPITAL LETTER G + 'H' # 0x0048 -> LATIN CAPITAL LETTER H + 'I' # 0x0049 -> LATIN CAPITAL LETTER I + 'J' # 0x004a -> LATIN CAPITAL LETTER J + 'K' # 0x004b -> LATIN CAPITAL LETTER K + 'L' # 0x004c -> LATIN CAPITAL LETTER L + 'M' # 0x004d -> LATIN CAPITAL LETTER M + 'N' # 0x004e -> LATIN CAPITAL LETTER N + 'O' # 0x004f -> LATIN CAPITAL LETTER O + 'P' # 0x0050 -> LATIN CAPITAL LETTER P + 'Q' # 0x0051 -> LATIN CAPITAL LETTER Q + 'R' # 0x0052 -> LATIN CAPITAL LETTER R + 'S' # 0x0053 -> LATIN CAPITAL LETTER S + 'T' # 0x0054 -> LATIN CAPITAL LETTER T + 'U' # 0x0055 -> LATIN CAPITAL LETTER U + 'V' # 0x0056 -> LATIN CAPITAL LETTER V + 'W' # 0x0057 -> LATIN CAPITAL LETTER W + 'X' # 0x0058 -> LATIN CAPITAL LETTER X + 'Y' # 0x0059 -> LATIN CAPITAL LETTER Y + 'Z' # 0x005a -> LATIN CAPITAL LETTER Z + '[' # 0x005b -> LEFT SQUARE BRACKET, left-right + '\\' # 0x005c -> REVERSE SOLIDUS, left-right + ']' # 0x005d -> RIGHT SQUARE BRACKET, left-right + '^' # 0x005e -> CIRCUMFLEX ACCENT, left-right + '_' # 0x005f -> LOW LINE, left-right + '`' # 0x0060 -> GRAVE ACCENT + 'a' # 0x0061 -> LATIN SMALL LETTER A + 'b' # 0x0062 -> LATIN SMALL LETTER B + 'c' # 0x0063 -> LATIN SMALL LETTER C + 'd' # 0x0064 -> LATIN SMALL LETTER D + 'e' # 0x0065 -> LATIN SMALL LETTER E + 'f' # 0x0066 -> LATIN SMALL LETTER F + 'g' # 0x0067 -> LATIN SMALL LETTER G + 'h' # 0x0068 -> LATIN SMALL LETTER H + 'i' # 0x0069 -> LATIN SMALL LETTER I + 'j' # 0x006a -> LATIN SMALL LETTER J + 'k' # 0x006b -> LATIN SMALL LETTER K + 'l' # 0x006c -> LATIN SMALL LETTER L + 'm' # 0x006d -> LATIN SMALL LETTER M + 'n' # 0x006e -> LATIN SMALL LETTER N + 'o' # 0x006f -> LATIN SMALL LETTER O + 'p' # 0x0070 -> LATIN SMALL LETTER P + 'q' # 0x0071 -> LATIN SMALL LETTER Q + 'r' # 0x0072 -> LATIN SMALL LETTER R + 's' # 0x0073 -> LATIN SMALL LETTER S + 't' # 0x0074 -> LATIN SMALL LETTER T + 'u' # 0x0075 -> LATIN SMALL LETTER U + 'v' # 0x0076 -> LATIN SMALL LETTER V + 'w' # 0x0077 -> LATIN SMALL LETTER W + 'x' # 0x0078 -> LATIN SMALL LETTER X + 'y' # 0x0079 -> LATIN SMALL LETTER Y + 'z' # 0x007a -> LATIN SMALL LETTER Z + '{' # 0x007b -> LEFT CURLY BRACKET, left-right + '|' # 0x007c -> VERTICAL LINE, left-right + '}' # 0x007d -> RIGHT CURLY BRACKET, left-right + '~' # 0x007e -> TILDE + '\x7f' # 0x007f -> CONTROL CHARACTER + '\xc4' # 0x0080 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xa0' # 0x0081 -> NO-BREAK SPACE, right-left + '\xc7' # 0x0082 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xc9' # 0x0083 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xd1' # 0x0084 -> LATIN CAPITAL LETTER N WITH TILDE + '\xd6' # 0x0085 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xdc' # 0x0086 -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xe1' # 0x0087 -> LATIN SMALL LETTER A WITH ACUTE + '\xe0' # 0x0088 -> LATIN SMALL LETTER A WITH GRAVE + '\xe2' # 0x0089 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe4' # 0x008a -> LATIN SMALL LETTER A WITH DIAERESIS + '\u06ba' # 0x008b -> ARABIC LETTER NOON GHUNNA + '\xab' # 0x008c -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left + '\xe7' # 0x008d -> LATIN SMALL LETTER C WITH CEDILLA + '\xe9' # 0x008e -> LATIN SMALL LETTER E WITH ACUTE + '\xe8' # 0x008f -> LATIN SMALL LETTER E WITH GRAVE + '\xea' # 0x0090 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0x0091 -> LATIN SMALL LETTER E WITH DIAERESIS + '\xed' # 0x0092 -> LATIN SMALL LETTER I WITH ACUTE + '\u2026' # 0x0093 -> HORIZONTAL ELLIPSIS, right-left + '\xee' # 0x0094 -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0x0095 -> LATIN SMALL LETTER I WITH DIAERESIS + '\xf1' # 0x0096 -> LATIN SMALL LETTER N WITH TILDE + '\xf3' # 0x0097 -> LATIN SMALL LETTER O WITH ACUTE + '\xbb' # 0x0098 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left + '\xf4' # 0x0099 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf6' # 0x009a -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf7' # 0x009b -> DIVISION SIGN, right-left + '\xfa' # 0x009c -> LATIN SMALL LETTER U WITH ACUTE + '\xf9' # 0x009d -> LATIN SMALL LETTER U WITH GRAVE + '\xfb' # 0x009e -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0x009f -> LATIN SMALL LETTER U WITH DIAERESIS + ' ' # 0x00a0 -> SPACE, right-left + '!' # 0x00a1 -> EXCLAMATION MARK, right-left + '"' # 0x00a2 -> QUOTATION MARK, right-left + '#' # 0x00a3 -> NUMBER SIGN, right-left + '$' # 0x00a4 -> DOLLAR SIGN, right-left + '\u066a' # 0x00a5 -> ARABIC PERCENT SIGN + '&' # 0x00a6 -> AMPERSAND, right-left + "'" # 0x00a7 -> APOSTROPHE, right-left + '(' # 0x00a8 -> LEFT PARENTHESIS, right-left + ')' # 0x00a9 -> RIGHT PARENTHESIS, right-left + '*' # 0x00aa -> ASTERISK, right-left + '+' # 0x00ab -> PLUS SIGN, right-left + '\u060c' # 0x00ac -> ARABIC COMMA + '-' # 0x00ad -> HYPHEN-MINUS, right-left + '.' # 0x00ae -> FULL STOP, right-left + '/' # 0x00af -> SOLIDUS, right-left + '\u0660' # 0x00b0 -> ARABIC-INDIC DIGIT ZERO, right-left (need override) + '\u0661' # 0x00b1 -> ARABIC-INDIC DIGIT ONE, right-left (need override) + '\u0662' # 0x00b2 -> ARABIC-INDIC DIGIT TWO, right-left (need override) + '\u0663' # 0x00b3 -> ARABIC-INDIC DIGIT THREE, right-left (need override) + '\u0664' # 0x00b4 -> ARABIC-INDIC DIGIT FOUR, right-left (need override) + '\u0665' # 0x00b5 -> ARABIC-INDIC DIGIT FIVE, right-left (need override) + '\u0666' # 0x00b6 -> ARABIC-INDIC DIGIT SIX, right-left (need override) + '\u0667' # 0x00b7 -> ARABIC-INDIC DIGIT SEVEN, right-left (need override) + '\u0668' # 0x00b8 -> ARABIC-INDIC DIGIT EIGHT, right-left (need override) + '\u0669' # 0x00b9 -> ARABIC-INDIC DIGIT NINE, right-left (need override) + ':' # 0x00ba -> COLON, right-left + '\u061b' # 0x00bb -> ARABIC SEMICOLON + '<' # 0x00bc -> LESS-THAN SIGN, right-left + '=' # 0x00bd -> EQUALS SIGN, right-left + '>' # 0x00be -> GREATER-THAN SIGN, right-left + '\u061f' # 0x00bf -> ARABIC QUESTION MARK + '\u274a' # 0x00c0 -> EIGHT TEARDROP-SPOKED PROPELLER ASTERISK, right-left + '\u0621' # 0x00c1 -> ARABIC LETTER HAMZA + '\u0622' # 0x00c2 -> ARABIC LETTER ALEF WITH MADDA ABOVE + '\u0623' # 0x00c3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE + '\u0624' # 0x00c4 -> ARABIC LETTER WAW WITH HAMZA ABOVE + '\u0625' # 0x00c5 -> ARABIC LETTER ALEF WITH HAMZA BELOW + '\u0626' # 0x00c6 -> ARABIC LETTER YEH WITH HAMZA ABOVE + '\u0627' # 0x00c7 -> ARABIC LETTER ALEF + '\u0628' # 0x00c8 -> ARABIC LETTER BEH + '\u0629' # 0x00c9 -> ARABIC LETTER TEH MARBUTA + '\u062a' # 0x00ca -> ARABIC LETTER TEH + '\u062b' # 0x00cb -> ARABIC LETTER THEH + '\u062c' # 0x00cc -> ARABIC LETTER JEEM + '\u062d' # 0x00cd -> ARABIC LETTER HAH + '\u062e' # 0x00ce -> ARABIC LETTER KHAH + '\u062f' # 0x00cf -> ARABIC LETTER DAL + '\u0630' # 0x00d0 -> ARABIC LETTER THAL + '\u0631' # 0x00d1 -> ARABIC LETTER REH + '\u0632' # 0x00d2 -> ARABIC LETTER ZAIN + '\u0633' # 0x00d3 -> ARABIC LETTER SEEN + '\u0634' # 0x00d4 -> ARABIC LETTER SHEEN + '\u0635' # 0x00d5 -> ARABIC LETTER SAD + '\u0636' # 0x00d6 -> ARABIC LETTER DAD + '\u0637' # 0x00d7 -> ARABIC LETTER TAH + '\u0638' # 0x00d8 -> ARABIC LETTER ZAH + '\u0639' # 0x00d9 -> ARABIC LETTER AIN + '\u063a' # 0x00da -> ARABIC LETTER GHAIN + '[' # 0x00db -> LEFT SQUARE BRACKET, right-left + '\\' # 0x00dc -> REVERSE SOLIDUS, right-left + ']' # 0x00dd -> RIGHT SQUARE BRACKET, right-left + '^' # 0x00de -> CIRCUMFLEX ACCENT, right-left + '_' # 0x00df -> LOW LINE, right-left + '\u0640' # 0x00e0 -> ARABIC TATWEEL + '\u0641' # 0x00e1 -> ARABIC LETTER FEH + '\u0642' # 0x00e2 -> ARABIC LETTER QAF + '\u0643' # 0x00e3 -> ARABIC LETTER KAF + '\u0644' # 0x00e4 -> ARABIC LETTER LAM + '\u0645' # 0x00e5 -> ARABIC LETTER MEEM + '\u0646' # 0x00e6 -> ARABIC LETTER NOON + '\u0647' # 0x00e7 -> ARABIC LETTER HEH + '\u0648' # 0x00e8 -> ARABIC LETTER WAW + '\u0649' # 0x00e9 -> ARABIC LETTER ALEF MAKSURA + '\u064a' # 0x00ea -> ARABIC LETTER YEH + '\u064b' # 0x00eb -> ARABIC FATHATAN + '\u064c' # 0x00ec -> ARABIC DAMMATAN + '\u064d' # 0x00ed -> ARABIC KASRATAN + '\u064e' # 0x00ee -> ARABIC FATHA + '\u064f' # 0x00ef -> ARABIC DAMMA + '\u0650' # 0x00f0 -> ARABIC KASRA + '\u0651' # 0x00f1 -> ARABIC SHADDA + '\u0652' # 0x00f2 -> ARABIC SUKUN + '\u067e' # 0x00f3 -> ARABIC LETTER PEH + '\u0679' # 0x00f4 -> ARABIC LETTER TTEH + '\u0686' # 0x00f5 -> ARABIC LETTER TCHEH + '\u06d5' # 0x00f6 -> ARABIC LETTER AE + '\u06a4' # 0x00f7 -> ARABIC LETTER VEH + '\u06af' # 0x00f8 -> ARABIC LETTER GAF + '\u0688' # 0x00f9 -> ARABIC LETTER DDAL + '\u0691' # 0x00fa -> ARABIC LETTER RREH + '{' # 0x00fb -> LEFT CURLY BRACKET, right-left + '|' # 0x00fc -> VERTICAL LINE, right-left + '}' # 0x00fd -> RIGHT CURLY BRACKET, right-left + '\u0698' # 0x00fe -> ARABIC LETTER JEH + '\u06d2' # 0x00ff -> ARABIC LETTER YEH BARREE +) + +### Encoding Map + +encoding_map = { + 0x0000: 0x0000, # CONTROL CHARACTER + 0x0001: 0x0001, # CONTROL CHARACTER + 0x0002: 0x0002, # CONTROL CHARACTER + 0x0003: 0x0003, # CONTROL CHARACTER + 0x0004: 0x0004, # CONTROL CHARACTER + 0x0005: 0x0005, # CONTROL CHARACTER + 0x0006: 0x0006, # CONTROL CHARACTER + 0x0007: 0x0007, # CONTROL CHARACTER + 0x0008: 0x0008, # CONTROL CHARACTER + 0x0009: 0x0009, # CONTROL CHARACTER + 0x000a: 0x000a, # CONTROL CHARACTER + 0x000b: 0x000b, # CONTROL CHARACTER + 0x000c: 0x000c, # CONTROL CHARACTER + 0x000d: 0x000d, # CONTROL CHARACTER + 0x000e: 0x000e, # CONTROL CHARACTER + 0x000f: 0x000f, # CONTROL CHARACTER + 0x0010: 0x0010, # CONTROL CHARACTER + 0x0011: 0x0011, # CONTROL CHARACTER + 0x0012: 0x0012, # CONTROL CHARACTER + 0x0013: 0x0013, # CONTROL CHARACTER + 0x0014: 0x0014, # CONTROL CHARACTER + 0x0015: 0x0015, # CONTROL CHARACTER + 0x0016: 0x0016, # CONTROL CHARACTER + 0x0017: 0x0017, # CONTROL CHARACTER + 0x0018: 0x0018, # CONTROL CHARACTER + 0x0019: 0x0019, # CONTROL CHARACTER + 0x001a: 0x001a, # CONTROL CHARACTER + 0x001b: 0x001b, # CONTROL CHARACTER + 0x001c: 0x001c, # CONTROL CHARACTER + 0x001d: 0x001d, # CONTROL CHARACTER + 0x001e: 0x001e, # CONTROL CHARACTER + 0x001f: 0x001f, # CONTROL CHARACTER + 0x0020: 0x0020, # SPACE, left-right + 0x0020: 0x00a0, # SPACE, right-left + 0x0021: 0x0021, # EXCLAMATION MARK, left-right + 0x0021: 0x00a1, # EXCLAMATION MARK, right-left + 0x0022: 0x0022, # QUOTATION MARK, left-right + 0x0022: 0x00a2, # QUOTATION MARK, right-left + 0x0023: 0x0023, # NUMBER SIGN, left-right + 0x0023: 0x00a3, # NUMBER SIGN, right-left + 0x0024: 0x0024, # DOLLAR SIGN, left-right + 0x0024: 0x00a4, # DOLLAR SIGN, right-left + 0x0025: 0x0025, # PERCENT SIGN, left-right + 0x0026: 0x0026, # AMPERSAND, left-right + 0x0026: 0x00a6, # AMPERSAND, right-left + 0x0027: 0x0027, # APOSTROPHE, left-right + 0x0027: 0x00a7, # APOSTROPHE, right-left + 0x0028: 0x0028, # LEFT PARENTHESIS, left-right + 0x0028: 0x00a8, # LEFT PARENTHESIS, right-left + 0x0029: 0x0029, # RIGHT PARENTHESIS, left-right + 0x0029: 0x00a9, # RIGHT PARENTHESIS, right-left + 0x002a: 0x002a, # ASTERISK, left-right + 0x002a: 0x00aa, # ASTERISK, right-left + 0x002b: 0x002b, # PLUS SIGN, left-right + 0x002b: 0x00ab, # PLUS SIGN, right-left + 0x002c: 0x002c, # COMMA, left-right; in Arabic-script context, displayed as 0x066C ARABIC THOUSANDS SEPARATOR + 0x002d: 0x002d, # HYPHEN-MINUS, left-right + 0x002d: 0x00ad, # HYPHEN-MINUS, right-left + 0x002e: 0x002e, # FULL STOP, left-right; in Arabic-script context, displayed as 0x066B ARABIC DECIMAL SEPARATOR + 0x002e: 0x00ae, # FULL STOP, right-left + 0x002f: 0x002f, # SOLIDUS, left-right + 0x002f: 0x00af, # SOLIDUS, right-left + 0x0030: 0x0030, # DIGIT ZERO; in Arabic-script context, displayed as 0x0660 ARABIC-INDIC DIGIT ZERO + 0x0031: 0x0031, # DIGIT ONE; in Arabic-script context, displayed as 0x0661 ARABIC-INDIC DIGIT ONE + 0x0032: 0x0032, # DIGIT TWO; in Arabic-script context, displayed as 0x0662 ARABIC-INDIC DIGIT TWO + 0x0033: 0x0033, # DIGIT THREE; in Arabic-script context, displayed as 0x0663 ARABIC-INDIC DIGIT THREE + 0x0034: 0x0034, # DIGIT FOUR; in Arabic-script context, displayed as 0x0664 ARABIC-INDIC DIGIT FOUR + 0x0035: 0x0035, # DIGIT FIVE; in Arabic-script context, displayed as 0x0665 ARABIC-INDIC DIGIT FIVE + 0x0036: 0x0036, # DIGIT SIX; in Arabic-script context, displayed as 0x0666 ARABIC-INDIC DIGIT SIX + 0x0037: 0x0037, # DIGIT SEVEN; in Arabic-script context, displayed as 0x0667 ARABIC-INDIC DIGIT SEVEN + 0x0038: 0x0038, # DIGIT EIGHT; in Arabic-script context, displayed as 0x0668 ARABIC-INDIC DIGIT EIGHT + 0x0039: 0x0039, # DIGIT NINE; in Arabic-script context, displayed as 0x0669 ARABIC-INDIC DIGIT NINE + 0x003a: 0x003a, # COLON, left-right + 0x003a: 0x00ba, # COLON, right-left + 0x003b: 0x003b, # SEMICOLON, left-right + 0x003c: 0x003c, # LESS-THAN SIGN, left-right + 0x003c: 0x00bc, # LESS-THAN SIGN, right-left + 0x003d: 0x003d, # EQUALS SIGN, left-right + 0x003d: 0x00bd, # EQUALS SIGN, right-left + 0x003e: 0x003e, # GREATER-THAN SIGN, left-right + 0x003e: 0x00be, # GREATER-THAN SIGN, right-left + 0x003f: 0x003f, # QUESTION MARK, left-right + 0x0040: 0x0040, # COMMERCIAL AT + 0x0041: 0x0041, # LATIN CAPITAL LETTER A + 0x0042: 0x0042, # LATIN CAPITAL LETTER B + 0x0043: 0x0043, # LATIN CAPITAL LETTER C + 0x0044: 0x0044, # LATIN CAPITAL LETTER D + 0x0045: 0x0045, # LATIN CAPITAL LETTER E + 0x0046: 0x0046, # LATIN CAPITAL LETTER F + 0x0047: 0x0047, # LATIN CAPITAL LETTER G + 0x0048: 0x0048, # LATIN CAPITAL LETTER H + 0x0049: 0x0049, # LATIN CAPITAL LETTER I + 0x004a: 0x004a, # LATIN CAPITAL LETTER J + 0x004b: 0x004b, # LATIN CAPITAL LETTER K + 0x004c: 0x004c, # LATIN CAPITAL LETTER L + 0x004d: 0x004d, # LATIN CAPITAL LETTER M + 0x004e: 0x004e, # LATIN CAPITAL LETTER N + 0x004f: 0x004f, # LATIN CAPITAL LETTER O + 0x0050: 0x0050, # LATIN CAPITAL LETTER P + 0x0051: 0x0051, # LATIN CAPITAL LETTER Q + 0x0052: 0x0052, # LATIN CAPITAL LETTER R + 0x0053: 0x0053, # LATIN CAPITAL LETTER S + 0x0054: 0x0054, # LATIN CAPITAL LETTER T + 0x0055: 0x0055, # LATIN CAPITAL LETTER U + 0x0056: 0x0056, # LATIN CAPITAL LETTER V + 0x0057: 0x0057, # LATIN CAPITAL LETTER W + 0x0058: 0x0058, # LATIN CAPITAL LETTER X + 0x0059: 0x0059, # LATIN CAPITAL LETTER Y + 0x005a: 0x005a, # LATIN CAPITAL LETTER Z + 0x005b: 0x005b, # LEFT SQUARE BRACKET, left-right + 0x005b: 0x00db, # LEFT SQUARE BRACKET, right-left + 0x005c: 0x005c, # REVERSE SOLIDUS, left-right + 0x005c: 0x00dc, # REVERSE SOLIDUS, right-left + 0x005d: 0x005d, # RIGHT SQUARE BRACKET, left-right + 0x005d: 0x00dd, # RIGHT SQUARE BRACKET, right-left + 0x005e: 0x005e, # CIRCUMFLEX ACCENT, left-right + 0x005e: 0x00de, # CIRCUMFLEX ACCENT, right-left + 0x005f: 0x005f, # LOW LINE, left-right + 0x005f: 0x00df, # LOW LINE, right-left + 0x0060: 0x0060, # GRAVE ACCENT + 0x0061: 0x0061, # LATIN SMALL LETTER A + 0x0062: 0x0062, # LATIN SMALL LETTER B + 0x0063: 0x0063, # LATIN SMALL LETTER C + 0x0064: 0x0064, # LATIN SMALL LETTER D + 0x0065: 0x0065, # LATIN SMALL LETTER E + 0x0066: 0x0066, # LATIN SMALL LETTER F + 0x0067: 0x0067, # LATIN SMALL LETTER G + 0x0068: 0x0068, # LATIN SMALL LETTER H + 0x0069: 0x0069, # LATIN SMALL LETTER I + 0x006a: 0x006a, # LATIN SMALL LETTER J + 0x006b: 0x006b, # LATIN SMALL LETTER K + 0x006c: 0x006c, # LATIN SMALL LETTER L + 0x006d: 0x006d, # LATIN SMALL LETTER M + 0x006e: 0x006e, # LATIN SMALL LETTER N + 0x006f: 0x006f, # LATIN SMALL LETTER O + 0x0070: 0x0070, # LATIN SMALL LETTER P + 0x0071: 0x0071, # LATIN SMALL LETTER Q + 0x0072: 0x0072, # LATIN SMALL LETTER R + 0x0073: 0x0073, # LATIN SMALL LETTER S + 0x0074: 0x0074, # LATIN SMALL LETTER T + 0x0075: 0x0075, # LATIN SMALL LETTER U + 0x0076: 0x0076, # LATIN SMALL LETTER V + 0x0077: 0x0077, # LATIN SMALL LETTER W + 0x0078: 0x0078, # LATIN SMALL LETTER X + 0x0079: 0x0079, # LATIN SMALL LETTER Y + 0x007a: 0x007a, # LATIN SMALL LETTER Z + 0x007b: 0x007b, # LEFT CURLY BRACKET, left-right + 0x007b: 0x00fb, # LEFT CURLY BRACKET, right-left + 0x007c: 0x007c, # VERTICAL LINE, left-right + 0x007c: 0x00fc, # VERTICAL LINE, right-left + 0x007d: 0x007d, # RIGHT CURLY BRACKET, left-right + 0x007d: 0x00fd, # RIGHT CURLY BRACKET, right-left + 0x007e: 0x007e, # TILDE + 0x007f: 0x007f, # CONTROL CHARACTER + 0x00a0: 0x0081, # NO-BREAK SPACE, right-left + 0x00ab: 0x008c, # LEFT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left + 0x00bb: 0x0098, # RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left + 0x00c4: 0x0080, # LATIN CAPITAL LETTER A WITH DIAERESIS + 0x00c7: 0x0082, # LATIN CAPITAL LETTER C WITH CEDILLA + 0x00c9: 0x0083, # LATIN CAPITAL LETTER E WITH ACUTE + 0x00d1: 0x0084, # LATIN CAPITAL LETTER N WITH TILDE + 0x00d6: 0x0085, # LATIN CAPITAL LETTER O WITH DIAERESIS + 0x00dc: 0x0086, # LATIN CAPITAL LETTER U WITH DIAERESIS + 0x00e0: 0x0088, # LATIN SMALL LETTER A WITH GRAVE + 0x00e1: 0x0087, # LATIN SMALL LETTER A WITH ACUTE + 0x00e2: 0x0089, # LATIN SMALL LETTER A WITH CIRCUMFLEX + 0x00e4: 0x008a, # LATIN SMALL LETTER A WITH DIAERESIS + 0x00e7: 0x008d, # LATIN SMALL LETTER C WITH CEDILLA + 0x00e8: 0x008f, # LATIN SMALL LETTER E WITH GRAVE + 0x00e9: 0x008e, # LATIN SMALL LETTER E WITH ACUTE + 0x00ea: 0x0090, # LATIN SMALL LETTER E WITH CIRCUMFLEX + 0x00eb: 0x0091, # LATIN SMALL LETTER E WITH DIAERESIS + 0x00ed: 0x0092, # LATIN SMALL LETTER I WITH ACUTE + 0x00ee: 0x0094, # LATIN SMALL LETTER I WITH CIRCUMFLEX + 0x00ef: 0x0095, # LATIN SMALL LETTER I WITH DIAERESIS + 0x00f1: 0x0096, # LATIN SMALL LETTER N WITH TILDE + 0x00f3: 0x0097, # LATIN SMALL LETTER O WITH ACUTE + 0x00f4: 0x0099, # LATIN SMALL LETTER O WITH CIRCUMFLEX + 0x00f6: 0x009a, # LATIN SMALL LETTER O WITH DIAERESIS + 0x00f7: 0x009b, # DIVISION SIGN, right-left + 0x00f9: 0x009d, # LATIN SMALL LETTER U WITH GRAVE + 0x00fa: 0x009c, # LATIN SMALL LETTER U WITH ACUTE + 0x00fb: 0x009e, # LATIN SMALL LETTER U WITH CIRCUMFLEX + 0x00fc: 0x009f, # LATIN SMALL LETTER U WITH DIAERESIS + 0x060c: 0x00ac, # ARABIC COMMA + 0x061b: 0x00bb, # ARABIC SEMICOLON + 0x061f: 0x00bf, # ARABIC QUESTION MARK + 0x0621: 0x00c1, # ARABIC LETTER HAMZA + 0x0622: 0x00c2, # ARABIC LETTER ALEF WITH MADDA ABOVE + 0x0623: 0x00c3, # ARABIC LETTER ALEF WITH HAMZA ABOVE + 0x0624: 0x00c4, # ARABIC LETTER WAW WITH HAMZA ABOVE + 0x0625: 0x00c5, # ARABIC LETTER ALEF WITH HAMZA BELOW + 0x0626: 0x00c6, # ARABIC LETTER YEH WITH HAMZA ABOVE + 0x0627: 0x00c7, # ARABIC LETTER ALEF + 0x0628: 0x00c8, # ARABIC LETTER BEH + 0x0629: 0x00c9, # ARABIC LETTER TEH MARBUTA + 0x062a: 0x00ca, # ARABIC LETTER TEH + 0x062b: 0x00cb, # ARABIC LETTER THEH + 0x062c: 0x00cc, # ARABIC LETTER JEEM + 0x062d: 0x00cd, # ARABIC LETTER HAH + 0x062e: 0x00ce, # ARABIC LETTER KHAH + 0x062f: 0x00cf, # ARABIC LETTER DAL + 0x0630: 0x00d0, # ARABIC LETTER THAL + 0x0631: 0x00d1, # ARABIC LETTER REH + 0x0632: 0x00d2, # ARABIC LETTER ZAIN + 0x0633: 0x00d3, # ARABIC LETTER SEEN + 0x0634: 0x00d4, # ARABIC LETTER SHEEN + 0x0635: 0x00d5, # ARABIC LETTER SAD + 0x0636: 0x00d6, # ARABIC LETTER DAD + 0x0637: 0x00d7, # ARABIC LETTER TAH + 0x0638: 0x00d8, # ARABIC LETTER ZAH + 0x0639: 0x00d9, # ARABIC LETTER AIN + 0x063a: 0x00da, # ARABIC LETTER GHAIN + 0x0640: 0x00e0, # ARABIC TATWEEL + 0x0641: 0x00e1, # ARABIC LETTER FEH + 0x0642: 0x00e2, # ARABIC LETTER QAF + 0x0643: 0x00e3, # ARABIC LETTER KAF + 0x0644: 0x00e4, # ARABIC LETTER LAM + 0x0645: 0x00e5, # ARABIC LETTER MEEM + 0x0646: 0x00e6, # ARABIC LETTER NOON + 0x0647: 0x00e7, # ARABIC LETTER HEH + 0x0648: 0x00e8, # ARABIC LETTER WAW + 0x0649: 0x00e9, # ARABIC LETTER ALEF MAKSURA + 0x064a: 0x00ea, # ARABIC LETTER YEH + 0x064b: 0x00eb, # ARABIC FATHATAN + 0x064c: 0x00ec, # ARABIC DAMMATAN + 0x064d: 0x00ed, # ARABIC KASRATAN + 0x064e: 0x00ee, # ARABIC FATHA + 0x064f: 0x00ef, # ARABIC DAMMA + 0x0650: 0x00f0, # ARABIC KASRA + 0x0651: 0x00f1, # ARABIC SHADDA + 0x0652: 0x00f2, # ARABIC SUKUN + 0x0660: 0x00b0, # ARABIC-INDIC DIGIT ZERO, right-left (need override) + 0x0661: 0x00b1, # ARABIC-INDIC DIGIT ONE, right-left (need override) + 0x0662: 0x00b2, # ARABIC-INDIC DIGIT TWO, right-left (need override) + 0x0663: 0x00b3, # ARABIC-INDIC DIGIT THREE, right-left (need override) + 0x0664: 0x00b4, # ARABIC-INDIC DIGIT FOUR, right-left (need override) + 0x0665: 0x00b5, # ARABIC-INDIC DIGIT FIVE, right-left (need override) + 0x0666: 0x00b6, # ARABIC-INDIC DIGIT SIX, right-left (need override) + 0x0667: 0x00b7, # ARABIC-INDIC DIGIT SEVEN, right-left (need override) + 0x0668: 0x00b8, # ARABIC-INDIC DIGIT EIGHT, right-left (need override) + 0x0669: 0x00b9, # ARABIC-INDIC DIGIT NINE, right-left (need override) + 0x066a: 0x00a5, # ARABIC PERCENT SIGN + 0x0679: 0x00f4, # ARABIC LETTER TTEH + 0x067e: 0x00f3, # ARABIC LETTER PEH + 0x0686: 0x00f5, # ARABIC LETTER TCHEH + 0x0688: 0x00f9, # ARABIC LETTER DDAL + 0x0691: 0x00fa, # ARABIC LETTER RREH + 0x0698: 0x00fe, # ARABIC LETTER JEH + 0x06a4: 0x00f7, # ARABIC LETTER VEH + 0x06af: 0x00f8, # ARABIC LETTER GAF + 0x06ba: 0x008b, # ARABIC LETTER NOON GHUNNA + 0x06d2: 0x00ff, # ARABIC LETTER YEH BARREE + 0x06d5: 0x00f6, # ARABIC LETTER AE + 0x2026: 0x0093, # HORIZONTAL ELLIPSIS, right-left + 0x274a: 0x00c0, # EIGHT TEARDROP-SPOKED PROPELLER ASTERISK, right-left +} diff --git a/contrib/tools/python3/src/Lib/encodings/mac_croatian.py b/contrib/tools/python3/src/Lib/encodings/mac_croatian.py new file mode 100644 index 0000000000..4a92fe61a4 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/mac_croatian.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec mac_croatian generated from 'MAPPINGS/VENDORS/APPLE/CROATIAN.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='mac-croatian', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> CONTROL CHARACTER + '\x01' # 0x01 -> CONTROL CHARACTER + '\x02' # 0x02 -> CONTROL CHARACTER + '\x03' # 0x03 -> CONTROL CHARACTER + '\x04' # 0x04 -> CONTROL CHARACTER + '\x05' # 0x05 -> CONTROL CHARACTER + '\x06' # 0x06 -> CONTROL CHARACTER + '\x07' # 0x07 -> CONTROL CHARACTER + '\x08' # 0x08 -> CONTROL CHARACTER + '\t' # 0x09 -> CONTROL CHARACTER + '\n' # 0x0A -> CONTROL CHARACTER + '\x0b' # 0x0B -> CONTROL CHARACTER + '\x0c' # 0x0C -> CONTROL CHARACTER + '\r' # 0x0D -> CONTROL CHARACTER + '\x0e' # 0x0E -> CONTROL CHARACTER + '\x0f' # 0x0F -> CONTROL CHARACTER + '\x10' # 0x10 -> CONTROL CHARACTER + '\x11' # 0x11 -> CONTROL CHARACTER + '\x12' # 0x12 -> CONTROL CHARACTER + '\x13' # 0x13 -> CONTROL CHARACTER + '\x14' # 0x14 -> CONTROL CHARACTER + '\x15' # 0x15 -> CONTROL CHARACTER + '\x16' # 0x16 -> CONTROL CHARACTER + '\x17' # 0x17 -> CONTROL CHARACTER + '\x18' # 0x18 -> CONTROL CHARACTER + '\x19' # 0x19 -> CONTROL CHARACTER + '\x1a' # 0x1A -> CONTROL CHARACTER + '\x1b' # 0x1B -> CONTROL CHARACTER + '\x1c' # 0x1C -> CONTROL CHARACTER + '\x1d' # 0x1D -> CONTROL CHARACTER + '\x1e' # 0x1E -> CONTROL CHARACTER + '\x1f' # 0x1F -> CONTROL CHARACTER + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> CONTROL CHARACTER + '\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0x81 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc7' # 0x82 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xc9' # 0x83 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xd1' # 0x84 -> LATIN CAPITAL LETTER N WITH TILDE + '\xd6' # 0x85 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xdc' # 0x86 -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xe1' # 0x87 -> LATIN SMALL LETTER A WITH ACUTE + '\xe0' # 0x88 -> LATIN SMALL LETTER A WITH GRAVE + '\xe2' # 0x89 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe3' # 0x8B -> LATIN SMALL LETTER A WITH TILDE + '\xe5' # 0x8C -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe7' # 0x8D -> LATIN SMALL LETTER C WITH CEDILLA + '\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE + '\xe8' # 0x8F -> LATIN SMALL LETTER E WITH GRAVE + '\xea' # 0x90 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0x91 -> LATIN SMALL LETTER E WITH DIAERESIS + '\xed' # 0x92 -> LATIN SMALL LETTER I WITH ACUTE + '\xec' # 0x93 -> LATIN SMALL LETTER I WITH GRAVE + '\xee' # 0x94 -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0x95 -> LATIN SMALL LETTER I WITH DIAERESIS + '\xf1' # 0x96 -> LATIN SMALL LETTER N WITH TILDE + '\xf3' # 0x97 -> LATIN SMALL LETTER O WITH ACUTE + '\xf2' # 0x98 -> LATIN SMALL LETTER O WITH GRAVE + '\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf5' # 0x9B -> LATIN SMALL LETTER O WITH TILDE + '\xfa' # 0x9C -> LATIN SMALL LETTER U WITH ACUTE + '\xf9' # 0x9D -> LATIN SMALL LETTER U WITH GRAVE + '\xfb' # 0x9E -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS + '\u2020' # 0xA0 -> DAGGER + '\xb0' # 0xA1 -> DEGREE SIGN + '\xa2' # 0xA2 -> CENT SIGN + '\xa3' # 0xA3 -> POUND SIGN + '\xa7' # 0xA4 -> SECTION SIGN + '\u2022' # 0xA5 -> BULLET + '\xb6' # 0xA6 -> PILCROW SIGN + '\xdf' # 0xA7 -> LATIN SMALL LETTER SHARP S + '\xae' # 0xA8 -> REGISTERED SIGN + '\u0160' # 0xA9 -> LATIN CAPITAL LETTER S WITH CARON + '\u2122' # 0xAA -> TRADE MARK SIGN + '\xb4' # 0xAB -> ACUTE ACCENT + '\xa8' # 0xAC -> DIAERESIS + '\u2260' # 0xAD -> NOT EQUAL TO + '\u017d' # 0xAE -> LATIN CAPITAL LETTER Z WITH CARON + '\xd8' # 0xAF -> LATIN CAPITAL LETTER O WITH STROKE + '\u221e' # 0xB0 -> INFINITY + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO + '\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO + '\u2206' # 0xB4 -> INCREMENT + '\xb5' # 0xB5 -> MICRO SIGN + '\u2202' # 0xB6 -> PARTIAL DIFFERENTIAL + '\u2211' # 0xB7 -> N-ARY SUMMATION + '\u220f' # 0xB8 -> N-ARY PRODUCT + '\u0161' # 0xB9 -> LATIN SMALL LETTER S WITH CARON + '\u222b' # 0xBA -> INTEGRAL + '\xaa' # 0xBB -> FEMININE ORDINAL INDICATOR + '\xba' # 0xBC -> MASCULINE ORDINAL INDICATOR + '\u03a9' # 0xBD -> GREEK CAPITAL LETTER OMEGA + '\u017e' # 0xBE -> LATIN SMALL LETTER Z WITH CARON + '\xf8' # 0xBF -> LATIN SMALL LETTER O WITH STROKE + '\xbf' # 0xC0 -> INVERTED QUESTION MARK + '\xa1' # 0xC1 -> INVERTED EXCLAMATION MARK + '\xac' # 0xC2 -> NOT SIGN + '\u221a' # 0xC3 -> SQUARE ROOT + '\u0192' # 0xC4 -> LATIN SMALL LETTER F WITH HOOK + '\u2248' # 0xC5 -> ALMOST EQUAL TO + '\u0106' # 0xC6 -> LATIN CAPITAL LETTER C WITH ACUTE + '\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u010c' # 0xC8 -> LATIN CAPITAL LETTER C WITH CARON + '\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS + '\xa0' # 0xCA -> NO-BREAK SPACE + '\xc0' # 0xCB -> LATIN CAPITAL LETTER A WITH GRAVE + '\xc3' # 0xCC -> LATIN CAPITAL LETTER A WITH TILDE + '\xd5' # 0xCD -> LATIN CAPITAL LETTER O WITH TILDE + '\u0152' # 0xCE -> LATIN CAPITAL LIGATURE OE + '\u0153' # 0xCF -> LATIN SMALL LIGATURE OE + '\u0110' # 0xD0 -> LATIN CAPITAL LETTER D WITH STROKE + '\u2014' # 0xD1 -> EM DASH + '\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK + '\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK + '\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK + '\xf7' # 0xD6 -> DIVISION SIGN + '\u25ca' # 0xD7 -> LOZENGE + '\uf8ff' # 0xD8 -> Apple logo + '\xa9' # 0xD9 -> COPYRIGHT SIGN + '\u2044' # 0xDA -> FRACTION SLASH + '\u20ac' # 0xDB -> EURO SIGN + '\u2039' # 0xDC -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + '\u203a' # 0xDD -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + '\xc6' # 0xDE -> LATIN CAPITAL LETTER AE + '\xbb' # 0xDF -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u2013' # 0xE0 -> EN DASH + '\xb7' # 0xE1 -> MIDDLE DOT + '\u201a' # 0xE2 -> SINGLE LOW-9 QUOTATION MARK + '\u201e' # 0xE3 -> DOUBLE LOW-9 QUOTATION MARK + '\u2030' # 0xE4 -> PER MILLE SIGN + '\xc2' # 0xE5 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\u0107' # 0xE6 -> LATIN SMALL LETTER C WITH ACUTE + '\xc1' # 0xE7 -> LATIN CAPITAL LETTER A WITH ACUTE + '\u010d' # 0xE8 -> LATIN SMALL LETTER C WITH CARON + '\xc8' # 0xE9 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xcd' # 0xEA -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0xEB -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0xEC -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\xcc' # 0xED -> LATIN CAPITAL LETTER I WITH GRAVE + '\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd4' # 0xEF -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\u0111' # 0xF0 -> LATIN SMALL LETTER D WITH STROKE + '\xd2' # 0xF1 -> LATIN CAPITAL LETTER O WITH GRAVE + '\xda' # 0xF2 -> LATIN CAPITAL LETTER U WITH ACUTE + '\xdb' # 0xF3 -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xd9' # 0xF4 -> LATIN CAPITAL LETTER U WITH GRAVE + '\u0131' # 0xF5 -> LATIN SMALL LETTER DOTLESS I + '\u02c6' # 0xF6 -> MODIFIER LETTER CIRCUMFLEX ACCENT + '\u02dc' # 0xF7 -> SMALL TILDE + '\xaf' # 0xF8 -> MACRON + '\u03c0' # 0xF9 -> GREEK SMALL LETTER PI + '\xcb' # 0xFA -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\u02da' # 0xFB -> RING ABOVE + '\xb8' # 0xFC -> CEDILLA + '\xca' # 0xFD -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xe6' # 0xFE -> LATIN SMALL LETTER AE + '\u02c7' # 0xFF -> CARON +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/mac_cyrillic.py b/contrib/tools/python3/src/Lib/encodings/mac_cyrillic.py new file mode 100644 index 0000000000..d20272acfa --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/mac_cyrillic.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec mac_cyrillic generated from 'MAPPINGS/VENDORS/APPLE/CYRILLIC.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='mac-cyrillic', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> CONTROL CHARACTER + '\x01' # 0x01 -> CONTROL CHARACTER + '\x02' # 0x02 -> CONTROL CHARACTER + '\x03' # 0x03 -> CONTROL CHARACTER + '\x04' # 0x04 -> CONTROL CHARACTER + '\x05' # 0x05 -> CONTROL CHARACTER + '\x06' # 0x06 -> CONTROL CHARACTER + '\x07' # 0x07 -> CONTROL CHARACTER + '\x08' # 0x08 -> CONTROL CHARACTER + '\t' # 0x09 -> CONTROL CHARACTER + '\n' # 0x0A -> CONTROL CHARACTER + '\x0b' # 0x0B -> CONTROL CHARACTER + '\x0c' # 0x0C -> CONTROL CHARACTER + '\r' # 0x0D -> CONTROL CHARACTER + '\x0e' # 0x0E -> CONTROL CHARACTER + '\x0f' # 0x0F -> CONTROL CHARACTER + '\x10' # 0x10 -> CONTROL CHARACTER + '\x11' # 0x11 -> CONTROL CHARACTER + '\x12' # 0x12 -> CONTROL CHARACTER + '\x13' # 0x13 -> CONTROL CHARACTER + '\x14' # 0x14 -> CONTROL CHARACTER + '\x15' # 0x15 -> CONTROL CHARACTER + '\x16' # 0x16 -> CONTROL CHARACTER + '\x17' # 0x17 -> CONTROL CHARACTER + '\x18' # 0x18 -> CONTROL CHARACTER + '\x19' # 0x19 -> CONTROL CHARACTER + '\x1a' # 0x1A -> CONTROL CHARACTER + '\x1b' # 0x1B -> CONTROL CHARACTER + '\x1c' # 0x1C -> CONTROL CHARACTER + '\x1d' # 0x1D -> CONTROL CHARACTER + '\x1e' # 0x1E -> CONTROL CHARACTER + '\x1f' # 0x1F -> CONTROL CHARACTER + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> CONTROL CHARACTER + '\u0410' # 0x80 -> CYRILLIC CAPITAL LETTER A + '\u0411' # 0x81 -> CYRILLIC CAPITAL LETTER BE + '\u0412' # 0x82 -> CYRILLIC CAPITAL LETTER VE + '\u0413' # 0x83 -> CYRILLIC CAPITAL LETTER GHE + '\u0414' # 0x84 -> CYRILLIC CAPITAL LETTER DE + '\u0415' # 0x85 -> CYRILLIC CAPITAL LETTER IE + '\u0416' # 0x86 -> CYRILLIC CAPITAL LETTER ZHE + '\u0417' # 0x87 -> CYRILLIC CAPITAL LETTER ZE + '\u0418' # 0x88 -> CYRILLIC CAPITAL LETTER I + '\u0419' # 0x89 -> CYRILLIC CAPITAL LETTER SHORT I + '\u041a' # 0x8A -> CYRILLIC CAPITAL LETTER KA + '\u041b' # 0x8B -> CYRILLIC CAPITAL LETTER EL + '\u041c' # 0x8C -> CYRILLIC CAPITAL LETTER EM + '\u041d' # 0x8D -> CYRILLIC CAPITAL LETTER EN + '\u041e' # 0x8E -> CYRILLIC CAPITAL LETTER O + '\u041f' # 0x8F -> CYRILLIC CAPITAL LETTER PE + '\u0420' # 0x90 -> CYRILLIC CAPITAL LETTER ER + '\u0421' # 0x91 -> CYRILLIC CAPITAL LETTER ES + '\u0422' # 0x92 -> CYRILLIC CAPITAL LETTER TE + '\u0423' # 0x93 -> CYRILLIC CAPITAL LETTER U + '\u0424' # 0x94 -> CYRILLIC CAPITAL LETTER EF + '\u0425' # 0x95 -> CYRILLIC CAPITAL LETTER HA + '\u0426' # 0x96 -> CYRILLIC CAPITAL LETTER TSE + '\u0427' # 0x97 -> CYRILLIC CAPITAL LETTER CHE + '\u0428' # 0x98 -> CYRILLIC CAPITAL LETTER SHA + '\u0429' # 0x99 -> CYRILLIC CAPITAL LETTER SHCHA + '\u042a' # 0x9A -> CYRILLIC CAPITAL LETTER HARD SIGN + '\u042b' # 0x9B -> CYRILLIC CAPITAL LETTER YERU + '\u042c' # 0x9C -> CYRILLIC CAPITAL LETTER SOFT SIGN + '\u042d' # 0x9D -> CYRILLIC CAPITAL LETTER E + '\u042e' # 0x9E -> CYRILLIC CAPITAL LETTER YU + '\u042f' # 0x9F -> CYRILLIC CAPITAL LETTER YA + '\u2020' # 0xA0 -> DAGGER + '\xb0' # 0xA1 -> DEGREE SIGN + '\u0490' # 0xA2 -> CYRILLIC CAPITAL LETTER GHE WITH UPTURN + '\xa3' # 0xA3 -> POUND SIGN + '\xa7' # 0xA4 -> SECTION SIGN + '\u2022' # 0xA5 -> BULLET + '\xb6' # 0xA6 -> PILCROW SIGN + '\u0406' # 0xA7 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + '\xae' # 0xA8 -> REGISTERED SIGN + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\u2122' # 0xAA -> TRADE MARK SIGN + '\u0402' # 0xAB -> CYRILLIC CAPITAL LETTER DJE + '\u0452' # 0xAC -> CYRILLIC SMALL LETTER DJE + '\u2260' # 0xAD -> NOT EQUAL TO + '\u0403' # 0xAE -> CYRILLIC CAPITAL LETTER GJE + '\u0453' # 0xAF -> CYRILLIC SMALL LETTER GJE + '\u221e' # 0xB0 -> INFINITY + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO + '\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO + '\u0456' # 0xB4 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + '\xb5' # 0xB5 -> MICRO SIGN + '\u0491' # 0xB6 -> CYRILLIC SMALL LETTER GHE WITH UPTURN + '\u0408' # 0xB7 -> CYRILLIC CAPITAL LETTER JE + '\u0404' # 0xB8 -> CYRILLIC CAPITAL LETTER UKRAINIAN IE + '\u0454' # 0xB9 -> CYRILLIC SMALL LETTER UKRAINIAN IE + '\u0407' # 0xBA -> CYRILLIC CAPITAL LETTER YI + '\u0457' # 0xBB -> CYRILLIC SMALL LETTER YI + '\u0409' # 0xBC -> CYRILLIC CAPITAL LETTER LJE + '\u0459' # 0xBD -> CYRILLIC SMALL LETTER LJE + '\u040a' # 0xBE -> CYRILLIC CAPITAL LETTER NJE + '\u045a' # 0xBF -> CYRILLIC SMALL LETTER NJE + '\u0458' # 0xC0 -> CYRILLIC SMALL LETTER JE + '\u0405' # 0xC1 -> CYRILLIC CAPITAL LETTER DZE + '\xac' # 0xC2 -> NOT SIGN + '\u221a' # 0xC3 -> SQUARE ROOT + '\u0192' # 0xC4 -> LATIN SMALL LETTER F WITH HOOK + '\u2248' # 0xC5 -> ALMOST EQUAL TO + '\u2206' # 0xC6 -> INCREMENT + '\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0xC8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS + '\xa0' # 0xCA -> NO-BREAK SPACE + '\u040b' # 0xCB -> CYRILLIC CAPITAL LETTER TSHE + '\u045b' # 0xCC -> CYRILLIC SMALL LETTER TSHE + '\u040c' # 0xCD -> CYRILLIC CAPITAL LETTER KJE + '\u045c' # 0xCE -> CYRILLIC SMALL LETTER KJE + '\u0455' # 0xCF -> CYRILLIC SMALL LETTER DZE + '\u2013' # 0xD0 -> EN DASH + '\u2014' # 0xD1 -> EM DASH + '\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK + '\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK + '\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK + '\xf7' # 0xD6 -> DIVISION SIGN + '\u201e' # 0xD7 -> DOUBLE LOW-9 QUOTATION MARK + '\u040e' # 0xD8 -> CYRILLIC CAPITAL LETTER SHORT U + '\u045e' # 0xD9 -> CYRILLIC SMALL LETTER SHORT U + '\u040f' # 0xDA -> CYRILLIC CAPITAL LETTER DZHE + '\u045f' # 0xDB -> CYRILLIC SMALL LETTER DZHE + '\u2116' # 0xDC -> NUMERO SIGN + '\u0401' # 0xDD -> CYRILLIC CAPITAL LETTER IO + '\u0451' # 0xDE -> CYRILLIC SMALL LETTER IO + '\u044f' # 0xDF -> CYRILLIC SMALL LETTER YA + '\u0430' # 0xE0 -> CYRILLIC SMALL LETTER A + '\u0431' # 0xE1 -> CYRILLIC SMALL LETTER BE + '\u0432' # 0xE2 -> CYRILLIC SMALL LETTER VE + '\u0433' # 0xE3 -> CYRILLIC SMALL LETTER GHE + '\u0434' # 0xE4 -> CYRILLIC SMALL LETTER DE + '\u0435' # 0xE5 -> CYRILLIC SMALL LETTER IE + '\u0436' # 0xE6 -> CYRILLIC SMALL LETTER ZHE + '\u0437' # 0xE7 -> CYRILLIC SMALL LETTER ZE + '\u0438' # 0xE8 -> CYRILLIC SMALL LETTER I + '\u0439' # 0xE9 -> CYRILLIC SMALL LETTER SHORT I + '\u043a' # 0xEA -> CYRILLIC SMALL LETTER KA + '\u043b' # 0xEB -> CYRILLIC SMALL LETTER EL + '\u043c' # 0xEC -> CYRILLIC SMALL LETTER EM + '\u043d' # 0xED -> CYRILLIC SMALL LETTER EN + '\u043e' # 0xEE -> CYRILLIC SMALL LETTER O + '\u043f' # 0xEF -> CYRILLIC SMALL LETTER PE + '\u0440' # 0xF0 -> CYRILLIC SMALL LETTER ER + '\u0441' # 0xF1 -> CYRILLIC SMALL LETTER ES + '\u0442' # 0xF2 -> CYRILLIC SMALL LETTER TE + '\u0443' # 0xF3 -> CYRILLIC SMALL LETTER U + '\u0444' # 0xF4 -> CYRILLIC SMALL LETTER EF + '\u0445' # 0xF5 -> CYRILLIC SMALL LETTER HA + '\u0446' # 0xF6 -> CYRILLIC SMALL LETTER TSE + '\u0447' # 0xF7 -> CYRILLIC SMALL LETTER CHE + '\u0448' # 0xF8 -> CYRILLIC SMALL LETTER SHA + '\u0449' # 0xF9 -> CYRILLIC SMALL LETTER SHCHA + '\u044a' # 0xFA -> CYRILLIC SMALL LETTER HARD SIGN + '\u044b' # 0xFB -> CYRILLIC SMALL LETTER YERU + '\u044c' # 0xFC -> CYRILLIC SMALL LETTER SOFT SIGN + '\u044d' # 0xFD -> CYRILLIC SMALL LETTER E + '\u044e' # 0xFE -> CYRILLIC SMALL LETTER YU + '\u20ac' # 0xFF -> EURO SIGN +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/mac_farsi.py b/contrib/tools/python3/src/Lib/encodings/mac_farsi.py new file mode 100644 index 0000000000..e357d43510 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/mac_farsi.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec mac_farsi generated from 'MAPPINGS/VENDORS/APPLE/FARSI.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='mac-farsi', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> CONTROL CHARACTER + '\x01' # 0x01 -> CONTROL CHARACTER + '\x02' # 0x02 -> CONTROL CHARACTER + '\x03' # 0x03 -> CONTROL CHARACTER + '\x04' # 0x04 -> CONTROL CHARACTER + '\x05' # 0x05 -> CONTROL CHARACTER + '\x06' # 0x06 -> CONTROL CHARACTER + '\x07' # 0x07 -> CONTROL CHARACTER + '\x08' # 0x08 -> CONTROL CHARACTER + '\t' # 0x09 -> CONTROL CHARACTER + '\n' # 0x0A -> CONTROL CHARACTER + '\x0b' # 0x0B -> CONTROL CHARACTER + '\x0c' # 0x0C -> CONTROL CHARACTER + '\r' # 0x0D -> CONTROL CHARACTER + '\x0e' # 0x0E -> CONTROL CHARACTER + '\x0f' # 0x0F -> CONTROL CHARACTER + '\x10' # 0x10 -> CONTROL CHARACTER + '\x11' # 0x11 -> CONTROL CHARACTER + '\x12' # 0x12 -> CONTROL CHARACTER + '\x13' # 0x13 -> CONTROL CHARACTER + '\x14' # 0x14 -> CONTROL CHARACTER + '\x15' # 0x15 -> CONTROL CHARACTER + '\x16' # 0x16 -> CONTROL CHARACTER + '\x17' # 0x17 -> CONTROL CHARACTER + '\x18' # 0x18 -> CONTROL CHARACTER + '\x19' # 0x19 -> CONTROL CHARACTER + '\x1a' # 0x1A -> CONTROL CHARACTER + '\x1b' # 0x1B -> CONTROL CHARACTER + '\x1c' # 0x1C -> CONTROL CHARACTER + '\x1d' # 0x1D -> CONTROL CHARACTER + '\x1e' # 0x1E -> CONTROL CHARACTER + '\x1f' # 0x1F -> CONTROL CHARACTER + ' ' # 0x20 -> SPACE, left-right + '!' # 0x21 -> EXCLAMATION MARK, left-right + '"' # 0x22 -> QUOTATION MARK, left-right + '#' # 0x23 -> NUMBER SIGN, left-right + '$' # 0x24 -> DOLLAR SIGN, left-right + '%' # 0x25 -> PERCENT SIGN, left-right + '&' # 0x26 -> AMPERSAND, left-right + "'" # 0x27 -> APOSTROPHE, left-right + '(' # 0x28 -> LEFT PARENTHESIS, left-right + ')' # 0x29 -> RIGHT PARENTHESIS, left-right + '*' # 0x2A -> ASTERISK, left-right + '+' # 0x2B -> PLUS SIGN, left-right + ',' # 0x2C -> COMMA, left-right; in Arabic-script context, displayed as 0x066C ARABIC THOUSANDS SEPARATOR + '-' # 0x2D -> HYPHEN-MINUS, left-right + '.' # 0x2E -> FULL STOP, left-right; in Arabic-script context, displayed as 0x066B ARABIC DECIMAL SEPARATOR + '/' # 0x2F -> SOLIDUS, left-right + '0' # 0x30 -> DIGIT ZERO; in Arabic-script context, displayed as 0x06F0 EXTENDED ARABIC-INDIC DIGIT ZERO + '1' # 0x31 -> DIGIT ONE; in Arabic-script context, displayed as 0x06F1 EXTENDED ARABIC-INDIC DIGIT ONE + '2' # 0x32 -> DIGIT TWO; in Arabic-script context, displayed as 0x06F2 EXTENDED ARABIC-INDIC DIGIT TWO + '3' # 0x33 -> DIGIT THREE; in Arabic-script context, displayed as 0x06F3 EXTENDED ARABIC-INDIC DIGIT THREE + '4' # 0x34 -> DIGIT FOUR; in Arabic-script context, displayed as 0x06F4 EXTENDED ARABIC-INDIC DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE; in Arabic-script context, displayed as 0x06F5 EXTENDED ARABIC-INDIC DIGIT FIVE + '6' # 0x36 -> DIGIT SIX; in Arabic-script context, displayed as 0x06F6 EXTENDED ARABIC-INDIC DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN; in Arabic-script context, displayed as 0x06F7 EXTENDED ARABIC-INDIC DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT; in Arabic-script context, displayed as 0x06F8 EXTENDED ARABIC-INDIC DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE; in Arabic-script context, displayed as 0x06F9 EXTENDED ARABIC-INDIC DIGIT NINE + ':' # 0x3A -> COLON, left-right + ';' # 0x3B -> SEMICOLON, left-right + '<' # 0x3C -> LESS-THAN SIGN, left-right + '=' # 0x3D -> EQUALS SIGN, left-right + '>' # 0x3E -> GREATER-THAN SIGN, left-right + '?' # 0x3F -> QUESTION MARK, left-right + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET, left-right + '\\' # 0x5C -> REVERSE SOLIDUS, left-right + ']' # 0x5D -> RIGHT SQUARE BRACKET, left-right + '^' # 0x5E -> CIRCUMFLEX ACCENT, left-right + '_' # 0x5F -> LOW LINE, left-right + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET, left-right + '|' # 0x7C -> VERTICAL LINE, left-right + '}' # 0x7D -> RIGHT CURLY BRACKET, left-right + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> CONTROL CHARACTER + '\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xa0' # 0x81 -> NO-BREAK SPACE, right-left + '\xc7' # 0x82 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xc9' # 0x83 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xd1' # 0x84 -> LATIN CAPITAL LETTER N WITH TILDE + '\xd6' # 0x85 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xdc' # 0x86 -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xe1' # 0x87 -> LATIN SMALL LETTER A WITH ACUTE + '\xe0' # 0x88 -> LATIN SMALL LETTER A WITH GRAVE + '\xe2' # 0x89 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS + '\u06ba' # 0x8B -> ARABIC LETTER NOON GHUNNA + '\xab' # 0x8C -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left + '\xe7' # 0x8D -> LATIN SMALL LETTER C WITH CEDILLA + '\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE + '\xe8' # 0x8F -> LATIN SMALL LETTER E WITH GRAVE + '\xea' # 0x90 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0x91 -> LATIN SMALL LETTER E WITH DIAERESIS + '\xed' # 0x92 -> LATIN SMALL LETTER I WITH ACUTE + '\u2026' # 0x93 -> HORIZONTAL ELLIPSIS, right-left + '\xee' # 0x94 -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0x95 -> LATIN SMALL LETTER I WITH DIAERESIS + '\xf1' # 0x96 -> LATIN SMALL LETTER N WITH TILDE + '\xf3' # 0x97 -> LATIN SMALL LETTER O WITH ACUTE + '\xbb' # 0x98 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK, right-left + '\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf7' # 0x9B -> DIVISION SIGN, right-left + '\xfa' # 0x9C -> LATIN SMALL LETTER U WITH ACUTE + '\xf9' # 0x9D -> LATIN SMALL LETTER U WITH GRAVE + '\xfb' # 0x9E -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS + ' ' # 0xA0 -> SPACE, right-left + '!' # 0xA1 -> EXCLAMATION MARK, right-left + '"' # 0xA2 -> QUOTATION MARK, right-left + '#' # 0xA3 -> NUMBER SIGN, right-left + '$' # 0xA4 -> DOLLAR SIGN, right-left + '\u066a' # 0xA5 -> ARABIC PERCENT SIGN + '&' # 0xA6 -> AMPERSAND, right-left + "'" # 0xA7 -> APOSTROPHE, right-left + '(' # 0xA8 -> LEFT PARENTHESIS, right-left + ')' # 0xA9 -> RIGHT PARENTHESIS, right-left + '*' # 0xAA -> ASTERISK, right-left + '+' # 0xAB -> PLUS SIGN, right-left + '\u060c' # 0xAC -> ARABIC COMMA + '-' # 0xAD -> HYPHEN-MINUS, right-left + '.' # 0xAE -> FULL STOP, right-left + '/' # 0xAF -> SOLIDUS, right-left + '\u06f0' # 0xB0 -> EXTENDED ARABIC-INDIC DIGIT ZERO, right-left (need override) + '\u06f1' # 0xB1 -> EXTENDED ARABIC-INDIC DIGIT ONE, right-left (need override) + '\u06f2' # 0xB2 -> EXTENDED ARABIC-INDIC DIGIT TWO, right-left (need override) + '\u06f3' # 0xB3 -> EXTENDED ARABIC-INDIC DIGIT THREE, right-left (need override) + '\u06f4' # 0xB4 -> EXTENDED ARABIC-INDIC DIGIT FOUR, right-left (need override) + '\u06f5' # 0xB5 -> EXTENDED ARABIC-INDIC DIGIT FIVE, right-left (need override) + '\u06f6' # 0xB6 -> EXTENDED ARABIC-INDIC DIGIT SIX, right-left (need override) + '\u06f7' # 0xB7 -> EXTENDED ARABIC-INDIC DIGIT SEVEN, right-left (need override) + '\u06f8' # 0xB8 -> EXTENDED ARABIC-INDIC DIGIT EIGHT, right-left (need override) + '\u06f9' # 0xB9 -> EXTENDED ARABIC-INDIC DIGIT NINE, right-left (need override) + ':' # 0xBA -> COLON, right-left + '\u061b' # 0xBB -> ARABIC SEMICOLON + '<' # 0xBC -> LESS-THAN SIGN, right-left + '=' # 0xBD -> EQUALS SIGN, right-left + '>' # 0xBE -> GREATER-THAN SIGN, right-left + '\u061f' # 0xBF -> ARABIC QUESTION MARK + '\u274a' # 0xC0 -> EIGHT TEARDROP-SPOKED PROPELLER ASTERISK, right-left + '\u0621' # 0xC1 -> ARABIC LETTER HAMZA + '\u0622' # 0xC2 -> ARABIC LETTER ALEF WITH MADDA ABOVE + '\u0623' # 0xC3 -> ARABIC LETTER ALEF WITH HAMZA ABOVE + '\u0624' # 0xC4 -> ARABIC LETTER WAW WITH HAMZA ABOVE + '\u0625' # 0xC5 -> ARABIC LETTER ALEF WITH HAMZA BELOW + '\u0626' # 0xC6 -> ARABIC LETTER YEH WITH HAMZA ABOVE + '\u0627' # 0xC7 -> ARABIC LETTER ALEF + '\u0628' # 0xC8 -> ARABIC LETTER BEH + '\u0629' # 0xC9 -> ARABIC LETTER TEH MARBUTA + '\u062a' # 0xCA -> ARABIC LETTER TEH + '\u062b' # 0xCB -> ARABIC LETTER THEH + '\u062c' # 0xCC -> ARABIC LETTER JEEM + '\u062d' # 0xCD -> ARABIC LETTER HAH + '\u062e' # 0xCE -> ARABIC LETTER KHAH + '\u062f' # 0xCF -> ARABIC LETTER DAL + '\u0630' # 0xD0 -> ARABIC LETTER THAL + '\u0631' # 0xD1 -> ARABIC LETTER REH + '\u0632' # 0xD2 -> ARABIC LETTER ZAIN + '\u0633' # 0xD3 -> ARABIC LETTER SEEN + '\u0634' # 0xD4 -> ARABIC LETTER SHEEN + '\u0635' # 0xD5 -> ARABIC LETTER SAD + '\u0636' # 0xD6 -> ARABIC LETTER DAD + '\u0637' # 0xD7 -> ARABIC LETTER TAH + '\u0638' # 0xD8 -> ARABIC LETTER ZAH + '\u0639' # 0xD9 -> ARABIC LETTER AIN + '\u063a' # 0xDA -> ARABIC LETTER GHAIN + '[' # 0xDB -> LEFT SQUARE BRACKET, right-left + '\\' # 0xDC -> REVERSE SOLIDUS, right-left + ']' # 0xDD -> RIGHT SQUARE BRACKET, right-left + '^' # 0xDE -> CIRCUMFLEX ACCENT, right-left + '_' # 0xDF -> LOW LINE, right-left + '\u0640' # 0xE0 -> ARABIC TATWEEL + '\u0641' # 0xE1 -> ARABIC LETTER FEH + '\u0642' # 0xE2 -> ARABIC LETTER QAF + '\u0643' # 0xE3 -> ARABIC LETTER KAF + '\u0644' # 0xE4 -> ARABIC LETTER LAM + '\u0645' # 0xE5 -> ARABIC LETTER MEEM + '\u0646' # 0xE6 -> ARABIC LETTER NOON + '\u0647' # 0xE7 -> ARABIC LETTER HEH + '\u0648' # 0xE8 -> ARABIC LETTER WAW + '\u0649' # 0xE9 -> ARABIC LETTER ALEF MAKSURA + '\u064a' # 0xEA -> ARABIC LETTER YEH + '\u064b' # 0xEB -> ARABIC FATHATAN + '\u064c' # 0xEC -> ARABIC DAMMATAN + '\u064d' # 0xED -> ARABIC KASRATAN + '\u064e' # 0xEE -> ARABIC FATHA + '\u064f' # 0xEF -> ARABIC DAMMA + '\u0650' # 0xF0 -> ARABIC KASRA + '\u0651' # 0xF1 -> ARABIC SHADDA + '\u0652' # 0xF2 -> ARABIC SUKUN + '\u067e' # 0xF3 -> ARABIC LETTER PEH + '\u0679' # 0xF4 -> ARABIC LETTER TTEH + '\u0686' # 0xF5 -> ARABIC LETTER TCHEH + '\u06d5' # 0xF6 -> ARABIC LETTER AE + '\u06a4' # 0xF7 -> ARABIC LETTER VEH + '\u06af' # 0xF8 -> ARABIC LETTER GAF + '\u0688' # 0xF9 -> ARABIC LETTER DDAL + '\u0691' # 0xFA -> ARABIC LETTER RREH + '{' # 0xFB -> LEFT CURLY BRACKET, right-left + '|' # 0xFC -> VERTICAL LINE, right-left + '}' # 0xFD -> RIGHT CURLY BRACKET, right-left + '\u0698' # 0xFE -> ARABIC LETTER JEH + '\u06d2' # 0xFF -> ARABIC LETTER YEH BARREE +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/mac_greek.py b/contrib/tools/python3/src/Lib/encodings/mac_greek.py new file mode 100644 index 0000000000..d3d0c4f0c3 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/mac_greek.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec mac_greek generated from 'MAPPINGS/VENDORS/APPLE/GREEK.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='mac-greek', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> CONTROL CHARACTER + '\x01' # 0x01 -> CONTROL CHARACTER + '\x02' # 0x02 -> CONTROL CHARACTER + '\x03' # 0x03 -> CONTROL CHARACTER + '\x04' # 0x04 -> CONTROL CHARACTER + '\x05' # 0x05 -> CONTROL CHARACTER + '\x06' # 0x06 -> CONTROL CHARACTER + '\x07' # 0x07 -> CONTROL CHARACTER + '\x08' # 0x08 -> CONTROL CHARACTER + '\t' # 0x09 -> CONTROL CHARACTER + '\n' # 0x0A -> CONTROL CHARACTER + '\x0b' # 0x0B -> CONTROL CHARACTER + '\x0c' # 0x0C -> CONTROL CHARACTER + '\r' # 0x0D -> CONTROL CHARACTER + '\x0e' # 0x0E -> CONTROL CHARACTER + '\x0f' # 0x0F -> CONTROL CHARACTER + '\x10' # 0x10 -> CONTROL CHARACTER + '\x11' # 0x11 -> CONTROL CHARACTER + '\x12' # 0x12 -> CONTROL CHARACTER + '\x13' # 0x13 -> CONTROL CHARACTER + '\x14' # 0x14 -> CONTROL CHARACTER + '\x15' # 0x15 -> CONTROL CHARACTER + '\x16' # 0x16 -> CONTROL CHARACTER + '\x17' # 0x17 -> CONTROL CHARACTER + '\x18' # 0x18 -> CONTROL CHARACTER + '\x19' # 0x19 -> CONTROL CHARACTER + '\x1a' # 0x1A -> CONTROL CHARACTER + '\x1b' # 0x1B -> CONTROL CHARACTER + '\x1c' # 0x1C -> CONTROL CHARACTER + '\x1d' # 0x1D -> CONTROL CHARACTER + '\x1e' # 0x1E -> CONTROL CHARACTER + '\x1f' # 0x1F -> CONTROL CHARACTER + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> CONTROL CHARACTER + '\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xb9' # 0x81 -> SUPERSCRIPT ONE + '\xb2' # 0x82 -> SUPERSCRIPT TWO + '\xc9' # 0x83 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xb3' # 0x84 -> SUPERSCRIPT THREE + '\xd6' # 0x85 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xdc' # 0x86 -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\u0385' # 0x87 -> GREEK DIALYTIKA TONOS + '\xe0' # 0x88 -> LATIN SMALL LETTER A WITH GRAVE + '\xe2' # 0x89 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS + '\u0384' # 0x8B -> GREEK TONOS + '\xa8' # 0x8C -> DIAERESIS + '\xe7' # 0x8D -> LATIN SMALL LETTER C WITH CEDILLA + '\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE + '\xe8' # 0x8F -> LATIN SMALL LETTER E WITH GRAVE + '\xea' # 0x90 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0x91 -> LATIN SMALL LETTER E WITH DIAERESIS + '\xa3' # 0x92 -> POUND SIGN + '\u2122' # 0x93 -> TRADE MARK SIGN + '\xee' # 0x94 -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0x95 -> LATIN SMALL LETTER I WITH DIAERESIS + '\u2022' # 0x96 -> BULLET + '\xbd' # 0x97 -> VULGAR FRACTION ONE HALF + '\u2030' # 0x98 -> PER MILLE SIGN + '\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS + '\xa6' # 0x9B -> BROKEN BAR + '\u20ac' # 0x9C -> EURO SIGN # before Mac OS 9.2.2, was SOFT HYPHEN + '\xf9' # 0x9D -> LATIN SMALL LETTER U WITH GRAVE + '\xfb' # 0x9E -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS + '\u2020' # 0xA0 -> DAGGER + '\u0393' # 0xA1 -> GREEK CAPITAL LETTER GAMMA + '\u0394' # 0xA2 -> GREEK CAPITAL LETTER DELTA + '\u0398' # 0xA3 -> GREEK CAPITAL LETTER THETA + '\u039b' # 0xA4 -> GREEK CAPITAL LETTER LAMDA + '\u039e' # 0xA5 -> GREEK CAPITAL LETTER XI + '\u03a0' # 0xA6 -> GREEK CAPITAL LETTER PI + '\xdf' # 0xA7 -> LATIN SMALL LETTER SHARP S + '\xae' # 0xA8 -> REGISTERED SIGN + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\u03a3' # 0xAA -> GREEK CAPITAL LETTER SIGMA + '\u03aa' # 0xAB -> GREEK CAPITAL LETTER IOTA WITH DIALYTIKA + '\xa7' # 0xAC -> SECTION SIGN + '\u2260' # 0xAD -> NOT EQUAL TO + '\xb0' # 0xAE -> DEGREE SIGN + '\xb7' # 0xAF -> MIDDLE DOT + '\u0391' # 0xB0 -> GREEK CAPITAL LETTER ALPHA + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO + '\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO + '\xa5' # 0xB4 -> YEN SIGN + '\u0392' # 0xB5 -> GREEK CAPITAL LETTER BETA + '\u0395' # 0xB6 -> GREEK CAPITAL LETTER EPSILON + '\u0396' # 0xB7 -> GREEK CAPITAL LETTER ZETA + '\u0397' # 0xB8 -> GREEK CAPITAL LETTER ETA + '\u0399' # 0xB9 -> GREEK CAPITAL LETTER IOTA + '\u039a' # 0xBA -> GREEK CAPITAL LETTER KAPPA + '\u039c' # 0xBB -> GREEK CAPITAL LETTER MU + '\u03a6' # 0xBC -> GREEK CAPITAL LETTER PHI + '\u03ab' # 0xBD -> GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA + '\u03a8' # 0xBE -> GREEK CAPITAL LETTER PSI + '\u03a9' # 0xBF -> GREEK CAPITAL LETTER OMEGA + '\u03ac' # 0xC0 -> GREEK SMALL LETTER ALPHA WITH TONOS + '\u039d' # 0xC1 -> GREEK CAPITAL LETTER NU + '\xac' # 0xC2 -> NOT SIGN + '\u039f' # 0xC3 -> GREEK CAPITAL LETTER OMICRON + '\u03a1' # 0xC4 -> GREEK CAPITAL LETTER RHO + '\u2248' # 0xC5 -> ALMOST EQUAL TO + '\u03a4' # 0xC6 -> GREEK CAPITAL LETTER TAU + '\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0xC8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS + '\xa0' # 0xCA -> NO-BREAK SPACE + '\u03a5' # 0xCB -> GREEK CAPITAL LETTER UPSILON + '\u03a7' # 0xCC -> GREEK CAPITAL LETTER CHI + '\u0386' # 0xCD -> GREEK CAPITAL LETTER ALPHA WITH TONOS + '\u0388' # 0xCE -> GREEK CAPITAL LETTER EPSILON WITH TONOS + '\u0153' # 0xCF -> LATIN SMALL LIGATURE OE + '\u2013' # 0xD0 -> EN DASH + '\u2015' # 0xD1 -> HORIZONTAL BAR + '\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK + '\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK + '\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK + '\xf7' # 0xD6 -> DIVISION SIGN + '\u0389' # 0xD7 -> GREEK CAPITAL LETTER ETA WITH TONOS + '\u038a' # 0xD8 -> GREEK CAPITAL LETTER IOTA WITH TONOS + '\u038c' # 0xD9 -> GREEK CAPITAL LETTER OMICRON WITH TONOS + '\u038e' # 0xDA -> GREEK CAPITAL LETTER UPSILON WITH TONOS + '\u03ad' # 0xDB -> GREEK SMALL LETTER EPSILON WITH TONOS + '\u03ae' # 0xDC -> GREEK SMALL LETTER ETA WITH TONOS + '\u03af' # 0xDD -> GREEK SMALL LETTER IOTA WITH TONOS + '\u03cc' # 0xDE -> GREEK SMALL LETTER OMICRON WITH TONOS + '\u038f' # 0xDF -> GREEK CAPITAL LETTER OMEGA WITH TONOS + '\u03cd' # 0xE0 -> GREEK SMALL LETTER UPSILON WITH TONOS + '\u03b1' # 0xE1 -> GREEK SMALL LETTER ALPHA + '\u03b2' # 0xE2 -> GREEK SMALL LETTER BETA + '\u03c8' # 0xE3 -> GREEK SMALL LETTER PSI + '\u03b4' # 0xE4 -> GREEK SMALL LETTER DELTA + '\u03b5' # 0xE5 -> GREEK SMALL LETTER EPSILON + '\u03c6' # 0xE6 -> GREEK SMALL LETTER PHI + '\u03b3' # 0xE7 -> GREEK SMALL LETTER GAMMA + '\u03b7' # 0xE8 -> GREEK SMALL LETTER ETA + '\u03b9' # 0xE9 -> GREEK SMALL LETTER IOTA + '\u03be' # 0xEA -> GREEK SMALL LETTER XI + '\u03ba' # 0xEB -> GREEK SMALL LETTER KAPPA + '\u03bb' # 0xEC -> GREEK SMALL LETTER LAMDA + '\u03bc' # 0xED -> GREEK SMALL LETTER MU + '\u03bd' # 0xEE -> GREEK SMALL LETTER NU + '\u03bf' # 0xEF -> GREEK SMALL LETTER OMICRON + '\u03c0' # 0xF0 -> GREEK SMALL LETTER PI + '\u03ce' # 0xF1 -> GREEK SMALL LETTER OMEGA WITH TONOS + '\u03c1' # 0xF2 -> GREEK SMALL LETTER RHO + '\u03c3' # 0xF3 -> GREEK SMALL LETTER SIGMA + '\u03c4' # 0xF4 -> GREEK SMALL LETTER TAU + '\u03b8' # 0xF5 -> GREEK SMALL LETTER THETA + '\u03c9' # 0xF6 -> GREEK SMALL LETTER OMEGA + '\u03c2' # 0xF7 -> GREEK SMALL LETTER FINAL SIGMA + '\u03c7' # 0xF8 -> GREEK SMALL LETTER CHI + '\u03c5' # 0xF9 -> GREEK SMALL LETTER UPSILON + '\u03b6' # 0xFA -> GREEK SMALL LETTER ZETA + '\u03ca' # 0xFB -> GREEK SMALL LETTER IOTA WITH DIALYTIKA + '\u03cb' # 0xFC -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA + '\u0390' # 0xFD -> GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS + '\u03b0' # 0xFE -> GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS + '\xad' # 0xFF -> SOFT HYPHEN # before Mac OS 9.2.2, was undefined +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/mac_iceland.py b/contrib/tools/python3/src/Lib/encodings/mac_iceland.py new file mode 100644 index 0000000000..add10f4e55 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/mac_iceland.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec mac_iceland generated from 'MAPPINGS/VENDORS/APPLE/ICELAND.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='mac-iceland', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> CONTROL CHARACTER + '\x01' # 0x01 -> CONTROL CHARACTER + '\x02' # 0x02 -> CONTROL CHARACTER + '\x03' # 0x03 -> CONTROL CHARACTER + '\x04' # 0x04 -> CONTROL CHARACTER + '\x05' # 0x05 -> CONTROL CHARACTER + '\x06' # 0x06 -> CONTROL CHARACTER + '\x07' # 0x07 -> CONTROL CHARACTER + '\x08' # 0x08 -> CONTROL CHARACTER + '\t' # 0x09 -> CONTROL CHARACTER + '\n' # 0x0A -> CONTROL CHARACTER + '\x0b' # 0x0B -> CONTROL CHARACTER + '\x0c' # 0x0C -> CONTROL CHARACTER + '\r' # 0x0D -> CONTROL CHARACTER + '\x0e' # 0x0E -> CONTROL CHARACTER + '\x0f' # 0x0F -> CONTROL CHARACTER + '\x10' # 0x10 -> CONTROL CHARACTER + '\x11' # 0x11 -> CONTROL CHARACTER + '\x12' # 0x12 -> CONTROL CHARACTER + '\x13' # 0x13 -> CONTROL CHARACTER + '\x14' # 0x14 -> CONTROL CHARACTER + '\x15' # 0x15 -> CONTROL CHARACTER + '\x16' # 0x16 -> CONTROL CHARACTER + '\x17' # 0x17 -> CONTROL CHARACTER + '\x18' # 0x18 -> CONTROL CHARACTER + '\x19' # 0x19 -> CONTROL CHARACTER + '\x1a' # 0x1A -> CONTROL CHARACTER + '\x1b' # 0x1B -> CONTROL CHARACTER + '\x1c' # 0x1C -> CONTROL CHARACTER + '\x1d' # 0x1D -> CONTROL CHARACTER + '\x1e' # 0x1E -> CONTROL CHARACTER + '\x1f' # 0x1F -> CONTROL CHARACTER + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> CONTROL CHARACTER + '\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0x81 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc7' # 0x82 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xc9' # 0x83 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xd1' # 0x84 -> LATIN CAPITAL LETTER N WITH TILDE + '\xd6' # 0x85 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xdc' # 0x86 -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xe1' # 0x87 -> LATIN SMALL LETTER A WITH ACUTE + '\xe0' # 0x88 -> LATIN SMALL LETTER A WITH GRAVE + '\xe2' # 0x89 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe3' # 0x8B -> LATIN SMALL LETTER A WITH TILDE + '\xe5' # 0x8C -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe7' # 0x8D -> LATIN SMALL LETTER C WITH CEDILLA + '\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE + '\xe8' # 0x8F -> LATIN SMALL LETTER E WITH GRAVE + '\xea' # 0x90 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0x91 -> LATIN SMALL LETTER E WITH DIAERESIS + '\xed' # 0x92 -> LATIN SMALL LETTER I WITH ACUTE + '\xec' # 0x93 -> LATIN SMALL LETTER I WITH GRAVE + '\xee' # 0x94 -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0x95 -> LATIN SMALL LETTER I WITH DIAERESIS + '\xf1' # 0x96 -> LATIN SMALL LETTER N WITH TILDE + '\xf3' # 0x97 -> LATIN SMALL LETTER O WITH ACUTE + '\xf2' # 0x98 -> LATIN SMALL LETTER O WITH GRAVE + '\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf5' # 0x9B -> LATIN SMALL LETTER O WITH TILDE + '\xfa' # 0x9C -> LATIN SMALL LETTER U WITH ACUTE + '\xf9' # 0x9D -> LATIN SMALL LETTER U WITH GRAVE + '\xfb' # 0x9E -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS + '\xdd' # 0xA0 -> LATIN CAPITAL LETTER Y WITH ACUTE + '\xb0' # 0xA1 -> DEGREE SIGN + '\xa2' # 0xA2 -> CENT SIGN + '\xa3' # 0xA3 -> POUND SIGN + '\xa7' # 0xA4 -> SECTION SIGN + '\u2022' # 0xA5 -> BULLET + '\xb6' # 0xA6 -> PILCROW SIGN + '\xdf' # 0xA7 -> LATIN SMALL LETTER SHARP S + '\xae' # 0xA8 -> REGISTERED SIGN + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\u2122' # 0xAA -> TRADE MARK SIGN + '\xb4' # 0xAB -> ACUTE ACCENT + '\xa8' # 0xAC -> DIAERESIS + '\u2260' # 0xAD -> NOT EQUAL TO + '\xc6' # 0xAE -> LATIN CAPITAL LETTER AE + '\xd8' # 0xAF -> LATIN CAPITAL LETTER O WITH STROKE + '\u221e' # 0xB0 -> INFINITY + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO + '\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO + '\xa5' # 0xB4 -> YEN SIGN + '\xb5' # 0xB5 -> MICRO SIGN + '\u2202' # 0xB6 -> PARTIAL DIFFERENTIAL + '\u2211' # 0xB7 -> N-ARY SUMMATION + '\u220f' # 0xB8 -> N-ARY PRODUCT + '\u03c0' # 0xB9 -> GREEK SMALL LETTER PI + '\u222b' # 0xBA -> INTEGRAL + '\xaa' # 0xBB -> FEMININE ORDINAL INDICATOR + '\xba' # 0xBC -> MASCULINE ORDINAL INDICATOR + '\u03a9' # 0xBD -> GREEK CAPITAL LETTER OMEGA + '\xe6' # 0xBE -> LATIN SMALL LETTER AE + '\xf8' # 0xBF -> LATIN SMALL LETTER O WITH STROKE + '\xbf' # 0xC0 -> INVERTED QUESTION MARK + '\xa1' # 0xC1 -> INVERTED EXCLAMATION MARK + '\xac' # 0xC2 -> NOT SIGN + '\u221a' # 0xC3 -> SQUARE ROOT + '\u0192' # 0xC4 -> LATIN SMALL LETTER F WITH HOOK + '\u2248' # 0xC5 -> ALMOST EQUAL TO + '\u2206' # 0xC6 -> INCREMENT + '\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0xC8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS + '\xa0' # 0xCA -> NO-BREAK SPACE + '\xc0' # 0xCB -> LATIN CAPITAL LETTER A WITH GRAVE + '\xc3' # 0xCC -> LATIN CAPITAL LETTER A WITH TILDE + '\xd5' # 0xCD -> LATIN CAPITAL LETTER O WITH TILDE + '\u0152' # 0xCE -> LATIN CAPITAL LIGATURE OE + '\u0153' # 0xCF -> LATIN SMALL LIGATURE OE + '\u2013' # 0xD0 -> EN DASH + '\u2014' # 0xD1 -> EM DASH + '\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK + '\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK + '\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK + '\xf7' # 0xD6 -> DIVISION SIGN + '\u25ca' # 0xD7 -> LOZENGE + '\xff' # 0xD8 -> LATIN SMALL LETTER Y WITH DIAERESIS + '\u0178' # 0xD9 -> LATIN CAPITAL LETTER Y WITH DIAERESIS + '\u2044' # 0xDA -> FRACTION SLASH + '\u20ac' # 0xDB -> EURO SIGN + '\xd0' # 0xDC -> LATIN CAPITAL LETTER ETH + '\xf0' # 0xDD -> LATIN SMALL LETTER ETH + '\xde' # 0xDE -> LATIN CAPITAL LETTER THORN + '\xfe' # 0xDF -> LATIN SMALL LETTER THORN + '\xfd' # 0xE0 -> LATIN SMALL LETTER Y WITH ACUTE + '\xb7' # 0xE1 -> MIDDLE DOT + '\u201a' # 0xE2 -> SINGLE LOW-9 QUOTATION MARK + '\u201e' # 0xE3 -> DOUBLE LOW-9 QUOTATION MARK + '\u2030' # 0xE4 -> PER MILLE SIGN + '\xc2' # 0xE5 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xca' # 0xE6 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xc1' # 0xE7 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xcb' # 0xE8 -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xc8' # 0xE9 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xcd' # 0xEA -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0xEB -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0xEC -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\xcc' # 0xED -> LATIN CAPITAL LETTER I WITH GRAVE + '\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd4' # 0xEF -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\uf8ff' # 0xF0 -> Apple logo + '\xd2' # 0xF1 -> LATIN CAPITAL LETTER O WITH GRAVE + '\xda' # 0xF2 -> LATIN CAPITAL LETTER U WITH ACUTE + '\xdb' # 0xF3 -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xd9' # 0xF4 -> LATIN CAPITAL LETTER U WITH GRAVE + '\u0131' # 0xF5 -> LATIN SMALL LETTER DOTLESS I + '\u02c6' # 0xF6 -> MODIFIER LETTER CIRCUMFLEX ACCENT + '\u02dc' # 0xF7 -> SMALL TILDE + '\xaf' # 0xF8 -> MACRON + '\u02d8' # 0xF9 -> BREVE + '\u02d9' # 0xFA -> DOT ABOVE + '\u02da' # 0xFB -> RING ABOVE + '\xb8' # 0xFC -> CEDILLA + '\u02dd' # 0xFD -> DOUBLE ACUTE ACCENT + '\u02db' # 0xFE -> OGONEK + '\u02c7' # 0xFF -> CARON +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/mac_latin2.py b/contrib/tools/python3/src/Lib/encodings/mac_latin2.py new file mode 100644 index 0000000000..da9d4b134a --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/mac_latin2.py @@ -0,0 +1,312 @@ +""" Python Character Mapping Codec mac_latin2 generated from 'MAPPINGS/VENDORS/MICSFT/MAC/LATIN2.TXT' with gencodec.py. + +Written by Marc-Andre Lemburg (mal@lemburg.com). + +(c) Copyright CNRI, All Rights Reserved. NO WARRANTY. +(c) Copyright 2000 Guido van Rossum. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='mac-latin2', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\u0100' # 0x81 -> LATIN CAPITAL LETTER A WITH MACRON + '\u0101' # 0x82 -> LATIN SMALL LETTER A WITH MACRON + '\xc9' # 0x83 -> LATIN CAPITAL LETTER E WITH ACUTE + '\u0104' # 0x84 -> LATIN CAPITAL LETTER A WITH OGONEK + '\xd6' # 0x85 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xdc' # 0x86 -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xe1' # 0x87 -> LATIN SMALL LETTER A WITH ACUTE + '\u0105' # 0x88 -> LATIN SMALL LETTER A WITH OGONEK + '\u010c' # 0x89 -> LATIN CAPITAL LETTER C WITH CARON + '\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS + '\u010d' # 0x8B -> LATIN SMALL LETTER C WITH CARON + '\u0106' # 0x8C -> LATIN CAPITAL LETTER C WITH ACUTE + '\u0107' # 0x8D -> LATIN SMALL LETTER C WITH ACUTE + '\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE + '\u0179' # 0x8F -> LATIN CAPITAL LETTER Z WITH ACUTE + '\u017a' # 0x90 -> LATIN SMALL LETTER Z WITH ACUTE + '\u010e' # 0x91 -> LATIN CAPITAL LETTER D WITH CARON + '\xed' # 0x92 -> LATIN SMALL LETTER I WITH ACUTE + '\u010f' # 0x93 -> LATIN SMALL LETTER D WITH CARON + '\u0112' # 0x94 -> LATIN CAPITAL LETTER E WITH MACRON + '\u0113' # 0x95 -> LATIN SMALL LETTER E WITH MACRON + '\u0116' # 0x96 -> LATIN CAPITAL LETTER E WITH DOT ABOVE + '\xf3' # 0x97 -> LATIN SMALL LETTER O WITH ACUTE + '\u0117' # 0x98 -> LATIN SMALL LETTER E WITH DOT ABOVE + '\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf5' # 0x9B -> LATIN SMALL LETTER O WITH TILDE + '\xfa' # 0x9C -> LATIN SMALL LETTER U WITH ACUTE + '\u011a' # 0x9D -> LATIN CAPITAL LETTER E WITH CARON + '\u011b' # 0x9E -> LATIN SMALL LETTER E WITH CARON + '\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS + '\u2020' # 0xA0 -> DAGGER + '\xb0' # 0xA1 -> DEGREE SIGN + '\u0118' # 0xA2 -> LATIN CAPITAL LETTER E WITH OGONEK + '\xa3' # 0xA3 -> POUND SIGN + '\xa7' # 0xA4 -> SECTION SIGN + '\u2022' # 0xA5 -> BULLET + '\xb6' # 0xA6 -> PILCROW SIGN + '\xdf' # 0xA7 -> LATIN SMALL LETTER SHARP S + '\xae' # 0xA8 -> REGISTERED SIGN + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\u2122' # 0xAA -> TRADE MARK SIGN + '\u0119' # 0xAB -> LATIN SMALL LETTER E WITH OGONEK + '\xa8' # 0xAC -> DIAERESIS + '\u2260' # 0xAD -> NOT EQUAL TO + '\u0123' # 0xAE -> LATIN SMALL LETTER G WITH CEDILLA + '\u012e' # 0xAF -> LATIN CAPITAL LETTER I WITH OGONEK + '\u012f' # 0xB0 -> LATIN SMALL LETTER I WITH OGONEK + '\u012a' # 0xB1 -> LATIN CAPITAL LETTER I WITH MACRON + '\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO + '\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO + '\u012b' # 0xB4 -> LATIN SMALL LETTER I WITH MACRON + '\u0136' # 0xB5 -> LATIN CAPITAL LETTER K WITH CEDILLA + '\u2202' # 0xB6 -> PARTIAL DIFFERENTIAL + '\u2211' # 0xB7 -> N-ARY SUMMATION + '\u0142' # 0xB8 -> LATIN SMALL LETTER L WITH STROKE + '\u013b' # 0xB9 -> LATIN CAPITAL LETTER L WITH CEDILLA + '\u013c' # 0xBA -> LATIN SMALL LETTER L WITH CEDILLA + '\u013d' # 0xBB -> LATIN CAPITAL LETTER L WITH CARON + '\u013e' # 0xBC -> LATIN SMALL LETTER L WITH CARON + '\u0139' # 0xBD -> LATIN CAPITAL LETTER L WITH ACUTE + '\u013a' # 0xBE -> LATIN SMALL LETTER L WITH ACUTE + '\u0145' # 0xBF -> LATIN CAPITAL LETTER N WITH CEDILLA + '\u0146' # 0xC0 -> LATIN SMALL LETTER N WITH CEDILLA + '\u0143' # 0xC1 -> LATIN CAPITAL LETTER N WITH ACUTE + '\xac' # 0xC2 -> NOT SIGN + '\u221a' # 0xC3 -> SQUARE ROOT + '\u0144' # 0xC4 -> LATIN SMALL LETTER N WITH ACUTE + '\u0147' # 0xC5 -> LATIN CAPITAL LETTER N WITH CARON + '\u2206' # 0xC6 -> INCREMENT + '\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0xC8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS + '\xa0' # 0xCA -> NO-BREAK SPACE + '\u0148' # 0xCB -> LATIN SMALL LETTER N WITH CARON + '\u0150' # 0xCC -> LATIN CAPITAL LETTER O WITH DOUBLE ACUTE + '\xd5' # 0xCD -> LATIN CAPITAL LETTER O WITH TILDE + '\u0151' # 0xCE -> LATIN SMALL LETTER O WITH DOUBLE ACUTE + '\u014c' # 0xCF -> LATIN CAPITAL LETTER O WITH MACRON + '\u2013' # 0xD0 -> EN DASH + '\u2014' # 0xD1 -> EM DASH + '\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK + '\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK + '\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK + '\xf7' # 0xD6 -> DIVISION SIGN + '\u25ca' # 0xD7 -> LOZENGE + '\u014d' # 0xD8 -> LATIN SMALL LETTER O WITH MACRON + '\u0154' # 0xD9 -> LATIN CAPITAL LETTER R WITH ACUTE + '\u0155' # 0xDA -> LATIN SMALL LETTER R WITH ACUTE + '\u0158' # 0xDB -> LATIN CAPITAL LETTER R WITH CARON + '\u2039' # 0xDC -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + '\u203a' # 0xDD -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + '\u0159' # 0xDE -> LATIN SMALL LETTER R WITH CARON + '\u0156' # 0xDF -> LATIN CAPITAL LETTER R WITH CEDILLA + '\u0157' # 0xE0 -> LATIN SMALL LETTER R WITH CEDILLA + '\u0160' # 0xE1 -> LATIN CAPITAL LETTER S WITH CARON + '\u201a' # 0xE2 -> SINGLE LOW-9 QUOTATION MARK + '\u201e' # 0xE3 -> DOUBLE LOW-9 QUOTATION MARK + '\u0161' # 0xE4 -> LATIN SMALL LETTER S WITH CARON + '\u015a' # 0xE5 -> LATIN CAPITAL LETTER S WITH ACUTE + '\u015b' # 0xE6 -> LATIN SMALL LETTER S WITH ACUTE + '\xc1' # 0xE7 -> LATIN CAPITAL LETTER A WITH ACUTE + '\u0164' # 0xE8 -> LATIN CAPITAL LETTER T WITH CARON + '\u0165' # 0xE9 -> LATIN SMALL LETTER T WITH CARON + '\xcd' # 0xEA -> LATIN CAPITAL LETTER I WITH ACUTE + '\u017d' # 0xEB -> LATIN CAPITAL LETTER Z WITH CARON + '\u017e' # 0xEC -> LATIN SMALL LETTER Z WITH CARON + '\u016a' # 0xED -> LATIN CAPITAL LETTER U WITH MACRON + '\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd4' # 0xEF -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\u016b' # 0xF0 -> LATIN SMALL LETTER U WITH MACRON + '\u016e' # 0xF1 -> LATIN CAPITAL LETTER U WITH RING ABOVE + '\xda' # 0xF2 -> LATIN CAPITAL LETTER U WITH ACUTE + '\u016f' # 0xF3 -> LATIN SMALL LETTER U WITH RING ABOVE + '\u0170' # 0xF4 -> LATIN CAPITAL LETTER U WITH DOUBLE ACUTE + '\u0171' # 0xF5 -> LATIN SMALL LETTER U WITH DOUBLE ACUTE + '\u0172' # 0xF6 -> LATIN CAPITAL LETTER U WITH OGONEK + '\u0173' # 0xF7 -> LATIN SMALL LETTER U WITH OGONEK + '\xdd' # 0xF8 -> LATIN CAPITAL LETTER Y WITH ACUTE + '\xfd' # 0xF9 -> LATIN SMALL LETTER Y WITH ACUTE + '\u0137' # 0xFA -> LATIN SMALL LETTER K WITH CEDILLA + '\u017b' # 0xFB -> LATIN CAPITAL LETTER Z WITH DOT ABOVE + '\u0141' # 0xFC -> LATIN CAPITAL LETTER L WITH STROKE + '\u017c' # 0xFD -> LATIN SMALL LETTER Z WITH DOT ABOVE + '\u0122' # 0xFE -> LATIN CAPITAL LETTER G WITH CEDILLA + '\u02c7' # 0xFF -> CARON +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/mac_roman.py b/contrib/tools/python3/src/Lib/encodings/mac_roman.py new file mode 100644 index 0000000000..b74b002134 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/mac_roman.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec mac_roman generated from 'MAPPINGS/VENDORS/APPLE/ROMAN.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='mac-roman', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> CONTROL CHARACTER + '\x01' # 0x01 -> CONTROL CHARACTER + '\x02' # 0x02 -> CONTROL CHARACTER + '\x03' # 0x03 -> CONTROL CHARACTER + '\x04' # 0x04 -> CONTROL CHARACTER + '\x05' # 0x05 -> CONTROL CHARACTER + '\x06' # 0x06 -> CONTROL CHARACTER + '\x07' # 0x07 -> CONTROL CHARACTER + '\x08' # 0x08 -> CONTROL CHARACTER + '\t' # 0x09 -> CONTROL CHARACTER + '\n' # 0x0A -> CONTROL CHARACTER + '\x0b' # 0x0B -> CONTROL CHARACTER + '\x0c' # 0x0C -> CONTROL CHARACTER + '\r' # 0x0D -> CONTROL CHARACTER + '\x0e' # 0x0E -> CONTROL CHARACTER + '\x0f' # 0x0F -> CONTROL CHARACTER + '\x10' # 0x10 -> CONTROL CHARACTER + '\x11' # 0x11 -> CONTROL CHARACTER + '\x12' # 0x12 -> CONTROL CHARACTER + '\x13' # 0x13 -> CONTROL CHARACTER + '\x14' # 0x14 -> CONTROL CHARACTER + '\x15' # 0x15 -> CONTROL CHARACTER + '\x16' # 0x16 -> CONTROL CHARACTER + '\x17' # 0x17 -> CONTROL CHARACTER + '\x18' # 0x18 -> CONTROL CHARACTER + '\x19' # 0x19 -> CONTROL CHARACTER + '\x1a' # 0x1A -> CONTROL CHARACTER + '\x1b' # 0x1B -> CONTROL CHARACTER + '\x1c' # 0x1C -> CONTROL CHARACTER + '\x1d' # 0x1D -> CONTROL CHARACTER + '\x1e' # 0x1E -> CONTROL CHARACTER + '\x1f' # 0x1F -> CONTROL CHARACTER + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> CONTROL CHARACTER + '\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0x81 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc7' # 0x82 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xc9' # 0x83 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xd1' # 0x84 -> LATIN CAPITAL LETTER N WITH TILDE + '\xd6' # 0x85 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xdc' # 0x86 -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xe1' # 0x87 -> LATIN SMALL LETTER A WITH ACUTE + '\xe0' # 0x88 -> LATIN SMALL LETTER A WITH GRAVE + '\xe2' # 0x89 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe3' # 0x8B -> LATIN SMALL LETTER A WITH TILDE + '\xe5' # 0x8C -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe7' # 0x8D -> LATIN SMALL LETTER C WITH CEDILLA + '\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE + '\xe8' # 0x8F -> LATIN SMALL LETTER E WITH GRAVE + '\xea' # 0x90 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0x91 -> LATIN SMALL LETTER E WITH DIAERESIS + '\xed' # 0x92 -> LATIN SMALL LETTER I WITH ACUTE + '\xec' # 0x93 -> LATIN SMALL LETTER I WITH GRAVE + '\xee' # 0x94 -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0x95 -> LATIN SMALL LETTER I WITH DIAERESIS + '\xf1' # 0x96 -> LATIN SMALL LETTER N WITH TILDE + '\xf3' # 0x97 -> LATIN SMALL LETTER O WITH ACUTE + '\xf2' # 0x98 -> LATIN SMALL LETTER O WITH GRAVE + '\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf5' # 0x9B -> LATIN SMALL LETTER O WITH TILDE + '\xfa' # 0x9C -> LATIN SMALL LETTER U WITH ACUTE + '\xf9' # 0x9D -> LATIN SMALL LETTER U WITH GRAVE + '\xfb' # 0x9E -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS + '\u2020' # 0xA0 -> DAGGER + '\xb0' # 0xA1 -> DEGREE SIGN + '\xa2' # 0xA2 -> CENT SIGN + '\xa3' # 0xA3 -> POUND SIGN + '\xa7' # 0xA4 -> SECTION SIGN + '\u2022' # 0xA5 -> BULLET + '\xb6' # 0xA6 -> PILCROW SIGN + '\xdf' # 0xA7 -> LATIN SMALL LETTER SHARP S + '\xae' # 0xA8 -> REGISTERED SIGN + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\u2122' # 0xAA -> TRADE MARK SIGN + '\xb4' # 0xAB -> ACUTE ACCENT + '\xa8' # 0xAC -> DIAERESIS + '\u2260' # 0xAD -> NOT EQUAL TO + '\xc6' # 0xAE -> LATIN CAPITAL LETTER AE + '\xd8' # 0xAF -> LATIN CAPITAL LETTER O WITH STROKE + '\u221e' # 0xB0 -> INFINITY + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO + '\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO + '\xa5' # 0xB4 -> YEN SIGN + '\xb5' # 0xB5 -> MICRO SIGN + '\u2202' # 0xB6 -> PARTIAL DIFFERENTIAL + '\u2211' # 0xB7 -> N-ARY SUMMATION + '\u220f' # 0xB8 -> N-ARY PRODUCT + '\u03c0' # 0xB9 -> GREEK SMALL LETTER PI + '\u222b' # 0xBA -> INTEGRAL + '\xaa' # 0xBB -> FEMININE ORDINAL INDICATOR + '\xba' # 0xBC -> MASCULINE ORDINAL INDICATOR + '\u03a9' # 0xBD -> GREEK CAPITAL LETTER OMEGA + '\xe6' # 0xBE -> LATIN SMALL LETTER AE + '\xf8' # 0xBF -> LATIN SMALL LETTER O WITH STROKE + '\xbf' # 0xC0 -> INVERTED QUESTION MARK + '\xa1' # 0xC1 -> INVERTED EXCLAMATION MARK + '\xac' # 0xC2 -> NOT SIGN + '\u221a' # 0xC3 -> SQUARE ROOT + '\u0192' # 0xC4 -> LATIN SMALL LETTER F WITH HOOK + '\u2248' # 0xC5 -> ALMOST EQUAL TO + '\u2206' # 0xC6 -> INCREMENT + '\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0xC8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS + '\xa0' # 0xCA -> NO-BREAK SPACE + '\xc0' # 0xCB -> LATIN CAPITAL LETTER A WITH GRAVE + '\xc3' # 0xCC -> LATIN CAPITAL LETTER A WITH TILDE + '\xd5' # 0xCD -> LATIN CAPITAL LETTER O WITH TILDE + '\u0152' # 0xCE -> LATIN CAPITAL LIGATURE OE + '\u0153' # 0xCF -> LATIN SMALL LIGATURE OE + '\u2013' # 0xD0 -> EN DASH + '\u2014' # 0xD1 -> EM DASH + '\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK + '\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK + '\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK + '\xf7' # 0xD6 -> DIVISION SIGN + '\u25ca' # 0xD7 -> LOZENGE + '\xff' # 0xD8 -> LATIN SMALL LETTER Y WITH DIAERESIS + '\u0178' # 0xD9 -> LATIN CAPITAL LETTER Y WITH DIAERESIS + '\u2044' # 0xDA -> FRACTION SLASH + '\u20ac' # 0xDB -> EURO SIGN + '\u2039' # 0xDC -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + '\u203a' # 0xDD -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + '\ufb01' # 0xDE -> LATIN SMALL LIGATURE FI + '\ufb02' # 0xDF -> LATIN SMALL LIGATURE FL + '\u2021' # 0xE0 -> DOUBLE DAGGER + '\xb7' # 0xE1 -> MIDDLE DOT + '\u201a' # 0xE2 -> SINGLE LOW-9 QUOTATION MARK + '\u201e' # 0xE3 -> DOUBLE LOW-9 QUOTATION MARK + '\u2030' # 0xE4 -> PER MILLE SIGN + '\xc2' # 0xE5 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xca' # 0xE6 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xc1' # 0xE7 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xcb' # 0xE8 -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xc8' # 0xE9 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xcd' # 0xEA -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0xEB -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0xEC -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\xcc' # 0xED -> LATIN CAPITAL LETTER I WITH GRAVE + '\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd4' # 0xEF -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\uf8ff' # 0xF0 -> Apple logo + '\xd2' # 0xF1 -> LATIN CAPITAL LETTER O WITH GRAVE + '\xda' # 0xF2 -> LATIN CAPITAL LETTER U WITH ACUTE + '\xdb' # 0xF3 -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xd9' # 0xF4 -> LATIN CAPITAL LETTER U WITH GRAVE + '\u0131' # 0xF5 -> LATIN SMALL LETTER DOTLESS I + '\u02c6' # 0xF6 -> MODIFIER LETTER CIRCUMFLEX ACCENT + '\u02dc' # 0xF7 -> SMALL TILDE + '\xaf' # 0xF8 -> MACRON + '\u02d8' # 0xF9 -> BREVE + '\u02d9' # 0xFA -> DOT ABOVE + '\u02da' # 0xFB -> RING ABOVE + '\xb8' # 0xFC -> CEDILLA + '\u02dd' # 0xFD -> DOUBLE ACUTE ACCENT + '\u02db' # 0xFE -> OGONEK + '\u02c7' # 0xFF -> CARON +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/mac_romanian.py b/contrib/tools/python3/src/Lib/encodings/mac_romanian.py new file mode 100644 index 0000000000..d141b4c509 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/mac_romanian.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec mac_romanian generated from 'MAPPINGS/VENDORS/APPLE/ROMANIAN.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='mac-romanian', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> CONTROL CHARACTER + '\x01' # 0x01 -> CONTROL CHARACTER + '\x02' # 0x02 -> CONTROL CHARACTER + '\x03' # 0x03 -> CONTROL CHARACTER + '\x04' # 0x04 -> CONTROL CHARACTER + '\x05' # 0x05 -> CONTROL CHARACTER + '\x06' # 0x06 -> CONTROL CHARACTER + '\x07' # 0x07 -> CONTROL CHARACTER + '\x08' # 0x08 -> CONTROL CHARACTER + '\t' # 0x09 -> CONTROL CHARACTER + '\n' # 0x0A -> CONTROL CHARACTER + '\x0b' # 0x0B -> CONTROL CHARACTER + '\x0c' # 0x0C -> CONTROL CHARACTER + '\r' # 0x0D -> CONTROL CHARACTER + '\x0e' # 0x0E -> CONTROL CHARACTER + '\x0f' # 0x0F -> CONTROL CHARACTER + '\x10' # 0x10 -> CONTROL CHARACTER + '\x11' # 0x11 -> CONTROL CHARACTER + '\x12' # 0x12 -> CONTROL CHARACTER + '\x13' # 0x13 -> CONTROL CHARACTER + '\x14' # 0x14 -> CONTROL CHARACTER + '\x15' # 0x15 -> CONTROL CHARACTER + '\x16' # 0x16 -> CONTROL CHARACTER + '\x17' # 0x17 -> CONTROL CHARACTER + '\x18' # 0x18 -> CONTROL CHARACTER + '\x19' # 0x19 -> CONTROL CHARACTER + '\x1a' # 0x1A -> CONTROL CHARACTER + '\x1b' # 0x1B -> CONTROL CHARACTER + '\x1c' # 0x1C -> CONTROL CHARACTER + '\x1d' # 0x1D -> CONTROL CHARACTER + '\x1e' # 0x1E -> CONTROL CHARACTER + '\x1f' # 0x1F -> CONTROL CHARACTER + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> CONTROL CHARACTER + '\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0x81 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc7' # 0x82 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xc9' # 0x83 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xd1' # 0x84 -> LATIN CAPITAL LETTER N WITH TILDE + '\xd6' # 0x85 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xdc' # 0x86 -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xe1' # 0x87 -> LATIN SMALL LETTER A WITH ACUTE + '\xe0' # 0x88 -> LATIN SMALL LETTER A WITH GRAVE + '\xe2' # 0x89 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe3' # 0x8B -> LATIN SMALL LETTER A WITH TILDE + '\xe5' # 0x8C -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe7' # 0x8D -> LATIN SMALL LETTER C WITH CEDILLA + '\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE + '\xe8' # 0x8F -> LATIN SMALL LETTER E WITH GRAVE + '\xea' # 0x90 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0x91 -> LATIN SMALL LETTER E WITH DIAERESIS + '\xed' # 0x92 -> LATIN SMALL LETTER I WITH ACUTE + '\xec' # 0x93 -> LATIN SMALL LETTER I WITH GRAVE + '\xee' # 0x94 -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0x95 -> LATIN SMALL LETTER I WITH DIAERESIS + '\xf1' # 0x96 -> LATIN SMALL LETTER N WITH TILDE + '\xf3' # 0x97 -> LATIN SMALL LETTER O WITH ACUTE + '\xf2' # 0x98 -> LATIN SMALL LETTER O WITH GRAVE + '\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf5' # 0x9B -> LATIN SMALL LETTER O WITH TILDE + '\xfa' # 0x9C -> LATIN SMALL LETTER U WITH ACUTE + '\xf9' # 0x9D -> LATIN SMALL LETTER U WITH GRAVE + '\xfb' # 0x9E -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS + '\u2020' # 0xA0 -> DAGGER + '\xb0' # 0xA1 -> DEGREE SIGN + '\xa2' # 0xA2 -> CENT SIGN + '\xa3' # 0xA3 -> POUND SIGN + '\xa7' # 0xA4 -> SECTION SIGN + '\u2022' # 0xA5 -> BULLET + '\xb6' # 0xA6 -> PILCROW SIGN + '\xdf' # 0xA7 -> LATIN SMALL LETTER SHARP S + '\xae' # 0xA8 -> REGISTERED SIGN + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\u2122' # 0xAA -> TRADE MARK SIGN + '\xb4' # 0xAB -> ACUTE ACCENT + '\xa8' # 0xAC -> DIAERESIS + '\u2260' # 0xAD -> NOT EQUAL TO + '\u0102' # 0xAE -> LATIN CAPITAL LETTER A WITH BREVE + '\u0218' # 0xAF -> LATIN CAPITAL LETTER S WITH COMMA BELOW # for Unicode 3.0 and later + '\u221e' # 0xB0 -> INFINITY + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO + '\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO + '\xa5' # 0xB4 -> YEN SIGN + '\xb5' # 0xB5 -> MICRO SIGN + '\u2202' # 0xB6 -> PARTIAL DIFFERENTIAL + '\u2211' # 0xB7 -> N-ARY SUMMATION + '\u220f' # 0xB8 -> N-ARY PRODUCT + '\u03c0' # 0xB9 -> GREEK SMALL LETTER PI + '\u222b' # 0xBA -> INTEGRAL + '\xaa' # 0xBB -> FEMININE ORDINAL INDICATOR + '\xba' # 0xBC -> MASCULINE ORDINAL INDICATOR + '\u03a9' # 0xBD -> GREEK CAPITAL LETTER OMEGA + '\u0103' # 0xBE -> LATIN SMALL LETTER A WITH BREVE + '\u0219' # 0xBF -> LATIN SMALL LETTER S WITH COMMA BELOW # for Unicode 3.0 and later + '\xbf' # 0xC0 -> INVERTED QUESTION MARK + '\xa1' # 0xC1 -> INVERTED EXCLAMATION MARK + '\xac' # 0xC2 -> NOT SIGN + '\u221a' # 0xC3 -> SQUARE ROOT + '\u0192' # 0xC4 -> LATIN SMALL LETTER F WITH HOOK + '\u2248' # 0xC5 -> ALMOST EQUAL TO + '\u2206' # 0xC6 -> INCREMENT + '\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0xC8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS + '\xa0' # 0xCA -> NO-BREAK SPACE + '\xc0' # 0xCB -> LATIN CAPITAL LETTER A WITH GRAVE + '\xc3' # 0xCC -> LATIN CAPITAL LETTER A WITH TILDE + '\xd5' # 0xCD -> LATIN CAPITAL LETTER O WITH TILDE + '\u0152' # 0xCE -> LATIN CAPITAL LIGATURE OE + '\u0153' # 0xCF -> LATIN SMALL LIGATURE OE + '\u2013' # 0xD0 -> EN DASH + '\u2014' # 0xD1 -> EM DASH + '\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK + '\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK + '\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK + '\xf7' # 0xD6 -> DIVISION SIGN + '\u25ca' # 0xD7 -> LOZENGE + '\xff' # 0xD8 -> LATIN SMALL LETTER Y WITH DIAERESIS + '\u0178' # 0xD9 -> LATIN CAPITAL LETTER Y WITH DIAERESIS + '\u2044' # 0xDA -> FRACTION SLASH + '\u20ac' # 0xDB -> EURO SIGN + '\u2039' # 0xDC -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + '\u203a' # 0xDD -> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + '\u021a' # 0xDE -> LATIN CAPITAL LETTER T WITH COMMA BELOW # for Unicode 3.0 and later + '\u021b' # 0xDF -> LATIN SMALL LETTER T WITH COMMA BELOW # for Unicode 3.0 and later + '\u2021' # 0xE0 -> DOUBLE DAGGER + '\xb7' # 0xE1 -> MIDDLE DOT + '\u201a' # 0xE2 -> SINGLE LOW-9 QUOTATION MARK + '\u201e' # 0xE3 -> DOUBLE LOW-9 QUOTATION MARK + '\u2030' # 0xE4 -> PER MILLE SIGN + '\xc2' # 0xE5 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xca' # 0xE6 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xc1' # 0xE7 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xcb' # 0xE8 -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xc8' # 0xE9 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xcd' # 0xEA -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0xEB -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0xEC -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\xcc' # 0xED -> LATIN CAPITAL LETTER I WITH GRAVE + '\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd4' # 0xEF -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\uf8ff' # 0xF0 -> Apple logo + '\xd2' # 0xF1 -> LATIN CAPITAL LETTER O WITH GRAVE + '\xda' # 0xF2 -> LATIN CAPITAL LETTER U WITH ACUTE + '\xdb' # 0xF3 -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xd9' # 0xF4 -> LATIN CAPITAL LETTER U WITH GRAVE + '\u0131' # 0xF5 -> LATIN SMALL LETTER DOTLESS I + '\u02c6' # 0xF6 -> MODIFIER LETTER CIRCUMFLEX ACCENT + '\u02dc' # 0xF7 -> SMALL TILDE + '\xaf' # 0xF8 -> MACRON + '\u02d8' # 0xF9 -> BREVE + '\u02d9' # 0xFA -> DOT ABOVE + '\u02da' # 0xFB -> RING ABOVE + '\xb8' # 0xFC -> CEDILLA + '\u02dd' # 0xFD -> DOUBLE ACUTE ACCENT + '\u02db' # 0xFE -> OGONEK + '\u02c7' # 0xFF -> CARON +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/mac_turkish.py b/contrib/tools/python3/src/Lib/encodings/mac_turkish.py new file mode 100644 index 0000000000..044d4cb5ad --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/mac_turkish.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec mac_turkish generated from 'MAPPINGS/VENDORS/APPLE/TURKISH.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='mac-turkish', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> CONTROL CHARACTER + '\x01' # 0x01 -> CONTROL CHARACTER + '\x02' # 0x02 -> CONTROL CHARACTER + '\x03' # 0x03 -> CONTROL CHARACTER + '\x04' # 0x04 -> CONTROL CHARACTER + '\x05' # 0x05 -> CONTROL CHARACTER + '\x06' # 0x06 -> CONTROL CHARACTER + '\x07' # 0x07 -> CONTROL CHARACTER + '\x08' # 0x08 -> CONTROL CHARACTER + '\t' # 0x09 -> CONTROL CHARACTER + '\n' # 0x0A -> CONTROL CHARACTER + '\x0b' # 0x0B -> CONTROL CHARACTER + '\x0c' # 0x0C -> CONTROL CHARACTER + '\r' # 0x0D -> CONTROL CHARACTER + '\x0e' # 0x0E -> CONTROL CHARACTER + '\x0f' # 0x0F -> CONTROL CHARACTER + '\x10' # 0x10 -> CONTROL CHARACTER + '\x11' # 0x11 -> CONTROL CHARACTER + '\x12' # 0x12 -> CONTROL CHARACTER + '\x13' # 0x13 -> CONTROL CHARACTER + '\x14' # 0x14 -> CONTROL CHARACTER + '\x15' # 0x15 -> CONTROL CHARACTER + '\x16' # 0x16 -> CONTROL CHARACTER + '\x17' # 0x17 -> CONTROL CHARACTER + '\x18' # 0x18 -> CONTROL CHARACTER + '\x19' # 0x19 -> CONTROL CHARACTER + '\x1a' # 0x1A -> CONTROL CHARACTER + '\x1b' # 0x1B -> CONTROL CHARACTER + '\x1c' # 0x1C -> CONTROL CHARACTER + '\x1d' # 0x1D -> CONTROL CHARACTER + '\x1e' # 0x1E -> CONTROL CHARACTER + '\x1f' # 0x1F -> CONTROL CHARACTER + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> CONTROL CHARACTER + '\xc4' # 0x80 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0x81 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc7' # 0x82 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xc9' # 0x83 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xd1' # 0x84 -> LATIN CAPITAL LETTER N WITH TILDE + '\xd6' # 0x85 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xdc' # 0x86 -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xe1' # 0x87 -> LATIN SMALL LETTER A WITH ACUTE + '\xe0' # 0x88 -> LATIN SMALL LETTER A WITH GRAVE + '\xe2' # 0x89 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe4' # 0x8A -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe3' # 0x8B -> LATIN SMALL LETTER A WITH TILDE + '\xe5' # 0x8C -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe7' # 0x8D -> LATIN SMALL LETTER C WITH CEDILLA + '\xe9' # 0x8E -> LATIN SMALL LETTER E WITH ACUTE + '\xe8' # 0x8F -> LATIN SMALL LETTER E WITH GRAVE + '\xea' # 0x90 -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0x91 -> LATIN SMALL LETTER E WITH DIAERESIS + '\xed' # 0x92 -> LATIN SMALL LETTER I WITH ACUTE + '\xec' # 0x93 -> LATIN SMALL LETTER I WITH GRAVE + '\xee' # 0x94 -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0x95 -> LATIN SMALL LETTER I WITH DIAERESIS + '\xf1' # 0x96 -> LATIN SMALL LETTER N WITH TILDE + '\xf3' # 0x97 -> LATIN SMALL LETTER O WITH ACUTE + '\xf2' # 0x98 -> LATIN SMALL LETTER O WITH GRAVE + '\xf4' # 0x99 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf6' # 0x9A -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf5' # 0x9B -> LATIN SMALL LETTER O WITH TILDE + '\xfa' # 0x9C -> LATIN SMALL LETTER U WITH ACUTE + '\xf9' # 0x9D -> LATIN SMALL LETTER U WITH GRAVE + '\xfb' # 0x9E -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0x9F -> LATIN SMALL LETTER U WITH DIAERESIS + '\u2020' # 0xA0 -> DAGGER + '\xb0' # 0xA1 -> DEGREE SIGN + '\xa2' # 0xA2 -> CENT SIGN + '\xa3' # 0xA3 -> POUND SIGN + '\xa7' # 0xA4 -> SECTION SIGN + '\u2022' # 0xA5 -> BULLET + '\xb6' # 0xA6 -> PILCROW SIGN + '\xdf' # 0xA7 -> LATIN SMALL LETTER SHARP S + '\xae' # 0xA8 -> REGISTERED SIGN + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\u2122' # 0xAA -> TRADE MARK SIGN + '\xb4' # 0xAB -> ACUTE ACCENT + '\xa8' # 0xAC -> DIAERESIS + '\u2260' # 0xAD -> NOT EQUAL TO + '\xc6' # 0xAE -> LATIN CAPITAL LETTER AE + '\xd8' # 0xAF -> LATIN CAPITAL LETTER O WITH STROKE + '\u221e' # 0xB0 -> INFINITY + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\u2264' # 0xB2 -> LESS-THAN OR EQUAL TO + '\u2265' # 0xB3 -> GREATER-THAN OR EQUAL TO + '\xa5' # 0xB4 -> YEN SIGN + '\xb5' # 0xB5 -> MICRO SIGN + '\u2202' # 0xB6 -> PARTIAL DIFFERENTIAL + '\u2211' # 0xB7 -> N-ARY SUMMATION + '\u220f' # 0xB8 -> N-ARY PRODUCT + '\u03c0' # 0xB9 -> GREEK SMALL LETTER PI + '\u222b' # 0xBA -> INTEGRAL + '\xaa' # 0xBB -> FEMININE ORDINAL INDICATOR + '\xba' # 0xBC -> MASCULINE ORDINAL INDICATOR + '\u03a9' # 0xBD -> GREEK CAPITAL LETTER OMEGA + '\xe6' # 0xBE -> LATIN SMALL LETTER AE + '\xf8' # 0xBF -> LATIN SMALL LETTER O WITH STROKE + '\xbf' # 0xC0 -> INVERTED QUESTION MARK + '\xa1' # 0xC1 -> INVERTED EXCLAMATION MARK + '\xac' # 0xC2 -> NOT SIGN + '\u221a' # 0xC3 -> SQUARE ROOT + '\u0192' # 0xC4 -> LATIN SMALL LETTER F WITH HOOK + '\u2248' # 0xC5 -> ALMOST EQUAL TO + '\u2206' # 0xC6 -> INCREMENT + '\xab' # 0xC7 -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbb' # 0xC8 -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u2026' # 0xC9 -> HORIZONTAL ELLIPSIS + '\xa0' # 0xCA -> NO-BREAK SPACE + '\xc0' # 0xCB -> LATIN CAPITAL LETTER A WITH GRAVE + '\xc3' # 0xCC -> LATIN CAPITAL LETTER A WITH TILDE + '\xd5' # 0xCD -> LATIN CAPITAL LETTER O WITH TILDE + '\u0152' # 0xCE -> LATIN CAPITAL LIGATURE OE + '\u0153' # 0xCF -> LATIN SMALL LIGATURE OE + '\u2013' # 0xD0 -> EN DASH + '\u2014' # 0xD1 -> EM DASH + '\u201c' # 0xD2 -> LEFT DOUBLE QUOTATION MARK + '\u201d' # 0xD3 -> RIGHT DOUBLE QUOTATION MARK + '\u2018' # 0xD4 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0xD5 -> RIGHT SINGLE QUOTATION MARK + '\xf7' # 0xD6 -> DIVISION SIGN + '\u25ca' # 0xD7 -> LOZENGE + '\xff' # 0xD8 -> LATIN SMALL LETTER Y WITH DIAERESIS + '\u0178' # 0xD9 -> LATIN CAPITAL LETTER Y WITH DIAERESIS + '\u011e' # 0xDA -> LATIN CAPITAL LETTER G WITH BREVE + '\u011f' # 0xDB -> LATIN SMALL LETTER G WITH BREVE + '\u0130' # 0xDC -> LATIN CAPITAL LETTER I WITH DOT ABOVE + '\u0131' # 0xDD -> LATIN SMALL LETTER DOTLESS I + '\u015e' # 0xDE -> LATIN CAPITAL LETTER S WITH CEDILLA + '\u015f' # 0xDF -> LATIN SMALL LETTER S WITH CEDILLA + '\u2021' # 0xE0 -> DOUBLE DAGGER + '\xb7' # 0xE1 -> MIDDLE DOT + '\u201a' # 0xE2 -> SINGLE LOW-9 QUOTATION MARK + '\u201e' # 0xE3 -> DOUBLE LOW-9 QUOTATION MARK + '\u2030' # 0xE4 -> PER MILLE SIGN + '\xc2' # 0xE5 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xca' # 0xE6 -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xc1' # 0xE7 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xcb' # 0xE8 -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xc8' # 0xE9 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xcd' # 0xEA -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0xEB -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0xEC -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\xcc' # 0xED -> LATIN CAPITAL LETTER I WITH GRAVE + '\xd3' # 0xEE -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd4' # 0xEF -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\uf8ff' # 0xF0 -> Apple logo + '\xd2' # 0xF1 -> LATIN CAPITAL LETTER O WITH GRAVE + '\xda' # 0xF2 -> LATIN CAPITAL LETTER U WITH ACUTE + '\xdb' # 0xF3 -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xd9' # 0xF4 -> LATIN CAPITAL LETTER U WITH GRAVE + '\uf8a0' # 0xF5 -> undefined1 + '\u02c6' # 0xF6 -> MODIFIER LETTER CIRCUMFLEX ACCENT + '\u02dc' # 0xF7 -> SMALL TILDE + '\xaf' # 0xF8 -> MACRON + '\u02d8' # 0xF9 -> BREVE + '\u02d9' # 0xFA -> DOT ABOVE + '\u02da' # 0xFB -> RING ABOVE + '\xb8' # 0xFC -> CEDILLA + '\u02dd' # 0xFD -> DOUBLE ACUTE ACCENT + '\u02db' # 0xFE -> OGONEK + '\u02c7' # 0xFF -> CARON +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/mbcs.py b/contrib/tools/python3/src/Lib/encodings/mbcs.py new file mode 100644 index 0000000000..baf46cbd48 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/mbcs.py @@ -0,0 +1,47 @@ +""" Python 'mbcs' Codec for Windows + + +Cloned by Mark Hammond (mhammond@skippinet.com.au) from ascii.py, +which was written by Marc-Andre Lemburg (mal@lemburg.com). + +(c) Copyright CNRI, All Rights Reserved. NO WARRANTY. + +""" +# Import them explicitly to cause an ImportError +# on non-Windows systems +from codecs import mbcs_encode, mbcs_decode +# for IncrementalDecoder, IncrementalEncoder, ... +import codecs + +### Codec APIs + +encode = mbcs_encode + +def decode(input, errors='strict'): + return mbcs_decode(input, errors, True) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return mbcs_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.BufferedIncrementalDecoder): + _buffer_decode = mbcs_decode + +class StreamWriter(codecs.StreamWriter): + encode = mbcs_encode + +class StreamReader(codecs.StreamReader): + decode = mbcs_decode + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='mbcs', + encode=encode, + decode=decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/oem.py b/contrib/tools/python3/src/Lib/encodings/oem.py new file mode 100644 index 0000000000..2c3426ba48 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/oem.py @@ -0,0 +1,41 @@ +""" Python 'oem' Codec for Windows + +""" +# Import them explicitly to cause an ImportError +# on non-Windows systems +from codecs import oem_encode, oem_decode +# for IncrementalDecoder, IncrementalEncoder, ... +import codecs + +### Codec APIs + +encode = oem_encode + +def decode(input, errors='strict'): + return oem_decode(input, errors, True) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return oem_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.BufferedIncrementalDecoder): + _buffer_decode = oem_decode + +class StreamWriter(codecs.StreamWriter): + encode = oem_encode + +class StreamReader(codecs.StreamReader): + decode = oem_decode + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='oem', + encode=encode, + decode=decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/palmos.py b/contrib/tools/python3/src/Lib/encodings/palmos.py new file mode 100644 index 0000000000..c506d65452 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/palmos.py @@ -0,0 +1,308 @@ +""" Python Character Mapping Codec for PalmOS 3.5. + +Written by Sjoerd Mullender (sjoerd@acm.org); based on iso8859_15.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='palmos', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\u20ac' # 0x80 -> EURO SIGN + '\x81' # 0x81 -> <control> + '\u201a' # 0x82 -> SINGLE LOW-9 QUOTATION MARK + '\u0192' # 0x83 -> LATIN SMALL LETTER F WITH HOOK + '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK + '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS + '\u2020' # 0x86 -> DAGGER + '\u2021' # 0x87 -> DOUBLE DAGGER + '\u02c6' # 0x88 -> MODIFIER LETTER CIRCUMFLEX ACCENT + '\u2030' # 0x89 -> PER MILLE SIGN + '\u0160' # 0x8A -> LATIN CAPITAL LETTER S WITH CARON + '\u2039' # 0x8B -> SINGLE LEFT-POINTING ANGLE QUOTATION MARK + '\u0152' # 0x8C -> LATIN CAPITAL LIGATURE OE + '\u2666' # 0x8D -> BLACK DIAMOND SUIT + '\u2663' # 0x8E -> BLACK CLUB SUIT + '\u2665' # 0x8F -> BLACK HEART SUIT + '\u2660' # 0x90 -> BLACK SPADE SUIT + '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK + '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK + '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK + '\u2022' # 0x95 -> BULLET + '\u2013' # 0x96 -> EN DASH + '\u2014' # 0x97 -> EM DASH + '\u02dc' # 0x98 -> SMALL TILDE + '\u2122' # 0x99 -> TRADE MARK SIGN + '\u0161' # 0x9A -> LATIN SMALL LETTER S WITH CARON + '\x9b' # 0x9B -> <control> + '\u0153' # 0x9C -> LATIN SMALL LIGATURE OE + '\x9d' # 0x9D -> <control> + '\x9e' # 0x9E -> <control> + '\u0178' # 0x9F -> LATIN CAPITAL LETTER Y WITH DIAERESIS + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\xa1' # 0xA1 -> INVERTED EXCLAMATION MARK + '\xa2' # 0xA2 -> CENT SIGN + '\xa3' # 0xA3 -> POUND SIGN + '\xa4' # 0xA4 -> CURRENCY SIGN + '\xa5' # 0xA5 -> YEN SIGN + '\xa6' # 0xA6 -> BROKEN BAR + '\xa7' # 0xA7 -> SECTION SIGN + '\xa8' # 0xA8 -> DIAERESIS + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\xaa' # 0xAA -> FEMININE ORDINAL INDICATOR + '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xac' # 0xAC -> NOT SIGN + '\xad' # 0xAD -> SOFT HYPHEN + '\xae' # 0xAE -> REGISTERED SIGN + '\xaf' # 0xAF -> MACRON + '\xb0' # 0xB0 -> DEGREE SIGN + '\xb1' # 0xB1 -> PLUS-MINUS SIGN + '\xb2' # 0xB2 -> SUPERSCRIPT TWO + '\xb3' # 0xB3 -> SUPERSCRIPT THREE + '\xb4' # 0xB4 -> ACUTE ACCENT + '\xb5' # 0xB5 -> MICRO SIGN + '\xb6' # 0xB6 -> PILCROW SIGN + '\xb7' # 0xB7 -> MIDDLE DOT + '\xb8' # 0xB8 -> CEDILLA + '\xb9' # 0xB9 -> SUPERSCRIPT ONE + '\xba' # 0xBA -> MASCULINE ORDINAL INDICATOR + '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xbc' # 0xBC -> VULGAR FRACTION ONE QUARTER + '\xbd' # 0xBD -> VULGAR FRACTION ONE HALF + '\xbe' # 0xBE -> VULGAR FRACTION THREE QUARTERS + '\xbf' # 0xBF -> INVERTED QUESTION MARK + '\xc0' # 0xC0 -> LATIN CAPITAL LETTER A WITH GRAVE + '\xc1' # 0xC1 -> LATIN CAPITAL LETTER A WITH ACUTE + '\xc2' # 0xC2 -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX + '\xc3' # 0xC3 -> LATIN CAPITAL LETTER A WITH TILDE + '\xc4' # 0xC4 -> LATIN CAPITAL LETTER A WITH DIAERESIS + '\xc5' # 0xC5 -> LATIN CAPITAL LETTER A WITH RING ABOVE + '\xc6' # 0xC6 -> LATIN CAPITAL LETTER AE + '\xc7' # 0xC7 -> LATIN CAPITAL LETTER C WITH CEDILLA + '\xc8' # 0xC8 -> LATIN CAPITAL LETTER E WITH GRAVE + '\xc9' # 0xC9 -> LATIN CAPITAL LETTER E WITH ACUTE + '\xca' # 0xCA -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX + '\xcb' # 0xCB -> LATIN CAPITAL LETTER E WITH DIAERESIS + '\xcc' # 0xCC -> LATIN CAPITAL LETTER I WITH GRAVE + '\xcd' # 0xCD -> LATIN CAPITAL LETTER I WITH ACUTE + '\xce' # 0xCE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX + '\xcf' # 0xCF -> LATIN CAPITAL LETTER I WITH DIAERESIS + '\xd0' # 0xD0 -> LATIN CAPITAL LETTER ETH (Icelandic) + '\xd1' # 0xD1 -> LATIN CAPITAL LETTER N WITH TILDE + '\xd2' # 0xD2 -> LATIN CAPITAL LETTER O WITH GRAVE + '\xd3' # 0xD3 -> LATIN CAPITAL LETTER O WITH ACUTE + '\xd4' # 0xD4 -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX + '\xd5' # 0xD5 -> LATIN CAPITAL LETTER O WITH TILDE + '\xd6' # 0xD6 -> LATIN CAPITAL LETTER O WITH DIAERESIS + '\xd7' # 0xD7 -> MULTIPLICATION SIGN + '\xd8' # 0xD8 -> LATIN CAPITAL LETTER O WITH STROKE + '\xd9' # 0xD9 -> LATIN CAPITAL LETTER U WITH GRAVE + '\xda' # 0xDA -> LATIN CAPITAL LETTER U WITH ACUTE + '\xdb' # 0xDB -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX + '\xdc' # 0xDC -> LATIN CAPITAL LETTER U WITH DIAERESIS + '\xdd' # 0xDD -> LATIN CAPITAL LETTER Y WITH ACUTE + '\xde' # 0xDE -> LATIN CAPITAL LETTER THORN (Icelandic) + '\xdf' # 0xDF -> LATIN SMALL LETTER SHARP S (German) + '\xe0' # 0xE0 -> LATIN SMALL LETTER A WITH GRAVE + '\xe1' # 0xE1 -> LATIN SMALL LETTER A WITH ACUTE + '\xe2' # 0xE2 -> LATIN SMALL LETTER A WITH CIRCUMFLEX + '\xe3' # 0xE3 -> LATIN SMALL LETTER A WITH TILDE + '\xe4' # 0xE4 -> LATIN SMALL LETTER A WITH DIAERESIS + '\xe5' # 0xE5 -> LATIN SMALL LETTER A WITH RING ABOVE + '\xe6' # 0xE6 -> LATIN SMALL LETTER AE + '\xe7' # 0xE7 -> LATIN SMALL LETTER C WITH CEDILLA + '\xe8' # 0xE8 -> LATIN SMALL LETTER E WITH GRAVE + '\xe9' # 0xE9 -> LATIN SMALL LETTER E WITH ACUTE + '\xea' # 0xEA -> LATIN SMALL LETTER E WITH CIRCUMFLEX + '\xeb' # 0xEB -> LATIN SMALL LETTER E WITH DIAERESIS + '\xec' # 0xEC -> LATIN SMALL LETTER I WITH GRAVE + '\xed' # 0xED -> LATIN SMALL LETTER I WITH ACUTE + '\xee' # 0xEE -> LATIN SMALL LETTER I WITH CIRCUMFLEX + '\xef' # 0xEF -> LATIN SMALL LETTER I WITH DIAERESIS + '\xf0' # 0xF0 -> LATIN SMALL LETTER ETH (Icelandic) + '\xf1' # 0xF1 -> LATIN SMALL LETTER N WITH TILDE + '\xf2' # 0xF2 -> LATIN SMALL LETTER O WITH GRAVE + '\xf3' # 0xF3 -> LATIN SMALL LETTER O WITH ACUTE + '\xf4' # 0xF4 -> LATIN SMALL LETTER O WITH CIRCUMFLEX + '\xf5' # 0xF5 -> LATIN SMALL LETTER O WITH TILDE + '\xf6' # 0xF6 -> LATIN SMALL LETTER O WITH DIAERESIS + '\xf7' # 0xF7 -> DIVISION SIGN + '\xf8' # 0xF8 -> LATIN SMALL LETTER O WITH STROKE + '\xf9' # 0xF9 -> LATIN SMALL LETTER U WITH GRAVE + '\xfa' # 0xFA -> LATIN SMALL LETTER U WITH ACUTE + '\xfb' # 0xFB -> LATIN SMALL LETTER U WITH CIRCUMFLEX + '\xfc' # 0xFC -> LATIN SMALL LETTER U WITH DIAERESIS + '\xfd' # 0xFD -> LATIN SMALL LETTER Y WITH ACUTE + '\xfe' # 0xFE -> LATIN SMALL LETTER THORN (Icelandic) + '\xff' # 0xFF -> LATIN SMALL LETTER Y WITH DIAERESIS +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/ptcp154.py b/contrib/tools/python3/src/Lib/encodings/ptcp154.py new file mode 100644 index 0000000000..656b79d6ac --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/ptcp154.py @@ -0,0 +1,312 @@ +""" Python Character Mapping Codec generated from 'PTCP154.txt' with gencodec.py. + +Written by Marc-Andre Lemburg (mal@lemburg.com). + +(c) Copyright CNRI, All Rights Reserved. NO WARRANTY. +(c) Copyright 2000 Guido van Rossum. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='ptcp154', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE (DEL) + '\u0496' # 0x80 -> CYRILLIC CAPITAL LETTER ZHE WITH DESCENDER + '\u0492' # 0x81 -> CYRILLIC CAPITAL LETTER GHE WITH STROKE + '\u04ee' # 0x82 -> CYRILLIC CAPITAL LETTER U WITH MACRON + '\u0493' # 0x83 -> CYRILLIC SMALL LETTER GHE WITH STROKE + '\u201e' # 0x84 -> DOUBLE LOW-9 QUOTATION MARK + '\u2026' # 0x85 -> HORIZONTAL ELLIPSIS + '\u04b6' # 0x86 -> CYRILLIC CAPITAL LETTER CHE WITH DESCENDER + '\u04ae' # 0x87 -> CYRILLIC CAPITAL LETTER STRAIGHT U + '\u04b2' # 0x88 -> CYRILLIC CAPITAL LETTER HA WITH DESCENDER + '\u04af' # 0x89 -> CYRILLIC SMALL LETTER STRAIGHT U + '\u04a0' # 0x8A -> CYRILLIC CAPITAL LETTER BASHKIR KA + '\u04e2' # 0x8B -> CYRILLIC CAPITAL LETTER I WITH MACRON + '\u04a2' # 0x8C -> CYRILLIC CAPITAL LETTER EN WITH DESCENDER + '\u049a' # 0x8D -> CYRILLIC CAPITAL LETTER KA WITH DESCENDER + '\u04ba' # 0x8E -> CYRILLIC CAPITAL LETTER SHHA + '\u04b8' # 0x8F -> CYRILLIC CAPITAL LETTER CHE WITH VERTICAL STROKE + '\u0497' # 0x90 -> CYRILLIC SMALL LETTER ZHE WITH DESCENDER + '\u2018' # 0x91 -> LEFT SINGLE QUOTATION MARK + '\u2019' # 0x92 -> RIGHT SINGLE QUOTATION MARK + '\u201c' # 0x93 -> LEFT DOUBLE QUOTATION MARK + '\u201d' # 0x94 -> RIGHT DOUBLE QUOTATION MARK + '\u2022' # 0x95 -> BULLET + '\u2013' # 0x96 -> EN DASH + '\u2014' # 0x97 -> EM DASH + '\u04b3' # 0x98 -> CYRILLIC SMALL LETTER HA WITH DESCENDER + '\u04b7' # 0x99 -> CYRILLIC SMALL LETTER CHE WITH DESCENDER + '\u04a1' # 0x9A -> CYRILLIC SMALL LETTER BASHKIR KA + '\u04e3' # 0x9B -> CYRILLIC SMALL LETTER I WITH MACRON + '\u04a3' # 0x9C -> CYRILLIC SMALL LETTER EN WITH DESCENDER + '\u049b' # 0x9D -> CYRILLIC SMALL LETTER KA WITH DESCENDER + '\u04bb' # 0x9E -> CYRILLIC SMALL LETTER SHHA + '\u04b9' # 0x9F -> CYRILLIC SMALL LETTER CHE WITH VERTICAL STROKE + '\xa0' # 0xA0 -> NO-BREAK SPACE + '\u040e' # 0xA1 -> CYRILLIC CAPITAL LETTER SHORT U (Byelorussian) + '\u045e' # 0xA2 -> CYRILLIC SMALL LETTER SHORT U (Byelorussian) + '\u0408' # 0xA3 -> CYRILLIC CAPITAL LETTER JE + '\u04e8' # 0xA4 -> CYRILLIC CAPITAL LETTER BARRED O + '\u0498' # 0xA5 -> CYRILLIC CAPITAL LETTER ZE WITH DESCENDER + '\u04b0' # 0xA6 -> CYRILLIC CAPITAL LETTER STRAIGHT U WITH STROKE + '\xa7' # 0xA7 -> SECTION SIGN + '\u0401' # 0xA8 -> CYRILLIC CAPITAL LETTER IO + '\xa9' # 0xA9 -> COPYRIGHT SIGN + '\u04d8' # 0xAA -> CYRILLIC CAPITAL LETTER SCHWA + '\xab' # 0xAB -> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + '\xac' # 0xAC -> NOT SIGN + '\u04ef' # 0xAD -> CYRILLIC SMALL LETTER U WITH MACRON + '\xae' # 0xAE -> REGISTERED SIGN + '\u049c' # 0xAF -> CYRILLIC CAPITAL LETTER KA WITH VERTICAL STROKE + '\xb0' # 0xB0 -> DEGREE SIGN + '\u04b1' # 0xB1 -> CYRILLIC SMALL LETTER STRAIGHT U WITH STROKE + '\u0406' # 0xB2 -> CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I + '\u0456' # 0xB3 -> CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I + '\u0499' # 0xB4 -> CYRILLIC SMALL LETTER ZE WITH DESCENDER + '\u04e9' # 0xB5 -> CYRILLIC SMALL LETTER BARRED O + '\xb6' # 0xB6 -> PILCROW SIGN + '\xb7' # 0xB7 -> MIDDLE DOT + '\u0451' # 0xB8 -> CYRILLIC SMALL LETTER IO + '\u2116' # 0xB9 -> NUMERO SIGN + '\u04d9' # 0xBA -> CYRILLIC SMALL LETTER SCHWA + '\xbb' # 0xBB -> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + '\u0458' # 0xBC -> CYRILLIC SMALL LETTER JE + '\u04aa' # 0xBD -> CYRILLIC CAPITAL LETTER ES WITH DESCENDER + '\u04ab' # 0xBE -> CYRILLIC SMALL LETTER ES WITH DESCENDER + '\u049d' # 0xBF -> CYRILLIC SMALL LETTER KA WITH VERTICAL STROKE + '\u0410' # 0xC0 -> CYRILLIC CAPITAL LETTER A + '\u0411' # 0xC1 -> CYRILLIC CAPITAL LETTER BE + '\u0412' # 0xC2 -> CYRILLIC CAPITAL LETTER VE + '\u0413' # 0xC3 -> CYRILLIC CAPITAL LETTER GHE + '\u0414' # 0xC4 -> CYRILLIC CAPITAL LETTER DE + '\u0415' # 0xC5 -> CYRILLIC CAPITAL LETTER IE + '\u0416' # 0xC6 -> CYRILLIC CAPITAL LETTER ZHE + '\u0417' # 0xC7 -> CYRILLIC CAPITAL LETTER ZE + '\u0418' # 0xC8 -> CYRILLIC CAPITAL LETTER I + '\u0419' # 0xC9 -> CYRILLIC CAPITAL LETTER SHORT I + '\u041a' # 0xCA -> CYRILLIC CAPITAL LETTER KA + '\u041b' # 0xCB -> CYRILLIC CAPITAL LETTER EL + '\u041c' # 0xCC -> CYRILLIC CAPITAL LETTER EM + '\u041d' # 0xCD -> CYRILLIC CAPITAL LETTER EN + '\u041e' # 0xCE -> CYRILLIC CAPITAL LETTER O + '\u041f' # 0xCF -> CYRILLIC CAPITAL LETTER PE + '\u0420' # 0xD0 -> CYRILLIC CAPITAL LETTER ER + '\u0421' # 0xD1 -> CYRILLIC CAPITAL LETTER ES + '\u0422' # 0xD2 -> CYRILLIC CAPITAL LETTER TE + '\u0423' # 0xD3 -> CYRILLIC CAPITAL LETTER U + '\u0424' # 0xD4 -> CYRILLIC CAPITAL LETTER EF + '\u0425' # 0xD5 -> CYRILLIC CAPITAL LETTER HA + '\u0426' # 0xD6 -> CYRILLIC CAPITAL LETTER TSE + '\u0427' # 0xD7 -> CYRILLIC CAPITAL LETTER CHE + '\u0428' # 0xD8 -> CYRILLIC CAPITAL LETTER SHA + '\u0429' # 0xD9 -> CYRILLIC CAPITAL LETTER SHCHA + '\u042a' # 0xDA -> CYRILLIC CAPITAL LETTER HARD SIGN + '\u042b' # 0xDB -> CYRILLIC CAPITAL LETTER YERU + '\u042c' # 0xDC -> CYRILLIC CAPITAL LETTER SOFT SIGN + '\u042d' # 0xDD -> CYRILLIC CAPITAL LETTER E + '\u042e' # 0xDE -> CYRILLIC CAPITAL LETTER YU + '\u042f' # 0xDF -> CYRILLIC CAPITAL LETTER YA + '\u0430' # 0xE0 -> CYRILLIC SMALL LETTER A + '\u0431' # 0xE1 -> CYRILLIC SMALL LETTER BE + '\u0432' # 0xE2 -> CYRILLIC SMALL LETTER VE + '\u0433' # 0xE3 -> CYRILLIC SMALL LETTER GHE + '\u0434' # 0xE4 -> CYRILLIC SMALL LETTER DE + '\u0435' # 0xE5 -> CYRILLIC SMALL LETTER IE + '\u0436' # 0xE6 -> CYRILLIC SMALL LETTER ZHE + '\u0437' # 0xE7 -> CYRILLIC SMALL LETTER ZE + '\u0438' # 0xE8 -> CYRILLIC SMALL LETTER I + '\u0439' # 0xE9 -> CYRILLIC SMALL LETTER SHORT I + '\u043a' # 0xEA -> CYRILLIC SMALL LETTER KA + '\u043b' # 0xEB -> CYRILLIC SMALL LETTER EL + '\u043c' # 0xEC -> CYRILLIC SMALL LETTER EM + '\u043d' # 0xED -> CYRILLIC SMALL LETTER EN + '\u043e' # 0xEE -> CYRILLIC SMALL LETTER O + '\u043f' # 0xEF -> CYRILLIC SMALL LETTER PE + '\u0440' # 0xF0 -> CYRILLIC SMALL LETTER ER + '\u0441' # 0xF1 -> CYRILLIC SMALL LETTER ES + '\u0442' # 0xF2 -> CYRILLIC SMALL LETTER TE + '\u0443' # 0xF3 -> CYRILLIC SMALL LETTER U + '\u0444' # 0xF4 -> CYRILLIC SMALL LETTER EF + '\u0445' # 0xF5 -> CYRILLIC SMALL LETTER HA + '\u0446' # 0xF6 -> CYRILLIC SMALL LETTER TSE + '\u0447' # 0xF7 -> CYRILLIC SMALL LETTER CHE + '\u0448' # 0xF8 -> CYRILLIC SMALL LETTER SHA + '\u0449' # 0xF9 -> CYRILLIC SMALL LETTER SHCHA + '\u044a' # 0xFA -> CYRILLIC SMALL LETTER HARD SIGN + '\u044b' # 0xFB -> CYRILLIC SMALL LETTER YERU + '\u044c' # 0xFC -> CYRILLIC SMALL LETTER SOFT SIGN + '\u044d' # 0xFD -> CYRILLIC SMALL LETTER E + '\u044e' # 0xFE -> CYRILLIC SMALL LETTER YU + '\u044f' # 0xFF -> CYRILLIC SMALL LETTER YA +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/punycode.py b/contrib/tools/python3/src/Lib/encodings/punycode.py new file mode 100644 index 0000000000..1c57264470 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/punycode.py @@ -0,0 +1,237 @@ +""" Codec for the Punicode encoding, as specified in RFC 3492 + +Written by Martin v. Löwis. +""" + +import codecs + +##################### Encoding ##################################### + +def segregate(str): + """3.1 Basic code point segregation""" + base = bytearray() + extended = set() + for c in str: + if ord(c) < 128: + base.append(ord(c)) + else: + extended.add(c) + extended = sorted(extended) + return bytes(base), extended + +def selective_len(str, max): + """Return the length of str, considering only characters below max.""" + res = 0 + for c in str: + if ord(c) < max: + res += 1 + return res + +def selective_find(str, char, index, pos): + """Return a pair (index, pos), indicating the next occurrence of + char in str. index is the position of the character considering + only ordinals up to and including char, and pos is the position in + the full string. index/pos is the starting position in the full + string.""" + + l = len(str) + while 1: + pos += 1 + if pos == l: + return (-1, -1) + c = str[pos] + if c == char: + return index+1, pos + elif c < char: + index += 1 + +def insertion_unsort(str, extended): + """3.2 Insertion unsort coding""" + oldchar = 0x80 + result = [] + oldindex = -1 + for c in extended: + index = pos = -1 + char = ord(c) + curlen = selective_len(str, char) + delta = (curlen+1) * (char - oldchar) + while 1: + index,pos = selective_find(str,c,index,pos) + if index == -1: + break + delta += index - oldindex + result.append(delta-1) + oldindex = index + delta = 0 + oldchar = char + + return result + +def T(j, bias): + # Punycode parameters: tmin = 1, tmax = 26, base = 36 + res = 36 * (j + 1) - bias + if res < 1: return 1 + if res > 26: return 26 + return res + +digits = b"abcdefghijklmnopqrstuvwxyz0123456789" +def generate_generalized_integer(N, bias): + """3.3 Generalized variable-length integers""" + result = bytearray() + j = 0 + while 1: + t = T(j, bias) + if N < t: + result.append(digits[N]) + return bytes(result) + result.append(digits[t + ((N - t) % (36 - t))]) + N = (N - t) // (36 - t) + j += 1 + +def adapt(delta, first, numchars): + if first: + delta //= 700 + else: + delta //= 2 + delta += delta // numchars + # ((base - tmin) * tmax) // 2 == 455 + divisions = 0 + while delta > 455: + delta = delta // 35 # base - tmin + divisions += 36 + bias = divisions + (36 * delta // (delta + 38)) + return bias + + +def generate_integers(baselen, deltas): + """3.4 Bias adaptation""" + # Punycode parameters: initial bias = 72, damp = 700, skew = 38 + result = bytearray() + bias = 72 + for points, delta in enumerate(deltas): + s = generate_generalized_integer(delta, bias) + result.extend(s) + bias = adapt(delta, points==0, baselen+points+1) + return bytes(result) + +def punycode_encode(text): + base, extended = segregate(text) + deltas = insertion_unsort(text, extended) + extended = generate_integers(len(base), deltas) + if base: + return base + b"-" + extended + return extended + +##################### Decoding ##################################### + +def decode_generalized_number(extended, extpos, bias, errors): + """3.3 Generalized variable-length integers""" + result = 0 + w = 1 + j = 0 + while 1: + try: + char = ord(extended[extpos]) + except IndexError: + if errors == "strict": + raise UnicodeError("incomplete punicode string") + return extpos + 1, None + extpos += 1 + if 0x41 <= char <= 0x5A: # A-Z + digit = char - 0x41 + elif 0x30 <= char <= 0x39: + digit = char - 22 # 0x30-26 + elif errors == "strict": + raise UnicodeError("Invalid extended code point '%s'" + % extended[extpos-1]) + else: + return extpos, None + t = T(j, bias) + result += digit * w + if digit < t: + return extpos, result + w = w * (36 - t) + j += 1 + + +def insertion_sort(base, extended, errors): + """3.2 Insertion unsort coding""" + char = 0x80 + pos = -1 + bias = 72 + extpos = 0 + while extpos < len(extended): + newpos, delta = decode_generalized_number(extended, extpos, + bias, errors) + if delta is None: + # There was an error in decoding. We can't continue because + # synchronization is lost. + return base + pos += delta+1 + char += pos // (len(base) + 1) + if char > 0x10FFFF: + if errors == "strict": + raise UnicodeError("Invalid character U+%x" % char) + char = ord('?') + pos = pos % (len(base) + 1) + base = base[:pos] + chr(char) + base[pos:] + bias = adapt(delta, (extpos == 0), len(base)) + extpos = newpos + return base + +def punycode_decode(text, errors): + if isinstance(text, str): + text = text.encode("ascii") + if isinstance(text, memoryview): + text = bytes(text) + pos = text.rfind(b"-") + if pos == -1: + base = "" + extended = str(text, "ascii").upper() + else: + base = str(text[:pos], "ascii", errors) + extended = str(text[pos+1:], "ascii").upper() + return insertion_sort(base, extended, errors) + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self, input, errors='strict'): + res = punycode_encode(input) + return res, len(input) + + def decode(self, input, errors='strict'): + if errors not in ('strict', 'replace', 'ignore'): + raise UnicodeError("Unsupported error handling "+errors) + res = punycode_decode(input, errors) + return res, len(input) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return punycode_encode(input) + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + if self.errors not in ('strict', 'replace', 'ignore'): + raise UnicodeError("Unsupported error handling "+self.errors) + return punycode_decode(input, self.errors) + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='punycode', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/quopri_codec.py b/contrib/tools/python3/src/Lib/encodings/quopri_codec.py new file mode 100644 index 0000000000..496cb7655d --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/quopri_codec.py @@ -0,0 +1,56 @@ +"""Codec for quoted-printable encoding. + +This codec de/encodes from bytes to bytes. +""" + +import codecs +import quopri +from io import BytesIO + +def quopri_encode(input, errors='strict'): + assert errors == 'strict' + f = BytesIO(input) + g = BytesIO() + quopri.encode(f, g, quotetabs=True) + return (g.getvalue(), len(input)) + +def quopri_decode(input, errors='strict'): + assert errors == 'strict' + f = BytesIO(input) + g = BytesIO() + quopri.decode(f, g) + return (g.getvalue(), len(input)) + +class Codec(codecs.Codec): + def encode(self, input, errors='strict'): + return quopri_encode(input, errors) + def decode(self, input, errors='strict'): + return quopri_decode(input, errors) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return quopri_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return quopri_decode(input, self.errors)[0] + +class StreamWriter(Codec, codecs.StreamWriter): + charbuffertype = bytes + +class StreamReader(Codec, codecs.StreamReader): + charbuffertype = bytes + +# encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='quopri', + encode=quopri_encode, + decode=quopri_decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + _is_text_encoding=False, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/raw_unicode_escape.py b/contrib/tools/python3/src/Lib/encodings/raw_unicode_escape.py new file mode 100644 index 0000000000..46c8e070dd --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/raw_unicode_escape.py @@ -0,0 +1,46 @@ +""" Python 'raw-unicode-escape' Codec + + +Written by Marc-Andre Lemburg (mal@lemburg.com). + +(c) Copyright CNRI, All Rights Reserved. NO WARRANTY. + +""" +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + # Note: Binding these as C functions will result in the class not + # converting them to methods. This is intended. + encode = codecs.raw_unicode_escape_encode + decode = codecs.raw_unicode_escape_decode + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.raw_unicode_escape_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.BufferedIncrementalDecoder): + def _buffer_decode(self, input, errors, final): + return codecs.raw_unicode_escape_decode(input, errors, final) + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + def decode(self, input, errors='strict'): + return codecs.raw_unicode_escape_decode(input, errors, False) + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='raw-unicode-escape', + encode=Codec.encode, + decode=Codec.decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/rot_13.py b/contrib/tools/python3/src/Lib/encodings/rot_13.py new file mode 100644 index 0000000000..5627bfbc69 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/rot_13.py @@ -0,0 +1,113 @@ +#!/usr/bin/env python +""" Python Character Mapping Codec for ROT13. + +This codec de/encodes from str to str. + +Written by Marc-Andre Lemburg (mal@lemburg.com). +""" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + def encode(self, input, errors='strict'): + return (str.translate(input, rot13_map), len(input)) + + def decode(self, input, errors='strict'): + return (str.translate(input, rot13_map), len(input)) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return str.translate(input, rot13_map) + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return str.translate(input, rot13_map) + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='rot-13', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + _is_text_encoding=False, + ) + +### Map + +rot13_map = codecs.make_identity_dict(range(256)) +rot13_map.update({ + 0x0041: 0x004e, + 0x0042: 0x004f, + 0x0043: 0x0050, + 0x0044: 0x0051, + 0x0045: 0x0052, + 0x0046: 0x0053, + 0x0047: 0x0054, + 0x0048: 0x0055, + 0x0049: 0x0056, + 0x004a: 0x0057, + 0x004b: 0x0058, + 0x004c: 0x0059, + 0x004d: 0x005a, + 0x004e: 0x0041, + 0x004f: 0x0042, + 0x0050: 0x0043, + 0x0051: 0x0044, + 0x0052: 0x0045, + 0x0053: 0x0046, + 0x0054: 0x0047, + 0x0055: 0x0048, + 0x0056: 0x0049, + 0x0057: 0x004a, + 0x0058: 0x004b, + 0x0059: 0x004c, + 0x005a: 0x004d, + 0x0061: 0x006e, + 0x0062: 0x006f, + 0x0063: 0x0070, + 0x0064: 0x0071, + 0x0065: 0x0072, + 0x0066: 0x0073, + 0x0067: 0x0074, + 0x0068: 0x0075, + 0x0069: 0x0076, + 0x006a: 0x0077, + 0x006b: 0x0078, + 0x006c: 0x0079, + 0x006d: 0x007a, + 0x006e: 0x0061, + 0x006f: 0x0062, + 0x0070: 0x0063, + 0x0071: 0x0064, + 0x0072: 0x0065, + 0x0073: 0x0066, + 0x0074: 0x0067, + 0x0075: 0x0068, + 0x0076: 0x0069, + 0x0077: 0x006a, + 0x0078: 0x006b, + 0x0079: 0x006c, + 0x007a: 0x006d, +}) + +### Filter API + +def rot13(infile, outfile): + outfile.write(codecs.encode(infile.read(), 'rot-13')) + +if __name__ == '__main__': + import sys + rot13(sys.stdin, sys.stdout) diff --git a/contrib/tools/python3/src/Lib/encodings/shift_jis.py b/contrib/tools/python3/src/Lib/encodings/shift_jis.py new file mode 100644 index 0000000000..8338117276 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/shift_jis.py @@ -0,0 +1,39 @@ +# +# shift_jis.py: Python Unicode Codec for SHIFT_JIS +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_jp, codecs +import _multibytecodec as mbc + +codec = _codecs_jp.getcodec('shift_jis') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='shift_jis', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/shift_jis_2004.py b/contrib/tools/python3/src/Lib/encodings/shift_jis_2004.py new file mode 100644 index 0000000000..161b1e86f9 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/shift_jis_2004.py @@ -0,0 +1,39 @@ +# +# shift_jis_2004.py: Python Unicode Codec for SHIFT_JIS_2004 +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_jp, codecs +import _multibytecodec as mbc + +codec = _codecs_jp.getcodec('shift_jis_2004') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='shift_jis_2004', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/shift_jisx0213.py b/contrib/tools/python3/src/Lib/encodings/shift_jisx0213.py new file mode 100644 index 0000000000..cb653f5305 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/shift_jisx0213.py @@ -0,0 +1,39 @@ +# +# shift_jisx0213.py: Python Unicode Codec for SHIFT_JISX0213 +# +# Written by Hye-Shik Chang <perky@FreeBSD.org> +# + +import _codecs_jp, codecs +import _multibytecodec as mbc + +codec = _codecs_jp.getcodec('shift_jisx0213') + +class Codec(codecs.Codec): + encode = codec.encode + decode = codec.decode + +class IncrementalEncoder(mbc.MultibyteIncrementalEncoder, + codecs.IncrementalEncoder): + codec = codec + +class IncrementalDecoder(mbc.MultibyteIncrementalDecoder, + codecs.IncrementalDecoder): + codec = codec + +class StreamReader(Codec, mbc.MultibyteStreamReader, codecs.StreamReader): + codec = codec + +class StreamWriter(Codec, mbc.MultibyteStreamWriter, codecs.StreamWriter): + codec = codec + +def getregentry(): + return codecs.CodecInfo( + name='shift_jisx0213', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/tis_620.py b/contrib/tools/python3/src/Lib/encodings/tis_620.py new file mode 100644 index 0000000000..e288386343 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/tis_620.py @@ -0,0 +1,307 @@ +""" Python Character Mapping Codec tis_620 generated from 'python-mappings/TIS-620.TXT' with gencodec.py. + +"""#" + +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + return codecs.charmap_encode(input,errors,encoding_table) + + def decode(self,input,errors='strict'): + return codecs.charmap_decode(input,errors,decoding_table) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.charmap_encode(input,self.errors,encoding_table)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return codecs.charmap_decode(input,self.errors,decoding_table)[0] + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='tis-620', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) + + +### Decoding Table + +decoding_table = ( + '\x00' # 0x00 -> NULL + '\x01' # 0x01 -> START OF HEADING + '\x02' # 0x02 -> START OF TEXT + '\x03' # 0x03 -> END OF TEXT + '\x04' # 0x04 -> END OF TRANSMISSION + '\x05' # 0x05 -> ENQUIRY + '\x06' # 0x06 -> ACKNOWLEDGE + '\x07' # 0x07 -> BELL + '\x08' # 0x08 -> BACKSPACE + '\t' # 0x09 -> HORIZONTAL TABULATION + '\n' # 0x0A -> LINE FEED + '\x0b' # 0x0B -> VERTICAL TABULATION + '\x0c' # 0x0C -> FORM FEED + '\r' # 0x0D -> CARRIAGE RETURN + '\x0e' # 0x0E -> SHIFT OUT + '\x0f' # 0x0F -> SHIFT IN + '\x10' # 0x10 -> DATA LINK ESCAPE + '\x11' # 0x11 -> DEVICE CONTROL ONE + '\x12' # 0x12 -> DEVICE CONTROL TWO + '\x13' # 0x13 -> DEVICE CONTROL THREE + '\x14' # 0x14 -> DEVICE CONTROL FOUR + '\x15' # 0x15 -> NEGATIVE ACKNOWLEDGE + '\x16' # 0x16 -> SYNCHRONOUS IDLE + '\x17' # 0x17 -> END OF TRANSMISSION BLOCK + '\x18' # 0x18 -> CANCEL + '\x19' # 0x19 -> END OF MEDIUM + '\x1a' # 0x1A -> SUBSTITUTE + '\x1b' # 0x1B -> ESCAPE + '\x1c' # 0x1C -> FILE SEPARATOR + '\x1d' # 0x1D -> GROUP SEPARATOR + '\x1e' # 0x1E -> RECORD SEPARATOR + '\x1f' # 0x1F -> UNIT SEPARATOR + ' ' # 0x20 -> SPACE + '!' # 0x21 -> EXCLAMATION MARK + '"' # 0x22 -> QUOTATION MARK + '#' # 0x23 -> NUMBER SIGN + '$' # 0x24 -> DOLLAR SIGN + '%' # 0x25 -> PERCENT SIGN + '&' # 0x26 -> AMPERSAND + "'" # 0x27 -> APOSTROPHE + '(' # 0x28 -> LEFT PARENTHESIS + ')' # 0x29 -> RIGHT PARENTHESIS + '*' # 0x2A -> ASTERISK + '+' # 0x2B -> PLUS SIGN + ',' # 0x2C -> COMMA + '-' # 0x2D -> HYPHEN-MINUS + '.' # 0x2E -> FULL STOP + '/' # 0x2F -> SOLIDUS + '0' # 0x30 -> DIGIT ZERO + '1' # 0x31 -> DIGIT ONE + '2' # 0x32 -> DIGIT TWO + '3' # 0x33 -> DIGIT THREE + '4' # 0x34 -> DIGIT FOUR + '5' # 0x35 -> DIGIT FIVE + '6' # 0x36 -> DIGIT SIX + '7' # 0x37 -> DIGIT SEVEN + '8' # 0x38 -> DIGIT EIGHT + '9' # 0x39 -> DIGIT NINE + ':' # 0x3A -> COLON + ';' # 0x3B -> SEMICOLON + '<' # 0x3C -> LESS-THAN SIGN + '=' # 0x3D -> EQUALS SIGN + '>' # 0x3E -> GREATER-THAN SIGN + '?' # 0x3F -> QUESTION MARK + '@' # 0x40 -> COMMERCIAL AT + 'A' # 0x41 -> LATIN CAPITAL LETTER A + 'B' # 0x42 -> LATIN CAPITAL LETTER B + 'C' # 0x43 -> LATIN CAPITAL LETTER C + 'D' # 0x44 -> LATIN CAPITAL LETTER D + 'E' # 0x45 -> LATIN CAPITAL LETTER E + 'F' # 0x46 -> LATIN CAPITAL LETTER F + 'G' # 0x47 -> LATIN CAPITAL LETTER G + 'H' # 0x48 -> LATIN CAPITAL LETTER H + 'I' # 0x49 -> LATIN CAPITAL LETTER I + 'J' # 0x4A -> LATIN CAPITAL LETTER J + 'K' # 0x4B -> LATIN CAPITAL LETTER K + 'L' # 0x4C -> LATIN CAPITAL LETTER L + 'M' # 0x4D -> LATIN CAPITAL LETTER M + 'N' # 0x4E -> LATIN CAPITAL LETTER N + 'O' # 0x4F -> LATIN CAPITAL LETTER O + 'P' # 0x50 -> LATIN CAPITAL LETTER P + 'Q' # 0x51 -> LATIN CAPITAL LETTER Q + 'R' # 0x52 -> LATIN CAPITAL LETTER R + 'S' # 0x53 -> LATIN CAPITAL LETTER S + 'T' # 0x54 -> LATIN CAPITAL LETTER T + 'U' # 0x55 -> LATIN CAPITAL LETTER U + 'V' # 0x56 -> LATIN CAPITAL LETTER V + 'W' # 0x57 -> LATIN CAPITAL LETTER W + 'X' # 0x58 -> LATIN CAPITAL LETTER X + 'Y' # 0x59 -> LATIN CAPITAL LETTER Y + 'Z' # 0x5A -> LATIN CAPITAL LETTER Z + '[' # 0x5B -> LEFT SQUARE BRACKET + '\\' # 0x5C -> REVERSE SOLIDUS + ']' # 0x5D -> RIGHT SQUARE BRACKET + '^' # 0x5E -> CIRCUMFLEX ACCENT + '_' # 0x5F -> LOW LINE + '`' # 0x60 -> GRAVE ACCENT + 'a' # 0x61 -> LATIN SMALL LETTER A + 'b' # 0x62 -> LATIN SMALL LETTER B + 'c' # 0x63 -> LATIN SMALL LETTER C + 'd' # 0x64 -> LATIN SMALL LETTER D + 'e' # 0x65 -> LATIN SMALL LETTER E + 'f' # 0x66 -> LATIN SMALL LETTER F + 'g' # 0x67 -> LATIN SMALL LETTER G + 'h' # 0x68 -> LATIN SMALL LETTER H + 'i' # 0x69 -> LATIN SMALL LETTER I + 'j' # 0x6A -> LATIN SMALL LETTER J + 'k' # 0x6B -> LATIN SMALL LETTER K + 'l' # 0x6C -> LATIN SMALL LETTER L + 'm' # 0x6D -> LATIN SMALL LETTER M + 'n' # 0x6E -> LATIN SMALL LETTER N + 'o' # 0x6F -> LATIN SMALL LETTER O + 'p' # 0x70 -> LATIN SMALL LETTER P + 'q' # 0x71 -> LATIN SMALL LETTER Q + 'r' # 0x72 -> LATIN SMALL LETTER R + 's' # 0x73 -> LATIN SMALL LETTER S + 't' # 0x74 -> LATIN SMALL LETTER T + 'u' # 0x75 -> LATIN SMALL LETTER U + 'v' # 0x76 -> LATIN SMALL LETTER V + 'w' # 0x77 -> LATIN SMALL LETTER W + 'x' # 0x78 -> LATIN SMALL LETTER X + 'y' # 0x79 -> LATIN SMALL LETTER Y + 'z' # 0x7A -> LATIN SMALL LETTER Z + '{' # 0x7B -> LEFT CURLY BRACKET + '|' # 0x7C -> VERTICAL LINE + '}' # 0x7D -> RIGHT CURLY BRACKET + '~' # 0x7E -> TILDE + '\x7f' # 0x7F -> DELETE + '\x80' # 0x80 -> <control> + '\x81' # 0x81 -> <control> + '\x82' # 0x82 -> <control> + '\x83' # 0x83 -> <control> + '\x84' # 0x84 -> <control> + '\x85' # 0x85 -> <control> + '\x86' # 0x86 -> <control> + '\x87' # 0x87 -> <control> + '\x88' # 0x88 -> <control> + '\x89' # 0x89 -> <control> + '\x8a' # 0x8A -> <control> + '\x8b' # 0x8B -> <control> + '\x8c' # 0x8C -> <control> + '\x8d' # 0x8D -> <control> + '\x8e' # 0x8E -> <control> + '\x8f' # 0x8F -> <control> + '\x90' # 0x90 -> <control> + '\x91' # 0x91 -> <control> + '\x92' # 0x92 -> <control> + '\x93' # 0x93 -> <control> + '\x94' # 0x94 -> <control> + '\x95' # 0x95 -> <control> + '\x96' # 0x96 -> <control> + '\x97' # 0x97 -> <control> + '\x98' # 0x98 -> <control> + '\x99' # 0x99 -> <control> + '\x9a' # 0x9A -> <control> + '\x9b' # 0x9B -> <control> + '\x9c' # 0x9C -> <control> + '\x9d' # 0x9D -> <control> + '\x9e' # 0x9E -> <control> + '\x9f' # 0x9F -> <control> + '\ufffe' + '\u0e01' # 0xA1 -> THAI CHARACTER KO KAI + '\u0e02' # 0xA2 -> THAI CHARACTER KHO KHAI + '\u0e03' # 0xA3 -> THAI CHARACTER KHO KHUAT + '\u0e04' # 0xA4 -> THAI CHARACTER KHO KHWAI + '\u0e05' # 0xA5 -> THAI CHARACTER KHO KHON + '\u0e06' # 0xA6 -> THAI CHARACTER KHO RAKHANG + '\u0e07' # 0xA7 -> THAI CHARACTER NGO NGU + '\u0e08' # 0xA8 -> THAI CHARACTER CHO CHAN + '\u0e09' # 0xA9 -> THAI CHARACTER CHO CHING + '\u0e0a' # 0xAA -> THAI CHARACTER CHO CHANG + '\u0e0b' # 0xAB -> THAI CHARACTER SO SO + '\u0e0c' # 0xAC -> THAI CHARACTER CHO CHOE + '\u0e0d' # 0xAD -> THAI CHARACTER YO YING + '\u0e0e' # 0xAE -> THAI CHARACTER DO CHADA + '\u0e0f' # 0xAF -> THAI CHARACTER TO PATAK + '\u0e10' # 0xB0 -> THAI CHARACTER THO THAN + '\u0e11' # 0xB1 -> THAI CHARACTER THO NANGMONTHO + '\u0e12' # 0xB2 -> THAI CHARACTER THO PHUTHAO + '\u0e13' # 0xB3 -> THAI CHARACTER NO NEN + '\u0e14' # 0xB4 -> THAI CHARACTER DO DEK + '\u0e15' # 0xB5 -> THAI CHARACTER TO TAO + '\u0e16' # 0xB6 -> THAI CHARACTER THO THUNG + '\u0e17' # 0xB7 -> THAI CHARACTER THO THAHAN + '\u0e18' # 0xB8 -> THAI CHARACTER THO THONG + '\u0e19' # 0xB9 -> THAI CHARACTER NO NU + '\u0e1a' # 0xBA -> THAI CHARACTER BO BAIMAI + '\u0e1b' # 0xBB -> THAI CHARACTER PO PLA + '\u0e1c' # 0xBC -> THAI CHARACTER PHO PHUNG + '\u0e1d' # 0xBD -> THAI CHARACTER FO FA + '\u0e1e' # 0xBE -> THAI CHARACTER PHO PHAN + '\u0e1f' # 0xBF -> THAI CHARACTER FO FAN + '\u0e20' # 0xC0 -> THAI CHARACTER PHO SAMPHAO + '\u0e21' # 0xC1 -> THAI CHARACTER MO MA + '\u0e22' # 0xC2 -> THAI CHARACTER YO YAK + '\u0e23' # 0xC3 -> THAI CHARACTER RO RUA + '\u0e24' # 0xC4 -> THAI CHARACTER RU + '\u0e25' # 0xC5 -> THAI CHARACTER LO LING + '\u0e26' # 0xC6 -> THAI CHARACTER LU + '\u0e27' # 0xC7 -> THAI CHARACTER WO WAEN + '\u0e28' # 0xC8 -> THAI CHARACTER SO SALA + '\u0e29' # 0xC9 -> THAI CHARACTER SO RUSI + '\u0e2a' # 0xCA -> THAI CHARACTER SO SUA + '\u0e2b' # 0xCB -> THAI CHARACTER HO HIP + '\u0e2c' # 0xCC -> THAI CHARACTER LO CHULA + '\u0e2d' # 0xCD -> THAI CHARACTER O ANG + '\u0e2e' # 0xCE -> THAI CHARACTER HO NOKHUK + '\u0e2f' # 0xCF -> THAI CHARACTER PAIYANNOI + '\u0e30' # 0xD0 -> THAI CHARACTER SARA A + '\u0e31' # 0xD1 -> THAI CHARACTER MAI HAN-AKAT + '\u0e32' # 0xD2 -> THAI CHARACTER SARA AA + '\u0e33' # 0xD3 -> THAI CHARACTER SARA AM + '\u0e34' # 0xD4 -> THAI CHARACTER SARA I + '\u0e35' # 0xD5 -> THAI CHARACTER SARA II + '\u0e36' # 0xD6 -> THAI CHARACTER SARA UE + '\u0e37' # 0xD7 -> THAI CHARACTER SARA UEE + '\u0e38' # 0xD8 -> THAI CHARACTER SARA U + '\u0e39' # 0xD9 -> THAI CHARACTER SARA UU + '\u0e3a' # 0xDA -> THAI CHARACTER PHINTHU + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' + '\u0e3f' # 0xDF -> THAI CURRENCY SYMBOL BAHT + '\u0e40' # 0xE0 -> THAI CHARACTER SARA E + '\u0e41' # 0xE1 -> THAI CHARACTER SARA AE + '\u0e42' # 0xE2 -> THAI CHARACTER SARA O + '\u0e43' # 0xE3 -> THAI CHARACTER SARA AI MAIMUAN + '\u0e44' # 0xE4 -> THAI CHARACTER SARA AI MAIMALAI + '\u0e45' # 0xE5 -> THAI CHARACTER LAKKHANGYAO + '\u0e46' # 0xE6 -> THAI CHARACTER MAIYAMOK + '\u0e47' # 0xE7 -> THAI CHARACTER MAITAIKHU + '\u0e48' # 0xE8 -> THAI CHARACTER MAI EK + '\u0e49' # 0xE9 -> THAI CHARACTER MAI THO + '\u0e4a' # 0xEA -> THAI CHARACTER MAI TRI + '\u0e4b' # 0xEB -> THAI CHARACTER MAI CHATTAWA + '\u0e4c' # 0xEC -> THAI CHARACTER THANTHAKHAT + '\u0e4d' # 0xED -> THAI CHARACTER NIKHAHIT + '\u0e4e' # 0xEE -> THAI CHARACTER YAMAKKAN + '\u0e4f' # 0xEF -> THAI CHARACTER FONGMAN + '\u0e50' # 0xF0 -> THAI DIGIT ZERO + '\u0e51' # 0xF1 -> THAI DIGIT ONE + '\u0e52' # 0xF2 -> THAI DIGIT TWO + '\u0e53' # 0xF3 -> THAI DIGIT THREE + '\u0e54' # 0xF4 -> THAI DIGIT FOUR + '\u0e55' # 0xF5 -> THAI DIGIT FIVE + '\u0e56' # 0xF6 -> THAI DIGIT SIX + '\u0e57' # 0xF7 -> THAI DIGIT SEVEN + '\u0e58' # 0xF8 -> THAI DIGIT EIGHT + '\u0e59' # 0xF9 -> THAI DIGIT NINE + '\u0e5a' # 0xFA -> THAI CHARACTER ANGKHANKHU + '\u0e5b' # 0xFB -> THAI CHARACTER KHOMUT + '\ufffe' + '\ufffe' + '\ufffe' + '\ufffe' +) + +### Encoding table +encoding_table=codecs.charmap_build(decoding_table) diff --git a/contrib/tools/python3/src/Lib/encodings/undefined.py b/contrib/tools/python3/src/Lib/encodings/undefined.py new file mode 100644 index 0000000000..4690288355 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/undefined.py @@ -0,0 +1,49 @@ +""" Python 'undefined' Codec + + This codec will always raise a ValueError exception when being + used. It is intended for use by the site.py file to switch off + automatic string to Unicode coercion. + +Written by Marc-Andre Lemburg (mal@lemburg.com). + +(c) Copyright CNRI, All Rights Reserved. NO WARRANTY. + +""" +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + def encode(self,input,errors='strict'): + raise UnicodeError("undefined encoding") + + def decode(self,input,errors='strict'): + raise UnicodeError("undefined encoding") + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + raise UnicodeError("undefined encoding") + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + raise UnicodeError("undefined encoding") + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + pass + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='undefined', + encode=Codec().encode, + decode=Codec().decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/unicode_escape.py b/contrib/tools/python3/src/Lib/encodings/unicode_escape.py new file mode 100644 index 0000000000..9b1ce99b33 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/unicode_escape.py @@ -0,0 +1,46 @@ +""" Python 'unicode-escape' Codec + + +Written by Marc-Andre Lemburg (mal@lemburg.com). + +(c) Copyright CNRI, All Rights Reserved. NO WARRANTY. + +""" +import codecs + +### Codec APIs + +class Codec(codecs.Codec): + + # Note: Binding these as C functions will result in the class not + # converting them to methods. This is intended. + encode = codecs.unicode_escape_encode + decode = codecs.unicode_escape_decode + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.unicode_escape_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.BufferedIncrementalDecoder): + def _buffer_decode(self, input, errors, final): + return codecs.unicode_escape_decode(input, errors, final) + +class StreamWriter(Codec,codecs.StreamWriter): + pass + +class StreamReader(Codec,codecs.StreamReader): + def decode(self, input, errors='strict'): + return codecs.unicode_escape_decode(input, errors, False) + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='unicode-escape', + encode=Codec.encode, + decode=Codec.decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamwriter=StreamWriter, + streamreader=StreamReader, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/utf_16.py b/contrib/tools/python3/src/Lib/encodings/utf_16.py new file mode 100644 index 0000000000..c61248242b --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/utf_16.py @@ -0,0 +1,155 @@ +""" Python 'utf-16' Codec + + +Written by Marc-Andre Lemburg (mal@lemburg.com). + +(c) Copyright CNRI, All Rights Reserved. NO WARRANTY. + +""" +import codecs, sys + +### Codec APIs + +encode = codecs.utf_16_encode + +def decode(input, errors='strict'): + return codecs.utf_16_decode(input, errors, True) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def __init__(self, errors='strict'): + codecs.IncrementalEncoder.__init__(self, errors) + self.encoder = None + + def encode(self, input, final=False): + if self.encoder is None: + result = codecs.utf_16_encode(input, self.errors)[0] + if sys.byteorder == 'little': + self.encoder = codecs.utf_16_le_encode + else: + self.encoder = codecs.utf_16_be_encode + return result + return self.encoder(input, self.errors)[0] + + def reset(self): + codecs.IncrementalEncoder.reset(self) + self.encoder = None + + def getstate(self): + # state info we return to the caller: + # 0: stream is in natural order for this platform + # 2: endianness hasn't been determined yet + # (we're never writing in unnatural order) + return (2 if self.encoder is None else 0) + + def setstate(self, state): + if state: + self.encoder = None + else: + if sys.byteorder == 'little': + self.encoder = codecs.utf_16_le_encode + else: + self.encoder = codecs.utf_16_be_encode + +class IncrementalDecoder(codecs.BufferedIncrementalDecoder): + def __init__(self, errors='strict'): + codecs.BufferedIncrementalDecoder.__init__(self, errors) + self.decoder = None + + def _buffer_decode(self, input, errors, final): + if self.decoder is None: + (output, consumed, byteorder) = \ + codecs.utf_16_ex_decode(input, errors, 0, final) + if byteorder == -1: + self.decoder = codecs.utf_16_le_decode + elif byteorder == 1: + self.decoder = codecs.utf_16_be_decode + elif consumed >= 2: + raise UnicodeError("UTF-16 stream does not start with BOM") + return (output, consumed) + return self.decoder(input, self.errors, final) + + def reset(self): + codecs.BufferedIncrementalDecoder.reset(self) + self.decoder = None + + def getstate(self): + # additional state info from the base class must be None here, + # as it isn't passed along to the caller + state = codecs.BufferedIncrementalDecoder.getstate(self)[0] + # additional state info we pass to the caller: + # 0: stream is in natural order for this platform + # 1: stream is in unnatural order + # 2: endianness hasn't been determined yet + if self.decoder is None: + return (state, 2) + addstate = int((sys.byteorder == "big") != + (self.decoder is codecs.utf_16_be_decode)) + return (state, addstate) + + def setstate(self, state): + # state[1] will be ignored by BufferedIncrementalDecoder.setstate() + codecs.BufferedIncrementalDecoder.setstate(self, state) + state = state[1] + if state == 0: + self.decoder = (codecs.utf_16_be_decode + if sys.byteorder == "big" + else codecs.utf_16_le_decode) + elif state == 1: + self.decoder = (codecs.utf_16_le_decode + if sys.byteorder == "big" + else codecs.utf_16_be_decode) + else: + self.decoder = None + +class StreamWriter(codecs.StreamWriter): + def __init__(self, stream, errors='strict'): + codecs.StreamWriter.__init__(self, stream, errors) + self.encoder = None + + def reset(self): + codecs.StreamWriter.reset(self) + self.encoder = None + + def encode(self, input, errors='strict'): + if self.encoder is None: + result = codecs.utf_16_encode(input, errors) + if sys.byteorder == 'little': + self.encoder = codecs.utf_16_le_encode + else: + self.encoder = codecs.utf_16_be_encode + return result + else: + return self.encoder(input, errors) + +class StreamReader(codecs.StreamReader): + + def reset(self): + codecs.StreamReader.reset(self) + try: + del self.decode + except AttributeError: + pass + + def decode(self, input, errors='strict'): + (object, consumed, byteorder) = \ + codecs.utf_16_ex_decode(input, errors, 0, False) + if byteorder == -1: + self.decode = codecs.utf_16_le_decode + elif byteorder == 1: + self.decode = codecs.utf_16_be_decode + elif consumed>=2: + raise UnicodeError("UTF-16 stream does not start with BOM") + return (object, consumed) + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='utf-16', + encode=encode, + decode=decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/utf_16_be.py b/contrib/tools/python3/src/Lib/encodings/utf_16_be.py new file mode 100644 index 0000000000..86b458eb9b --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/utf_16_be.py @@ -0,0 +1,42 @@ +""" Python 'utf-16-be' Codec + + +Written by Marc-Andre Lemburg (mal@lemburg.com). + +(c) Copyright CNRI, All Rights Reserved. NO WARRANTY. + +""" +import codecs + +### Codec APIs + +encode = codecs.utf_16_be_encode + +def decode(input, errors='strict'): + return codecs.utf_16_be_decode(input, errors, True) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.utf_16_be_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.BufferedIncrementalDecoder): + _buffer_decode = codecs.utf_16_be_decode + +class StreamWriter(codecs.StreamWriter): + encode = codecs.utf_16_be_encode + +class StreamReader(codecs.StreamReader): + decode = codecs.utf_16_be_decode + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='utf-16-be', + encode=encode, + decode=decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/utf_16_le.py b/contrib/tools/python3/src/Lib/encodings/utf_16_le.py new file mode 100644 index 0000000000..ec454142ee --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/utf_16_le.py @@ -0,0 +1,42 @@ +""" Python 'utf-16-le' Codec + + +Written by Marc-Andre Lemburg (mal@lemburg.com). + +(c) Copyright CNRI, All Rights Reserved. NO WARRANTY. + +""" +import codecs + +### Codec APIs + +encode = codecs.utf_16_le_encode + +def decode(input, errors='strict'): + return codecs.utf_16_le_decode(input, errors, True) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.utf_16_le_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.BufferedIncrementalDecoder): + _buffer_decode = codecs.utf_16_le_decode + +class StreamWriter(codecs.StreamWriter): + encode = codecs.utf_16_le_encode + +class StreamReader(codecs.StreamReader): + decode = codecs.utf_16_le_decode + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='utf-16-le', + encode=encode, + decode=decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/utf_32.py b/contrib/tools/python3/src/Lib/encodings/utf_32.py new file mode 100644 index 0000000000..cdf84d1412 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/utf_32.py @@ -0,0 +1,150 @@ +""" +Python 'utf-32' Codec +""" +import codecs, sys + +### Codec APIs + +encode = codecs.utf_32_encode + +def decode(input, errors='strict'): + return codecs.utf_32_decode(input, errors, True) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def __init__(self, errors='strict'): + codecs.IncrementalEncoder.__init__(self, errors) + self.encoder = None + + def encode(self, input, final=False): + if self.encoder is None: + result = codecs.utf_32_encode(input, self.errors)[0] + if sys.byteorder == 'little': + self.encoder = codecs.utf_32_le_encode + else: + self.encoder = codecs.utf_32_be_encode + return result + return self.encoder(input, self.errors)[0] + + def reset(self): + codecs.IncrementalEncoder.reset(self) + self.encoder = None + + def getstate(self): + # state info we return to the caller: + # 0: stream is in natural order for this platform + # 2: endianness hasn't been determined yet + # (we're never writing in unnatural order) + return (2 if self.encoder is None else 0) + + def setstate(self, state): + if state: + self.encoder = None + else: + if sys.byteorder == 'little': + self.encoder = codecs.utf_32_le_encode + else: + self.encoder = codecs.utf_32_be_encode + +class IncrementalDecoder(codecs.BufferedIncrementalDecoder): + def __init__(self, errors='strict'): + codecs.BufferedIncrementalDecoder.__init__(self, errors) + self.decoder = None + + def _buffer_decode(self, input, errors, final): + if self.decoder is None: + (output, consumed, byteorder) = \ + codecs.utf_32_ex_decode(input, errors, 0, final) + if byteorder == -1: + self.decoder = codecs.utf_32_le_decode + elif byteorder == 1: + self.decoder = codecs.utf_32_be_decode + elif consumed >= 4: + raise UnicodeError("UTF-32 stream does not start with BOM") + return (output, consumed) + return self.decoder(input, self.errors, final) + + def reset(self): + codecs.BufferedIncrementalDecoder.reset(self) + self.decoder = None + + def getstate(self): + # additional state info from the base class must be None here, + # as it isn't passed along to the caller + state = codecs.BufferedIncrementalDecoder.getstate(self)[0] + # additional state info we pass to the caller: + # 0: stream is in natural order for this platform + # 1: stream is in unnatural order + # 2: endianness hasn't been determined yet + if self.decoder is None: + return (state, 2) + addstate = int((sys.byteorder == "big") != + (self.decoder is codecs.utf_32_be_decode)) + return (state, addstate) + + def setstate(self, state): + # state[1] will be ignored by BufferedIncrementalDecoder.setstate() + codecs.BufferedIncrementalDecoder.setstate(self, state) + state = state[1] + if state == 0: + self.decoder = (codecs.utf_32_be_decode + if sys.byteorder == "big" + else codecs.utf_32_le_decode) + elif state == 1: + self.decoder = (codecs.utf_32_le_decode + if sys.byteorder == "big" + else codecs.utf_32_be_decode) + else: + self.decoder = None + +class StreamWriter(codecs.StreamWriter): + def __init__(self, stream, errors='strict'): + self.encoder = None + codecs.StreamWriter.__init__(self, stream, errors) + + def reset(self): + codecs.StreamWriter.reset(self) + self.encoder = None + + def encode(self, input, errors='strict'): + if self.encoder is None: + result = codecs.utf_32_encode(input, errors) + if sys.byteorder == 'little': + self.encoder = codecs.utf_32_le_encode + else: + self.encoder = codecs.utf_32_be_encode + return result + else: + return self.encoder(input, errors) + +class StreamReader(codecs.StreamReader): + + def reset(self): + codecs.StreamReader.reset(self) + try: + del self.decode + except AttributeError: + pass + + def decode(self, input, errors='strict'): + (object, consumed, byteorder) = \ + codecs.utf_32_ex_decode(input, errors, 0, False) + if byteorder == -1: + self.decode = codecs.utf_32_le_decode + elif byteorder == 1: + self.decode = codecs.utf_32_be_decode + elif consumed>=4: + raise UnicodeError("UTF-32 stream does not start with BOM") + return (object, consumed) + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='utf-32', + encode=encode, + decode=decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/utf_32_be.py b/contrib/tools/python3/src/Lib/encodings/utf_32_be.py new file mode 100644 index 0000000000..fe272b5faf --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/utf_32_be.py @@ -0,0 +1,37 @@ +""" +Python 'utf-32-be' Codec +""" +import codecs + +### Codec APIs + +encode = codecs.utf_32_be_encode + +def decode(input, errors='strict'): + return codecs.utf_32_be_decode(input, errors, True) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.utf_32_be_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.BufferedIncrementalDecoder): + _buffer_decode = codecs.utf_32_be_decode + +class StreamWriter(codecs.StreamWriter): + encode = codecs.utf_32_be_encode + +class StreamReader(codecs.StreamReader): + decode = codecs.utf_32_be_decode + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='utf-32-be', + encode=encode, + decode=decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/utf_32_le.py b/contrib/tools/python3/src/Lib/encodings/utf_32_le.py new file mode 100644 index 0000000000..9e48210928 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/utf_32_le.py @@ -0,0 +1,37 @@ +""" +Python 'utf-32-le' Codec +""" +import codecs + +### Codec APIs + +encode = codecs.utf_32_le_encode + +def decode(input, errors='strict'): + return codecs.utf_32_le_decode(input, errors, True) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.utf_32_le_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.BufferedIncrementalDecoder): + _buffer_decode = codecs.utf_32_le_decode + +class StreamWriter(codecs.StreamWriter): + encode = codecs.utf_32_le_encode + +class StreamReader(codecs.StreamReader): + decode = codecs.utf_32_le_decode + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='utf-32-le', + encode=encode, + decode=decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/utf_7.py b/contrib/tools/python3/src/Lib/encodings/utf_7.py new file mode 100644 index 0000000000..8e0567f208 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/utf_7.py @@ -0,0 +1,38 @@ +""" Python 'utf-7' Codec + +Written by Brian Quinlan (brian@sweetapp.com). +""" +import codecs + +### Codec APIs + +encode = codecs.utf_7_encode + +def decode(input, errors='strict'): + return codecs.utf_7_decode(input, errors, True) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.utf_7_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.BufferedIncrementalDecoder): + _buffer_decode = codecs.utf_7_decode + +class StreamWriter(codecs.StreamWriter): + encode = codecs.utf_7_encode + +class StreamReader(codecs.StreamReader): + decode = codecs.utf_7_decode + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='utf-7', + encode=encode, + decode=decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/utf_8.py b/contrib/tools/python3/src/Lib/encodings/utf_8.py new file mode 100644 index 0000000000..1bf6336571 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/utf_8.py @@ -0,0 +1,42 @@ +""" Python 'utf-8' Codec + + +Written by Marc-Andre Lemburg (mal@lemburg.com). + +(c) Copyright CNRI, All Rights Reserved. NO WARRANTY. + +""" +import codecs + +### Codec APIs + +encode = codecs.utf_8_encode + +def decode(input, errors='strict'): + return codecs.utf_8_decode(input, errors, True) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return codecs.utf_8_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.BufferedIncrementalDecoder): + _buffer_decode = codecs.utf_8_decode + +class StreamWriter(codecs.StreamWriter): + encode = codecs.utf_8_encode + +class StreamReader(codecs.StreamReader): + decode = codecs.utf_8_decode + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='utf-8', + encode=encode, + decode=decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/utf_8_sig.py b/contrib/tools/python3/src/Lib/encodings/utf_8_sig.py new file mode 100644 index 0000000000..1bb479203f --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/utf_8_sig.py @@ -0,0 +1,130 @@ +""" Python 'utf-8-sig' Codec +This work similar to UTF-8 with the following changes: + +* On encoding/writing a UTF-8 encoded BOM will be prepended/written as the + first three bytes. + +* On decoding/reading if the first three bytes are a UTF-8 encoded BOM, these + bytes will be skipped. +""" +import codecs + +### Codec APIs + +def encode(input, errors='strict'): + return (codecs.BOM_UTF8 + codecs.utf_8_encode(input, errors)[0], + len(input)) + +def decode(input, errors='strict'): + prefix = 0 + if input[:3] == codecs.BOM_UTF8: + input = input[3:] + prefix = 3 + (output, consumed) = codecs.utf_8_decode(input, errors, True) + return (output, consumed+prefix) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def __init__(self, errors='strict'): + codecs.IncrementalEncoder.__init__(self, errors) + self.first = 1 + + def encode(self, input, final=False): + if self.first: + self.first = 0 + return codecs.BOM_UTF8 + \ + codecs.utf_8_encode(input, self.errors)[0] + else: + return codecs.utf_8_encode(input, self.errors)[0] + + def reset(self): + codecs.IncrementalEncoder.reset(self) + self.first = 1 + + def getstate(self): + return self.first + + def setstate(self, state): + self.first = state + +class IncrementalDecoder(codecs.BufferedIncrementalDecoder): + def __init__(self, errors='strict'): + codecs.BufferedIncrementalDecoder.__init__(self, errors) + self.first = 1 + + def _buffer_decode(self, input, errors, final): + if self.first: + if len(input) < 3: + if codecs.BOM_UTF8.startswith(input): + # not enough data to decide if this really is a BOM + # => try again on the next call + return ("", 0) + else: + self.first = 0 + else: + self.first = 0 + if input[:3] == codecs.BOM_UTF8: + (output, consumed) = \ + codecs.utf_8_decode(input[3:], errors, final) + return (output, consumed+3) + return codecs.utf_8_decode(input, errors, final) + + def reset(self): + codecs.BufferedIncrementalDecoder.reset(self) + self.first = 1 + + def getstate(self): + state = codecs.BufferedIncrementalDecoder.getstate(self) + # state[1] must be 0 here, as it isn't passed along to the caller + return (state[0], self.first) + + def setstate(self, state): + # state[1] will be ignored by BufferedIncrementalDecoder.setstate() + codecs.BufferedIncrementalDecoder.setstate(self, state) + self.first = state[1] + +class StreamWriter(codecs.StreamWriter): + def reset(self): + codecs.StreamWriter.reset(self) + try: + del self.encode + except AttributeError: + pass + + def encode(self, input, errors='strict'): + self.encode = codecs.utf_8_encode + return encode(input, errors) + +class StreamReader(codecs.StreamReader): + def reset(self): + codecs.StreamReader.reset(self) + try: + del self.decode + except AttributeError: + pass + + def decode(self, input, errors='strict'): + if len(input) < 3: + if codecs.BOM_UTF8.startswith(input): + # not enough data to decide if this is a BOM + # => try again on the next call + return ("", 0) + elif input[:3] == codecs.BOM_UTF8: + self.decode = codecs.utf_8_decode + (output, consumed) = codecs.utf_8_decode(input[3:],errors) + return (output, consumed+3) + # (else) no BOM present + self.decode = codecs.utf_8_decode + return codecs.utf_8_decode(input, errors) + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='utf-8-sig', + encode=encode, + decode=decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/uu_codec.py b/contrib/tools/python3/src/Lib/encodings/uu_codec.py new file mode 100644 index 0000000000..4e58c62fe9 --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/uu_codec.py @@ -0,0 +1,103 @@ +"""Python 'uu_codec' Codec - UU content transfer encoding. + +This codec de/encodes from bytes to bytes. + +Written by Marc-Andre Lemburg (mal@lemburg.com). Some details were +adapted from uu.py which was written by Lance Ellinghouse and +modified by Jack Jansen and Fredrik Lundh. +""" + +import codecs +import binascii +from io import BytesIO + +### Codec APIs + +def uu_encode(input, errors='strict', filename='<data>', mode=0o666): + assert errors == 'strict' + infile = BytesIO(input) + outfile = BytesIO() + read = infile.read + write = outfile.write + + # Remove newline chars from filename + filename = filename.replace('\n','\\n') + filename = filename.replace('\r','\\r') + + # Encode + write(('begin %o %s\n' % (mode & 0o777, filename)).encode('ascii')) + chunk = read(45) + while chunk: + write(binascii.b2a_uu(chunk)) + chunk = read(45) + write(b' \nend\n') + + return (outfile.getvalue(), len(input)) + +def uu_decode(input, errors='strict'): + assert errors == 'strict' + infile = BytesIO(input) + outfile = BytesIO() + readline = infile.readline + write = outfile.write + + # Find start of encoded data + while 1: + s = readline() + if not s: + raise ValueError('Missing "begin" line in input data') + if s[:5] == b'begin': + break + + # Decode + while True: + s = readline() + if not s or s == b'end\n': + break + try: + data = binascii.a2b_uu(s) + except binascii.Error as v: + # Workaround for broken uuencoders by /Fredrik Lundh + nbytes = (((s[0]-32) & 63) * 4 + 5) // 3 + data = binascii.a2b_uu(s[:nbytes]) + #sys.stderr.write("Warning: %s\n" % str(v)) + write(data) + if not s: + raise ValueError('Truncated input data') + + return (outfile.getvalue(), len(input)) + +class Codec(codecs.Codec): + def encode(self, input, errors='strict'): + return uu_encode(input, errors) + + def decode(self, input, errors='strict'): + return uu_decode(input, errors) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def encode(self, input, final=False): + return uu_encode(input, self.errors)[0] + +class IncrementalDecoder(codecs.IncrementalDecoder): + def decode(self, input, final=False): + return uu_decode(input, self.errors)[0] + +class StreamWriter(Codec, codecs.StreamWriter): + charbuffertype = bytes + +class StreamReader(Codec, codecs.StreamReader): + charbuffertype = bytes + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='uu', + encode=uu_encode, + decode=uu_decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + _is_text_encoding=False, + ) diff --git a/contrib/tools/python3/src/Lib/encodings/zlib_codec.py b/contrib/tools/python3/src/Lib/encodings/zlib_codec.py new file mode 100644 index 0000000000..95908a4b4a --- /dev/null +++ b/contrib/tools/python3/src/Lib/encodings/zlib_codec.py @@ -0,0 +1,77 @@ +"""Python 'zlib_codec' Codec - zlib compression encoding. + +This codec de/encodes from bytes to bytes. + +Written by Marc-Andre Lemburg (mal@lemburg.com). +""" + +import codecs +import zlib # this codec needs the optional zlib module ! + +### Codec APIs + +def zlib_encode(input, errors='strict'): + assert errors == 'strict' + return (zlib.compress(input), len(input)) + +def zlib_decode(input, errors='strict'): + assert errors == 'strict' + return (zlib.decompress(input), len(input)) + +class Codec(codecs.Codec): + def encode(self, input, errors='strict'): + return zlib_encode(input, errors) + def decode(self, input, errors='strict'): + return zlib_decode(input, errors) + +class IncrementalEncoder(codecs.IncrementalEncoder): + def __init__(self, errors='strict'): + assert errors == 'strict' + self.errors = errors + self.compressobj = zlib.compressobj() + + def encode(self, input, final=False): + if final: + c = self.compressobj.compress(input) + return c + self.compressobj.flush() + else: + return self.compressobj.compress(input) + + def reset(self): + self.compressobj = zlib.compressobj() + +class IncrementalDecoder(codecs.IncrementalDecoder): + def __init__(self, errors='strict'): + assert errors == 'strict' + self.errors = errors + self.decompressobj = zlib.decompressobj() + + def decode(self, input, final=False): + if final: + c = self.decompressobj.decompress(input) + return c + self.decompressobj.flush() + else: + return self.decompressobj.decompress(input) + + def reset(self): + self.decompressobj = zlib.decompressobj() + +class StreamWriter(Codec, codecs.StreamWriter): + charbuffertype = bytes + +class StreamReader(Codec, codecs.StreamReader): + charbuffertype = bytes + +### encodings module API + +def getregentry(): + return codecs.CodecInfo( + name='zlib', + encode=zlib_encode, + decode=zlib_decode, + incrementalencoder=IncrementalEncoder, + incrementaldecoder=IncrementalDecoder, + streamreader=StreamReader, + streamwriter=StreamWriter, + _is_text_encoding=False, + ) |