diff options
author | orivej <orivej@yandex-team.ru> | 2022-02-10 16:44:49 +0300 |
---|---|---|
committer | Daniil Cherednik <dcherednik@yandex-team.ru> | 2022-02-10 16:44:49 +0300 |
commit | 718c552901d703c502ccbefdfc3c9028d608b947 (patch) | |
tree | 46534a98bbefcd7b1f3faa5b52c138ab27db75b7 /contrib/tools/cython/Cython/Compiler/StringEncoding.py | |
parent | e9656aae26e0358d5378e5b63dcac5c8dbe0e4d0 (diff) | |
download | ydb-718c552901d703c502ccbefdfc3c9028d608b947.tar.gz |
Restoring authorship annotation for <orivej@yandex-team.ru>. Commit 1 of 2.
Diffstat (limited to 'contrib/tools/cython/Cython/Compiler/StringEncoding.py')
-rw-r--r-- | contrib/tools/cython/Cython/Compiler/StringEncoding.py | 50 |
1 files changed, 25 insertions, 25 deletions
diff --git a/contrib/tools/cython/Cython/Compiler/StringEncoding.py b/contrib/tools/cython/Cython/Compiler/StringEncoding.py index c37e8aab79..ee2df88a2f 100644 --- a/contrib/tools/cython/Cython/Compiler/StringEncoding.py +++ b/contrib/tools/cython/Cython/Compiler/StringEncoding.py @@ -8,10 +8,10 @@ import re import sys if sys.version_info[0] >= 3: - _unicode, _str, _bytes, _unichr = str, str, bytes, chr + _unicode, _str, _bytes, _unichr = str, str, bytes, chr IS_PYTHON3 = True else: - _unicode, _str, _bytes, _unichr = unicode, str, str, unichr + _unicode, _str, _bytes, _unichr = unicode, str, str, unichr IS_PYTHON3 = False empty_bytes = _bytes() @@ -39,13 +39,13 @@ class UnicodeLiteralBuilder(object): # wide Unicode character on narrow platform => replace # by surrogate pair char_number -= 0x10000 - self.chars.append( _unichr((char_number // 1024) + 0xD800) ) - self.chars.append( _unichr((char_number % 1024) + 0xDC00) ) + self.chars.append( _unichr((char_number // 1024) + 0xD800) ) + self.chars.append( _unichr((char_number % 1024) + 0xDC00) ) else: - self.chars.append( _unichr(char_number) ) + self.chars.append( _unichr(char_number) ) else: def append_charval(self, char_number): - self.chars.append( _unichr(char_number) ) + self.chars.append( _unichr(char_number) ) def append_uescape(self, char_number, escape_string): self.append_charval(char_number) @@ -71,14 +71,14 @@ class BytesLiteralBuilder(object): self.chars.append(characters) def append_charval(self, char_number): - self.chars.append( _unichr(char_number).encode('ISO-8859-1') ) + self.chars.append( _unichr(char_number).encode('ISO-8859-1') ) def append_uescape(self, char_number, escape_string): self.append(escape_string) def getstring(self): # this *must* return a byte string! - return bytes_literal(join_bytes(self.chars), self.target_encoding) + return bytes_literal(join_bytes(self.chars), self.target_encoding) def getchar(self): # this *must* return a byte string! @@ -135,10 +135,10 @@ class EncodedString(_unicode): def contains_surrogates(self): return string_contains_surrogates(self) - def as_utf8_string(self): - return bytes_literal(self.utf8encode(), 'utf8') - + def as_utf8_string(self): + return bytes_literal(self.utf8encode(), 'utf8') + def string_contains_surrogates(ustring): """ Check if the unicode string contains surrogate code points @@ -207,18 +207,18 @@ class BytesLiteral(_bytes): is_unicode = False - def as_c_string_literal(self): - value = split_string_literal(escape_byte_string(self)) - return '"%s"' % value - - -def bytes_literal(s, encoding): - assert isinstance(s, bytes) - s = BytesLiteral(s) - s.encoding = encoding - return s - - + def as_c_string_literal(self): + value = split_string_literal(escape_byte_string(self)) + return '"%s"' % value + + +def bytes_literal(s, encoding): + assert isinstance(s, bytes) + s = BytesLiteral(s) + s.encoding = encoding + return s + + def encoded_string(s, encoding): assert isinstance(s, (_unicode, bytes)) s = EncodedString(s) @@ -338,7 +338,7 @@ def split_string_literal(s, limit=2000): def encode_pyunicode_string(s): """Create Py_UNICODE[] representation of a given unicode string. """ - s = list(map(ord, s)) + [0] + s = list(map(ord, s)) + [0] if sys.maxunicode >= 0x10000: # Wide build or Py3.3 utf16, utf32 = [], s @@ -360,4 +360,4 @@ def encode_pyunicode_string(s): if utf16 == utf32: utf16 = [] - return ",".join(map(_unicode, utf16)), ",".join(map(_unicode, utf32)) + return ",".join(map(_unicode, utf16)), ",".join(map(_unicode, utf32)) |