diff options
author | ilezhankin <ilezhankin@yandex-team.ru> | 2022-02-10 16:45:56 +0300 |
---|---|---|
committer | Daniil Cherednik <dcherednik@yandex-team.ru> | 2022-02-10 16:45:56 +0300 |
commit | 62a805381e41500fbc7914c37c71ab040a098f4e (patch) | |
tree | 1a2c5ffcf89eb53ecd79dbc9bc0a195c27404d0c /contrib/python/Pygments/py3/pygments/lexers/c_cpp.py | |
parent | 1d125034f06575234f83f24f08677955133f140e (diff) | |
download | ydb-62a805381e41500fbc7914c37c71ab040a098f4e.tar.gz |
Restoring authorship annotation for <ilezhankin@yandex-team.ru>. Commit 2 of 2.
Diffstat (limited to 'contrib/python/Pygments/py3/pygments/lexers/c_cpp.py')
-rw-r--r-- | contrib/python/Pygments/py3/pygments/lexers/c_cpp.py | 346 |
1 files changed, 173 insertions, 173 deletions
diff --git a/contrib/python/Pygments/py3/pygments/lexers/c_cpp.py b/contrib/python/Pygments/py3/pygments/lexers/c_cpp.py index 97b957e5d9c..c9d1ed38ead 100644 --- a/contrib/python/Pygments/py3/pygments/lexers/c_cpp.py +++ b/contrib/python/Pygments/py3/pygments/lexers/c_cpp.py @@ -1,34 +1,34 @@ -""" - pygments.lexers.c_cpp - ~~~~~~~~~~~~~~~~~~~~~ - - Lexers for C/C++ languages. - +""" + pygments.lexers.c_cpp + ~~~~~~~~~~~~~~~~~~~~~ + + Lexers for C/C++ languages. + :copyright: Copyright 2006-2021 by the Pygments team, see AUTHORS. - :license: BSD, see LICENSE for details. -""" - -import re - -from pygments.lexer import RegexLexer, include, bygroups, using, \ - this, inherit, default, words -from pygments.util import get_bool_opt -from pygments.token import Text, Comment, Operator, Keyword, Name, String, \ + :license: BSD, see LICENSE for details. +""" + +import re + +from pygments.lexer import RegexLexer, include, bygroups, using, \ + this, inherit, default, words +from pygments.util import get_bool_opt +from pygments.token import Text, Comment, Operator, Keyword, Name, String, \ Number, Punctuation, Whitespace - -__all__ = ['CLexer', 'CppLexer'] - - -class CFamilyLexer(RegexLexer): - """ - For C family source code. This is used as a base class to avoid repetitious - definitions. - """ - - # The trailing ?, rather than *, avoids a geometric performance drop here. - #: only one /* */ style comment - _ws1 = r'\s*(?:/[*].*?[*]/\s*)?' - + +__all__ = ['CLexer', 'CppLexer'] + + +class CFamilyLexer(RegexLexer): + """ + For C family source code. This is used as a base class to avoid repetitious + definitions. + """ + + # The trailing ?, rather than *, avoids a geometric performance drop here. + #: only one /* */ style comment + _ws1 = r'\s*(?:/[*].*?[*]/\s*)?' + # Hexadecimal part in an hexadecimal integer/floating-point literal. # This includes decimal separators matching. _hexpart = r'[0-9a-fA-F](\'?[0-9a-fA-F])*' @@ -42,27 +42,27 @@ class CFamilyLexer(RegexLexer): _ident = r'(?!\d)(?:[\w$]|\\u[0-9a-fA-F]{4}|\\U[0-9a-fA-F]{8})+' _namespaced_ident = r'(?!\d)(?:[\w$]|\\u[0-9a-fA-F]{4}|\\U[0-9a-fA-F]{8}|::)+' - tokens = { - 'whitespace': [ - # preprocessor directives: without whitespace + tokens = { + 'whitespace': [ + # preprocessor directives: without whitespace (r'^#if\s+0', Comment.Preproc, 'if0'), - ('^#', Comment.Preproc, 'macro'), - # or with whitespace - ('^(' + _ws1 + r')(#if\s+0)', - bygroups(using(this), Comment.Preproc), 'if0'), - ('^(' + _ws1 + ')(#)', - bygroups(using(this), Comment.Preproc), 'macro'), + ('^#', Comment.Preproc, 'macro'), + # or with whitespace + ('^(' + _ws1 + r')(#if\s+0)', + bygroups(using(this), Comment.Preproc), 'if0'), + ('^(' + _ws1 + ')(#)', + bygroups(using(this), Comment.Preproc), 'macro'), (r'(^[ \t]*)(?!(?:public|private|protected|default)\b)(case\b\s+)?(' + _ident + r')(\s*)(:)(?!:)', bygroups(Whitespace, using(this), Name.Label, Whitespace, Punctuation)), (r'\n', Whitespace), (r'[^\S\n]+', Whitespace), - (r'\\\n', Text), # line continuation + (r'\\\n', Text), # line continuation (r'//(\n|[\w\W]*?[^\\]\n)', Comment.Single), (r'/(\\\n)?[*][\w\W]*?[*](\\\n)?/', Comment.Multiline), # Open until EOF, so no ending delimeter (r'/(\\\n)?[*][\w\W]*', Comment.Multiline), - ], - 'statements': [ + ], + 'statements': [ include('keywords'), include('types'), (r'([LuU]|u8)?(")', bygroups(String.Affix, String), 'string'), @@ -78,8 +78,8 @@ class CFamilyLexer(RegexLexer): (r'(-)?0[bB][01](\'?[01])*' + _intsuffix, Number.Bin), (r'(-)?0(\'?[0-7])+' + _intsuffix, Number.Oct), (r'(-)?' + _decpart + _intsuffix, Number.Integer), - (r'[~!%^&*+=|?:<>/-]', Operator), - (r'[()\[\],.]', Punctuation), + (r'[~!%^&*+=|?:<>/-]', Operator), + (r'[()\[\],.]', Punctuation), (r'(true|false|NULL)\b', Name.Builtin), (_ident, Name) ], @@ -96,101 +96,101 @@ class CFamilyLexer(RegexLexer): 'if', 'register', 'restricted', 'return', 'sizeof', 'struct', 'static', 'switch', 'typedef', 'volatile', 'while', 'union', 'thread_local', 'alignas', 'alignof', 'static_assert', '_Pragma'), - suffix=r'\b'), Keyword), - (words(('inline', '_inline', '__inline', 'naked', 'restrict', + suffix=r'\b'), Keyword), + (words(('inline', '_inline', '__inline', 'naked', 'restrict', 'thread'), suffix=r'\b'), Keyword.Reserved), - # Vector intrinsics - (r'(__m(128i|128d|128|64))\b', Keyword.Reserved), - # Microsoft-isms - (words(( + # Vector intrinsics + (r'(__m(128i|128d|128|64))\b', Keyword.Reserved), + # Microsoft-isms + (words(( 'asm', 'based', 'except', 'stdcall', 'cdecl', 'fastcall', 'declspec', 'finally', 'try', 'leave', 'w64', 'unaligned', 'raise', 'noop', - 'identifier', 'forceinline', 'assume'), + 'identifier', 'forceinline', 'assume'), prefix=r'__', suffix=r'\b'), Keyword.Reserved) - ], - 'root': [ - include('whitespace'), + ], + 'root': [ + include('whitespace'), include('keywords'), - # functions + # functions (r'(' + _namespaced_ident + r'(?:[&*\s])+)' # return arguments r'(' + _namespaced_ident + r')' # method name r'(\s*\([^;]*?\))' # signature - r'([^;{]*)(\{)', - bygroups(using(this), Name.Function, using(this), using(this), - Punctuation), - 'function'), - # function declarations + r'([^;{]*)(\{)', + bygroups(using(this), Name.Function, using(this), using(this), + Punctuation), + 'function'), + # function declarations (r'(' + _namespaced_ident + r'(?:[&*\s])+)' # return arguments r'(' + _namespaced_ident + r')' # method name r'(\s*\([^;]*?\))' # signature - r'([^;]*)(;)', - bygroups(using(this), Name.Function, using(this), using(this), - Punctuation)), + r'([^;]*)(;)', + bygroups(using(this), Name.Function, using(this), using(this), + Punctuation)), include('types'), - default('statement'), - ], - 'statement': [ - include('whitespace'), - include('statements'), + default('statement'), + ], + 'statement': [ + include('whitespace'), + include('statements'), (r'\}', Punctuation), (r'[{;]', Punctuation, '#pop'), - ], - 'function': [ - include('whitespace'), - include('statements'), - (';', Punctuation), - (r'\{', Punctuation, '#push'), - (r'\}', Punctuation, '#pop'), - ], - 'string': [ - (r'"', String, '#pop'), - (r'\\([\\abfnrtv"\']|x[a-fA-F0-9]{2,4}|' - r'u[a-fA-F0-9]{4}|U[a-fA-F0-9]{8}|[0-7]{1,3})', String.Escape), - (r'[^\\"\n]+', String), # all other characters - (r'\\\n', String), # line continuation - (r'\\', String), # stray backslash - ], - 'macro': [ + ], + 'function': [ + include('whitespace'), + include('statements'), + (';', Punctuation), + (r'\{', Punctuation, '#push'), + (r'\}', Punctuation, '#pop'), + ], + 'string': [ + (r'"', String, '#pop'), + (r'\\([\\abfnrtv"\']|x[a-fA-F0-9]{2,4}|' + r'u[a-fA-F0-9]{4}|U[a-fA-F0-9]{8}|[0-7]{1,3})', String.Escape), + (r'[^\\"\n]+', String), # all other characters + (r'\\\n', String), # line continuation + (r'\\', String), # stray backslash + ], + 'macro': [ (r'('+_ws1+r')(include)('+_ws1+r')("[^"]+")([^\n]*)', bygroups(using(this), Comment.Preproc, using(this), Comment.PreprocFile, Comment.Single)), (r'('+_ws1+r')(include)('+_ws1+r')(<[^>]+>)([^\n]*)', bygroups(using(this), Comment.Preproc, using(this), Comment.PreprocFile, Comment.Single)), - (r'[^/\n]+', Comment.Preproc), - (r'/[*](.|\n)*?[*]/', Comment.Multiline), - (r'//.*?\n', Comment.Single, '#pop'), - (r'/', Comment.Preproc), - (r'(?<=\\)\n', Comment.Preproc), - (r'\n', Comment.Preproc, '#pop'), - ], - 'if0': [ - (r'^\s*#if.*?(?<!\\)\n', Comment.Preproc, '#push'), - (r'^\s*#el(?:se|if).*\n', Comment.Preproc, '#pop'), - (r'^\s*#endif.*?(?<!\\)\n', Comment.Preproc, '#pop'), - (r'.*?\n', Comment), + (r'[^/\n]+', Comment.Preproc), + (r'/[*](.|\n)*?[*]/', Comment.Multiline), + (r'//.*?\n', Comment.Single, '#pop'), + (r'/', Comment.Preproc), + (r'(?<=\\)\n', Comment.Preproc), + (r'\n', Comment.Preproc, '#pop'), + ], + 'if0': [ + (r'^\s*#if.*?(?<!\\)\n', Comment.Preproc, '#push'), + (r'^\s*#el(?:se|if).*\n', Comment.Preproc, '#pop'), + (r'^\s*#endif.*?(?<!\\)\n', Comment.Preproc, '#pop'), + (r'.*?\n', Comment), ], 'classname': [ (_ident, Name.Class, '#pop'), # template specification (r'\s*(?=>)', Text, '#pop'), default('#pop') - ] - } - + ] + } + stdlib_types = { - 'size_t', 'ssize_t', 'off_t', 'wchar_t', 'ptrdiff_t', 'sig_atomic_t', 'fpos_t', - 'clock_t', 'time_t', 'va_list', 'jmp_buf', 'FILE', 'DIR', 'div_t', 'ldiv_t', + 'size_t', 'ssize_t', 'off_t', 'wchar_t', 'ptrdiff_t', 'sig_atomic_t', 'fpos_t', + 'clock_t', 'time_t', 'va_list', 'jmp_buf', 'FILE', 'DIR', 'div_t', 'ldiv_t', 'mbstate_t', 'wctrans_t', 'wint_t', 'wctype_t'} c99_types = { 'int8_t', 'int16_t', 'int32_t', 'int64_t', 'uint8_t', - 'uint16_t', 'uint32_t', 'uint64_t', 'int_least8_t', 'int_least16_t', - 'int_least32_t', 'int_least64_t', 'uint_least8_t', 'uint_least16_t', - 'uint_least32_t', 'uint_least64_t', 'int_fast8_t', 'int_fast16_t', 'int_fast32_t', - 'int_fast64_t', 'uint_fast8_t', 'uint_fast16_t', 'uint_fast32_t', 'uint_fast64_t', + 'uint16_t', 'uint32_t', 'uint64_t', 'int_least8_t', 'int_least16_t', + 'int_least32_t', 'int_least64_t', 'uint_least8_t', 'uint_least16_t', + 'uint_least32_t', 'uint_least64_t', 'int_fast8_t', 'int_fast16_t', 'int_fast32_t', + 'int_fast64_t', 'uint_fast8_t', 'uint_fast16_t', 'uint_fast32_t', 'uint_fast64_t', 'intptr_t', 'uintptr_t', 'intmax_t', 'uintmax_t'} linux_types = { - 'clockid_t', 'cpu_set_t', 'cpumask_t', 'dev_t', 'gid_t', 'id_t', 'ino_t', 'key_t', - 'mode_t', 'nfds_t', 'pid_t', 'rlim_t', 'sig_t', 'sighandler_t', 'siginfo_t', + 'clockid_t', 'cpu_set_t', 'cpumask_t', 'dev_t', 'gid_t', 'id_t', 'ino_t', 'key_t', + 'mode_t', 'nfds_t', 'pid_t', 'rlim_t', 'sig_t', 'sighandler_t', 'siginfo_t', 'sigset_t', 'sigval_t', 'socklen_t', 'timer_t', 'uid_t'} c11_atomic_types = { 'atomic_bool', 'atomic_char', 'atomic_schar', 'atomic_uchar', 'atomic_short', @@ -203,32 +203,32 @@ class CFamilyLexer(RegexLexer): 'atomic_int_fast32_t', 'atomic_uint_fast32_t', 'atomic_int_fast64_t', 'atomic_uint_fast64_t', 'atomic_intptr_t', 'atomic_uintptr_t', 'atomic_size_t', 'atomic_ptrdiff_t', 'atomic_intmax_t', 'atomic_uintmax_t'} - - def __init__(self, **options): - self.stdlibhighlighting = get_bool_opt(options, 'stdlibhighlighting', True) - self.c99highlighting = get_bool_opt(options, 'c99highlighting', True) + + def __init__(self, **options): + self.stdlibhighlighting = get_bool_opt(options, 'stdlibhighlighting', True) + self.c99highlighting = get_bool_opt(options, 'c99highlighting', True) self.c11highlighting = get_bool_opt(options, 'c11highlighting', True) - self.platformhighlighting = get_bool_opt(options, 'platformhighlighting', True) - RegexLexer.__init__(self, **options) - - def get_tokens_unprocessed(self, text): - for index, token, value in \ - RegexLexer.get_tokens_unprocessed(self, text): - if token is Name: - if self.stdlibhighlighting and value in self.stdlib_types: - token = Keyword.Type - elif self.c99highlighting and value in self.c99_types: - token = Keyword.Type + self.platformhighlighting = get_bool_opt(options, 'platformhighlighting', True) + RegexLexer.__init__(self, **options) + + def get_tokens_unprocessed(self, text): + for index, token, value in \ + RegexLexer.get_tokens_unprocessed(self, text): + if token is Name: + if self.stdlibhighlighting and value in self.stdlib_types: + token = Keyword.Type + elif self.c99highlighting and value in self.c99_types: + token = Keyword.Type elif self.c11highlighting and value in self.c11_atomic_types: token = Keyword.Type - elif self.platformhighlighting and value in self.linux_types: - token = Keyword.Type - yield index, token, value - - -class CLexer(CFamilyLexer): - """ - For C source code with preprocessor directives. + elif self.platformhighlighting and value in self.linux_types: + token = Keyword.Type + yield index, token, value + + +class CLexer(CFamilyLexer): + """ + For C source code with preprocessor directives. Additional options accepted: @@ -248,13 +248,13 @@ class CLexer(CFamilyLexer): `platformhighlighting` Highlight common types found in the platform SDK headers (e.g. `clockid_t` on Linux). (default: ``True``). - """ - name = 'C' - aliases = ['c'] + """ + name = 'C' + aliases = ['c'] filenames = ['*.c', '*.h', '*.idc', '*.x[bp]m'] mimetypes = ['text/x-chdr', 'text/x-csrc', 'image/x-xbitmap', 'image/x-xpixmap'] - priority = 0.1 - + priority = 0.1 + tokens = { 'keywords': [ (words(( @@ -269,16 +269,16 @@ class CLexer(CFamilyLexer): ] } - def analyse_text(text): + def analyse_text(text): if re.search(r'^\s*#include [<"]', text, re.MULTILINE): - return 0.1 + return 0.1 if re.search(r'^\s*#ifn?def ', text, re.MULTILINE): - return 0.1 - - -class CppLexer(CFamilyLexer): - """ - For C++ source code with preprocessor directives. + return 0.1 + + +class CppLexer(CFamilyLexer): + """ + For C++ source code with preprocessor directives. Additional options accepted: @@ -298,39 +298,39 @@ class CppLexer(CFamilyLexer): `platformhighlighting` Highlight common types found in the platform SDK headers (e.g. `clockid_t` on Linux). (default: ``True``). - """ - name = 'C++' - aliases = ['cpp', 'c++'] - filenames = ['*.cpp', '*.hpp', '*.c++', '*.h++', - '*.cc', '*.hh', '*.cxx', '*.hxx', - '*.C', '*.H', '*.cp', '*.CPP'] - mimetypes = ['text/x-c++hdr', 'text/x-c++src'] - priority = 0.1 - - tokens = { - 'statements': [ + """ + name = 'C++' + aliases = ['cpp', 'c++'] + filenames = ['*.cpp', '*.hpp', '*.c++', '*.h++', + '*.cc', '*.hh', '*.cxx', '*.hxx', + '*.C', '*.H', '*.cp', '*.CPP'] + mimetypes = ['text/x-c++hdr', 'text/x-c++src'] + priority = 0.1 + + tokens = { + 'statements': [ # C++11 raw strings (r'((?:[LuU]|u8)?R)(")([^\\()\s]{,16})(\()((?:.|\n)*?)(\)\3)(")', bygroups(String.Affix, String, String.Delimiter, String.Delimiter, String, String.Delimiter, String)), - inherit, - ], - 'root': [ - inherit, - # C++ Microsoft-isms - (words(('virtual_inheritance', 'uuidof', 'super', 'single_inheritance', - 'multiple_inheritance', 'interface', 'event'), - prefix=r'__', suffix=r'\b'), Keyword.Reserved), - # Offload C++ extensions, http://offload.codeplay.com/ - (r'__(offload|blockingoffload|outer)\b', Keyword.Pseudo), - ], + inherit, + ], + 'root': [ + inherit, + # C++ Microsoft-isms + (words(('virtual_inheritance', 'uuidof', 'super', 'single_inheritance', + 'multiple_inheritance', 'interface', 'event'), + prefix=r'__', suffix=r'\b'), Keyword.Reserved), + # Offload C++ extensions, http://offload.codeplay.com/ + (r'__(offload|blockingoffload|outer)\b', Keyword.Pseudo), + ], 'enumname': [ include('whitespace'), # 'enum class' and 'enum struct' C++11 support (words(('class', 'struct'), suffix=r'\b'), Keyword), (CFamilyLexer._ident, Name.Class, '#pop'), - # template specification - (r'\s*(?=>)', Text, '#pop'), + # template specification + (r'\s*(?=>)', Text, '#pop'), default('#pop') ], 'keywords': [ @@ -359,10 +359,10 @@ class CppLexer(CFamilyLexer): (CFamilyLexer._ident, Name.Namespace), include('statement') ] - } - - def analyse_text(text): + } + + def analyse_text(text): if re.search('#include <[a-z_]+>', text): - return 0.2 - if re.search('using namespace ', text): - return 0.4 + return 0.2 + if re.search('using namespace ', text): + return 0.4 |