# -*- coding: utf-8 -*- """ pygments.lexers.c_cpp ~~~~~~~~~~~~~~~~~~~~~ Lexers for C/C++ languages. :copyright: Copyright 2006-2014 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, \ Number, Punctuation, Error __all__ = ['CLexer', 'CppLexer'] class CFamilyLexer(RegexLexer): """ For C family source code. This is used as a base class to avoid repetitious definitions. """ #: optional Comment or Whitespace _ws = r'(?:\s|//.*?\n|/[*].*?[*]/)+' #: only one /* */ style comment _ws1 = r'\s*(?:/[*].*?[*]/\s*)*' tokens = { 'whitespace': [ # preprocessor directives: without whitespace ('^#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'), (r'\n', Text), (r'\s+', Text), (r'\\\n', Text), # line continuation (r'//(\n|(.|\n)*?[^\\]\n)', Comment.Single), (r'/(\\\n)?[*](.|\n)*?[*](\\\n)?/', Comment.Multiline), ], 'statements': [ (r'L?"', String, 'string'), (r"L?'(\\.|\\[0-7]{1,3}|\\x[a-fA-F0-9]{1,2}|[^\\\'\n])'", String.Char), (r'(\d+\.\d*|\.\d+|\d+)[eE][+-]?\d+[LlUu]*', Number.Float), (r'(\d+\.\d*|\.\d+|\d+[fF])[fF]?', Number.Float), (r'0x[0-9a-fA-F]+[LlUu]*', Number.Hex), (r'0[0-7]+[LlUu]*', Number.Oct), (r'\d+[LlUu]*', Number.Integer), (r'\*/', Error), (r'[~!%^&*+=|?:<>/-]', Operator), (r'[()\[\],.]', Punctuation), (words(('auto', 'break', 'case', 'const', 'continue', 'default', 'do', 'else', 'enum', 'extern', 'for', 'goto', 'if', 'register', 'restricted', 'return', 'sizeof', 'static', 'struct', 'switch', 'typedef', 'union', 'volatile', 'while'), suffix=r'\b'), Keyword), (r'(bool|int|long|float|short|double|char|unsigned|signed|void|' r'[a-z_][a-z0-9_]*_t)\b', Keyword.Type), (words(('inline', '_inline', '__inline', 'naked', 'restrict', 'thread', 'typename'), suffix=r'\b'), Keyword.Reserved), # Vector intrinsics (r'(__m(128i|128d|128|64))\b', Keyword.Reserved), # Microsoft-isms (words(( 'asm', 'int8', 'based', 'except', 'int16', 'stdcall', 'cdecl', 'fastcall', 'int32', 'declspec', 'finally', 'int64', 'try', 'leave', 'wchar_t', 'w64', 'unaligned', 'raise', 'noop', 'identifier', 'forceinline', 'assume'), prefix=r'__', suffix=r'\b'), Keyword.Reserved), (r'(true|false|NULL)\b', Name.Builtin), (r'([a-zA-Z_]\w*)(\s*)(:)(?!:)', bygroups(Name.Label, Text, Punctuation)), ('[a-zA-Z_]\w*', Name), ], 'root': [ include('whitespace'), # functions (r'((?:[\w*\s])+?(?:\s|[*]))' # return arguments r'([a-zA-Z_]\w*)' # method name r'(\s*\([^;]*?\))' # signature r'(' + _ws + r')?(\{)', bygroups(using(this), Name.Function, using(this), using(this), Punctuation), 'function'), # function declarations (r'((?:[\w*\s])+?(?:\s|[*]))' # return arguments r'([a-zA-Z_]\w*)' # method name r'(\s*\([^;]*?\))' # signature r'(' + _ws + r')?(;)', bygroups(using(this), Name.Function, using(this), using(this), Punctuation)), default('statement'), ], 'statement': [ include('whitespace'), include('statements'), ('[{}]', Punctuation), (';', 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': [ (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.*?(?)', Text, '#pop'), ], } def analyse_text(text): if re.search('#include <[a-z]+>', text): return 0.2 if re.search('using namespace ', text): return 0.4