"""
pygments.lexers.c_cpp
~~~~~~~~~~~~~~~~~~~~~
Lexers for C/C++ languages.
:copyright: Copyright 2006-2025 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, 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*)?'
# Hexadecimal part in an hexadecimal integer/floating-point literal.
# This includes decimal separators matching.
_hexpart = r'[0-9a-fA-F](\'?[0-9a-fA-F])*'
# Decimal part in an decimal integer/floating-point literal.
# This includes decimal separators matching.
_decpart = r'\d(\'?\d)*'
# Integer literal suffix (e.g. 'ull' or 'll').
_intsuffix = r'(([uU][lL]{0,2})|[lL]{1,2}[uU]?)?'
# Identifier regex with C and C++ Universal Character Name (UCN) support.
_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}|::)+'
# Single and multiline comment regexes
# Beware not to use *? for the inner content! When these regexes
# are embedded in larger regexes, that can cause the stuff*? to
# match more than it would have if the regex had been used in
# a standalone way ...
_comment_single = r'//(?:.|(?<=\\)\n)*\n'
_comment_multiline = r'/(?:\\\n)?[*](?:[^*]|[*](?!(?:\\\n)?/))*[*](?:\\\n)?/'
# Regex to match optional comments
_possible_comments = rf'\s*(?:(?:(?:{_comment_single})|(?:{_comment_multiline}))\s*)*'
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'),
# Labels:
# Line start and possible indentation.
(r'(^[ \t]*)'
# Not followed by keywords which can be mistaken as labels.
r'(?!(?:public|private|protected|default)\b)'
# Actual label, followed by a single colon.
r'(' + _ident + r')(\s*)(:)(?!:)',
bygroups(Whitespace, Name.Label, Whitespace, Punctuation)),
(r'\n', Whitespace),
(r'[^\S\n]+', Whitespace),
(r'\\\n', Text), # line continuation
(_comment_single, Comment.Single),
(_comment_multiline, Comment.Multiline),
# Open until EOF, so no ending delimiter
(r'/(\\\n)?[*][\w\W]*', Comment.Multiline),
],
'statements': [
include('keywords'),
include('types'),
(r'([LuU]|u8)?(")', bygroups(String.Affix, String), 'string'),
(r"([LuU]|u8)?(')(\\.|\\[0-7]{1,3}|\\x[a-fA-F0-9]{1,2}|[^\\\'\n])(')",
bygroups(String.Affix, String.Char, String.Char, String.Char)),
# Hexadecimal floating-point literals (C11, C++17)
(r'0[xX](' + _hexpart + r'\.' + _hexpart + r'|\.' + _hexpart +
r'|' + _hexpart + r')[pP][+-]?' + _hexpart + r'[lL]?', Number.Float),
(r'(-)?(' + _decpart + r'\.' + _decpart + r'|\.' + _decpart + r'|' +
_decpart + r')[eE][+-]?' + _decpart + r'[fFlL]?', Number.Float),
(r'(-)?((' + _decpart + r'\.(' + _decpart + r')?|\.' +
_decpart + r')[fFlL]?)|(' + _decpart + r'[fFlL])', Number.Float),
(r'(-)?0[xX]' + _hexpart + _intsuffix, Number.Hex),
(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'(true|false|NULL)\b', Name.Builtin),
(_ident, Name)
],
'types': [
(words(('int8', 'int16', 'int32', 'int64', 'wchar_t'), prefix=r'__',
suffix=r'\b'), Keyword.Reserved),
(words(('bool', 'int', 'long', 'float', 'short', 'double', 'char',
'unsigned', 'signed', 'void', '_BitInt',
'__int128'), suffix=r'\b'), Keyword.Type)
],
'keywords': [
(r'(struct|union)(\s+)', bygroups(Keyword, Whitespace), 'classname'),
(r'case\b', Keyword, 'case-value'),
(words(('asm', 'auto', 'break', 'const', 'continue', 'default',
'do', 'else', 'enum', 'extern', 'for', 'goto', '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',
'thread'), suffix=r'\b'), Keyword.Reserved),
# 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'),
prefix=r'__', suffix=r'\b'), Keyword.Reserved)
],
'root': [
include('whitespace'),
include('keywords'),
# functions
(r'(' + _namespaced_ident + r'(?:[&*\s])+)' # return arguments
r'(' + _possible_comments + r')'
r'(' + _namespaced_ident + r')' # method name
r'(' + _possible_comments + r')'
r'(\([^;"\')]*?\))' # signature
r'(' + _possible_comments + r')'
r'([^;{/"\']*)(\{)',
bygroups(using(this), using(this, state='whitespace'),
Name.Function, using(this, state='whitespace'),
using(this), using(this, state='whitespace'),
using(this), Punctuation),
'function'),
# function declarations
(r'(' + _namespaced_ident + r'(?:[&*\s])+)' # return arguments
r'(' + _possible_comments + r')'
r'(' + _namespaced_ident + r')' # method name
r'(' + _possible_comments + r')'
r'(\([^;"\')]*?\))' # signature
r'(' + _possible_comments + r')'
r'([^;/"\']*)(;)',
bygroups(using(this), using(this, state='whitespace'),
Name.Function, using(this, state='whitespace'),
using(this), using(this, state='whitespace'),
using(this), Punctuation)),
include('types'),
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': [
(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.*?(?)', Text, '#pop'),
default('#pop')
],
# Mark identifiers preceded by `case` keyword as constants.
'case-value': [
(r'(?)', Text, '#pop'),
default('#pop')
],
'keywords': [
(r'(class|concept|typename)(\s+)', bygroups(Keyword, Whitespace), 'classname'),
(words((
'catch', 'const_cast', 'delete', 'dynamic_cast', 'explicit',
'export', 'friend', 'mutable', 'new', 'operator',
'private', 'protected', 'public', 'reinterpret_cast', 'class',
'__restrict', 'static_cast', 'template', 'this', 'throw', 'throws',
'try', 'typeid', 'using', 'virtual', 'constexpr', 'nullptr', 'concept',
'decltype', 'noexcept', 'override', 'final', 'constinit', 'consteval',
'co_await', 'co_return', 'co_yield', 'requires', 'import', 'module',
'typename', 'and', 'and_eq', 'bitand', 'bitor', 'compl', 'not',
'not_eq', 'or', 'or_eq', 'xor', 'xor_eq'),
suffix=r'\b'), Keyword),
(r'namespace\b', Keyword, 'namespace'),
(r'(enum)(\s+)', bygroups(Keyword, Whitespace), 'enumname'),
inherit
],
'types': [
(r'char(16_t|32_t|8_t)\b', Keyword.Type),
inherit
],
'namespace': [
(r'[;{]', Punctuation, ('#pop', 'root')),
(r'inline\b', Keyword.Reserved),
(CFamilyLexer._ident, Name.Namespace),
include('statement')
]
}
def analyse_text(text):
if re.search('#include <[a-z_]+>', text):
return 0.2
if re.search('using namespace ', text):
return 0.4