Shortcuts on this page
r m x toggle line displays
j k next/prev highlighted chunk
0 (zero) top of page
1 (one) first highlighted chunk
1"""
2 pygments.lexers.c_cpp
3 ~~~~~~~~~~~~~~~~~~~~~
5 Lexers for C/C++ languages.
7 :copyright: Copyright 2006-2025 by the Pygments team, see AUTHORS.
8 :license: BSD, see LICENSE for details.
9"""
11import re
13from pygments.lexer import RegexLexer, include, bygroups, using, \
14 this, inherit, default, words
15from pygments.util import get_bool_opt
16from pygments.token import Text, Comment, Operator, Keyword, Name, String, \
17 Number, Punctuation, Whitespace
19__all__ = ['CLexer', 'CppLexer']
22class CFamilyLexer(RegexLexer):
23 """
24 For C family source code. This is used as a base class to avoid repetitious
25 definitions.
26 """
28 # The trailing ?, rather than *, avoids a geometric performance drop here.
29 #: only one /* */ style comment
30 _ws1 = r'\s*(?:/[*].*?[*]/\s*)?'
32 # Hexadecimal part in an hexadecimal integer/floating-point literal.
33 # This includes decimal separators matching.
34 _hexpart = r'[0-9a-fA-F](\'?[0-9a-fA-F])*'
35 # Decimal part in an decimal integer/floating-point literal.
36 # This includes decimal separators matching.
37 _decpart = r'\d(\'?\d)*'
38 # Integer literal suffix (e.g. 'ull' or 'll').
39 _intsuffix = r'(([uU][lL]{0,2})|[lL]{1,2}[uU]?)?'
41 # Identifier regex with C and C++ Universal Character Name (UCN) support.
42 _ident = r'(?!\d)(?:[\w$]|\\u[0-9a-fA-F]{4}|\\U[0-9a-fA-F]{8})+'
43 _namespaced_ident = r'(?!\d)(?:[\w$]|\\u[0-9a-fA-F]{4}|\\U[0-9a-fA-F]{8}|::)+'
45 # Single and multiline comment regexes
46 # Beware not to use *? for the inner content! When these regexes
47 # are embedded in larger regexes, that can cause the stuff*? to
48 # match more than it would have if the regex had been used in
49 # a standalone way ...
50 _comment_single = r'//(?:.|(?<=\\)\n)*\n'
51 _comment_multiline = r'/(?:\\\n)?[*](?:[^*]|[*](?!(?:\\\n)?/))*[*](?:\\\n)?/'
53 # Regex to match optional comments
54 _possible_comments = rf'\s*(?:(?:(?:{_comment_single})|(?:{_comment_multiline}))\s*)*'
56 tokens = {
57 'whitespace': [
58 # preprocessor directives: without whitespace
59 (r'^#if\s+0', Comment.Preproc, 'if0'),
60 ('^#', Comment.Preproc, 'macro'),
61 # or with whitespace
62 ('^(' + _ws1 + r')(#if\s+0)',
63 bygroups(using(this), Comment.Preproc), 'if0'),
64 ('^(' + _ws1 + ')(#)',
65 bygroups(using(this), Comment.Preproc), 'macro'),
66 # Labels:
67 # Line start and possible indentation.
68 (r'(^[ \t]*)'
69 # Not followed by keywords which can be mistaken as labels.
70 r'(?!(?:public|private|protected|default)\b)'
71 # Actual label, followed by a single colon.
72 r'(' + _ident + r')(\s*)(:)(?!:)',
73 bygroups(Whitespace, Name.Label, Whitespace, Punctuation)),
74 (r'\n', Whitespace),
75 (r'[^\S\n]+', Whitespace),
76 (r'\\\n', Text), # line continuation
77 (_comment_single, Comment.Single),
78 (_comment_multiline, Comment.Multiline),
79 # Open until EOF, so no ending delimiter
80 (r'/(\\\n)?[*][\w\W]*', Comment.Multiline),
81 ],
82 'statements': [
83 include('keywords'),
84 include('types'),
85 (r'([LuU]|u8)?(")', bygroups(String.Affix, String), 'string'),
86 (r"([LuU]|u8)?(')(\\.|\\[0-7]{1,3}|\\x[a-fA-F0-9]{1,2}|[^\\\'\n])(')",
87 bygroups(String.Affix, String.Char, String.Char, String.Char)),
89 # Hexadecimal floating-point literals (C11, C++17)
90 (r'0[xX](' + _hexpart + r'\.' + _hexpart + r'|\.' + _hexpart +
91 r'|' + _hexpart + r')[pP][+-]?' + _hexpart + r'[lL]?', Number.Float),
93 (r'(-)?(' + _decpart + r'\.' + _decpart + r'|\.' + _decpart + r'|' +
94 _decpart + r')[eE][+-]?' + _decpart + r'[fFlL]?', Number.Float),
95 (r'(-)?((' + _decpart + r'\.(' + _decpart + r')?|\.' +
96 _decpart + r')[fFlL]?)|(' + _decpart + r'[fFlL])', Number.Float),
97 (r'(-)?0[xX]' + _hexpart + _intsuffix, Number.Hex),
98 (r'(-)?0[bB][01](\'?[01])*' + _intsuffix, Number.Bin),
99 (r'(-)?0(\'?[0-7])+' + _intsuffix, Number.Oct),
100 (r'(-)?' + _decpart + _intsuffix, Number.Integer),
101 (r'[~!%^&*+=|?:<>/-]', Operator),
102 (r'[()\[\],.]', Punctuation),
103 (r'(true|false|NULL)\b', Name.Builtin),
104 (_ident, Name)
105 ],
106 'types': [
107 (words(('int8', 'int16', 'int32', 'int64', 'wchar_t'), prefix=r'__',
108 suffix=r'\b'), Keyword.Reserved),
109 (words(('bool', 'int', 'long', 'float', 'short', 'double', 'char',
110 'unsigned', 'signed', 'void', '_BitInt',
111 '__int128'), suffix=r'\b'), Keyword.Type)
112 ],
113 'keywords': [
114 (r'(struct|union)(\s+)', bygroups(Keyword, Whitespace), 'classname'),
115 (r'case\b', Keyword, 'case-value'),
116 (words(('asm', 'auto', 'break', 'const', 'continue', 'default',
117 'do', 'else', 'enum', 'extern', 'for', 'goto', 'if',
118 'register', 'restricted', 'return', 'sizeof', 'struct',
119 'static', 'switch', 'typedef', 'volatile', 'while', 'union',
120 'thread_local', 'alignas', 'alignof', 'static_assert', '_Pragma'),
121 suffix=r'\b'), Keyword),
122 (words(('inline', '_inline', '__inline', 'naked', 'restrict',
123 'thread'), suffix=r'\b'), Keyword.Reserved),
124 # Vector intrinsics
125 (r'(__m(128i|128d|128|64))\b', Keyword.Reserved),
126 # Microsoft-isms
127 (words((
128 'asm', 'based', 'except', 'stdcall', 'cdecl',
129 'fastcall', 'declspec', 'finally', 'try',
130 'leave', 'w64', 'unaligned', 'raise', 'noop',
131 'identifier', 'forceinline', 'assume'),
132 prefix=r'__', suffix=r'\b'), Keyword.Reserved)
133 ],
134 'root': [
135 include('whitespace'),
136 include('keywords'),
137 # functions
138 (r'(' + _namespaced_ident + r'(?:[&*\s])+)' # return arguments
139 r'(' + _possible_comments + r')'
140 r'(' + _namespaced_ident + r')' # method name
141 r'(' + _possible_comments + r')'
142 r'(\([^;"\')]*?\))' # signature
143 r'(' + _possible_comments + r')'
144 r'([^;{/"\']*)(\{)',
145 bygroups(using(this), using(this, state='whitespace'),
146 Name.Function, using(this, state='whitespace'),
147 using(this), using(this, state='whitespace'),
148 using(this), Punctuation),
149 'function'),
150 # function declarations
151 (r'(' + _namespaced_ident + r'(?:[&*\s])+)' # return arguments
152 r'(' + _possible_comments + r')'
153 r'(' + _namespaced_ident + r')' # method name
154 r'(' + _possible_comments + r')'
155 r'(\([^;"\')]*?\))' # signature
156 r'(' + _possible_comments + r')'
157 r'([^;/"\']*)(;)',
158 bygroups(using(this), using(this, state='whitespace'),
159 Name.Function, using(this, state='whitespace'),
160 using(this), using(this, state='whitespace'),
161 using(this), Punctuation)),
162 include('types'),
163 default('statement'),
164 ],
165 'statement': [
166 include('whitespace'),
167 include('statements'),
168 (r'\}', Punctuation),
169 (r'[{;]', Punctuation, '#pop'),
170 ],
171 'function': [
172 include('whitespace'),
173 include('statements'),
174 (';', Punctuation),
175 (r'\{', Punctuation, '#push'),
176 (r'\}', Punctuation, '#pop'),
177 ],
178 'string': [
179 (r'"', String, '#pop'),
180 (r'\\([\\abfnrtv"\']|x[a-fA-F0-9]{2,4}|'
181 r'u[a-fA-F0-9]{4}|U[a-fA-F0-9]{8}|[0-7]{1,3})', String.Escape),
182 (r'[^\\"\n]+', String), # all other characters
183 (r'\\\n', String), # line continuation
184 (r'\\', String), # stray backslash
185 ],
186 'macro': [
187 (r'('+_ws1+r')(include)('+_ws1+r')("[^"]+")([^\n]*)',
188 bygroups(using(this), Comment.Preproc, using(this),
189 Comment.PreprocFile, Comment.Single)),
190 (r'('+_ws1+r')(include)('+_ws1+r')(<[^>]+>)([^\n]*)',
191 bygroups(using(this), Comment.Preproc, using(this),
192 Comment.PreprocFile, Comment.Single)),
193 (r'[^/\n]+', Comment.Preproc),
194 (r'/[*](.|\n)*?[*]/', Comment.Multiline),
195 (r'//.*?\n', Comment.Single, '#pop'),
196 (r'/', Comment.Preproc),
197 (r'(?<=\\)\n', Comment.Preproc),
198 (r'\n', Comment.Preproc, '#pop'),
199 ],
200 'if0': [
201 (r'^\s*#if.*?(?<!\\)\n', Comment.Preproc, '#push'),
202 (r'^\s*#el(?:se|if).*\n', Comment.Preproc, '#pop'),
203 (r'^\s*#endif.*?(?<!\\)\n', Comment.Preproc, '#pop'),
204 (r'.*?\n', Comment),
205 ],
206 'classname': [
207 (_ident, Name.Class, '#pop'),
208 # template specification
209 (r'\s*(?=>)', Text, '#pop'),
210 default('#pop')
211 ],
212 # Mark identifiers preceded by `case` keyword as constants.
213 'case-value': [
214 (r'(?<!:)(:)(?!:)', Punctuation, '#pop'),
215 (_ident, Name.Constant),
216 include('whitespace'),
217 include('statements'),
218 ]
219 }
221 stdlib_types = {
222 'size_t', 'ssize_t', 'off_t', 'wchar_t', 'ptrdiff_t', 'sig_atomic_t', 'fpos_t',
223 'clock_t', 'time_t', 'va_list', 'jmp_buf', 'FILE', 'DIR', 'div_t', 'ldiv_t',
224 'mbstate_t', 'wctrans_t', 'wint_t', 'wctype_t'}
225 c99_types = {
226 'int8_t', 'int16_t', 'int32_t', 'int64_t', 'uint8_t',
227 'uint16_t', 'uint32_t', 'uint64_t', 'int_least8_t', 'int_least16_t',
228 'int_least32_t', 'int_least64_t', 'uint_least8_t', 'uint_least16_t',
229 'uint_least32_t', 'uint_least64_t', 'int_fast8_t', 'int_fast16_t', 'int_fast32_t',
230 'int_fast64_t', 'uint_fast8_t', 'uint_fast16_t', 'uint_fast32_t', 'uint_fast64_t',
231 'intptr_t', 'uintptr_t', 'intmax_t', 'uintmax_t'}
232 linux_types = {
233 'clockid_t', 'cpu_set_t', 'cpumask_t', 'dev_t', 'gid_t', 'id_t', 'ino_t', 'key_t',
234 'mode_t', 'nfds_t', 'pid_t', 'rlim_t', 'sig_t', 'sighandler_t', 'siginfo_t',
235 'sigset_t', 'sigval_t', 'socklen_t', 'timer_t', 'uid_t'}
236 c11_atomic_types = {
237 'atomic_bool', 'atomic_char', 'atomic_schar', 'atomic_uchar', 'atomic_short',
238 'atomic_ushort', 'atomic_int', 'atomic_uint', 'atomic_long', 'atomic_ulong',
239 'atomic_llong', 'atomic_ullong', 'atomic_char16_t', 'atomic_char32_t', 'atomic_wchar_t',
240 'atomic_int_least8_t', 'atomic_uint_least8_t', 'atomic_int_least16_t',
241 'atomic_uint_least16_t', 'atomic_int_least32_t', 'atomic_uint_least32_t',
242 'atomic_int_least64_t', 'atomic_uint_least64_t', 'atomic_int_fast8_t',
243 'atomic_uint_fast8_t', 'atomic_int_fast16_t', 'atomic_uint_fast16_t',
244 'atomic_int_fast32_t', 'atomic_uint_fast32_t', 'atomic_int_fast64_t',
245 'atomic_uint_fast64_t', 'atomic_intptr_t', 'atomic_uintptr_t', 'atomic_size_t',
246 'atomic_ptrdiff_t', 'atomic_intmax_t', 'atomic_uintmax_t'}
248 def __init__(self, **options):
249 self.stdlibhighlighting = get_bool_opt(options, 'stdlibhighlighting', True)
250 self.c99highlighting = get_bool_opt(options, 'c99highlighting', True)
251 self.c11highlighting = get_bool_opt(options, 'c11highlighting', True)
252 self.platformhighlighting = get_bool_opt(options, 'platformhighlighting', True)
253 RegexLexer.__init__(self, **options)
255 def get_tokens_unprocessed(self, text, stack=('root',)):
256 for index, token, value in \
257 RegexLexer.get_tokens_unprocessed(self, text, stack):
258 if token is Name:
259 if self.stdlibhighlighting and value in self.stdlib_types:
260 token = Keyword.Type
261 elif self.c99highlighting and value in self.c99_types:
262 token = Keyword.Type
263 elif self.c11highlighting and value in self.c11_atomic_types:
264 token = Keyword.Type
265 elif self.platformhighlighting and value in self.linux_types:
266 token = Keyword.Type
267 yield index, token, value
270class CLexer(CFamilyLexer):
271 """
272 For C source code with preprocessor directives.
274 Additional options accepted:
276 `stdlibhighlighting`
277 Highlight common types found in the C/C++ standard library (e.g. `size_t`).
278 (default: ``True``).
280 `c99highlighting`
281 Highlight common types found in the C99 standard library (e.g. `int8_t`).
282 Actually, this includes all fixed-width integer types.
283 (default: ``True``).
285 `c11highlighting`
286 Highlight atomic types found in the C11 standard library (e.g. `atomic_bool`).
287 (default: ``True``).
289 `platformhighlighting`
290 Highlight common types found in the platform SDK headers (e.g. `clockid_t` on Linux).
291 (default: ``True``).
292 """
293 name = 'C'
294 aliases = ['c']
295 filenames = ['*.c', '*.h', '*.idc', '*.x[bp]m']
296 mimetypes = ['text/x-chdr', 'text/x-csrc', 'image/x-xbitmap', 'image/x-xpixmap']
297 url = 'https://en.wikipedia.org/wiki/C_(programming_language)'
298 version_added = ''
299 priority = 0.1
301 tokens = {
302 'keywords': [
303 (words((
304 '_Alignas', '_Alignof', '_Noreturn', '_Generic', '_Thread_local',
305 '_Static_assert', '_Imaginary', 'noreturn', 'imaginary', 'complex'),
306 suffix=r'\b'), Keyword),
307 inherit
308 ],
309 'types': [
310 (words(('_Bool', '_Complex', '_Atomic'), suffix=r'\b'), Keyword.Type),
311 inherit
312 ]
313 }
315 def analyse_text(text):
316 if re.search(r'^\s*#include [<"]', text, re.MULTILINE):
317 return 0.1
318 if re.search(r'^\s*#ifn?def ', text, re.MULTILINE):
319 return 0.1
322class CppLexer(CFamilyLexer):
323 """
324 For C++ source code with preprocessor directives.
326 Additional options accepted:
328 `stdlibhighlighting`
329 Highlight common types found in the C/C++ standard library (e.g. `size_t`).
330 (default: ``True``).
332 `c99highlighting`
333 Highlight common types found in the C99 standard library (e.g. `int8_t`).
334 Actually, this includes all fixed-width integer types.
335 (default: ``True``).
337 `c11highlighting`
338 Highlight atomic types found in the C11 standard library (e.g. `atomic_bool`).
339 (default: ``True``).
341 `platformhighlighting`
342 Highlight common types found in the platform SDK headers (e.g. `clockid_t` on Linux).
343 (default: ``True``).
344 """
345 name = 'C++'
346 url = 'https://isocpp.org/'
347 aliases = ['cpp', 'c++']
348 filenames = ['*.cpp', '*.hpp', '*.c++', '*.h++',
349 '*.cc', '*.hh', '*.cxx', '*.hxx',
350 '*.C', '*.H', '*.cp', '*.CPP', '*.tpp']
351 mimetypes = ['text/x-c++hdr', 'text/x-c++src']
352 version_added = ''
353 priority = 0.1
355 tokens = {
356 'statements': [
357 # C++11 raw strings
358 (r'((?:[LuU]|u8)?R)(")([^\\()\s]{,16})(\()((?:.|\n)*?)(\)\3)(")',
359 bygroups(String.Affix, String, String.Delimiter, String.Delimiter,
360 String, String.Delimiter, String)),
361 inherit,
362 ],
363 'root': [
364 inherit,
365 # C++ Microsoft-isms
366 (words(('virtual_inheritance', 'uuidof', 'super', 'single_inheritance',
367 'multiple_inheritance', 'interface', 'event'),
368 prefix=r'__', suffix=r'\b'), Keyword.Reserved),
369 # Offload C++ extensions, http://offload.codeplay.com/
370 (r'__(offload|blockingoffload|outer)\b', Keyword.Pseudo),
371 ],
372 'enumname': [
373 include('whitespace'),
374 # 'enum class' and 'enum struct' C++11 support
375 (words(('class', 'struct'), suffix=r'\b'), Keyword),
376 (CFamilyLexer._ident, Name.Class, '#pop'),
377 # template specification
378 (r'\s*(?=>)', Text, '#pop'),
379 default('#pop')
380 ],
381 'keywords': [
382 (r'(class|concept|typename)(\s+)', bygroups(Keyword, Whitespace), 'classname'),
383 (words((
384 'catch', 'const_cast', 'delete', 'dynamic_cast', 'explicit',
385 'export', 'friend', 'mutable', 'new', 'operator',
386 'private', 'protected', 'public', 'reinterpret_cast', 'class',
387 '__restrict', 'static_cast', 'template', 'this', 'throw', 'throws',
388 'try', 'typeid', 'using', 'virtual', 'constexpr', 'nullptr', 'concept',
389 'decltype', 'noexcept', 'override', 'final', 'constinit', 'consteval',
390 'co_await', 'co_return', 'co_yield', 'requires', 'import', 'module',
391 'typename', 'and', 'and_eq', 'bitand', 'bitor', 'compl', 'not',
392 'not_eq', 'or', 'or_eq', 'xor', 'xor_eq'),
393 suffix=r'\b'), Keyword),
394 (r'namespace\b', Keyword, 'namespace'),
395 (r'(enum)(\s+)', bygroups(Keyword, Whitespace), 'enumname'),
396 inherit
397 ],
398 'types': [
399 (r'char(16_t|32_t|8_t)\b', Keyword.Type),
400 inherit
401 ],
402 'namespace': [
403 (r'[;{]', Punctuation, ('#pop', 'root')),
404 (r'inline\b', Keyword.Reserved),
405 (CFamilyLexer._ident, Name.Namespace),
406 include('statement')
407 ]
408 }
410 def analyse_text(text):
411 if re.search('#include <[a-z_]+>', text):
412 return 0.2
413 if re.search('using namespace ', text):
414 return 0.4