Training courses

Kernel and Embedded Linux

Bootlin training courses

Embedded Linux, kernel,
Yocto Project, Buildroot, real-time,
graphics, boot time, debugging...

Bootlin logo

Elixir Cross Referencer

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
// class template regex -*- C++ -*-

// Copyright (C) 2013-2017 Free Software Foundation, Inc.
//
// This file is part of the GNU ISO C++ Library.  This library is free
// software; you can redistribute it and/or modify it under the
// terms of the GNU General Public License as published by the
// Free Software Foundation; either version 3, or (at your option)
// any later version.

// This library is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
// GNU General Public License for more details.

// Under Section 7 of GPL version 3, you are granted additional
// permissions described in the GCC Runtime Library Exception, version
// 3.1, as published by the Free Software Foundation.

// You should have received a copy of the GNU General Public License and
// a copy of the GCC Runtime Library Exception along with this program;
// see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
// <http://www.gnu.org/licenses/>.

/**
 *  @file bits/regex_scanner.tcc
 *  This is an internal header file, included by other library headers.
 *  Do not attempt to use it directly. @headername{regex}
 */

// FIXME make comments doxygen format.

// N3376 specified 6 regex styles: ECMAScript, basic, extended, grep, egrep
// and awk
// 1) grep is basic except '\n' is treated as '|'
// 2) egrep is extended except '\n' is treated as '|'
// 3) awk is extended except special escaping rules, and there's no
//    back-reference.
//
// References:
//
// ECMAScript: ECMA-262 15.10
//
// basic, extended:
// http://pubs.opengroup.org/onlinepubs/009695399/basedefs/xbd_chap09.html
//
// awk: http://pubs.opengroup.org/onlinepubs/000095399/utilities/awk.html

namespace std _GLIBCXX_VISIBILITY(default)
{
namespace __detail
{
_GLIBCXX_BEGIN_NAMESPACE_VERSION

  template<typename _CharT>
    _Scanner<_CharT>::
    _Scanner(typename _Scanner::_IterT __begin,
	     typename _Scanner::_IterT __end,
	     _FlagT __flags, std::locale __loc)
    : _ScannerBase(__flags),
      _M_current(__begin), _M_end(__end),
      _M_ctype(std::use_facet<_CtypeT>(__loc)),
      _M_eat_escape(_M_is_ecma()
		    ? &_Scanner::_M_eat_escape_ecma
		    : &_Scanner::_M_eat_escape_posix)
    { _M_advance(); }

  template<typename _CharT>
    void
    _Scanner<_CharT>::
    _M_advance()
    {
      if (_M_current == _M_end)
	{
	  _M_token = _S_token_eof;
	  return;
	}

      if (_M_state == _S_state_normal)
	_M_scan_normal();
      else if (_M_state == _S_state_in_bracket)
	_M_scan_in_bracket();
      else if (_M_state == _S_state_in_brace)
	_M_scan_in_brace();
      else
	{
	  __glibcxx_assert(false);
	}
    }

  // Differences between styles:
  // 1) "\(", "\)", "\{" in basic. It's not escaping.
  // 2) "(?:", "(?=", "(?!" in ECMAScript.
  template<typename _CharT>
    void
    _Scanner<_CharT>::
    _M_scan_normal()
    {
      auto __c = *_M_current++;

      if (std::strchr(_M_spec_char, _M_ctype.narrow(__c, ' ')) == nullptr)
	{
	  _M_token = _S_token_ord_char;
	  _M_value.assign(1, __c);
	  return;
	}
      if (__c == '\\')
	{
	  if (_M_current == _M_end)
	    __throw_regex_error(
	      regex_constants::error_escape,
	      "Unexpected end of regex when escaping.");

	  if (!_M_is_basic()
	      || (*_M_current != '('
		  && *_M_current != ')'
		  && *_M_current != '{'))
	    {
	      (this->*_M_eat_escape)();
	      return;
	    }
	  __c = *_M_current++;
	}
      if (__c == '(')
	{
	  if (_M_is_ecma() && *_M_current == '?')
	    {
	      if (++_M_current == _M_end)
		__throw_regex_error(
		  regex_constants::error_paren,
		  "Unexpected end of regex when in an open parenthesis.");

	      if (*_M_current == ':')
		{
		  ++_M_current;
		  _M_token = _S_token_subexpr_no_group_begin;
		}
	      else if (*_M_current == '=')
		{
		  ++_M_current;
		  _M_token = _S_token_subexpr_lookahead_begin;
		  _M_value.assign(1, 'p');
		}
	      else if (*_M_current == '!')
		{
		  ++_M_current;
		  _M_token = _S_token_subexpr_lookahead_begin;
		  _M_value.assign(1, 'n');
		}
	      else
		__throw_regex_error(
		  regex_constants::error_paren,
		  "Invalid special open parenthesis.");
	    }
	  else if (_M_flags & regex_constants::nosubs)
	    _M_token = _S_token_subexpr_no_group_begin;
	  else
	    _M_token = _S_token_subexpr_begin;
	}
      else if (__c == ')')
	_M_token = _S_token_subexpr_end;
      else if (__c == '[')
	{
	  _M_state = _S_state_in_bracket;
	  _M_at_bracket_start = true;
	  if (_M_current != _M_end && *_M_current == '^')
	    {
	      _M_token = _S_token_bracket_neg_begin;
	      ++_M_current;
	    }
	  else
	    _M_token = _S_token_bracket_begin;
	}
      else if (__c == '{')
	{
	  _M_state = _S_state_in_brace;
	  _M_token = _S_token_interval_begin;
	}
      else if (__c != ']' && __c != '}')
	{
	  auto __it = _M_token_tbl;
	  auto __narrowc = _M_ctype.narrow(__c, '\0');
	  for (; __it->first != '\0'; ++__it)
	    if (__it->first == __narrowc)
	      {
		_M_token = __it->second;
		return;
	      }
	  __glibcxx_assert(false);
	}
      else
	{
	  _M_token = _S_token_ord_char;
	  _M_value.assign(1, __c);
	}
    }

  // Differences between styles:
  // 1) different semantics of "[]" and "[^]".
  // 2) Escaping in bracket expr.
  template<typename _CharT>
    void
    _Scanner<_CharT>::
    _M_scan_in_bracket()
    {
      if (_M_current == _M_end)
	__throw_regex_error(
	  regex_constants::error_brack,
	  "Unexpected end of regex when in bracket expression.");

      auto __c = *_M_current++;

      if (__c == '-')
	_M_token = _S_token_bracket_dash;
      else if (__c == '[')
	{
	  if (_M_current == _M_end)
	    __throw_regex_error(regex_constants::error_brack,
				"Unexpected character class open bracket.");

	  if (*_M_current == '.')
	    {
	      _M_token = _S_token_collsymbol;
	      _M_eat_class(*_M_current++);
	    }
	  else if (*_M_current == ':')
	    {
	      _M_token = _S_token_char_class_name;
	      _M_eat_class(*_M_current++);
	    }
	  else if (*_M_current == '=')
	    {
	      _M_token = _S_token_equiv_class_name;
	      _M_eat_class(*_M_current++);
	    }
	  else
	    {
	      _M_token = _S_token_ord_char;
	      _M_value.assign(1, __c);
	    }
	}
      // In POSIX, when encountering "[]" or "[^]", the ']' is interpreted
      // literally. So "[]]" and "[^]]" are valid regexes. See the testcases
      // `*/empty_range.cc`.
      else if (__c == ']' && (_M_is_ecma() || !_M_at_bracket_start))
	{
	  _M_token = _S_token_bracket_end;
	  _M_state = _S_state_normal;
	}
      // ECMAScript and awk permits escaping in bracket.
      else if (__c == '\\' && (_M_is_ecma() || _M_is_awk()))
	(this->*_M_eat_escape)();
      else
	{
	  _M_token = _S_token_ord_char;
	  _M_value.assign(1, __c);
	}
      _M_at_bracket_start = false;
    }

  // Differences between styles:
  // 1) "\}" in basic style.
  template<typename _CharT>
    void
    _Scanner<_CharT>::
    _M_scan_in_brace()
    {
      if (_M_current == _M_end)
	__throw_regex_error(
	  regex_constants::error_brace,
	  "Unexpected end of regex when in brace expression.");

      auto __c = *_M_current++;

      if (_M_ctype.is(_CtypeT::digit, __c))
	{
	  _M_token = _S_token_dup_count;
	  _M_value.assign(1, __c);
	  while (_M_current != _M_end
		 && _M_ctype.is(_CtypeT::digit, *_M_current))
	    _M_value += *_M_current++;
	}
      else if (__c == ',')
	_M_token = _S_token_comma;
      // basic use \}.
      else if (_M_is_basic())
	{
	  if (__c == '\\' && _M_current != _M_end && *_M_current == '}')
	    {
	      _M_state = _S_state_normal;
	      _M_token = _S_token_interval_end;
	      ++_M_current;
	    }
	  else
	    __throw_regex_error(regex_constants::error_badbrace,
				"Unexpected character in brace expression.");
	}
      else if (__c == '}')
	{
	  _M_state = _S_state_normal;
	  _M_token = _S_token_interval_end;
	}
      else
	__throw_regex_error(regex_constants::error_badbrace,
			    "Unexpected character in brace expression.");
    }

  template<typename _CharT>
    void
    _Scanner<_CharT>::
    _M_eat_escape_ecma()
    {
      if (_M_current == _M_end)
	__throw_regex_error(regex_constants::error_escape,
			    "Unexpected end of regex when escaping.");

      auto __c = *_M_current++;
      auto __pos = _M_find_escape(_M_ctype.narrow(__c, '\0'));

      if (__pos != nullptr && (__c != 'b' || _M_state == _S_state_in_bracket))
	{
	  _M_token = _S_token_ord_char;
	  _M_value.assign(1, *__pos);
	}
      else if (__c == 'b')
	{
	  _M_token = _S_token_word_bound;
	  _M_value.assign(1, 'p');
	}
      else if (__c == 'B')
	{
	  _M_token = _S_token_word_bound;
	  _M_value.assign(1, 'n');
	}
      // N3376 28.13
      else if (__c == 'd'
	       || __c == 'D'
	       || __c == 's'
	       || __c == 'S'
	       || __c == 'w'
	       || __c == 'W')
	{
	  _M_token = _S_token_quoted_class;
	  _M_value.assign(1, __c);
	}
      else if (__c == 'c')
	{
	  if (_M_current == _M_end)
	    __throw_regex_error(
	      regex_constants::error_escape,
	      "Unexpected end of regex when reading control code.");
	  _M_token = _S_token_ord_char;
	  _M_value.assign(1, *_M_current++);
	}
      else if (__c == 'x' || __c == 'u')
	{
	  _M_value.erase();
	  for (int __i = 0; __i < (__c == 'x' ? 2 : 4); __i++)
	    {
	      if (_M_current == _M_end
		  || !_M_ctype.is(_CtypeT::xdigit, *_M_current))
		__throw_regex_error(
		  regex_constants::error_escape,
		  "Unexpected end of regex when ascii character.");
	      _M_value += *_M_current++;
	    }
	  _M_token = _S_token_hex_num;
	}
      // ECMAScript recognizes multi-digit back-references.
      else if (_M_ctype.is(_CtypeT::digit, __c))
	{
	  _M_value.assign(1, __c);
	  while (_M_current != _M_end
		 && _M_ctype.is(_CtypeT::digit, *_M_current))
	    _M_value += *_M_current++;
	  _M_token = _S_token_backref;
	}
      else
	{
	  _M_token = _S_token_ord_char;
	  _M_value.assign(1, __c);
	}
    }

  // Differences between styles:
  // 1) Extended doesn't support backref, but basic does.
  template<typename _CharT>
    void
    _Scanner<_CharT>::
    _M_eat_escape_posix()
    {
      if (_M_current == _M_end)
	__throw_regex_error(regex_constants::error_escape,
			    "Unexpected end of regex when escaping.");

      auto __c = *_M_current;
      auto __pos = std::strchr(_M_spec_char, _M_ctype.narrow(__c, '\0'));

      if (__pos != nullptr && *__pos != '\0')
	{
	  _M_token = _S_token_ord_char;
	  _M_value.assign(1, __c);
	}
      // We MUST judge awk before handling backrefs. There's no backref in awk.
      else if (_M_is_awk())
	{
	  _M_eat_escape_awk();
	  return;
	}
      else if (_M_is_basic() && _M_ctype.is(_CtypeT::digit, __c) && __c != '0')
	{
	  _M_token = _S_token_backref;
	  _M_value.assign(1, __c);
	}
      else
	{
#ifdef __STRICT_ANSI__
	  // POSIX says it is undefined to escape ordinary characters
	  __throw_regex_error(regex_constants::error_escape,
			      "Unexpected escape character.");
#else
	  _M_token = _S_token_ord_char;
	  _M_value.assign(1, __c);
#endif
	}
      ++_M_current;
    }

  template<typename _CharT>
    void
    _Scanner<_CharT>::
    _M_eat_escape_awk()
    {
      auto __c = *_M_current++;
      auto __pos = _M_find_escape(_M_ctype.narrow(__c, '\0'));

      if (__pos != nullptr)
	{
	  _M_token = _S_token_ord_char;
	  _M_value.assign(1, *__pos);
	}
      // \ddd for oct representation
      else if (_M_ctype.is(_CtypeT::digit, __c)
	       && __c != '8'
	       && __c != '9')
	{
	  _M_value.assign(1,  __c);
	  for (int __i = 0;
	       __i < 2
	       && _M_current != _M_end
	       && _M_ctype.is(_CtypeT::digit, *_M_current)
	       && *_M_current != '8'
	       && *_M_current != '9';
	       __i++)
	    _M_value += *_M_current++;
	  _M_token = _S_token_oct_num;
	  return;
	}
      else
	__throw_regex_error(regex_constants::error_escape,
			    "Unexpected escape character.");
    }

  // Eats a character class or throws an exception.
  // __ch could be ':', '.' or '=', _M_current is the char after ']' when
  // returning.
  template<typename _CharT>
    void
    _Scanner<_CharT>::
    _M_eat_class(char __ch)
    {
      for (_M_value.clear(); _M_current != _M_end && *_M_current != __ch;)
	_M_value += *_M_current++;
      if (_M_current == _M_end
	  || *_M_current++ != __ch
	  || _M_current == _M_end // skip __ch
	  || *_M_current++ != ']') // skip ']'
	{
	  if (__ch == ':')
	    __throw_regex_error(regex_constants::error_ctype,
				"Unexpected end of character class.");
	  else
	    __throw_regex_error(regex_constants::error_collate,
				"Unexpected end of character class.");
	}
    }

#ifdef _GLIBCXX_DEBUG
  template<typename _CharT>
    std::ostream&
    _Scanner<_CharT>::
    _M_print(std::ostream& ostr)
    {
      switch (_M_token)
      {
      case _S_token_anychar:
	ostr << "any-character\n";
	break;
      case _S_token_backref:
	ostr << "backref\n";
	break;
      case _S_token_bracket_begin:
	ostr << "bracket-begin\n";
	break;
      case _S_token_bracket_neg_begin:
	ostr << "bracket-neg-begin\n";
	break;
      case _S_token_bracket_end:
	ostr << "bracket-end\n";
	break;
      case _S_token_char_class_name:
	ostr << "char-class-name \"" << _M_value << "\"\n";
	break;
      case _S_token_closure0:
	ostr << "closure0\n";
	break;
      case _S_token_closure1:
	ostr << "closure1\n";
	break;
      case _S_token_collsymbol:
	ostr << "collsymbol \"" << _M_value << "\"\n";
	break;
      case _S_token_comma:
	ostr << "comma\n";
	break;
      case _S_token_dup_count:
	ostr << "dup count: " << _M_value << "\n";
	break;
      case _S_token_eof:
	ostr << "EOF\n";
	break;
      case _S_token_equiv_class_name:
	ostr << "equiv-class-name \"" << _M_value << "\"\n";
	break;
      case _S_token_interval_begin:
	ostr << "interval begin\n";
	break;
      case _S_token_interval_end:
	ostr << "interval end\n";
	break;
      case _S_token_line_begin:
	ostr << "line begin\n";
	break;
      case _S_token_line_end:
	ostr << "line end\n";
	break;
      case _S_token_opt:
	ostr << "opt\n";
	break;
      case _S_token_or:
	ostr << "or\n";
	break;
      case _S_token_ord_char:
	ostr << "ordinary character: \"" << _M_value << "\"\n";
	break;
      case _S_token_subexpr_begin:
	ostr << "subexpr begin\n";
	break;
      case _S_token_subexpr_no_group_begin:
	ostr << "no grouping subexpr begin\n";
	break;
      case _S_token_subexpr_lookahead_begin:
	ostr << "lookahead subexpr begin\n";
	break;
      case _S_token_subexpr_end:
	ostr << "subexpr end\n";
	break;
      case _S_token_unknown:
	ostr << "-- unknown token --\n";
	break;
      case _S_token_oct_num:
	ostr << "oct number " << _M_value << "\n";
	break;
      case _S_token_hex_num:
	ostr << "hex number " << _M_value << "\n";
	break;
      case _S_token_quoted_class:
	ostr << "quoted class " << "\\" << _M_value << "\n";
	break;
      default:
	_GLIBCXX_DEBUG_ASSERT(false);
      }
      return ostr;
    }
#endif

_GLIBCXX_END_NAMESPACE_VERSION
} // namespace __detail
} // namespace