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
|
// class template regex -*- C++ -*-
// Copyright (C) 2013-2014 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_executor.tcc
* This is an internal header file, included by other library headers.
* Do not attempt to use it directly. @headername{regex}
*/
namespace std _GLIBCXX_VISIBILITY(default)
{
namespace __detail
{
_GLIBCXX_BEGIN_NAMESPACE_VERSION
template<typename _BiIter, typename _Alloc, typename _TraitsT,
bool __dfs_mode>
bool _Executor<_BiIter, _Alloc, _TraitsT, __dfs_mode>::
_M_search()
{
if (_M_search_from_first())
return true;
if (_M_flags & regex_constants::match_continuous)
return false;
_M_flags |= regex_constants::match_prev_avail;
while (_M_begin != _M_end)
{
++_M_begin;
if (_M_search_from_first())
return true;
}
return false;
}
// The _M_main function operates in different modes, DFS mode or BFS mode,
// indicated by template parameter __dfs_mode, and dispatches to one of the
// _M_main_dispatch overloads.
//
// ------------------------------------------------------------
//
// DFS mode:
//
// It applies a Depth-First-Search (aka backtracking) on given NFA and input
// string.
// At the very beginning the executor stands in the start state, then it
// tries every possible state transition in current state recursively. Some
// state transitions consume input string, say, a single-char-matcher or a
// back-reference matcher; some don't, like assertion or other anchor nodes.
// When the input is exhausted and/or the current state is an accepting
// state, the whole executor returns true.
//
// TODO: This approach is exponentially slow for certain input.
// Try to compile the NFA to a DFA.
//
// Time complexity: \Omega(match_length), O(2^(_M_nfa.size()))
// Space complexity: \theta(match_results.size() + match_length)
//
template<typename _BiIter, typename _Alloc, typename _TraitsT,
bool __dfs_mode>
bool _Executor<_BiIter, _Alloc, _TraitsT, __dfs_mode>::
_M_main_dispatch(_Match_mode __match_mode, __dfs)
{
_M_has_sol = false;
*_M_states._M_get_sol_pos() = _BiIter();
_M_cur_results = _M_results;
_M_dfs(__match_mode, _M_states._M_start);
return _M_has_sol;
}
// ------------------------------------------------------------
//
// BFS mode:
//
// Russ Cox's article (http://swtch.com/~rsc/regexp/regexp1.html)
// explained this algorithm clearly.
//
// It first computes epsilon closure (states that can be achieved without
// consuming characters) for every state that's still matching,
// using the same DFS algorithm, but doesn't re-enter states (using
// _M_states._M_visited to check), nor follow _S_opcode_match.
//
// Then apply DFS using every _S_opcode_match (in _M_states._M_match_queue)
// as the start state.
//
// It significantly reduces potential duplicate states, so has a better
// upper bound; but it requires more overhead.
//
// Time complexity: \Omega(match_length * match_results.size())
// O(match_length * _M_nfa.size() * match_results.size())
// Space complexity: \Omega(_M_nfa.size() + match_results.size())
// O(_M_nfa.size() * match_results.size())
template<typename _BiIter, typename _Alloc, typename _TraitsT,
bool __dfs_mode>
bool _Executor<_BiIter, _Alloc, _TraitsT, __dfs_mode>::
_M_main_dispatch(_Match_mode __match_mode, __bfs)
{
_M_states._M_queue(_M_states._M_start, _M_results);
bool __ret = false;
while (1)
{
_M_has_sol = false;
if (_M_states._M_match_queue.empty())
break;
std::fill_n(_M_states._M_visited_states.get(), _M_nfa.size(), false);
auto __old_queue = std::move(_M_states._M_match_queue);
for (auto& __task : __old_queue)
{
_M_cur_results = std::move(__task.second);
_M_dfs(__match_mode, __task.first);
}
if (__match_mode == _Match_mode::_Prefix)
__ret |= _M_has_sol;
if (_M_current == _M_end)
break;
++_M_current;
}
if (__match_mode == _Match_mode::_Exact)
__ret = _M_has_sol;
_M_states._M_match_queue.clear();
return __ret;
}
// Return whether now match the given sub-NFA.
template<typename _BiIter, typename _Alloc, typename _TraitsT,
bool __dfs_mode>
bool _Executor<_BiIter, _Alloc, _TraitsT, __dfs_mode>::
_M_lookahead(_State<_TraitsT> __state)
{
_ResultsVec __what(_M_cur_results.size());
_Executor __sub(_M_current, _M_end, __what, _M_re, _M_flags);
__sub._M_states._M_start = __state._M_alt;
if (__sub._M_search_from_first())
{
for (size_t __i = 0; __i < __what.size(); __i++)
if (__what[__i].matched)
_M_cur_results[__i] = __what[__i];
return true;
}
return false;
}
// __rep_count records how many times (__rep_count.second)
// this node is visited under certain input iterator
// (__rep_count.first). This prevent the executor from entering
// infinite loop by refusing to continue when it's already been
// visited more than twice. It's `twice` instead of `once` because
// we need to spare one more time for potential group capture.
template<typename _BiIter, typename _Alloc, typename _TraitsT,
bool __dfs_mode>
void _Executor<_BiIter, _Alloc, _TraitsT, __dfs_mode>::
_M_rep_once_more(_Match_mode __match_mode, _StateIdT __i)
{
const auto& __state = _M_nfa[__i];
auto& __rep_count = _M_rep_count[__i];
if (__rep_count.second == 0 || __rep_count.first != _M_current)
{
auto __back = __rep_count;
__rep_count.first = _M_current;
__rep_count.second = 1;
_M_dfs(__match_mode, __state._M_alt);
__rep_count = __back;
}
else
{
if (__rep_count.second < 2)
{
__rep_count.second++;
_M_dfs(__match_mode, __state._M_alt);
__rep_count.second--;
}
}
};
template<typename _BiIter, typename _Alloc, typename _TraitsT,
bool __dfs_mode>
void _Executor<_BiIter, _Alloc, _TraitsT, __dfs_mode>::
_M_dfs(_Match_mode __match_mode, _StateIdT __i)
{
if (_M_states._M_visited(__i))
return;
const auto& __state = _M_nfa[__i];
// Every change on _M_cur_results and _M_current will be rolled back after
// finishing the recursion step.
switch (__state._M_opcode)
{
// _M_alt branch is "match once more", while _M_next is "get me out
// of this quantifier". Executing _M_next first or _M_alt first don't
// mean the same thing, and we need to choose the correct order under
// given greedy mode.
case _S_opcode_repeat:
{
// Greedy.
if (!__state._M_neg)
{
_M_rep_once_more(__match_mode, __i);
// If it's DFS executor and already accepted, we're done.
if (!__dfs_mode || !_M_has_sol)
_M_dfs(__match_mode, __state._M_next);
}
else // Non-greedy mode
{
if (__dfs_mode)
{
// vice-versa.
_M_dfs(__match_mode, __state._M_next);
if (!_M_has_sol)
_M_rep_once_more(__match_mode, __i);
}
else
{
// DON'T attempt anything, because there's already another
// state with higher priority accepted. This state cannot
// be better by attempting its next node.
if (!_M_has_sol)
{
_M_dfs(__match_mode, __state._M_next);
// DON'T attempt anything if it's already accepted. An
// accepted state *must* be better than a solution that
// matches a non-greedy quantifier one more time.
if (!_M_has_sol)
_M_rep_once_more(__match_mode, __i);
}
}
}
}
break;
case _S_opcode_subexpr_begin:
{
auto& __res = _M_cur_results[__state._M_subexpr];
auto __back = __res.first;
__res.first = _M_current;
_M_dfs(__match_mode, __state._M_next);
__res.first = __back;
}
break;
case _S_opcode_subexpr_end:
{
auto& __res = _M_cur_results[__state._M_subexpr];
auto __back = __res;
__res.second = _M_current;
__res.matched = true;
_M_dfs(__match_mode, __state._M_next);
__res = __back;
}
break;
case _S_opcode_line_begin_assertion:
if (_M_at_begin())
_M_dfs(__match_mode, __state._M_next);
break;
case _S_opcode_line_end_assertion:
if (_M_at_end())
_M_dfs(__match_mode, __state._M_next);
break;
case _S_opcode_word_boundary:
if (_M_word_boundary() == !__state._M_neg)
_M_dfs(__match_mode, __state._M_next);
break;
// Here __state._M_alt offers a single start node for a sub-NFA.
// We recursively invoke our algorithm to match the sub-NFA.
case _S_opcode_subexpr_lookahead:
if (_M_lookahead(__state) == !__state._M_neg)
_M_dfs(__match_mode, __state._M_next);
break;
case _S_opcode_match:
if (_M_current == _M_end)
break;
if (__dfs_mode)
{
if (__state._M_matches(*_M_current))
{
++_M_current;
_M_dfs(__match_mode, __state._M_next);
--_M_current;
}
}
else
if (__state._M_matches(*_M_current))
_M_states._M_queue(__state._M_next, _M_cur_results);
break;
// First fetch the matched result from _M_cur_results as __submatch;
// then compare it with
// (_M_current, _M_current + (__submatch.second - __submatch.first)).
// If matched, keep going; else just return and try another state.
case _S_opcode_backref:
{
_GLIBCXX_DEBUG_ASSERT(__dfs_mode);
auto& __submatch = _M_cur_results[__state._M_backref_index];
if (!__submatch.matched)
break;
auto __last = _M_current;
for (auto __tmp = __submatch.first;
__last != _M_end && __tmp != __submatch.second;
++__tmp)
++__last;
if (_M_re._M_automaton->_M_traits.transform(__submatch.first,
__submatch.second)
== _M_re._M_automaton->_M_traits.transform(_M_current, __last))
{
if (__last != _M_current)
{
auto __backup = _M_current;
_M_current = __last;
_M_dfs(__match_mode, __state._M_next);
_M_current = __backup;
}
else
_M_dfs(__match_mode, __state._M_next);
}
}
break;
case _S_opcode_accept:
if (__dfs_mode)
{
_GLIBCXX_DEBUG_ASSERT(!_M_has_sol);
if (__match_mode == _Match_mode::_Exact)
_M_has_sol = _M_current == _M_end;
else
_M_has_sol = true;
if (_M_current == _M_begin
&& (_M_flags & regex_constants::match_not_null))
_M_has_sol = false;
if (_M_has_sol)
{
if (_M_nfa._M_flags & regex_constants::ECMAScript)
_M_results = _M_cur_results;
else // POSIX
{
_GLIBCXX_DEBUG_ASSERT(_M_states._M_get_sol_pos());
// Here's POSIX's logic: match the longest one. However
// we never know which one (lhs or rhs of "|") is longer
// unless we try both of them and compare the results.
// The member variable _M_sol_pos records the end
// position of the last successful match. It's better
// to be larger, because POSIX regex is always greedy.
// TODO: This could be slow.
if (*_M_states._M_get_sol_pos() == _BiIter()
|| std::distance(_M_begin,
*_M_states._M_get_sol_pos())
< std::distance(_M_begin, _M_current))
{
*_M_states._M_get_sol_pos() = _M_current;
_M_results = _M_cur_results;
}
}
}
}
else
{
if (_M_current == _M_begin
&& (_M_flags & regex_constants::match_not_null))
break;
if (__match_mode == _Match_mode::_Prefix || _M_current == _M_end)
if (!_M_has_sol)
{
_M_has_sol = true;
_M_results = _M_cur_results;
}
}
break;
case _S_opcode_alternative:
if (_M_nfa._M_flags & regex_constants::ECMAScript)
{
// TODO: Let BFS support ECMAScript's alternative operation.
_GLIBCXX_DEBUG_ASSERT(__dfs_mode);
_M_dfs(__match_mode, __state._M_alt);
// Pick lhs if it matches. Only try rhs if it doesn't.
if (!_M_has_sol)
_M_dfs(__match_mode, __state._M_next);
}
else
{
// Try both and compare the result.
// See "case _S_opcode_accept:" handling above.
_M_dfs(__match_mode, __state._M_alt);
auto __has_sol = _M_has_sol;
_M_has_sol = false;
_M_dfs(__match_mode, __state._M_next);
_M_has_sol |= __has_sol;
}
break;
default:
_GLIBCXX_DEBUG_ASSERT(false);
}
}
// Return whether now is at some word boundary.
template<typename _BiIter, typename _Alloc, typename _TraitsT,
bool __dfs_mode>
bool _Executor<_BiIter, _Alloc, _TraitsT, __dfs_mode>::
_M_word_boundary() const
{
bool __left_is_word = false;
if (_M_current != _M_begin
|| (_M_flags & regex_constants::match_prev_avail))
{
auto __prev = _M_current;
if (_M_is_word(*std::prev(__prev)))
__left_is_word = true;
}
bool __right_is_word =
_M_current != _M_end && _M_is_word(*_M_current);
if (__left_is_word == __right_is_word)
return false;
if (__left_is_word && !(_M_flags & regex_constants::match_not_eow))
return true;
if (__right_is_word && !(_M_flags & regex_constants::match_not_bow))
return true;
return false;
}
_GLIBCXX_END_NAMESPACE_VERSION
} // namespace __detail
} // namespace
|