-
Notifications
You must be signed in to change notification settings - Fork 2
/
preprocessor.cc
2949 lines (2578 loc) · 90.9 KB
/
preprocessor.cc
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
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* Copyright (C) 2019 SUSE Software Solutions Germany GmbH
*
* This file is part of klp-ccp.
*
* klp-ccp is free software: you can redistribute it and/or modify it
* under the terms of version 2 of the GNU General Public License as
* published by the Free Software Foundation.
*
* klp-ccp 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.
*
* You should have received a copy of the GNU General Public License
* along with klp-ccp. If not, see <https://www.gnu.org/licenses/>.
*/
#include <cassert>
#include <functional>
#include "preprocessor.hh"
#include "target.hh"
#include "pp_except.hh"
#include "parse_except.hh"
#include "semantic_except.hh"
#include "path.hh"
#include "pp_expr_parser_driver.hh"
using namespace klp::ccp;
class preprocessor::_pp_token
{
private:
template <pp_token::type... types>
struct __is_type_any_of;
public:
static constexpr raw_pp_token_index not_passed_through =
std::numeric_limits<raw_pp_token_index>::max();
_pp_token(const pp_token::type type, const std::string &value,
const raw_pp_tokens_range &token_source,
const pp_result::used_macros &eh,
const raw_pp_token_index passed_through_raw_token
= not_passed_through);
_pp_token(const pp_token::type type, const std::string &value,
const raw_pp_tokens_range &token_source,
const raw_pp_token_index passed_through_raw_token
= not_passed_through);
_pp_token(const pp_token::type type, std::string &&value,
const raw_pp_tokens_range &token_source,
const raw_pp_token_index passed_through_raw_token
= not_passed_through) noexcept;
pp_token::type get_type() const noexcept
{
return _type;
}
const std::string& get_value() const noexcept
{
return _value;
}
std::string&& grab_value() noexcept
{
return std::move(_value);
}
void set_type_and_value(const pp_token::type type,
const std::string &value);
const class pp_result::used_macros& expansion_history() const noexcept
{
return _expansion_history;
}
class pp_result::used_macros& expansion_history() noexcept
{
return _expansion_history;
}
const raw_pp_tokens_range& get_token_source() const noexcept
{
return _token_source;
}
void set_macro_invocation(pp_result::macro_invocation *mi)
noexcept;
pp_result::macro_invocation * get_macro_invocation()
const noexcept;
raw_pp_token_index get_passed_through_raw_token() const noexcept
{ return _passed_through_raw_token; }
operator bool() const noexcept
{
return _type != pp_token::type::eof;
}
template <typename T>
bool is_punctuator(T &&s) const noexcept
{
return (_type == pp_token::type::punctuator &&
_value == std::forward<T>(s));
}
template <pp_token::type... types>
bool is_type_any_of() const noexcept
{ return __is_type_any_of<types...>()(*this); }
bool is_id() const noexcept
{
return is_type_any_of<pp_token::type::id>();
}
bool is_ws() const noexcept
{
return is_type_any_of<pp_token::type::ws>();
}
bool is_newline() const noexcept
{
return is_type_any_of<pp_token::type::newline>();
}
bool is_eof() const noexcept
{
return is_type_any_of<pp_token::type::eof>();
}
bool is_empty() const noexcept
{
return is_type_any_of<pp_token::type::empty>();
}
std::string stringify() const;
void concat(const _pp_token &tok, preprocessor &p,
code_remarks &remarks);
private:
template <pp_token::type... types>
struct __is_type_any_of
{
// This is the sizeof...(types) == 0 case,
// c.f. the specialization below.
bool operator()(const _pp_token &) const noexcept
{ return false; }
};
template <pp_token::type type0, pp_token::type... types>
struct __is_type_any_of<type0, types...>
{
bool operator()(const _pp_token &tok) const noexcept
{
return tok._type == type0 || __is_type_any_of<types...>()(tok);
}
};
pp_token::type _type;
std::string _value;
raw_pp_tokens_range _token_source;
pp_result::macro_invocation * _macro_invocation;
raw_pp_token_index _passed_through_raw_token;
// Used for avoiding macro recursion as appropriate.
pp_result::used_macros _expansion_history;
};
class preprocessor::_macro_expander
{
public:
_macro_expander(preprocessor &preprocessor,
const pp_result::macro ¯o,
std::vector<_pp_tokens> &&args,
std::vector<_pp_tokens> &&exp_args,
const raw_pp_tokens_range &invocation_range);
const pp_result::macro& get_macro() const noexcept
{ return _macro; }
code_remarks& get_remarks() noexcept
{ return _remarks; }
std::vector<_pp_token> expand();
private:
_pp_token _read_next_token();
const _pp_tokens*
_resolve_arg(const std::string &name, const bool expanded)
const noexcept;
pp_result::used_macros _tok_expansion_history_init() const;
bool _is_stringification(raw_pp_tokens::const_iterator it)
const noexcept;
raw_pp_tokens::const_iterator
_skip_stringification_or_single(const raw_pp_tokens::const_iterator &it)
const noexcept;
bool _is_concat_op(const raw_pp_tokens::const_iterator &it)
const noexcept;
_pp_token _handle_stringification();
void _add_concat_token(const _pp_token &tok);
void _add_concat_token(const raw_pp_token &raw_tok);
_pp_token _yield_concat_token();
_pp_token _yield_empty_token();
preprocessor &_preprocessor;
const pp_result::macro &_macro;
std::map<std::string,
std::pair<_pp_tokens, _pp_tokens> > _args;
const raw_pp_tokens_range _invocation_range;
code_remarks _remarks;
raw_pp_tokens::const_iterator _it_repl;
const _pp_tokens *_cur_arg;
_pp_tokens::const_iterator _cur_arg_it;
std::unique_ptr<_pp_token> _concat_token;
bool _emit_empty_tok;
bool _last_tok_was_empty_or_ws;
bool _is_builtin_special;
};
struct preprocessor::_cond_incl_state
{
_cond_incl_state(pp_result::conditional_inclusion_node &_incl_node);
std::reference_wrapper<pp_result::conditional_inclusion_node> incl_node;
pp_result::used_macros um;
pp_result::macro_nondef_constraints mnc;
pp_result::conditional_inclusion_node::directive_ranges_type
directive_ranges;
bool branch_active;
pp_result::conditional_inclusion_node::directive_ranges_type::size_type
taken_branch;
bool has_else_branch;
};
struct preprocessor::_expansion_state
{
_expansion_state();
typedef std::vector<_pp_token> expanded_tokens_type;
struct stack_entry
{
stack_entry(expanded_tokens_type &&_tokens)
: tokens(std::move(_tokens)), next_token(0)
{}
expanded_tokens_type tokens;
expanded_tokens_type::size_type next_token;
};
std::stack<stack_entry> expansion_stack;
std::queue<_pp_token> pending_tokens;
};
preprocessor::preprocessor(const header_resolver &header_resolver,
const target &tgt)
: _header_resolver(header_resolver), _tgt(tgt),
_pp_result(new pp_result{}),
_cur_header_inclusion_root(_pp_result->get_header_inclusion_roots()
.begin()),
_cond_incl_nesting(0),
_root_expansion_state(new _expansion_state{}),
_cur_macro_invocation(nullptr), __counter__(0),
_maybe_pp_directive(true), _line_empty(true),
_eof(false), _eof_index(std::numeric_limits<raw_pp_token_index>::max())
{
// Populate the special builtin macros.
for (const auto &name : { "__FILE__",
"__BASE_FILE__",
"__LINE__",
"__INCLUDE_LEVEL__",
"__COUNTER__" }) {
const pp_result::macro &m =
_pp_result->_add_macro(name, pp_result::macro::builtin_special_tag{});
_macros.insert(std::make_pair(m.get_name(), std::ref(m)));
}
}
preprocessor::preprocessor(preprocessor &&pp) = default;
preprocessor::~preprocessor() noexcept = default;
void preprocessor::add_root_source(const std::string &filename,
const bool is_preinclude)
{
pp_result::header_inclusion_roots &roots =
_pp_result->get_header_inclusion_roots();
assert(_cur_header_inclusion_root == roots.begin());
_pp_result->get_header_inclusion_roots().add(filename, is_preinclude);
_cur_header_inclusion_root = roots.begin();
}
void preprocessor::set_base_file(const std::string &filename)
{
assert(_base_file.empty());
assert(_tokenizers.empty());
_base_file = filename;
}
pp_token_index preprocessor::read_next_token()
{
// Basically, this is just a wrapper around _expand()
// which removes or adds whitespace as needed:
// - Whitespace at the end of lines gets removed.
// - Multiple whitespace tokens get collated into one.
// - Empty lines are removed.
// - Whitespace gets inserted inbetween certain kind of tokens
// in order to guarantee idempotency of preprocessing.
//
// A queue of pending tokens is maintained in ::_pending_tokens.
//
// The following patters are possible for _pending_tokens at each
// invocation:
// - a single whitespace token,
// - a non-whitespace token from lookahead,
// - (added) whitespace + some punctuator, pp_number or id from lookahead
//
assert(_pending_tokens.empty() ||
(_pending_tokens.size() == 1) ||
(_pending_tokens.size() == 2 && _pending_tokens.front().is_ws() &&
(_pending_tokens.back().get_type() == pp_token::type::punctuator ||
_pending_tokens.back().get_type() == pp_token::type::pp_number ||
_pending_tokens.back().get_type() == pp_token::type::id)));
if (!_pending_tokens.empty() &&
(_pending_tokens.size() == 2 ||
!(_pending_tokens.front()
.is_type_any_of<pp_token::type::ws,
pp_token::type::punctuator,
pp_token::type::pp_number,
pp_token::type::id>()))) {
auto tok = std::move(_pending_tokens.front());
_pending_tokens.pop();
assert(!_line_empty);
if (tok.is_newline())
_line_empty = true;
return _emit_pp_token(*_pp_result, std::move(tok));
}
assert(_pending_tokens.empty() ||
(_pending_tokens.size() == 1 &&
(_pending_tokens.front().is_type_any_of<pp_token::type::ws,
pp_token::type::punctuator,
pp_token::type::pp_number,
pp_token::type::id>())));
read_next:
_pp_token next_tok = _expand(*_root_expansion_state,
std::bind(&preprocessor::_read_next_plain_token, this));
bool empty_seen = false;
while (next_tok.is_empty()) {
empty_seen = true;
next_tok = _expand(*_root_expansion_state,
std::bind(&preprocessor::_read_next_plain_token, this));
}
next_tok.expansion_history().clear();
// First, handle pending whitespace.
if (!_pending_tokens.empty() && _pending_tokens.front().is_ws()) {
if (next_tok.is_newline()) {
// Queued whitespace at end of line. Drop it.
_pending_tokens.pop();
assert(_pending_tokens.empty());
if (!_line_empty) {
_line_empty = true;
return _emit_pp_token(*_pp_result, std::move(next_tok));
}
goto read_next;
} else if (next_tok.is_eof()) {
// Queued whitespace at end of file. Drop it.
_pending_tokens.pop();
assert(_pending_tokens.empty());
return _emit_pp_token(*_pp_result, std::move(next_tok));
} else if (next_tok.is_ws()) {
// Multiple consecutive whitespace tokens.
goto read_next;
}
// Something which is not an EOF, newline, whitespace or empty
// token. Emit the pending whitespace and queue the current
// token.
_line_empty = false;
_pending_tokens.push(std::move(next_tok));
next_tok = std::move(_pending_tokens.front());
_pending_tokens.pop();
return _emit_pp_token(*_pp_result, std::move(next_tok));
}
// At this point, a pending token, if any, is a punctuator,
// pp_number or id which might have to get separated from the
// subsequent token by extra whitespace.
assert(_pending_tokens.empty() ||
(_pending_tokens.size() == 1 &&
(_pending_tokens.front().is_type_any_of<pp_token::type::punctuator,
pp_token::type::pp_number,
pp_token::type::id>())));
// There are certain token combinations where GNU cpp emits an extra
// space in order to make preprocessing idempotent:
// pp_number {-, +, --, ++, -=, +=, ., id, pp_number}
// . pp_number
// id {id, pp_number)
// + {+, ++, =}, - {-, --, =, >}, ! =, * =, / =, % =, ^ =,
// < {<, =, <=, <<=, :, %}, << =, > {>, =, >=, >>=}, >> =,
// & {=, &}, | {=, |},
// % {=, >, :}, %: %:, : >,
// : :, . ., # # if any of these is coming from macro expansion
// or they're separated by any empties
if (next_tok.is_ws()) {
if (!_pending_tokens.empty()) {
std::swap(next_tok, _pending_tokens.front());
return _emit_pp_token(*_pp_result, std::move(next_tok));
} else {
_pending_tokens.push(std::move(next_tok));
goto read_next;
}
} else if (next_tok.is_newline()) {
if (_line_empty) {
assert(_pending_tokens.empty());
goto read_next;
} else {
if (!_pending_tokens.empty())
std::swap(next_tok, _pending_tokens.front());
return _emit_pp_token(*_pp_result, std::move(next_tok));
}
} else if (!next_tok.is_type_any_of<pp_token::type::punctuator,
pp_token::type::pp_number,
pp_token::type::id>()) {
_line_empty = false;
if (!_pending_tokens.empty())
std::swap(next_tok, _pending_tokens.front());
return _emit_pp_token(*_pp_result, std::move(next_tok));
} else if (_pending_tokens.empty()) {
_line_empty = false;
_pending_tokens.push(std::move(next_tok));
goto read_next;
}
// There is a pending punctuator, pp_numer or id and the next token
// is also of this type. Check whether extra whitespace needs to get
// inserted.
_line_empty = false;
_pp_token prev_tok = std::move(_pending_tokens.front());
_pending_tokens.pop();
if ((prev_tok.is_type_any_of<pp_token::type::pp_number>() &&
(next_tok.is_punctuator("-") || next_tok.is_punctuator("+") ||
next_tok.is_punctuator("--") || next_tok.is_punctuator("++") ||
next_tok.is_punctuator("-=") || next_tok.is_punctuator("+=") ||
next_tok.is_punctuator(".") || next_tok.is_id() ||
next_tok.is_type_any_of<pp_token::type::pp_number>())) ||
(prev_tok.is_punctuator(".") &&
next_tok.is_type_any_of<pp_token::type::pp_number>()) ||
(prev_tok.is_id() &&
(next_tok.is_id() ||
next_tok.is_type_any_of<pp_token::type::pp_number>())) ||
(prev_tok.is_type_any_of<pp_token::type::punctuator>() &&
next_tok.is_type_any_of<pp_token::type::punctuator>() &&
((prev_tok.is_punctuator("+") &&
(next_tok.is_punctuator("+") || next_tok.is_punctuator("++") ||
next_tok.is_punctuator("="))) ||
(prev_tok.is_punctuator("-") &&
(next_tok.is_punctuator("-") || next_tok.is_punctuator("--") ||
next_tok.is_punctuator("=") || next_tok.is_punctuator(">"))) ||
(prev_tok.is_punctuator("!") && next_tok.is_punctuator("=")) ||
(prev_tok.is_punctuator("*") && next_tok.is_punctuator("=")) ||
(prev_tok.is_punctuator("/") && next_tok.is_punctuator("=")) ||
(prev_tok.is_punctuator("%") && next_tok.is_punctuator("=")) ||
(prev_tok.is_punctuator("^") && next_tok.is_punctuator("=")) ||
(prev_tok.is_punctuator("<") &&
(next_tok.is_punctuator("<") || next_tok.is_punctuator("=") ||
next_tok.is_punctuator("<=") || next_tok.is_punctuator("<<=") ||
next_tok.is_punctuator(":") || next_tok.is_punctuator("%"))) ||
(prev_tok.is_punctuator("<<") && next_tok.is_punctuator("=")) ||
(prev_tok.is_punctuator(">") &&
(next_tok.is_punctuator(">") || next_tok.is_punctuator("=") ||
next_tok.is_punctuator(">=") || next_tok.is_punctuator(">>="))) ||
(prev_tok.is_punctuator(">>") && next_tok.is_punctuator("=")) ||
(prev_tok.is_punctuator("&") &&
(next_tok.is_punctuator("=") || next_tok.is_punctuator("&"))) ||
(prev_tok.is_punctuator("|") &&
(next_tok.is_punctuator("=") || next_tok.is_punctuator("|"))) ||
(prev_tok.is_punctuator("%") &&
(next_tok.is_punctuator("=") || next_tok.is_punctuator(">") ||
next_tok.is_punctuator(":"))) ||
(prev_tok.is_punctuator("%:") && next_tok.is_punctuator("%:")) ||
(prev_tok.is_punctuator(":") && next_tok.is_punctuator(">")) ||
(empty_seen &&
((prev_tok.is_punctuator(":") && next_tok.is_punctuator(":")) ||
(prev_tok.is_punctuator(".") && next_tok.is_punctuator(".")) ||
(prev_tok.is_punctuator("#") && next_tok.is_punctuator("#"))))))) {
// Insert a ws token. Be careful to set the source range to keep
// the source ranges sorted, otherwise the lookup from
// raw_pp_tokens_ranges to pp_token_ranges will break.
const raw_pp_tokens_range r =
(prev_tok.get_token_source() == next_tok.get_token_source() ?
next_tok.get_token_source() :
raw_pp_tokens_range{next_tok.get_token_source().begin,
next_tok.get_token_source().begin});
_pp_token extra_ws_tok{pp_token::type::ws, " ", r};
extra_ws_tok.set_macro_invocation(next_tok.get_macro_invocation());
_pending_tokens.push(std::move(extra_ws_tok));
}
_pending_tokens.push(std::move(next_tok));
return _emit_pp_token(*_pp_result, std::move(prev_tok));
}
void preprocessor::register_builtin_macro(const std::string &name,
const std::string &repl)
{
const raw_pp_tokens tokenized_repl =
pp_string_tokenizer::tokenize_builtin(repl);
raw_pp_tokens normalized_repl =
_normalize_macro_repl(tokenized_repl.begin(), tokenized_repl.end(),
false, std::vector<std::string>{},
[](const std::string&,
const raw_pp_tokens::const_iterator&)
-> pp_except {
assert(0);
__builtin_unreachable();
});
const pp_result::macro &m =
_pp_result->_add_macro(name, false, false, std::vector<std::string>{},
pp_string_tokenizer::tokenize_builtin(repl),
pp_result::macro::builtin_tag{});
if (!_macros.insert(std::make_pair(m.get_name(), std::ref(m))).second)
assert(0);
}
void preprocessor::
register_builtin_macro(const std::string &name,
const std::initializer_list<const char *> &arg_list,
const bool variadic,
const std::string &repl)
{
std::vector<std::string> _arg_list;
_arg_list.reserve(arg_list.size());
for (const auto a : arg_list)
_arg_list.emplace_back(a);
const raw_pp_tokens tokenized_repl =
pp_string_tokenizer::tokenize_builtin(repl);
raw_pp_tokens normalized_repl =
_normalize_macro_repl(tokenized_repl.begin(), tokenized_repl.end(),
true, _arg_list,
[](const std::string&,
const raw_pp_tokens::const_iterator&)
-> pp_except {
assert(0);
__builtin_unreachable();
});
const pp_result::macro &m =
_pp_result->_add_macro(name, true, variadic, std::move(_arg_list),
std::move(normalized_repl),
pp_result::macro::builtin_tag{});
if (!_macros.insert(std::make_pair(m.get_name(), std::ref(m))).second)
assert(0);
}
void preprocessor::register_predefined_macro
(const std::string &signature,
const std::string &repl,
const std::function<void(const std::string)> &report_warning)
{
const auto &report_fatal =
[](const std::string &s) {
return pp_except{s};
};
pp_string_tokenizer signature_tokenizer{
signature, report_warning, report_fatal
};
raw_pp_tokens signature_toks;
while (true) {
raw_pp_token tok = signature_tokenizer.read_next_token();
if (tok.is_eof())
break;
signature_toks.push_back(std::move(tok));
}
pp_string_tokenizer repl_tokenizer{
repl, report_warning, report_fatal
};
raw_pp_tokens repl_toks;
while (true) {
raw_pp_token tok = repl_tokenizer.read_next_token();
if (tok.is_eof())
break;
repl_toks.push_back(std::move(tok));
}
const auto &skip_ws
= [](const raw_pp_tokens::const_iterator &it,
const raw_pp_tokens::const_iterator &end) {
if (it == end || !it->is_ws()) {
return it;
}
// No need to loop here: pp_tokenizer won't emit more than one
// consecutive whitespace.
assert(it + 1 == end || !(it + 1)->is_ws());
return it + 1;
};
raw_pp_tokens::const_iterator signature_end;
std::string name;
bool func_like;
std::vector<std::string> arg_names;
bool variadic;
std::tie(signature_end, name, func_like, arg_names, variadic)
= _parse_macro_signature(skip_ws(signature_toks.cbegin(),
signature_toks.cend()),
signature_toks.cend(),
[&](const std::string &msg,
const raw_pp_tokens::const_iterator&) {
return report_fatal(msg);
});
if (skip_ws(signature_end, signature_toks.cend()) !=
signature_toks.cend()) {
throw report_fatal("garbage after macro signature");
}
raw_pp_tokens normalized_repl =
_normalize_macro_repl(skip_ws(repl_toks.cbegin(), repl_toks.cend()),
repl_toks.cend(),
func_like, arg_names,
[&](const std::string &msg,
const raw_pp_tokens::const_iterator&) {
return report_fatal(msg);
});
const pp_result::macro &m =
_pp_result->_add_macro(name, func_like, variadic, std::move(arg_names),
std::move(normalized_repl),
pp_result::macro::predefined_user_tag{});
const auto it_existing = _macros.find(name);
if (it_existing != _macros.end() && it_existing->second.get() != m) {
throw report_fatal("macro redefined in an incompatible way");
}
_macros.insert(std::make_pair(m.get_name(), std::ref(m)));
}
void preprocessor::register_predefined_macro_undef
(const std::string &name,
const std::function<void(const std::string)> &report_warning)
{
const auto &report_fatal =
[](const std::string &s) {
return pp_except{s};
};
pp_string_tokenizer name_tokenizer{
name, report_warning, report_fatal
};
raw_pp_tokens name_toks;
while (true) {
raw_pp_token tok = name_tokenizer.read_next_token();
if (tok.is_eof())
break;
name_toks.push_back(std::move(tok));
}
const auto &skip_ws
= [](const raw_pp_tokens::const_iterator &it,
const raw_pp_tokens::const_iterator &end) {
if (it == end || !it->is_ws()) {
return it;
}
// No need to loop here: pp_tokenizer won't emit more than one
// consecutive whitespace.
assert(it + 1 == end || !(it + 1)->is_ws());
return it + 1;
};
const auto it_name = skip_ws(name_toks.cbegin(), name_toks.cend());
if (it_name == name_toks.cend() ||
!it_name->is_id() ||
skip_ws(it_name + 1, name_toks.cend()) != name_toks.end()) {
throw report_fatal("invalid macro name");
}
_pp_result->_add_macro_undef(it_name->get_value(),
pp_result::macro_undef::predefined_user_tag{});
_macros.erase(it_name->get_value());
}
template<typename T>
void preprocessor::_grab_remarks_from(T &from)
{
_remarks += from.get_remarks();
from.get_remarks().clear();
}
pp_token_index preprocessor::_emit_pp_token(pp_result &r, _pp_token &&tok)
{
r._append_token
(pp_token{tok.get_type(), tok.grab_value(),
tok.get_token_source()});
const pp_token_index tok_index = r._get_last_pp_index();
// Amend the macro_invocation's map of passed through raw macro
// argument tokens.
if (tok.get_macro_invocation() &&
tok.get_passed_through_raw_token() != _pp_token::not_passed_through) {
tok.get_macro_invocation()->_add_passed_through_macro_arg_token
(tok.get_passed_through_raw_token(), tok_index);
}
return tok_index;
}
preprocessor::_pp_token preprocessor::_read_next_plain_token()
{
again:
// Has the final eof token been seen?
if (_eof) {
return _pp_token{pp_token::type::eof, std::string{""},
raw_pp_tokens_range{_eof_index, _eof_index}};
}
if (_tokenizers.empty()) {
// First time _read_next_plain_token() gets called.
// Setup the tokenizer for the first root file.
assert(_cur_header_inclusion_root ==
_pp_result->get_header_inclusion_roots().begin());
assert(!_pp_result->get_header_inclusion_roots().empty());
_pp_result->_enter_root(*_cur_header_inclusion_root, 0);
_tokenizers.emplace(*_cur_header_inclusion_root);
_inclusions.emplace(std::ref(*_cur_header_inclusion_root));
}
try {
auto raw_tok = _tokenizers.top().read_next_token();
_grab_remarks_from(_tokenizers.top());
if (raw_tok.is_eof()) {
_handle_eof_from_tokenizer(std::move(raw_tok));
_maybe_pp_directive = true;
goto again;
}
std::string tok_value{raw_tok.get_value()};
const pp_token::type tok_type = raw_tok.get_type();
const bool is_pp_directive =
_maybe_pp_directive && raw_tok.is_punctuator("#");
_pp_result->_append_token(std::move(raw_tok));
if (raw_tok.is_newline()) {
_maybe_pp_directive = true;
} else if (is_pp_directive) {
_handle_pp_directive();
goto again;
} else if (!raw_tok.is_ws()) {
_maybe_pp_directive = false;
}
if (_cond_incl_inactive())
goto again;
const raw_pp_token_index raw_token_index =
_pp_result->_get_last_raw_index();
return _pp_token{tok_type, std::move(tok_value),
raw_pp_tokens_range{raw_token_index},
raw_token_index};
} catch (const pp_except&) {
_grab_remarks_from(_tokenizers.top());
throw;
}
}
void preprocessor::_handle_eof_from_tokenizer(raw_pp_token &&eof_tok)
{
// If the topmost inclusion tree node is an (unfinished) conditional
// inclusion, that's an error.
if (_cur_incl_node_is_cond()) {
_fixup_inclusion_node_ranges();
const raw_pp_token_index eof_index = _pp_result->get_raw_tokens().size();
const raw_pp_tokens_range eof_range{eof_index, eof_index};
const auto it_src
= _pp_result->intersecting_sources_begin(eof_range);
assert(it_src != _pp_result->intersecting_sources_end(eof_range));
code_remark remark(code_remark::severity::fatal,
"missing #endif at end of file",
*it_src, eof_tok.get_range_in_file());
_remarks.add(remark);
throw pp_except(remark);
}
_tokenizers.pop();
const raw_pp_token_index cur_raw_pos =
(!_pp_result->get_raw_tokens().empty() ?
_pp_result->_get_last_raw_index() + 1 :
0);
_inclusions.top().get()._set_range_end(cur_raw_pos);
_inclusions.pop();
if (_tokenizers.empty()) {
if (++_cur_header_inclusion_root ==
_pp_result->get_header_inclusion_roots().end()) {
_eof = true;
_eof_index = _pp_result->get_raw_tokens().size();
return;
}
_pp_result->_enter_root(*_cur_header_inclusion_root, cur_raw_pos);
_tokenizers.emplace(*_cur_header_inclusion_root);
_inclusions.emplace(std::ref(*_cur_header_inclusion_root));
}
}
void preprocessor::_fixup_inclusion_node_ranges() noexcept
{
// Fixup the all pending inclusion nodes' range information such
// that those intersecting a given query range can be found.
if (_cur_header_inclusion_root ==
_pp_result->get_header_inclusion_roots().end()) {
return;
}
const raw_pp_token_index cur_raw_end = _pp_result->_raw_tokens.size();
for (auto it_root = _cur_header_inclusion_root + 1;
it_root != _pp_result->get_header_inclusion_roots().end();
++it_root) {
it_root->_range.begin = cur_raw_end;
it_root->_range.end = cur_raw_end;
}
for (pp_result::inclusion_node *n = &_inclusions.top().get(); n;
n = n->_parent) {
n->_range.end = cur_raw_end;
}
}
const pp_result::header_inclusion_node& preprocessor::
_raw_tok_it_to_source(const raw_pp_tokens::const_iterator &it)
{
const raw_pp_token_index index = it - _pp_result->get_raw_tokens().begin();
return get_pending_token_source(index);
}
const pp_result::header_inclusion_node&
preprocessor::_raw_pp_tokens_range_to_source(const raw_pp_tokens_range &r)
{
const pp_result::header_inclusion_node &s
= get_pending_token_source(r.begin);
assert(r.begin == r.end || &s == &get_pending_token_source(r.end - 1));
return s;
}
range_in_file preprocessor::
_raw_pp_tokens_range_to_range_in_file(const raw_pp_tokens_range &r)
const noexcept
{
if (r.begin == r.end + 1) {
// A single token, emit "point" range for its start.
const raw_pp_token &tok = _pp_result->get_raw_tokens()[r.begin];
const range_in_file &tok_rif = tok.get_range_in_file();
return range_in_file{tok_rif.begin};
} else if (r.begin == r.end) {
// An empty range, used for EOFs. Emit a "point" range for the
// preceeding token's end.
assert(r.begin > 0);
assert(r.begin <= _pp_result->get_raw_tokens().size());
const raw_pp_token &tok = _pp_result->get_raw_tokens()[r.begin - 1];
const range_in_file &tok_rif = tok.get_range_in_file();
return range_in_file{tok_rif.end};
} else {
// A real range. It must come from a single header.
assert(r.end <= _pp_result->get_raw_tokens().size());
const raw_pp_token &first_tok = _pp_result->get_raw_tokens()[r.begin];
const raw_pp_token &last_tok = _pp_result->get_raw_tokens()[r.end - 1];
const range_in_file &first_tok_rif = first_tok.get_range_in_file();
const range_in_file &last_tok_rif = last_tok.get_range_in_file();
return range_in_file{first_tok_rif.begin, last_tok_rif.end};
}
}
const pp_result::header_inclusion_node&
preprocessor::_pp_token_to_source(const _pp_token &tok)
{
return _raw_pp_tokens_range_to_source(tok.get_token_source());
}
range_in_file preprocessor::_pp_token_to_range_in_file(const _pp_token &tok)
const noexcept
{
return _raw_pp_tokens_range_to_range_in_file(tok.get_token_source());
}
void preprocessor::_handle_pp_directive()
{
const raw_pp_token_index raw_begin = _pp_result->_get_last_raw_index();
raw_pp_token_index raw_end = raw_begin + 1;
assert(_pp_result->get_raw_tokens()[raw_begin].is_punctuator("#"));
bool endif_possible = true;
bool is_endif = false;
while (true) {
assert(!_tokenizers.empty());
auto tok = _tokenizers.top().read_next_token();
_grab_remarks_from(_tokenizers.top());
if (tok.is_eof()) {
_handle_eof_from_tokenizer(std::move(tok));
break;
}
_pp_result->_append_token(tok);
raw_end = _pp_result->_get_last_raw_index() + 1;
if (tok.is_newline()) {
break;
} else if (endif_possible && tok.get_type() == pp_token::type::id &&
tok.get_value() == "endif") {
// Be careful not to read until the end of line or end of file
// for #endif directives: _handle_eof_from_tokenizer() will
// throw an exception if there's some conditional inclusion
// pending.
is_endif = true;
endif_possible = false;
if (!_cur_incl_node_is_cond()) {
code_remark remark
(code_remark::severity::fatal,
"#endif without #if",
get_pending_token_source(_pp_result->_get_last_raw_index()),
tok.get_range_in_file());
_remarks.add(remark);
throw pp_except(remark);
}
do {
tok = _tokenizers.top().read_next_token();
_grab_remarks_from(_tokenizers.top());
_pp_result->_append_token(tok);
raw_end = _pp_result->_get_last_raw_index() + 1;
} while (tok.is_ws());
if (tok.is_newline()) {
_pp_result->_append_token(tok);
raw_end = _pp_result->_get_last_raw_index() + 1;
} else if (!tok.is_eof()) {
code_remark remark
(code_remark::severity::warning,
"garbage after #endif",
get_pending_token_source(_pp_result->_get_last_raw_index()),
tok.get_range_in_file());
_remarks.add(remark);
}
if (_cond_incl_nesting == _cond_incl_states.size()) {
_cond_incl_states.top().directive_ranges.emplace_back(raw_begin,
raw_end);
_pop_cond_incl(raw_end);
}
--_cond_incl_nesting;
// Handling EOF is safe now after the conditional inclusion has
// been popped.
if (tok.is_eof())
_handle_eof_from_tokenizer(std::move(tok));
break;
} else if (!tok.is_ws()) {
endif_possible = false;
}
}
_pp_result->_add_directive(raw_pp_tokens_range{raw_begin, raw_end});
if (is_endif)
return;
auto it_tok = _pp_result->get_raw_tokens().begin() + raw_begin + 1;
if (it_tok == _pp_result->get_raw_tokens().begin() + raw_end) {