forked from schacon/perl
-
Notifications
You must be signed in to change notification settings - Fork 0
/
toke.c
11657 lines (10540 loc) · 315 KB
/
toke.c
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
/* toke.c
*
* Copyright (C) 1991, 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000,
* 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008 by Larry Wall and others
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
*
*/
/*
* 'It all comes from here, the stench and the peril.' --Frodo
*
* [p.719 of _The Lord of the Rings_, IV/ix: "Shelob's Lair"]
*/
/*
* This file is the lexer for Perl. It's closely linked to the
* parser, perly.y.
*
* The main routine is yylex(), which returns the next token.
*/
/*
=head1 Lexer interface
This is the lower layer of the Perl parser, managing characters and tokens.
=for apidoc AmU|yy_parser *|PL_parser
Pointer to a structure encapsulating the state of the parsing operation
currently in progress. The pointer can be locally changed to perform
a nested parse without interfering with the state of an outer parse.
Individual members of C<PL_parser> have their own documentation.
=cut
*/
#include "EXTERN.h"
#define PERL_IN_TOKE_C
#include "perl.h"
#include "dquote_static.c"
#define new_constant(a,b,c,d,e,f,g) \
S_new_constant(aTHX_ a,b,STR_WITH_LEN(c),d,e,f, g)
#define pl_yylval (PL_parser->yylval)
/* XXX temporary backwards compatibility */
#define PL_lex_brackets (PL_parser->lex_brackets)
#define PL_lex_allbrackets (PL_parser->lex_allbrackets)
#define PL_lex_fakeeof (PL_parser->lex_fakeeof)
#define PL_lex_brackstack (PL_parser->lex_brackstack)
#define PL_lex_casemods (PL_parser->lex_casemods)
#define PL_lex_casestack (PL_parser->lex_casestack)
#define PL_lex_defer (PL_parser->lex_defer)
#define PL_lex_dojoin (PL_parser->lex_dojoin)
#define PL_lex_expect (PL_parser->lex_expect)
#define PL_lex_formbrack (PL_parser->lex_formbrack)
#define PL_lex_inpat (PL_parser->lex_inpat)
#define PL_lex_inwhat (PL_parser->lex_inwhat)
#define PL_lex_op (PL_parser->lex_op)
#define PL_lex_repl (PL_parser->lex_repl)
#define PL_lex_starts (PL_parser->lex_starts)
#define PL_lex_stuff (PL_parser->lex_stuff)
#define PL_multi_start (PL_parser->multi_start)
#define PL_multi_open (PL_parser->multi_open)
#define PL_multi_close (PL_parser->multi_close)
#define PL_pending_ident (PL_parser->pending_ident)
#define PL_preambled (PL_parser->preambled)
#define PL_sublex_info (PL_parser->sublex_info)
#define PL_linestr (PL_parser->linestr)
#define PL_expect (PL_parser->expect)
#define PL_copline (PL_parser->copline)
#define PL_bufptr (PL_parser->bufptr)
#define PL_oldbufptr (PL_parser->oldbufptr)
#define PL_oldoldbufptr (PL_parser->oldoldbufptr)
#define PL_linestart (PL_parser->linestart)
#define PL_bufend (PL_parser->bufend)
#define PL_last_uni (PL_parser->last_uni)
#define PL_last_lop (PL_parser->last_lop)
#define PL_last_lop_op (PL_parser->last_lop_op)
#define PL_lex_state (PL_parser->lex_state)
#define PL_rsfp (PL_parser->rsfp)
#define PL_rsfp_filters (PL_parser->rsfp_filters)
#define PL_in_my (PL_parser->in_my)
#define PL_in_my_stash (PL_parser->in_my_stash)
#define PL_tokenbuf (PL_parser->tokenbuf)
#define PL_multi_end (PL_parser->multi_end)
#define PL_error_count (PL_parser->error_count)
#ifdef PERL_MAD
# define PL_endwhite (PL_parser->endwhite)
# define PL_faketokens (PL_parser->faketokens)
# define PL_lasttoke (PL_parser->lasttoke)
# define PL_nextwhite (PL_parser->nextwhite)
# define PL_realtokenstart (PL_parser->realtokenstart)
# define PL_skipwhite (PL_parser->skipwhite)
# define PL_thisclose (PL_parser->thisclose)
# define PL_thismad (PL_parser->thismad)
# define PL_thisopen (PL_parser->thisopen)
# define PL_thisstuff (PL_parser->thisstuff)
# define PL_thistoken (PL_parser->thistoken)
# define PL_thiswhite (PL_parser->thiswhite)
# define PL_thiswhite (PL_parser->thiswhite)
# define PL_nexttoke (PL_parser->nexttoke)
# define PL_curforce (PL_parser->curforce)
#else
# define PL_nexttoke (PL_parser->nexttoke)
# define PL_nexttype (PL_parser->nexttype)
# define PL_nextval (PL_parser->nextval)
#endif
/* This can't be done with embed.fnc, because struct yy_parser contains a
member named pending_ident, which clashes with the generated #define */
static int
S_pending_ident(pTHX);
static const char ident_too_long[] = "Identifier too long";
#ifdef PERL_MAD
# define CURMAD(slot,sv) if (PL_madskills) { curmad(slot,sv); sv = 0; }
# define NEXTVAL_NEXTTOKE PL_nexttoke[PL_curforce].next_val
#else
# define CURMAD(slot,sv)
# define NEXTVAL_NEXTTOKE PL_nextval[PL_nexttoke]
#endif
#define XENUMMASK 0x3f
#define XFAKEEOF 0x40
#define XFAKEBRACK 0x80
#ifdef USE_UTF8_SCRIPTS
# define UTF (!IN_BYTES)
#else
# define UTF ((PL_linestr && DO_UTF8(PL_linestr)) || ( !(PL_parser->lex_flags & LEX_IGNORE_UTF8_HINTS) && (PL_hints & HINT_UTF8)))
#endif
/* The maximum number of characters preceding the unrecognized one to display */
#define UNRECOGNIZED_PRECEDE_COUNT 10
/* In variables named $^X, these are the legal values for X.
* 1999-02-27 mjd-perl-patch@plover.com */
#define isCONTROLVAR(x) (isUPPER(x) || strchr("[\\]^_?", (x)))
#define SPACE_OR_TAB(c) ((c)==' '||(c)=='\t')
/* LEX_* are values for PL_lex_state, the state of the lexer.
* They are arranged oddly so that the guard on the switch statement
* can get by with a single comparison (if the compiler is smart enough).
*/
/* #define LEX_NOTPARSING 11 is done in perl.h. */
#define LEX_NORMAL 10 /* normal code (ie not within "...") */
#define LEX_INTERPNORMAL 9 /* code within a string, eg "$foo[$x+1]" */
#define LEX_INTERPCASEMOD 8 /* expecting a \U, \Q or \E etc */
#define LEX_INTERPPUSH 7 /* starting a new sublex parse level */
#define LEX_INTERPSTART 6 /* expecting the start of a $var */
/* at end of code, eg "$x" followed by: */
#define LEX_INTERPEND 5 /* ... eg not one of [, { or -> */
#define LEX_INTERPENDMAYBE 4 /* ... eg one of [, { or -> */
#define LEX_INTERPCONCAT 3 /* expecting anything, eg at start of
string or after \E, $foo, etc */
#define LEX_INTERPCONST 2 /* NOT USED */
#define LEX_FORMLINE 1 /* expecting a format line */
#define LEX_KNOWNEXT 0 /* next token known; just return it */
#ifdef DEBUGGING
static const char* const lex_state_names[] = {
"KNOWNEXT",
"FORMLINE",
"INTERPCONST",
"INTERPCONCAT",
"INTERPENDMAYBE",
"INTERPEND",
"INTERPSTART",
"INTERPPUSH",
"INTERPCASEMOD",
"INTERPNORMAL",
"NORMAL"
};
#endif
#ifdef ff_next
#undef ff_next
#endif
#include "keywords.h"
/* CLINE is a macro that ensures PL_copline has a sane value */
#ifdef CLINE
#undef CLINE
#endif
#define CLINE (PL_copline = (CopLINE(PL_curcop) < PL_copline ? CopLINE(PL_curcop) : PL_copline))
#ifdef PERL_MAD
# define SKIPSPACE0(s) skipspace0(s)
# define SKIPSPACE1(s) skipspace1(s)
# define SKIPSPACE2(s,tsv) skipspace2(s,&tsv)
# define PEEKSPACE(s) skipspace2(s,0)
#else
# define SKIPSPACE0(s) skipspace(s)
# define SKIPSPACE1(s) skipspace(s)
# define SKIPSPACE2(s,tsv) skipspace(s)
# define PEEKSPACE(s) skipspace(s)
#endif
/*
* Convenience functions to return different tokens and prime the
* lexer for the next token. They all take an argument.
*
* TOKEN : generic token (used for '(', DOLSHARP, etc)
* OPERATOR : generic operator
* AOPERATOR : assignment operator
* PREBLOCK : beginning the block after an if, while, foreach, ...
* PRETERMBLOCK : beginning a non-code-defining {} block (eg, hash ref)
* PREREF : *EXPR where EXPR is not a simple identifier
* TERM : expression term
* LOOPX : loop exiting command (goto, last, dump, etc)
* FTST : file test operator
* FUN0 : zero-argument function
* FUN0OP : zero-argument function, with its op created in this file
* FUN1 : not used, except for not, which isn't a UNIOP
* BOop : bitwise or or xor
* BAop : bitwise and
* SHop : shift operator
* PWop : power operator
* PMop : pattern-matching operator
* Aop : addition-level operator
* Mop : multiplication-level operator
* Eop : equality-testing operator
* Rop : relational operator <= != gt
*
* Also see LOP and lop() below.
*/
#ifdef DEBUGGING /* Serve -DT. */
# define REPORT(retval) tokereport((I32)retval, &pl_yylval)
#else
# define REPORT(retval) (retval)
#endif
#define TOKEN(retval) return ( PL_bufptr = s, REPORT(retval))
#define OPERATOR(retval) return (PL_expect = XTERM, PL_bufptr = s, REPORT(retval))
#define AOPERATOR(retval) return ao((PL_expect = XTERM, PL_bufptr = s, REPORT(retval)))
#define PREBLOCK(retval) return (PL_expect = XBLOCK,PL_bufptr = s, REPORT(retval))
#define PRETERMBLOCK(retval) return (PL_expect = XTERMBLOCK,PL_bufptr = s, REPORT(retval))
#define PREREF(retval) return (PL_expect = XREF,PL_bufptr = s, REPORT(retval))
#define TERM(retval) return (CLINE, PL_expect = XOPERATOR, PL_bufptr = s, REPORT(retval))
#define LOOPX(f) return (pl_yylval.ival=f, PL_expect=XTERM, PL_bufptr=s, REPORT((int)LOOPEX))
#define FTST(f) return (pl_yylval.ival=f, PL_expect=XTERMORDORDOR, PL_bufptr=s, REPORT((int)UNIOP))
#define FUN0(f) return (pl_yylval.ival=f, PL_expect=XOPERATOR, PL_bufptr=s, REPORT((int)FUNC0))
#define FUN0OP(f) return (pl_yylval.opval=f, CLINE, PL_expect=XOPERATOR, PL_bufptr=s, REPORT((int)FUNC0OP))
#define FUN1(f) return (pl_yylval.ival=f, PL_expect=XOPERATOR, PL_bufptr=s, REPORT((int)FUNC1))
#define BOop(f) return ao((pl_yylval.ival=f, PL_expect=XTERM, PL_bufptr=s, REPORT((int)BITOROP)))
#define BAop(f) return ao((pl_yylval.ival=f, PL_expect=XTERM, PL_bufptr=s, REPORT((int)BITANDOP)))
#define SHop(f) return ao((pl_yylval.ival=f, PL_expect=XTERM, PL_bufptr=s, REPORT((int)SHIFTOP)))
#define PWop(f) return ao((pl_yylval.ival=f, PL_expect=XTERM, PL_bufptr=s, REPORT((int)POWOP)))
#define PMop(f) return(pl_yylval.ival=f, PL_expect=XTERM, PL_bufptr=s, REPORT((int)MATCHOP))
#define Aop(f) return ao((pl_yylval.ival=f, PL_expect=XTERM, PL_bufptr=s, REPORT((int)ADDOP)))
#define Mop(f) return ao((pl_yylval.ival=f, PL_expect=XTERM, PL_bufptr=s, REPORT((int)MULOP)))
#define Eop(f) return (pl_yylval.ival=f, PL_expect=XTERM, PL_bufptr=s, REPORT((int)EQOP))
#define Rop(f) return (pl_yylval.ival=f, PL_expect=XTERM, PL_bufptr=s, REPORT((int)RELOP))
/* This bit of chicanery makes a unary function followed by
* a parenthesis into a function with one argument, highest precedence.
* The UNIDOR macro is for unary functions that can be followed by the //
* operator (such as C<shift // 0>).
*/
#define UNI2(f,x) { \
pl_yylval.ival = f; \
PL_expect = x; \
PL_bufptr = s; \
PL_last_uni = PL_oldbufptr; \
PL_last_lop_op = f; \
if (*s == '(') \
return REPORT( (int)FUNC1 ); \
s = PEEKSPACE(s); \
return REPORT( *s=='(' ? (int)FUNC1 : (int)UNIOP ); \
}
#define UNI(f) UNI2(f,XTERM)
#define UNIDOR(f) UNI2(f,XTERMORDORDOR)
#define UNIPROTO(f,optional) { \
if (optional) PL_last_uni = PL_oldbufptr; \
OPERATOR(f); \
}
#define UNIBRACK(f) { \
pl_yylval.ival = f; \
PL_bufptr = s; \
PL_last_uni = PL_oldbufptr; \
if (*s == '(') \
return REPORT( (int)FUNC1 ); \
s = PEEKSPACE(s); \
return REPORT( (*s == '(') ? (int)FUNC1 : (int)UNIOP ); \
}
/* grandfather return to old style */
#define OLDLOP(f) \
do { \
if (!PL_lex_allbrackets && PL_lex_fakeeof > LEX_FAKEEOF_LOWLOGIC) \
PL_lex_fakeeof = LEX_FAKEEOF_LOWLOGIC; \
pl_yylval.ival = (f); \
PL_expect = XTERM; \
PL_bufptr = s; \
return (int)LSTOP; \
} while(0)
#ifdef DEBUGGING
/* how to interpret the pl_yylval associated with the token */
enum token_type {
TOKENTYPE_NONE,
TOKENTYPE_IVAL,
TOKENTYPE_OPNUM, /* pl_yylval.ival contains an opcode number */
TOKENTYPE_PVAL,
TOKENTYPE_OPVAL,
TOKENTYPE_GVVAL
};
static struct debug_tokens {
const int token;
enum token_type type;
const char *name;
} const debug_tokens[] =
{
{ ADDOP, TOKENTYPE_OPNUM, "ADDOP" },
{ ANDAND, TOKENTYPE_NONE, "ANDAND" },
{ ANDOP, TOKENTYPE_NONE, "ANDOP" },
{ ANONSUB, TOKENTYPE_IVAL, "ANONSUB" },
{ ARROW, TOKENTYPE_NONE, "ARROW" },
{ ASSIGNOP, TOKENTYPE_OPNUM, "ASSIGNOP" },
{ BITANDOP, TOKENTYPE_OPNUM, "BITANDOP" },
{ BITOROP, TOKENTYPE_OPNUM, "BITOROP" },
{ COLONATTR, TOKENTYPE_NONE, "COLONATTR" },
{ CONTINUE, TOKENTYPE_NONE, "CONTINUE" },
{ DEFAULT, TOKENTYPE_NONE, "DEFAULT" },
{ DO, TOKENTYPE_NONE, "DO" },
{ DOLSHARP, TOKENTYPE_NONE, "DOLSHARP" },
{ DORDOR, TOKENTYPE_NONE, "DORDOR" },
{ DOROP, TOKENTYPE_OPNUM, "DOROP" },
{ DOTDOT, TOKENTYPE_IVAL, "DOTDOT" },
{ ELSE, TOKENTYPE_NONE, "ELSE" },
{ ELSIF, TOKENTYPE_IVAL, "ELSIF" },
{ EQOP, TOKENTYPE_OPNUM, "EQOP" },
{ FOR, TOKENTYPE_IVAL, "FOR" },
{ FORMAT, TOKENTYPE_NONE, "FORMAT" },
{ FUNC, TOKENTYPE_OPNUM, "FUNC" },
{ FUNC0, TOKENTYPE_OPNUM, "FUNC0" },
{ FUNC0OP, TOKENTYPE_OPVAL, "FUNC0OP" },
{ FUNC0SUB, TOKENTYPE_OPVAL, "FUNC0SUB" },
{ FUNC1, TOKENTYPE_OPNUM, "FUNC1" },
{ FUNCMETH, TOKENTYPE_OPVAL, "FUNCMETH" },
{ GIVEN, TOKENTYPE_IVAL, "GIVEN" },
{ HASHBRACK, TOKENTYPE_NONE, "HASHBRACK" },
{ IF, TOKENTYPE_IVAL, "IF" },
{ LABEL, TOKENTYPE_OPVAL, "LABEL" },
{ LOCAL, TOKENTYPE_IVAL, "LOCAL" },
{ LOOPEX, TOKENTYPE_OPNUM, "LOOPEX" },
{ LSTOP, TOKENTYPE_OPNUM, "LSTOP" },
{ LSTOPSUB, TOKENTYPE_OPVAL, "LSTOPSUB" },
{ MATCHOP, TOKENTYPE_OPNUM, "MATCHOP" },
{ METHOD, TOKENTYPE_OPVAL, "METHOD" },
{ MULOP, TOKENTYPE_OPNUM, "MULOP" },
{ MY, TOKENTYPE_IVAL, "MY" },
{ MYSUB, TOKENTYPE_NONE, "MYSUB" },
{ NOAMP, TOKENTYPE_NONE, "NOAMP" },
{ NOTOP, TOKENTYPE_NONE, "NOTOP" },
{ OROP, TOKENTYPE_IVAL, "OROP" },
{ OROR, TOKENTYPE_NONE, "OROR" },
{ PACKAGE, TOKENTYPE_NONE, "PACKAGE" },
{ PLUGEXPR, TOKENTYPE_OPVAL, "PLUGEXPR" },
{ PLUGSTMT, TOKENTYPE_OPVAL, "PLUGSTMT" },
{ PMFUNC, TOKENTYPE_OPVAL, "PMFUNC" },
{ POSTDEC, TOKENTYPE_NONE, "POSTDEC" },
{ POSTINC, TOKENTYPE_NONE, "POSTINC" },
{ POWOP, TOKENTYPE_OPNUM, "POWOP" },
{ PREDEC, TOKENTYPE_NONE, "PREDEC" },
{ PREINC, TOKENTYPE_NONE, "PREINC" },
{ PRIVATEREF, TOKENTYPE_OPVAL, "PRIVATEREF" },
{ REFGEN, TOKENTYPE_NONE, "REFGEN" },
{ RELOP, TOKENTYPE_OPNUM, "RELOP" },
{ SHIFTOP, TOKENTYPE_OPNUM, "SHIFTOP" },
{ SUB, TOKENTYPE_NONE, "SUB" },
{ THING, TOKENTYPE_OPVAL, "THING" },
{ UMINUS, TOKENTYPE_NONE, "UMINUS" },
{ UNIOP, TOKENTYPE_OPNUM, "UNIOP" },
{ UNIOPSUB, TOKENTYPE_OPVAL, "UNIOPSUB" },
{ UNLESS, TOKENTYPE_IVAL, "UNLESS" },
{ UNTIL, TOKENTYPE_IVAL, "UNTIL" },
{ USE, TOKENTYPE_IVAL, "USE" },
{ WHEN, TOKENTYPE_IVAL, "WHEN" },
{ WHILE, TOKENTYPE_IVAL, "WHILE" },
{ WORD, TOKENTYPE_OPVAL, "WORD" },
{ YADAYADA, TOKENTYPE_IVAL, "YADAYADA" },
{ 0, TOKENTYPE_NONE, NULL }
};
/* dump the returned token in rv, plus any optional arg in pl_yylval */
STATIC int
S_tokereport(pTHX_ I32 rv, const YYSTYPE* lvalp)
{
dVAR;
PERL_ARGS_ASSERT_TOKEREPORT;
if (DEBUG_T_TEST) {
const char *name = NULL;
enum token_type type = TOKENTYPE_NONE;
const struct debug_tokens *p;
SV* const report = newSVpvs("<== ");
for (p = debug_tokens; p->token; p++) {
if (p->token == (int)rv) {
name = p->name;
type = p->type;
break;
}
}
if (name)
Perl_sv_catpv(aTHX_ report, name);
else if ((char)rv > ' ' && (char)rv < '~')
Perl_sv_catpvf(aTHX_ report, "'%c'", (char)rv);
else if (!rv)
sv_catpvs(report, "EOF");
else
Perl_sv_catpvf(aTHX_ report, "?? %"IVdf, (IV)rv);
switch (type) {
case TOKENTYPE_NONE:
case TOKENTYPE_GVVAL: /* doesn't appear to be used */
break;
case TOKENTYPE_IVAL:
Perl_sv_catpvf(aTHX_ report, "(ival=%"IVdf")", (IV)lvalp->ival);
break;
case TOKENTYPE_OPNUM:
Perl_sv_catpvf(aTHX_ report, "(ival=op_%s)",
PL_op_name[lvalp->ival]);
break;
case TOKENTYPE_PVAL:
Perl_sv_catpvf(aTHX_ report, "(pval=\"%s\")", lvalp->pval);
break;
case TOKENTYPE_OPVAL:
if (lvalp->opval) {
Perl_sv_catpvf(aTHX_ report, "(opval=op_%s)",
PL_op_name[lvalp->opval->op_type]);
if (lvalp->opval->op_type == OP_CONST) {
Perl_sv_catpvf(aTHX_ report, " %s",
SvPEEK(cSVOPx_sv(lvalp->opval)));
}
}
else
sv_catpvs(report, "(opval=null)");
break;
}
PerlIO_printf(Perl_debug_log, "### %s\n\n", SvPV_nolen_const(report));
};
return (int)rv;
}
/* print the buffer with suitable escapes */
STATIC void
S_printbuf(pTHX_ const char *const fmt, const char *const s)
{
SV* const tmp = newSVpvs("");
PERL_ARGS_ASSERT_PRINTBUF;
PerlIO_printf(Perl_debug_log, fmt, pv_display(tmp, s, strlen(s), 0, 60));
SvREFCNT_dec(tmp);
}
#endif
static int
S_deprecate_commaless_var_list(pTHX) {
PL_expect = XTERM;
deprecate("comma-less variable list");
return REPORT(','); /* grandfather non-comma-format format */
}
/*
* S_ao
*
* This subroutine detects &&=, ||=, and //= and turns an ANDAND, OROR or DORDOR
* into an OP_ANDASSIGN, OP_ORASSIGN, or OP_DORASSIGN
*/
STATIC int
S_ao(pTHX_ int toketype)
{
dVAR;
if (*PL_bufptr == '=') {
PL_bufptr++;
if (toketype == ANDAND)
pl_yylval.ival = OP_ANDASSIGN;
else if (toketype == OROR)
pl_yylval.ival = OP_ORASSIGN;
else if (toketype == DORDOR)
pl_yylval.ival = OP_DORASSIGN;
toketype = ASSIGNOP;
}
return toketype;
}
/*
* S_no_op
* When Perl expects an operator and finds something else, no_op
* prints the warning. It always prints "<something> found where
* operator expected. It prints "Missing semicolon on previous line?"
* if the surprise occurs at the start of the line. "do you need to
* predeclare ..." is printed out for code like "sub bar; foo bar $x"
* where the compiler doesn't know if foo is a method call or a function.
* It prints "Missing operator before end of line" if there's nothing
* after the missing operator, or "... before <...>" if there is something
* after the missing operator.
*/
STATIC void
S_no_op(pTHX_ const char *const what, char *s)
{
dVAR;
char * const oldbp = PL_bufptr;
const bool is_first = (PL_oldbufptr == PL_linestart);
PERL_ARGS_ASSERT_NO_OP;
if (!s)
s = oldbp;
else
PL_bufptr = s;
yywarn(Perl_form(aTHX_ "%s found where operator expected", what), UTF ? SVf_UTF8 : 0);
if (ckWARN_d(WARN_SYNTAX)) {
if (is_first)
Perl_warner(aTHX_ packWARN(WARN_SYNTAX),
"\t(Missing semicolon on previous line?)\n");
else if (PL_oldoldbufptr && isIDFIRST_lazy_if(PL_oldoldbufptr,UTF)) {
const char *t;
for (t = PL_oldoldbufptr; (isALNUM_lazy_if(t,UTF) || *t == ':');
t += UTF ? UTF8SKIP(t) : 1)
NOOP;
if (t < PL_bufptr && isSPACE(*t))
Perl_warner(aTHX_ packWARN(WARN_SYNTAX),
"\t(Do you need to predeclare %"SVf"?)\n",
SVfARG(newSVpvn_flags(PL_oldoldbufptr, (STRLEN)(t - PL_oldoldbufptr),
SVs_TEMP | (UTF ? SVf_UTF8 : 0))));
}
else {
assert(s >= oldbp);
Perl_warner(aTHX_ packWARN(WARN_SYNTAX),
"\t(Missing operator before %"SVf"?)\n",
SVfARG(newSVpvn_flags(oldbp, (STRLEN)(s - oldbp),
SVs_TEMP | (UTF ? SVf_UTF8 : 0))));
}
}
PL_bufptr = oldbp;
}
/*
* S_missingterm
* Complain about missing quote/regexp/heredoc terminator.
* If it's called with NULL then it cauterizes the line buffer.
* If we're in a delimited string and the delimiter is a control
* character, it's reformatted into a two-char sequence like ^C.
* This is fatal.
*/
STATIC void
S_missingterm(pTHX_ char *s)
{
dVAR;
char tmpbuf[3];
char q;
if (s) {
char * const nl = strrchr(s,'\n');
if (nl)
*nl = '\0';
}
else if (isCNTRL(PL_multi_close)) {
*tmpbuf = '^';
tmpbuf[1] = (char)toCTRL(PL_multi_close);
tmpbuf[2] = '\0';
s = tmpbuf;
}
else {
*tmpbuf = (char)PL_multi_close;
tmpbuf[1] = '\0';
s = tmpbuf;
}
q = strchr(s,'"') ? '\'' : '"';
Perl_croak(aTHX_ "Can't find string terminator %c%s%c anywhere before EOF",q,s,q);
}
#include "feature.h"
/*
* Check whether the named feature is enabled.
*/
bool
Perl_feature_is_enabled(pTHX_ const char *const name, STRLEN namelen)
{
dVAR;
char he_name[8 + MAX_FEATURE_LEN] = "feature_";
PERL_ARGS_ASSERT_FEATURE_IS_ENABLED;
assert(CURRENT_FEATURE_BUNDLE == FEATURE_BUNDLE_CUSTOM);
if (namelen > MAX_FEATURE_LEN)
return FALSE;
memcpy(&he_name[8], name, namelen);
return cBOOL(cop_hints_fetch_pvn(PL_curcop, he_name, 8 + namelen, 0,
REFCOUNTED_HE_EXISTS));
}
/*
* experimental text filters for win32 carriage-returns, utf16-to-utf8 and
* utf16-to-utf8-reversed.
*/
#ifdef PERL_CR_FILTER
static void
strip_return(SV *sv)
{
register const char *s = SvPVX_const(sv);
register const char * const e = s + SvCUR(sv);
PERL_ARGS_ASSERT_STRIP_RETURN;
/* outer loop optimized to do nothing if there are no CR-LFs */
while (s < e) {
if (*s++ == '\r' && *s == '\n') {
/* hit a CR-LF, need to copy the rest */
register char *d = s - 1;
*d++ = *s++;
while (s < e) {
if (*s == '\r' && s[1] == '\n')
s++;
*d++ = *s++;
}
SvCUR(sv) -= s - d;
return;
}
}
}
STATIC I32
S_cr_textfilter(pTHX_ int idx, SV *sv, int maxlen)
{
const I32 count = FILTER_READ(idx+1, sv, maxlen);
if (count > 0 && !maxlen)
strip_return(sv);
return count;
}
#endif
/*
=for apidoc Amx|void|lex_start|SV *line|PerlIO *rsfp|U32 flags
Creates and initialises a new lexer/parser state object, supplying
a context in which to lex and parse from a new source of Perl code.
A pointer to the new state object is placed in L</PL_parser>. An entry
is made on the save stack so that upon unwinding the new state object
will be destroyed and the former value of L</PL_parser> will be restored.
Nothing else need be done to clean up the parsing context.
The code to be parsed comes from I<line> and I<rsfp>. I<line>, if
non-null, provides a string (in SV form) containing code to be parsed.
A copy of the string is made, so subsequent modification of I<line>
does not affect parsing. I<rsfp>, if non-null, provides an input stream
from which code will be read to be parsed. If both are non-null, the
code in I<line> comes first and must consist of complete lines of input,
and I<rsfp> supplies the remainder of the source.
The I<flags> parameter is reserved for future use. Currently it is only
used by perl internally, so extensions should always pass zero.
=cut
*/
/* LEX_START_SAME_FILTER indicates that this is not a new file, so it
can share filters with the current parser.
LEX_START_DONT_CLOSE indicates that the file handle wasn't opened by the
caller, hence isn't owned by the parser, so shouldn't be closed on parser
destruction. This is used to handle the case of defaulting to reading the
script from the standard input because no filename was given on the command
line (without getting confused by situation where STDIN has been closed, so
the script handle is opened on fd 0) */
void
Perl_lex_start(pTHX_ SV *line, PerlIO *rsfp, U32 flags)
{
dVAR;
const char *s = NULL;
yy_parser *parser, *oparser;
if (flags && flags & ~LEX_START_FLAGS)
Perl_croak(aTHX_ "Lexing code internal error (%s)", "lex_start");
/* create and initialise a parser */
Newxz(parser, 1, yy_parser);
parser->old_parser = oparser = PL_parser;
PL_parser = parser;
parser->stack = NULL;
parser->ps = NULL;
parser->stack_size = 0;
/* on scope exit, free this parser and restore any outer one */
SAVEPARSER(parser);
parser->saved_curcop = PL_curcop;
/* initialise lexer state */
#ifdef PERL_MAD
parser->curforce = -1;
#else
parser->nexttoke = 0;
#endif
parser->error_count = oparser ? oparser->error_count : 0;
parser->copline = NOLINE;
parser->lex_state = LEX_NORMAL;
parser->expect = XSTATE;
parser->rsfp = rsfp;
parser->rsfp_filters =
!(flags & LEX_START_SAME_FILTER) || !oparser
? NULL
: MUTABLE_AV(SvREFCNT_inc(
oparser->rsfp_filters
? oparser->rsfp_filters
: (oparser->rsfp_filters = newAV())
));
Newx(parser->lex_brackstack, 120, char);
Newx(parser->lex_casestack, 12, char);
*parser->lex_casestack = '\0';
if (line) {
STRLEN len;
s = SvPV_const(line, len);
parser->linestr = flags & LEX_START_COPIED
? SvREFCNT_inc_simple_NN(line)
: newSVpvn_flags(s, len, SvUTF8(line));
if (!len || s[len-1] != ';')
sv_catpvs(parser->linestr, "\n;");
} else {
parser->linestr = newSVpvs("\n;");
}
parser->oldoldbufptr =
parser->oldbufptr =
parser->bufptr =
parser->linestart = SvPVX(parser->linestr);
parser->bufend = parser->bufptr + SvCUR(parser->linestr);
parser->last_lop = parser->last_uni = NULL;
parser->lex_flags = flags & (LEX_IGNORE_UTF8_HINTS|LEX_EVALBYTES
|LEX_DONT_CLOSE_RSFP);
parser->in_pod = parser->filtered = 0;
}
/* delete a parser object */
void
Perl_parser_free(pTHX_ const yy_parser *parser)
{
PERL_ARGS_ASSERT_PARSER_FREE;
PL_curcop = parser->saved_curcop;
SvREFCNT_dec(parser->linestr);
if (PL_parser->lex_flags & LEX_DONT_CLOSE_RSFP)
PerlIO_clearerr(parser->rsfp);
else if (parser->rsfp && (!parser->old_parser ||
(parser->old_parser && parser->rsfp != parser->old_parser->rsfp)))
PerlIO_close(parser->rsfp);
SvREFCNT_dec(parser->rsfp_filters);
Safefree(parser->lex_brackstack);
Safefree(parser->lex_casestack);
PL_parser = parser->old_parser;
Safefree(parser);
}
/*
=for apidoc AmxU|SV *|PL_parser-E<gt>linestr
Buffer scalar containing the chunk currently under consideration of the
text currently being lexed. This is always a plain string scalar (for
which C<SvPOK> is true). It is not intended to be used as a scalar by
normal scalar means; instead refer to the buffer directly by the pointer
variables described below.
The lexer maintains various C<char*> pointers to things in the
C<PL_parser-E<gt>linestr> buffer. If C<PL_parser-E<gt>linestr> is ever
reallocated, all of these pointers must be updated. Don't attempt to
do this manually, but rather use L</lex_grow_linestr> if you need to
reallocate the buffer.
The content of the text chunk in the buffer is commonly exactly one
complete line of input, up to and including a newline terminator,
but there are situations where it is otherwise. The octets of the
buffer may be intended to be interpreted as either UTF-8 or Latin-1.
The function L</lex_bufutf8> tells you which. Do not use the C<SvUTF8>
flag on this scalar, which may disagree with it.
For direct examination of the buffer, the variable
L</PL_parser-E<gt>bufend> points to the end of the buffer. The current
lexing position is pointed to by L</PL_parser-E<gt>bufptr>. Direct use
of these pointers is usually preferable to examination of the scalar
through normal scalar means.
=for apidoc AmxU|char *|PL_parser-E<gt>bufend
Direct pointer to the end of the chunk of text currently being lexed, the
end of the lexer buffer. This is equal to C<SvPVX(PL_parser-E<gt>linestr)
+ SvCUR(PL_parser-E<gt>linestr)>. A NUL character (zero octet) is
always located at the end of the buffer, and does not count as part of
the buffer's contents.
=for apidoc AmxU|char *|PL_parser-E<gt>bufptr
Points to the current position of lexing inside the lexer buffer.
Characters around this point may be freely examined, within
the range delimited by C<SvPVX(L</PL_parser-E<gt>linestr>)> and
L</PL_parser-E<gt>bufend>. The octets of the buffer may be intended to be
interpreted as either UTF-8 or Latin-1, as indicated by L</lex_bufutf8>.
Lexing code (whether in the Perl core or not) moves this pointer past
the characters that it consumes. It is also expected to perform some
bookkeeping whenever a newline character is consumed. This movement
can be more conveniently performed by the function L</lex_read_to>,
which handles newlines appropriately.
Interpretation of the buffer's octets can be abstracted out by
using the slightly higher-level functions L</lex_peek_unichar> and
L</lex_read_unichar>.
=for apidoc AmxU|char *|PL_parser-E<gt>linestart
Points to the start of the current line inside the lexer buffer.
This is useful for indicating at which column an error occurred, and
not much else. This must be updated by any lexing code that consumes
a newline; the function L</lex_read_to> handles this detail.
=cut
*/
/*
=for apidoc Amx|bool|lex_bufutf8
Indicates whether the octets in the lexer buffer
(L</PL_parser-E<gt>linestr>) should be interpreted as the UTF-8 encoding
of Unicode characters. If not, they should be interpreted as Latin-1
characters. This is analogous to the C<SvUTF8> flag for scalars.
In UTF-8 mode, it is not guaranteed that the lexer buffer actually
contains valid UTF-8. Lexing code must be robust in the face of invalid
encoding.
The actual C<SvUTF8> flag of the L</PL_parser-E<gt>linestr> scalar
is significant, but not the whole story regarding the input character
encoding. Normally, when a file is being read, the scalar contains octets
and its C<SvUTF8> flag is off, but the octets should be interpreted as
UTF-8 if the C<use utf8> pragma is in effect. During a string eval,
however, the scalar may have the C<SvUTF8> flag on, and in this case its
octets should be interpreted as UTF-8 unless the C<use bytes> pragma
is in effect. This logic may change in the future; use this function
instead of implementing the logic yourself.
=cut
*/
bool
Perl_lex_bufutf8(pTHX)
{
return UTF;
}
/*
=for apidoc Amx|char *|lex_grow_linestr|STRLEN len
Reallocates the lexer buffer (L</PL_parser-E<gt>linestr>) to accommodate
at least I<len> octets (including terminating NUL). Returns a
pointer to the reallocated buffer. This is necessary before making
any direct modification of the buffer that would increase its length.
L</lex_stuff_pvn> provides a more convenient way to insert text into
the buffer.
Do not use C<SvGROW> or C<sv_grow> directly on C<PL_parser-E<gt>linestr>;
this function updates all of the lexer's variables that point directly
into the buffer.
=cut
*/
char *
Perl_lex_grow_linestr(pTHX_ STRLEN len)
{
SV *linestr;
char *buf;
STRLEN bufend_pos, bufptr_pos, oldbufptr_pos, oldoldbufptr_pos;
STRLEN linestart_pos, last_uni_pos, last_lop_pos;
linestr = PL_parser->linestr;
buf = SvPVX(linestr);
if (len <= SvLEN(linestr))
return buf;
bufend_pos = PL_parser->bufend - buf;
bufptr_pos = PL_parser->bufptr - buf;
oldbufptr_pos = PL_parser->oldbufptr - buf;
oldoldbufptr_pos = PL_parser->oldoldbufptr - buf;
linestart_pos = PL_parser->linestart - buf;
last_uni_pos = PL_parser->last_uni ? PL_parser->last_uni - buf : 0;
last_lop_pos = PL_parser->last_lop ? PL_parser->last_lop - buf : 0;
buf = sv_grow(linestr, len);
PL_parser->bufend = buf + bufend_pos;
PL_parser->bufptr = buf + bufptr_pos;
PL_parser->oldbufptr = buf + oldbufptr_pos;
PL_parser->oldoldbufptr = buf + oldoldbufptr_pos;
PL_parser->linestart = buf + linestart_pos;
if (PL_parser->last_uni)
PL_parser->last_uni = buf + last_uni_pos;
if (PL_parser->last_lop)
PL_parser->last_lop = buf + last_lop_pos;
return buf;
}
/*
=for apidoc Amx|void|lex_stuff_pvn|const char *pv|STRLEN len|U32 flags
Insert characters into the lexer buffer (L</PL_parser-E<gt>linestr>),
immediately after the current lexing point (L</PL_parser-E<gt>bufptr>),
reallocating the buffer if necessary. This means that lexing code that
runs later will see the characters as if they had appeared in the input.
It is not recommended to do this as part of normal parsing, and most
uses of this facility run the risk of the inserted characters being
interpreted in an unintended manner.
The string to be inserted is represented by I<len> octets starting
at I<pv>. These octets are interpreted as either UTF-8 or Latin-1,
according to whether the C<LEX_STUFF_UTF8> flag is set in I<flags>.
The characters are recoded for the lexer buffer, according to how the
buffer is currently being interpreted (L</lex_bufutf8>). If a string
to be inserted is available as a Perl scalar, the L</lex_stuff_sv>
function is more convenient.
=cut
*/
void
Perl_lex_stuff_pvn(pTHX_ const char *pv, STRLEN len, U32 flags)
{
dVAR;
char *bufptr;
PERL_ARGS_ASSERT_LEX_STUFF_PVN;
if (flags & ~(LEX_STUFF_UTF8))
Perl_croak(aTHX_ "Lexing code internal error (%s)", "lex_stuff_pvn");
if (UTF) {
if (flags & LEX_STUFF_UTF8) {
goto plain_copy;
} else {
STRLEN highhalf = 0;
const char *p, *e = pv+len;
for (p = pv; p != e; p++)
highhalf += !!(((U8)*p) & 0x80);
if (!highhalf)
goto plain_copy;
lex_grow_linestr(SvCUR(PL_parser->linestr)+1+len+highhalf);
bufptr = PL_parser->bufptr;
Move(bufptr, bufptr+len+highhalf, PL_parser->bufend+1-bufptr, char);
SvCUR_set(PL_parser->linestr,
SvCUR(PL_parser->linestr) + len+highhalf);
PL_parser->bufend += len+highhalf;
for (p = pv; p != e; p++) {
U8 c = (U8)*p;
if (c & 0x80) {
*bufptr++ = (char)(0xc0 | (c >> 6));
*bufptr++ = (char)(0x80 | (c & 0x3f));
} else {
*bufptr++ = (char)c;
}
}
}
} else {
if (flags & LEX_STUFF_UTF8) {
STRLEN highhalf = 0;
const char *p, *e = pv+len;
for (p = pv; p != e; p++) {
U8 c = (U8)*p;
if (c >= 0xc4) {