-
Notifications
You must be signed in to change notification settings - Fork 3
/
Copy pathc-lex.c
2021 lines (1762 loc) · 49.9 KB
/
c-lex.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
/* Lexical analyzer for C and Objective C.
Copyright (C) 1987, 88, 89, 92, 94, 1995 Free Software Foundation, Inc.
This file is part of GNU CC.
GNU CC 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 2, or (at your option)
any later version.
GNU CC 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 GNU CC; see the file COPYING. If not, write to
the Free Software Foundation, 59 Temple Place - Suite 330,
Boston, MA 02111-1307, USA. */
#include <stdio.h>
#include <errno.h>
#include <setjmp.h>
#include "config.h"
#include "rtl.h"
#include "tree.h"
#include "input.h"
#include "c-lex.h"
#include "c-tree.h"
#include "flags.h"
#include "c-parse.h"
#include "c-pragma.h"
#include <ctype.h>
#ifdef MULTIBYTE_CHARS
#include <stdlib.h>
#include <locale.h>
#endif
#ifndef errno
extern int errno;
#endif
/* The elements of `ridpointers' are identifier nodes
for the reserved type names and storage classes.
It is indexed by a RID_... value. */
tree ridpointers[(int) RID_MAX];
/* Cause the `yydebug' variable to be defined. */
#define YYDEBUG 1
/* the declaration found for the last IDENTIFIER token read in.
yylex must look this up to detect typedefs, which get token type TYPENAME,
so it is left around in case the identifier is not a typedef but is
used in a context which makes it a reference to a variable. */
tree lastiddecl;
/* Nonzero enables objc features. */
int doing_objc_thang;
extern tree is_class_name ();
extern int yydebug;
/* File used for outputting assembler code. */
extern FILE *asm_out_file;
#ifndef WCHAR_TYPE_SIZE
#ifdef INT_TYPE_SIZE
#define WCHAR_TYPE_SIZE INT_TYPE_SIZE
#else
#define WCHAR_TYPE_SIZE BITS_PER_WORD
#endif
#endif
/* Number of bytes in a wide character. */
#define WCHAR_BYTES (WCHAR_TYPE_SIZE / BITS_PER_UNIT)
static int maxtoken; /* Current nominal length of token buffer. */
char *token_buffer; /* Pointer to token buffer.
Actual allocated length is maxtoken + 2.
This is not static because objc-parse.y uses it. */
/* Nonzero if end-of-file has been seen on input. */
static int end_of_file;
/* Buffered-back input character; faster than using ungetc. */
static int nextchar = -1;
int check_newline ();
/* Do not insert generated code into the source, instead, include it.
This allows us to build gcc automatically even for targets that
need to add or modify the reserved keyword lists. */
#include "c-gperf.h"
/* Return something to represent absolute declarators containing a *.
TARGET is the absolute declarator that the * contains.
TYPE_QUALS is a list of modifiers such as const or volatile
to apply to the pointer type, represented as identifiers.
We return an INDIRECT_REF whose "contents" are TARGET
and whose type is the modifier list. */
tree
make_pointer_declarator (type_quals, target)
tree type_quals, target;
{
return build1 (INDIRECT_REF, type_quals, target);
}
void
forget_protocol_qualifiers ()
{
int i, n = sizeof wordlist / sizeof (struct resword);
for (i = 0; i < n; i++)
if ((int) wordlist[i].rid >= (int) RID_IN
&& (int) wordlist[i].rid <= (int) RID_ONEWAY)
wordlist[i].name = "";
}
void
remember_protocol_qualifiers ()
{
int i, n = sizeof wordlist / sizeof (struct resword);
for (i = 0; i < n; i++)
if (wordlist[i].rid == RID_IN)
wordlist[i].name = "in";
else if (wordlist[i].rid == RID_OUT)
wordlist[i].name = "out";
else if (wordlist[i].rid == RID_INOUT)
wordlist[i].name = "inout";
else if (wordlist[i].rid == RID_BYCOPY)
wordlist[i].name = "bycopy";
else if (wordlist[i].rid == RID_ONEWAY)
wordlist[i].name = "oneway";
}
void
init_lex ()
{
/* Make identifier nodes long enough for the language-specific slots. */
set_identifier_size (sizeof (struct lang_identifier));
/* Start it at 0, because check_newline is called at the very beginning
and will increment it to 1. */
lineno = 0;
#ifdef MULTIBYTE_CHARS
/* Change to the native locale for multibyte conversions. */
setlocale (LC_CTYPE, "");
#endif
maxtoken = 40;
token_buffer = (char *) xmalloc (maxtoken + 2);
ridpointers[(int) RID_INT] = get_identifier ("int");
ridpointers[(int) RID_CHAR] = get_identifier ("char");
ridpointers[(int) RID_VOID] = get_identifier ("void");
ridpointers[(int) RID_FLOAT] = get_identifier ("float");
ridpointers[(int) RID_DOUBLE] = get_identifier ("double");
ridpointers[(int) RID_SHORT] = get_identifier ("short");
ridpointers[(int) RID_LONG] = get_identifier ("long");
ridpointers[(int) RID_UNSIGNED] = get_identifier ("unsigned");
ridpointers[(int) RID_SIGNED] = get_identifier ("signed");
ridpointers[(int) RID_INLINE] = get_identifier ("inline");
ridpointers[(int) RID_CONST] = get_identifier ("const");
ridpointers[(int) RID_VOLATILE] = get_identifier ("volatile");
ridpointers[(int) RID_AUTO] = get_identifier ("auto");
ridpointers[(int) RID_STATIC] = get_identifier ("static");
ridpointers[(int) RID_EXTERN] = get_identifier ("extern");
ridpointers[(int) RID_TYPEDEF] = get_identifier ("typedef");
ridpointers[(int) RID_REGISTER] = get_identifier ("register");
ridpointers[(int) RID_ITERATOR] = get_identifier ("iterator");
ridpointers[(int) RID_COMPLEX] = get_identifier ("complex");
ridpointers[(int) RID_ID] = get_identifier ("id");
ridpointers[(int) RID_IN] = get_identifier ("in");
ridpointers[(int) RID_OUT] = get_identifier ("out");
ridpointers[(int) RID_INOUT] = get_identifier ("inout");
ridpointers[(int) RID_BYCOPY] = get_identifier ("bycopy");
ridpointers[(int) RID_ONEWAY] = get_identifier ("oneway");
forget_protocol_qualifiers();
/* Some options inhibit certain reserved words.
Clear those words out of the hash table so they won't be recognized. */
#define UNSET_RESERVED_WORD(STRING) \
do { struct resword *s = is_reserved_word (STRING, sizeof (STRING) - 1); \
if (s) s->name = ""; } while (0)
if (! doing_objc_thang)
UNSET_RESERVED_WORD ("id");
if (flag_traditional)
{
UNSET_RESERVED_WORD ("const");
UNSET_RESERVED_WORD ("volatile");
UNSET_RESERVED_WORD ("typeof");
UNSET_RESERVED_WORD ("signed");
UNSET_RESERVED_WORD ("inline");
UNSET_RESERVED_WORD ("iterator");
UNSET_RESERVED_WORD ("complex");
}
if (flag_no_asm)
{
UNSET_RESERVED_WORD ("asm");
UNSET_RESERVED_WORD ("typeof");
UNSET_RESERVED_WORD ("inline");
UNSET_RESERVED_WORD ("iterator");
UNSET_RESERVED_WORD ("complex");
}
}
void
reinit_parse_for_function ()
{
}
/* Function used when yydebug is set, to print a token in more detail. */
void
yyprint (file, yychar, yylval)
FILE *file;
int yychar;
YYSTYPE yylval;
{
tree t;
switch (yychar)
{
case IDENTIFIER:
case TYPENAME:
case OBJECTNAME:
t = yylval.ttype;
if (IDENTIFIER_POINTER (t))
fprintf (file, " `%s'", IDENTIFIER_POINTER (t));
break;
case CONSTANT:
t = yylval.ttype;
if (TREE_CODE (t) == INTEGER_CST)
fprintf (file,
#if HOST_BITS_PER_WIDE_INT == 64
#if HOST_BITS_PER_WIDE_INT != HOST_BITS_PER_INT
" 0x%lx%016lx",
#else
" 0x%x%016x",
#endif
#else
#if HOST_BITS_PER_WIDE_INT != HOST_BITS_PER_INT
" 0x%lx%08lx",
#else
" 0x%x%08x",
#endif
#endif
TREE_INT_CST_HIGH (t), TREE_INT_CST_LOW (t));
break;
}
}
/* If C is not whitespace, return C.
Otherwise skip whitespace and return first nonwhite char read. */
static int
skip_white_space (c)
register int c;
{
static int newline_warning = 0;
for (;;)
{
switch (c)
{
/* We don't recognize comments here, because
cpp output can include / and * consecutively as operators.
Also, there's no need, since cpp removes all comments. */
case '\n':
c = check_newline ();
break;
case ' ':
case '\t':
case '\f':
case '\v':
case '\b':
c = getc (finput);
break;
case '\r':
/* ANSI C says the effects of a carriage return in a source file
are undefined. */
if (pedantic && !newline_warning)
{
warning ("carriage return in source file");
warning ("(we only warn about the first carriage return)");
newline_warning = 1;
}
c = getc (finput);
break;
case '\\':
c = getc (finput);
if (c == '\n')
lineno++;
else
error ("stray '\\' in program");
c = getc (finput);
break;
default:
return (c);
}
}
}
/* Skips all of the white space at the current location in the input file.
Must use and reset nextchar if it has the next character. */
void
position_after_white_space ()
{
register int c;
if (nextchar != -1)
c = nextchar, nextchar = -1;
else
c = getc (finput);
ungetc (skip_white_space (c), finput);
}
/* Make the token buffer longer, preserving the data in it.
P should point to just beyond the last valid character in the old buffer.
The value we return is a pointer to the new buffer
at a place corresponding to P. */
static char *
extend_token_buffer (p)
char *p;
{
int offset = p - token_buffer;
maxtoken = maxtoken * 2 + 10;
token_buffer = (char *) xrealloc (token_buffer, maxtoken + 2);
return token_buffer + offset;
}
/* At the beginning of a line, increment the line number
and process any #-directive on this line.
If the line is a #-directive, read the entire line and return a newline.
Otherwise, return the line's first non-whitespace character. */
int
check_newline ()
{
register int c;
register int token;
lineno++;
/* Read first nonwhite char on the line. */
c = getc (finput);
while (c == ' ' || c == '\t')
c = getc (finput);
if (c != '#')
{
/* If not #, return it so caller will use it. */
return c;
}
/* Read first nonwhite char after the `#'. */
c = getc (finput);
while (c == ' ' || c == '\t')
c = getc (finput);
/* If a letter follows, then if the word here is `line', skip
it and ignore it; otherwise, ignore the line, with an error
if the word isn't `pragma', `ident', `define', or `undef'. */
if ((c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z'))
{
if (c == 'p')
{
if (getc (finput) == 'r'
&& getc (finput) == 'a'
&& getc (finput) == 'g'
&& getc (finput) == 'm'
&& getc (finput) == 'a'
&& ((c = getc (finput)) == ' ' || c == '\t' || c == '\n'))
{
#ifdef HANDLE_SYSV_PRAGMA
return handle_sysv_pragma (finput, c);
#else /* !HANDLE_SYSV_PRAGMA */
#ifdef HANDLE_PRAGMA
HANDLE_PRAGMA (finput);
#endif /* HANDLE_PRAGMA */
goto skipline;
#endif /* !HANDLE_SYSV_PRAGMA */
}
}
else if (c == 'd')
{
if (getc (finput) == 'e'
&& getc (finput) == 'f'
&& getc (finput) == 'i'
&& getc (finput) == 'n'
&& getc (finput) == 'e'
&& ((c = getc (finput)) == ' ' || c == '\t' || c == '\n'))
{
#ifdef DWARF_DEBUGGING_INFO
if ((debug_info_level == DINFO_LEVEL_VERBOSE)
&& (write_symbols == DWARF_DEBUG))
dwarfout_define (lineno, get_directive_line (finput));
#endif /* DWARF_DEBUGGING_INFO */
goto skipline;
}
}
else if (c == 'u')
{
if (getc (finput) == 'n'
&& getc (finput) == 'd'
&& getc (finput) == 'e'
&& getc (finput) == 'f'
&& ((c = getc (finput)) == ' ' || c == '\t' || c == '\n'))
{
#ifdef DWARF_DEBUGGING_INFO
if ((debug_info_level == DINFO_LEVEL_VERBOSE)
&& (write_symbols == DWARF_DEBUG))
dwarfout_undef (lineno, get_directive_line (finput));
#endif /* DWARF_DEBUGGING_INFO */
goto skipline;
}
}
else if (c == 'l')
{
if (getc (finput) == 'i'
&& getc (finput) == 'n'
&& getc (finput) == 'e'
&& ((c = getc (finput)) == ' ' || c == '\t'))
goto linenum;
}
else if (c == 'i')
{
if (getc (finput) == 'd'
&& getc (finput) == 'e'
&& getc (finput) == 'n'
&& getc (finput) == 't'
&& ((c = getc (finput)) == ' ' || c == '\t'))
{
/* #ident. The pedantic warning is now in cccp.c. */
/* Here we have just seen `#ident '.
A string constant should follow. */
while (c == ' ' || c == '\t')
c = getc (finput);
/* If no argument, ignore the line. */
if (c == '\n')
return c;
ungetc (c, finput);
token = yylex ();
if (token != STRING
|| TREE_CODE (yylval.ttype) != STRING_CST)
{
error ("invalid #ident");
goto skipline;
}
if (!flag_no_ident)
{
#ifdef ASM_OUTPUT_IDENT
ASM_OUTPUT_IDENT (asm_out_file, TREE_STRING_POINTER (yylval.ttype));
#endif
}
/* Skip the rest of this line. */
goto skipline;
}
}
error ("undefined or invalid # directive");
goto skipline;
}
linenum:
/* Here we have either `#line' or `# <nonletter>'.
In either case, it should be a line number; a digit should follow. */
while (c == ' ' || c == '\t')
c = getc (finput);
/* If the # is the only nonwhite char on the line,
just ignore it. Check the new newline. */
if (c == '\n')
return c;
/* Something follows the #; read a token. */
ungetc (c, finput);
token = yylex ();
if (token == CONSTANT
&& TREE_CODE (yylval.ttype) == INTEGER_CST)
{
int old_lineno = lineno;
int used_up = 0;
/* subtract one, because it is the following line that
gets the specified number */
int l = TREE_INT_CST_LOW (yylval.ttype) - 1;
/* Is this the last nonwhite stuff on the line? */
c = getc (finput);
while (c == ' ' || c == '\t')
c = getc (finput);
if (c == '\n')
{
/* No more: store the line number and check following line. */
lineno = l;
return c;
}
ungetc (c, finput);
/* More follows: it must be a string constant (filename). */
/* Read the string constant. */
token = yylex ();
if (token != STRING || TREE_CODE (yylval.ttype) != STRING_CST)
{
error ("invalid #line");
goto skipline;
}
input_filename
= (char *) permalloc (TREE_STRING_LENGTH (yylval.ttype) + 1);
strcpy (input_filename, TREE_STRING_POINTER (yylval.ttype));
lineno = l;
/* Each change of file name
reinitializes whether we are now in a system header. */
in_system_header = 0;
if (main_input_filename == 0)
main_input_filename = input_filename;
/* Is this the last nonwhite stuff on the line? */
c = getc (finput);
while (c == ' ' || c == '\t')
c = getc (finput);
if (c == '\n')
{
/* Update the name in the top element of input_file_stack. */
if (input_file_stack)
input_file_stack->name = input_filename;
return c;
}
ungetc (c, finput);
token = yylex ();
used_up = 0;
/* `1' after file name means entering new file.
`2' after file name means just left a file. */
if (token == CONSTANT
&& TREE_CODE (yylval.ttype) == INTEGER_CST)
{
if (TREE_INT_CST_LOW (yylval.ttype) == 1)
{
/* Pushing to a new file. */
struct file_stack *p
= (struct file_stack *) xmalloc (sizeof (struct file_stack));
input_file_stack->line = old_lineno;
p->next = input_file_stack;
p->name = input_filename;
input_file_stack = p;
input_file_stack_tick++;
#ifdef DWARF_DEBUGGING_INFO
if (debug_info_level == DINFO_LEVEL_VERBOSE
&& write_symbols == DWARF_DEBUG)
dwarfout_start_new_source_file (input_filename);
#endif /* DWARF_DEBUGGING_INFO */
used_up = 1;
}
else if (TREE_INT_CST_LOW (yylval.ttype) == 2)
{
/* Popping out of a file. */
if (input_file_stack->next)
{
struct file_stack *p = input_file_stack;
input_file_stack = p->next;
free (p);
input_file_stack_tick++;
#ifdef DWARF_DEBUGGING_INFO
if (debug_info_level == DINFO_LEVEL_VERBOSE
&& write_symbols == DWARF_DEBUG)
dwarfout_resume_previous_source_file (input_file_stack->line);
#endif /* DWARF_DEBUGGING_INFO */
}
else
error ("#-lines for entering and leaving files don't match");
used_up = 1;
}
}
/* Now that we've pushed or popped the input stack,
update the name in the top element. */
if (input_file_stack)
input_file_stack->name = input_filename;
/* If we have handled a `1' or a `2',
see if there is another number to read. */
if (used_up)
{
/* Is this the last nonwhite stuff on the line? */
c = getc (finput);
while (c == ' ' || c == '\t')
c = getc (finput);
if (c == '\n')
return c;
ungetc (c, finput);
token = yylex ();
used_up = 0;
}
/* `3' after file name means this is a system header file. */
if (token == CONSTANT
&& TREE_CODE (yylval.ttype) == INTEGER_CST
&& TREE_INT_CST_LOW (yylval.ttype) == 3)
in_system_header = 1, used_up = 1;
if (used_up)
{
/* Is this the last nonwhite stuff on the line? */
c = getc (finput);
while (c == ' ' || c == '\t')
c = getc (finput);
if (c == '\n')
return c;
ungetc (c, finput);
}
warning ("unrecognized text at end of #line");
}
else
error ("invalid #-line");
/* skip the rest of this line. */
skipline:
if (c == '\n')
return c;
while ((c = getc (finput)) != EOF && c != '\n');
return c;
}
#ifdef HANDLE_SYSV_PRAGMA
/* Handle a #pragma directive. INPUT is the current input stream,
and C is a character to reread. Processes the entire input line
and returns a character for the caller to reread: either \n or EOF. */
/* This function has to be in this file, in order to get at
the token types. */
int
handle_sysv_pragma (input, c)
FILE *input;
int c;
{
for (;;)
{
while (c == ' ' || c == '\t')
c = getc (input);
if (c == '\n' || c == EOF)
{
handle_pragma_token (0, 0);
return c;
}
ungetc (c, input);
switch (yylex ())
{
case IDENTIFIER:
case TYPENAME:
case STRING:
case CONSTANT:
handle_pragma_token (token_buffer, yylval.ttype);
break;
default:
handle_pragma_token (token_buffer, 0);
}
if (nextchar >= 0)
c = nextchar, nextchar = -1;
else
c = getc (input);
}
}
#endif /* HANDLE_SYSV_PRAGMA */
#define ENDFILE -1 /* token that represents end-of-file */
/* Read an escape sequence, returning its equivalent as a character,
or store 1 in *ignore_ptr if it is backslash-newline. */
static int
readescape (ignore_ptr)
int *ignore_ptr;
{
register int c = getc (finput);
register int code;
register unsigned count;
unsigned firstdig = 0;
int nonnull;
switch (c)
{
case 'x':
if (warn_traditional)
warning ("the meaning of `\\x' varies with -traditional");
if (flag_traditional)
return c;
code = 0;
count = 0;
nonnull = 0;
while (1)
{
c = getc (finput);
if (!(c >= 'a' && c <= 'f')
&& !(c >= 'A' && c <= 'F')
&& !(c >= '0' && c <= '9'))
{
ungetc (c, finput);
break;
}
code *= 16;
if (c >= 'a' && c <= 'f')
code += c - 'a' + 10;
if (c >= 'A' && c <= 'F')
code += c - 'A' + 10;
if (c >= '0' && c <= '9')
code += c - '0';
if (code != 0 || count != 0)
{
if (count == 0)
firstdig = code;
count++;
}
nonnull = 1;
}
if (! nonnull)
error ("\\x used with no following hex digits");
else if (count == 0)
/* Digits are all 0's. Ok. */
;
else if ((count - 1) * 4 >= TYPE_PRECISION (integer_type_node)
|| (count > 1
&& ((1 << (TYPE_PRECISION (integer_type_node) - (count - 1) * 4))
<= firstdig)))
pedwarn ("hex escape out of range");
return code;
case '0': case '1': case '2': case '3': case '4':
case '5': case '6': case '7':
code = 0;
count = 0;
while ((c <= '7') && (c >= '0') && (count++ < 3))
{
code = (code * 8) + (c - '0');
c = getc (finput);
}
ungetc (c, finput);
return code;
case '\\': case '\'': case '"':
return c;
case '\n':
lineno++;
*ignore_ptr = 1;
return 0;
case 'n':
return TARGET_NEWLINE;
case 't':
return TARGET_TAB;
case 'r':
return TARGET_CR;
case 'f':
return TARGET_FF;
case 'b':
return TARGET_BS;
case 'a':
if (warn_traditional)
warning ("the meaning of `\\a' varies with -traditional");
if (flag_traditional)
return c;
return TARGET_BELL;
case 'v':
#if 0 /* Vertical tab is present in common usage compilers. */
if (flag_traditional)
return c;
#endif
return TARGET_VT;
case 'e':
case 'E':
if (pedantic)
pedwarn ("non-ANSI-standard escape sequence, `\\%c'", c);
return 033;
case '?':
return c;
/* `\(', etc, are used at beginning of line to avoid confusing Emacs. */
case '(':
case '{':
case '[':
/* `\%' is used to prevent SCCS from getting confused. */
case '%':
if (pedantic)
pedwarn ("non-ANSI escape sequence `\\%c'", c);
return c;
}
if (c >= 040 && c < 0177)
pedwarn ("unknown escape sequence `\\%c'", c);
else
pedwarn ("unknown escape sequence: `\\' followed by char code 0x%x", c);
return c;
}
void
yyerror (string)
char *string;
{
char buf[200];
strcpy (buf, string);
/* We can't print string and character constants well
because the token_buffer contains the result of processing escapes. */
if (end_of_file)
strcat (buf, " at end of input");
else if (token_buffer[0] == 0)
strcat (buf, " at null character");
else if (token_buffer[0] == '"')
strcat (buf, " before string constant");
else if (token_buffer[0] == '\'')
strcat (buf, " before character constant");
else if (token_buffer[0] < 040 || (unsigned char) token_buffer[0] >= 0177)
sprintf (buf + strlen (buf), " before character 0%o",
(unsigned char) token_buffer[0]);
else
strcat (buf, " before `%s'");
error (buf, token_buffer);
}
#if 0
struct try_type
{
tree *node_var;
char unsigned_flag;
char long_flag;
char long_long_flag;
};
struct try_type type_sequence[] =
{
{ &integer_type_node, 0, 0, 0},
{ &unsigned_type_node, 1, 0, 0},
{ &long_integer_type_node, 0, 1, 0},
{ &long_unsigned_type_node, 1, 1, 0},
{ &long_long_integer_type_node, 0, 1, 1},
{ &long_long_unsigned_type_node, 1, 1, 1}
};
#endif /* 0 */
int
yylex ()
{
register int c;
register char *p;
register int value;
int wide_flag = 0;
int objc_flag = 0;
if (nextchar >= 0)
c = nextchar, nextchar = -1;
else
c = getc (finput);
/* Effectively do c = skip_white_space (c)
but do it faster in the usual cases. */
while (1)
switch (c)
{
case ' ':
case '\t':
case '\f':
case '\v':
case '\b':
c = getc (finput);
break;
case '\r':
/* Call skip_white_space so we can warn if appropriate. */
case '\n':
case '/':
case '\\':
c = skip_white_space (c);
default:
goto found_nonwhite;
}
found_nonwhite:
token_buffer[0] = c;
token_buffer[1] = 0;
/* yylloc.first_line = lineno; */
switch (c)
{
case EOF:
end_of_file = 1;
token_buffer[0] = 0;
value = ENDFILE;
break;
case '$':
if (dollars_in_ident)
goto letter;
return '$';
case 'L':
/* Capital L may start a wide-string or wide-character constant. */
{
register int c = getc (finput);
if (c == '\'')
{
wide_flag = 1;
goto char_constant;
}
if (c == '"')
{
wide_flag = 1;
goto string_constant;
}
ungetc (c, finput);
}
goto letter;
case '@':
if (!doing_objc_thang)
{
value = c;
break;
}
else
{
/* '@' may start a constant string object. */
register int c = getc(finput);
if (c == '"')
{
objc_flag = 1;
goto string_constant;
}
ungetc(c, finput);
/* Fall through to treat '@' as the start of an identifier. */
}