File: scanners.c

package info (click to toggle)
id-utils 3.2d-2.1
  • links: PTS
  • area: main
  • in suites: potato
  • size: 1,808 kB
  • ctags: 1,677
  • sloc: ansic: 14,285; sh: 403; makefile: 262; perl: 255; sed: 93; lisp: 26
file content (1196 lines) | stat: -rw-r--r-- 30,146 bytes parent folder | download | duplicates (3)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
/* scanners.c -- file & directory name manipulations
   Copyright (C) 1986, 1995, 1996, 1999 Free Software Foundation, Inc.
   Written by Greg McGary <gkm@gnu.ai.mit.edu>

   This program 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.

   This program 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 this program; if not, write to the Free Software
   Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */

#include <config.h>
#include <stdio.h>
#include <ctype.h>
#if HAVE_FCNTL_H
# include <fcntl.h>
#endif
#include <getopt.h>
#include "xstdlib.h"
#include "xstddef.h"
#include "xunistd.h"
#include "xsysstat.h"
#include "xstring.h"
#include "xmalloc.h"
#include "xnls.h"
#include "error.h"
#include "scanners.h"
#include "tokflags.h"

#define DEBUG(args) /* printf args */

struct obstack lang_args_obstack;
struct lang_args *lang_args_default = 0;
struct lang_args *lang_args_list = 0;
struct obstack tokens_obstack;
int log_8_member_files = 0;

extern void usage __P((void));
extern char *program_name;

/****************************************************************************/

struct lang_args **parse_language_map_file __P((char const *file_name, struct lang_args **next_ptr));
char *read_language_map_file __P((char const *file_name));
void tokenize_args_string __P((char *args_string, int *argcp, char ***argvp));

static struct token *get_token_c __P((FILE *in_FILE, void const *args, int *flags));
static void *parse_args_c __P((char **argv, int argc));
static void help_me_c __P((void));

static struct token *get_token_asm __P((FILE *in_FILE, void const *args, int *flags));
static void *parse_args_asm __P((char **argv, int argc));
static void help_me_asm __P((void));

static struct token *get_token_text __P((FILE *in_FILE, void const *args, int *flags));
static void *parse_args_text __P((char **argv, int argc));
static void help_me_text __P((void));

struct language languages_0[] =
{
  { "C", parse_args_c, get_token_c, help_me_c },
  { "C++", parse_args_c, get_token_c, help_me_c },
  { "asm", parse_args_asm, get_token_asm, help_me_asm },
  { "text", parse_args_text, get_token_text, help_me_text },
};
struct language const *languages_N = &languages_0[cardinalityof (languages_0)];

void
language_help_me (void)
{
  struct language *lang;
  for (lang = languages_0; lang < languages_N; lang++)
    {
      putchar ('\n');
      (*lang->lg_help_me) ();
    }
}

void
language_save_arg (char *arg)
{
  static char horizontal_space[] = " \t";
  char *lang_name = strtok (arg, ":");
  struct language *lang = get_language (lang_name);

  if (lang == 0)
    {
      error (0, 0, _("unrecognized language: `%s'"), lang_name);
      usage ();
    }
  if (lang->lg_argc == 0)
    lang->lg_argv[lang->lg_argc++] = program_name;
  lang->lg_argv[lang->lg_argc++] = strtok (0, horizontal_space);
}

void
language_getopt (void)
{
  struct language *lang;

  for (lang = languages_0; lang < languages_N; lang++)
    if (lang->lg_argc)
      lang->lg_parse_args (lang->lg_argv, lang->lg_argc);
}

struct language *
get_language (char const *lang_name)
{
  struct language *lang;

  for (lang = languages_0; lang < languages_N; lang++)
    if (strequ (lang_name, lang->lg_name))
      {
	DEBUG (("lang=%s", lang_name));
	return lang;
      }
  DEBUG (("!lang=%s", lang_name));
  return 0;
}

/****************************************************************************/

int lang_args_index = 0;

void
set_default_language (char const *lang_name)
{
}

void
parse_language_map (char const *file_name)
{
  if (obstack_init (&lang_args_obstack) == 0)
    error (1, 0, _("can't allocate language args obstack: memory exhausted"));
  if (file_name == 0)
    file_name = LANGUAGE_MAP_FILE;
  parse_language_map_file (file_name, &lang_args_list);
}

struct lang_args **
parse_language_map_file (char const *file_name, struct lang_args **next_ptr)
{
  static char white_space[] = " \t\r\n\v\f";
  static char horizontal_space[] = " \t";
  static char vertical_space[] = "\r\n\v\f";
  char *lang_map_buffer;
  char *lmp;

  lmp = lang_map_buffer = read_language_map_file (file_name);
  for (;;)
    {
      struct lang_args *new_args;
      struct language const *lang;
      int pattern_size;
      char *lang_name;
      int space;

      /* Skip leading white space and full-line comments */
      while (*lmp)
	{
	  lmp += strspn (lmp, white_space);
	  if (*lmp != '#')
	    break;
	  lmp += strcspn (lmp, vertical_space);
	}
      if (*lmp == '\0')
	break;

      pattern_size = strcspn (lmp, white_space);
      if (pattern_size == 3 && strnequ (lmp, "***", 3))
	{
	  lmp += pattern_size;
	  lmp += strspn (lmp, horizontal_space);
	  if (isspace (*lmp))
	    next_ptr = parse_language_map_file (LANGUAGE_MAP_FILE, next_ptr);
	  else
	    {
	      char *end = lmp + strcspn (lmp, white_space);
	      *end = '\0';
	      next_ptr = parse_language_map_file (lmp, next_ptr);
	      lmp = end + 1;
	    }
	  continue;
	}

      new_args = OBSTACK_ALLOC (&lang_args_obstack, struct lang_args, 1);
      if (new_args == 0)
	error (1, 0, _("can't allocate language args: memory exhausted"));
      new_args->la_pattern = obstack_copy0 (&lang_args_obstack, lmp, pattern_size);
      new_args->la_args_string = 0;
      new_args->la_next = 0;
      lmp += pattern_size;
      lmp += strspn (lmp, horizontal_space);
      if (isspace (*lmp))
	{
	  error (0, 0, _("language name expected following `%s' in file `%s'"),
		 new_args->la_pattern, file_name);
	  obstack_free (&lang_args_obstack, new_args);
	  continue;
	}
      lang_name = lmp;
      lmp += strcspn (lmp, white_space);
      space = *lmp;
      *lmp++ = '\0';
      lmp += strspn (lmp, horizontal_space);
      lang = new_args->la_language = get_language (lang_name);

      if (*lmp == '#')
	lmp += strcspn (lmp, vertical_space);
      else if (!isspace (*lmp) && (space == ' ' || space == '\t'))
	{
	  int args_size = strcspn (lmp, vertical_space);
	  new_args->la_args_string = obstack_copy0 (&lang_args_obstack, lmp, args_size);
	  lmp += args_size;
	}
      new_args->la_args_digested = (lang
				    ? lang->lg_parse_args (&new_args->la_args_string, 0)
				    : 0);
      if (pattern_size == 2 && strnequ (new_args->la_pattern, "**", 2))
	{
	  if (lang_args_default)
	    {
	      obstack_free (&lang_args_obstack, new_args);
	      continue;
	    }
	  lang_args_default = new_args;
	  DEBUG ((", <default>"));
	}
      else
	{
	  new_args->la_index = lang_args_index++;
	  *next_ptr = new_args;
	  next_ptr = &new_args->la_next;
	}
      DEBUG ((", pat=%s\n", new_args->la_pattern));
    }
  free (lang_map_buffer);
  return next_ptr;
}

char *
read_language_map_file (char const *file_name)
{
  int map_fd;
  char *lang_map_buffer;
  struct stat st;
  int bytes;

  map_fd = open (file_name, O_RDONLY);
  if (map_fd < 0)
    error (1, errno, _("can't open language map file `%s'"), file_name);
  if (fstat (map_fd, &st) < 0)
    error (1, errno, _("can't get size of map file `%s'"), file_name);

  lang_map_buffer = MALLOC (char, st.st_size + 2);
  if (lang_map_buffer == 0)
    error (1, 0, _("can't allocate language args: memory exhausted"));
  lang_map_buffer[st.st_size] = '\n';
  lang_map_buffer[st.st_size+1] = '\0';

  bytes = read (map_fd, lang_map_buffer, st.st_size);
  if (bytes < 0)
    error (1, errno, _("can't read language map file `%s'"), file_name);
  /* FIXME: handle interrupted & partial reads */
  if (bytes != st.st_size)
    error (1, errno, _("can't read entire language map file `%s'"), file_name);

  close (map_fd);
  return lang_map_buffer;
}

/****************************************************************************/

void
tokenize_args_string (char *args_string, int *argcp, char ***argvp)
{
  static char horizontal_space[] = " \t";
  char **argv_0 = MALLOC (char *, strlen (args_string) / 2);
  char **argv = argv_0;
  char *arg;

  *argv++ = program_name;
  arg = strtok (args_string, horizontal_space);
  while (arg)
    {
      *argv++ = arg;
      arg = strtok (0, horizontal_space);
    }
  *argcp = argv - argv_0;
  *argvp = REALLOC (argv_0, char *, *argcp);
}

static void
set_ushort_ctype (unsigned short *ctype, char const *chars, int type)
{
  unsigned short *rct = &ctype[1];
  unsigned char const *uc = (unsigned char const *) chars;

  while (*uc)
    rct[*uc++] |= type;
}

static void
clear_ushort_ctype (unsigned short *ctype, char const *chars, int type)
{
  unsigned short *rct = &ctype[1];
  unsigned char const *uc = (unsigned char const *) chars;

  while (*uc)
    rct[*uc++] &= ~type;
}

static void
set_uchar_ctype (unsigned char *ctype, char const *chars, int type)
{
  unsigned char *rct = &ctype[1];
  unsigned char const *uc = (unsigned char const *) chars;

  while (*uc)
    rct[*uc++] |= type;
}

static void
clear_uchar_ctype (unsigned char *ctype, char const *chars, int type)
{
  unsigned char *rct = &ctype[1];
  unsigned char const *uc = (unsigned char const *) chars;

  while (*uc)
    rct[*uc++] &= ~type;
}

/*************** C & C++ ****************************************************/

#define I1	0x0001		/* 1st char of an identifier [a-zA-Z_] */
#define DG	0x0002		/* decimal digit [0-9] */
#define NM	0x0004		/* extra chars in a hex or long number [a-fA-FxXlL] */
#define C1	0x0008		/* C comment introduction char: / */
#define C2	0x0010		/* C comment termination  char: * */
#define Q1	0x0020		/* single quote: ' */
#define Q2	0x0040		/* double quote: " */
#define ES	0x0080		/* escape char: \ */
#define NL	0x0100		/* newline: \n */
#define EF	0x0200		/* EOF */
#define SK	0x0400		/* Make these chars valid for names within strings */
#define VH	0x0800		/* VHIL comment introduction char: # */
#define WS	0x1000		/* White space characters */

/* character class membership macros: */

#define ISDIGIT(c)	((rct)[c] & (DG))	/* digit */
#define ISNUMBER(c)	((rct)[c] & (DG|NM))	/* legal in a number */
#define ISEOF(c)	((rct)[c] & (EF))	/* EOF */
#define ISID1ST(c)	((rct)[c] & (I1))	/* 1st char of an identifier */
#define ISIDREST(c)	((rct)[c] & (I1|DG))	/* rest of an identifier */
#define ISSTRKEEP(c)	((rct)[c] & (I1|DG|SK))	/* keep contents of string */
#define ISSPACE(c)	((rct)[c] & (WS))	/* white space character */

/* The `BORING' classes should be skipped over until something
   interesting comes along... */

#define ISBORING(c)	(!((rct)[c] & (EF|NL|I1|DG|Q1|Q2|C1|VH)))	/* fluff */
#define ISCBORING(c)	(!((rct)[c] & (EF|C2)))	/* comment fluff */
#define ISCCBORING(c)	(!((rct)[c] & (EF|NL)))	/* C++ // comment fluff */
#define ISQ1BORING(c)	(!((rct)[c] & (EF|NL|Q1|ES)))	/* char const fluff */
#define ISQ2BORING(c)	(!((rct)[c] & (EF|NL|Q2|ES)))	/* quoted str fluff */

static unsigned short ctype_c[257] =
{
  EF,
/*      0       1       2       3       4       5       6       7   */
/*    -----   -----   -----   -----   -----   -----   -----   ----- */
/*000*/ 0,	0,	0,	0,	0,	0,	0,	0,
/*010*/ 0,	0,	NL,	0,	0,	0,	0,	0,
/*020*/ 0,	0,	0,	0,	0,	0,	0,	0,
/*030*/ 0,	0,	0,	0,	0,	0,	0,	0,
/*040*/ 0,	0,	Q2,	0,	0,	0,	0,	Q1,
/*050*/ 0,	0,	C2,	0,	0,	0,	0,	C1,
/*060*/ DG,	DG,	DG,	DG,	DG,	DG,	DG,	DG,
/*070*/ DG,	DG,	0,	0,	0,	0,	0,	0,
/*100*/ 0,	I1|NM,	I1|NM,	I1|NM,	I1|NM,	I1|NM,	I1|NM,	I1,
/*110*/ I1,	I1,	I1,	I1,	I1|NM,	I1,	I1,	I1,
/*120*/ I1,	I1,	I1,	I1,	I1,	I1,	I1,	I1,
/*130*/ I1|NM,	I1,	I1,	0,	ES,	0,	0,	I1,
/*140*/ 0,	I1|NM,	I1|NM,	I1|NM,	I1|NM,	I1|NM,	I1|NM,	I1,
/*150*/ I1,	I1,	I1,	I1,	I1|NM,	I1,	I1,	I1,
/*160*/ I1,	I1,	I1,	I1,	I1,	I1,	I1,	I1,
/*170*/ I1|NM,	I1,	I1,	0,	0,	0,	0,	0,
  /* FIXME: latin-1 */
};

struct args_c
{
  int strip_underscore;
  unsigned short *ctype;
};

static struct args_c args_c = { 0, ctype_c };

static struct option const long_options_c[] =
{
  { "keep", required_argument, 0, 'k' },
  { "ignore", required_argument, 0, 'i' },
  { "strip-underscore", no_argument, 0, 'u' },
  { 0 }
};

static void
help_me_c (void)
{
  printf (_("\
C language:\n\
  -k,--keep=CHARS        Allow CHARS in single-token strings, keep the result\n\
  -i,--ignore=CHARS      Allow CHARS in single-token strings, toss the result\n\
  -u,--strip-underscore  Strip a leading underscore from single-token strings\n\
"));
}

static void *
parse_args_c (char **argv, int argc)
{
  char *tmp_string = 0;
  struct args_c *args;

  if (argv == 0 || *argv == 0)
    return &args_c;

  if (argc)
    args = &args_c;
  else
    {
      tmp_string = strdup (*argv);
      tokenize_args_string (tmp_string, &argc, &argv);
      args = MALLOC (struct args_c, 1);
      args->strip_underscore = 0;
      args->ctype = ctype_c;
    }

  optind = 0;
  for (;;)
    {
      int optc = getopt_long (argc, argv, "k:i:u",
			      long_options_c, (int *) 0);
      if (optc < 0)
	break;
      if ((optc == 'k' || optc == 'i') && args->ctype == ctype_c)
	args->ctype = CLONE (ctype_c, unsigned short, cardinalityof (ctype_c));
      switch (optc)
	{
	case 'k':
	  set_ushort_ctype (args->ctype, optarg, SK);
	  break;

	case 'i':
	  clear_ushort_ctype (args->ctype, optarg, SK);
	  break;

	case 'u':
	  args->strip_underscore = 1;
	  break;

	default:
	  usage ();
	}
    }
  if (tmp_string)
    {
      free (argv);
      free (tmp_string);
    }
  return args;
}

unsigned char *scanner_buffer;

#define SCAN_CPP_DIRECTIVE						\
  do									\
    {									\
      c = getc (in_FILE);						\
      while (ISBORING (c))						\
	c = getc (in_FILE);						\
      if (!ISID1ST (c))							\
	goto next;							\
      id = scanner_buffer;						\
      *id++ = c;							\
      while (ISIDREST (c = getc (in_FILE)))				\
	*id++ = c;							\
      *id = '\0';							\
      if (strequ (scanner_buffer, "include"))				\
	{								\
	  while (c == ' ' || c == '\t')					\
	    c = getc (in_FILE);						\
	  if (c == '\n')						\
	    {								\
	      new_line = 1;						\
	      goto top;							\
	    }								\
	  id = scanner_buffer;						\
	  if (c == '"')							\
	    {								\
	      c = getc (in_FILE);					\
	      while (c != '\n' && c != EOF && c != '"')			\
		{							\
		  *id++ = c;						\
		  c = getc (in_FILE);					\
		}							\
	      *flags = TOK_STRING;					\
	    }								\
	  else if (c == '<')						\
	    {								\
	      c = getc (in_FILE);					\
	      while (c != '\n' && c != EOF && c != '>')			\
		{							\
		  *id++ = c;						\
		  c = getc (in_FILE);					\
		}							\
	      *flags = TOK_STRING;					\
	    }								\
	  else if (ISID1ST (c))						\
	    {								\
	      *id++ = c;						\
	      while (ISIDREST (c = getc (in_FILE)))			\
		*id++ = c;						\
	      *flags = TOK_NAME;					\
	    }								\
	  else								\
	    {								\
	      while (c != '\n' && c != EOF)				\
		c = getc (in_FILE);					\
	      new_line = 1;						\
	      goto top;							\
	    }								\
	  while (c != '\n' && c != EOF)					\
	    c = getc (in_FILE);						\
	  new_line = 1;							\
	  obstack_grow0 (&tokens_obstack, scanner_buffer,		\
			 id - scanner_buffer);				\
	  return (struct token *) obstack_finish (&tokens_obstack);	\
	}								\
      if (strnequ (scanner_buffer, "if", 2)				\
	  || strequ (scanner_buffer, "define")				\
	  || strequ (scanner_buffer, "elif")	/* ansi C */		\
	  || strequ (scanner_buffer, "undef"))				\
	goto next;							\
      while ((c != '\n') && (c != EOF))					\
	c = getc (in_FILE);						\
      new_line = 1;							\
      goto top;								\
  } while (0)


/* Grab the next identifier from the C source file.  This state
   machine is built for speed, not elegance.  */

static struct token *
get_token_c (FILE *in_FILE, void const *args, int *flags)
{
#define ARGS ((struct args_c const *) args)
  static int new_line = 1;
  unsigned short const *rct = &ARGS->ctype[1];
  unsigned char *id = scanner_buffer;
  int c;

  obstack_blank (&tokens_obstack, OFFSETOF_TOKEN_NAME);

top:
  c = getc (in_FILE);
  if (new_line)
    {
      new_line = 0;
      if (c != '#')
	goto next;
      SCAN_CPP_DIRECTIVE;
    }

next:
  while (ISBORING (c))
    c = getc (in_FILE);

  switch (c)
    {
    case '"':
      id = scanner_buffer;
      *id++ = c = getc (in_FILE);
      for (;;)
	{
	  while (ISQ2BORING (c))
	    *id++ = c = getc (in_FILE);
	  if (c == '\\')
	    {
	      *id++ = c = getc (in_FILE);
	      continue;
	    }
	  else if (c != '"')
	    goto next;
	  break;
	}
      *--id = '\0';
      id = scanner_buffer;
      while (ISSTRKEEP (*id))
	id++;
      if (*id || id == scanner_buffer)
	{
	  c = getc (in_FILE);
	  goto next;
	}
      *flags = TOK_STRING;
      if (ARGS->strip_underscore && scanner_buffer[0] == '_' && scanner_buffer[1])
	obstack_grow0 (&tokens_obstack, scanner_buffer + 1, id - scanner_buffer - 1);
      else
	obstack_grow0 (&tokens_obstack, scanner_buffer, id - scanner_buffer);
      return (struct token *) obstack_finish (&tokens_obstack);

    case '\'':
      c = getc (in_FILE);
      for (;;)
	{
	  while (ISQ1BORING (c))
	    c = getc (in_FILE);
	  if (c == '\\')
	    {
	      c = getc (in_FILE);
	      continue;
	    }
	  else if (c == '\'')
	    c = getc (in_FILE);
	  goto next;
	}

    case '/':
      c = getc (in_FILE);
      if (c == '/')
	{			/* Cope with C++ comment */
	  while (ISCCBORING (c))
	    c = getc (in_FILE);
	  new_line = 1;
	  goto top;
	}
      else if (c != '*')
	goto next;
      c = getc (in_FILE);
      for (;;)
	{
	  while (ISCBORING (c))
	    c = getc (in_FILE);
	  c = getc (in_FILE);
	  if (c == '/')
	    {
	      c = getc (in_FILE);
	      goto next;
	    }
	  else if (ISEOF (c))
	    {
	      new_line = 1;
	      obstack_free (&tokens_obstack, obstack_finish (&tokens_obstack));
	      return 0;
	    }
	}

    case '\n':
      new_line = 1;
      goto top;

    default:
      if (ISEOF (c))
	{
	  new_line = 1;
	  obstack_free (&tokens_obstack, obstack_finish (&tokens_obstack));
	  return 0;
	}
      id = scanner_buffer;
      *id++ = c;
      if (ISID1ST (c))
	{
	  *flags = TOK_NAME;
	  while (ISIDREST (c = getc (in_FILE)))
	    *id++ = c;
	}
      else if (ISDIGIT (c))
	{
	  *flags = TOK_NUMBER;
	  while (ISNUMBER (c = getc (in_FILE)))
	    *id++ = c;
	}
      else
	{
	  if (isprint (c))
	    fprintf (stderr, _("junk: `%c'"), c);
	  else
	    fprintf (stderr, _("junk: `\\%03o'"), c);
	}
      ungetc (c, in_FILE);
      *flags |= TOK_LITERAL;
      obstack_grow0 (&tokens_obstack, scanner_buffer, id - scanner_buffer);
      return (struct token *) obstack_finish (&tokens_obstack);
    }
#undef ARGS
}

#undef I1
#undef DG
#undef NM
#undef C1
#undef C2
#undef Q1
#undef Q2
#undef ES
#undef NL
#undef EF
#undef SK
#undef VH
#undef WS
#undef ISDIGIT
#undef ISNUMBER
#undef ISEOF
#undef ISID1ST
#undef ISIDREST
#undef ISSTRKEEP
#undef ISSPACE
#undef ISBORING
#undef ISCBORING
#undef ISCCBORING
#undef ISQ1BORING
#undef ISQ2BORING

/*************** Assembly ***************************************************/

#define I1	0x01		/* 1st char of an identifier [a-zA-Z_] */
#define NM	0x02		/* digit [0-9a-fA-FxX] */
#define NL	0x04		/* newline: \n */
#define CM	0x08		/* assembler comment char: usually # or | */
#define IG	0x10		/* ignore `identifiers' with these chars in them */
#define C1	0x20		/* C comment introduction char: / */
#define C2	0x40		/* C comment termination  char: * */
#define EF	0x80		/* EOF */

/* Assembly Language character classes */
#define ISID1ST(c)	((rct)[c] & (I1))
#define ISIDREST(c)	((rct)[c] & (I1|NM))
#define ISNUMBER(c)	((rct)[c] & (NM))
#define ISEOF(c)	((rct)[c] & (EF))
#define ISCOMMENT(c)	((rct)[c] & (CM))
#define ISBORING(c)	(!((rct)[c] & (EF|NL|I1|NM|CM|C1)))
#define ISCBORING(c)	(!((rct)[c] & (EF|NL)))
#define ISCCBORING(c)	(!((rct)[c] & (EF|C2)))
#define ISIGNORE(c)	((rct)[c] & (IG))

static unsigned char ctype_asm[257] =
{
  EF,
/*      0       1       2       3       4       5       6       7   */
/*    -----   -----   -----   -----   -----   -----   -----   ----- */
/*000*/ 0,	0,	0,	0,	0,	0,	0,	0,
/*010*/ 0,	0,	NL,	0,	0,	0,	0,	0,
/*020*/ 0,	0,	0,	0,	0,	0,	0,	0,
/*030*/ 0,	0,	0,	0,	0,	0,	0,	0,
/*040*/ 0,	0,	0,	0,	0,	0,	0,	0,
/*050*/ 0,	0,	C2,	0,	0,	0,	0,	C1,
/*060*/ NM,	NM,	NM,	NM,	NM,	NM,	NM,	NM,
/*070*/ NM,	NM,	0,	0,	0,	0,	0,	0,
/*100*/ 0,	I1|NM,	I1|NM,	I1|NM,	I1|NM,	I1|NM,	I1|NM,	I1,
/*110*/ I1,	I1,	I1,	I1,	I1|NM,	I1,	I1,	I1,
/*120*/ I1,	I1,	I1,	I1,	I1,	I1,	I1,	I1,
/*130*/ I1|NM,	I1,	I1,	0,	0,	0,	0,	I1,
/*140*/ 0,	I1|NM,	I1|NM,	I1|NM,	I1|NM,	I1|NM,	I1|NM,	I1,
/*150*/ I1,	I1,	I1,	I1,	I1|NM,	I1,	I1,	I1,
/*160*/ I1,	I1,	I1,	I1,	I1,	I1,	I1,	I1,
/*170*/ I1|NM,	I1,	I1,	0,	0,	0,	0,	0,

};

struct args_asm
{
  int handle_cpp;
  int strip_underscore;
  unsigned char *ctype;
};

static struct args_asm args_asm = { 1, 0, ctype_asm };

static struct option const long_options_asm[] =
{
  { "comment", required_argument, 0, 'c' },
  { "keep", required_argument, 0, 'k' },
  { "ignore", required_argument, 0, 'i' },
  { "strip-underscore", no_argument, 0, 'u' },
  { "no-cpp", no_argument, 0, 'p' },
  { 0 }
};

static void
help_me_asm (void)
{
  printf (_("\
Assembly language:\n\
  -c,--comment=CHARS     Any of CHARS starts a comment until end-of-line\n\
  -k,--keep=CHARS        Allow CHARS in tokens, and keep the result\n\
  -i,--ignore=CHARS      Allow CHARS in tokens, and toss the result\n\
  -u,--strip-underscore  Strip a leading underscore from tokens\n\
  -n,--no-cpp            Don't handle C pre-processor directives\n\
"));
}

static void *
parse_args_asm (char **argv, int argc)
{
  char *tmp_string = 0;
  struct args_asm *args;

  if (argv == 0 || *argv == 0)
    return &args_asm;

  if (argc)
    args = &args_asm;
  else
    {
      tmp_string = strdup (*argv);
      tokenize_args_string (tmp_string, &argc, &argv);
      args = MALLOC (struct args_asm, 1);
      args->strip_underscore = 0;
      args->ctype = ctype_asm;
      args->handle_cpp = 1;
    }

  optind = 0;
  for (;;)
    {
      int optc = getopt_long (argc, argv, "c:k:i:un",
			      long_options_asm, (int *) 0);
      if (optc < 0)
	break;
      if ((optc == 'k' || optc == 'i' || optc == 'c')
	  && args->ctype == ctype_asm)
	args->ctype = CLONE (ctype_asm, unsigned char, cardinalityof (ctype_asm));
      switch (optc)
	{
	case 'c':
	  set_uchar_ctype (args->ctype, optarg, CM);
	  break;

	case 'k':
	  set_uchar_ctype (args->ctype, optarg, I1);
	  break;

	case 'i':
	  set_uchar_ctype (args->ctype, optarg, I1 | IG);
	  break;

	case 'u':
	  args->strip_underscore = 1;
	  break;

	case 'n':
	  args->handle_cpp = 0;
	  break;

	default:
	  usage ();
	}
    }
  if (tmp_string)
    {
      free (argv);
      free (tmp_string);
    }
  return args;
}

/* Grab the next identifier the assembly language source file. This
   state machine is built for speed, not elegance.  */

static struct token *
get_token_asm (FILE *in_FILE, void const *args, int *flags)
{
#define ARGS ((struct args_asm const *) args)
  static int new_line = 1;
  unsigned char const *rct = &ARGS->ctype[1];
  unsigned char *id = scanner_buffer;
  int c;

  obstack_blank (&tokens_obstack, OFFSETOF_TOKEN_NAME);

top:
  c = getc (in_FILE);
  if (ARGS->handle_cpp > 0 && new_line)
    {
      new_line = 0;
      if (c != '#')
	goto next;
      SCAN_CPP_DIRECTIVE;
    }

next:
  while (ISBORING (c))
    c = getc (in_FILE);

  if (ISCOMMENT (c))
    {
      while (ISCBORING (c))
	c = getc (in_FILE);
      new_line = 1;
    }

  if (ISEOF (c))
    {
      new_line = 1;
      obstack_free (&tokens_obstack, obstack_finish (&tokens_obstack));
      return 0;
    }

  if (c == '\n')
    {
      new_line = 1;
      goto top;
    }

  if (c == '/')
    {
      if ((c = getc (in_FILE)) != '*')
	goto next;
      c = getc (in_FILE);
      for (;;)
	{
	  while (ISCCBORING (c))
	    c = getc (in_FILE);
	  c = getc (in_FILE);
	  if (c == '/')
	    {
	      c = getc (in_FILE);
	      break;
	    }
	  else if (ISEOF (c))
	    {
	      new_line = 1;
	      obstack_free (&tokens_obstack, obstack_finish (&tokens_obstack));
	      return 0;
	    }
	}
      goto next;
    }

  id = scanner_buffer;
  if (ARGS->strip_underscore && c == '_' && !ISID1ST (c = getc (in_FILE)))
    {
      obstack_grow0 (&tokens_obstack, "_", 1);
      return (struct token *) obstack_finish (&tokens_obstack);
    }
  *id++ = c;
  if (ISID1ST (c))
    {
      *flags = TOK_NAME;
      while (ISIDREST (c = getc (in_FILE)))
	*id++ = c;
    }
  else if (ISNUMBER (c))
    {
      *flags = TOK_NUMBER;
      while (ISNUMBER (c = getc (in_FILE)))
	*id++ = c;
    }
  else
    {
      if (isprint (c))
	fprintf (stderr, _("junk: `%c'"), c);
      else
	fprintf (stderr, _("junk: `\\%03o'"), c);
      goto next;
    }

  *id = '\0';
  for (id = scanner_buffer; *id; id++)
    if (ISIGNORE (*id))
      goto next;
  ungetc (c, in_FILE);
  *flags |= TOK_LITERAL;
  obstack_grow0 (&tokens_obstack, scanner_buffer, id - scanner_buffer);
  return (struct token *) obstack_finish (&tokens_obstack);
#undef ARGS
}

#undef I1
#undef NM
#undef NL
#undef CM
#undef IG
#undef C1
#undef C2
#undef EF
#undef ISID1ST
#undef ISIDREST
#undef ISNUMBER
#undef ISEOF
#undef ISCOMMENT
#undef ISBORING
#undef ISCBORING
#undef ISCCBORING
#undef ISIGNORE

/*************** Text *******************************************************/

#define I1	0x01		/* 1st char of an identifier [a-zA-Z_] */
#define NM	0x02		/* digit [0-9a-fA-FxX] */
#define SQ	0x04		/* squeeze these out (.,',-) */
#define EF	0x80		/* EOF */

/* Text character classes */
#define ISID1ST(c)	((rct)[c] & (I1))
#define ISIDREST(c)	((rct)[c] & (I1|NM|SQ))
#define ISNUMBER(c)	((rct)[c] & (NM))
#define ISEOF(c)	((rct)[c] & (EF))
#define ISBORING(c)	(!((rct)[c] & (I1|NM|EF)))
#define ISIDSQUEEZE(c)	((rct)[c] & (SQ))

static unsigned char ctype_text[257] =
{
  EF,
/*      0       1       2       3       4       5       6       7   */
/*    -----   -----   -----   -----   -----   -----   -----   ----- */
/*000*/ 0,	0,	0,	0,	0,	0,	0,	0,
/*010*/ 0,	0,	0,	0,	0,	0,	0,	0,
/*020*/ 0,	0,	0,	0,	0,	0,	0,	0,
/*030*/ 0,	0,	0,	0,	0,	0,	0,	0,
/*040*/ 0,	0,	0,	0,	0,	0,	0,	0,
/*050*/ 0,	0,	0,	0,	0,	0,	0,	0,
/*060*/ NM,	NM,	NM,	NM,	NM,	NM,	NM,	NM,
/*070*/ NM,	NM,	0,	0,	0,	0,	0,	0,
/*100*/ 0,	I1|NM,	I1|NM,	I1|NM,	I1|NM,	I1|NM,	I1|NM,	I1,
/*110*/ I1,	I1,	I1,	I1,	I1|NM,	I1,	I1,	I1,
/*120*/ I1,	I1,	I1,	I1,	I1,	I1,	I1,	I1,
/*130*/ I1|NM,	I1,	I1,	0,	0,	0,	0,	I1,
/*140*/ 0,	I1|NM,	I1|NM,	I1|NM,	I1|NM,	I1|NM,	I1|NM,	I1,
/*150*/ I1,	I1,	I1,	I1,	I1|NM,	I1,	I1,	I1,
/*160*/ I1,	I1,	I1,	I1,	I1,	I1,	I1,	I1,
/*170*/ I1|NM,	I1,	I1,	0,	0,	0,	0,	0,
/*200*/ 0,	0,	0,	0,	0,	0,	0,	0,
/*210*/ 0,	0,	0,	0,	0,	0,	0,	0,
/*220*/ 0,	0,	0,	0,	0,	0,	0,	0,
/*230*/ 0,	0,	0,	0,	0,	0,	0,	0,
/*240*/ 0,	0,	0,	0,	0,	0,	0,	0,
/*250*/ 0,	0,	0,	0,	0,	0,	0,	0,
/*260*/ 0,	0,	0,	0,	0,	0,	0,	0,
/*270*/ 0,	0,	0,	0,	0,	0,	0,	0,
/*300*/ I1,	I1,	I1,	I1,	I1,	I1,	I1,	I1,
/*310*/ I1,	I1,	I1,	I1,	I1,	I1,	I1,	I1,
/*320*/ I1,	I1,	I1,	I1,	I1,	I1,	I1,	0,
/*330*/ I1,	I1,	I1,	I1,	I1,	I1,	I1,	I1,
/*340*/ I1,	I1,	I1,	I1,	I1,	I1,	I1,	I1,
/*350*/ I1,	I1,	I1,	I1,	I1,	I1,	I1,	I1,
/*360*/ I1,	I1,	I1,	I1,	I1,	I1,	I1,	0,
/*370*/ I1,	I1,	I1,	I1,	I1,	I1,	I1,	I1,
};

struct args_text
{
  unsigned char *ctype;
};

static struct args_text args_text = { ctype_text };

static struct option const long_options_text[] =
{
  { "include", required_argument, 0, 'i' },
  { "exclude", required_argument, 0, 'x' },
  { 0 }
};

static void
help_me_text (void)
{
  printf (_("\
Text language:\n\
  -i,--include=CHAR-CLASS  Treat characters of CHAR-CLASS as token constituents\n\
  -x,--exclude=CHAR-CLASS  Treat characters of CHAR-CLASS as token delimiters\n\
"));
}

static void *
parse_args_text (char **argv, int argc)
{
  char *tmp_string = 0;
  struct args_text *args;

  if (argv == 0 || *argv == 0)
    return &args_text;

  if (argc)
    args = &args_text;
  else
    {
      tmp_string = strdup (*argv);
      tokenize_args_string (tmp_string, &argc, &argv);
      args = MALLOC (struct args_text, 1);
      args->ctype = ctype_text;
    }

  optind = 0;
  for (;;)
    {
      int optc = getopt_long (argc, argv, "i:x:",
			      long_options_text, (int *) 0);
      if (optc < 0)
	break;
      if ((optc == 'k' || optc == 'i') && args->ctype == ctype_text)
	args->ctype = CLONE (ctype_text, unsigned char, cardinalityof (ctype_text));
      switch (optc)
	{
	case 'i':
	  set_uchar_ctype (args->ctype, optarg, I1);
	  break;

	case 'x':
	  clear_uchar_ctype (args->ctype, optarg, I1);
	  break;

	default:
	  usage ();
	}
    }
  if (tmp_string)
    {
      free (argv);
      free (tmp_string);
    }
  return args;
}

/* Grab the next identifier the text source file.  This state machine
   is built for speed, not elegance.  */

static struct token *
get_token_text (FILE *in_FILE, void const *args, int *flags)
{
#define ARGS ((struct args_text const *) args)
  unsigned char const *rct = &ARGS->ctype[1];
  int c;
  unsigned char *id = scanner_buffer;

  obstack_blank (&tokens_obstack, OFFSETOF_TOKEN_NAME);

top:
  c = getc (in_FILE);
  while (ISBORING (c))
    c = getc (in_FILE);
  if (ISEOF (c))
    {
      obstack_free (&tokens_obstack, obstack_finish (&tokens_obstack));
      return 0;
    }
  id = scanner_buffer;
  *id++ = c;
  if (ISID1ST (c))
    {
      *flags = TOK_NAME;
      while (ISIDREST (c = getc (in_FILE)))
	if (!ISIDSQUEEZE (c))
	  *id++ = c;
    }
  else if (ISNUMBER (c))
    {
      *flags = TOK_NUMBER;
      while (ISNUMBER (c = getc (in_FILE)))
	*id++ = c;
    }
  else
    {
      if (isprint (c))
	fprintf (stderr, _("junk: `%c'"), c);
      else
	fprintf (stderr, _("junk: `\\%03o'"), c);
      goto top;
    }

  ungetc (c, in_FILE);
  *flags |= TOK_LITERAL;
  obstack_grow0 (&tokens_obstack, scanner_buffer, id - scanner_buffer);
  return (struct token *) obstack_finish (&tokens_obstack);
#undef ARGS
}

#undef I1
#undef NM
#undef SQ
#undef EF
#undef ISID1ST
#undef ISIDREST
#undef ISNUMBER
#undef ISEOF
#undef ISBORING
#undef ISIDSQUEEZE