aboutsummaryrefslogtreecommitdiff
path: root/binutils/strings.c
blob: e2c1ead6bfd329605fb80d552a002b5cc26c0e8a (plain)
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
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
/* strings -- print the strings of printable characters in files
   Copyright (C) 1993-2023 Free Software Foundation, Inc.

   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 3, 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., 51 Franklin Street - Fifth Floor, Boston, MA
   02110-1301, USA.  */

/* Usage: strings [options] file...

   Options:
   --all
   -a
   -		Scan each file in its entirety.

   --data
   -d		Scan only the initialized data section(s) of object files.

   --print-file-name
   -f		Print the name of the file before each string.

   --bytes=min-len
   -n min-len
   -min-len	Print graphic char sequences, MIN-LEN or more bytes long,
		that are followed by a NUL or a non-displayable character.
		Default is 4.

   --radix={o,x,d}
   -t {o,x,d}	Print the offset within the file before each string,
		in octal/hex/decimal.

  --include-all-whitespace
  -w		By default tab and space are the only whitepace included in graphic
		char sequences.  This option considers all of isspace() valid.

   -o		Like -to.  (Some other implementations have -o like -to,
		others like -td.  We chose one arbitrarily.)

   --encoding={s,S,b,l,B,L}
   -e {s,S,b,l,B,L}
		Select character encoding: 7-bit-character, 8-bit-character,
		bigendian 16-bit, littleendian 16-bit, bigendian 32-bit,
		littleendian 32-bit.

   --target=BFDNAME
   -T {bfdname}
		Specify a non-default object file format.

  --unicode={default|locale|invalid|hex|escape|highlight}
  -U {d|l|i|x|e|h}
		Determine how to handle UTF-8 unicode characters.  The default
		is no special treatment.  All other versions of this option
		only apply if the encoding is valid and enabling the option
		implies --encoding=S.
		The 'locale' option displays the characters according to the
		current locale.  The 'invalid' option treats them as
		non-string characters.  The 'hex' option displays them as hex
		byte sequences.  The 'escape' option displays them as escape
		sequences and the 'highlight' option displays them as
		coloured escape sequences.

  --output-separator=sep_string
  -s sep_string	String used to separate parsed strings in output.
		Default is newline.

   --help
   -h		Print the usage message on the standard output.

   --version
   -V
   -v		Print the program version number.

   Written by Richard Stallman <rms@gnu.ai.mit.edu>
   and David MacKenzie <djm@gnu.ai.mit.edu>.  */

#include "sysdep.h"
#include "bfd.h"
#include "getopt.h"
#include "libiberty.h"
#include "safe-ctype.h"
#include "bucomm.h"

#ifndef streq
#define streq(a,b) (strcmp ((a),(b)) == 0)
#endif

typedef enum unicode_display_type
{
  unicode_default = 0,
  unicode_locale,
  unicode_escape,
  unicode_hex,
  unicode_highlight,
  unicode_invalid
} unicode_display_type;

static unicode_display_type unicode_display = unicode_default;

#define STRING_ISGRAPHIC(c) \
      (   (c) >= 0 \
       && (c) <= 255 \
       && ((c) == '\t' || ISPRINT (c) || (encoding == 'S' && (c) > 127) \
	   || (include_all_whitespace && ISSPACE (c))) \
      )

#ifndef errno
extern int errno;
#endif

/* The BFD section flags that identify an initialized data section.  */
#define DATA_FLAGS (SEC_ALLOC | SEC_LOAD | SEC_HAS_CONTENTS)

/* Radix for printing addresses (must be 8, 10 or 16).  */
static int address_radix;

/* Minimum length of sequence of graphic chars to trigger output.  */
static unsigned int string_min;

/* Whether or not we include all whitespace as a graphic char.   */
static bool include_all_whitespace;

/* TRUE means print address within file for each string.  */
static bool print_addresses;

/* TRUE means print filename for each string.  */
static bool print_filenames;

/* TRUE means for object files scan only the data section.  */
static bool datasection_only;

/* The BFD object file format.  */
static char *target;

/* The character encoding format.  */
static char encoding;
static int encoding_bytes;

/* Output string used to separate parsed strings  */
static char *output_separator;

static struct option long_options[] =
{
  {"all", no_argument, NULL, 'a'},
  {"bytes", required_argument, NULL, 'n'},
  {"data", no_argument, NULL, 'd'},
  {"encoding", required_argument, NULL, 'e'},
  {"help", no_argument, NULL, 'h'},
  {"include-all-whitespace", no_argument, NULL, 'w'},
  {"output-separator", required_argument, NULL, 's'},
  {"print-file-name", no_argument, NULL, 'f'},
  {"radix", required_argument, NULL, 't'},
  {"target", required_argument, NULL, 'T'},
  {"unicode", required_argument, NULL, 'U'},
  {"version", no_argument, NULL, 'v'},
  {NULL, 0, NULL, 0}
};

static bool strings_file (char *);
static void print_strings (const char *, FILE *, file_ptr, int, char *);
static void usage (FILE *, int) ATTRIBUTE_NORETURN;

int main (int, char **);

int
main (int argc, char **argv)
{
  int optc;
  int exit_status = 0;
  bool files_given = false;
  char *s;
  int numeric_opt = 0;

  setlocale (LC_ALL, "");
  bindtextdomain (PACKAGE, LOCALEDIR);
  textdomain (PACKAGE);

  program_name = argv[0];
  xmalloc_set_program_name (program_name);
  bfd_set_error_program_name (program_name);

  expandargv (&argc, &argv);

  string_min = 4;
  include_all_whitespace = false;
  print_addresses = false;
  print_filenames = false;
  if (DEFAULT_STRINGS_ALL)
    datasection_only = false;
  else
    datasection_only = true;
  target = NULL;
  encoding = 's';
  output_separator = NULL;

  while ((optc = getopt_long (argc, argv, "adfhHn:wot:e:T:s:U:Vv0123456789",
			      long_options, (int *) 0)) != EOF)
    {
      switch (optc)
	{
	case 'a':
	  datasection_only = false;
	  break;

	case 'd':
	  datasection_only = true;
	  break;

	case 'f':
	  print_filenames = true;
	  break;

	case 'H':
	case 'h':
	  usage (stdout, 0);

	case 'n':
	  string_min = (int) strtoul (optarg, &s, 0);
	  if (s != NULL && *s != 0)
	    fatal (_("invalid integer argument %s"), optarg);
	  break;

	case 'w':
	  include_all_whitespace = true;
	  break;

	case 'o':
	  print_addresses = true;
	  address_radix = 8;
	  break;

	case 't':
	  print_addresses = true;
	  if (optarg[1] != '\0')
	    usage (stderr, 1);
	  switch (optarg[0])
	    {
	    case 'o':
	      address_radix = 8;
	      break;

	    case 'd':
	      address_radix = 10;
	      break;

	    case 'x':
	      address_radix = 16;
	      break;

	    default:
	      usage (stderr, 1);
	    }
	  break;

	case 'T':
	  target = optarg;
	  break;

	case 'e':
	  if (optarg[1] != '\0')
	    usage (stderr, 1);
	  encoding = optarg[0];
	  break;

	case 's':
	  output_separator = optarg;
	  break;

	case 'U':
	  if (streq (optarg, "default") || streq (optarg, "d"))
	    unicode_display = unicode_default;
	  else if (streq (optarg, "locale") || streq (optarg, "l"))
	    unicode_display = unicode_locale;
	  else if (streq (optarg, "escape") || streq (optarg, "e"))
	    unicode_display = unicode_escape;
	  else if (streq (optarg, "invalid") || streq (optarg, "i"))
	    unicode_display = unicode_invalid;
	  else if (streq (optarg, "hex") || streq (optarg, "x"))
	    unicode_display = unicode_hex;
	  else if (streq (optarg, "highlight") || streq (optarg, "h"))
	    unicode_display = unicode_highlight;
	  else
	    fatal (_("invalid argument to -U/--unicode: %s"), optarg);
	  break;

	case 'V':
	case 'v':
	  print_version ("strings");
	  break;

	case '?':
	  usage (stderr, 1);

	default:
	  numeric_opt = optind;
	  break;
	}
    }

  if (unicode_display != unicode_default)
    encoding = 'S';

  if (numeric_opt != 0)
    {
      string_min = (int) strtoul (argv[numeric_opt - 1] + 1, &s, 0);
      if (s != NULL && *s != 0)
	fatal (_("invalid integer argument %s"), argv[numeric_opt - 1] + 1);
    }
  if (string_min < 1)
    fatal (_("invalid minimum string length %d"), string_min);

  switch (encoding)
    {
    case 'S':
    case 's':
      encoding_bytes = 1;
      break;
    case 'b':
    case 'l':
      encoding_bytes = 2;
      break;
    case 'B':
    case 'L':
      encoding_bytes = 4;
      break;
    default:
      usage (stderr, 1);
    }

  if (bfd_init () != BFD_INIT_MAGIC)
    fatal (_("fatal error: libbfd ABI mismatch"));
  set_default_bfd_target ();

  if (optind >= argc)
    {
      datasection_only = false;
      SET_BINARY (fileno (stdin));
      print_strings ("{standard input}", stdin, 0, 0, (char *) NULL);
      files_given = true;
    }
  else
    {
      for (; optind < argc; ++optind)
	{
	  if (streq (argv[optind], "-"))
	    datasection_only = false;
	  else
	    {
	      files_given = true;
	      exit_status |= !strings_file (argv[optind]);
	    }
	}
    }

  if (!files_given)
    usage (stderr, 1);

  return (exit_status);
}

/* Scan section SECT of the file ABFD, whose printable name is
   FILENAME.  If it contains initialized data set GOT_A_SECTION and
   print the strings in it.  */

static void
strings_a_section (bfd *abfd, asection *sect, const char *filename,
		   bool *got_a_section)
{
  bfd_size_type sectsize;
  bfd_byte *mem;

  if ((sect->flags & DATA_FLAGS) != DATA_FLAGS)
    return;

  sectsize = bfd_section_size (sect);
  if (sectsize == 0)
    return;

  if (!bfd_malloc_and_get_section (abfd, sect, &mem))
    {
      non_fatal (_("%s: Reading section %s failed: %s"),
		 filename, sect->name, bfd_errmsg (bfd_get_error ()));
      return;
    }

  *got_a_section = true;
  print_strings (filename, NULL, sect->filepos, sectsize, (char *) mem);
  free (mem);
}

/* Scan all of the sections in FILE, and print the strings
   in the initialized data section(s).

   Return TRUE if successful,
   FALSE if not (such as if FILE is not an object file).  */

static bool
strings_object_file (const char *file)
{
  bfd *abfd;
  asection *s;
  bool got_a_section;

  abfd = bfd_openr (file, target);

  if (abfd == NULL)
    /* Treat the file as a non-object file.  */
    return false;

  /* This call is mainly for its side effect of reading in the sections.
     We follow the traditional behavior of `strings' in that we don't
     complain if we don't recognize a file to be an object file.  */
  if (!bfd_check_format (abfd, bfd_object))
    {
      bfd_close (abfd);
      return false;
    }

  got_a_section = false;
  for (s = abfd->sections; s != NULL; s = s->next)
    strings_a_section (abfd, s, file, &got_a_section);

  if (!bfd_close (abfd))
    {
      bfd_nonfatal (file);
      return false;
    }

  return got_a_section;
}

/* Print the strings in FILE.  Return TRUE if ok, FALSE if an error occurs.  */

static bool
strings_file (char *file)
{
  struct stat st;

  /* get_file_size does not support non-S_ISREG files.  */

  if (stat (file, &st) < 0)
    {
      if (errno == ENOENT)
	non_fatal (_("'%s': No such file"), file);
      else
	non_fatal (_("Warning: could not locate '%s'.  reason: %s"),
		   file, strerror (errno));
      return false;
    }
  else if (S_ISDIR (st.st_mode))
    {
      non_fatal (_("Warning: '%s' is a directory"), file);
      return false;
    }

  /* If we weren't told to scan the whole file,
     try to open it as an object file and only look at
     initialized data sections.  If that fails, fall back to the
     whole file.  */
  if (!datasection_only || !strings_object_file (file))
    {
      FILE *stream;

      stream = fopen (file, FOPEN_RB);
      if (stream == NULL)
	{
	  fprintf (stderr, "%s: ", program_name);
	  perror (file);
	  return false;
	}

      print_strings (file, stream, (file_ptr) 0, 0, (char *) NULL);

      if (fclose (stream) == EOF)
	{
	  fprintf (stderr, "%s: ", program_name);
	  perror (file);
	  return false;
	}
    }

  return true;
}

/* Read the next character, return EOF if none available.
   Assume that STREAM is positioned so that the next byte read
   is at address ADDRESS in the file.

   If STREAM is NULL, do not read from it.
   The caller can supply a buffer of characters
   to be processed before the data in STREAM.
   MAGIC is the address of the buffer and
   MAGICCOUNT is how many characters are in it.  */

static long
get_char (FILE *stream, file_ptr *address, int *magiccount, char **magic)
{
  int c, i;
  long r = 0;

  for (i = 0; i < encoding_bytes; i++)
    {
      if (*magiccount)
	{
	  (*magiccount)--;
	  c = *(*magic)++;
	}
      else
	{
	  if (stream == NULL)
	    return EOF;

	  /* Only use getc_unlocked if we found a declaration for it.
	     Otherwise, libc is not thread safe by default, and we
	     should not use it.  */

#if defined(HAVE_GETC_UNLOCKED) && HAVE_DECL_GETC_UNLOCKED
	  c = getc_unlocked (stream);
#else
	  c = getc (stream);
#endif
	  if (c == EOF)
	    return EOF;
	}

      (*address)++;
      r = (r << 8) | (c & 0xff);
    }

  switch (encoding)
    {
    default:
      break;
    case 'l':
      r = ((r & 0xff) << 8) | ((r & 0xff00) >> 8);
      break;
    case 'L':
      r = (((r & 0xff) << 24) | ((r & 0xff00) << 8)
	   | ((r & 0xff0000) >> 8) | ((r & 0xff000000) >> 24));
      break;
    }

  return r;
}

/* Throw away one byte of a (possibly) multi-byte char C, updating
   address and buffer to suit.  */

static void
unget_part_char (long c, file_ptr *address, int *magiccount, char **magic)
{
  static char tmp[4];

  if (encoding_bytes > 1)
    {
      *address -= encoding_bytes - 1;

      if (*magiccount == 0)
	{
	  /* If no magic buffer exists, use temp buffer.  */
	  switch (encoding)
	    {
	    default:
	      break;
	    case 'b':
	      tmp[0] = c & 0xff;
	      *magiccount = 1;
	      break;
	    case 'l':
	      tmp[0] = (c >> 8) & 0xff;
	      *magiccount = 1;
	      break;
	    case 'B':
	      tmp[0] = (c >> 16) & 0xff;
	      tmp[1] = (c >> 8) & 0xff;
	      tmp[2] = c & 0xff;
	      *magiccount = 3;
	      break;
	    case 'L':
	      tmp[0] = (c >> 8) & 0xff;
	      tmp[1] = (c >> 16) & 0xff;
	      tmp[2] = (c >> 24) & 0xff;
	      *magiccount = 3;
	      break;
	    }
	  *magic = tmp;
	}
      else
	{
	  /* If magic buffer exists, rewind.  */
	  *magic -= encoding_bytes - 1;
	  *magiccount += encoding_bytes - 1;
	}
    }
}

static void
print_filename_and_address (const char * filename, file_ptr address)
{
  if (print_filenames)
    printf ("%s: ", filename);

  if (! print_addresses)
    return;

  switch (address_radix)
    {
    case 8:
      if (sizeof (address) > sizeof (long))
	{
#ifndef __MSVCRT__
	  printf ("%7llo ", (unsigned long long) address);
#else
	  printf ("%7I64o ", (unsigned long long) address);
#endif
	}
      else
	printf ("%7lo ", (unsigned long) address);
      break;

    case 10:
      if (sizeof (address) > sizeof (long))
	{
#ifndef __MSVCRT__
	  printf ("%7llu ", (unsigned long long) address);
#else
	  printf ("%7I64d ", (unsigned long long) address);
#endif
	}
      else
	printf ("%7ld ", (long) address);
      break;

    case 16:
      if (sizeof (address) > sizeof (long))
	{
#ifndef __MSVCRT__
	  printf ("%7llx ", (unsigned long long) address);
#else
	  printf ("%7I64x ", (unsigned long long) address);
#endif
	}
      else
	printf ("%7lx ", (unsigned long) address);
      break;
    }
}

/* Return non-zero if the bytes starting at BUFFER form a valid UTF-8 encoding.
   If the encoding is valid then returns the number of bytes it uses.  */

static unsigned int
is_valid_utf8 (const unsigned char * buffer, unsigned long buflen)
{
  if (buffer[0] < 0xc0)
    return 0;

  if (buflen < 2)
    return 0;

  if ((buffer[1] & 0xc0) != 0x80)
    return 0;

  if ((buffer[0] & 0x20) == 0)
    return 2;

  if (buflen < 3)
    return 0;

  if ((buffer[2] & 0xc0) != 0x80)
    return 0;

  if ((buffer[0] & 0x10) == 0)
    return 3;

  if (buflen < 4)
    return 0;

  if ((buffer[3] & 0xc0) != 0x80)
    return 0;

  return 4;
}

/* Display a UTF-8 encoded character in BUFFER according to the setting
   of unicode_display.  The character is known to be valid.
   Returns the number of bytes consumed.  */

static unsigned int
display_utf8_char (const unsigned char * buffer)
{
  unsigned int j;
  unsigned int utf8_len;

  switch (buffer[0] & 0x30)
    {
    case 0x00:
    case 0x10:
      utf8_len = 2;
      break;
    case 0x20:
      utf8_len = 3;
      break;
    default:
      utf8_len = 4;
    }

  switch (unicode_display)
    {
    default:
      fprintf (stderr, "ICE: unexpected unicode display type\n");
      break;

    case unicode_escape:
    case unicode_highlight:
      if (unicode_display == unicode_highlight && isatty (1))
	printf ("\x1B[31;47m"); /* Red.  */

      switch (utf8_len)
	{
	case 2:
	  printf ("\\u%02x%02x",
		  ((buffer[0] & 0x1c) >> 2),
		  ((buffer[0] & 0x03) << 6) | (buffer[1] & 0x3f));
	  break;

	case 3:
	  printf ("\\u%02x%02x",
		  ((buffer[0] & 0x0f) << 4) | ((buffer[1] & 0x3c) >> 2),
		  ((buffer[1] & 0x03) << 6) | ((buffer[2] & 0x3f)));
	  break;

	case 4:
	  printf ("\\u%02x%02x%02x",
		  ((buffer[0] & 0x07) << 6) | ((buffer[1] & 0x3c) >> 2),
		  ((buffer[1] & 0x03) << 6) | ((buffer[2] & 0x3c) >> 2),
		  ((buffer[2] & 0x03) << 6) | ((buffer[3] & 0x3f)));
	  break;
	default:
	  /* URG.  */
	  break;
	}

      if (unicode_display == unicode_highlight && isatty (1))
	printf ("\033[0m"); /* Default colour.  */
      break;

    case unicode_hex:
      putchar ('<');
      printf ("0x");
      for (j = 0; j < utf8_len; j++)
	printf ("%02x", buffer [j]);
      putchar ('>');
      break;

    case unicode_locale:
      printf ("%.1s", buffer);
      break;
    }

  return utf8_len;
}

/* Display strings in BUFFER.  Treat any UTF-8 encoded characters encountered
   according to the setting of the unicode_display variable.  The buffer
   contains BUFLEN bytes.

   Display the characters as if they started at ADDRESS and are contained in
   FILENAME.  */

static void
print_unicode_buffer (const char *            filename,
		      file_ptr                address,
		      const unsigned char *   buffer,
		      unsigned long           buflen)
{
  /* Paranoia checks...  */
  if (filename == NULL
      || buffer == NULL
      || unicode_display == unicode_default
      || encoding != 'S'
      || encoding_bytes != 1)
    {
      fprintf (stderr, "ICE: bad arguments to print_unicode_buffer\n");
      return;
    }

  if (buflen == 0)
    return;

  /* We must only display strings that are at least string_min *characters*
     long.  So we scan the buffer in two stages.  First we locate the start
     of a potential string.  Then we walk along it until we have found
     string_min characters.  Then we go back to the start point and start
     displaying characters according to the unicode_display setting.  */

  unsigned long start_point = 0;
  unsigned long i = 0;
  unsigned int char_len = 1;
  unsigned int num_found = 0;

  for (i = 0; i < buflen; i += char_len)
    {
      int c = buffer[i];

      char_len = 1;

      /* Find the first potential character of a string.  */
      if (! STRING_ISGRAPHIC (c))
	{
	  num_found = 0;
	  continue;
	}

      if (c > 126)
	{
	  if (c < 0xc0)
	    {
	      num_found = 0;
	      continue;
	    }

	  if ((char_len = is_valid_utf8 (buffer + i, buflen - i)) == 0)
	    {
	      char_len = 1;
	      num_found = 0;
	      continue;
	    }

	  if (unicode_display == unicode_invalid)
	    {
	      /* We have found a valid UTF-8 character, but we treat it as non-graphic.  */
	      num_found = 0;
	      continue;
	    }
	}

      if (num_found == 0)
	/* We have found a potential starting point for a string.  */
	start_point = i;

      ++ num_found;

      if (num_found >= string_min)
	break;
    }

  if (num_found < string_min)
    return;

  print_filename_and_address (filename, address + start_point);

  /* We have found string_min characters.  Display them and any
     more that follow.  */
  for (i = start_point; i < buflen; i += char_len)
    {
      int c = buffer[i];

      char_len = 1;

      if (! STRING_ISGRAPHIC (c))
	break;
      else if (c < 127)
	putchar (c);
      else if (! is_valid_utf8 (buffer + i, buflen - i))
	break;
      else if (unicode_display == unicode_invalid)
	break;
      else
	char_len = display_utf8_char (buffer + i);
    }

  if (output_separator)
    fputs (output_separator, stdout);
  else
    putchar ('\n');

  /* FIXME: Using tail recursion here is lazy programming...  */
  print_unicode_buffer (filename, address + i, buffer + i, buflen - i);
}

static int
get_unicode_byte (FILE *          stream,
		  unsigned char * putback,
		  unsigned int *  num_putback,
		  unsigned int *  num_read)
{
  if (* num_putback > 0)
    {
      * num_putback = * num_putback - 1;
      return putback [* num_putback];
    }

  * num_read = * num_read + 1;

#if defined(HAVE_GETC_UNLOCKED) && HAVE_DECL_GETC_UNLOCKED
  return getc_unlocked (stream);
#else
  return getc (stream);
#endif
}

/* Helper function for print_unicode_stream.  */

static void
print_unicode_stream_body (const char *     filename,
			   file_ptr         address,
			   FILE *           stream,
			   unsigned char *  putback_buf,
			   unsigned int     num_putback,
			   unsigned char *  print_buf)
{
  /* It would be nice if we could just read the stream into a buffer
     and then process if with print_unicode_buffer.  But the input
     might be huge or it might time-locked (eg stdin).  So instead
     we go one byte at a time...  */

  file_ptr start_point = 0;
  unsigned int num_read = 0;
  unsigned int num_chars = 0;
  unsigned int num_print = 0;
  int c = 0;

  /* Find a series of string_min characters.  Put them into print_buf.  */
  do
    {
      if (num_chars >= string_min)
	break;

      c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read);
      if (c == EOF)
	break;

      if (! STRING_ISGRAPHIC (c))
	{
	  num_chars = num_print = 0;
	  continue;
	}

      if (num_chars == 0)
	start_point = num_read - 1;

      if (c < 127)
	{
	  print_buf[num_print] = c;
	  num_chars ++;
	  num_print ++;
	  continue;
	}

      if (c < 0xc0)
	{
	  num_chars = num_print = 0;
	  continue;
	}

      /* We *might* have a UTF-8 sequence.  Time to start peeking.  */
      char utf8[4];

      utf8[0] = c;
      c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read);
      if (c == EOF)
	break;
      utf8[1] = c;

      if ((utf8[1] & 0xc0) != 0x80)
	{
	  /* Invalid UTF-8.  */
	  putback_buf[num_putback++] = utf8[1];
	  num_chars = num_print = 0;
	  continue;
	}
      else if ((utf8[0] & 0x20) == 0)
	{
	  /* A valid 2-byte UTF-8 encoding.  */
	  if (unicode_display == unicode_invalid)
	    {
	      putback_buf[num_putback++] = utf8[1];
	      num_chars = num_print = 0;
	    }
	  else
	    {
	      print_buf[num_print ++] = utf8[0];
	      print_buf[num_print ++] = utf8[1];
	      num_chars ++;
	    }
	  continue;
	}

      c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read);
      if (c == EOF)
	break;
      utf8[2] = c;

      if ((utf8[2] & 0xc0) != 0x80)
	{
	  /* Invalid UTF-8.  */
	  putback_buf[num_putback++] = utf8[2];
	  putback_buf[num_putback++] = utf8[1];
	  num_chars = num_print = 0;
	  continue;
	}
      else if ((utf8[0] & 0x10) == 0)
	{
	  /* A valid 3-byte UTF-8 encoding.  */
	  if (unicode_display == unicode_invalid)
	    {
	      putback_buf[num_putback++] = utf8[2];
	      putback_buf[num_putback++] = utf8[1];
	      num_chars = num_print = 0;
	    }
	  else
	    {
	      print_buf[num_print ++] = utf8[0];
	      print_buf[num_print ++] = utf8[1];
	      print_buf[num_print ++] = utf8[2];
	      num_chars ++;
	    }
	  continue;
	}

      c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read);
      if (c == EOF)
	break;
      utf8[3] = c;

      if ((utf8[3] & 0xc0) != 0x80)
	{
	  /* Invalid UTF-8.  */
	  putback_buf[num_putback++] = utf8[3];
	  putback_buf[num_putback++] = utf8[2];
	  putback_buf[num_putback++] = utf8[1];
	  num_chars = num_print = 0;
	}
      /* We have a valid 4-byte UTF-8 encoding.  */
      else if (unicode_display == unicode_invalid)
	{
	  putback_buf[num_putback++] = utf8[3];
	  putback_buf[num_putback++] = utf8[1];
	  putback_buf[num_putback++] = utf8[2];
	  num_chars = num_print = 0;
	}
      else
	{
	  print_buf[num_print ++] = utf8[0];
	  print_buf[num_print ++] = utf8[1];
	  print_buf[num_print ++] = utf8[2];
	  print_buf[num_print ++] = utf8[3];
	  num_chars ++;
	}
    }
  while (1);

  if (num_chars >= string_min)
    {
      /* We know that we have string_min valid characters in print_buf,
	 and there may be more to come in the stream.  Start displaying
	 them.  */

      print_filename_and_address (filename, address + start_point);

      unsigned int i;
      for (i = 0; i < num_print;)
	{
	  if (print_buf[i] < 127)
	    putchar (print_buf[i++]);
	  else
	    i += display_utf8_char (print_buf + i);
	}

      /* OK so now we have to start read unchecked bytes.  */

      /* Find a series of string_min characters.  Put them into print_buf.  */
      do
	{
	  c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read);
	  if (c == EOF)
	    break;

	  if (! STRING_ISGRAPHIC (c))
	    break;

	  if (c < 127)
	    {
	      putchar (c);
	      continue;
	    }

	  if (c < 0xc0)
	    break;

	  /* We *might* have a UTF-8 sequence.  Time to start peeking.  */
	  unsigned char utf8[4];

	  utf8[0] = c;
	  c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read);
	  if (c == EOF)
	    break;
	  utf8[1] = c;

	  if ((utf8[1] & 0xc0) != 0x80)
	    {
	      /* Invalid UTF-8.  */
	      putback_buf[num_putback++] = utf8[1];
	      break;
	    }
	  else if ((utf8[0] & 0x20) == 0)
	    {
	      /* Valid 2-byte UTF-8.  */
	      if (unicode_display == unicode_invalid)
		{
		  putback_buf[num_putback++] = utf8[1];
		  break;
		}
	      else
		{
		  (void) display_utf8_char (utf8);
		  continue;
		}
	    }

	  c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read);
	  if (c == EOF)
	    break;
	  utf8[2] = c;

	  if ((utf8[2] & 0xc0) != 0x80)
	    {
	      /* Invalid UTF-8.  */
	      putback_buf[num_putback++] = utf8[2];
	      putback_buf[num_putback++] = utf8[1];
	      break;
	    }
	  else if ((utf8[0] & 0x10) == 0)
	    {
	      /* Valid 3-byte UTF-8.  */
	      if (unicode_display == unicode_invalid)
		{
		  putback_buf[num_putback++] = utf8[2];
		  putback_buf[num_putback++] = utf8[1];
		  break;
		}
	      else
		{
		  (void) display_utf8_char (utf8);
		  continue;
		}
	    }

	  c = get_unicode_byte (stream, putback_buf, & num_putback, & num_read);
	  if (c == EOF)
	    break;
	  utf8[3] = c;

	  if ((utf8[3] & 0xc0) != 0x80)
	    {
	      /* Invalid UTF-8.  */
	      putback_buf[num_putback++] = utf8[3];
	      putback_buf[num_putback++] = utf8[2];
	      putback_buf[num_putback++] = utf8[1];
	      break;
	    }
	  else if (unicode_display == unicode_invalid)
	    {
	      putback_buf[num_putback++] = utf8[3];
	      putback_buf[num_putback++] = utf8[2];
	      putback_buf[num_putback++] = utf8[1];
	      break;
	    }
	  else
	    /* A valid 4-byte UTF-8 encoding.  */
	    (void) display_utf8_char (utf8);
	}
      while (1);

      if (output_separator)
	fputs (output_separator, stdout);
      else
	putchar ('\n');
    }

  if (c != EOF)
    /* FIXME: Using tail recursion here is lazy, but it works.  */
    print_unicode_stream_body (filename, address + num_read, stream, putback_buf, num_putback, print_buf);
}

/* Display strings read in from STREAM.  Treat any UTF-8 encoded characters
   encountered according to the setting of the unicode_display variable.
   The stream is positioned at ADDRESS and is attached to FILENAME.  */

static void
print_unicode_stream (const char * filename,
		      file_ptr     address,
		      FILE *       stream)
{
  /* Paranoia checks...  */
  if (filename == NULL
      || stream == NULL
      || unicode_display == unicode_default
      || encoding != 'S'
      || encoding_bytes != 1)
    {
      fprintf (stderr, "ICE: bad arguments to print_unicode_stream\n");
      return;
    }

  /* Allocate space for string_min 4-byte utf-8 characters.  */
  unsigned char * print_buf = xmalloc ((4 * string_min) + 1);
  /* We should never have to put back more than 4 bytes.  */
  unsigned char putback_buf[5];
  unsigned int num_putback = 0;

  print_unicode_stream_body (filename, address, stream, putback_buf, num_putback, print_buf);
  free (print_buf);
}

/* Find the strings in file FILENAME, read from STREAM.
   Assume that STREAM is positioned so that the next byte read
   is at address ADDRESS in the file.

   If STREAM is NULL, do not read from it.
   The caller can supply a buffer of characters
   to be processed before the data in STREAM.
   MAGIC is the address of the buffer and
   MAGICCOUNT is how many characters are in it.
   Those characters come at address ADDRESS and the data in STREAM follow.  */

static void
print_strings (const char *filename, FILE *stream, file_ptr address,
	       int magiccount, char *magic)
{
  if (unicode_display != unicode_default)
    {
      if (magic != NULL)
	print_unicode_buffer (filename, address,
			      (const unsigned char *) magic, magiccount);

      if (stream != NULL)
	print_unicode_stream (filename, address, stream);
      return;
    }

  char *buf = (char *) xmalloc (sizeof (char) * (string_min + 1));

  while (1)
    {
      file_ptr start;
      unsigned int i;
      long c;

      /* See if the next `string_min' chars are all graphic chars.  */
    tryline:
      start = address;
      for (i = 0; i < string_min; i++)
	{
	  c = get_char (stream, &address, &magiccount, &magic);
	  if (c == EOF)
	    {
	      free (buf);
	      return;
	    }

	  if (! STRING_ISGRAPHIC (c))
	    {
	      /* Found a non-graphic.  Try again starting with next byte.  */
	      unget_part_char (c, &address, &magiccount, &magic);
	      goto tryline;
	    }
	  buf[i] = c;
	}

      /* We found a run of `string_min' graphic characters.  Print up
	 to the next non-graphic character.  */
      print_filename_and_address (filename, start);

      buf[i] = '\0';
      fputs (buf, stdout);

      while (1)
	{
	  c = get_char (stream, &address, &magiccount, &magic);
	  if (c == EOF)
	    break;
	  if (! STRING_ISGRAPHIC (c))
	    {
	      unget_part_char (c, &address, &magiccount, &magic);
	      break;
	    }
	  putchar (c);
	}

      if (output_separator)
	fputs (output_separator, stdout);
      else
	putchar ('\n');
    }
  free (buf);
}

static void
usage (FILE *stream, int status)
{
  fprintf (stream, _("Usage: %s [option(s)] [file(s)]\n"), program_name);
  fprintf (stream, _(" Display printable strings in [file(s)] (stdin by default)\n"));
  fprintf (stream, _(" The options are:\n"));

  if (DEFAULT_STRINGS_ALL)
    fprintf (stream, _("\
  -a - --all                Scan the entire file, not just the data section [default]\n\
  -d --data                 Only scan the data sections in the file\n"));
  else
    fprintf (stream, _("\
  -a - --all                Scan the entire file, not just the data section\n\
  -d --data                 Only scan the data sections in the file [default]\n"));

  fprintf (stream, _("\
  -f --print-file-name      Print the name of the file before each string\n\
  -n <number>               Locate & print any sequence of at least <number>\n\
    --bytes=<number>         displayable characters.  (The default is 4).\n\
  -t --radix={o,d,x}        Print the location of the string in base 8, 10 or 16\n\
  -w --include-all-whitespace Include all whitespace as valid string characters\n\
  -o                        An alias for --radix=o\n\
  -T --target=<BFDNAME>     Specify the binary file format\n\
  -e --encoding={s,S,b,l,B,L} Select character size and endianness:\n\
                            s = 7-bit, S = 8-bit, {b,l} = 16-bit, {B,L} = 32-bit\n\
  --unicode={default|show|invalid|hex|escape|highlight}\n\
  -U {d|s|i|x|e|h}          Specify how to treat UTF-8 encoded unicode characters\n\
  -s --output-separator=<string> String used to separate strings in output.\n\
  @<file>                   Read options from <file>\n\
  -h --help                 Display this information\n\
  -v -V --version           Print the program's version number\n"));
  list_supported_targets (program_name, stream);
  if (REPORT_BUGS_TO[0] && status == 0)
    fprintf (stream, _("Report bugs to %s\n"), REPORT_BUGS_TO);
  exit (status);
}