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
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
|
/* C language support routines for GDB, the GNU debugger.
Copyright (C) 1992, 1993, 1994, 1995, 1996, 1998, 1999, 2000, 2002, 2003,
2004, 2005, 2007, 2008, 2009, 2010 Free Software Foundation, Inc.
This file is part of GDB.
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 of the License, 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, see <http://www.gnu.org/licenses/>. */
#include "defs.h"
#include "symtab.h"
#include "gdbtypes.h"
#include "expression.h"
#include "parser-defs.h"
#include "language.h"
#include "c-lang.h"
#include "valprint.h"
#include "macroscope.h"
#include "gdb_assert.h"
#include "charset.h"
#include "gdb_string.h"
#include "demangle.h"
#include "cp-abi.h"
#include "cp-support.h"
#include "gdb_obstack.h"
#include <ctype.h>
extern void _initialize_c_language (void);
/* Given a C string type, STR_TYPE, return the corresponding target
character set name. */
static const char *
charset_for_string_type (enum c_string_type str_type,
enum bfd_endian byte_order)
{
switch (str_type & ~C_CHAR)
{
case C_STRING:
return target_charset ();
case C_WIDE_STRING:
return target_wide_charset (byte_order);
case C_STRING_16:
/* FIXME: UTF-16 is not always correct. */
if (byte_order == BFD_ENDIAN_BIG)
return "UTF-16BE";
else
return "UTF-16LE";
case C_STRING_32:
/* FIXME: UTF-32 is not always correct. */
if (byte_order == BFD_ENDIAN_BIG)
return "UTF-32BE";
else
return "UTF-32LE";
}
internal_error (__FILE__, __LINE__, "unhandled c_string_type");
}
/* Classify ELTTYPE according to what kind of character it is. Return
the enum constant representing the character type. Also set
*ENCODING to the name of the character set to use when converting
characters of this type in target BYTE_ORDER to the host character set. */
static enum c_string_type
classify_type (struct type *elttype, enum bfd_endian byte_order,
const char **encoding)
{
struct type *saved_type;
enum c_string_type result;
/* We loop because ELTTYPE may be a typedef, and we want to
successively peel each typedef until we reach a type we
understand. We don't use CHECK_TYPEDEF because that will strip
all typedefs at once -- but in C, wchar_t is itself a typedef, so
that would do the wrong thing. */
while (elttype)
{
char *name = TYPE_NAME (elttype);
if (TYPE_CODE (elttype) == TYPE_CODE_CHAR || !name)
{
result = C_CHAR;
goto done;
}
if (!strcmp (name, "wchar_t"))
{
result = C_WIDE_CHAR;
goto done;
}
if (!strcmp (name, "char16_t"))
{
result = C_CHAR_16;
goto done;
}
if (!strcmp (name, "char32_t"))
{
result = C_CHAR_32;
goto done;
}
if (TYPE_CODE (elttype) != TYPE_CODE_TYPEDEF)
break;
/* Call for side effects. */
check_typedef (elttype);
if (TYPE_TARGET_TYPE (elttype))
elttype = TYPE_TARGET_TYPE (elttype);
else
{
/* Perhaps check_typedef did not update the target type. In
this case, force the lookup again and hope it works out.
It never will for C, but it might for C++. */
CHECK_TYPEDEF (elttype);
}
}
/* Punt. */
result = C_CHAR;
done:
if (encoding)
*encoding = charset_for_string_type (result, byte_order);
return result;
}
/* Return true if print_wchar can display W without resorting to a
numeric escape, false otherwise. */
static int
wchar_printable (gdb_wchar_t w)
{
return (gdb_iswprint (w)
|| w == LCST ('\a') || w == LCST ('\b')
|| w == LCST ('\f') || w == LCST ('\n')
|| w == LCST ('\r') || w == LCST ('\t')
|| w == LCST ('\v'));
}
/* A helper function that converts the contents of STRING to wide
characters and then appends them to OUTPUT. */
static void
append_string_as_wide (const char *string, struct obstack *output)
{
for (; *string; ++string)
{
gdb_wchar_t w = gdb_btowc (*string);
obstack_grow (output, &w, sizeof (gdb_wchar_t));
}
}
/* Print a wide character W to OUTPUT. ORIG is a pointer to the
original (target) bytes representing the character, ORIG_LEN is the
number of valid bytes. WIDTH is the number of bytes in a base
characters of the type. OUTPUT is an obstack to which wide
characters are emitted. QUOTER is a (narrow) character indicating
the style of quotes surrounding the character to be printed.
NEED_ESCAPE is an in/out flag which is used to track numeric
escapes across calls. */
static void
print_wchar (gdb_wint_t w, const gdb_byte *orig, int orig_len,
int width, enum bfd_endian byte_order, struct obstack *output,
int quoter, int *need_escapep)
{
int need_escape = *need_escapep;
*need_escapep = 0;
if (gdb_iswprint (w) && (!need_escape || (!gdb_iswdigit (w)
&& w != LCST ('8')
&& w != LCST ('9'))))
{
gdb_wchar_t wchar = w;
if (w == gdb_btowc (quoter) || w == LCST ('\\'))
obstack_grow_wstr (output, LCST ("\\"));
obstack_grow (output, &wchar, sizeof (gdb_wchar_t));
}
else
{
switch (w)
{
case LCST ('\a'):
obstack_grow_wstr (output, LCST ("\\a"));
break;
case LCST ('\b'):
obstack_grow_wstr (output, LCST ("\\b"));
break;
case LCST ('\f'):
obstack_grow_wstr (output, LCST ("\\f"));
break;
case LCST ('\n'):
obstack_grow_wstr (output, LCST ("\\n"));
break;
case LCST ('\r'):
obstack_grow_wstr (output, LCST ("\\r"));
break;
case LCST ('\t'):
obstack_grow_wstr (output, LCST ("\\t"));
break;
case LCST ('\v'):
obstack_grow_wstr (output, LCST ("\\v"));
break;
default:
{
int i;
for (i = 0; i + width <= orig_len; i += width)
{
char octal[30];
ULONGEST value;
value = extract_unsigned_integer (&orig[i], width, byte_order);
/* If the value fits in 3 octal digits, print it that
way. Otherwise, print it as a hex escape. */
if (value <= 0777)
sprintf (octal, "\\%.3o", (int) (value & 0777));
else
sprintf (octal, "\\x%lx", (long) value);
append_string_as_wide (octal, output);
}
/* If we somehow have extra bytes, print them now. */
while (i < orig_len)
{
char octal[5];
sprintf (octal, "\\%.3o", orig[i] & 0xff);
append_string_as_wide (octal, output);
++i;
}
*need_escapep = 1;
}
break;
}
}
}
/* Print the character C on STREAM as part of the contents of a literal
string whose delimiter is QUOTER. Note that that format for printing
characters and strings is language specific. */
static void
c_emit_char (int c, struct type *type, struct ui_file *stream, int quoter)
{
enum bfd_endian byte_order = gdbarch_byte_order (get_type_arch (type));
struct obstack wchar_buf, output;
struct cleanup *cleanups;
const char *encoding;
gdb_byte *buf;
struct wchar_iterator *iter;
int need_escape = 0;
classify_type (type, byte_order, &encoding);
buf = alloca (TYPE_LENGTH (type));
pack_long (buf, type, c);
iter = make_wchar_iterator (buf, TYPE_LENGTH (type), encoding,
TYPE_LENGTH (type));
cleanups = make_cleanup_wchar_iterator (iter);
/* This holds the printable form of the wchar_t data. */
obstack_init (&wchar_buf);
make_cleanup_obstack_free (&wchar_buf);
while (1)
{
int num_chars;
gdb_wchar_t *chars;
const gdb_byte *buf;
size_t buflen;
int print_escape = 1;
enum wchar_iterate_result result;
num_chars = wchar_iterate (iter, &result, &chars, &buf, &buflen);
if (num_chars < 0)
break;
if (num_chars > 0)
{
/* If all characters are printable, print them. Otherwise,
we're going to have to print an escape sequence. We
check all characters because we want to print the target
bytes in the escape sequence, and we don't know character
boundaries there. */
int i;
print_escape = 0;
for (i = 0; i < num_chars; ++i)
if (!wchar_printable (chars[i]))
{
print_escape = 1;
break;
}
if (!print_escape)
{
for (i = 0; i < num_chars; ++i)
print_wchar (chars[i], buf, buflen, TYPE_LENGTH (type),
byte_order, &wchar_buf, quoter, &need_escape);
}
}
/* This handles the NUM_CHARS == 0 case as well. */
if (print_escape)
print_wchar (gdb_WEOF, buf, buflen, TYPE_LENGTH (type), byte_order,
&wchar_buf, quoter, &need_escape);
}
/* The output in the host encoding. */
obstack_init (&output);
make_cleanup_obstack_free (&output);
convert_between_encodings (INTERMEDIATE_ENCODING, host_charset (),
obstack_base (&wchar_buf),
obstack_object_size (&wchar_buf),
1, &output, translit_char);
obstack_1grow (&output, '\0');
fputs_filtered (obstack_base (&output), stream);
do_cleanups (cleanups);
}
void
c_printchar (int c, struct type *type, struct ui_file *stream)
{
enum c_string_type str_type;
str_type = classify_type (type, BFD_ENDIAN_UNKNOWN, NULL);
switch (str_type)
{
case C_CHAR:
break;
case C_WIDE_CHAR:
fputc_filtered ('L', stream);
break;
case C_CHAR_16:
fputc_filtered ('u', stream);
break;
case C_CHAR_32:
fputc_filtered ('U', stream);
break;
}
fputc_filtered ('\'', stream);
LA_EMIT_CHAR (c, type, stream, '\'');
fputc_filtered ('\'', stream);
}
/* Print the character string STRING, printing at most LENGTH characters.
LENGTH is -1 if the string is nul terminated. Each character is WIDTH bytes
long. Printing stops early if the number hits print_max; repeat counts are
printed as appropriate. Print ellipses at the end if we had to stop before
printing LENGTH characters, or if FORCE_ELLIPSES. */
void
c_printstr (struct ui_file *stream, struct type *type, const gdb_byte *string,
unsigned int length, int force_ellipses,
const struct value_print_options *options)
{
enum bfd_endian byte_order = gdbarch_byte_order (get_type_arch (type));
unsigned int i;
unsigned int things_printed = 0;
int in_quotes = 0;
int need_comma = 0;
int width = TYPE_LENGTH (type);
struct obstack wchar_buf, output;
struct cleanup *cleanup;
enum c_string_type str_type;
const char *encoding;
struct wchar_iterator *iter;
int finished = 0;
int need_escape = 0;
/* If the string was not truncated due to `set print elements', and
the last byte of it is a null, we don't print that, in traditional C
style. */
if (!force_ellipses
&& length > 0
&& (extract_unsigned_integer (string + (length - 1) * width,
width, byte_order) == 0))
length--;
str_type = classify_type (type, byte_order, &encoding) & ~C_CHAR;
switch (str_type)
{
case C_STRING:
break;
case C_WIDE_STRING:
fputs_filtered ("L", stream);
break;
case C_STRING_16:
fputs_filtered ("u", stream);
break;
case C_STRING_32:
fputs_filtered ("U", stream);
break;
}
if (length == 0)
{
fputs_filtered ("\"\"", stream);
return;
}
if (length == -1)
{
unsigned long current_char = 1;
for (i = 0; current_char; ++i)
{
QUIT;
current_char = extract_unsigned_integer (string + i * width,
width, byte_order);
}
length = i;
}
/* Arrange to iterate over the characters, in wchar_t form. */
iter = make_wchar_iterator (string, length * width, encoding, width);
cleanup = make_cleanup_wchar_iterator (iter);
/* WCHAR_BUF is the obstack we use to represent the string in
wchar_t form. */
obstack_init (&wchar_buf);
make_cleanup_obstack_free (&wchar_buf);
while (!finished && things_printed < options->print_max)
{
int num_chars;
enum wchar_iterate_result result;
gdb_wchar_t *chars;
const gdb_byte *buf;
size_t buflen;
QUIT;
if (need_comma)
{
obstack_grow_wstr (&wchar_buf, LCST (", "));
need_comma = 0;
}
num_chars = wchar_iterate (iter, &result, &chars, &buf, &buflen);
/* We only look at repetitions when we were able to convert a
single character in isolation. This makes the code simpler
and probably does the sensible thing in the majority of
cases. */
while (num_chars == 1 && things_printed < options->print_max)
{
/* Count the number of repetitions. */
unsigned int reps = 0;
gdb_wchar_t current_char = chars[0];
const gdb_byte *orig_buf = buf;
int orig_len = buflen;
if (need_comma)
{
obstack_grow_wstr (&wchar_buf, LCST (", "));
need_comma = 0;
}
while (num_chars == 1 && current_char == chars[0])
{
num_chars = wchar_iterate (iter, &result, &chars, &buf, &buflen);
++reps;
}
/* Emit CURRENT_CHAR according to the repetition count and
options. */
if (reps > options->repeat_count_threshold)
{
if (in_quotes)
{
if (options->inspect_it)
obstack_grow_wstr (&wchar_buf, LCST ("\\\", "));
else
obstack_grow_wstr (&wchar_buf, LCST ("\", "));
in_quotes = 0;
}
obstack_grow_wstr (&wchar_buf, LCST ("'"));
need_escape = 0;
print_wchar (current_char, orig_buf, orig_len, width,
byte_order, &wchar_buf, '\'', &need_escape);
obstack_grow_wstr (&wchar_buf, LCST ("'"));
{
/* Painful gyrations. */
int j;
char *s = xstrprintf (_(" <repeats %u times>"), reps);
for (j = 0; s[j]; ++j)
{
gdb_wchar_t w = gdb_btowc (s[j]);
obstack_grow (&wchar_buf, &w, sizeof (gdb_wchar_t));
}
xfree (s);
}
things_printed += options->repeat_count_threshold;
need_comma = 1;
}
else
{
/* Saw the character one or more times, but fewer than
the repetition threshold. */
if (!in_quotes)
{
if (options->inspect_it)
obstack_grow_wstr (&wchar_buf, LCST ("\\\""));
else
obstack_grow_wstr (&wchar_buf, LCST ("\""));
in_quotes = 1;
need_escape = 0;
}
while (reps-- > 0)
{
print_wchar (current_char, orig_buf, orig_len, width,
byte_order, &wchar_buf, '"', &need_escape);
++things_printed;
}
}
}
/* NUM_CHARS and the other outputs from wchar_iterate are valid
here regardless of which branch was taken above. */
if (num_chars < 0)
{
/* Hit EOF. */
finished = 1;
break;
}
switch (result)
{
case wchar_iterate_invalid:
if (!in_quotes)
{
if (options->inspect_it)
obstack_grow_wstr (&wchar_buf, LCST ("\\\""));
else
obstack_grow_wstr (&wchar_buf, LCST ("\""));
in_quotes = 1;
}
need_escape = 0;
print_wchar (gdb_WEOF, buf, buflen, width, byte_order, &wchar_buf,
'"', &need_escape);
break;
case wchar_iterate_incomplete:
if (in_quotes)
{
if (options->inspect_it)
obstack_grow_wstr (&wchar_buf, LCST ("\\\","));
else
obstack_grow_wstr (&wchar_buf, LCST ("\","));
in_quotes = 0;
}
obstack_grow_wstr (&wchar_buf, LCST (" <incomplete sequence "));
print_wchar (gdb_WEOF, buf, buflen, width, byte_order, &wchar_buf,
0, &need_escape);
obstack_grow_wstr (&wchar_buf, LCST (">"));
finished = 1;
break;
}
}
/* Terminate the quotes if necessary. */
if (in_quotes)
{
if (options->inspect_it)
obstack_grow_wstr (&wchar_buf, LCST ("\\\""));
else
obstack_grow_wstr (&wchar_buf, LCST ("\""));
}
if (force_ellipses || !finished)
obstack_grow_wstr (&wchar_buf, LCST ("..."));
/* OUTPUT is where we collect `char's for printing. */
obstack_init (&output);
make_cleanup_obstack_free (&output);
convert_between_encodings (INTERMEDIATE_ENCODING, host_charset (),
obstack_base (&wchar_buf),
obstack_object_size (&wchar_buf),
1, &output, translit_char);
obstack_1grow (&output, '\0');
fputs_filtered (obstack_base (&output), stream);
do_cleanups (cleanup);
}
/* Obtain a C string from the inferior storing it in a newly allocated
buffer in BUFFER, which should be freed by the caller. If the
in- and out-parameter *LENGTH is specified at -1, the string is read
until a null character of the appropriate width is found, otherwise
the string is read to the length of characters specified.
The size of a character is determined by the length of the target
type of the pointer or array. If VALUE is an array with a known
length, the function will not read past the end of the array.
On completion, *LENGTH will be set to the size of the string read in
characters. (If a length of -1 is specified, the length returned
will not include the null character). CHARSET is always set to the
target charset. */
void
c_get_string (struct value *value, gdb_byte **buffer, int *length,
struct type **char_type, const char **charset)
{
int err, width;
unsigned int fetchlimit;
struct type *type = check_typedef (value_type (value));
struct type *element_type = TYPE_TARGET_TYPE (type);
int req_length = *length;
enum bfd_endian byte_order = gdbarch_byte_order (get_type_arch (type));
enum c_string_type kind;
if (element_type == NULL)
goto error;
if (TYPE_CODE (type) == TYPE_CODE_ARRAY)
{
/* If we know the size of the array, we can use it as a limit on the
number of characters to be fetched. */
if (TYPE_NFIELDS (type) == 1
&& TYPE_CODE (TYPE_FIELD_TYPE (type, 0)) == TYPE_CODE_RANGE)
{
LONGEST low_bound, high_bound;
get_discrete_bounds (TYPE_FIELD_TYPE (type, 0),
&low_bound, &high_bound);
fetchlimit = high_bound - low_bound + 1;
}
else
fetchlimit = UINT_MAX;
}
else if (TYPE_CODE (type) == TYPE_CODE_PTR)
fetchlimit = UINT_MAX;
else
/* We work only with arrays and pointers. */
goto error;
if (! c_textual_element_type (element_type, 0))
goto error;
kind = classify_type (element_type,
gdbarch_byte_order (get_type_arch (element_type)),
charset);
width = TYPE_LENGTH (element_type);
/* If the string lives in GDB's memory instead of the inferior's, then we
just need to copy it to BUFFER. Also, since such strings are arrays
with known size, FETCHLIMIT will hold the size of the array. */
if ((VALUE_LVAL (value) == not_lval
|| VALUE_LVAL (value) == lval_internalvar)
&& fetchlimit != UINT_MAX)
{
int i;
const gdb_byte *contents = value_contents (value);
/* If a length is specified, use that. */
if (*length >= 0)
i = *length;
else
/* Otherwise, look for a null character. */
for (i = 0; i < fetchlimit; i++)
if (extract_unsigned_integer (contents + i * width, width,
byte_order) == 0)
break;
/* I is now either a user-defined length, the number of non-null
characters, or FETCHLIMIT. */
*length = i * width;
*buffer = xmalloc (*length);
memcpy (*buffer, contents, *length);
err = 0;
}
else
{
err = read_string (value_as_address (value), *length, width, fetchlimit,
byte_order, buffer, length);
if (err)
{
xfree (*buffer);
error (_("Error reading string from inferior: %s"),
safe_strerror (err));
}
}
/* If the LENGTH is specified at -1, we want to return the string
length up to the terminating null character. If an actual length
was specified, we want to return the length of exactly what was
read. */
if (req_length == -1)
/* If the last character is null, subtract it from LENGTH. */
if (*length > 0
&& extract_unsigned_integer (*buffer + *length - width, width,
byte_order) == 0)
*length -= width;
/* The read_string function will return the number of bytes read.
If length returned from read_string was > 0, return the number of
characters read by dividing the number of bytes by width. */
if (*length != 0)
*length = *length / width;
*char_type = element_type;
return;
error:
{
char *type_str;
type_str = type_to_string (type);
if (type_str)
{
make_cleanup (xfree, type_str);
error (_("Trying to read string with inappropriate type `%s'."),
type_str);
}
else
error (_("Trying to read string with inappropriate type."));
}
}
/* Evaluating C and C++ expressions. */
/* Convert a UCN. The digits of the UCN start at P and extend no
farther than LIMIT. DEST_CHARSET is the name of the character set
into which the UCN should be converted. The results are written to
OUTPUT. LENGTH is the maximum length of the UCN, either 4 or 8.
Returns a pointer to just after the final digit of the UCN. */
static char *
convert_ucn (char *p, char *limit, const char *dest_charset,
struct obstack *output, int length)
{
unsigned long result = 0;
gdb_byte data[4];
int i;
for (i = 0; i < length && p < limit && isxdigit (*p); ++i, ++p)
result = (result << 4) + host_hex_value (*p);
for (i = 3; i >= 0; --i)
{
data[i] = result & 0xff;
result >>= 8;
}
convert_between_encodings ("UTF-32BE", dest_charset, data, 4, 4, output,
translit_none);
return p;
}
/* Emit a character, VALUE, which was specified numerically, to
OUTPUT. TYPE is the target character type. */
static void
emit_numeric_character (struct type *type, unsigned long value,
struct obstack *output)
{
gdb_byte *buffer;
buffer = alloca (TYPE_LENGTH (type));
pack_long (buffer, type, value);
obstack_grow (output, buffer, TYPE_LENGTH (type));
}
/* Convert an octal escape sequence. TYPE is the target character
type. The digits of the escape sequence begin at P and extend no
farther than LIMIT. The result is written to OUTPUT. Returns a
pointer to just after the final digit of the escape sequence. */
static char *
convert_octal (struct type *type, char *p, char *limit, struct obstack *output)
{
int i;
unsigned long value = 0;
for (i = 0;
i < 3 && p < limit && isdigit (*p) && *p != '8' && *p != '9';
++i)
{
value = 8 * value + host_hex_value (*p);
++p;
}
emit_numeric_character (type, value, output);
return p;
}
/* Convert a hex escape sequence. TYPE is the target character type.
The digits of the escape sequence begin at P and extend no farther
than LIMIT. The result is written to OUTPUT. Returns a pointer to
just after the final digit of the escape sequence. */
static char *
convert_hex (struct type *type, char *p, char *limit, struct obstack *output)
{
unsigned long value = 0;
while (p < limit && isxdigit (*p))
{
value = 16 * value + host_hex_value (*p);
++p;
}
emit_numeric_character (type, value, output);
return p;
}
#define ADVANCE \
do { \
++p; \
if (p == limit) \
error (_("Malformed escape sequence")); \
} while (0)
/* Convert an escape sequence to a target format. TYPE is the target
character type to use, and DEST_CHARSET is the name of the target
character set. The backslash of the escape sequence is at *P, and
the escape sequence will not extend past LIMIT. The results are
written to OUTPUT. Returns a pointer to just past the final
character of the escape sequence. */
static char *
convert_escape (struct type *type, const char *dest_charset,
char *p, char *limit, struct obstack *output)
{
/* Skip the backslash. */
ADVANCE;
switch (*p)
{
case '\\':
obstack_1grow (output, '\\');
++p;
break;
case 'x':
ADVANCE;
if (!isxdigit (*p))
error (_("\\x used with no following hex digits."));
p = convert_hex (type, p, limit, output);
break;
case '0':
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
p = convert_octal (type, p, limit, output);
break;
case 'u':
case 'U':
{
int length = *p == 'u' ? 4 : 8;
ADVANCE;
if (!isxdigit (*p))
error (_("\\u used with no following hex digits"));
p = convert_ucn (p, limit, dest_charset, output, length);
}
}
return p;
}
/* Given a single string from a (C-specific) OP_STRING list, convert
it to a target string, handling escape sequences specially. The
output is written to OUTPUT. DATA is the input string, which has
length LEN. DEST_CHARSET is the name of the target character set,
and TYPE is the type of target character to use. */
static void
parse_one_string (struct obstack *output, char *data, int len,
const char *dest_charset, struct type *type)
{
char *limit;
limit = data + len;
while (data < limit)
{
char *p = data;
/* Look for next escape, or the end of the input. */
while (p < limit && *p != '\\')
++p;
/* If we saw a run of characters, convert them all. */
if (p > data)
convert_between_encodings (host_charset (), dest_charset,
data, p - data, 1, output, translit_none);
/* If we saw an escape, convert it. */
if (p < limit)
p = convert_escape (type, dest_charset, p, limit, output);
data = p;
}
}
/* Expression evaluator for the C language family. Most operations
are delegated to evaluate_subexp_standard; see that function for a
description of the arguments. */
static struct value *
evaluate_subexp_c (struct type *expect_type, struct expression *exp,
int *pos, enum noside noside)
{
enum exp_opcode op = exp->elts[*pos].opcode;
switch (op)
{
case OP_STRING:
{
int oplen, limit;
struct type *type;
struct obstack output;
struct cleanup *cleanup;
struct value *result;
enum c_string_type dest_type;
const char *dest_charset;
enum bfd_endian byte_order;
obstack_init (&output);
cleanup = make_cleanup_obstack_free (&output);
++*pos;
oplen = longest_to_int (exp->elts[*pos].longconst);
++*pos;
limit = *pos + BYTES_TO_EXP_ELEM (oplen + 1);
dest_type
= (enum c_string_type) longest_to_int (exp->elts[*pos].longconst);
switch (dest_type & ~C_CHAR)
{
case C_STRING:
type = language_string_char_type (exp->language_defn,
exp->gdbarch);
break;
case C_WIDE_STRING:
type = lookup_typename (exp->language_defn, exp->gdbarch,
"wchar_t", NULL, 0);
break;
case C_STRING_16:
type = lookup_typename (exp->language_defn, exp->gdbarch,
"char16_t", NULL, 0);
break;
case C_STRING_32:
type = lookup_typename (exp->language_defn, exp->gdbarch,
"char32_t", NULL, 0);
break;
default:
internal_error (__FILE__, __LINE__, "unhandled c_string_type");
}
/* Ensure TYPE_LENGTH is valid for TYPE. */
check_typedef (type);
byte_order = gdbarch_byte_order (exp->gdbarch);
dest_charset = charset_for_string_type (dest_type, byte_order);
++*pos;
while (*pos < limit)
{
int len;
len = longest_to_int (exp->elts[*pos].longconst);
++*pos;
if (noside != EVAL_SKIP)
parse_one_string (&output, &exp->elts[*pos].string, len,
dest_charset, type);
*pos += BYTES_TO_EXP_ELEM (len);
}
/* Skip the trailing length and opcode. */
*pos += 2;
if (noside == EVAL_SKIP)
{
/* Return a dummy value of the appropriate type. */
if ((dest_type & C_CHAR) != 0)
result = allocate_value (type);
else
result = value_cstring ("", 0, type);
do_cleanups (cleanup);
return result;
}
if ((dest_type & C_CHAR) != 0)
{
LONGEST value;
if (obstack_object_size (&output) != TYPE_LENGTH (type))
error (_("Could not convert character constant to target character set"));
value = unpack_long (type, obstack_base (&output));
result = value_from_longest (type, value);
}
else
{
int i;
/* Write the terminating character. */
for (i = 0; i < TYPE_LENGTH (type); ++i)
obstack_1grow (&output, 0);
result = value_cstring (obstack_base (&output),
obstack_object_size (&output),
type);
}
do_cleanups (cleanup);
return result;
}
break;
default:
break;
}
return evaluate_subexp_standard (expect_type, exp, pos, noside);
}
/* Table mapping opcodes into strings for printing operators
and precedences of the operators. */
const struct op_print c_op_print_tab[] =
{
{",", BINOP_COMMA, PREC_COMMA, 0},
{"=", BINOP_ASSIGN, PREC_ASSIGN, 1},
{"||", BINOP_LOGICAL_OR, PREC_LOGICAL_OR, 0},
{"&&", BINOP_LOGICAL_AND, PREC_LOGICAL_AND, 0},
{"|", BINOP_BITWISE_IOR, PREC_BITWISE_IOR, 0},
{"^", BINOP_BITWISE_XOR, PREC_BITWISE_XOR, 0},
{"&", BINOP_BITWISE_AND, PREC_BITWISE_AND, 0},
{"==", BINOP_EQUAL, PREC_EQUAL, 0},
{"!=", BINOP_NOTEQUAL, PREC_EQUAL, 0},
{"<=", BINOP_LEQ, PREC_ORDER, 0},
{">=", BINOP_GEQ, PREC_ORDER, 0},
{">", BINOP_GTR, PREC_ORDER, 0},
{"<", BINOP_LESS, PREC_ORDER, 0},
{">>", BINOP_RSH, PREC_SHIFT, 0},
{"<<", BINOP_LSH, PREC_SHIFT, 0},
{"+", BINOP_ADD, PREC_ADD, 0},
{"-", BINOP_SUB, PREC_ADD, 0},
{"*", BINOP_MUL, PREC_MUL, 0},
{"/", BINOP_DIV, PREC_MUL, 0},
{"%", BINOP_REM, PREC_MUL, 0},
{"@", BINOP_REPEAT, PREC_REPEAT, 0},
{"-", UNOP_NEG, PREC_PREFIX, 0},
{"!", UNOP_LOGICAL_NOT, PREC_PREFIX, 0},
{"~", UNOP_COMPLEMENT, PREC_PREFIX, 0},
{"*", UNOP_IND, PREC_PREFIX, 0},
{"&", UNOP_ADDR, PREC_PREFIX, 0},
{"sizeof ", UNOP_SIZEOF, PREC_PREFIX, 0},
{"++", UNOP_PREINCREMENT, PREC_PREFIX, 0},
{"--", UNOP_PREDECREMENT, PREC_PREFIX, 0},
{NULL, 0, 0, 0}
};
enum c_primitive_types {
c_primitive_type_int,
c_primitive_type_long,
c_primitive_type_short,
c_primitive_type_char,
c_primitive_type_float,
c_primitive_type_double,
c_primitive_type_void,
c_primitive_type_long_long,
c_primitive_type_signed_char,
c_primitive_type_unsigned_char,
c_primitive_type_unsigned_short,
c_primitive_type_unsigned_int,
c_primitive_type_unsigned_long,
c_primitive_type_unsigned_long_long,
c_primitive_type_long_double,
c_primitive_type_complex,
c_primitive_type_double_complex,
c_primitive_type_decfloat,
c_primitive_type_decdouble,
c_primitive_type_declong,
nr_c_primitive_types
};
void
c_language_arch_info (struct gdbarch *gdbarch,
struct language_arch_info *lai)
{
const struct builtin_type *builtin = builtin_type (gdbarch);
lai->string_char_type = builtin->builtin_char;
lai->primitive_type_vector
= GDBARCH_OBSTACK_CALLOC (gdbarch, nr_c_primitive_types + 1,
struct type *);
lai->primitive_type_vector [c_primitive_type_int] = builtin->builtin_int;
lai->primitive_type_vector [c_primitive_type_long] = builtin->builtin_long;
lai->primitive_type_vector [c_primitive_type_short] = builtin->builtin_short;
lai->primitive_type_vector [c_primitive_type_char] = builtin->builtin_char;
lai->primitive_type_vector [c_primitive_type_float] = builtin->builtin_float;
lai->primitive_type_vector [c_primitive_type_double] = builtin->builtin_double;
lai->primitive_type_vector [c_primitive_type_void] = builtin->builtin_void;
lai->primitive_type_vector [c_primitive_type_long_long] = builtin->builtin_long_long;
lai->primitive_type_vector [c_primitive_type_signed_char] = builtin->builtin_signed_char;
lai->primitive_type_vector [c_primitive_type_unsigned_char] = builtin->builtin_unsigned_char;
lai->primitive_type_vector [c_primitive_type_unsigned_short] = builtin->builtin_unsigned_short;
lai->primitive_type_vector [c_primitive_type_unsigned_int] = builtin->builtin_unsigned_int;
lai->primitive_type_vector [c_primitive_type_unsigned_long] = builtin->builtin_unsigned_long;
lai->primitive_type_vector [c_primitive_type_unsigned_long_long] = builtin->builtin_unsigned_long_long;
lai->primitive_type_vector [c_primitive_type_long_double] = builtin->builtin_long_double;
lai->primitive_type_vector [c_primitive_type_complex] = builtin->builtin_complex;
lai->primitive_type_vector [c_primitive_type_double_complex] = builtin->builtin_double_complex;
lai->primitive_type_vector [c_primitive_type_decfloat] = builtin->builtin_decfloat;
lai->primitive_type_vector [c_primitive_type_decdouble] = builtin->builtin_decdouble;
lai->primitive_type_vector [c_primitive_type_declong] = builtin->builtin_declong;
lai->bool_type_default = builtin->builtin_int;
}
static const struct exp_descriptor exp_descriptor_c =
{
print_subexp_standard,
operator_length_standard,
op_name_standard,
dump_subexp_body_standard,
evaluate_subexp_c
};
const struct language_defn c_language_defn =
{
"c", /* Language name */
language_c,
range_check_off,
type_check_off,
case_sensitive_on,
array_row_major,
macro_expansion_c,
&exp_descriptor_c,
c_parse,
c_error,
null_post_parser,
c_printchar, /* Print a character constant */
c_printstr, /* Function to print string constant */
c_emit_char, /* Print a single char */
c_print_type, /* Print a type using appropriate syntax */
c_print_typedef, /* Print a typedef using appropriate syntax */
c_val_print, /* Print a value using appropriate syntax */
c_value_print, /* Print a top-level value */
NULL, /* Language specific skip_trampoline */
NULL, /* name_of_this */
basic_lookup_symbol_nonlocal, /* lookup_symbol_nonlocal */
basic_lookup_transparent_type,/* lookup_transparent_type */
NULL, /* Language specific symbol demangler */
NULL, /* Language specific class_name_from_physname */
c_op_print_tab, /* expression operators for printing */
1, /* c-style arrays */
0, /* String lower bound */
default_word_break_characters,
default_make_symbol_completion_list,
c_language_arch_info,
default_print_array_index,
default_pass_by_reference,
c_get_string,
LANG_MAGIC
};
enum cplus_primitive_types {
cplus_primitive_type_int,
cplus_primitive_type_long,
cplus_primitive_type_short,
cplus_primitive_type_char,
cplus_primitive_type_float,
cplus_primitive_type_double,
cplus_primitive_type_void,
cplus_primitive_type_long_long,
cplus_primitive_type_signed_char,
cplus_primitive_type_unsigned_char,
cplus_primitive_type_unsigned_short,
cplus_primitive_type_unsigned_int,
cplus_primitive_type_unsigned_long,
cplus_primitive_type_unsigned_long_long,
cplus_primitive_type_long_double,
cplus_primitive_type_complex,
cplus_primitive_type_double_complex,
cplus_primitive_type_bool,
cplus_primitive_type_decfloat,
cplus_primitive_type_decdouble,
cplus_primitive_type_declong,
nr_cplus_primitive_types
};
static void
cplus_language_arch_info (struct gdbarch *gdbarch,
struct language_arch_info *lai)
{
const struct builtin_type *builtin = builtin_type (gdbarch);
lai->string_char_type = builtin->builtin_char;
lai->primitive_type_vector
= GDBARCH_OBSTACK_CALLOC (gdbarch, nr_cplus_primitive_types + 1,
struct type *);
lai->primitive_type_vector [cplus_primitive_type_int]
= builtin->builtin_int;
lai->primitive_type_vector [cplus_primitive_type_long]
= builtin->builtin_long;
lai->primitive_type_vector [cplus_primitive_type_short]
= builtin->builtin_short;
lai->primitive_type_vector [cplus_primitive_type_char]
= builtin->builtin_char;
lai->primitive_type_vector [cplus_primitive_type_float]
= builtin->builtin_float;
lai->primitive_type_vector [cplus_primitive_type_double]
= builtin->builtin_double;
lai->primitive_type_vector [cplus_primitive_type_void]
= builtin->builtin_void;
lai->primitive_type_vector [cplus_primitive_type_long_long]
= builtin->builtin_long_long;
lai->primitive_type_vector [cplus_primitive_type_signed_char]
= builtin->builtin_signed_char;
lai->primitive_type_vector [cplus_primitive_type_unsigned_char]
= builtin->builtin_unsigned_char;
lai->primitive_type_vector [cplus_primitive_type_unsigned_short]
= builtin->builtin_unsigned_short;
lai->primitive_type_vector [cplus_primitive_type_unsigned_int]
= builtin->builtin_unsigned_int;
lai->primitive_type_vector [cplus_primitive_type_unsigned_long]
= builtin->builtin_unsigned_long;
lai->primitive_type_vector [cplus_primitive_type_unsigned_long_long]
= builtin->builtin_unsigned_long_long;
lai->primitive_type_vector [cplus_primitive_type_long_double]
= builtin->builtin_long_double;
lai->primitive_type_vector [cplus_primitive_type_complex]
= builtin->builtin_complex;
lai->primitive_type_vector [cplus_primitive_type_double_complex]
= builtin->builtin_double_complex;
lai->primitive_type_vector [cplus_primitive_type_bool]
= builtin->builtin_bool;
lai->primitive_type_vector [cplus_primitive_type_decfloat]
= builtin->builtin_decfloat;
lai->primitive_type_vector [cplus_primitive_type_decdouble]
= builtin->builtin_decdouble;
lai->primitive_type_vector [cplus_primitive_type_declong]
= builtin->builtin_declong;
lai->bool_type_symbol = "bool";
lai->bool_type_default = builtin->builtin_bool;
}
const struct language_defn cplus_language_defn =
{
"c++", /* Language name */
language_cplus,
range_check_off,
type_check_off,
case_sensitive_on,
array_row_major,
macro_expansion_c,
&exp_descriptor_c,
c_parse,
c_error,
null_post_parser,
c_printchar, /* Print a character constant */
c_printstr, /* Function to print string constant */
c_emit_char, /* Print a single char */
c_print_type, /* Print a type using appropriate syntax */
c_print_typedef, /* Print a typedef using appropriate syntax */
c_val_print, /* Print a value using appropriate syntax */
c_value_print, /* Print a top-level value */
cplus_skip_trampoline, /* Language specific skip_trampoline */
"this", /* name_of_this */
cp_lookup_symbol_nonlocal, /* lookup_symbol_nonlocal */
cp_lookup_transparent_type, /* lookup_transparent_type */
cplus_demangle, /* Language specific symbol demangler */
cp_class_name_from_physname, /* Language specific class_name_from_physname */
c_op_print_tab, /* expression operators for printing */
1, /* c-style arrays */
0, /* String lower bound */
default_word_break_characters,
default_make_symbol_completion_list,
cplus_language_arch_info,
default_print_array_index,
cp_pass_by_reference,
c_get_string,
LANG_MAGIC
};
const struct language_defn asm_language_defn =
{
"asm", /* Language name */
language_asm,
range_check_off,
type_check_off,
case_sensitive_on,
array_row_major,
macro_expansion_c,
&exp_descriptor_c,
c_parse,
c_error,
null_post_parser,
c_printchar, /* Print a character constant */
c_printstr, /* Function to print string constant */
c_emit_char, /* Print a single char */
c_print_type, /* Print a type using appropriate syntax */
c_print_typedef, /* Print a typedef using appropriate syntax */
c_val_print, /* Print a value using appropriate syntax */
c_value_print, /* Print a top-level value */
NULL, /* Language specific skip_trampoline */
NULL, /* name_of_this */
basic_lookup_symbol_nonlocal, /* lookup_symbol_nonlocal */
basic_lookup_transparent_type,/* lookup_transparent_type */
NULL, /* Language specific symbol demangler */
NULL, /* Language specific class_name_from_physname */
c_op_print_tab, /* expression operators for printing */
1, /* c-style arrays */
0, /* String lower bound */
default_word_break_characters,
default_make_symbol_completion_list,
c_language_arch_info, /* FIXME: la_language_arch_info. */
default_print_array_index,
default_pass_by_reference,
c_get_string,
LANG_MAGIC
};
/* The following language_defn does not represent a real language.
It just provides a minimal support a-la-C that should allow users
to do some simple operations when debugging applications that use
a language currently not supported by GDB. */
const struct language_defn minimal_language_defn =
{
"minimal", /* Language name */
language_minimal,
range_check_off,
type_check_off,
case_sensitive_on,
array_row_major,
macro_expansion_c,
&exp_descriptor_c,
c_parse,
c_error,
null_post_parser,
c_printchar, /* Print a character constant */
c_printstr, /* Function to print string constant */
c_emit_char, /* Print a single char */
c_print_type, /* Print a type using appropriate syntax */
c_print_typedef, /* Print a typedef using appropriate syntax */
c_val_print, /* Print a value using appropriate syntax */
c_value_print, /* Print a top-level value */
NULL, /* Language specific skip_trampoline */
NULL, /* name_of_this */
basic_lookup_symbol_nonlocal, /* lookup_symbol_nonlocal */
basic_lookup_transparent_type,/* lookup_transparent_type */
NULL, /* Language specific symbol demangler */
NULL, /* Language specific class_name_from_physname */
c_op_print_tab, /* expression operators for printing */
1, /* c-style arrays */
0, /* String lower bound */
default_word_break_characters,
default_make_symbol_completion_list,
c_language_arch_info,
default_print_array_index,
default_pass_by_reference,
c_get_string,
LANG_MAGIC
};
void
_initialize_c_language (void)
{
add_language (&c_language_defn);
add_language (&cplus_language_defn);
add_language (&asm_language_defn);
add_language (&minimal_language_defn);
}
|