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
|
/* Parse C expressions for CCCP.
Copyright (C) 1987, 1992, 94 - 97, 1998 Free Software Foundation.
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, 59 Temple Place - Suite 330,
Boston, MA 02111-1307, USA.
In other words, you are welcome to use, share and improve this program.
You are forbidden to forbid anyone else to use, share and improve
what you give them. Help stamp out software-hoarding!
Adapted from expread.y of GDB by Paul Rubin, July 1986. */
/* Parse a C expression from text in a string */
%{
#include "config.h"
#define PRINTF_PROTO(ARGS, m, n) PVPROTO (ARGS) ATTRIBUTE_PRINTF(m, n)
#define PRINTF_PROTO_1(ARGS) PRINTF_PROTO(ARGS, 1, 2)
#include "system.h"
#include <setjmp.h>
/* #define YYDEBUG 1 */
#ifdef MULTIBYTE_CHARS
#include "mbchar.h"
#include <locale.h>
#endif /* MULTIBYTE_CHARS */
typedef unsigned char U_CHAR;
/* This is used for communicating lists of keywords with cccp.c. */
struct arglist {
struct arglist *next;
U_CHAR *name;
int length;
int argno;
};
/* Find the largest host integer type and set its size and type.
Watch out: on some crazy hosts `long' is shorter than `int'. */
#ifndef HOST_WIDE_INT
# if HAVE_INTTYPES_H
# include <inttypes.h>
# define HOST_WIDE_INT intmax_t
# define unsigned_HOST_WIDE_INT uintmax_t
# else
# if (HOST_BITS_PER_LONG <= HOST_BITS_PER_INT && HOST_BITS_PER_LONGLONG <= HOST_BITS_PER_INT)
# define HOST_WIDE_INT int
# else
# if (HOST_BITS_PER_LONGLONG <= HOST_BITS_PER_LONG || ! (defined LONG_LONG_MAX || defined LLONG_MAX))
# define HOST_WIDE_INT long
# else
# define HOST_WIDE_INT long long
# endif
# endif
# endif
#endif
#ifndef unsigned_HOST_WIDE_INT
#define unsigned_HOST_WIDE_INT unsigned HOST_WIDE_INT
#endif
#ifndef CHAR_BIT
#define CHAR_BIT 8
#endif
#ifndef HOST_BITS_PER_WIDE_INT
#define HOST_BITS_PER_WIDE_INT (CHAR_BIT * sizeof (HOST_WIDE_INT))
#endif
HOST_WIDE_INT parse_c_expression PROTO((char *, int));
static int yylex PROTO((void));
static void yyerror PROTO((char *)) __attribute__ ((noreturn));
static HOST_WIDE_INT expression_value;
#ifdef TEST_EXP_READER
static int expression_signedp;
#endif
static jmp_buf parse_return_error;
/* Nonzero means count most punctuation as part of a name. */
static int keyword_parsing = 0;
/* Nonzero means do not evaluate this expression.
This is a count, since unevaluated expressions can nest. */
static int skip_evaluation;
/* Nonzero means warn if undefined identifiers are evaluated. */
static int warn_undef;
/* some external tables of character types */
extern unsigned char is_idstart[], is_idchar[], is_space[];
/* Flag for -pedantic. */
extern int pedantic;
/* Flag for -traditional. */
extern int traditional;
/* Flag for -lang-c89. */
extern int c89;
#ifndef CHAR_TYPE_SIZE
#define CHAR_TYPE_SIZE BITS_PER_UNIT
#endif
#ifndef INT_TYPE_SIZE
#define INT_TYPE_SIZE BITS_PER_WORD
#endif
#ifndef LONG_TYPE_SIZE
#define LONG_TYPE_SIZE BITS_PER_WORD
#endif
#ifndef WCHAR_TYPE_SIZE
#define WCHAR_TYPE_SIZE INT_TYPE_SIZE
#endif
#ifndef MAX_CHAR_TYPE_SIZE
#define MAX_CHAR_TYPE_SIZE CHAR_TYPE_SIZE
#endif
#ifndef MAX_INT_TYPE_SIZE
#define MAX_INT_TYPE_SIZE INT_TYPE_SIZE
#endif
#ifndef MAX_LONG_TYPE_SIZE
#define MAX_LONG_TYPE_SIZE LONG_TYPE_SIZE
#endif
#ifndef MAX_WCHAR_TYPE_SIZE
#define MAX_WCHAR_TYPE_SIZE WCHAR_TYPE_SIZE
#endif
#define MAX_CHAR_TYPE_MASK (MAX_CHAR_TYPE_SIZE < HOST_BITS_PER_WIDE_INT \
? (~ (~ (HOST_WIDE_INT) 0 << MAX_CHAR_TYPE_SIZE)) \
: ~ (HOST_WIDE_INT) 0)
#define MAX_WCHAR_TYPE_MASK (MAX_WCHAR_TYPE_SIZE < HOST_BITS_PER_WIDE_INT \
? ~ (~ (HOST_WIDE_INT) 0 << MAX_WCHAR_TYPE_SIZE) \
: ~ (HOST_WIDE_INT) 0)
/* Suppose A1 + B1 = SUM1, using 2's complement arithmetic ignoring overflow.
Suppose A, B and SUM have the same respective signs as A1, B1, and SUM1.
Suppose SIGNEDP is negative if the result is signed, zero if unsigned.
Then this yields nonzero if overflow occurred during the addition.
Overflow occurs if A and B have the same sign, but A and SUM differ in sign,
and SIGNEDP is negative.
Use `^' to test whether signs differ, and `< 0' to isolate the sign. */
#define overflow_sum_sign(a, b, sum, signedp) \
((~((a) ^ (b)) & ((a) ^ (sum)) & (signedp)) < 0)
struct constant;
GENERIC_PTR xmalloc PROTO((size_t));
HOST_WIDE_INT parse_escape PROTO((char **, HOST_WIDE_INT));
int check_assertion PROTO((U_CHAR *, int, int, struct arglist *));
struct hashnode *lookup PROTO((U_CHAR *, int, int));
void error PRINTF_PROTO_1((char *, ...));
void pedwarn PRINTF_PROTO_1((char *, ...));
void warning PRINTF_PROTO_1((char *, ...));
static int parse_number PROTO((int));
static HOST_WIDE_INT left_shift PROTO((struct constant *, unsigned_HOST_WIDE_INT));
static HOST_WIDE_INT right_shift PROTO((struct constant *, unsigned_HOST_WIDE_INT));
static void integer_overflow PROTO((void));
/* `signedp' values */
#define SIGNED (~0)
#define UNSIGNED 0
%}
%union {
struct constant {HOST_WIDE_INT value; int signedp;} integer;
struct name {U_CHAR *address; int length;} name;
struct arglist *keywords;
}
%type <integer> exp exp1 start
%type <keywords> keywords
%token <integer> INT CHAR
%token <name> NAME
%token <integer> ERROR
%right '?' ':'
%left ','
%left OR
%left AND
%left '|'
%left '^'
%left '&'
%left EQUAL NOTEQUAL
%left '<' '>' LEQ GEQ
%left LSH RSH
%left '+' '-'
%left '*' '/' '%'
%right UNARY
/* %expect 40 */
%%
start : exp1
{
expression_value = $1.value;
#ifdef TEST_EXP_READER
expression_signedp = $1.signedp;
#endif
}
;
/* Expressions, including the comma operator. */
exp1 : exp
| exp1 ',' exp
{ if (pedantic)
pedwarn ("comma operator in operand of `#if'");
$$ = $3; }
;
/* Expressions, not including the comma operator. */
exp : '-' exp %prec UNARY
{ $$.value = - $2.value;
$$.signedp = $2.signedp;
if (($$.value & $2.value & $$.signedp) < 0)
integer_overflow (); }
| '!' exp %prec UNARY
{ $$.value = ! $2.value;
$$.signedp = SIGNED; }
| '+' exp %prec UNARY
{ $$ = $2; }
| '~' exp %prec UNARY
{ $$.value = ~ $2.value;
$$.signedp = $2.signedp; }
| '#' NAME
{ $$.value = check_assertion ($2.address, $2.length,
0, NULL_PTR);
$$.signedp = SIGNED; }
| '#' NAME
{ keyword_parsing = 1; }
'(' keywords ')'
{ $$.value = check_assertion ($2.address, $2.length,
1, $5);
keyword_parsing = 0;
$$.signedp = SIGNED; }
| '(' exp1 ')'
{ $$ = $2; }
;
/* Binary operators in order of decreasing precedence. */
exp : exp '*' exp
{ $$.signedp = $1.signedp & $3.signedp;
if ($$.signedp)
{
$$.value = $1.value * $3.value;
if ($1.value
&& ($$.value / $1.value != $3.value
|| ($$.value & $1.value & $3.value) < 0))
integer_overflow ();
}
else
$$.value = ((unsigned_HOST_WIDE_INT) $1.value
* $3.value); }
| exp '/' exp
{ if ($3.value == 0)
{
if (!skip_evaluation)
error ("division by zero in #if");
$3.value = 1;
}
$$.signedp = $1.signedp & $3.signedp;
if ($$.signedp)
{
$$.value = $1.value / $3.value;
if (($$.value & $1.value & $3.value) < 0)
integer_overflow ();
}
else
$$.value = ((unsigned_HOST_WIDE_INT) $1.value
/ $3.value); }
| exp '%' exp
{ if ($3.value == 0)
{
if (!skip_evaluation)
error ("division by zero in #if");
$3.value = 1;
}
$$.signedp = $1.signedp & $3.signedp;
if ($$.signedp)
$$.value = $1.value % $3.value;
else
$$.value = ((unsigned_HOST_WIDE_INT) $1.value
% $3.value); }
| exp '+' exp
{ $$.value = $1.value + $3.value;
$$.signedp = $1.signedp & $3.signedp;
if (overflow_sum_sign ($1.value, $3.value,
$$.value, $$.signedp))
integer_overflow (); }
| exp '-' exp
{ $$.value = $1.value - $3.value;
$$.signedp = $1.signedp & $3.signedp;
if (overflow_sum_sign ($$.value, $3.value,
$1.value, $$.signedp))
integer_overflow (); }
| exp LSH exp
{ $$.signedp = $1.signedp;
if (($3.value & $3.signedp) < 0)
$$.value = right_shift (&$1, -$3.value);
else
$$.value = left_shift (&$1, $3.value); }
| exp RSH exp
{ $$.signedp = $1.signedp;
if (($3.value & $3.signedp) < 0)
$$.value = left_shift (&$1, -$3.value);
else
$$.value = right_shift (&$1, $3.value); }
| exp EQUAL exp
{ $$.value = ($1.value == $3.value);
$$.signedp = SIGNED; }
| exp NOTEQUAL exp
{ $$.value = ($1.value != $3.value);
$$.signedp = SIGNED; }
| exp LEQ exp
{ $$.signedp = SIGNED;
if ($1.signedp & $3.signedp)
$$.value = $1.value <= $3.value;
else
$$.value = ((unsigned_HOST_WIDE_INT) $1.value
<= $3.value); }
| exp GEQ exp
{ $$.signedp = SIGNED;
if ($1.signedp & $3.signedp)
$$.value = $1.value >= $3.value;
else
$$.value = ((unsigned_HOST_WIDE_INT) $1.value
>= $3.value); }
| exp '<' exp
{ $$.signedp = SIGNED;
if ($1.signedp & $3.signedp)
$$.value = $1.value < $3.value;
else
$$.value = ((unsigned_HOST_WIDE_INT) $1.value
< $3.value); }
| exp '>' exp
{ $$.signedp = SIGNED;
if ($1.signedp & $3.signedp)
$$.value = $1.value > $3.value;
else
$$.value = ((unsigned_HOST_WIDE_INT) $1.value
> $3.value); }
| exp '&' exp
{ $$.value = $1.value & $3.value;
$$.signedp = $1.signedp & $3.signedp; }
| exp '^' exp
{ $$.value = $1.value ^ $3.value;
$$.signedp = $1.signedp & $3.signedp; }
| exp '|' exp
{ $$.value = $1.value | $3.value;
$$.signedp = $1.signedp & $3.signedp; }
| exp AND
{ skip_evaluation += !$1.value; }
exp
{ skip_evaluation -= !$1.value;
$$.value = ($1.value && $4.value);
$$.signedp = SIGNED; }
| exp OR
{ skip_evaluation += !!$1.value; }
exp
{ skip_evaluation -= !!$1.value;
$$.value = ($1.value || $4.value);
$$.signedp = SIGNED; }
| exp '?'
{ skip_evaluation += !$1.value; }
exp ':'
{ skip_evaluation += !!$1.value - !$1.value; }
exp
{ skip_evaluation -= !!$1.value;
$$.value = $1.value ? $4.value : $7.value;
$$.signedp = $4.signedp & $7.signedp; }
| INT
{ $$ = yylval.integer; }
| CHAR
{ $$ = yylval.integer; }
| NAME
{ if (warn_undef && !skip_evaluation)
warning ("`%.*s' is not defined",
$1.length, $1.address);
$$.value = 0;
$$.signedp = SIGNED; }
;
keywords :
{ $$ = 0; }
| '(' keywords ')' keywords
{ struct arglist *temp;
$$ = (struct arglist *) xmalloc (sizeof (struct arglist));
$$->next = $2;
$$->name = (U_CHAR *) "(";
$$->length = 1;
temp = $$;
while (temp != 0 && temp->next != 0)
temp = temp->next;
temp->next = (struct arglist *) xmalloc (sizeof (struct arglist));
temp->next->next = $4;
temp->next->name = (U_CHAR *) ")";
temp->next->length = 1; }
| NAME keywords
{ $$ = (struct arglist *) xmalloc (sizeof (struct arglist));
$$->name = $1.address;
$$->length = $1.length;
$$->next = $2; }
;
%%
/* During parsing of a C expression, the pointer to the next character
is in this variable. */
static char *lexptr;
/* Take care of parsing a number (anything that starts with a digit).
Set yylval and return the token type; update lexptr.
LEN is the number of characters in it. */
/* maybe needs to actually deal with floating point numbers */
static int
parse_number (olen)
int olen;
{
register char *p = lexptr;
register int c;
register unsigned_HOST_WIDE_INT n = 0, nd, max_over_base;
register int base = 10;
register int len = olen;
register int overflow = 0;
register int digit, largest_digit = 0;
int spec_long = 0;
yylval.integer.signedp = SIGNED;
if (*p == '0') {
base = 8;
if (len >= 3 && (p[1] == 'x' || p[1] == 'X')) {
p += 2;
base = 16;
len -= 2;
}
}
max_over_base = (unsigned_HOST_WIDE_INT) -1 / base;
for (; len > 0; len--) {
c = *p++;
if (c >= '0' && c <= '9')
digit = c - '0';
else if (base == 16 && c >= 'a' && c <= 'f')
digit = c - 'a' + 10;
else if (base == 16 && c >= 'A' && c <= 'F')
digit = c - 'A' + 10;
else {
/* `l' means long, and `u' means unsigned. */
while (1) {
if (c == 'l' || c == 'L')
{
if (!pedantic < spec_long)
yyerror ("too many `l's in integer constant");
spec_long++;
}
else if (c == 'u' || c == 'U')
{
if (! yylval.integer.signedp)
yyerror ("two `u's in integer constant");
yylval.integer.signedp = UNSIGNED;
}
else {
if (c == '.' || c == 'e' || c == 'E' || c == 'p' || c == 'P')
yyerror ("Floating point numbers not allowed in #if expressions");
else {
char *buf = (char *) alloca (p - lexptr + 40);
sprintf (buf, "missing white space after number `%.*s'",
(int) (p - lexptr - 1), lexptr);
yyerror (buf);
}
}
if (--len == 0)
break;
c = *p++;
}
/* Don't look for any more digits after the suffixes. */
break;
}
if (largest_digit < digit)
largest_digit = digit;
nd = n * base + digit;
overflow |= (max_over_base < n) | (nd < n);
n = nd;
}
if (base <= largest_digit)
pedwarn ("integer constant contains digits beyond the radix");
if (overflow)
pedwarn ("integer constant out of range");
/* If too big to be signed, consider it unsigned. */
if (((HOST_WIDE_INT) n & yylval.integer.signedp) < 0)
{
if (base == 10)
warning ("integer constant is so large that it is unsigned");
yylval.integer.signedp = UNSIGNED;
}
lexptr = p;
yylval.integer.value = n;
return INT;
}
struct token {
char *operator;
int token;
};
static struct token tokentab2[] = {
{"&&", AND},
{"||", OR},
{"<<", LSH},
{">>", RSH},
{"==", EQUAL},
{"!=", NOTEQUAL},
{"<=", LEQ},
{">=", GEQ},
{"++", ERROR},
{"--", ERROR},
{NULL, ERROR}
};
/* Read one token, getting characters through lexptr. */
static int
yylex ()
{
register int c;
register int namelen;
register unsigned char *tokstart;
register struct token *toktab;
int wide_flag;
HOST_WIDE_INT mask;
retry:
tokstart = (unsigned char *) lexptr;
c = *tokstart;
/* See if it is a special token of length 2. */
if (! keyword_parsing)
for (toktab = tokentab2; toktab->operator != NULL; toktab++)
if (c == *toktab->operator && tokstart[1] == toktab->operator[1]) {
lexptr += 2;
if (toktab->token == ERROR)
{
char *buf = (char *) alloca (40);
sprintf (buf, "`%s' not allowed in operand of `#if'", toktab->operator);
yyerror (buf);
}
return toktab->token;
}
switch (c) {
case '\n':
return 0;
case ' ':
case '\t':
case '\r':
lexptr++;
goto retry;
case 'L':
/* Capital L may start a wide-string or wide-character constant. */
if (lexptr[1] == '\'')
{
lexptr++;
wide_flag = 1;
mask = MAX_WCHAR_TYPE_MASK;
goto char_constant;
}
if (lexptr[1] == '"')
{
lexptr++;
wide_flag = 1;
mask = MAX_WCHAR_TYPE_MASK;
goto string_constant;
}
break;
case '\'':
wide_flag = 0;
mask = MAX_CHAR_TYPE_MASK;
char_constant:
lexptr++;
if (keyword_parsing) {
char *start_ptr = lexptr - 1;
while (1) {
c = *lexptr++;
if (c == '\\')
c = parse_escape (&lexptr, mask);
else if (c == '\'')
break;
}
yylval.name.address = tokstart;
yylval.name.length = lexptr - start_ptr;
return NAME;
}
/* This code for reading a character constant
handles multicharacter constants and wide characters.
It is mostly copied from c-lex.c. */
{
register HOST_WIDE_INT result = 0;
register int num_chars = 0;
int chars_seen = 0;
unsigned width = MAX_CHAR_TYPE_SIZE;
int max_chars;
#ifdef MULTIBYTE_CHARS
int longest_char = local_mb_cur_max ();
char *token_buffer = (char *) alloca (longest_char);
(void) local_mbtowc (NULL_PTR, NULL_PTR, 0);
#endif
max_chars = MAX_LONG_TYPE_SIZE / width;
if (wide_flag)
width = MAX_WCHAR_TYPE_SIZE;
while (1)
{
c = *lexptr++;
if (c == '\'' || c == EOF)
break;
++chars_seen;
if (c == '\\')
{
c = parse_escape (&lexptr, mask);
}
else
{
#ifdef MULTIBYTE_CHARS
wchar_t wc;
int i;
int char_len = -1;
for (i = 1; i <= longest_char; ++i)
{
token_buffer[i - 1] = c;
char_len = local_mbtowc (& wc, token_buffer, i);
if (char_len != -1)
break;
c = *lexptr++;
}
if (char_len > 1)
{
/* mbtowc sometimes needs an extra char before accepting */
if (char_len < i)
lexptr--;
if (! wide_flag)
{
/* Merge character into result; ignore excess chars. */
for (i = 1; i <= char_len; ++i)
{
if (i > max_chars)
break;
if (width < HOST_BITS_PER_INT)
result = (result << width)
| (token_buffer[i - 1]
& ((1 << width) - 1));
else
result = token_buffer[i - 1];
}
num_chars += char_len;
continue;
}
}
else
{
if (char_len == -1)
warning ("Ignoring invalid multibyte character");
}
if (wide_flag)
c = wc;
#endif /* ! MULTIBYTE_CHARS */
}
if (wide_flag)
{
if (chars_seen == 1) /* only keep the first one */
result = c;
continue;
}
/* Merge character into result; ignore excess chars. */
num_chars++;
if (num_chars <= max_chars)
{
if (width < HOST_BITS_PER_INT)
result = (result << width) | (c & ((1 << width) - 1));
else
result = c;
}
}
if (c != '\'')
error ("malformatted character constant");
else if (chars_seen == 0)
error ("empty character constant");
else if (num_chars > max_chars)
{
num_chars = max_chars;
error ("character constant too long");
}
else if (chars_seen != 1 && ! traditional)
warning ("multi-character character constant");
/* If char type is signed, sign-extend the constant. */
if (! wide_flag)
{
int num_bits = num_chars * width;
if (num_bits == 0)
/* We already got an error; avoid invalid shift. */
yylval.integer.value = 0;
else if (lookup ((U_CHAR *) "__CHAR_UNSIGNED__",
sizeof ("__CHAR_UNSIGNED__") - 1, -1)
|| ((result >> (num_bits - 1)) & 1) == 0)
yylval.integer.value
= result & (~ (unsigned_HOST_WIDE_INT) 0
>> (HOST_BITS_PER_WIDE_INT - num_bits));
else
yylval.integer.value
= result | ~(~ (unsigned_HOST_WIDE_INT) 0
>> (HOST_BITS_PER_WIDE_INT - num_bits));
}
else
{
yylval.integer.value = result;
}
}
/* This is always a signed type. */
yylval.integer.signedp = SIGNED;
return CHAR;
/* some of these chars are invalid in constant expressions;
maybe do something about them later */
case '/':
case '+':
case '-':
case '*':
case '%':
case '|':
case '&':
case '^':
case '~':
case '!':
case '@':
case '<':
case '>':
case '[':
case ']':
case '.':
case '?':
case ':':
case '=':
case '{':
case '}':
case ',':
case '#':
if (keyword_parsing)
break;
case '(':
case ')':
lexptr++;
return c;
case '"':
mask = MAX_CHAR_TYPE_MASK;
string_constant:
if (keyword_parsing) {
char *start_ptr = lexptr;
lexptr++;
while (1) {
c = *lexptr++;
if (c == '\\')
c = parse_escape (&lexptr, mask);
else if (c == '"')
break;
}
yylval.name.address = tokstart;
yylval.name.length = lexptr - start_ptr;
return NAME;
}
yyerror ("string constants not allowed in #if expressions");
return ERROR;
}
if (c >= '0' && c <= '9' && !keyword_parsing) {
/* It's a number */
for (namelen = 1; ; namelen++) {
int d = tokstart[namelen];
if (! ((is_idchar[d] || d == '.')
|| ((d == '-' || d == '+')
&& (c == 'e' || c == 'E'
|| ((c == 'p' || c == 'P') && ! c89))
&& ! traditional)))
break;
c = d;
}
return parse_number (namelen);
}
/* It is a name. See how long it is. */
if (keyword_parsing) {
for (namelen = 0;; namelen++) {
if (is_space[tokstart[namelen]])
break;
if (tokstart[namelen] == '(' || tokstart[namelen] == ')')
break;
if (tokstart[namelen] == '"' || tokstart[namelen] == '\'')
break;
}
} else {
if (!is_idstart[c]) {
yyerror ("Invalid token in expression");
return ERROR;
}
for (namelen = 0; is_idchar[tokstart[namelen]]; namelen++)
;
}
lexptr += namelen;
yylval.name.address = tokstart;
yylval.name.length = namelen;
return NAME;
}
/* Parse a C escape sequence. STRING_PTR points to a variable
containing a pointer to the string to parse. That pointer
is updated past the characters we use. The value of the
escape sequence is returned.
RESULT_MASK is used to mask out the result;
an error is reported if bits are lost thereby.
A negative value means the sequence \ newline was seen,
which is supposed to be equivalent to nothing at all.
If \ is followed by a null character, we return a negative
value and leave the string pointer pointing at the null character.
If \ is followed by 000, we return 0 and leave the string pointer
after the zeros. A value of 0 does not mean end of string. */
HOST_WIDE_INT
parse_escape (string_ptr, result_mask)
char **string_ptr;
HOST_WIDE_INT result_mask;
{
register int c = *(*string_ptr)++;
switch (c)
{
case 'a':
return TARGET_BELL;
case 'b':
return TARGET_BS;
case 'e':
case 'E':
if (pedantic)
pedwarn ("non-ANSI-standard escape sequence, `\\%c'", c);
return 033;
case 'f':
return TARGET_FF;
case 'n':
return TARGET_NEWLINE;
case 'r':
return TARGET_CR;
case 't':
return TARGET_TAB;
case 'v':
return TARGET_VT;
case '\n':
return -2;
case 0:
(*string_ptr)--;
return 0;
case '0':
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
{
register HOST_WIDE_INT i = c - '0';
register int count = 0;
while (++count < 3)
{
c = *(*string_ptr)++;
if (c >= '0' && c <= '7')
i = (i << 3) + c - '0';
else
{
(*string_ptr)--;
break;
}
}
if (i != (i & result_mask))
{
i &= result_mask;
pedwarn ("octal escape sequence out of range");
}
return i;
}
case 'x':
{
register unsigned_HOST_WIDE_INT i = 0, overflow = 0;
register int digits_found = 0, digit;
for (;;)
{
c = *(*string_ptr)++;
if (c >= '0' && c <= '9')
digit = c - '0';
else if (c >= 'a' && c <= 'f')
digit = c - 'a' + 10;
else if (c >= 'A' && c <= 'F')
digit = c - 'A' + 10;
else
{
(*string_ptr)--;
break;
}
overflow |= i ^ (i << 4 >> 4);
i = (i << 4) + digit;
digits_found = 1;
}
if (!digits_found)
yyerror ("\\x used with no following hex digits");
if (overflow | (i != (i & result_mask)))
{
i &= result_mask;
pedwarn ("hex escape sequence out of range");
}
return i;
}
default:
return c;
}
}
static void
yyerror (s)
char *s;
{
error ("%s", s);
skip_evaluation = 0;
longjmp (parse_return_error, 1);
}
static void
integer_overflow ()
{
if (!skip_evaluation && pedantic)
pedwarn ("integer overflow in preprocessor expression");
}
static HOST_WIDE_INT
left_shift (a, b)
struct constant *a;
unsigned_HOST_WIDE_INT b;
{
/* It's unclear from the C standard whether shifts can overflow.
The following code ignores overflow; perhaps a C standard
interpretation ruling is needed. */
if (b >= HOST_BITS_PER_WIDE_INT)
return 0;
else
return (unsigned_HOST_WIDE_INT) a->value << b;
}
static HOST_WIDE_INT
right_shift (a, b)
struct constant *a;
unsigned_HOST_WIDE_INT b;
{
if (b >= HOST_BITS_PER_WIDE_INT)
return a->signedp ? a->value >> (HOST_BITS_PER_WIDE_INT - 1) : 0;
else if (a->signedp)
return a->value >> b;
else
return (unsigned_HOST_WIDE_INT) a->value >> b;
}
/* This page contains the entry point to this file. */
/* Parse STRING as an expression, and complain if this fails
to use up all of the contents of STRING.
STRING may contain '\0' bytes; it is terminated by the first '\n'
outside a string constant, so that we can diagnose '\0' properly.
If WARN_UNDEFINED is nonzero, warn if undefined identifiers are evaluated.
We do not support C comments. They should be removed before
this function is called. */
HOST_WIDE_INT
parse_c_expression (string, warn_undefined)
char *string;
int warn_undefined;
{
lexptr = string;
warn_undef = warn_undefined;
/* if there is some sort of scanning error, just return 0 and assume
the parsing routine has printed an error message somewhere.
there is surely a better thing to do than this. */
if (setjmp (parse_return_error))
return 0;
if (yyparse () != 0)
abort ();
if (*lexptr != '\n')
error ("Junk after end of expression.");
return expression_value; /* set by yyparse () */
}
#ifdef TEST_EXP_READER
#if YYDEBUG
extern int yydebug;
#endif
int pedantic;
int traditional;
int main PROTO((int, char **));
static void initialize_random_junk PROTO((void));
static void print_unsigned_host_wide_int PROTO((unsigned_HOST_WIDE_INT));
/* Main program for testing purposes. */
int
main (argc, argv)
int argc;
char **argv;
{
int n, c;
char buf[1024];
unsigned_HOST_WIDE_INT u;
pedantic = 1 < argc;
traditional = 2 < argc;
#if YYDEBUG
yydebug = 3 < argc;
#endif
initialize_random_junk ();
for (;;) {
printf ("enter expression: ");
n = 0;
while ((buf[n] = c = getchar ()) != '\n' && c != EOF)
n++;
if (c == EOF)
break;
parse_c_expression (buf, 1);
printf ("parser returned ");
u = (unsigned_HOST_WIDE_INT) expression_value;
if (expression_value < 0 && expression_signedp) {
u = -u;
printf ("-");
}
if (u == 0)
printf ("0");
else
print_unsigned_host_wide_int (u);
if (! expression_signedp)
printf("u");
printf ("\n");
}
return 0;
}
static void
print_unsigned_host_wide_int (u)
unsigned_HOST_WIDE_INT u;
{
if (u) {
print_unsigned_host_wide_int (u / 10);
putchar ('0' + (int) (u % 10));
}
}
/* table to tell if char can be part of a C identifier. */
unsigned char is_idchar[256];
/* table to tell if char can be first char of a c identifier. */
unsigned char is_idstart[256];
/* table to tell if c is horizontal or vertical space. */
unsigned char is_space[256];
/*
* initialize random junk in the hash table and maybe other places
*/
static void
initialize_random_junk ()
{
register int i;
/*
* Set up is_idchar and is_idstart tables. These should be
* faster than saying (is_alpha (c) || c == '_'), etc.
* Must do set up these things before calling any routines tthat
* refer to them.
*/
for (i = 'a'; i <= 'z'; i++) {
++is_idchar[i - 'a' + 'A'];
++is_idchar[i];
++is_idstart[i - 'a' + 'A'];
++is_idstart[i];
}
for (i = '0'; i <= '9'; i++)
++is_idchar[i];
++is_idchar['_'];
++is_idstart['_'];
++is_idchar['$'];
++is_idstart['$'];
++is_space[' '];
++is_space['\t'];
++is_space['\v'];
++is_space['\f'];
++is_space['\n'];
++is_space['\r'];
}
void
error VPROTO ((char * msg, ...))
{
#ifndef ANSI_PROTOTYPES
char * msg;
#endif
va_list args;
VA_START (args, msg);
#ifndef ANSI_PROTOTYPES
msg = va_arg (args, char *);
#endif
fprintf (stderr, "error: ");
vfprintf (stderr, msg, args);
fprintf (stderr, "\n");
va_end (args);
}
void
pedwarn VPROTO ((char * msg, ...))
{
#ifndef ANSI_PROTOTYPES
char * msg;
#endif
va_list args;
VA_START (args, msg);
#ifndef ANSI_PROTOTYPES
msg = va_arg (args, char *);
#endif
fprintf (stderr, "pedwarn: ");
vfprintf (stderr, msg, args);
fprintf (stderr, "\n");
va_end (args);
}
void
warning VPROTO ((char * msg, ...))
{
#ifndef ANSI_PROTOTYPES
char * msg;
#endif
va_list args;
VA_START (args, msg);
#ifndef ANSI_PROTOTYPES
msg = va_arg (args, char *);
#endif
fprintf (stderr, "warning: ");
vfprintf (stderr, msg, args);
fprintf (stderr, "\n");
va_end (args);
}
int
check_assertion (name, sym_length, tokens_specified, tokens)
U_CHAR *name;
int sym_length;
int tokens_specified;
struct arglist *tokens;
{
return 0;
}
struct hashnode *
lookup (name, len, hash)
U_CHAR *name;
int len;
int hash;
{
return (DEFAULT_SIGNED_CHAR) ? 0 : ((struct hashnode *) -1);
}
GENERIC_PTR
xmalloc (size)
size_t size;
{
return (GENERIC_PTR) malloc (size);
}
#endif
|