-
Notifications
You must be signed in to change notification settings - Fork 0
/
field.c
1691 lines (1489 loc) · 43.5 KB
/
field.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* field.c - routines for dealing with fields and record parsing
*/
/*
* Copyright (C) 1986, 1988, 1989, 1991-2021 the Free Software Foundation, Inc.
*
* This file is part of GAWK, the GNU implementation of the
* AWK Programming Language.
*
* GAWK 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.
*
* GAWK 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
*/
#include "awk.h"
/*
* In case that the system doesn't have isblank().
* Don't bother with autoconf ifdef junk, just force it.
* See dfa.c and regex_internal.h and regcomp.c. Bleah.
*/
static int
is_blank(int c)
{
return c == ' ' || c == '\t';
}
typedef void (* Setfunc)(long, char *, long, NODE *);
/* is the API currently overriding the default parsing mechanism? */
static bool api_parser_override = false;
typedef long (*parse_field_func_t)(long, char **, int, NODE *,
Regexp *, Setfunc, NODE *, NODE *, bool);
static parse_field_func_t parse_field;
/*
* N.B. The normal_parse_field function pointer contains the parse_field value
* that should be used except when API field parsing is overriding the default
* field parsing mechanism.
*/
static parse_field_func_t normal_parse_field;
static long re_parse_field(long, char **, int, NODE *,
Regexp *, Setfunc, NODE *, NODE *, bool);
static long def_parse_field(long, char **, int, NODE *,
Regexp *, Setfunc, NODE *, NODE *, bool);
static long null_parse_field(long, char **, int, NODE *,
Regexp *, Setfunc, NODE *, NODE *, bool);
static long sc_parse_field(long, char **, int, NODE *,
Regexp *, Setfunc, NODE *, NODE *, bool);
static long fw_parse_field(long, char **, int, NODE *,
Regexp *, Setfunc, NODE *, NODE *, bool);
static const awk_fieldwidth_info_t *api_fw = NULL;
static long fpat_parse_field(long, char **, int, NODE *,
Regexp *, Setfunc, NODE *, NODE *, bool);
static void set_element(long num, char * str, long len, NODE *arr);
static void grow_fields_arr(long num);
static void set_field(long num, char *str, long len, NODE *dummy);
static void purge_record(void);
static char *parse_extent; /* marks where to restart parse of record */
static long parse_high_water = 0; /* field number that we have parsed so far */
static long nf_high_water = 0; /* size of fields_arr */
static bool resave_fs;
static NODE *save_FS; /* save current value of FS when line is read,
* to be used in deferred parsing
*/
static NODE *save_FPAT; /* save current value of FPAT when line is read,
* to be used in deferred parsing
*/
static awk_fieldwidth_info_t *FIELDWIDTHS = NULL;
NODE **fields_arr; /* array of pointers to the field nodes */
bool field0_valid; /* $(>0) has not been changed yet */
static int default_FS; /* true when FS == " " */
static Regexp *FS_re_yes_case = NULL;
static Regexp *FS_re_no_case = NULL;
static Regexp *FS_regexp = NULL;
static Regexp *FPAT_re_yes_case = NULL;
static Regexp *FPAT_re_no_case = NULL;
static Regexp *FPAT_regexp = NULL;
NODE *Null_field = NULL;
#define clear_mpfr(n) ((n)->flags &= ~(MPFN | MPZN | NUMCUR))
/* init_fields --- set up the fields array to start with */
void
init_fields()
{
emalloc(fields_arr, NODE **, sizeof(NODE *), "init_fields");
fields_arr[0] = make_string("", 0);
fields_arr[0]->flags |= NULL_FIELD;
parse_extent = fields_arr[0]->stptr;
save_FS = dupnode(FS_node->var_value);
Null_field = make_string("", 0);
Null_field->flags = (STRCUR|STRING|NULL_FIELD); /* do not set MALLOC */
field0_valid = true;
}
/* grow_fields --- acquire new fields as needed */
static void
grow_fields_arr(long num)
{
int t;
NODE *n;
erealloc(fields_arr, NODE **, (num + 1) * sizeof(NODE *), "grow_fields_arr");
for (t = nf_high_water + 1; t <= num; t++) {
getnode(n);
*n = *Null_field;
fields_arr[t] = n;
}
nf_high_water = num;
}
/* set_field --- set the value of a particular field */
/*ARGSUSED*/
static void
set_field(long num,
char *str,
long len,
NODE *dummy ATTRIBUTE_UNUSED) /* just to make interface same as set_element */
{
NODE *n;
if (num > nf_high_water)
grow_fields_arr(num);
n = fields_arr[num];
n->stptr = str;
n->stlen = len;
n->flags = (STRCUR|STRING|USER_INPUT); /* do not set MALLOC */
}
/* rebuild_record --- Someone assigned a value to $(something).
Fix up $0 to be right */
void
rebuild_record()
{
/*
* use explicit unsigned longs for lengths, in case
* a size_t isn't big enough.
*/
unsigned long tlen;
NODE *tmp;
char *ops;
char *cops;
long i;
assert(NF != -1);
tlen = 0;
for (i = NF; i > 0; i--) {
tmp = fields_arr[i];
tmp = force_string(tmp);
tlen += tmp->stlen;
}
tlen += (NF - 1) * OFSlen;
if ((long) tlen < 0)
tlen = 0;
emalloc(ops, char *, tlen + 1, "rebuild_record");
cops = ops;
ops[0] = '\0';
for (i = 1; i <= NF; i++) {
free_wstr(fields_arr[i]);
tmp = fields_arr[i];
/* copy field */
if (tmp->stlen == 1)
*cops++ = tmp->stptr[0];
else if (tmp->stlen != 0) {
memcpy(cops, tmp->stptr, tmp->stlen);
cops += tmp->stlen;
}
/* copy OFS */
if (i != NF) {
if (OFSlen == 1)
*cops++ = *OFS;
else if (OFSlen != 0) {
memcpy(cops, OFS, OFSlen);
cops += OFSlen;
}
}
}
tmp = make_str_node(ops, tlen, ALREADY_MALLOCED);
/*
* Since we are about to unref fields_arr[0], we want to find
* any fields that still point into it, and have them point
* into the new field zero. This has to be done intelligently,
* so that unrefing a field doesn't try to unref into the old $0.
*/
for (cops = ops, i = 1; i <= NF; i++) {
NODE *r = fields_arr[i];
/*
* There is no reason to copy malloc'ed fields to point into
* the new $0 buffer, although that's how previous versions did
* it. It seems faster to leave the malloc'ed fields in place.
*/
if (r->stlen > 0 && (r->flags & MALLOC) == 0) {
NODE *n;
getnode(n);
*n = *r;
if (r->valref > 1) {
/*
* This can and does happen. It seems clear that
* we can't leave r's stptr pointing into the
* old $0 buffer that we are about to unref.
*/
emalloc(r->stptr, char *, r->stlen + 1, "rebuild_record");
memcpy(r->stptr, cops, r->stlen);
r->stptr[r->stlen] = '\0';
r->flags |= MALLOC;
n->valref = 1; // reset in the new field to start it off correctly!
}
n->stptr = cops;
clear_mpfr(n);
unref(r);
fields_arr[i] = n;
assert((n->flags & WSTRCUR) == 0);
}
cops += fields_arr[i]->stlen + OFSlen;
}
assert((fields_arr[0]->flags & MALLOC) == 0
? fields_arr[0]->valref == 1
: true);
unref(fields_arr[0]);
fields_arr[0] = tmp;
field0_valid = true;
}
/*
* set_record:
* setup $0, but defer parsing rest of line until reference is made to $(>0)
* or to NF. At that point, parse only as much as necessary.
*
* Manage a private buffer for the contents of $0. Doing so keeps us safe
* if `getline var' decides to rearrange the contents of the IOBUF that
* $0 might have been pointing into. The cost is the copying of the buffer;
* but better correct than fast.
*/
void
set_record(const char *buf, int cnt, const awk_fieldwidth_info_t *fw)
{
NODE *n;
static char *databuf;
static unsigned long databuf_size;
#define INITIAL_SIZE 512
#define MAX_SIZE ((unsigned long) ~0) /* maximally portable ... */
purge_record();
/* buffer management: */
if (databuf_size == 0) { /* first time */
ezalloc(databuf, char *, INITIAL_SIZE, "set_record");
databuf_size = INITIAL_SIZE;
}
/*
* Make sure there's enough room. Since we sometimes need
* to place a sentinel at the end, we make sure
* databuf_size is > cnt after allocation.
*/
if (cnt >= databuf_size) {
do {
if (databuf_size > MAX_SIZE/2)
fatal(_("input record too large"));
databuf_size *= 2;
} while (cnt >= databuf_size);
erealloc(databuf, char *, databuf_size, "set_record");
memset(databuf, '\0', databuf_size);
}
/* copy the data */
if (cnt != 0) {
memcpy(databuf, buf, cnt);
}
/*
* Add terminating '\0' so that C library routines
* will know when to stop.
*/
databuf[cnt] = '\0';
/* manage field 0: */
assert((fields_arr[0]->flags & MALLOC) == 0
? fields_arr[0]->valref == 1
: true);
unref(fields_arr[0]);
getnode(n);
n->stptr = databuf;
n->stlen = cnt;
n->valref = 1;
n->type = Node_val;
n->stfmt = STFMT_UNUSED;
#ifdef HAVE_MPFR
n->strndmode = MPFR_round_mode;
#endif
n->flags = (STRING|STRCUR|USER_INPUT); /* do not set MALLOC */
fields_arr[0] = n;
if (fw != api_fw) {
if ((api_fw = fw) != NULL) {
if (! api_parser_override) {
api_parser_override = true;
parse_field = fw_parse_field;
update_PROCINFO_str("FS", "API");
}
} else if (api_parser_override) {
api_parser_override = false;
parse_field = normal_parse_field;
update_PROCINFO_str("FS", current_field_sep_str());
}
}
#undef INITIAL_SIZE
#undef MAX_SIZE
}
/* reset_record --- start over again with current $0 */
void
reset_record()
{
fields_arr[0] = force_string(fields_arr[0]);
purge_record();
if (api_parser_override) {
api_parser_override = false;
parse_field = normal_parse_field;
update_PROCINFO_str("FS", current_field_sep_str());
}
}
/*
* purge_record --- throw away the fields, make sure that
* individual nodes remain valid.
*/
static void
purge_record()
{
int i;
NF = -1;
for (i = 1; i <= parse_high_water; i++) {
NODE *n;
NODE *r = fields_arr[i];
if ((r->flags & MALLOC) == 0 && r->valref > 1) {
/* This can and does happen. We must copy the string! */
const char *save = r->stptr;
emalloc(r->stptr, char *, r->stlen + 1, "purge_record");
memcpy(r->stptr, save, r->stlen);
r->stptr[r->stlen] = '\0';
r->flags |= MALLOC;
}
unref(r);
getnode(n);
*n = *Null_field;
fields_arr[i] = n;
}
parse_high_water = 0;
/*
* $0 = $0 should resplit using the current value of FS.
*/
if (resave_fs) {
resave_fs = false;
unref(save_FS);
save_FS = dupnode(FS_node->var_value);
}
field0_valid = true;
}
/* set_NF --- handle what happens to $0 and fields when NF is changed */
void
set_NF()
{
int i;
long nf;
NODE *n;
assert(NF != -1);
(void) force_number(NF_node->var_value);
nf = get_number_si(NF_node->var_value);
if (nf < 0)
fatal(_("NF set to negative value"));
static bool warned = false;
if (do_lint && NF > nf && ! warned) {
warned = true;
lintwarn(_("decrementing NF is not portable to many awk versions"));
}
NF = nf;
if (NF > nf_high_water)
grow_fields_arr(NF);
if (parse_high_water < NF) {
for (i = parse_high_water + 1; i >= 0 && i <= NF; i++) {
unref(fields_arr[i]);
getnode(n);
*n = *Null_field;
fields_arr[i] = n;
}
parse_high_water = NF;
} else if (parse_high_water > 0) {
for (i = NF + 1; i >= 0 && i <= parse_high_water; i++) {
unref(fields_arr[i]);
getnode(n);
*n = *Null_field;
fields_arr[i] = n;
}
parse_high_water = NF;
}
field0_valid = false;
}
/*
* re_parse_field --- parse fields using a regexp.
*
* This is called both from get_field() and from do_split()
* via (*parse_field)(). This variation is for when FS is a regular
* expression -- either user-defined or because RS=="" and FS==" "
*/
static long
re_parse_field(long up_to, /* parse only up to this field number */
char **buf, /* on input: string to parse; on output: point to start next */
int len,
NODE *fs ATTRIBUTE_UNUSED,
Regexp *rp,
Setfunc set, /* routine to set the value of the parsed field */
NODE *n,
NODE *sep_arr, /* array of field separators (maybe NULL) */
bool in_middle)
{
char *scan = *buf;
long nf = parse_high_water;
char *field;
char *end = scan + len;
int regex_flags = RE_NEED_START;
char *sep;
size_t mbclen = 0;
mbstate_t mbs;
memset(&mbs, 0, sizeof(mbstate_t));
if (in_middle)
regex_flags |= RE_NO_BOL;
if (up_to == UNLIMITED)
nf = 0;
if (len == 0)
return nf;
bool default_field_splitting = (RS_is_null && default_FS);
if (default_field_splitting) {
sep = scan;
while (scan < end && (*scan == ' ' || *scan == '\t' || *scan == '\n'))
scan++;
if (sep_arr != NULL && sep < scan)
set_element(nf, sep, (long)(scan - sep), sep_arr);
}
if (rp == NULL) /* use FS */
rp = FS_regexp;
field = scan;
while (scan < end
&& research(rp, scan, 0, (end - scan), regex_flags) != -1
&& nf < up_to) {
regex_flags |= RE_NO_BOL;
if (REEND(rp, scan) == RESTART(rp, scan)) { /* null match */
if (gawk_mb_cur_max > 1) {
mbclen = mbrlen(scan, end-scan, &mbs);
if ((mbclen == 1) || (mbclen == (size_t) -1)
|| (mbclen == (size_t) -2) || (mbclen == 0)) {
/* We treat it as a singlebyte character. */
mbclen = 1;
}
scan += mbclen;
} else
scan++;
if (scan == end) {
(*set)(++nf, field, (long)(scan - field), n);
up_to = nf;
break;
}
continue;
}
(*set)(++nf, field,
(long)(scan + RESTART(rp, scan) - field), n);
if (sep_arr != NULL)
set_element(nf, scan + RESTART(rp, scan),
(long) (REEND(rp, scan) - RESTART(rp, scan)), sep_arr);
scan += REEND(rp, scan);
field = scan;
if (scan == end && ! default_field_splitting) /* FS at end of record */
(*set)(++nf, field, 0L, n);
}
if (nf != up_to && scan < end) {
(*set)(++nf, scan, (long)(end - scan), n);
scan = end;
}
*buf = scan;
return nf;
}
/*
* def_parse_field --- default field parsing.
*
* This is called both from get_field() and from do_split()
* via (*parse_field)(). This variation is for when FS is a single space
* character.
*/
static long
def_parse_field(long up_to, /* parse only up to this field number */
char **buf, /* on input: string to parse; on output: point to start next */
int len,
NODE *fs,
Regexp *rp ATTRIBUTE_UNUSED,
Setfunc set, /* routine to set the value of the parsed field */
NODE *n,
NODE *sep_arr, /* array of field separators (maybe NULL) */
bool in_middle ATTRIBUTE_UNUSED)
{
char *scan = *buf;
long nf = parse_high_water;
char *field;
char *end = scan + len;
char sav;
char *sep;
if (up_to == UNLIMITED)
nf = 0;
if (len == 0)
return nf;
/*
* Nasty special case. If FS set to "", return whole record
* as first field. This is not worth a separate function.
*/
if (fs->stlen == 0) {
(*set)(++nf, *buf, len, n);
*buf += len;
return nf;
}
/* before doing anything save the char at *end */
sav = *end;
/* because it will be destroyed now: */
*end = ' '; /* sentinel character */
sep = scan;
for (; nf < up_to; scan++) {
/*
* special case: fs is single space, strip leading whitespace
*/
while (scan < end && (*scan == ' ' || *scan == '\t' || *scan == '\n'))
scan++;
if (sep_arr != NULL && scan > sep)
set_element(nf, sep, (long) (scan - sep), sep_arr);
if (scan >= end)
break;
field = scan;
while (*scan != ' ' && *scan != '\t' && *scan != '\n')
scan++;
(*set)(++nf, field, (long)(scan - field), n);
if (scan == end)
break;
sep = scan;
}
/* everything done, restore original char at *end */
*end = sav;
*buf = scan;
return nf;
}
/*
* null_parse_field --- each character is a separate field
*
* This is called both from get_field() and from do_split()
* via (*parse_field)(). This variation is for when FS is the null string.
*/
static long
null_parse_field(long up_to, /* parse only up to this field number */
char **buf, /* on input: string to parse; on output: point to start next */
int len,
NODE *fs ATTRIBUTE_UNUSED,
Regexp *rp ATTRIBUTE_UNUSED,
Setfunc set, /* routine to set the value of the parsed field */
NODE *n,
NODE *sep_arr, /* array of field separators (maybe NULL) */
bool in_middle ATTRIBUTE_UNUSED)
{
char *scan = *buf;
long nf = parse_high_water;
char *end = scan + len;
if (up_to == UNLIMITED)
nf = 0;
if (len == 0)
return nf;
if (gawk_mb_cur_max > 1) {
mbstate_t mbs;
memset(&mbs, 0, sizeof(mbstate_t));
for (; nf < up_to && scan < end;) {
size_t mbclen = mbrlen(scan, end-scan, &mbs);
if ((mbclen == 1) || (mbclen == (size_t) -1)
|| (mbclen == (size_t) -2) || (mbclen == 0)) {
/* We treat it as a singlebyte character. */
mbclen = 1;
}
if (sep_arr != NULL && nf > 0)
set_element(nf, scan, 0L, sep_arr);
(*set)(++nf, scan, mbclen, n);
scan += mbclen;
}
} else {
for (; nf < up_to && scan < end; scan++) {
if (sep_arr != NULL && nf > 0)
set_element(nf, scan, 0L, sep_arr);
(*set)(++nf, scan, 1L, n);
}
}
*buf = scan;
return nf;
}
/*
* sc_parse_field --- single character field separator
*
* This is called both from get_field() and from do_split()
* via (*parse_field)(). This variation is for when FS is a single character
* other than space.
*/
static long
sc_parse_field(long up_to, /* parse only up to this field number */
char **buf, /* on input: string to parse; on output: point to start next */
int len,
NODE *fs,
Regexp *rp ATTRIBUTE_UNUSED,
Setfunc set, /* routine to set the value of the parsed field */
NODE *n,
NODE *sep_arr, /* array of field separators (maybe NULL) */
bool in_middle ATTRIBUTE_UNUSED)
{
char *scan = *buf;
char fschar;
long nf = parse_high_water;
char *field;
char *end = scan + len;
char sav;
size_t mbclen = 0;
mbstate_t mbs;
memset(&mbs, 0, sizeof(mbstate_t));
if (up_to == UNLIMITED)
nf = 0;
if (len == 0)
return nf;
if (RS_is_null && fs->stlen == 0)
fschar = '\n';
else
fschar = fs->stptr[0];
/* before doing anything save the char at *end */
sav = *end;
/* because it will be destroyed now: */
*end = fschar; /* sentinel character */
for (; nf < up_to;) {
field = scan;
if (gawk_mb_cur_max > 1) {
while (*scan != fschar) {
mbclen = mbrlen(scan, end-scan, &mbs);
if ((mbclen == 1) || (mbclen == (size_t) -1)
|| (mbclen == (size_t) -2) || (mbclen == 0)) {
/* We treat it as a singlebyte character. */
mbclen = 1;
}
scan += mbclen;
}
} else {
while (*scan != fschar)
scan++;
}
(*set)(++nf, field, (long)(scan - field), n);
if (scan == end)
break;
if (sep_arr != NULL)
set_element(nf, scan, 1L, sep_arr);
scan++;
if (scan == end) { /* FS at end of record */
(*set)(++nf, field, 0L, n);
break;
}
}
/* everything done, restore original char at *end */
*end = sav;
*buf = scan;
return nf;
}
/*
* calc_mbslen --- calculate the length in bytes of a multi-byte string
* containing len characters.
*/
static size_t
calc_mbslen(char *scan, char *end, size_t len, mbstate_t *mbs)
{
size_t mbclen;
char *mbscan = scan;
while (len-- > 0 && mbscan < end) {
mbclen = mbrlen(mbscan, end - mbscan, mbs);
if (!(mbclen > 0 && mbclen <= (size_t)(end - mbscan)))
/*
* We treat it as a singlebyte character. This should
* catch error codes 0, (size_t) -1, and (size_t) -2.
*/
mbclen = 1;
mbscan += mbclen;
}
return mbscan - scan;
}
/*
* fw_parse_field --- field parsing using FIELDWIDTHS spec
*
* This is called from get_field() via (*parse_field)().
* This variation is for fields are fixed widths.
*/
static long
fw_parse_field(long up_to, /* parse only up to this field number */
char **buf, /* on input: string to parse; on output: point to start next */
int len,
NODE *fs ATTRIBUTE_UNUSED,
Regexp *rp ATTRIBUTE_UNUSED,
Setfunc set, /* routine to set the value of the parsed field */
NODE *n,
NODE *dummy ATTRIBUTE_UNUSED, /* sep_arr not needed here: hence dummy */
bool in_middle ATTRIBUTE_UNUSED)
{
char *scan = *buf;
long nf = parse_high_water;
char *end = scan + len;
const awk_fieldwidth_info_t *fw;
mbstate_t mbs;
size_t skiplen;
size_t flen;
fw = (api_parser_override ? api_fw : FIELDWIDTHS);
if (up_to == UNLIMITED)
nf = 0;
if (len == 0)
return nf;
if (gawk_mb_cur_max > 1 && fw->use_chars) {
/*
* Reset the shift state. Arguably, the shift state should
* be part of the file state and carried forward at all times,
* but nobody has complained so far, so this may not matter
* in practice.
*/
memset(&mbs, 0, sizeof(mbstate_t));
while (nf < up_to && scan < end) {
if (nf >= fw->nf) {
*buf = end;
return nf;
}
scan += calc_mbslen(scan, end, fw->fields[nf].skip, &mbs);
flen = calc_mbslen(scan, end, fw->fields[nf].len, &mbs);
(*set)(++nf, scan, (long) flen, n);
scan += flen;
}
} else {
while (nf < up_to && scan < end) {
if (nf >= fw->nf) {
*buf = end;
return nf;
}
skiplen = fw->fields[nf].skip;
if (skiplen > end - scan)
skiplen = end - scan;
scan += skiplen;
flen = fw->fields[nf].len;
if (flen > end - scan)
flen = end - scan;
(*set)(++nf, scan, (long) flen, n);
scan += flen;
}
}
*buf = scan;
return nf;
}
/* invalidate_field0 --- $0 needs reconstruction */
static void
invalidate_field0()
{
field0_valid = false;
}
/* get_field --- return a particular $n */
/* assign is not NULL if this field is on the LHS of an assign */
NODE **
get_field(long requested, Func_ptr *assign)
{
bool in_middle = false;
static bool warned = false;
extern int currule;
NODE *saved_fs;
Regexp *fs_regexp;
if (do_lint && currule == END && ! warned) {
warned = true;
lintwarn(_("accessing fields from an END rule may not be portable"));
}
/*
* if requesting whole line but some other field has been altered,
* then the whole line must be rebuilt
*/
if (requested == 0) {
if (! field0_valid) {
/* first, parse remainder of input record */
if (NF == -1) {
in_middle = (parse_high_water != 0);
if (current_field_sep() == Using_FPAT) {
saved_fs = save_FPAT;
fs_regexp = FPAT_regexp;
} else {
saved_fs = save_FS;
fs_regexp = FS_regexp;
}
NF = (*parse_field)(UNLIMITED - 1, &parse_extent,
fields_arr[0]->stlen -
(parse_extent - fields_arr[0]->stptr),
saved_fs, fs_regexp, set_field,
(NODE *) NULL,
(NODE *) NULL,
in_middle);
parse_high_water = NF;
}
rebuild_record();
}
if (assign != NULL)
*assign = reset_record;
return &fields_arr[0];
}
/* assert(requested > 0); */
#if 0
if (assign != NULL)
field0_valid = false; /* $0 needs reconstruction */
#else
/*
* Keep things uniform. Also, mere intention of assigning something
* to $n should not make $0 invalid. Makes sense to invalidate $0
* after the actual assignment is performed. Not a real issue in
* the interpreter otherwise, but causes problem in the
* debugger when watching or printing fields.
*/
if (assign != NULL)
*assign = invalidate_field0; /* $0 needs reconstruction */
#endif
if (requested <= parse_high_water) /* already parsed this field */
return &fields_arr[requested];
if (NF == -1) { /* have not yet parsed to end of record */
/*
* parse up to requested fields, calling set_field() for each,
* saving in parse_extent the point where the parse left off
*/
if (parse_high_water == 0) /* starting at the beginning */
parse_extent = fields_arr[0]->stptr;
else
in_middle = true;
parse_high_water = (*parse_field)(requested, &parse_extent,
fields_arr[0]->stlen - (parse_extent - fields_arr[0]->stptr),
save_FS, NULL, set_field, (NODE *) NULL, (NODE *) NULL, in_middle);
/*
* if we reached the end of the record, set NF to the number of
* fields so far. Note that requested might actually refer to
* a field that is beyond the end of the record, but we won't
* set NF to that value at this point, since this is only a
* reference to the field and NF only gets set if the field
* is assigned to -- this case is handled below
*/
if (parse_extent == fields_arr[0]->stptr + fields_arr[0]->stlen)
NF = parse_high_water;
if (requested == UNLIMITED - 1) /* UNLIMITED-1 means set NF */
requested = parse_high_water;
}
if (parse_high_water < requested) { /* requested beyond end of record */
if (assign != NULL) { /* expand record */
if (requested > nf_high_water)
grow_fields_arr(requested);
NF = requested;
parse_high_water = requested;
} else
return &Null_field;
}
return &fields_arr[requested];
}
/* set_element --- set an array element, used by do_split() */
static void
set_element(long num, char *s, long len, NODE *n)
{
NODE *it;
NODE *sub;
it = make_string(s, len);
it->flags |= USER_INPUT;
sub = make_number((AWKNUM) (num));
assoc_set(n, sub, it);
}
/* do_split --- implement split(), semantics are same as for field splitting */
NODE *
do_split(int nargs)
{
NODE *src, *arr, *sep, *fs, *tmp, *sep_arr = NULL;
char *s;
long (*parseit)(long, char **, int, NODE *,
Regexp *, Setfunc, NODE *, NODE *, bool);
Regexp *rp = NULL;
if (nargs == 4) {
static bool warned = false;
if (do_traditional || do_posix) {
fatal(_("split: fourth argument is a gawk extension"));
}
sep_arr = POP_PARAM();
if (sep_arr->type != Node_var_array)
fatal(_("split: fourth argument is not an array"));
check_symtab_functab(sep_arr, "split",
_("%s: cannot use %s as fourth argument"));
if ((do_lint_extensions || do_lint_old) && ! warned) {
warned = true;
lintwarn(_("split: fourth argument is a gawk extension"));
}
}
sep = POP();
arr = POP_PARAM();