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
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
|
/*
* field.c - routines for dealing with fields and record parsing
*/
/*
* Copyright (C) 1986, 1988, 1989, 1991-2010 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 *);
static long (*parse_field)(long, char **, int, NODE *,
Regexp *, Setfunc, NODE *, NODE *, int);
static void rebuild_record(void);
static long re_parse_field(long, char **, int, NODE *,
Regexp *, Setfunc, NODE *, NODE *, int);
static long def_parse_field(long, char **, int, NODE *,
Regexp *, Setfunc, NODE *, NODE *, int);
static long posix_def_parse_field(long, char **, int, NODE *,
Regexp *, Setfunc, NODE *, NODE *, int);
static long null_parse_field(long, char **, int, NODE *,
Regexp *, Setfunc, NODE *, NODE *, int);
static long sc_parse_field(long, char **, int, NODE *,
Regexp *, Setfunc, NODE *, NODE *, int);
static long fw_parse_field(long, char **, int, NODE *,
Regexp *, Setfunc, NODE *, NODE *, int);
static long fpat_parse_field(long, char **, int, NODE *,
Regexp *, Setfunc, NODE *, NODE *, int);
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 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 int resave_fs;
static NODE *save_FS; /* save current value of FS when line is read,
* to be used in deferred parsing
*/
static int *FIELDWIDTHS = NULL;
NODE **fields_arr; /* array of pointers to the field nodes */
int field0_valid; /* $(>0) has not been changed yet */
int default_FS; /* TRUE when FS == " " */
Regexp *FS_re_yes_case = NULL;
Regexp *FS_re_no_case = NULL;
Regexp *FS_regexp = NULL;
Regexp *FPAT_re_yes_case = NULL;
Regexp *FPAT_re_no_case = NULL;
Regexp *FPAT_regexp = NULL;
NODE *Null_field = NULL;
/* init_fields --- set up the fields array to start with */
void
init_fields()
{
emalloc(fields_arr, NODE **, sizeof(NODE *), "init_fields");
fields_arr[0] = Nnull_string;
parse_extent = fields_arr[0]->stptr;
save_FS = dupnode(FS_node->var_value);
getnode(Null_field);
*Null_field = *Nnull_string;
Null_field->flags |= FIELD;
Null_field->flags &= ~(NUMCUR|NUMBER|MAYBE_NUM|PERM|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|MAYBE_NUM|FIELD);
}
/* rebuild_record --- Someone assigned a value to $(something).
Fix up $0 to be right */
static void
rebuild_record()
{
/*
* use explicit unsigned longs for lengths, in case
* a size_t isn't big enough.
*/
unsigned long tlen;
unsigned long ofslen;
NODE *tmp;
NODE *ofs;
char *ops;
char *cops;
long i;
assert(NF != -1);
tlen = 0;
ofs = force_string(OFS_node->var_value);
ofslen = ofs->stlen;
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 + 2, "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->stptr[0];
else if (ofslen != 0) {
memcpy(cops, ofs->stptr, 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++) {
if (fields_arr[i]->stlen > 0) {
NODE *n;
getnode(n);
if ((fields_arr[i]->flags & FIELD) == 0) {
*n = *Null_field;
n->stlen = fields_arr[i]->stlen;
if ((fields_arr[i]->flags & (NUMCUR|NUMBER)) != 0) {
n->flags |= (fields_arr[i]->flags & (NUMCUR|NUMBER));
n->numbr = fields_arr[i]->numbr;
}
} else {
*n = *(fields_arr[i]);
n->flags &= ~(MALLOC|PERM|STRING);
}
n->stptr = cops;
unref(fields_arr[i]);
fields_arr[i] = n;
assert((n->flags & WSTRCUR) == 0);
}
cops += fields_arr[i]->stlen + ofslen;
}
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)
{
NODE *n;
static char *databuf;
static unsigned long databuf_size;
#define INITIAL_SIZE 512
#define MAX_SIZE ((unsigned long) ~0) /* maximally portable ... */
reset_record();
/* buffer management: */
if (databuf_size == 0) { /* first time */
emalloc(databuf, char *, INITIAL_SIZE, "set_record");
databuf_size = INITIAL_SIZE;
memset(databuf, '\0', 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) {
while (cnt >= databuf_size && databuf_size <= MAX_SIZE)
databuf_size *= 2;
erealloc(databuf, char *, databuf_size, "set_record");
memset(databuf, '\0', databuf_size);
}
/* copy the data */
memcpy(databuf, buf, cnt);
/* manage field 0: */
unref(fields_arr[0]);
getnode(n);
n->stptr = databuf;
n->stlen = cnt;
n->valref = 1;
n->type = Node_val;
n->stfmt = -1;
n->flags = (STRING|STRCUR|MAYBE_NUM|FIELD);
fields_arr[0] = n;
#undef INITIAL_SIZE
#undef MAX_SIZE
}
/* reset_record --- start over again with current $0 */
void
reset_record()
{
int i;
NODE *n;
(void) force_string(fields_arr[0]);
NF = -1;
for (i = 1; i <= parse_high_water; i++) {
unref(fields_arr[i]);
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);
nf = (long) force_number(NF_node->var_value);
if (nf < 0)
fatal(_("NF set to negative value"));
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;
}
} 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) */
int in_middle)
{
char *scan = *buf;
long nf = parse_high_water;
char *field;
char *end = scan + len;
int regex_flags = RE_NEED_START;
char *sep;
#ifdef MBS_SUPPORT
size_t mbclen = 0;
mbstate_t mbs;
if (gawk_mb_cur_max > 1)
memset(&mbs, 0, sizeof(mbstate_t));
#endif
if (in_middle)
regex_flags |= RE_NO_BOL;
if (up_to == UNLIMITED)
nf = 0;
if (len == 0)
return nf;
if (RS_is_null && default_FS) {
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 */
#ifdef MBS_SUPPORT
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
#endif
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) /* 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) */
int 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;
}
/*
* posix_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. The only difference between this and def_parse_field()
* is that this one does not allow newlines to separate fields.
*/
static long
posix_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 *dummy ATTRIBUTE_UNUSED, /* sep_arr not needed here: hence dummy */
int in_middle ATTRIBUTE_UNUSED)
{
char *scan = *buf;
long nf = parse_high_water;
char *field;
char *end = scan + len;
char sav;
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 */
for (; nf < up_to; scan++) {
/*
* special case: fs is single space, strip leading whitespace
*/
while (scan < end && (*scan == ' ' || *scan == '\t'))
scan++;
if (scan >= end)
break;
field = scan;
while (*scan != ' ' && *scan != '\t')
scan++;
(*set)(++nf, field, (long)(scan - field), n);
if (scan == end)
break;
}
/* 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) */
int 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;
#ifdef MBS_SUPPORT
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
#endif
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) */
int in_middle ATTRIBUTE_UNUSED)
{
char *scan = *buf;
char fschar;
long nf = parse_high_water;
char *field;
char *end = scan + len;
char sav;
#ifdef MBS_SUPPORT
size_t mbclen = 0;
mbstate_t mbs;
if (gawk_mb_cur_max > 1)
memset(&mbs, 0, sizeof(mbstate_t));
#endif
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;
#ifdef MBS_SUPPORT
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
#endif
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;
}
/*
* 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 */
int in_middle ATTRIBUTE_UNUSED)
{
char *scan = *buf;
long nf = parse_high_water;
char *end = scan + len;
#ifdef MBS_SUPPORT
int nmbc;
size_t mbclen;
size_t mbslen;
size_t lenrest;
char *mbscan;
mbstate_t mbs;
memset(&mbs, 0, sizeof(mbstate_t));
#endif
if (up_to == UNLIMITED)
nf = 0;
if (len == 0)
return nf;
for (; nf < up_to && (len = FIELDWIDTHS[nf+1]) != -1; ) {
#ifdef MBS_SUPPORT
if (gawk_mb_cur_max > 1) {
nmbc = 0;
mbslen = 0;
mbscan = scan;
lenrest = end - scan;
while (nmbc < len && mbslen < lenrest) {
mbclen = mbrlen(mbscan, end - mbscan, &mbs);
if ( mbclen == 1
|| mbclen == (size_t) -1
|| mbclen == (size_t) -2
|| mbclen == 0) {
/* We treat it as a singlebyte character. */
mbclen = 1;
}
if (mbclen <= end - mbscan) {
mbscan += mbclen;
mbslen += mbclen;
++nmbc;
}
}
(*set)(++nf, scan, (long) mbslen, n);
scan += mbslen;
}
else
#endif
{
if (len > end - scan)
len = end - scan;
(*set)(++nf, scan, (long) len, n);
scan += len;
}
}
if (len == -1)
*buf = end;
else
*buf = scan;
return nf;
}
/* invalidate_field0 --- $0 needs reconstruction */
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)
{
int in_middle = FALSE;
/*
* 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) {
NF = (*parse_field)(UNLIMITED - 1, &parse_extent,
fields_arr[0]->stlen -
(parse_extent - fields_arr[0]->stptr),
save_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 **lhs;
NODE *sub;
it = make_string(s, len);
it->flags |= MAYBE_NUM;
sub = make_number((AWKNUM) (num));
lhs = assoc_lookup(n, sub, FALSE);
unref(sub);
unref(*lhs);
*lhs = 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 *, int);
Regexp *rp = NULL;
if (nargs == 4) {
static short warned1 = FALSE, warned2 = 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"));
if (do_lint && ! warned1) {
warned1 = TRUE;
lintwarn(_("split: fourth argument is a gawk extension"));
}
if (do_lint_old && ! warned2) {
warned2 = TRUE;
warning(_("split: fourth argument is a gawk extension"));
}
}
sep = POP();
arr = POP_PARAM();
if (arr->type != Node_var_array)
fatal(_("split: second argument is not an array"));
assoc_clear(arr);
if (sep_arr != NULL)
assoc_clear(sep_arr);
src = TOP_STRING();
if (src->stlen == 0) {
/*
* Skip the work if first arg is the null string.
*/
decr_sp();
DEREF(src);
return make_number((AWKNUM) 0);
}
if ((sep->re_flags & FS_DFLT) != 0 && current_field_sep() != Using_FIELDWIDTHS && ! RS_is_null) {
parseit = parse_field;
fs = dupnode(force_string(FS_node->var_value));
rp = FS_regexp;
} else {
fs = dupnode(sep->re_exp);
if (fs->stlen == 0) {
static short warned = FALSE;
parseit = null_parse_field;
if (do_lint && ! warned) {
warned = TRUE;
lintwarn(_("split: null string for third arg is a gawk extension"));
}
} else if (fs->stlen == 1 && (sep->re_flags & CONSTANT) == 0) {
if (fs->stptr[0] == ' ') {
if (do_posix)
parseit = posix_def_parse_field;
else
parseit = def_parse_field;
} else
parseit = sc_parse_field;
} else {
parseit = re_parse_field;
rp = re_update(sep);
}
}
s = src->stptr;
tmp = make_number((AWKNUM) (*parseit)(UNLIMITED, &s, (int) src->stlen,
fs, rp, set_element, arr, sep_arr, FALSE));
decr_sp();
DEREF(src);
unref(fs);
return tmp;
}
/*
* do_patsplit --- implement patsplit(), semantics are same as for field
* splitting with FPAT.
*/
NODE *
do_patsplit(int nargs)
{
NODE *src, *arr, *sep, *fpat, *tmp, *sep_arr = NULL;
char *s;
Regexp *rp = NULL;
if (nargs == 4) {
sep_arr = POP_PARAM();
if (sep_arr->type != Node_var_array)
fatal(_("patsplit: fourth argument is not an array"));
}
sep = POP();
arr = POP_PARAM();
if (arr->type != Node_var_array)
fatal(_("patsplit: second argument is not an array"));
src = TOP_STRING();
if (src->stlen == 0) {
/*
* Skip the work if first arg is the null string.
*/
assoc_clear(arr);
if (sep_arr != NULL)
assoc_clear(sep_arr);
decr_sp();
DEREF(src);
return make_number((AWKNUM) 0);
}
fpat = dupnode(sep->re_exp);
if (fpat->stlen == 0) {
unref(fpat);
fatal(_("patsplit: third argument must be non-null"));
}
assoc_clear(arr);
if (sep_arr != NULL)
assoc_clear(sep_arr);
rp = re_update(sep);
s = src->stptr;
tmp = make_number((AWKNUM) fpat_parse_field(UNLIMITED, &s,
(int) src->stlen, fpat, rp,
set_element, arr, sep_arr, FALSE));
decr_sp();
DEREF(src);
unref(fpat);
return tmp;
}
/* set_FIELDWIDTHS --- handle an assignment to FIELDWIDTHS */
void
set_FIELDWIDTHS()
{
char *scan;
char *end;
int i;
static int fw_alloc = 4;
static short warned = FALSE;
extern unsigned long strtoul(const char *, char **endptr, int base);
int fatal_error = FALSE;
if (do_lint && ! warned) {
warned = TRUE;
lintwarn(_("`FIELDWIDTHS' is a gawk extension"));
}
if (do_traditional) /* quick and dirty, does the trick */
return;
/*
* If changing the way fields are split, obey least-suprise
* semantics, and force $0 to be split totally.
*/
if (fields_arr != NULL)
(void) get_field(UNLIMITED - 1, 0);
parse_field = fw_parse_field;
scan = force_string(FIELDWIDTHS_node->var_value)->stptr;
if (FIELDWIDTHS == NULL)
emalloc(FIELDWIDTHS, int *, fw_alloc * sizeof(int), "set_FIELDWIDTHS");
FIELDWIDTHS[0] = 0;
for (i = 1; ; i++) {
unsigned long int tmp;
if (i + 1 >= fw_alloc) {
fw_alloc *= 2;
erealloc(FIELDWIDTHS, int *, fw_alloc * sizeof(int), "set_FIELDWIDTHS");
}
/* Ensure that there is no leading `-' sign. Otherwise,
strtoul would accept it and return a bogus result. */
while (is_blank(*scan)) {
++scan;
}
if (*scan == '-') {
fatal_error = TRUE;
break;
}
if (*scan == '\0')
break;
/* Detect an invalid base-10 integer, a valid value that
is followed by something other than a blank or '\0',
or a value that is not in the range [1..INT_MAX]. */
errno = 0;
tmp = strtoul(scan, &end, 10);
if (errno != 0
|| (*end != '\0' && ! is_blank(*end))
|| !(0 < tmp && tmp <= INT_MAX)
) {
fatal_error = TRUE;
break;
}
FIELDWIDTHS[i] = tmp;
scan = end;
/* Skip past any trailing blanks. */
while (is_blank(*scan)) {
++scan;
}
if (*scan == '\0')
break;
}
if (i == 1) /* empty string! */
i--;
FIELDWIDTHS[i+1] = -1;
update_PROCINFO_str("FS", "FIELDWIDTHS");
if (fatal_error)
fatal(_("invalid FIELDWIDTHS value, near `%s'"),
scan);
}
/* set_FS --- handle things when FS is assigned to */
void
set_FS()
{
char buf[10];
NODE *fs;
static NODE *save_fs = NULL;
static NODE *save_rs = NULL;
int remake_re = TRUE;
/*
* If changing the way fields are split, obey least-surprise
* semantics, and force $0 to be split totally.
*/
if (fields_arr != NULL)
(void) get_field(UNLIMITED - 1, 0);
/* It's possible that only IGNORECASE changed, or FS = FS */
/*
* This comparison can't use cmp_nodes(), which pays attention
* to IGNORECASE, and that's not what we want.
*/
if (save_fs
&& FS_node->var_value->stlen == save_fs->stlen
&& memcmp(FS_node->var_value->stptr, save_fs->stptr, save_fs->stlen) == 0
&& save_rs
&& RS_node->var_value->stlen == save_rs->stlen
&& memcmp(RS_node->var_value->stptr, save_rs->stptr, save_rs->stlen) == 0) {
if (FS_regexp != NULL)
FS_regexp = (IGNORECASE ? FS_re_no_case : FS_re_yes_case);
/* FS = FS */
if (current_field_sep() == Using_FS) {
return;
} else {
remake_re = FALSE;
goto choose_fs_function;
}
}
unref(save_fs);
save_fs = dupnode(FS_node->var_value);
unref(save_rs);
save_rs = dupnode(RS_node->var_value);
resave_fs = TRUE;
/* If FS_re_no_case assignment is fatal (make_regexp in remake_re)
* FS_regexp will be NULL with a non-null FS_re_yes_case.
* refree() handles null argument; no need for `if (FS_regexp != NULL)' below.
* Please do not remerge.
*/
refree(FS_re_yes_case);
refree(FS_re_no_case);
FS_re_yes_case = FS_re_no_case = FS_regexp = NULL;
choose_fs_function:
buf[0] = '\0';
default_FS = FALSE;
fs = force_string(FS_node->var_value);
if (! do_traditional && fs->stlen == 0) {
static short warned = FALSE;
parse_field = null_parse_field;
if (do_lint && ! warned) {
warned = TRUE;
lintwarn(_("null string for `FS' is a gawk extension"));
}
} else if (fs->stlen > 1) {
if (do_lint_old)
warning(_("old awk does not support regexps as value of `FS'"));
parse_field = re_parse_field;
} else if (RS_is_null) {
/* we know that fs->stlen <= 1 */
parse_field = sc_parse_field;
if (fs->stlen == 1) {
if (fs->stptr[0] == ' ') {
default_FS = TRUE;
strcpy(buf, "[ \t\n]+");
} else if (fs->stptr[0] == '\\') {
/* yet another special case */
strcpy(buf, "[\\\\\n]");
} else if (fs->stptr[0] != '\n')
sprintf(buf, "[%c\n]", fs->stptr[0]);
}
} else {
if (do_posix)
parse_field = posix_def_parse_field;
else
parse_field = def_parse_field;
if (fs->stlen == 1) {
if (fs->stptr[0] == ' ')
default_FS = TRUE;
else if (fs->stptr[0] == '\\')
/* same special case */
strcpy(buf, "[\\\\]");
else
parse_field = sc_parse_field;
}
}
if (remake_re) {
refree(FS_re_yes_case);
refree(FS_re_no_case);
FS_re_yes_case = FS_re_no_case = FS_regexp = NULL;
if (buf[0] != '\0') {
FS_re_yes_case = make_regexp(buf, strlen(buf), FALSE, TRUE, TRUE);
FS_re_no_case = make_regexp(buf, strlen(buf), TRUE, TRUE, TRUE);
FS_regexp = (IGNORECASE ? FS_re_no_case : FS_re_yes_case);
parse_field = re_parse_field;
} else if (parse_field == re_parse_field) {
FS_re_yes_case = make_regexp(fs->stptr, fs->stlen, FALSE, TRUE, TRUE);
FS_re_no_case = make_regexp(fs->stptr, fs->stlen, TRUE, TRUE, TRUE);
FS_regexp = (IGNORECASE ? FS_re_no_case : FS_re_yes_case);
} else
FS_re_yes_case = FS_re_no_case = FS_regexp = NULL;
}
/*
* For FS = "c", we don't use IGNORECASE. But we must use
* re_parse_field to get the character and the newline as
* field separators.
*/
if (fs->stlen == 1 && parse_field == re_parse_field)
FS_regexp = FS_re_yes_case;
update_PROCINFO_str("FS", "FS");
}
/* current_field_sep --- return what field separator is */
field_sep_type
current_field_sep()
{
if (parse_field == fw_parse_field)
return Using_FIELDWIDTHS;
else if (parse_field == fpat_parse_field)
return Using_FPAT;
else
return Using_FS;
}
/* update_PROCINFO_str --- update PROCINFO[sub] with string value */
void
update_PROCINFO_str(char *subscript, char *str)
{
NODE **aptr;
NODE *tmp;
if (PROCINFO_node == NULL)
return;
tmp = make_string(subscript, strlen(subscript));
aptr = assoc_lookup(PROCINFO_node, tmp, FALSE);
unref(tmp);
unref(*aptr);
*aptr = make_string(str, strlen(str));
}
/* update_PROCINFO_num --- update PROCINFO[sub] with numeric value */
void
update_PROCINFO_num(char *subscript, AWKNUM val)
{
NODE **aptr;
NODE *tmp;
if (PROCINFO_node == NULL)
return;
tmp = make_string(subscript, strlen(subscript));
aptr = assoc_lookup(PROCINFO_node, tmp, FALSE);
unref(tmp);
unref(*aptr);
*aptr = make_number(val);
}
/* set_FPAT --- handle an assignment to FPAT */
void
set_FPAT()
{
static short warned = FALSE;
static NODE *save_fpat = NULL;
int remake_re = TRUE;
NODE *fpat;
if (do_lint && ! warned) {
warned = TRUE;
lintwarn(_("`FPAT' is a gawk extension"));
}
if (do_traditional) /* quick and dirty, does the trick */
return;
/*
* If changing the way fields are split, obey least-suprise
* semantics, and force $0 to be split totally.
*/
if (fields_arr != NULL)
(void) get_field(UNLIMITED - 1, 0);
/* It's possible that only IGNORECASE changed, or FPAT = FPAT */
/*
* This comparison can't use cmp_nodes(), which pays attention
* to IGNORECASE, and that's not what we want.
*/
if (save_fpat
&& FPAT_node->var_value->stlen == save_fpat->stlen
&& memcmp(FPAT_node->var_value->stptr, save_fpat->stptr, save_fpat->stlen) == 0) {
if (FPAT_regexp != NULL)
FPAT_regexp = (IGNORECASE ? FPAT_re_no_case : FPAT_re_yes_case);
/* FPAT = FPAT */
if (current_field_sep() == Using_FPAT) {
return;
} else {
remake_re = FALSE;
goto set_fpat_function;
}
}
unref(save_fpat);
save_fpat = dupnode(FPAT_node->var_value);
refree(FPAT_re_yes_case);
refree(FPAT_re_no_case);
FPAT_re_yes_case = FPAT_re_no_case = FPAT_regexp = NULL;
set_fpat_function:
fpat = force_string(FPAT_node->var_value);
parse_field = fpat_parse_field;
if (remake_re) {
refree(FPAT_re_yes_case);
refree(FPAT_re_no_case);
FPAT_re_yes_case = FPAT_re_no_case = FPAT_regexp = NULL;
FPAT_re_yes_case = make_regexp(fpat->stptr, fpat->stlen, FALSE, TRUE, TRUE);
FPAT_re_no_case = make_regexp(fpat->stptr, fpat->stlen, TRUE, TRUE, TRUE);
FPAT_regexp = (IGNORECASE ? FPAT_re_no_case : FPAT_re_yes_case);
}
update_PROCINFO_str("FS", "FPAT");
}
/*
* increment_scan --- macro to move scan pointer ahead by one character.
* Implementation varies if doing MBS or not.
*/
#ifdef MBS_SUPPORT
#define increment_scan(scanp, len) incr_scan(scanp, len, & mbs)
#else
#define increment_scan(scanp, len) ((*scanp)++)
#endif
#ifdef MBS_SUPPORT
/* incr_scan --- MBS version of increment_scan() */
static void
incr_scan(char **scanp, size_t len, mbstate_t *mbs)
{
size_t mbclen = 0;
if (gawk_mb_cur_max > 1) {
mbclen = mbrlen(*scanp, len, mbs);
if ( (mbclen == 1)
|| (mbclen == (size_t) -1)
|| (mbclen == (size_t) -2)
|| (mbclen == 0)) {
/* We treat it as a singlebyte character. */
mbclen = 1;
}
*scanp += mbclen;
} else
(*scanp)++;
}
#endif
/*
* fpat_parse_field --- parse fields using a regexp.
*
* This is called both from get_field() and from do_patsplit()
* via (*parse_field)(). This variation is for when FPAT is a regular
* expression -- use the value to find field contents.
*
* This was really hard to get right. It happens to bear many resemblances
* to issues I had with getting gsub right with null matches. When dealing
* with that I prototyped in awk and had the foresight to save the awk code
* over in the C file. Starting with that as a base, I finally got to this
* awk code to do what I needed, and then translated it into C. Fortunately
* the C code bears a closer correspondance to the awk code here than over
* by gsub.
*
* BEGIN {
* FALSE = 0
* TRUE = 1
*
* fpat[1] = "([^,]*)|(\"[^\"]+\")"
* fpat[2] = fpat[1]
* fpat[3] = fpat[1]
* fpat[4] = "aa+"
* fpat[5] = fpat[4]
*
* data[1] = "Robbins,,Arnold,"
* data[2] = "Smith,,\"1234 A Pretty Place, NE\",Sometown,NY,12345-6789,USA"
* data[3] = "Robbins,Arnold,\"1234 A Pretty Place, NE\",Sometown,NY,12345-6789,USA"
* data[4] = "bbbaaacccdddaaaaaqqqq"
* data[5] = "bbbaaacccdddaaaaaqqqqa" # should get trailing qqqa
*
* for (i = 1; i in data; i++) {
* printf("Splitting: <%s>\n", data[i])
* n = mypatsplit(data[i], fields, fpat[i], seps)
* print "n =", n
* for (j = 1; j <= n; j++)
* printf("fields[%d] = <%s>\n", j, fields[j])
* for (j = 0; j in seps; j++)
* printf("seps[%s] = <%s>\n", j, seps[j])
* }
* }
*
* function mypatsplit(string, array, pattern, seps,
* eosflag, non_empty, nf) # locals
* {
* delete array
* delete seps
* if (length(string) == 0)
* return 0
*
* eosflag = non_empty = FALSE
* nf = 0
* while (match(string, pattern)) {
* if (RLENGTH > 0) { # easy case
* non_empty = TRUE
* if (! (nf in seps)) {
* if (RSTART == 1) # match at front of string
* seps[nf] = ""
* else
* seps[nf] = substr(string, 1, RSTART - 1)
* }
* array[++nf] = substr(string, RSTART, RLENGTH)
* string = substr(string, RSTART+RLENGTH)
* if (length(string) == 0)
* break
* } else if (non_empty) {
* # last match was non-empty, and at the
* # current character we get a zero length match,
* # which we don't want, so skip over it
* non_empty = FALSE
* seps[nf] = substr(string, 1, 1)
* string = substr(string, 2)
* } else {
* # 0 length match
* if (! (nf in seps)) {
* if (RSTART == 1)
* seps[nf] = ""
* else
* seps[nf] = substr(string, 1, RSTART - 1)
* }
* array[++nf] = ""
* if (! non_empty && ! eosflag) { # prev was empty
* seps[nf] = substr(string, 1, 1)
* }
* if (RSTART == 1) {
* string = substr(string, 2)
* } else {
* string = substr(string, RSTART + 1)
* }
* non_empty = FALSE
* }
* if (length(string) == 0) {
* if (eosflag)
* break
* else
* eosflag = TRUE
* }
* }
* if (length(string) > 0)
* seps[nf] = string
*
* return length(array)
* }
*/
static long
fpat_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 (may be NULL) */
int in_middle)
{
char *scan = *buf;
long nf = parse_high_water;
char *start;
char *end = scan + len;
int regex_flags = RE_NEED_START;
int need_to_set_sep;
int non_empty;
int eosflag;
#ifdef MBS_SUPPORT
mbstate_t mbs;
if (gawk_mb_cur_max > 1)
memset(&mbs, 0, sizeof(mbstate_t));
#endif
if (in_middle)
regex_flags |= RE_NO_BOL;
if (up_to == UNLIMITED)
nf = 0;
if (len == 0)
return nf;
if (rp == NULL) /* use FPAT */
rp = FPAT_regexp;
eosflag = non_empty = FALSE;
need_to_set_sep = TRUE;
start = scan;
while (research(rp, scan, 0, (end - scan), regex_flags) != -1
&& nf < up_to) {
regex_flags |= RE_NO_BOL;
if (REEND(rp, scan) > RESTART(rp, scan)) { /* if (RLENGTH > 0) */
non_empty = TRUE;
if (sep_arr != NULL && need_to_set_sep) {
if (RESTART(rp, scan) == 0) /* match at front */
set_element(nf, start, 0L, sep_arr);
else
set_element(nf,
start,
(long) RESTART(rp, scan),
sep_arr);
}
/* field is text that matched */
(*set)(++nf,
scan + RESTART(rp, scan),
(long)(REEND(rp, scan) - RESTART(rp, scan)),
n);
scan += REEND(rp, scan);
if (scan >= end)
break;
need_to_set_sep = TRUE;
} else if (non_empty) { /* else if non_empty */
/*
* last match was non-empty, and at the
* current character we get a zero length match,
* which we don't want, so skip over it
*/
non_empty = FALSE;
if (sep_arr != NULL) {
need_to_set_sep = FALSE;
set_element(nf, start, 1L, sep_arr);
}
increment_scan(& scan, end - scan);
} else {
/* 0 length match */
if (sep_arr != NULL && need_to_set_sep) {
if (RESTART(rp, scan) == 0) /* RSTART == 1 */
set_element(nf, start, 0L, sep_arr);
else
set_element(nf, start,
(long) RESTART(rp, scan),
sep_arr);
}
need_to_set_sep = TRUE;
(*set)(++nf, scan, 0L, n);
if (! non_empty && ! eosflag) { /* prev was empty */
if (sep_arr != NULL) {
set_element(nf, start, 1L, sep_arr);
need_to_set_sep = FALSE;
}
}
if (RESTART(rp, scan) == 0)
increment_scan(& scan, end - scan);
else {
scan += RESTART(rp, scan);
}
non_empty = FALSE;
}
if (scan >= end) { /* length(string) == 0 */
if (eosflag)
break;
else
eosflag = TRUE;
}
start = scan;
}
if (scan < end) {
if (sep_arr != NULL)
set_element(nf, scan, (long) (end - scan), sep_arr);
}
*buf = scan;
return nf;
}
|