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
|
/* inline.h
*
* Copyright (C) 2012 by Larry Wall and others
*
* You may distribute under the terms of either the GNU General Public
* License or the Artistic License, as specified in the README file.
*
* This file is a home for static inline functions that cannot go in other
* headers files, because they depend on proto.h (included after most other
* headers) or struct definitions.
*
* Each section names the header file that the functions "belong" to.
*/
/* ------------------------------- av.h ------------------------------- */
PERL_STATIC_INLINE SSize_t
S_av_top_index(pTHX_ AV *av)
{
PERL_ARGS_ASSERT_AV_TOP_INDEX;
assert(SvTYPE(av) == SVt_PVAV);
return AvFILL(av);
}
/* ------------------------------- cv.h ------------------------------- */
PERL_STATIC_INLINE GV *
S_CvGV(pTHX_ CV *sv)
{
return CvNAMED(sv)
? Perl_cvgv_from_hek(aTHX_ sv)
: ((XPVCV*)MUTABLE_PTR(SvANY(sv)))->xcv_gv_u.xcv_gv;
}
PERL_STATIC_INLINE I32 *
S_CvDEPTHp(const CV * const sv)
{
assert(SvTYPE(sv) == SVt_PVCV || SvTYPE(sv) == SVt_PVFM);
return &((XPVCV*)SvANY(sv))->xcv_depth;
}
/*
CvPROTO returns the prototype as stored, which is not necessarily what
the interpreter should be using. Specifically, the interpreter assumes
that spaces have been stripped, which has been the case if the prototype
was added by toke.c, but is generally not the case if it was added elsewhere.
Since we can't enforce the spacelessness at assignment time, this routine
provides a temporary copy at parse time with spaces removed.
I<orig> is the start of the original buffer, I<len> is the length of the
prototype and will be updated when this returns.
*/
#ifdef PERL_CORE
PERL_STATIC_INLINE char *
S_strip_spaces(pTHX_ const char * orig, STRLEN * const len)
{
SV * tmpsv;
char * tmps;
tmpsv = newSVpvn_flags(orig, *len, SVs_TEMP);
tmps = SvPVX(tmpsv);
while ((*len)--) {
if (!isSPACE(*orig))
*tmps++ = *orig;
orig++;
}
*tmps = '\0';
*len = tmps - SvPVX(tmpsv);
return SvPVX(tmpsv);
}
#endif
/* ------------------------------- mg.h ------------------------------- */
#if defined(PERL_CORE) || defined(PERL_EXT)
/* assumes get-magic and stringification have already occurred */
PERL_STATIC_INLINE STRLEN
S_MgBYTEPOS(pTHX_ MAGIC *mg, SV *sv, const char *s, STRLEN len)
{
assert(mg->mg_type == PERL_MAGIC_regex_global);
assert(mg->mg_len != -1);
if (mg->mg_flags & MGf_BYTES || !DO_UTF8(sv))
return (STRLEN)mg->mg_len;
else {
const STRLEN pos = (STRLEN)mg->mg_len;
/* Without this check, we may read past the end of the buffer: */
if (pos > sv_or_pv_len_utf8(sv, s, len)) return len+1;
return sv_or_pv_pos_u2b(sv, s, pos, NULL);
}
}
#endif
/* ------------------------------- pad.h ------------------------------ */
#if defined(PERL_IN_PAD_C) || defined(PERL_IN_OP_C)
PERL_STATIC_INLINE bool
PadnameIN_SCOPE(const PADNAME * const pn, const U32 seq)
{
/* is seq within the range _LOW to _HIGH ?
* This is complicated by the fact that PL_cop_seqmax
* may have wrapped around at some point */
if (COP_SEQ_RANGE_LOW(pn) == PERL_PADSEQ_INTRO)
return FALSE; /* not yet introduced */
if (COP_SEQ_RANGE_HIGH(pn) == PERL_PADSEQ_INTRO) {
/* in compiling scope */
if (
(seq > COP_SEQ_RANGE_LOW(pn))
? (seq - COP_SEQ_RANGE_LOW(pn) < (U32_MAX >> 1))
: (COP_SEQ_RANGE_LOW(pn) - seq > (U32_MAX >> 1))
)
return TRUE;
}
else if (
(COP_SEQ_RANGE_LOW(pn) > COP_SEQ_RANGE_HIGH(pn))
?
( seq > COP_SEQ_RANGE_LOW(pn)
|| seq <= COP_SEQ_RANGE_HIGH(pn))
: ( seq > COP_SEQ_RANGE_LOW(pn)
&& seq <= COP_SEQ_RANGE_HIGH(pn))
)
return TRUE;
return FALSE;
}
#endif
/* ------------------------------- pp.h ------------------------------- */
PERL_STATIC_INLINE I32
S_TOPMARK(pTHX)
{
DEBUG_s(DEBUG_v(PerlIO_printf(Perl_debug_log,
"MARK top %p %" IVdf "\n",
PL_markstack_ptr,
(IV)*PL_markstack_ptr)));
return *PL_markstack_ptr;
}
PERL_STATIC_INLINE I32
S_POPMARK(pTHX)
{
DEBUG_s(DEBUG_v(PerlIO_printf(Perl_debug_log,
"MARK pop %p %" IVdf "\n",
(PL_markstack_ptr-1),
(IV)*(PL_markstack_ptr-1))));
assert((PL_markstack_ptr > PL_markstack) || !"MARK underflow");
return *PL_markstack_ptr--;
}
/* ----------------------------- regexp.h ----------------------------- */
PERL_STATIC_INLINE struct regexp *
S_ReANY(const REGEXP * const re)
{
assert(isREGEXP(re));
return re->sv_u.svu_rx;
}
/* ------------------------------- sv.h ------------------------------- */
PERL_STATIC_INLINE SV *
S_SvREFCNT_inc(SV *sv)
{
if (LIKELY(sv != NULL))
SvREFCNT(sv)++;
return sv;
}
PERL_STATIC_INLINE SV *
S_SvREFCNT_inc_NN(SV *sv)
{
SvREFCNT(sv)++;
return sv;
}
PERL_STATIC_INLINE void
S_SvREFCNT_inc_void(SV *sv)
{
if (LIKELY(sv != NULL))
SvREFCNT(sv)++;
}
PERL_STATIC_INLINE void
S_SvREFCNT_dec(pTHX_ SV *sv)
{
if (LIKELY(sv != NULL)) {
U32 rc = SvREFCNT(sv);
if (LIKELY(rc > 1))
SvREFCNT(sv) = rc - 1;
else
Perl_sv_free2(aTHX_ sv, rc);
}
}
PERL_STATIC_INLINE void
S_SvREFCNT_dec_NN(pTHX_ SV *sv)
{
U32 rc = SvREFCNT(sv);
if (LIKELY(rc > 1))
SvREFCNT(sv) = rc - 1;
else
Perl_sv_free2(aTHX_ sv, rc);
}
PERL_STATIC_INLINE void
SvAMAGIC_on(SV *sv)
{
assert(SvROK(sv));
if (SvOBJECT(SvRV(sv))) HvAMAGIC_on(SvSTASH(SvRV(sv)));
}
PERL_STATIC_INLINE void
SvAMAGIC_off(SV *sv)
{
if (SvROK(sv) && SvOBJECT(SvRV(sv)))
HvAMAGIC_off(SvSTASH(SvRV(sv)));
}
PERL_STATIC_INLINE U32
S_SvPADSTALE_on(SV *sv)
{
assert(!(SvFLAGS(sv) & SVs_PADTMP));
return SvFLAGS(sv) |= SVs_PADSTALE;
}
PERL_STATIC_INLINE U32
S_SvPADSTALE_off(SV *sv)
{
assert(!(SvFLAGS(sv) & SVs_PADTMP));
return SvFLAGS(sv) &= ~SVs_PADSTALE;
}
#if defined(PERL_CORE) || defined (PERL_EXT)
PERL_STATIC_INLINE STRLEN
S_sv_or_pv_pos_u2b(pTHX_ SV *sv, const char *pv, STRLEN pos, STRLEN *lenp)
{
PERL_ARGS_ASSERT_SV_OR_PV_POS_U2B;
if (SvGAMAGIC(sv)) {
U8 *hopped = utf8_hop((U8 *)pv, pos);
if (lenp) *lenp = (STRLEN)(utf8_hop(hopped, *lenp) - hopped);
return (STRLEN)(hopped - (U8 *)pv);
}
return sv_pos_u2b_flags(sv,pos,lenp,SV_CONST_RETURN);
}
#endif
/* ------------------------------- handy.h ------------------------------- */
/* saves machine code for a common noreturn idiom typically used in Newx*() */
#ifdef GCC_DIAG_PRAGMA
GCC_DIAG_IGNORE(-Wunused-function) /* Intentionally left semicolonless. */
#endif
static void
S_croak_memory_wrap(void)
{
Perl_croak_nocontext("%s",PL_memory_wrap);
}
#ifdef GCC_DIAG_PRAGMA
GCC_DIAG_RESTORE /* Intentionally left semicolonless. */
#endif
/* ------------------------------- utf8.h ------------------------------- */
/*
=head1 Unicode Support
*/
PERL_STATIC_INLINE void
S_append_utf8_from_native_byte(const U8 byte, U8** dest)
{
/* Takes an input 'byte' (Latin1 or EBCDIC) and appends it to the UTF-8
* encoded string at '*dest', updating '*dest' to include it */
PERL_ARGS_ASSERT_APPEND_UTF8_FROM_NATIVE_BYTE;
if (NATIVE_BYTE_IS_INVARIANT(byte))
*((*dest)++) = byte;
else {
*((*dest)++) = UTF8_EIGHT_BIT_HI(byte);
*((*dest)++) = UTF8_EIGHT_BIT_LO(byte);
}
}
/*
=for apidoc valid_utf8_to_uvchr
Like C<L</utf8_to_uvchr_buf>>, but should only be called when it is known that
the next character in the input UTF-8 string C<s> is well-formed (I<e.g.>,
it passes C<L</isUTF8_CHAR>>. Surrogates, non-character code points, and
non-Unicode code points are allowed.
=cut
*/
PERL_STATIC_INLINE UV
Perl_valid_utf8_to_uvchr(const U8 *s, STRLEN *retlen)
{
const UV expectlen = UTF8SKIP(s);
const U8* send = s + expectlen;
UV uv = *s;
PERL_ARGS_ASSERT_VALID_UTF8_TO_UVCHR;
if (retlen) {
*retlen = expectlen;
}
/* An invariant is trivially returned */
if (expectlen == 1) {
return uv;
}
/* Remove the leading bits that indicate the number of bytes, leaving just
* the bits that are part of the value */
uv = NATIVE_UTF8_TO_I8(uv) & UTF_START_MASK(expectlen);
/* Now, loop through the remaining bytes, accumulating each into the
* working total as we go. (I khw tried unrolling the loop for up to 4
* bytes, but there was no performance improvement) */
for (++s; s < send; s++) {
uv = UTF8_ACCUMULATE(uv, *s);
}
return UNI_TO_NATIVE(uv);
}
/*
=for apidoc is_utf8_invariant_string
Returns TRUE if the first C<len> bytes of the string C<s> are the same
regardless of the UTF-8 encoding of the string (or UTF-EBCDIC encoding on
EBCDIC machines); otherwise it returns FALSE. That is, it returns TRUE if they
are UTF-8 invariant. On ASCII-ish machines, all the ASCII characters and only
the ASCII characters fit this definition. On EBCDIC machines, the ASCII-range
characters are invariant, but so also are the C1 controls.
If C<len> is 0, it will be calculated using C<strlen(s)>, (which means if you
use this option, that C<s> can't have embedded C<NUL> characters and has to
have a terminating C<NUL> byte).
See also
C<L</is_utf8_string>>,
C<L</is_utf8_string_flags>>,
C<L</is_utf8_string_loc>>,
C<L</is_utf8_string_loc_flags>>,
C<L</is_utf8_string_loclen>>,
C<L</is_utf8_string_loclen_flags>>,
C<L</is_utf8_fixed_width_buf_flags>>,
C<L</is_utf8_fixed_width_buf_loc_flags>>,
C<L</is_utf8_fixed_width_buf_loclen_flags>>,
C<L</is_strict_utf8_string>>,
C<L</is_strict_utf8_string_loc>>,
C<L</is_strict_utf8_string_loclen>>,
C<L</is_c9strict_utf8_string>>,
C<L</is_c9strict_utf8_string_loc>>,
and
C<L</is_c9strict_utf8_string_loclen>>.
=cut
*/
PERL_STATIC_INLINE bool
S_is_utf8_invariant_string(const U8* const s, const STRLEN len)
{
const U8* const send = s + (len ? len : strlen((const char *)s));
const U8* x = s;
PERL_ARGS_ASSERT_IS_UTF8_INVARIANT_STRING;
for (; x < send; ++x) {
if (!UTF8_IS_INVARIANT(*x))
return FALSE;
}
return TRUE;
}
/*
=for apidoc is_utf8_string
Returns TRUE if the first C<len> bytes of string C<s> form a valid
Perl-extended-UTF-8 string; returns FALSE otherwise. If C<len> is 0, it will
be calculated using C<strlen(s)> (which means if you use this option, that C<s>
can't have embedded C<NUL> characters and has to have a terminating C<NUL>
byte). Note that all characters being ASCII constitute 'a valid UTF-8 string'.
This function considers Perl's extended UTF-8 to be valid. That means that
code points above Unicode, surrogates, and non-character code points are
considered valid by this function. Use C<L</is_strict_utf8_string>>,
C<L</is_c9strict_utf8_string>>, or C<L</is_utf8_string_flags>> to restrict what
code points are considered valid.
See also
C<L</is_utf8_invariant_string>>,
C<L</is_utf8_string_loc>>,
C<L</is_utf8_string_loclen>>,
C<L</is_utf8_fixed_width_buf_flags>>,
C<L</is_utf8_fixed_width_buf_loc_flags>>,
C<L</is_utf8_fixed_width_buf_loclen_flags>>,
=cut
*/
PERL_STATIC_INLINE bool
Perl_is_utf8_string(const U8 *s, const STRLEN len)
{
/* This is now marked pure in embed.fnc, because isUTF8_CHAR now is pure.
* Be aware of possible changes to that */
const U8* const send = s + (len ? len : strlen((const char *)s));
const U8* x = s;
PERL_ARGS_ASSERT_IS_UTF8_STRING;
while (x < send) {
const STRLEN cur_len = isUTF8_CHAR(x, send);
if (UNLIKELY(! cur_len)) {
return FALSE;
}
x += cur_len;
}
return TRUE;
}
/*
=for apidoc is_strict_utf8_string
Returns TRUE if the first C<len> bytes of string C<s> form a valid
UTF-8-encoded string that is fully interchangeable by any application using
Unicode rules; otherwise it returns FALSE. If C<len> is 0, it will be
calculated using C<strlen(s)> (which means if you use this option, that C<s>
can't have embedded C<NUL> characters and has to have a terminating C<NUL>
byte). Note that all characters being ASCII constitute 'a valid UTF-8 string'.
This function returns FALSE for strings containing any
code points above the Unicode max of 0x10FFFF, surrogate code points, or
non-character code points.
See also
C<L</is_utf8_invariant_string>>,
C<L</is_utf8_string>>,
C<L</is_utf8_string_flags>>,
C<L</is_utf8_string_loc>>,
C<L</is_utf8_string_loc_flags>>,
C<L</is_utf8_string_loclen>>,
C<L</is_utf8_string_loclen_flags>>,
C<L</is_utf8_fixed_width_buf_flags>>,
C<L</is_utf8_fixed_width_buf_loc_flags>>,
C<L</is_utf8_fixed_width_buf_loclen_flags>>,
C<L</is_strict_utf8_string_loc>>,
C<L</is_strict_utf8_string_loclen>>,
C<L</is_c9strict_utf8_string>>,
C<L</is_c9strict_utf8_string_loc>>,
and
C<L</is_c9strict_utf8_string_loclen>>.
=cut
*/
PERL_STATIC_INLINE bool
S_is_strict_utf8_string(const U8 *s, const STRLEN len)
{
const U8* const send = s + (len ? len : strlen((const char *)s));
const U8* x = s;
PERL_ARGS_ASSERT_IS_STRICT_UTF8_STRING;
while (x < send) {
const STRLEN cur_len = isSTRICT_UTF8_CHAR(x, send);
if (UNLIKELY(! cur_len)) {
return FALSE;
}
x += cur_len;
}
return TRUE;
}
/*
=for apidoc is_c9strict_utf8_string
Returns TRUE if the first C<len> bytes of string C<s> form a valid
UTF-8-encoded string that conforms to
L<Unicode Corrigendum #9|http://www.unicode.org/versions/corrigendum9.html>;
otherwise it returns FALSE. If C<len> is 0, it will be calculated using
C<strlen(s)> (which means if you use this option, that C<s> can't have embedded
C<NUL> characters and has to have a terminating C<NUL> byte). Note that all
characters being ASCII constitute 'a valid UTF-8 string'.
This function returns FALSE for strings containing any code points above the
Unicode max of 0x10FFFF or surrogate code points, but accepts non-character
code points per
L<Corrigendum #9|http://www.unicode.org/versions/corrigendum9.html>.
See also
C<L</is_utf8_invariant_string>>,
C<L</is_utf8_string>>,
C<L</is_utf8_string_flags>>,
C<L</is_utf8_string_loc>>,
C<L</is_utf8_string_loc_flags>>,
C<L</is_utf8_string_loclen>>,
C<L</is_utf8_string_loclen_flags>>,
C<L</is_utf8_fixed_width_buf_flags>>,
C<L</is_utf8_fixed_width_buf_loc_flags>>,
C<L</is_utf8_fixed_width_buf_loclen_flags>>,
C<L</is_strict_utf8_string>>,
C<L</is_strict_utf8_string_loc>>,
C<L</is_strict_utf8_string_loclen>>,
C<L</is_c9strict_utf8_string_loc>>,
and
C<L</is_c9strict_utf8_string_loclen>>.
=cut
*/
PERL_STATIC_INLINE bool
S_is_c9strict_utf8_string(const U8 *s, const STRLEN len)
{
const U8* const send = s + (len ? len : strlen((const char *)s));
const U8* x = s;
PERL_ARGS_ASSERT_IS_C9STRICT_UTF8_STRING;
while (x < send) {
const STRLEN cur_len = isC9_STRICT_UTF8_CHAR(x, send);
if (UNLIKELY(! cur_len)) {
return FALSE;
}
x += cur_len;
}
return TRUE;
}
/* The above 3 functions could have been moved into the more general one just
* below, and made #defines that call it with the right 'flags'. They are
* currently kept separate to increase their chances of getting inlined */
/*
=for apidoc is_utf8_string_flags
Returns TRUE if the first C<len> bytes of string C<s> form a valid
UTF-8 string, subject to the restrictions imposed by C<flags>;
returns FALSE otherwise. If C<len> is 0, it will be calculated
using C<strlen(s)> (which means if you use this option, that C<s> can't have
embedded C<NUL> characters and has to have a terminating C<NUL> byte). Note
that all characters being ASCII constitute 'a valid UTF-8 string'.
If C<flags> is 0, this gives the same results as C<L</is_utf8_string>>; if
C<flags> is C<UTF8_DISALLOW_ILLEGAL_INTERCHANGE>, this gives the same results
as C<L</is_strict_utf8_string>>; and if C<flags> is
C<UTF8_DISALLOW_ILLEGAL_C9_INTERCHANGE>, this gives the same results as
C<L</is_c9strict_utf8_string>>. Otherwise C<flags> may be any
combination of the C<UTF8_DISALLOW_I<foo>> flags understood by
C<L</utf8n_to_uvchr>>, with the same meanings.
See also
C<L</is_utf8_invariant_string>>,
C<L</is_utf8_string>>,
C<L</is_utf8_string_loc>>,
C<L</is_utf8_string_loc_flags>>,
C<L</is_utf8_string_loclen>>,
C<L</is_utf8_string_loclen_flags>>,
C<L</is_utf8_fixed_width_buf_flags>>,
C<L</is_utf8_fixed_width_buf_loc_flags>>,
C<L</is_utf8_fixed_width_buf_loclen_flags>>,
C<L</is_strict_utf8_string>>,
C<L</is_strict_utf8_string_loc>>,
C<L</is_strict_utf8_string_loclen>>,
C<L</is_c9strict_utf8_string>>,
C<L</is_c9strict_utf8_string_loc>>,
and
C<L</is_c9strict_utf8_string_loclen>>.
=cut
*/
PERL_STATIC_INLINE bool
S_is_utf8_string_flags(const U8 *s, const STRLEN len, const U32 flags)
{
const U8* const send = s + (len ? len : strlen((const char *)s));
const U8* x = s;
PERL_ARGS_ASSERT_IS_UTF8_STRING_FLAGS;
assert(0 == (flags & ~(UTF8_DISALLOW_ILLEGAL_INTERCHANGE
|UTF8_DISALLOW_ABOVE_31_BIT)));
if (flags == 0) {
return is_utf8_string(s, len);
}
if ((flags & ~UTF8_DISALLOW_ABOVE_31_BIT)
== UTF8_DISALLOW_ILLEGAL_INTERCHANGE)
{
return is_strict_utf8_string(s, len);
}
if ((flags & ~UTF8_DISALLOW_ABOVE_31_BIT)
== UTF8_DISALLOW_ILLEGAL_C9_INTERCHANGE)
{
return is_c9strict_utf8_string(s, len);
}
while (x < send) {
STRLEN cur_len = isUTF8_CHAR_flags(x, send, flags);
if (UNLIKELY(! cur_len)) {
return FALSE;
}
x += cur_len;
}
return TRUE;
}
/*
=for apidoc is_utf8_string_loc
Like C<L</is_utf8_string>> but stores the location of the failure (in the
case of "utf8ness failure") or the location C<s>+C<len> (in the case of
"utf8ness success") in the C<ep> pointer.
See also C<L</is_utf8_string_loclen>>.
=cut
*/
#define is_utf8_string_loc(s, len, ep) is_utf8_string_loclen(s, len, ep, 0)
/*
=for apidoc is_utf8_string_loclen
Like C<L</is_utf8_string>> but stores the location of the failure (in the
case of "utf8ness failure") or the location C<s>+C<len> (in the case of
"utf8ness success") in the C<ep> pointer, and the number of UTF-8
encoded characters in the C<el> pointer.
See also C<L</is_utf8_string_loc>>.
=cut
*/
PERL_STATIC_INLINE bool
Perl_is_utf8_string_loclen(const U8 *s, const STRLEN len, const U8 **ep, STRLEN *el)
{
const U8* const send = s + (len ? len : strlen((const char *)s));
const U8* x = s;
STRLEN outlen = 0;
PERL_ARGS_ASSERT_IS_UTF8_STRING_LOCLEN;
while (x < send) {
const STRLEN cur_len = isUTF8_CHAR(x, send);
if (UNLIKELY(! cur_len)) {
break;
}
x += cur_len;
outlen++;
}
if (el)
*el = outlen;
if (ep) {
*ep = x;
}
return (x == send);
}
/*
=for apidoc is_strict_utf8_string_loc
Like C<L</is_strict_utf8_string>> but stores the location of the failure (in the
case of "utf8ness failure") or the location C<s>+C<len> (in the case of
"utf8ness success") in the C<ep> pointer.
See also C<L</is_strict_utf8_string_loclen>>.
=cut
*/
#define is_strict_utf8_string_loc(s, len, ep) \
is_strict_utf8_string_loclen(s, len, ep, 0)
/*
=for apidoc is_strict_utf8_string_loclen
Like C<L</is_strict_utf8_string>> but stores the location of the failure (in the
case of "utf8ness failure") or the location C<s>+C<len> (in the case of
"utf8ness success") in the C<ep> pointer, and the number of UTF-8
encoded characters in the C<el> pointer.
See also C<L</is_strict_utf8_string_loc>>.
=cut
*/
PERL_STATIC_INLINE bool
S_is_strict_utf8_string_loclen(const U8 *s, const STRLEN len, const U8 **ep, STRLEN *el)
{
const U8* const send = s + (len ? len : strlen((const char *)s));
const U8* x = s;
STRLEN outlen = 0;
PERL_ARGS_ASSERT_IS_STRICT_UTF8_STRING_LOCLEN;
while (x < send) {
const STRLEN cur_len = isSTRICT_UTF8_CHAR(x, send);
if (UNLIKELY(! cur_len)) {
break;
}
x += cur_len;
outlen++;
}
if (el)
*el = outlen;
if (ep) {
*ep = x;
}
return (x == send);
}
/*
=for apidoc is_c9strict_utf8_string_loc
Like C<L</is_c9strict_utf8_string>> but stores the location of the failure (in
the case of "utf8ness failure") or the location C<s>+C<len> (in the case of
"utf8ness success") in the C<ep> pointer.
See also C<L</is_c9strict_utf8_string_loclen>>.
=cut
*/
#define is_c9strict_utf8_string_loc(s, len, ep) \
is_c9strict_utf8_string_loclen(s, len, ep, 0)
/*
=for apidoc is_c9strict_utf8_string_loclen
Like C<L</is_c9strict_utf8_string>> but stores the location of the failure (in
the case of "utf8ness failure") or the location C<s>+C<len> (in the case of
"utf8ness success") in the C<ep> pointer, and the number of UTF-8 encoded
characters in the C<el> pointer.
See also C<L</is_c9strict_utf8_string_loc>>.
=cut
*/
PERL_STATIC_INLINE bool
S_is_c9strict_utf8_string_loclen(const U8 *s, const STRLEN len, const U8 **ep, STRLEN *el)
{
const U8* const send = s + (len ? len : strlen((const char *)s));
const U8* x = s;
STRLEN outlen = 0;
PERL_ARGS_ASSERT_IS_C9STRICT_UTF8_STRING_LOCLEN;
while (x < send) {
const STRLEN cur_len = isC9_STRICT_UTF8_CHAR(x, send);
if (UNLIKELY(! cur_len)) {
break;
}
x += cur_len;
outlen++;
}
if (el)
*el = outlen;
if (ep) {
*ep = x;
}
return (x == send);
}
/*
=for apidoc is_utf8_string_loc_flags
Like C<L</is_utf8_string_flags>> but stores the location of the failure (in the
case of "utf8ness failure") or the location C<s>+C<len> (in the case of
"utf8ness success") in the C<ep> pointer.
See also C<L</is_utf8_string_loclen_flags>>.
=cut
*/
#define is_utf8_string_loc_flags(s, len, ep, flags) \
is_utf8_string_loclen_flags(s, len, ep, 0, flags)
/* The above 3 actual functions could have been moved into the more general one
* just below, and made #defines that call it with the right 'flags'. They are
* currently kept separate to increase their chances of getting inlined */
/*
=for apidoc is_utf8_string_loclen_flags
Like C<L</is_utf8_string_flags>> but stores the location of the failure (in the
case of "utf8ness failure") or the location C<s>+C<len> (in the case of
"utf8ness success") in the C<ep> pointer, and the number of UTF-8
encoded characters in the C<el> pointer.
See also C<L</is_utf8_string_loc_flags>>.
=cut
*/
PERL_STATIC_INLINE bool
S_is_utf8_string_loclen_flags(const U8 *s, const STRLEN len, const U8 **ep, STRLEN *el, const U32 flags)
{
const U8* const send = s + (len ? len : strlen((const char *)s));
const U8* x = s;
STRLEN outlen = 0;
PERL_ARGS_ASSERT_IS_UTF8_STRING_LOCLEN_FLAGS;
assert(0 == (flags & ~(UTF8_DISALLOW_ILLEGAL_INTERCHANGE
|UTF8_DISALLOW_ABOVE_31_BIT)));
if (flags == 0) {
return is_utf8_string_loclen(s, len, ep, el);
}
if ((flags & ~UTF8_DISALLOW_ABOVE_31_BIT)
== UTF8_DISALLOW_ILLEGAL_INTERCHANGE)
{
return is_strict_utf8_string_loclen(s, len, ep, el);
}
if ((flags & ~UTF8_DISALLOW_ABOVE_31_BIT)
== UTF8_DISALLOW_ILLEGAL_C9_INTERCHANGE)
{
return is_c9strict_utf8_string_loclen(s, len, ep, el);
}
while (x < send) {
const STRLEN cur_len = isUTF8_CHAR_flags(x, send, flags);
if (UNLIKELY(! cur_len)) {
break;
}
x += cur_len;
outlen++;
}
if (el)
*el = outlen;
if (ep) {
*ep = x;
}
return (x == send);
}
/*
=for apidoc utf8_distance
Returns the number of UTF-8 characters between the UTF-8 pointers C<a>
and C<b>.
WARNING: use only if you *know* that the pointers point inside the
same UTF-8 buffer.
=cut
*/
PERL_STATIC_INLINE IV
Perl_utf8_distance(pTHX_ const U8 *a, const U8 *b)
{
PERL_ARGS_ASSERT_UTF8_DISTANCE;
return (a < b) ? -1 * (IV) utf8_length(a, b) : (IV) utf8_length(b, a);
}
/*
=for apidoc utf8_hop
Return the UTF-8 pointer C<s> displaced by C<off> characters, either
forward or backward.
WARNING: do not use the following unless you *know* C<off> is within
the UTF-8 data pointed to by C<s> *and* that on entry C<s> is aligned
on the first byte of character or just after the last byte of a character.
=cut
*/
PERL_STATIC_INLINE U8 *
Perl_utf8_hop(const U8 *s, SSize_t off)
{
PERL_ARGS_ASSERT_UTF8_HOP;
/* Note: cannot use UTF8_IS_...() too eagerly here since e.g
* the bitops (especially ~) can create illegal UTF-8.
* In other words: in Perl UTF-8 is not just for Unicode. */
if (off >= 0) {
while (off--)
s += UTF8SKIP(s);
}
else {
while (off++) {
s--;
while (UTF8_IS_CONTINUATION(*s))
s--;
}
}
GCC_DIAG_IGNORE(-Wcast-qual);
return (U8 *)s;
GCC_DIAG_RESTORE;
}
/*
=for apidoc utf8_hop_forward
Return the UTF-8 pointer C<s> displaced by up to C<off> characters,
forward.
C<off> must be non-negative.
C<s> must be before or equal to C<end>.
When moving forward it will not move beyond C<end>.
Will not exceed this limit even if the string is not valid "UTF-8".
=cut
*/
PERL_STATIC_INLINE U8 *
Perl_utf8_hop_forward(const U8 *s, SSize_t off, const U8 *end)
{
PERL_ARGS_ASSERT_UTF8_HOP_FORWARD;
/* Note: cannot use UTF8_IS_...() too eagerly here since e.g
* the bitops (especially ~) can create illegal UTF-8.
* In other words: in Perl UTF-8 is not just for Unicode. */
assert(s <= end);
assert(off >= 0);
while (off--) {
STRLEN skip = UTF8SKIP(s);
if ((STRLEN)(end - s) <= skip) {
GCC_DIAG_IGNORE(-Wcast-qual);
return (U8 *)end;
GCC_DIAG_RESTORE;
}
s += skip;
}
GCC_DIAG_IGNORE(-Wcast-qual);
return (U8 *)s;
GCC_DIAG_RESTORE;
}
/*
=for apidoc utf8_hop_back
Return the UTF-8 pointer C<s> displaced by up to C<off> characters,
backward.
C<off> must be non-positive.
C<s> must be after or equal to C<start>.
When moving backward it will not move before C<start>.
Will not exceed this limit even if the string is not valid "UTF-8".
=cut
*/
PERL_STATIC_INLINE U8 *
Perl_utf8_hop_back(const U8 *s, SSize_t off, const U8 *start)
{
PERL_ARGS_ASSERT_UTF8_HOP_BACK;
/* Note: cannot use UTF8_IS_...() too eagerly here since e.g
* the bitops (especially ~) can create illegal UTF-8.
* In other words: in Perl UTF-8 is not just for Unicode. */
assert(start <= s);
assert(off <= 0);
while (off++ && s > start) {
s--;
while (UTF8_IS_CONTINUATION(*s) && s > start)
s--;
}
GCC_DIAG_IGNORE(-Wcast-qual);
return (U8 *)s;
GCC_DIAG_RESTORE;
}
/*
=for apidoc utf8_hop_safe
Return the UTF-8 pointer C<s> displaced by up to C<off> characters,
either forward or backward.
When moving backward it will not move before C<start>.
When moving forward it will not move beyond C<end>.
Will not exceed those limits even if the string is not valid "UTF-8".
=cut
*/
PERL_STATIC_INLINE U8 *
Perl_utf8_hop_safe(const U8 *s, SSize_t off, const U8 *start, const U8 *end)
{
PERL_ARGS_ASSERT_UTF8_HOP_SAFE;
/* Note: cannot use UTF8_IS_...() too eagerly here since e.g
* the bitops (especially ~) can create illegal UTF-8.
* In other words: in Perl UTF-8 is not just for Unicode. */
assert(start <= s && s <= end);
if (off >= 0) {
return utf8_hop_forward(s, off, end);
}
else {
return utf8_hop_back(s, off, start);
}
}
/*
=for apidoc is_utf8_valid_partial_char
Returns 0 if the sequence of bytes starting at C<s> and looking no further than
S<C<e - 1>> is the UTF-8 encoding, as extended by Perl, for one or more code
points. Otherwise, it returns 1 if there exists at least one non-empty
sequence of bytes that when appended to sequence C<s>, starting at position
C<e> causes the entire sequence to be the well-formed UTF-8 of some code point;
otherwise returns 0.
In other words this returns TRUE if C<s> points to a partial UTF-8-encoded code
point.
This is useful when a fixed-length buffer is being tested for being well-formed
UTF-8, but the final few bytes in it don't comprise a full character; that is,
it is split somewhere in the middle of the final code point's UTF-8
representation. (Presumably when the buffer is refreshed with the next chunk
of data, the new first bytes will complete the partial code point.) This
function is used to verify that the final bytes in the current buffer are in
fact the legal beginning of some code point, so that if they aren't, the
failure can be signalled without having to wait for the next read.
=cut
*/
#define is_utf8_valid_partial_char(s, e) \
is_utf8_valid_partial_char_flags(s, e, 0)
/*
=for apidoc is_utf8_valid_partial_char_flags
Like C<L</is_utf8_valid_partial_char>>, it returns a boolean giving whether
or not the input is a valid UTF-8 encoded partial character, but it takes an
extra parameter, C<flags>, which can further restrict which code points are
considered valid.
If C<flags> is 0, this behaves identically to
C<L</is_utf8_valid_partial_char>>. Otherwise C<flags> can be any combination
of the C<UTF8_DISALLOW_I<foo>> flags accepted by C<L</utf8n_to_uvchr>>. If
there is any sequence of bytes that can complete the input partial character in
such a way that a non-prohibited character is formed, the function returns
TRUE; otherwise FALSE. Non character code points cannot be determined based on
partial character input. But many of the other possible excluded types can be
determined from just the first one or two bytes.
=cut
*/
PERL_STATIC_INLINE bool
S_is_utf8_valid_partial_char_flags(const U8 * const s, const U8 * const e, const U32 flags)
{
PERL_ARGS_ASSERT_IS_UTF8_VALID_PARTIAL_CHAR_FLAGS;
assert(0 == (flags & ~(UTF8_DISALLOW_ILLEGAL_INTERCHANGE
|UTF8_DISALLOW_ABOVE_31_BIT)));
if (s >= e || s + UTF8SKIP(s) <= e) {
return FALSE;
}
return cBOOL(_is_utf8_char_helper(s, e, flags));
}
/*
=for apidoc is_utf8_fixed_width_buf_flags
Returns TRUE if the fixed-width buffer starting at C<s> with length C<len>
is entirely valid UTF-8, subject to the restrictions given by C<flags>;
otherwise it returns FALSE.
If C<flags> is 0, any well-formed UTF-8, as extended by Perl, is accepted
without restriction. If the final few bytes of the buffer do not form a
complete code point, this will return TRUE anyway, provided that
C<L</is_utf8_valid_partial_char_flags>> returns TRUE for them.
If C<flags> in non-zero, it can be any combination of the
C<UTF8_DISALLOW_I<foo>> flags accepted by C<L</utf8n_to_uvchr>>, and with the
same meanings.
This function differs from C<L</is_utf8_string_flags>> only in that the latter
returns FALSE if the final few bytes of the string don't form a complete code
point.
=cut
*/
#define is_utf8_fixed_width_buf_flags(s, len, flags) \
is_utf8_fixed_width_buf_loclen_flags(s, len, 0, 0, flags)
/*
=for apidoc is_utf8_fixed_width_buf_loc_flags
Like C<L</is_utf8_fixed_width_buf_flags>> but stores the location of the
failure in the C<ep> pointer. If the function returns TRUE, C<*ep> will point
to the beginning of any partial character at the end of the buffer; if there is
no partial character C<*ep> will contain C<s>+C<len>.
See also C<L</is_utf8_fixed_width_buf_loclen_flags>>.
=cut
*/
#define is_utf8_fixed_width_buf_loc_flags(s, len, loc, flags) \
is_utf8_fixed_width_buf_loclen_flags(s, len, loc, 0, flags)
/*
=for apidoc is_utf8_fixed_width_buf_loclen_flags
Like C<L</is_utf8_fixed_width_buf_loc_flags>> but stores the number of
complete, valid characters found in the C<el> pointer.
=cut
*/
PERL_STATIC_INLINE bool
S_is_utf8_fixed_width_buf_loclen_flags(const U8 * const s,
const STRLEN len,
const U8 **ep,
STRLEN *el,
const U32 flags)
{
const U8 * maybe_partial;
PERL_ARGS_ASSERT_IS_UTF8_FIXED_WIDTH_BUF_LOCLEN_FLAGS;
if (! ep) {
ep = &maybe_partial;
}
/* If it's entirely valid, return that; otherwise see if the only error is
* that the final few bytes are for a partial character */
return is_utf8_string_loclen_flags(s, len, ep, el, flags)
|| is_utf8_valid_partial_char_flags(*ep, s + len, flags);
}
/* ------------------------------- perl.h ----------------------------- */
/*
=head1 Miscellaneous Functions
=for apidoc AiR|bool|is_safe_syscall|const char *pv|STRLEN len|const char *what|const char *op_name
Test that the given C<pv> doesn't contain any internal C<NUL> characters.
If it does, set C<errno> to C<ENOENT>, optionally warn, and return FALSE.
Return TRUE if the name is safe.
Used by the C<IS_SAFE_SYSCALL()> macro.
=cut
*/
PERL_STATIC_INLINE bool
S_is_safe_syscall(pTHX_ const char *pv, STRLEN len, const char *what, const char *op_name) {
/* While the Windows CE API provides only UCS-16 (or UTF-16) APIs
* perl itself uses xce*() functions which accept 8-bit strings.
*/
PERL_ARGS_ASSERT_IS_SAFE_SYSCALL;
if (len > 1) {
char *null_at;
if (UNLIKELY((null_at = (char *)memchr(pv, 0, len-1)) != NULL)) {
SETERRNO(ENOENT, LIB_INVARG);
Perl_ck_warner(aTHX_ packWARN(WARN_SYSCALLS),
"Invalid \\0 character in %s for %s: %s\\0%s",
what, op_name, pv, null_at+1);
return FALSE;
}
}
return TRUE;
}
/*
Return true if the supplied filename has a newline character
immediately before the first (hopefully only) NUL.
My original look at this incorrectly used the len from SvPV(), but
that's incorrect, since we allow for a NUL in pv[len-1].
So instead, strlen() and work from there.
This allow for the user reading a filename, forgetting to chomp it,
then calling:
open my $foo, "$file\0";
*/
#ifdef PERL_CORE
PERL_STATIC_INLINE bool
S_should_warn_nl(const char *pv) {
STRLEN len;
PERL_ARGS_ASSERT_SHOULD_WARN_NL;
len = strlen(pv);
return len > 0 && pv[len-1] == '\n';
}
#endif
/* ------------------ pp.c, regcomp.c, toke.c, universal.c ------------ */
#define MAX_CHARSET_NAME_LENGTH 2
PERL_STATIC_INLINE const char *
get_regex_charset_name(const U32 flags, STRLEN* const lenp)
{
/* Returns a string that corresponds to the name of the regex character set
* given by 'flags', and *lenp is set the length of that string, which
* cannot exceed MAX_CHARSET_NAME_LENGTH characters */
*lenp = 1;
switch (get_regex_charset(flags)) {
case REGEX_DEPENDS_CHARSET: return DEPENDS_PAT_MODS;
case REGEX_LOCALE_CHARSET: return LOCALE_PAT_MODS;
case REGEX_UNICODE_CHARSET: return UNICODE_PAT_MODS;
case REGEX_ASCII_RESTRICTED_CHARSET: return ASCII_RESTRICT_PAT_MODS;
case REGEX_ASCII_MORE_RESTRICTED_CHARSET:
*lenp = 2;
return ASCII_MORE_RESTRICT_PAT_MODS;
}
/* The NOT_REACHED; hides an assert() which has a rather complex
* definition in perl.h. */
NOT_REACHED; /* NOTREACHED */
return "?"; /* Unknown */
}
/*
Return false if any get magic is on the SV other than taint magic.
*/
PERL_STATIC_INLINE bool
S_sv_only_taint_gmagic(SV *sv) {
MAGIC *mg = SvMAGIC(sv);
PERL_ARGS_ASSERT_SV_ONLY_TAINT_GMAGIC;
while (mg) {
if (mg->mg_type != PERL_MAGIC_taint
&& !(mg->mg_flags & MGf_GSKIP)
&& mg->mg_virtual->svt_get) {
return FALSE;
}
mg = mg->mg_moremagic;
}
return TRUE;
}
/* ------------------ cop.h ------------------------------------------- */
/* Enter a block. Push a new base context and return its address. */
PERL_STATIC_INLINE PERL_CONTEXT *
S_cx_pushblock(pTHX_ U8 type, U8 gimme, SV** sp, I32 saveix)
{
PERL_CONTEXT * cx;
PERL_ARGS_ASSERT_CX_PUSHBLOCK;
CXINC;
cx = CX_CUR();
cx->cx_type = type;
cx->blk_gimme = gimme;
cx->blk_oldsaveix = saveix;
cx->blk_oldsp = (I32)(sp - PL_stack_base);
cx->blk_oldcop = PL_curcop;
cx->blk_oldmarksp = (I32)(PL_markstack_ptr - PL_markstack);
cx->blk_oldscopesp = PL_scopestack_ix;
cx->blk_oldpm = PL_curpm;
cx->blk_old_tmpsfloor = PL_tmps_floor;
PL_tmps_floor = PL_tmps_ix;
CX_DEBUG(cx, "PUSH");
return cx;
}
/* Exit a block (RETURN and LAST). */
PERL_STATIC_INLINE void
S_cx_popblock(pTHX_ PERL_CONTEXT *cx)
{
PERL_ARGS_ASSERT_CX_POPBLOCK;
CX_DEBUG(cx, "POP");
/* these 3 are common to cx_popblock and cx_topblock */
PL_markstack_ptr = PL_markstack + cx->blk_oldmarksp;
PL_scopestack_ix = cx->blk_oldscopesp;
PL_curpm = cx->blk_oldpm;
/* LEAVE_SCOPE() should have made this true. /(?{})/ cheats
* and leaves a CX entry lying around for repeated use, so
* skip for multicall */ \
assert( (CxTYPE(cx) == CXt_SUB && CxMULTICALL(cx))
|| PL_savestack_ix == cx->blk_oldsaveix);
PL_curcop = cx->blk_oldcop;
PL_tmps_floor = cx->blk_old_tmpsfloor;
}
/* Continue a block elsewhere (e.g. NEXT, REDO, GOTO).
* Whereas cx_popblock() restores the state to the point just before
* cx_pushblock() was called, cx_topblock() restores it to the point just
* *after* cx_pushblock() was called. */
PERL_STATIC_INLINE void
S_cx_topblock(pTHX_ PERL_CONTEXT *cx)
{
PERL_ARGS_ASSERT_CX_TOPBLOCK;
CX_DEBUG(cx, "TOP");
/* these 3 are common to cx_popblock and cx_topblock */
PL_markstack_ptr = PL_markstack + cx->blk_oldmarksp;
PL_scopestack_ix = cx->blk_oldscopesp;
PL_curpm = cx->blk_oldpm;
PL_stack_sp = PL_stack_base + cx->blk_oldsp;
}
PERL_STATIC_INLINE void
S_cx_pushsub(pTHX_ PERL_CONTEXT *cx, CV *cv, OP *retop, bool hasargs)
{
U8 phlags = CX_PUSHSUB_GET_LVALUE_MASK(Perl_was_lvalue_sub);
PERL_ARGS_ASSERT_CX_PUSHSUB;
PERL_DTRACE_PROBE_ENTRY(cv);
cx->blk_sub.cv = cv;
cx->blk_sub.olddepth = CvDEPTH(cv);
cx->blk_sub.prevcomppad = PL_comppad;
cx->cx_type |= (hasargs) ? CXp_HASARGS : 0;
cx->blk_sub.retop = retop;
SvREFCNT_inc_simple_void_NN(cv);
cx->blk_u16 = PL_op->op_private & (phlags|OPpDEREF);
}
/* subsets of cx_popsub() */
PERL_STATIC_INLINE void
S_cx_popsub_common(pTHX_ PERL_CONTEXT *cx)
{
CV *cv;
PERL_ARGS_ASSERT_CX_POPSUB_COMMON;
assert(CxTYPE(cx) == CXt_SUB);
PL_comppad = cx->blk_sub.prevcomppad;
PL_curpad = LIKELY(PL_comppad) ? AvARRAY(PL_comppad) : NULL;
cv = cx->blk_sub.cv;
CvDEPTH(cv) = cx->blk_sub.olddepth;
cx->blk_sub.cv = NULL;
SvREFCNT_dec(cv);
}
/* handle the @_ part of leaving a sub */
PERL_STATIC_INLINE void
S_cx_popsub_args(pTHX_ PERL_CONTEXT *cx)
{
AV *av;
PERL_ARGS_ASSERT_CX_POPSUB_ARGS;
assert(CxTYPE(cx) == CXt_SUB);
assert(AvARRAY(MUTABLE_AV(
PadlistARRAY(CvPADLIST(cx->blk_sub.cv))[
CvDEPTH(cx->blk_sub.cv)])) == PL_curpad);
CX_POP_SAVEARRAY(cx);
av = MUTABLE_AV(PAD_SVl(0));
if (UNLIKELY(AvREAL(av)))
/* abandon @_ if it got reified */
clear_defarray(av, 0);
else {
CLEAR_ARGARRAY(av);
}
}
PERL_STATIC_INLINE void
S_cx_popsub(pTHX_ PERL_CONTEXT *cx)
{
PERL_ARGS_ASSERT_CX_POPSUB;
assert(CxTYPE(cx) == CXt_SUB);
PERL_DTRACE_PROBE_RETURN(cx->blk_sub.cv);
if (CxHASARGS(cx))
cx_popsub_args(cx);
cx_popsub_common(cx);
}
PERL_STATIC_INLINE void
S_cx_pushformat(pTHX_ PERL_CONTEXT *cx, CV *cv, OP *retop, GV *gv)
{
PERL_ARGS_ASSERT_CX_PUSHFORMAT;
cx->blk_format.cv = cv;
cx->blk_format.retop = retop;
cx->blk_format.gv = gv;
cx->blk_format.dfoutgv = PL_defoutgv;
cx->blk_format.prevcomppad = PL_comppad;
cx->blk_u16 = 0;
SvREFCNT_inc_simple_void_NN(cv);
CvDEPTH(cv)++;
SvREFCNT_inc_void(cx->blk_format.dfoutgv);
}
PERL_STATIC_INLINE void
S_cx_popformat(pTHX_ PERL_CONTEXT *cx)
{
CV *cv;
GV *dfout;
PERL_ARGS_ASSERT_CX_POPFORMAT;
assert(CxTYPE(cx) == CXt_FORMAT);
dfout = cx->blk_format.dfoutgv;
setdefout(dfout);
cx->blk_format.dfoutgv = NULL;
SvREFCNT_dec_NN(dfout);
PL_comppad = cx->blk_format.prevcomppad;
PL_curpad = LIKELY(PL_comppad) ? AvARRAY(PL_comppad) : NULL;
cv = cx->blk_format.cv;
cx->blk_format.cv = NULL;
--CvDEPTH(cv);
SvREFCNT_dec_NN(cv);
}
PERL_STATIC_INLINE void
S_cx_pusheval(pTHX_ PERL_CONTEXT *cx, OP *retop, SV *namesv)
{
PERL_ARGS_ASSERT_CX_PUSHEVAL;
cx->blk_eval.retop = retop;
cx->blk_eval.old_namesv = namesv;
cx->blk_eval.old_eval_root = PL_eval_root;
cx->blk_eval.cur_text = PL_parser ? PL_parser->linestr : NULL;
cx->blk_eval.cv = NULL; /* later set by doeval_compile() */
cx->blk_eval.cur_top_env = PL_top_env;
assert(!(PL_in_eval & ~ 0x3F));
assert(!(PL_op->op_type & ~0x1FF));
cx->blk_u16 = (PL_in_eval & 0x3F) | ((U16)PL_op->op_type << 7);
}
PERL_STATIC_INLINE void
S_cx_popeval(pTHX_ PERL_CONTEXT *cx)
{
SV *sv;
PERL_ARGS_ASSERT_CX_POPEVAL;
assert(CxTYPE(cx) == CXt_EVAL);
PL_in_eval = CxOLD_IN_EVAL(cx);
assert(!(PL_in_eval & 0xc0));
PL_eval_root = cx->blk_eval.old_eval_root;
sv = cx->blk_eval.cur_text;
if (sv && CxEVAL_TXT_REFCNTED(cx)) {
cx->blk_eval.cur_text = NULL;
SvREFCNT_dec_NN(sv);
}
sv = cx->blk_eval.old_namesv;
if (sv) {
cx->blk_eval.old_namesv = NULL;
SvREFCNT_dec_NN(sv);
}
}
/* push a plain loop, i.e.
* { block }
* while (cond) { block }
* for (init;cond;continue) { block }
* This loop can be last/redo'ed etc.
*/
PERL_STATIC_INLINE void
S_cx_pushloop_plain(pTHX_ PERL_CONTEXT *cx)
{
PERL_ARGS_ASSERT_CX_PUSHLOOP_PLAIN;
cx->blk_loop.my_op = cLOOP;
}
/* push a true for loop, i.e.
* for var (list) { block }
*/
PERL_STATIC_INLINE void
S_cx_pushloop_for(pTHX_ PERL_CONTEXT *cx, void *itervarp, SV* itersave)
{
PERL_ARGS_ASSERT_CX_PUSHLOOP_FOR;
/* this one line is common with cx_pushloop_plain */
cx->blk_loop.my_op = cLOOP;
cx->blk_loop.itervar_u.svp = (SV**)itervarp;
cx->blk_loop.itersave = itersave;
#ifdef USE_ITHREADS
cx->blk_loop.oldcomppad = PL_comppad;
#endif
}
/* pop all loop types, including plain */
PERL_STATIC_INLINE void
S_cx_poploop(pTHX_ PERL_CONTEXT *cx)
{
PERL_ARGS_ASSERT_CX_POPLOOP;
assert(CxTYPE_is_LOOP(cx));
if ( CxTYPE(cx) == CXt_LOOP_ARY
|| CxTYPE(cx) == CXt_LOOP_LAZYSV)
{
/* Free ary or cur. This assumes that state_u.ary.ary
* aligns with state_u.lazysv.cur. See cx_dup() */
SV *sv = cx->blk_loop.state_u.lazysv.cur;
cx->blk_loop.state_u.lazysv.cur = NULL;
SvREFCNT_dec_NN(sv);
if (CxTYPE(cx) == CXt_LOOP_LAZYSV) {
sv = cx->blk_loop.state_u.lazysv.end;
cx->blk_loop.state_u.lazysv.end = NULL;
SvREFCNT_dec_NN(sv);
}
}
if (cx->cx_type & (CXp_FOR_PAD|CXp_FOR_GV)) {
SV *cursv;
SV **svp = (cx)->blk_loop.itervar_u.svp;
if ((cx->cx_type & CXp_FOR_GV))
svp = &GvSV((GV*)svp);
cursv = *svp;
*svp = cx->blk_loop.itersave;
cx->blk_loop.itersave = NULL;
SvREFCNT_dec(cursv);
}
}
PERL_STATIC_INLINE void
S_cx_pushwhen(pTHX_ PERL_CONTEXT *cx)
{
PERL_ARGS_ASSERT_CX_PUSHWHEN;
cx->blk_givwhen.leave_op = cLOGOP->op_other;
}
PERL_STATIC_INLINE void
S_cx_popwhen(pTHX_ PERL_CONTEXT *cx)
{
PERL_ARGS_ASSERT_CX_POPWHEN;
assert(CxTYPE(cx) == CXt_WHEN);
PERL_UNUSED_ARG(cx);
PERL_UNUSED_CONTEXT;
/* currently NOOP */
}
PERL_STATIC_INLINE void
S_cx_pushgiven(pTHX_ PERL_CONTEXT *cx, SV *orig_defsv)
{
PERL_ARGS_ASSERT_CX_PUSHGIVEN;
cx->blk_givwhen.leave_op = cLOGOP->op_other;
cx->blk_givwhen.defsv_save = orig_defsv;
}
PERL_STATIC_INLINE void
S_cx_popgiven(pTHX_ PERL_CONTEXT *cx)
{
SV *sv;
PERL_ARGS_ASSERT_CX_POPGIVEN;
assert(CxTYPE(cx) == CXt_GIVEN);
sv = GvSV(PL_defgv);
GvSV(PL_defgv) = cx->blk_givwhen.defsv_save;
cx->blk_givwhen.defsv_save = NULL;
SvREFCNT_dec(sv);
}
/*
* ex: set ts=8 sts=4 sw=4 et:
*/
|