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
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
|
/*
*******************************************************************************
*
* Copyright (C) 2005, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
* file name: utext.cpp
* encoding: US-ASCII
* tab size: 8 (not used)
* indentation:4
*
* created on: 2005apr12
* created by: Markus W. Scherer
*/
#include "unicode/utypes.h"
#include "unicode/ustring.h"
#include "unicode/unistr.h"
#include "unicode/utext.h"
#include "ustr_imp.h"
#include "cmemory.h"
#include "cstring.h"
#include "uassert.h"
#define I32_FLAG(bitIndex) ((int32_t)1<<(bitIndex))
static UBool
utext_access(UText *ut, int32_t index, UBool forward) {
return ut->access(ut, index, forward, &ut->chunk);
}
U_DRAFT UBool U_EXPORT2
utext_moveIndex32(UText *ut, int32_t delta) {
UBool retval = TRUE;
if(delta>0) {
do {
if(ut->chunk.offset>=ut->chunk.length && !utext_access(ut, ut->chunk.nativeLimit, TRUE)) {
retval = FALSE;
break;
}
U16_FWD_1(ut->chunk.contents, ut->chunk.offset, ut->chunk.length);
} while(--delta>0);
} else if (delta<0) {
do {
if(ut->chunk.offset<=0 && !utext_access(ut, ut->chunk.nativeStart, FALSE)) {
retval = FALSE;
break;
}
U16_BACK_1(ut->chunk.contents, 0, ut->chunk.offset);
} while(++delta<0);
}
return retval;
}
U_DRAFT int32_t U_EXPORT2
utext_nativeLength(UText *ut) {
return ut->nativeLength(ut);
}
U_DRAFT UBool U_EXPORT2
utext_isLengthExpensive(const UText *ut) {
UBool r = (ut->providerProperties & I32_FLAG(UTEXT_PROVIDER_LENGTH_IS_EXPENSIVE)) != 0;
return r;
}
U_DRAFT int32_t U_EXPORT2
utext_getNativeIndex(UText *ut) {
if(!ut->chunk.nonUTF16Indexes || ut->chunk.offset==0) {
return ut->chunk.nativeStart+ut->chunk.offset;
} else {
return ut->mapOffsetToNative(ut, ut->chunk.offset);
}
}
U_DRAFT void U_EXPORT2
utext_setNativeIndex(UText *ut, int32_t index) {
if(index<ut->chunk.nativeStart || ut->chunk.nativeLimit<index) {
// The desired position is outside of the current chunk.
// Access the new position. Assume a forward iteration from here,
// which will also be optimimum for a single random access.
// Reverse iterations may suffer slightly.
ut->access(ut, index, TRUE, &ut->chunk);
} else if(ut->chunk.nonUTF16Indexes) {
ut->chunk.offset=ut->mapNativeIndexToUTF16(ut, index);
} else {
ut->chunk.offset=index-ut->chunk.nativeStart;
// Our convention is that the index must always be on a code point boundary.
// If we are somewhere in the middle of a utf-16 buffer, check that new index
// is not in the middle of a surrogate pair.
if (index>ut->chunk.nativeStart && index < ut->chunk.nativeLimit) {
UChar c = ut->chunk.contents[ut->chunk.offset];
if (U16_TRAIL(c)) {
utext_current32(ut); // force index to the start of the curent code point.
}
}
}
}
U_DRAFT UChar32 U_EXPORT2
utext_current32(UText *ut) {
UChar32 c = U_SENTINEL;
if (ut->chunk.offset==ut->chunk.length) {
// Current position is just off the end of the chunk.
// Can also happen at startup, with a zero length chunk at zero offset.
ut->access(ut, ut->chunk.nativeLimit, TRUE, &ut->chunk);
}
if (ut->chunk.offset < ut->chunk.length) {
c = ut->chunk.contents[ut->chunk.offset];
if (U16_IS_SURROGATE(c)) {
// looking at a surrogate. Could be unpaired, need to be careful.
// Speed doesn't matter, will be very rare.
UChar32 char16AtIndex = c;
U16_GET(ut->chunk.contents, 0, ut->chunk.offset, ut->chunk.length, c);
if (U16_IS_TRAIL(char16AtIndex) && U_IS_SUPPLEMENTARY(c)) {
// Incoming position pointed to the trailing part of a supplementary pair.
// Move offset to point to the lead surrogate. This is needed because utext_current()
// is used internally to force code point alignment. When called from
// the outside we should always be pre-aligned, but this check doesn't hurt.
ut->chunk.offset--;
}
}
}
return c;
}
U_DRAFT UChar32 U_EXPORT2
utext_char32At(UText *ut, int32_t nativeIndex) {
UChar32 c = U_SENTINEL;
utext_setNativeIndex(ut, nativeIndex);
if (ut->chunk.offset < ut->chunk.length) {
c = ut->chunk.contents[ut->chunk.offset];
if (c >= 0xd800) {
c = utext_current32(ut);
}
}
return c;
}
U_DRAFT UChar32 U_EXPORT2
utext_next32(UText *ut) {
UTextChunk *chunk = &ut->chunk;
UChar32 c = U_SENTINEL;
if (chunk->offset >= chunk->length) {
if (ut->access(ut, chunk->nativeLimit, TRUE, chunk) == FALSE) {
goto next32_return;
}
}
c = chunk->contents[chunk->offset++];
if (U16_IS_SURROGATE(c)) {
// looking at a surrogate. Could be unpaired, need to be careful.
// Speed doesn't matter, will be very rare.
chunk->offset--;
c = utext_current32(ut);
chunk->offset++;
if (U_IS_SUPPLEMENTARY(c)) {
chunk->offset++;
}
}
next32_return:
return c;
}
U_DRAFT UChar32 U_EXPORT2
utext_previous32(UText *ut) {
UTextChunk *chunk = &ut->chunk;
int32_t offset = chunk->offset;
UChar32 c = U_SENTINEL;
if (offset <= 0) {
if (ut->access(ut, chunk->nativeStart, FALSE, chunk) == FALSE) {
goto prev32_return;
}
offset = chunk->offset;
}
c = chunk->contents[--offset];
chunk->offset = offset;
if (U16_IS_SURROGATE(c)) {
// Note that utext_current() will move the chunk offset to the lead surrogate
// if we come in referring to trail half of a surrogate pair.
c = utext_current32(ut);
}
prev32_return:
return c;
}
U_DRAFT UChar32 U_EXPORT2
utext_next32From(UText *ut, int32_t index) {
UTextChunk *chunk = &ut->chunk;
UChar32 c = U_SENTINEL;
if(index<chunk->nativeStart || index>=chunk->nativeLimit) {
if(!ut->access(ut, index, TRUE, chunk)) {
// no chunk available here
goto next32return;
}
} else if(chunk->nonUTF16Indexes) {
chunk->offset = ut->mapNativeIndexToUTF16(ut, index);
} else {
chunk->offset = index - chunk->nativeStart;
}
c = chunk->contents[chunk->offset++];
if (U16_IS_SURROGATE(c)) {
// Surrogate code unit. Speed doesn't matter, let plain next32() do the work.
chunk->offset--; // undo the ++, above.
c = utext_next32(ut);
}
next32return:
return c;
}
U_DRAFT UChar32 U_EXPORT2
utext_previous32From(UText *ut, int32_t index) {
UTextChunk *chunk = &ut->chunk;
UChar32 c = U_SENTINEL;
if(index<=chunk->nativeStart || index>chunk->nativeLimit) {
// Requested native index is outside of the current chunk.
if(!ut->access(ut, index, FALSE, chunk)) {
// no chunk available here
goto prev32return;
}
} else if(chunk->nonUTF16Indexes) {
chunk->offset=ut->mapNativeIndexToUTF16(ut, index);
} else {
// This chunk uses UTF-16 indexing. Index into it.
chunk->offset = index - chunk->nativeStart;
// put offset onto a code point boundary if it isn't there already.
if (index>ut->chunk.nativeStart && index < ut->chunk.nativeLimit) {
c = chunk->contents[chunk->offset];
if (U16_TRAIL(c)) {
utext_current32(ut); // force index to the start of the curent code point.
}
}
}
if (chunk->offset<=0) {
// already at the start of text. Return U_SENTINEL.
goto prev32return;
}
// Do the operation assuming that there are no surrogates involved. Fast, common case.
chunk->offset--;
c = chunk->contents[chunk->offset];
// Check for the char being a surrogate, get the whole char if it is.
if (U16_IS_SURROGATE(c)) {
c = utext_current32(ut);
}
prev32return:
return c;
}
U_DRAFT int32_t U_EXPORT2
utext_extract(UText *ut,
int32_t start, int32_t limit,
UChar *dest, int32_t destCapacity,
UErrorCode *status) {
return ut->extract(ut, start, limit, dest, destCapacity, status);
}
U_DRAFT UBool U_EXPORT2
utext_isWritable(const UText *ut)
{
UBool b = (ut->providerProperties & I32_FLAG(UTEXT_PROVIDER_WRITABLE)) != 0;
return b;
}
U_DRAFT UBool U_EXPORT2
utext_hasMetaData(const UText *ut)
{
UBool b = (ut->providerProperties & I32_FLAG(UTEXT_PROVIDER_HAS_META_DATA)) != 0;
return b;
}
U_DRAFT int32_t U_EXPORT2
utext_replace(UText *ut,
int32_t nativeStart, int32_t nativeLimit,
const UChar *replacementText, int32_t replacementLength,
UErrorCode *status)
{
if (U_FAILURE(*status)) {
return 0;
}
if ((ut->providerProperties & I32_FLAG(UTEXT_PROVIDER_WRITABLE)) == 0) {
*status = U_NO_WRITE_PERMISSION;
return 0;
}
int32_t i = ut->replace(ut, nativeStart, nativeLimit, replacementText, replacementLength, status);
return i;
}
U_DRAFT void U_EXPORT2
utext_copy(UText *ut,
int32_t nativeStart, int32_t nativeLimit,
int32_t destIndex,
UBool move,
UErrorCode *status)
{
if (U_FAILURE(*status)) {
return;
}
if ((ut->providerProperties & I32_FLAG(UTEXT_PROVIDER_WRITABLE)) == 0) {
*status = U_NO_WRITE_PERMISSION;
return;
}
ut->copy(ut, nativeStart, nativeLimit, destIndex, move, status);
}
U_DRAFT UText * U_EXPORT2
utext_clone(UText *dest, const UText *src, UBool deep, UErrorCode *status) {
return src->clone(dest, src, deep, status);
}
//------------------------------------------------------------------------------
//
// UText common functions implementation
//
//------------------------------------------------------------------------------
//
// UText.flags bit definitions
//
enum {
UTEXT_HEAP_ALLOCATED = 1, // 1 if ICU has allocated this UText struct on the heap.
// 0 if caller provided storage for the UText.
UTEXT_EXTRA_HEAP_ALLOCATED = 2, // 1 if ICU has allocated extra storage as a separate
// heap block.
// 0 if there is no separate allocation. Either no extra
// storage was requested, or it is appended to the end
// of the main UText storage.
UTEXT_OPEN = 4 // 1 if this UText is currently open
// 0 if this UText is not open.
};
//
// Extended form of a UText. The purpose is to aid in computing the total size required
// when a provider asks for a UText to be allocated with extra storage.
struct ExtendedUText {
UText ut;
UAlignedMemory extension;
};
static const UText emptyText = UTEXT_INITIALIZER;
U_DRAFT UText * U_EXPORT2
utext_setup(UText *ut, int32_t extraSpace, UErrorCode *status) {
if (U_FAILURE(*status)) {
return ut;
}
if (ut == NULL) {
// We need to heap-allocate storage for the new UText
int32_t spaceRequired = sizeof(UText);
if (extraSpace > 0) {
spaceRequired = sizeof(ExtendedUText) + extraSpace - sizeof(UAlignedMemory);
}
ut = (UText *)uprv_malloc(spaceRequired);
if (ut == NULL) {
*status = U_MEMORY_ALLOCATION_ERROR;
} else {
*ut = emptyText;
ut->flags |= UTEXT_HEAP_ALLOCATED;
if (spaceRequired>0) {
ut->extraSize = extraSpace;
ut->pExtra = &((ExtendedUText *)ut)->extension;
uprv_memset(ut->pExtra, 0, extraSpace); // Purify whines about copying untouched extra [buffer]
// space when cloning, so init it now.
}
}
} else {
// We have been supplied with an already existing UText.
// Verify that it really appears to be a UText.
if (ut->magic != UTEXT_MAGIC) {
*status = U_ILLEGAL_ARGUMENT_ERROR;
return ut;
}
// If the ut is already open and there's a provider supplied close
// function, call it.
if ((ut->flags & UTEXT_OPEN) && ut->close != NULL) {
ut->close(ut);
}
ut->flags &= ~UTEXT_OPEN;
// If extra space was requested by our caller, check whether
// sufficient already exists, and allocate new if needed.
if (extraSpace > ut->extraSize) {
// Need more space. If there is existing separately allocated space,
// delete it first, then allocate new space.
if (ut->flags & UTEXT_EXTRA_HEAP_ALLOCATED) {
uprv_free(ut->pExtra);
ut->extraSize = 0;
}
ut->pExtra = uprv_malloc(extraSpace);
if (ut->pExtra == NULL) {
*status = U_MEMORY_ALLOCATION_ERROR;
} else {
ut->extraSize = extraSpace;
ut->flags |= UTEXT_EXTRA_HEAP_ALLOCATED;
uprv_memset(ut->pExtra, 0, extraSpace);
}
}
}
if (U_SUCCESS(*status)) {
ut->flags |= UTEXT_OPEN;
}
return ut;
}
U_DRAFT UText * U_EXPORT2
utext_close(UText *ut) {
if (ut==NULL ||
ut->magic != UTEXT_MAGIC ||
(ut->flags & UTEXT_OPEN) == 0)
{
// The supplied ut is not an open UText.
// Do nothing.
return ut;
}
// If the provider gave us a close function, call it now.
// This will clean up anything allocated specifically by the provider.
if (ut->close != NULL) {
ut->close(ut);
}
ut->flags &= ~UTEXT_OPEN;
// If we (the framework) allocated the UText or subsidiary storage,
// delete it.
if (ut->flags & UTEXT_EXTRA_HEAP_ALLOCATED) {
uprv_free(ut->pExtra);
ut->pExtra = NULL;
}
if (ut->flags & UTEXT_HEAP_ALLOCATED) {
// This UText was allocated by UText setup. We need to free it.
// Clear magic, so we can detect if the user messes up and immediately
// tries to reopen another UText using the deleted storage.
ut->magic = 0;
uprv_free(ut);
ut = NULL;
}
return ut;
}
//
// resetChunk When an access fails for attempting to get text that is out-of-range
// this function puts the chunk into a benign state with the index at the
// at the requested position.
//
// If there is a pre-existing chunk that is adjacent to the index
// preserve the chunk, otherwise set up a dummy zero length chunk.
//
static void
resetChunk(UTextChunk *chunk, int32_t index) {
if (index==chunk->nativeLimit) {
chunk->offset = chunk->length;
} else if (index==chunk->nativeStart) {
chunk->offset = 0;
} else {
chunk->length = 0;
chunk->nativeStart = index;
chunk->nativeLimit = index;
chunk->offset = 0;
}
}
//
// invalidateChunk Reset a chunk to have no contents, so that the next call
// to access will new data to load.
// This is needed when copy/move/replace operate directly on the
// backing text, potentially putting it out of sync with the
// contents in the chunk.
//
static void
invalidateChunk(UTextChunk *chunk) {
chunk->length = 0;
chunk->nativeLimit = 0;
chunk->nativeStart = 0;
chunk->offset = 0;
}
U_CDECL_BEGIN
//
// Clone. This is a generic copy-the-utext-by-value clone function that can be
// used as-is with some utext types, and as helper by other clones.
//
static UText * U_CALLCONV
shallowTextClone(UText * dest, const UText * src, UErrorCode * status) {
if (U_FAILURE(*status)) {
return NULL;
}
int32_t srcExtraSize = src->extraSize;
//
// Use the generic text_setup to allocate storage if required.
//
dest = utext_setup(dest, srcExtraSize, status);
if (U_FAILURE(*status)) {
return dest;
}
//
// flags (how the UText was allocated) and the pointer to the
// extra storage must retain the values in the cloned utext that
// were set up by utext_setup. Save them separately before
// copying the whole struct.
//
void *destExtra = dest->pExtra;
int32_t flags = dest->flags;
//
// Copy the whole UText struct by value.
// Any "Extra" storage is copied also.
//
int sizeToCopy = src->sizeOfStruct;
if (sizeToCopy > dest->sizeOfStruct) {
sizeToCopy = dest->sizeOfStruct;
}
uprv_memcpy(dest, src, sizeToCopy);
dest->pExtra = destExtra;
dest->flags = flags;
if (srcExtraSize > 0) {
uprv_memcpy(dest->pExtra, src->pExtra, srcExtraSize);
}
return dest;
}
U_CDECL_END
//------------------------------------------------------------------------------
//
// UText implementation for UTF-8 strings (read-only)
//
// Use of UText data members:
// context pointer to UTF-8 string
// utext.b is the input string length (bytes).
// utext.p pointer to allocated utf-8 string if owned by this utext (after a clone)
// utext.q pointer to the filled part of the Map array.
//
// TODO: make creation of the index mapping array lazy.
// Create it for a chunk the first time the user asks for an index.
//
//------------------------------------------------------------------------------
enum { UTF8_TEXT_CHUNK_SIZE=10 };
struct UTF8Extra {
/*
* Chunk UChars.
* +1 to simplify filling with surrogate pair at the end.
*/
UChar s[UTF8_TEXT_CHUNK_SIZE+1];
/*
* Index map, from UTF-16 indexes into s back to native indexes.
* +2: length of s[] + one more for chunk limit index.
*
* When accessing preceding text, chunk.contents may point into the middle
* of s[].
*/
int32_t map[UTF8_TEXT_CHUNK_SIZE+2];
};
// because backwards iteration fills the buffers starting at the end and
// working towards the front, the filled part of the buffers may not begin
// at the start of the available storage for the buffers.
U_CDECL_BEGIN
static int32_t U_CALLCONV
utf8TextLength(UText *ut) {
return ut->b;
}
static UBool U_CALLCONV
utf8TextAccess(UText *ut, int32_t index, UBool forward, UTextChunk *chunk) {
const uint8_t *s8=(const uint8_t *)ut->context;
UChar32 c;
int32_t i;
int32_t length = ut->b; // Length of original utf-8
UTF8Extra *ut8e = (UTF8Extra *)ut->pExtra;
UChar *u16buf = ut8e->s;
int32_t *map = ut8e->map;
if (index<0) {
index = 0;
} else if (index>length) {
index = length;
}
if(forward) {
if(index >= length) {
resetChunk(chunk, length);
return FALSE;
}
c=s8[index];
if(c<=0x7f) {
// get a run of ASCII characters.
// Even if we don't fill the buffer, we will stop with the first
// non-ascii char, so that the buffer can use utf-16 indexing.
chunk->nativeStart=index;
u16buf[0]=(UChar)c;
for(i=1, ++index;
i<UTF8_TEXT_CHUNK_SIZE && index<length && (c=s8[index])<=0x7f;
++i, ++index
) {
u16buf[i]=(UChar)c;
}
chunk->nonUTF16Indexes=FALSE;
} else {
// get a chunk of characters starting with a non-ASCII one
U8_SET_CP_START(s8, 0, index); // put utf-8 index at first byte of char, if not there already.
chunk->nativeStart=index;
for(i=0; i<UTF8_TEXT_CHUNK_SIZE && index<length; ) {
// i is utf-16 index into chunk buffer.
// index is utf-8 index into original string
map[i]=index;
map[i+1]=index; // in case there is a trail surrogate
U8_NEXT(s8, index, length, c);
if(c<0) {
c=0xfffd; // use SUB for illegal sequences
}
U16_APPEND_UNSAFE(u16buf, i, c); // post-increments i.
}
map[i]=index;
chunk->nonUTF16Indexes=TRUE;
}
chunk->contents = u16buf;
chunk->length = i;
chunk->nativeLimit = index;
ut->q = map;
chunk->offset = 0; // chunkOffset corresponding to index
return TRUE;
} else {
// Reverse Access. The chunk buffer must be filled so as to contain the
// character preceding the specified index.
if(index<=0) {
resetChunk(chunk, 0);
return FALSE;
}
c=s8[index-1];
if(c<=0x7f) {
// get a chunk of ASCII characters. Don't build the index map
chunk->nativeLimit=index;
i=UTF8_TEXT_CHUNK_SIZE;
do {
u16buf[--i]=(UChar)c;
--index;
} while(i>0 && index>0 && (c=s8[index-1])<=0x7f);
chunk->nonUTF16Indexes=FALSE;
} else {
// get a chunk of characters starting with a non-ASCII one
if(index<length) {
U8_SET_CP_START(s8, 0, index);
}
chunk->nativeLimit=index;
i=UTF8_TEXT_CHUNK_SIZE;
map[i]=index; // map position for char following the last one in the buffer.
do {
// i is utf-16 index into chunk buffer.
// index is utf-8 index into original string
U8_PREV(s8, 0, index, c);
if(c<0) {
c=0xfffd; // use SUB for illegal sequences
}
if(c<=0xffff) {
u16buf[--i]=(UChar)c;
map[i]=index;
} else {
// We've got a supplementary char
if (i<2) {
// Both halves of the surrogate pair wont fit in the chunk buffer.
// Stop without putting either half in.
U8_NEXT(s8, index, length, c); // restore index.
break;
}
u16buf[--i]=U16_TRAIL(c);
map[i]=index;
u16buf[--i]=U16_LEAD(c);
map[i]=index;
}
} while(i>0 && index>0);
// Because we have filled the map & chunk buffers from back to front,
// the start position for accesses may not be at the start of the
// available storage.
ut->q = map+i;
chunk->nonUTF16Indexes=TRUE;
}
// Common reverse iteration, for both UTF16 and non-UTIF16 indexes.
chunk->contents = u16buf+i;
chunk->length = (UTF8_TEXT_CHUNK_SIZE)-i;
chunk->nativeStart = index;
chunk->offset = chunk->length; // chunkOffset corresponding to index
return TRUE;
}
}
//
// This is a slightly modified copy of u_strFromUTF8,
// Inserts a Replacement Char rather than failing on invalid UTF-8
// Removes unnecessary features.
//
static UChar*
utext_strFromUTF8(UChar *dest,
int32_t destCapacity,
int32_t *pDestLength,
const char* src,
int32_t srcLength, // required. NUL terminated not supported.
UErrorCode *pErrorCode
)
{
UChar *pDest = dest;
UChar *pDestLimit = dest+destCapacity;
UChar32 ch=0;
int32_t index = 0;
int32_t reqLength = 0;
uint8_t* pSrc = (uint8_t*) src;
while((index < srcLength)&&(pDest<pDestLimit)){
ch = pSrc[index++];
if(ch <=0x7f){
*pDest++=(UChar)ch;
}else{
ch=utf8_nextCharSafeBody(pSrc, &index, srcLength, ch, -1);
if(ch<0){
ch = 0xfffd;
}
if(ch<=0xFFFF){
*(pDest++)=(UChar)ch;
}else{
*(pDest++)=UTF16_LEAD(ch);
if(pDest<pDestLimit){
*(pDest++)=UTF16_TRAIL(ch);
}else{
reqLength++;
break;
}
}
}
}
/* donot fill the dest buffer just count the UChars needed */
while(index < srcLength){
ch = pSrc[index++];
if(ch <= 0x7f){
reqLength++;
}else{
ch=utf8_nextCharSafeBody(pSrc, &index, srcLength, ch, -1);
if(ch<0){
ch = 0xfffd;
}
reqLength+=UTF_CHAR_LENGTH(ch);
}
}
reqLength+=(int32_t)(pDest - dest);
if(pDestLength){
*pDestLength = reqLength;
}
/* Terminate the buffer */
u_terminateUChars(dest,destCapacity,reqLength,pErrorCode);
return dest;
}
static int32_t U_CALLCONV
utf8TextExtract(UText *ut,
int32_t start, int32_t limit,
UChar *dest, int32_t destCapacity,
UErrorCode *pErrorCode) {
if(U_FAILURE(*pErrorCode)) {
return 0;
}
if(destCapacity<0 || (dest==NULL && destCapacity>0)) {
*pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
return 0;
}
if(start<0 || start>limit) {
*pErrorCode=U_INDEX_OUTOFBOUNDS_ERROR;
return 0;
}
if (limit>ut->b) {
limit = ut->b;
}
if (start>ut->b) {
start = ut->b;
}
// adjust the incoming indexes to land on code point boundaries if needed.
// adjust by no more than three, because that is the largest number of trail bytes
// in a well formed UTF8 character.
const uint8_t *buf = (const uint8_t *)ut->context;
int i;
if (start < ut->chunk.nativeLimit) {
for (i=0; i<3; i++) {
if (U8_IS_LEAD(buf[start]) || start==0) {
break;
}
start--;
}
}
if (limit < ut->chunk.nativeLimit) {
for (i=0; i<3; i++) {
if (U8_IS_LEAD(buf[limit]) || limit==0) {
break;
}
limit--;
}
}
// Do the actual extract.
int32_t destLength=0;
utext_strFromUTF8(dest, destCapacity, &destLength,
(const char *)ut->context+start, limit-start,
pErrorCode);
return destLength;
}
// Assume nonUTF16Indexes and 0<=offset<=chunk->length
static int32_t U_CALLCONV
utf8TextMapOffsetToNative(UText *ut, int32_t offset) {
// UText.q points to the index mapping array that is allocated in the extra storage area.
U_ASSERT(offset>=0 && offset<=ut->chunk.length);
int32_t *map=(int32_t *)(ut->q);
return map[offset];
}
// Assume nonUTF16Indexes and chunk->start<=index<=chunk->limit
static int32_t U_CALLCONV
utf8TextMapIndexToUTF16(UText *ut, int32_t index) {
int32_t *map=(int32_t *)(ut->q);
int32_t offset=0;
U_ASSERT(index>=ut->chunk.nativeStart && index<=ut->chunk.nativeLimit);
while(index>map[offset]) {
++offset;
}
if (index<map[offset]) {
// index was to a trail byte of a multi-byte utf-8 char.
// The loop above advanced offset to the start of the following char, now
// offset must be backed up to the start of the utf-16 char into which
// the utf-8 index pointed.
offset--;
if (offset>0 && map[offset] == map[offset-1]) {
// index was to a utf-8 trail byte of a supplemenary char.
// Offset now points to the trail surrogate (one in back of the following char)
// Back offset up one more time to get to the utf-16 lead surrogate.
offset--;
}
}
return offset;
}
static UText * U_CALLCONV
utf8TextClone(UText *dest, const UText *src, UBool deep, UErrorCode *status)
{
// First do a generic shallow clone. Does everything needed for the UText struct itself.
dest = shallowTextClone(dest, src, status);
// For deep clones, make a copy of the string.
// The copied storage is owned by the newly created clone.
// A non-NULL pointer in UText.p is the signal to the close() function to delete
// it.
//
if (deep && U_SUCCESS(*status)) {
int32_t len = src->b;
char *copyStr = (char *)uprv_malloc(len+1);
if (copyStr == NULL) {
*status = U_MEMORY_ALLOCATION_ERROR;
} else {
uprv_memcpy(copyStr, src->context, len+1);
dest->context = copyStr;
dest->p = copyStr;
}
}
return dest;
}
static void U_CALLCONV
utf8TextClose(UText *ut) {
// Most of the work of close is done by the generic UText framework close.
// All that needs to be done here is to delete the UTF8 string if the UText
// owns it. This occurs if the UText was created by cloning.
char *s = (char *)ut->p;
uprv_free(s);
ut->p = NULL;
}
U_DRAFT UText * U_EXPORT2
utext_openUTF8(UText *ut, const char *s, int32_t length, UErrorCode *status) {
if(U_FAILURE(*status)) {
return NULL;
}
if(s==NULL || length<-1) {
*status=U_ILLEGAL_ARGUMENT_ERROR;
return NULL;
}
ut = utext_setup(ut, sizeof(UTF8Extra), status);
if (U_FAILURE(*status)) {
return ut;
}
ut->providerProperties = I32_FLAG(UTEXT_PROVIDER_NON_UTF16_INDEXES);
ut->clone = utf8TextClone;
ut->nativeLength = utf8TextLength;
ut->access = utf8TextAccess;
ut->extract = utf8TextExtract;
ut->mapOffsetToNative = utf8TextMapOffsetToNative;
ut->mapNativeIndexToUTF16 = utf8TextMapIndexToUTF16;
ut->close = utf8TextClose;
ut->context=s;
if(length>=0) {
ut->b=length;
} else {
// TODO: really undesirable to do this scan upfront.
ut->b=(int32_t)uprv_strlen(s);
}
return ut;
}
U_CDECL_END
//------------------------------------------------------------------------------
//
// UText implementation wrapper for Replaceable (read/write)
//
// Use of UText data members:
// context pointer to Replaceable.
// p pointer to Replaceable if it is owned by the UText.
//
//------------------------------------------------------------------------------
// minimum chunk size for this implementation: 3
// to allow for possible trimming for code point boundaries
enum { REP_TEXT_CHUNK_SIZE=10 };
struct ReplExtra {
/*
* Chunk UChars.
* +1 to simplify filling with surrogate pair at the end.
*/
UChar s[REP_TEXT_CHUNK_SIZE+1];
};
U_CDECL_BEGIN
static UText * U_CALLCONV
repTextClone(UText *dest, const UText *src, UBool deep, UErrorCode *status) {
// First do a generic shallow clone. Does everything needed for the UText struct itself.
dest = shallowTextClone(dest, src, status);
// For deep clones, make a copy of the Replaceable.
// The copied Replaceable storage is owned by the newly created UText clone.
// A non-NULL pointer in UText.p is the signal to the close() function to delete
// it.
//
if (deep && U_SUCCESS(*status)) {
const Replaceable *replSrc = (const Replaceable *)src->context;
dest->context = replSrc->clone();
dest->p = dest->context;
}
return dest;
}
static void U_CALLCONV
repTextClose(UText *ut) {
// Most of the work of close is done by the generic UText framework close.
// All that needs to be done here is delete the Replaceable if the UText
// owns it. This occurs if the UText was created by cloning.
Replaceable *rep = (Replaceable *)ut->p;
delete rep;
ut->p = NULL;
}
static int32_t U_CALLCONV
repTextLength(UText *ut) {
const Replaceable *replSrc = (const Replaceable *)ut->context;
int32_t len = replSrc->length();
return len;
}
static UBool U_CALLCONV
repTextAccess(UText *ut, int32_t index, UBool forward, UTextChunk* /* chunk*/ ) {
const Replaceable *rep=(const Replaceable *)ut->context;
int32_t length=rep->length(); // Full length of the input text (bigger than a chunk)
// clip the requested index to the limits of the text.
if (index<0) {
index = 0;
}
if (index>length) {
index = length;
}
/*
* Compute start/limit boundaries around index, for a segment of text
* to be extracted.
* To allow for the possibility that our user gave an index to the trailing
* half of a surrogate pair, we must request one extra preceding UChar when
* going in the forward direction. This will ensure that the buffer has the
* entire code point at the specified index.
*/
if(forward) {
if (index>=ut->chunk.nativeStart && index<ut->chunk.nativeLimit) {
// Buffer already contains the requested position.
ut->chunk.offset = index - ut->chunk.nativeStart;
return TRUE;
}
if (index>=length && ut->chunk.nativeLimit==length) {
// Request for end of string, and buffer already extends up to it.
// Can't get the data, but don't change the buffer.
ut->chunk.offset = length - ut->chunk.nativeStart;
return FALSE;
}
ut->chunk.nativeLimit = index + REP_TEXT_CHUNK_SIZE - 1;
// Going forward, so we want to have the buffer with stuff at and beyond
// the requested index. The -1 gets us one code point before the
// requested index also, to handle the case of the index being on
// a trail surrogate of a surrogate pair.
if(ut->chunk.nativeLimit > length) {
ut->chunk.nativeLimit = length;
}
// unless buffer ran off end, start is index-1.
ut->chunk.nativeStart = ut->chunk.nativeLimit - REP_TEXT_CHUNK_SIZE;
if(ut->chunk.nativeStart < 0) {
ut->chunk.nativeStart = 0;
}
} else {
// Reverse iteration. Fill buffer with data preceding the requested index.
if (index>ut->chunk.nativeStart && index<=ut->chunk.nativeLimit) {
// Requested position already in buffer.
ut->chunk.offset = index - ut->chunk.nativeStart;
return TRUE;
}
if (index==0 && ut->chunk.nativeStart==0) {
// Request for start, buffer already begins at start.
// No data, but keep the buffer as is.
ut->chunk.offset = 0;
return FALSE;
}
// Figure out the bounds of the chunk to extract for reverse iteration.
// Need to worry about chunk not splitting surrogate pairs, and while still
// containing the data we need.
// Fix by requesting a chunk that includes an extra UChar at the end.
// If this turns out to be a lead surrogate, we can lop it off and still have
// the data we wanted.
ut->chunk.nativeStart = index + 1 - REP_TEXT_CHUNK_SIZE;
if (ut->chunk.nativeStart < 0) {
ut->chunk.nativeStart = 0;
}
ut->chunk.nativeLimit = index + 1;
if (ut->chunk.nativeLimit > length) {
ut->chunk.nativeLimit = length;
}
}
// Extract the new chunk of text from the Replaceable source.
ReplExtra *ex = (ReplExtra *)ut->pExtra;
// UnicodeString with its buffer a writable alias to the chunk buffer
UnicodeString buffer(ex->s, 0 /*buffer length*/, REP_TEXT_CHUNK_SIZE /*buffer capacity*/);
rep->extractBetween(ut->chunk.nativeStart, ut->chunk.nativeLimit, buffer);
ut->chunk.contents = ex->s;
ut->chunk.length = ut->chunk.nativeLimit - ut->chunk.nativeStart;
ut->chunk.offset = index - ut->chunk.nativeStart;
// Surrogate pairs from the input text must not span chunk boundaries.
// If end of chunk could be the start of a surrogate, trim it off.
if (ut->chunk.nativeLimit < length &&
U16_IS_LEAD(ex->s[ut->chunk.length-1])) {
ut->chunk.length--;
ut->chunk.nativeLimit--;
if (ut->chunk.offset > ut->chunk.length) {
ut->chunk.offset = ut->chunk.length;
}
}
// if the first UChar in the chunk could be the trailing half of a surrogate pair,
// trim it off.
if(ut->chunk.nativeStart>0 && U16_IS_TRAIL(ex->s[0])) {
++(ut->chunk.contents);
++(ut->chunk.nativeStart);
--(ut->chunk.length);
--(ut->chunk.offset);
}
// adjust the index/chunkOffset to a code point boundary
U16_SET_CP_START(ut->chunk.contents, 0, ut->chunk.offset);
return TRUE;
}
static int32_t U_CALLCONV
repTextExtract(UText *ut,
int32_t start, int32_t limit,
UChar *dest, int32_t destCapacity,
UErrorCode *status) {
const Replaceable *rep=(const Replaceable *)ut->context;
int32_t length=rep->length();
if(U_FAILURE(*status)) {
return 0;
}
if(destCapacity<0 || (dest==NULL && destCapacity>0)) {
*status=U_ILLEGAL_ARGUMENT_ERROR;
}
if(start<0 || start>limit) {
*status=U_INDEX_OUTOFBOUNDS_ERROR;
return 0;
}
if (start>length) {
start=length;
}
if (limit>length) {
limit=length;
}
// adjust start, limit if they point to trail half of surrogates
if (start<length && U16_IS_TRAIL(rep->charAt(start)) &&
U_IS_SUPPLEMENTARY(rep->char32At(start))){
start--;
}
if (limit<length && U16_IS_TRAIL(rep->charAt(limit)) &&
U_IS_SUPPLEMENTARY(rep->char32At(limit))){
limit--;
}
length=limit-start;
if(length>destCapacity) {
limit = start + destCapacity;
}
UnicodeString buffer(dest, 0, destCapacity); // writable alias
rep->extractBetween(start, limit, buffer);
return u_terminateUChars(dest, destCapacity, length, status);
}
static int32_t U_CALLCONV
repTextReplace(UText *ut,
int32_t start, int32_t limit,
const UChar *src, int32_t length,
UErrorCode *status) {
Replaceable *rep=(Replaceable *)ut->context;
int32_t oldLength;
if(U_FAILURE(*status)) {
return 0;
}
if(src==NULL && length!=0) {
*status=U_ILLEGAL_ARGUMENT_ERROR;
return 0;
}
oldLength=rep->length(); // will subtract from new length
if(start<0 || start>limit ) {
*status=U_INDEX_OUTOFBOUNDS_ERROR;
return 0;
}
if (start > oldLength) {
start = oldLength;
}
if (limit > oldLength) {
limit = oldLength;
}
// Do the actual replace operation using methods of the Replaceable class
UnicodeString replStr((UBool)(length<0), src, length); // read-only alias
rep->handleReplaceBetween(start, limit, replStr);
int32_t newLength = rep->length();
int32_t lengthDelta = newLength - oldLength;
// Is the UText chunk buffer OK?
if (ut->chunk.nativeLimit > start) {
// this replace operation may have impacted the current chunk.
// invalidate it, which will force a reload on the next access.
invalidateChunk(&ut->chunk);
}
// set the iteration position to the end of the newly inserted replacement text.
int32_t newIndexPos = limit + lengthDelta;
repTextAccess(ut, newIndexPos, TRUE, &ut->chunk);
return lengthDelta;
}
static void U_CALLCONV
repTextCopy(UText *ut,
int32_t start, int32_t limit,
int32_t destIndex,
UBool move,
UErrorCode *status)
{
Replaceable *rep=(Replaceable *)ut->context;
int32_t length=rep->length();
if(U_FAILURE(*status)) {
return;
}
if( start<0 || start>limit || destIndex<0 ||
(start<destIndex && destIndex<limit) )
{
*status=U_INDEX_OUTOFBOUNDS_ERROR;
return;
}
if (destIndex > length) {
destIndex = length;
}
if (limit > length) {
limit = length;
}
if (start > length) {
start = length;
}
if(move) {
// move: copy to destIndex, then replace original with nothing
int32_t segLength=limit-start;
rep->copy(start, limit, destIndex);
if(destIndex<start) {
start+=segLength;
limit+=segLength;
}
rep->handleReplaceBetween(start, limit, UnicodeString());
} else {
// copy
rep->copy(start, limit, destIndex);
}
// If the change to the text touched the region in the chunk buffer,
// invalidate the buffer.
int32_t firstAffectedIndex = destIndex;
if (move && start<firstAffectedIndex) {
firstAffectedIndex = start;
}
if (firstAffectedIndex < ut->chunk.nativeLimit) {
// changes may have affected range covered by the chunk
invalidateChunk(&ut->chunk);
}
// Put iteration position at the newly inserted (moved) block,
int32_t nativeIterIndex = destIndex + limit - start;
if (move && destIndex>start) {
// moved a block of text towards the end of the string.
nativeIterIndex = destIndex;
}
// Set position, reload chunk if needed.
repTextAccess(ut, nativeIterIndex, TRUE, &ut->chunk);
}
U_DRAFT UText * U_EXPORT2
utext_openReplaceable(UText *ut, Replaceable *rep, UErrorCode *status)
{
if(U_FAILURE(*status)) {
return NULL;
}
if(rep==NULL) {
*status=U_ILLEGAL_ARGUMENT_ERROR;
return NULL;
}
ut = utext_setup(ut, sizeof(ReplExtra), status);
ut->providerProperties = I32_FLAG(UTEXT_PROVIDER_WRITABLE);
if(rep->hasMetaData()) {
ut->providerProperties |=I32_FLAG(UTEXT_PROVIDER_HAS_META_DATA);
}
ut->clone = repTextClone;
ut->nativeLength = repTextLength;
ut->access = repTextAccess;
ut->extract = repTextExtract;
ut->replace = repTextReplace;
ut->copy = repTextCopy;
ut->close = repTextClose;
ut->context=rep;
return ut;
}
U_CDECL_END
//------------------------------------------------------------------------------
//
// UText implementation for UnicodeString (read/write) and
// for const UnicodeString (read only)
// (same implementation, only the flags are different)
//
// Use of UText data members:
// context pointer to UnicodeString
// p pointer to UnicodeString IF this UText owns the string
// and it must be deleted on close(). NULL otherwise.
//
//------------------------------------------------------------------------------
U_CDECL_BEGIN
static UText * U_CALLCONV
unistrTextClone(UText *dest, const UText *src, UBool deep, UErrorCode *status) {
// First do a generic shallow clone. Does everything needed for the UText struct itself.
dest = shallowTextClone(dest, src, status);
// For deep clones, make a copy of the UnicodeSring.
// The copied UnicodeString storage is owned by the newly created UText clone.
// A non-NULL pointer in UText.p is the signal to the close() function to delete
// the UText.
//
if (deep && U_SUCCESS(*status)) {
const UnicodeString *srcString = (const UnicodeString *)src->context;
dest->context = new UnicodeString(*srcString);
dest->p = dest->context;
}
return dest;
}
static void U_CALLCONV
unistrTextClose(UText *ut) {
// Most of the work of close is done by the generic UText framework close.
// All that needs to be done here is delete the UnicodeString if the UText
// owns it. This occurs if the UText was created by cloning.
UnicodeString *str = (UnicodeString *)ut->p;
delete str;
ut->p = NULL;
}
static int32_t U_CALLCONV
unistrTextLength(UText *t) {
return ((const UnicodeString *)t->context)->length();
}
static UBool U_CALLCONV
unistrTextAccess(UText *ut, int32_t index, UBool forward, UTextChunk *chunk) {
const UnicodeString *us = (const UnicodeString *)ut->context;
int32_t length = us->length();
if (chunk->nativeLimit != length) {
// This chunk is not yet set up. Do it now.
// TODO: probably simplify things to move this into the open operation.
chunk->contents = us->getBuffer();
chunk->length = length;
chunk->nativeStart = 0;
chunk->nativeLimit = length;
chunk->nonUTF16Indexes = FALSE;
}
// pin the requested index to the bounds of the string,
// and set current iteration position.
if (index<0) {
index = 0;
} else if (index>length) {
index = length;
}
chunk->offset = index;
// Check whether request is at the start or end
UBool retVal = (forward && index<length) || (!forward && index>0);
return retVal;
}
static int32_t U_CALLCONV
unistrTextExtract(UText *t,
int32_t start, int32_t limit,
UChar *dest, int32_t destCapacity,
UErrorCode *pErrorCode) {
const UnicodeString *us=(const UnicodeString *)t->context;
int32_t length=us->length();
if(U_FAILURE(*pErrorCode)) {
return 0;
}
if(destCapacity<0 || (dest==NULL && destCapacity>0)) {
*pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
}
if(start<0 || start>limit) {
*pErrorCode=U_INDEX_OUTOFBOUNDS_ERROR;
return 0;
}
start = start<length ? us->getChar32Start(start) : length;
limit = limit<length ? us->getChar32Start(limit) : length;
length=limit-start;
if (destCapacity>0 && dest!=NULL) {
int32_t trimmedLength = length;
if(trimmedLength>destCapacity) {
trimmedLength=destCapacity;
}
us->extract(start, trimmedLength, dest);
}
u_terminateUChars(dest, destCapacity, length, pErrorCode);
return length;
}
static int32_t U_CALLCONV
unistrTextReplace(UText *ut,
int32_t start, int32_t limit,
const UChar *src, int32_t length,
UErrorCode *pErrorCode) {
UnicodeString *us=(UnicodeString *)ut->context;
int32_t oldLength;
if(U_FAILURE(*pErrorCode)) {
return 0;
}
if(src==NULL && length!=0) {
*pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
}
oldLength=us->length(); // will subtract from new length
if(start<0 || start>limit) {
*pErrorCode=U_INDEX_OUTOFBOUNDS_ERROR;
return 0;
}
start = start<oldLength ? us->getChar32Start(start) : oldLength;
limit = limit<oldLength ? us->getChar32Start(limit) : oldLength;
// replace
us->replace(start, limit-start, src, length);
int32_t newLength = us->length();
// Update the chunk description.
ut->chunk.contents = us->getBuffer();
ut->chunk.length = newLength;
ut->chunk.nativeLimit = newLength;
// Set iteration position to the point just following the newly inserted text.
int32_t lengthDelta = newLength - oldLength;
ut->chunk.offset = limit + lengthDelta;
return lengthDelta;
}
static void U_CALLCONV
unistrTextCopy(UText *ut,
int32_t start, int32_t limit,
int32_t destIndex,
UBool move,
UErrorCode *pErrorCode) {
UnicodeString *us=(UnicodeString *)ut->context;
int32_t length=us->length();
if(U_FAILURE(*pErrorCode)) {
return;
}
if( start<0 || start>limit || destIndex<0 ||
(start<destIndex && destIndex<limit)
) {
*pErrorCode=U_INDEX_OUTOFBOUNDS_ERROR;
return;
}
if (limit>length) {
limit = length;
}
if (destIndex>length) {
destIndex = length;
}
if(move) {
// move: copy to destIndex, then replace original with nothing
int32_t segLength=limit-start;
us->copy(start, limit, destIndex);
if(destIndex<start) {
start+=segLength;
}
us->replace(start, segLength, NULL, 0);
} else {
// copy
us->copy(start, limit, destIndex);
}
// update chunk description, set iteration position.
ut->chunk.contents = us->getBuffer();
if (move==FALSE) {
// copy operation, string length grows
ut->chunk.length += limit-start;
ut->chunk.nativeLimit = ut->chunk.length;
}
// Iteration position to end of the newly inserted text.
ut->chunk.offset = destIndex+limit-start;
if (move && destIndex>start) { //TODO: backwards? check.
ut->chunk.offset = destIndex;
}
}
U_CDECL_END
U_DRAFT UText * U_EXPORT2
utext_openUnicodeString(UText *ut, UnicodeString *s, UErrorCode *status) {
ut = utext_setup(ut, 0, status);
if (U_SUCCESS(*status)) {
ut->clone = unistrTextClone;
ut->nativeLength = unistrTextLength;
ut->access = unistrTextAccess;
ut->extract = unistrTextExtract;
ut->replace = unistrTextReplace;
ut->copy = unistrTextCopy;
ut->close = unistrTextClose;
ut->context = s;
ut->providerProperties = I32_FLAG(UTEXT_PROVIDER_STABLE_CHUNKS)|
I32_FLAG(UTEXT_PROVIDER_WRITABLE);
}
return ut;
}
U_DRAFT UText * U_EXPORT2
utext_openConstUnicodeString(UText *ut, const UnicodeString *s, UErrorCode *status) {
ut = utext_setup(ut, 0, status);
if (U_SUCCESS(*status)) {
ut->clone = unistrTextClone;
ut->nativeLength = unistrTextLength;
ut->access = unistrTextAccess;
ut->extract = unistrTextExtract;
ut->close = unistrTextClose;
ut->context = s;
ut->providerProperties = I32_FLAG(UTEXT_PROVIDER_STABLE_CHUNKS);
}
return ut;
}
//------------------------------------------------------------------------------
//
// UText implementation for const UChar * strings
//
// Use of UText data members:
// context pointer to UnicodeString
// a length. -1 if not yet known.
//
//------------------------------------------------------------------------------
U_CDECL_BEGIN
static UText * U_CALLCONV
ucstrTextClone(UText *dest, const UText * src, UBool deep, UErrorCode * status) {
// First do a generic shallow clone.
dest = shallowTextClone(dest, src, status);
// For deep clones, make a copy of the string.
// The copied storage is owned by the newly created clone.
// A non-NULL pointer in UText.p is the signal to the close() function to delete
// it.
//
if (deep && U_SUCCESS(*status)) {
int32_t len = utext_nativeLength(dest);
// The cloned string IS going to be NUL terminated, whether or not the orginal was.
const UChar *srcStr = (const UChar *)src->context;
UChar *copyStr = (UChar *)uprv_malloc((len+1) * sizeof(UChar));
if (copyStr == NULL) {
*status = U_MEMORY_ALLOCATION_ERROR;
} else {
int i;
for (i=0; i<len; i++) {
copyStr[i] = srcStr[i];
}
copyStr[len] = 0;
dest->context = copyStr;
dest->p = copyStr;
}
}
return dest;
}
static void U_CALLCONV
ucstrTextClose(UText *ut) {
// Most of the work of close is done by the generic UText framework close.
// All that needs to be done here is delete the Replaceable if the UText
// owns it. This occurs if the UText was created by cloning.
UChar *s = (UChar *)ut->p;
uprv_free(s);
ut->p = NULL;
}
static int32_t U_CALLCONV
ucstrTextLength(UText *ut) {
if (ut->a < 0) {
// null terminated, we don't yet know the length. Scan for it.
// Access is not convenient for doing this
// because the current interation postion can't be changed.
const UChar *str = (const UChar *)ut->context;
for (;;) {
if (str[ut->chunk.nativeLimit] == 0) {
break;
}
ut->chunk.nativeLimit++;
}
ut->a = ut->chunk.nativeLimit;
ut->chunk.length = ut->chunk.nativeLimit;
ut->providerProperties &= ~I32_FLAG(UTEXT_PROVIDER_LENGTH_IS_EXPENSIVE);
}
return ut->a;
}
static UBool U_CALLCONV
ucstrTextAccess(UText *ut, int32_t index, UBool forward, UTextChunk *chunk) {
const UChar *str = (const UChar *)ut->context;
// pin the requested index to the bounds of the string,
// and set current iteration position.
if (index<0) {
index = 0;
} else if (index < ut->chunk.nativeLimit) {
// The request data is within the chunk as it is known so far.
// There is nothing more that needs to be done within this access function.
} else if (ut->a >= 0) {
// We know the length of this string, and the user is requesting something
// at or beyond the length. Trim the requested index to the length.
index = ut->a;
} else {
// Null terminated string, length not yet known.
// Scan down another 32 UChars or to the requested index, whichever is further
int scanLimit = ut->chunk.nativeLimit + 32;
if (scanLimit <= index) {
scanLimit = index+1; // TODO: beware int overflow
}
for (; ut->chunk.nativeLimit<scanLimit; ut->chunk.nativeLimit++) {
if (str[ut->chunk.nativeLimit] == 0) {
// We found the end of the string. Remember it, trim the index to it,
// and bail out of here.
ut->a = ut->chunk.nativeLimit;
ut->chunk.length = ut->chunk.nativeLimit;
if (index > ut->chunk.nativeLimit) {
index = ut->chunk.nativeLimit;
}
ut->providerProperties &= ~I32_FLAG(UTEXT_PROVIDER_LENGTH_IS_EXPENSIVE);
goto breakout;
}
}
// We scanned through the next batch of UChars without finding the end.
// The endpoint of a chunk must not be left in the middle of a surrogate pair.
// If the current end is on a lead surrogate, back the end up by one.
// It doesn't matter if the end char happens to be an unpaired surrogate,
// and it's simpler not to worry about it.
if (U16_IS_LEAD(str[ut->chunk.nativeLimit-1])) {
--ut->chunk.nativeLimit;
}
}
breakout:
chunk->offset = index;
// Check whether request is at the start or end
UBool retVal = (forward && index<ut->chunk.nativeLimit) || (!forward && index>0);
return retVal;
}
static int32_t U_CALLCONV
ucstrTextExtract(UText *ut,
int32_t start, int32_t limit,
UChar *dest, int32_t destCapacity,
UErrorCode *pErrorCode) {
if(U_FAILURE(*pErrorCode)) {
return 0;
}
if(destCapacity<0 || (dest==NULL && destCapacity>0)) {
*pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
return 0;
}
const UChar *s=(const UChar *)ut->context;
int32_t strLength=ut->a;
int32_t si, di;
// If text is null terminated and we haven't yet scanned down as far as the starting
// position of the extract, do it now.
if (strLength<0 && limit>=ut->chunk.nativeLimit) {
ucstrTextAccess(ut, start, TRUE, &ut->chunk);
}
// Raise an error if starting position is outside of the string.
if(start<0 || start>limit) {
*pErrorCode=U_INDEX_OUTOFBOUNDS_ERROR;
return 0;
}
if (strLength >= 0 && limit > strLength) {
// String length is known. Trim requested limit to be no more than the length
limit = strLength;
}
di = 0;
for (si=start; si<limit; si++) {
if (strLength<0 && s[si]==0) {
// Just hit the end of a null-terminated string.
ut->a = si; // set string length for this UText
ut->chunk.nativeLimit = si;
ut->chunk.length = si;
//
break;
}
if (di<destCapacity) {
// only store if there is space.
dest[di] = s[si];
} else {
if (strLength>=0) {
// We have filled the destination buffer, and the string is known.
// Cut the loop short. There is no need to scan string termination.
di = strLength;
break;
}
}
di++;
}
u_terminateUChars(dest, destCapacity, di, pErrorCode);
return di;
}
U_CDECL_END
U_DRAFT UText * U_EXPORT2
utext_openUChars(UText *ut, const UChar *s, int32_t length, UErrorCode *status) {
if (U_FAILURE(*status)) {
return NULL;
}
if (length < -1) {
*status = U_ILLEGAL_ARGUMENT_ERROR;
return NULL;
}
ut = utext_setup(ut, 0, status);
if (U_SUCCESS(*status)) {
ut->clone = ucstrTextClone;
ut->nativeLength = ucstrTextLength;
ut->access = ucstrTextAccess;
ut->extract = ucstrTextExtract;
ut->replace = NULL;
ut->copy = NULL;
ut->close = ucstrTextClose;
ut->context = s;
ut->providerProperties = I32_FLAG(UTEXT_PROVIDER_STABLE_CHUNKS);
if (length==-1) {
ut->providerProperties |= I32_FLAG(UTEXT_PROVIDER_LENGTH_IS_EXPENSIVE);
}
ut->a = length;
ut->chunk.contents = s;
ut->chunk.nativeStart = 0;
ut->chunk.nativeLimit = length>=0? length : 0;
ut->chunk.length = ut->chunk.nativeLimit;
ut->chunk.nonUTF16Indexes = FALSE;
}
return ut;
}
|