summaryrefslogtreecommitdiffstats
path: root/intl/icu/source/common/ucase.cpp
blob: 392e1266ae4429c4ef76c9d3e02b67502c9daa3e (plain)
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
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
*   Copyright (C) 2004-2014, International Business Machines
*   Corporation and others.  All Rights Reserved.
*
*******************************************************************************
*   file name:  ucase.cpp
*   encoding:   UTF-8
*   tab size:   8 (not used)
*   indentation:4
*
*   created on: 2004aug30
*   created by: Markus W. Scherer
*
*   Low-level Unicode character/string case mapping code.
*   Much code moved here (and modified) from uchar.c.
*/

#include "unicode/utypes.h"
#include "unicode/unistr.h"
#include "unicode/uset.h"
#include "unicode/utf16.h"
#include "cmemory.h"
#include "uassert.h"
#include "ucase.h"
#include "umutex.h"
#include "utrie2.h"

/* ucase_props_data.h is machine-generated by genprops/casepropsbuilder.cpp */
#define INCLUDED_FROM_UCASE_CPP
#include "ucase_props_data.h"

/* set of property starts for UnicodeSet ------------------------------------ */

static UBool U_CALLCONV
_enumPropertyStartsRange(const void *context, UChar32 start, UChar32 /*end*/, uint32_t /*value*/) {
    /* add the start code point to the USet */
    const USetAdder *sa=(const USetAdder *)context;
    sa->add(sa->set, start);
    return true;
}

U_CFUNC void U_EXPORT2
ucase_addPropertyStarts(const USetAdder *sa, UErrorCode *pErrorCode) {
    if(U_FAILURE(*pErrorCode)) {
        return;
    }

    /* add the start code point of each same-value range of the trie */
    utrie2_enum(&ucase_props_singleton.trie, nullptr, _enumPropertyStartsRange, sa);

    /* add code points with hardcoded properties, plus the ones following them */

    /* (none right now, see comment below) */

    /*
     * Omit code points with hardcoded specialcasing properties
     * because we do not build property UnicodeSets for them right now.
     */
}

/* data access primitives --------------------------------------------------- */

U_CAPI const struct UCaseProps * U_EXPORT2
ucase_getSingleton(int32_t *pExceptionsLength, int32_t *pUnfoldLength) {
    *pExceptionsLength = UPRV_LENGTHOF(ucase_props_exceptions);
    *pUnfoldLength = UPRV_LENGTHOF(ucase_props_unfold);
    return &ucase_props_singleton;
}

U_CFUNC const UTrie2 * U_EXPORT2
ucase_getTrie() {
    return &ucase_props_singleton.trie;
}

#define GET_EXCEPTIONS(csp, props) ((csp)->exceptions+((props)>>UCASE_EXC_SHIFT))

/* number of bits in an 8-bit integer value */
static const uint8_t flagsOffset[256]={
    0, 1, 1, 2, 1, 2, 2, 3, 1, 2, 2, 3, 2, 3, 3, 4,
    1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
    1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
    2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
    1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
    2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
    2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
    3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
    1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5,
    2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
    2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
    3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
    2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6,
    3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
    3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7,
    4, 5, 5, 6, 5, 6, 6, 7, 5, 6, 6, 7, 6, 7, 7, 8
};

#define HAS_SLOT(flags, idx) ((flags)&(1<<(idx)))
#define SLOT_OFFSET(flags, idx) flagsOffset[(flags)&((1<<(idx))-1)]

/*
 * Get the value of an optional-value slot where HAS_SLOT(excWord, idx).
 *
 * @param excWord (in) initial exceptions word
 * @param idx (in) desired slot index
 * @param pExc16 (in/out) const uint16_t * after excWord=*pExc16++;
 *               moved to the last uint16_t of the value, use +1 for beginning of next slot
 * @param value (out) int32_t or uint32_t output if hasSlot, otherwise not modified
 */
#define GET_SLOT_VALUE(excWord, idx, pExc16, value) UPRV_BLOCK_MACRO_BEGIN { \
    if(((excWord)&UCASE_EXC_DOUBLE_SLOTS)==0) { \
        (pExc16)+=SLOT_OFFSET(excWord, idx); \
        (value)=*pExc16; \
    } else { \
        (pExc16)+=2*SLOT_OFFSET(excWord, idx); \
        (value)=*pExc16++; \
        (value)=((value)<<16)|*pExc16; \
    } \
} UPRV_BLOCK_MACRO_END

/* simple case mappings ----------------------------------------------------- */

U_CAPI UChar32 U_EXPORT2
ucase_tolower(UChar32 c) {
    uint16_t props=UTRIE2_GET16(&ucase_props_singleton.trie, c);
    if(!UCASE_HAS_EXCEPTION(props)) {
        if(UCASE_IS_UPPER_OR_TITLE(props)) {
            c+=UCASE_GET_DELTA(props);
        }
    } else {
        const uint16_t *pe=GET_EXCEPTIONS(&ucase_props_singleton, props);
        uint16_t excWord=*pe++;
        if(HAS_SLOT(excWord, UCASE_EXC_DELTA) && UCASE_IS_UPPER_OR_TITLE(props)) {
            int32_t delta;
            GET_SLOT_VALUE(excWord, UCASE_EXC_DELTA, pe, delta);
            return (excWord&UCASE_EXC_DELTA_IS_NEGATIVE)==0 ? c+delta : c-delta;
        }
        if(HAS_SLOT(excWord, UCASE_EXC_LOWER)) {
            GET_SLOT_VALUE(excWord, UCASE_EXC_LOWER, pe, c);
        }
    }
    return c;
}

U_CAPI UChar32 U_EXPORT2
ucase_toupper(UChar32 c) {
    uint16_t props=UTRIE2_GET16(&ucase_props_singleton.trie, c);
    if(!UCASE_HAS_EXCEPTION(props)) {
        if(UCASE_GET_TYPE(props)==UCASE_LOWER) {
            c+=UCASE_GET_DELTA(props);
        }
    } else {
        const uint16_t *pe=GET_EXCEPTIONS(&ucase_props_singleton, props);
        uint16_t excWord=*pe++;
        if(HAS_SLOT(excWord, UCASE_EXC_DELTA) && UCASE_GET_TYPE(props)==UCASE_LOWER) {
            int32_t delta;
            GET_SLOT_VALUE(excWord, UCASE_EXC_DELTA, pe, delta);
            return (excWord&UCASE_EXC_DELTA_IS_NEGATIVE)==0 ? c+delta : c-delta;
        }
        if(HAS_SLOT(excWord, UCASE_EXC_UPPER)) {
            GET_SLOT_VALUE(excWord, UCASE_EXC_UPPER, pe, c);
        }
    }
    return c;
}

U_CAPI UChar32 U_EXPORT2
ucase_totitle(UChar32 c) {
    uint16_t props=UTRIE2_GET16(&ucase_props_singleton.trie, c);
    if(!UCASE_HAS_EXCEPTION(props)) {
        if(UCASE_GET_TYPE(props)==UCASE_LOWER) {
            c+=UCASE_GET_DELTA(props);
        }
    } else {
        const uint16_t *pe=GET_EXCEPTIONS(&ucase_props_singleton, props);
        uint16_t excWord=*pe++;
        if(HAS_SLOT(excWord, UCASE_EXC_DELTA) && UCASE_GET_TYPE(props)==UCASE_LOWER) {
            int32_t delta;
            GET_SLOT_VALUE(excWord, UCASE_EXC_DELTA, pe, delta);
            return (excWord&UCASE_EXC_DELTA_IS_NEGATIVE)==0 ? c+delta : c-delta;
        }
        int32_t idx;
        if(HAS_SLOT(excWord, UCASE_EXC_TITLE)) {
            idx=UCASE_EXC_TITLE;
        } else if(HAS_SLOT(excWord, UCASE_EXC_UPPER)) {
            idx=UCASE_EXC_UPPER;
        } else {
            return c;
        }
        GET_SLOT_VALUE(excWord, idx, pe, c);
    }
    return c;
}

static const char16_t iDot[2] = { 0x69, 0x307 };
static const char16_t jDot[2] = { 0x6a, 0x307 };
static const char16_t iOgonekDot[3] = { 0x12f, 0x307 };
static const char16_t iDotGrave[3] = { 0x69, 0x307, 0x300 };
static const char16_t iDotAcute[3] = { 0x69, 0x307, 0x301 };
static const char16_t iDotTilde[3] = { 0x69, 0x307, 0x303 };


U_CFUNC void U_EXPORT2
ucase_addCaseClosure(UChar32 c, const USetAdder *sa) {
    uint16_t props=UTRIE2_GET16(&ucase_props_singleton.trie, c);
    if(!UCASE_HAS_EXCEPTION(props)) {
        if(UCASE_GET_TYPE(props)!=UCASE_NONE) {
            /* add the one simple case mapping, no matter what type it is */
            int32_t delta=UCASE_GET_DELTA(props);
            if(delta!=0) {
                sa->add(sa->set, c+delta);
            }
        }
    } else {
        /*
         * c has exceptions, so there may be multiple simple and/or
         * full case mappings. Add them all.
         */
        const uint16_t *pe=GET_EXCEPTIONS(&ucase_props_singleton, props);
        uint16_t excWord=*pe++;
        const uint16_t *pe0=pe;

        // Hardcode the case closure of i and its relatives and ignore the
        // data file data for these characters.
        // The Turkic dotless i and dotted I with their case mapping conditions
        // and case folding option make the related characters behave specially.
        // This code matches their closure behavior to their case folding behavior.
        if (excWord&UCASE_EXC_CONDITIONAL_FOLD) {
            // These characters have Turkic case foldings. Hardcode their closure.
            if (c == 0x49) {
                // Regular i and I are in one equivalence class.
                sa->add(sa->set, 0x69);
                return;
            } else if (c == 0x130) {
                // Dotted I is in a class with <0069 0307>
                // (for canonical equivalence with <0049 0307>).
                sa->addString(sa->set, iDot, 2);
                return;
            }
        } else if (c == 0x69) {
            sa->add(sa->set, 0x49);
            return;
        } else if (c == 0x131) {
            // Dotless i is in a class by itself.
            return;
        }

        /* add all simple case mappings */
        for(int32_t idx=UCASE_EXC_LOWER; idx<=UCASE_EXC_TITLE; ++idx) {
            if(HAS_SLOT(excWord, idx)) {
                pe=pe0;
                UChar32 mapping;
                GET_SLOT_VALUE(excWord, idx, pe, mapping);
                sa->add(sa->set, mapping);
            }
        }
        if(HAS_SLOT(excWord, UCASE_EXC_DELTA)) {
            pe=pe0;
            int32_t delta;
            GET_SLOT_VALUE(excWord, UCASE_EXC_DELTA, pe, delta);
            sa->add(sa->set, (excWord&UCASE_EXC_DELTA_IS_NEGATIVE)==0 ? c+delta : c-delta);
        }

        /* get the closure string pointer & length */
        const char16_t *closure;
        int32_t closureLength;
        if(HAS_SLOT(excWord, UCASE_EXC_CLOSURE)) {
            pe=pe0;
            GET_SLOT_VALUE(excWord, UCASE_EXC_CLOSURE, pe, closureLength);
            closureLength&=UCASE_CLOSURE_MAX_LENGTH; /* higher bits are reserved */
            closure=(const char16_t *)pe+1; /* behind this slot, unless there are full case mappings */
        } else {
            closureLength=0;
            closure=nullptr;
        }

        /* add the full case folding */
        if(HAS_SLOT(excWord, UCASE_EXC_FULL_MAPPINGS)) {
            pe=pe0;
            int32_t fullLength;
            GET_SLOT_VALUE(excWord, UCASE_EXC_FULL_MAPPINGS, pe, fullLength);

            /* start of full case mapping strings */
            ++pe;

            fullLength&=0xffff; /* bits 16 and higher are reserved */

            /* skip the lowercase result string */
            pe+=fullLength&UCASE_FULL_LOWER;
            fullLength>>=4;

            /* add the full case folding string */
            int32_t length=fullLength&0xf;
            if(length!=0) {
                sa->addString(sa->set, (const char16_t *)pe, length);
                pe+=length;
            }

            /* skip the uppercase and titlecase strings */
            fullLength>>=4;
            pe+=fullLength&0xf;
            fullLength>>=4;
            pe+=fullLength;

            closure=(const char16_t *)pe; /* behind full case mappings */
        }

        /* add each code point in the closure string */
        for(int32_t idx=0; idx<closureLength;) {
            UChar32 mapping;
            U16_NEXT_UNSAFE(closure, idx, mapping);
            sa->add(sa->set, mapping);
        }
    }
}

namespace {

/**
 * Add the simple case closure mapping,
 * except if there is not actually an scf relationship between the two characters.
 * TODO: Unicode should probably add the corresponding scf mappings.
 * See https://crbug.com/v8/13377 and Unicode-internal PAG issue #23.
 * If & when those scf mappings are added, we should be able to remove all of these exceptions.
 */
void addOneSimpleCaseClosure(UChar32 c, UChar32 t, const USetAdder *sa) {
    switch (c) {
    case 0x0390:
        if (t == 0x1FD3) { return; }
        break;
    case 0x03B0:
        if (t == 0x1FE3) { return; }
        break;
    case 0x1FD3:
        if (t == 0x0390) { return; }
        break;
    case 0x1FE3:
        if (t == 0x03B0) { return; }
        break;
    case 0xFB05:
        if (t == 0xFB06) { return; }
        break;
    case 0xFB06:
        if (t == 0xFB05) { return; }
        break;
    default:
        break;
    }
    sa->add(sa->set, t);
}

}  // namespace

U_CFUNC void U_EXPORT2
ucase_addSimpleCaseClosure(UChar32 c, const USetAdder *sa) {
    uint16_t props=UTRIE2_GET16(&ucase_props_singleton.trie, c);
    if(!UCASE_HAS_EXCEPTION(props)) {
        if(UCASE_GET_TYPE(props)!=UCASE_NONE) {
            /* add the one simple case mapping, no matter what type it is */
            int32_t delta=UCASE_GET_DELTA(props);
            if(delta!=0) {
                sa->add(sa->set, c+delta);
            }
        }
    } else {
        // c has exceptions. Add the mappings relevant for scf=Simple_Case_Folding.
        const uint16_t *pe=GET_EXCEPTIONS(&ucase_props_singleton, props);
        uint16_t excWord=*pe++;
        const uint16_t *pe0=pe;

        // Hardcode the case closure of i and its relatives and ignore the
        // data file data for these characters, like in ucase_addCaseClosure().
        if (excWord&UCASE_EXC_CONDITIONAL_FOLD) {
            // These characters have Turkic case foldings. Hardcode their closure.
            if (c == 0x49) {
                // Regular i and I are in one equivalence class.
                sa->add(sa->set, 0x69);
                return;
            } else if (c == 0x130) {
                // For scf=Simple_Case_Folding, dotted I is in a class by itself.
                return;
            }
        } else if (c == 0x69) {
            sa->add(sa->set, 0x49);
            return;
        } else if (c == 0x131) {
            // Dotless i is in a class by itself.
            return;
        }

        // Add all simple case mappings.
        for(int32_t idx=UCASE_EXC_LOWER; idx<=UCASE_EXC_TITLE; ++idx) {
            if(HAS_SLOT(excWord, idx)) {
                pe=pe0;
                UChar32 mapping;
                GET_SLOT_VALUE(excWord, idx, pe, mapping);
                addOneSimpleCaseClosure(c, mapping, sa);
            }
        }
        if(HAS_SLOT(excWord, UCASE_EXC_DELTA)) {
            pe=pe0;
            int32_t delta;
            GET_SLOT_VALUE(excWord, UCASE_EXC_DELTA, pe, delta);
            UChar32 mapping = (excWord&UCASE_EXC_DELTA_IS_NEGATIVE)==0 ? c+delta : c-delta;
            addOneSimpleCaseClosure(c, mapping, sa);
        }

        /* get the closure string pointer & length */
        const char16_t *closure;
        int32_t closureLength;
        if(HAS_SLOT(excWord, UCASE_EXC_CLOSURE)) {
            pe=pe0;
            GET_SLOT_VALUE(excWord, UCASE_EXC_CLOSURE, pe, closureLength);
            closureLength&=UCASE_CLOSURE_MAX_LENGTH; /* higher bits are reserved */
            closure=(const char16_t *)pe+1; /* behind this slot, unless there are full case mappings */
        } else {
            closureLength=0;
            closure=nullptr;
        }

        // Skip the full case mappings.
        if(closureLength > 0 && HAS_SLOT(excWord, UCASE_EXC_FULL_MAPPINGS)) {
            pe=pe0;
            int32_t fullLength;
            GET_SLOT_VALUE(excWord, UCASE_EXC_FULL_MAPPINGS, pe, fullLength);

            /* start of full case mapping strings */
            ++pe;

            fullLength&=0xffff; /* bits 16 and higher are reserved */

            // Skip all 4 full case mappings.
            pe+=fullLength&UCASE_FULL_LOWER;
            fullLength>>=4;
            pe+=fullLength&0xf;
            fullLength>>=4;
            pe+=fullLength&0xf;
            fullLength>>=4;
            pe+=fullLength;

            closure=(const char16_t *)pe; /* behind full case mappings */
        }

        // Add each code point in the closure string whose scf maps back to c.
        for(int32_t idx=0; idx<closureLength;) {
            UChar32 mapping;
            U16_NEXT_UNSAFE(closure, idx, mapping);
            addOneSimpleCaseClosure(c, mapping, sa);
        }
    }
}

/*
 * compare s, which has a length, with t, which has a maximum length or is NUL-terminated
 * must be length>0 and max>0 and length<=max
 */
static inline int32_t
strcmpMax(const char16_t *s, int32_t length, const char16_t *t, int32_t max) {
    int32_t c1, c2;

    max-=length; /* we require length<=max, so no need to decrement max in the loop */
    do {
        c1=*s++;
        c2=*t++;
        if(c2==0) {
            return 1; /* reached the end of t but not of s */
        }
        c1-=c2;
        if(c1!=0) {
            return c1; /* return difference result */
        }
    } while(--length>0);
    /* ends with length==0 */

    if(max==0 || *t==0) {
        return 0; /* equal to length of both strings */
    } else {
        return -max; /* return length difference */
    }
}

U_CFUNC UBool U_EXPORT2
ucase_addStringCaseClosure(const char16_t *s, int32_t length, const USetAdder *sa) {
    int32_t i, start, limit, result, unfoldRows, unfoldRowWidth, unfoldStringWidth;

    if(ucase_props_singleton.unfold==nullptr || s==nullptr) {
        return false; /* no reverse case folding data, or no string */
    }
    if(length<=1) {
        /* the string is too short to find any match */
        /*
         * more precise would be:
         * if(!u_strHasMoreChar32Than(s, length, 1))
         * but this does not make much practical difference because
         * a single supplementary code point would just not be found
         */
        return false;
    }

    const uint16_t *unfold=ucase_props_singleton.unfold;
    unfoldRows=unfold[UCASE_UNFOLD_ROWS];
    unfoldRowWidth=unfold[UCASE_UNFOLD_ROW_WIDTH];
    unfoldStringWidth=unfold[UCASE_UNFOLD_STRING_WIDTH];
    unfold+=unfoldRowWidth;

    if(length>unfoldStringWidth) {
        /* the string is too long to find any match */
        return false;
    }

    /* do a binary search for the string */
    start=0;
    limit=unfoldRows;
    while(start<limit) {
        i=(start+limit)/2;
        const char16_t *p=reinterpret_cast<const char16_t *>(unfold+(i*unfoldRowWidth));
        result=strcmpMax(s, length, p, unfoldStringWidth);

        if(result==0) {
            /* found the string: add each code point, and its case closure */
            UChar32 c;

            for(i=unfoldStringWidth; i<unfoldRowWidth && p[i]!=0;) {
                U16_NEXT_UNSAFE(p, i, c);
                sa->add(sa->set, c);
                ucase_addCaseClosure(c, sa);
            }
            return true;
        } else if(result<0) {
            limit=i;
        } else /* result>0 */ {
            start=i+1;
        }
    }

    return false; /* string not found */
}

U_NAMESPACE_BEGIN

FullCaseFoldingIterator::FullCaseFoldingIterator()
        : unfold(reinterpret_cast<const char16_t *>(ucase_props_singleton.unfold)),
          unfoldRows(unfold[UCASE_UNFOLD_ROWS]),
          unfoldRowWidth(unfold[UCASE_UNFOLD_ROW_WIDTH]),
          unfoldStringWidth(unfold[UCASE_UNFOLD_STRING_WIDTH]),
          currentRow(0),
          rowCpIndex(unfoldStringWidth) {
    unfold+=unfoldRowWidth;
}

UChar32
FullCaseFoldingIterator::next(UnicodeString &full) {
    // Advance past the last-delivered code point.
    const char16_t *p=unfold+(currentRow*unfoldRowWidth);
    if(rowCpIndex>=unfoldRowWidth || p[rowCpIndex]==0) {
        ++currentRow;
        p+=unfoldRowWidth;
        rowCpIndex=unfoldStringWidth;
    }
    if(currentRow>=unfoldRows) { return U_SENTINEL; }
    // Set "full" to the NUL-terminated string in the first unfold column.
    int32_t length=unfoldStringWidth;
    while(length>0 && p[length-1]==0) { --length; }
    full.setTo(false, p, length);
    // Return the code point.
    UChar32 c;
    U16_NEXT_UNSAFE(p, rowCpIndex, c);
    return c;
}

namespace LatinCase {

const int8_t TO_LOWER_NORMAL[LIMIT] = {
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,

    0, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32,
    32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,

    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, EXC, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,

    32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32,
    32, 32, 32, 32, 32, 32, 32, 0, 32, 32, 32, 32, 32, 32, 32, EXC,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,

    1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
    1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
    1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
    EXC, 0, 1, 0, 1, 0, 1, 0, 0, 1, 0, 1, 0, 1, 0, 1,

    0, 1, 0, 1, 0, 1, 0, 1, 0, EXC, 1, 0, 1, 0, 1, 0,
    1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
    1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
    1, 0, 1, 0, 1, 0, 1, 0, -121, 1, 0, 1, 0, 1, 0, EXC
};

const int8_t TO_LOWER_TR_LT[LIMIT] = {
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,

    0, 32, 32, 32, 32, 32, 32, 32, 32, EXC, EXC, 32, 32, 32, 32, 32,
    32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,

    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, EXC, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,

    32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, 32, EXC, EXC, 32, 32,
    32, 32, 32, 32, 32, 32, 32, 0, 32, 32, 32, 32, 32, 32, 32, EXC,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,

    1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
    1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
    1, 0, 1, 0, 1, 0, 1, 0, EXC, 0, 1, 0, 1, 0, EXC, 0,
    EXC, 0, 1, 0, 1, 0, 1, 0, 0, 1, 0, 1, 0, 1, 0, 1,

    0, 1, 0, 1, 0, 1, 0, 1, 0, EXC, 1, 0, 1, 0, 1, 0,
    1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
    1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0, 1, 0,
    1, 0, 1, 0, 1, 0, 1, 0, -121, 1, 0, 1, 0, 1, 0, EXC
};

const int8_t TO_UPPER_NORMAL[LIMIT] = {
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,

    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32,
    -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, 0, 0, 0, 0, 0,

    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, EXC, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,

    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, EXC,
    -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32,
    -32, -32, -32, -32, -32, -32, -32, 0, -32, -32, -32, -32, -32, -32, -32, 121,

    0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1,
    0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1,
    0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1,
    0, EXC, 0, -1, 0, -1, 0, -1, 0, 0, -1, 0, -1, 0, -1, 0,

    -1, 0, -1, 0, -1, 0, -1, 0, -1, EXC, 0, -1, 0, -1, 0, -1,
    0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1,
    0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1,
    0, -1, 0, -1, 0, -1, 0, -1, 0, 0, -1, 0, -1, 0, -1, EXC
};

const int8_t TO_UPPER_TR[LIMIT] = {
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,

    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, -32, -32, -32, -32, -32, -32, -32, -32, EXC, -32, -32, -32, -32, -32, -32,
    -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, 0, 0, 0, 0, 0,

    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, EXC, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,

    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, EXC,
    -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32, -32,
    -32, -32, -32, -32, -32, -32, -32, 0, -32, -32, -32, -32, -32, -32, -32, 121,

    0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1,
    0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1,
    0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1,
    0, EXC, 0, -1, 0, -1, 0, -1, 0, 0, -1, 0, -1, 0, -1, 0,

    -1, 0, -1, 0, -1, 0, -1, 0, -1, EXC, 0, -1, 0, -1, 0, -1,
    0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1,
    0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1, 0, -1,
    0, -1, 0, -1, 0, -1, 0, -1, 0, 0, -1, 0, -1, 0, -1, EXC
};

}  // namespace LatinCase

U_NAMESPACE_END

/** @return UCASE_NONE, UCASE_LOWER, UCASE_UPPER, UCASE_TITLE */
U_CAPI int32_t U_EXPORT2
ucase_getType(UChar32 c) {
    uint16_t props=UTRIE2_GET16(&ucase_props_singleton.trie, c);
    return UCASE_GET_TYPE(props);
}

/** @return same as ucase_getType() and set bit 2 if c is case-ignorable */
U_CAPI int32_t U_EXPORT2
ucase_getTypeOrIgnorable(UChar32 c) {
    uint16_t props=UTRIE2_GET16(&ucase_props_singleton.trie, c);
    return UCASE_GET_TYPE_AND_IGNORABLE(props);
}

/** @return UCASE_NO_DOT, UCASE_SOFT_DOTTED, UCASE_ABOVE, UCASE_OTHER_ACCENT */
static inline int32_t
getDotType(UChar32 c) {
    uint16_t props=UTRIE2_GET16(&ucase_props_singleton.trie, c);
    if(!UCASE_HAS_EXCEPTION(props)) {
        return props&UCASE_DOT_MASK;
    } else {
        const uint16_t *pe=GET_EXCEPTIONS(&ucase_props_singleton, props);
        return (*pe>>UCASE_EXC_DOT_SHIFT)&UCASE_DOT_MASK;
    }
}

U_CAPI UBool U_EXPORT2
ucase_isSoftDotted(UChar32 c) {
    return (UBool)(getDotType(c)==UCASE_SOFT_DOTTED);
}

U_CAPI UBool U_EXPORT2
ucase_isCaseSensitive(UChar32 c) {
    uint16_t props=UTRIE2_GET16(&ucase_props_singleton.trie, c);
    if(!UCASE_HAS_EXCEPTION(props)) {
        return (UBool)((props&UCASE_SENSITIVE)!=0);
    } else {
        const uint16_t *pe=GET_EXCEPTIONS(&ucase_props_singleton, props);
        return (UBool)((*pe&UCASE_EXC_SENSITIVE)!=0);
    }
}

/* string casing ------------------------------------------------------------ */

/*
 * These internal functions form the core of string case mappings.
 * They map single code points to result code points or strings and take
 * all necessary conditions (context, locale ID, options) into account.
 *
 * They do not iterate over the source or write to the destination
 * so that the same functions are useful for non-standard string storage,
 * such as in a Replaceable (for Transliterator) or UTF-8/32 strings etc.
 * For the same reason, the "surrounding text" context is passed in as a
 * UCaseContextIterator which does not make any assumptions about
 * the underlying storage.
 *
 * This section contains helper functions that check for conditions
 * in the input text surrounding the current code point
 * according to SpecialCasing.txt.
 *
 * Each helper function gets the index
 * - after the current code point if it looks at following text
 * - before the current code point if it looks at preceding text
 *
 * Unicode 3.2 UAX 21 "Case Mappings" defines the conditions as follows:
 *
 * Final_Sigma
 *   C is preceded by a sequence consisting of
 *     a cased letter and a case-ignorable sequence,
 *   and C is not followed by a sequence consisting of
 *     an ignorable sequence and then a cased letter.
 *
 * More_Above
 *   C is followed by one or more characters of combining class 230 (ABOVE)
 *   in the combining character sequence.
 *
 * After_Soft_Dotted
 *   The last preceding character with combining class of zero before C
 *   was Soft_Dotted,
 *   and there is no intervening combining character class 230 (ABOVE).
 *
 * Before_Dot
 *   C is followed by combining dot above (U+0307).
 *   Any sequence of characters with a combining class that is neither 0 nor 230
 *   may intervene between the current character and the combining dot above.
 *
 * The erratum from 2002-10-31 adds the condition
 *
 * After_I
 *   The last preceding base character was an uppercase I, and there is no
 *   intervening combining character class 230 (ABOVE).
 *
 *   (See Jitterbug 2344 and the comments on After_I below.)
 *
 * Helper definitions in Unicode 3.2 UAX 21:
 *
 * D1. A character C is defined to be cased
 *     if it meets any of the following criteria:
 *
 *   - The general category of C is Titlecase Letter (Lt)
 *   - In [CoreProps], C has one of the properties Uppercase, or Lowercase
 *   - Given D = NFD(C), then it is not the case that:
 *     D = UCD_lower(D) = UCD_upper(D) = UCD_title(D)
 *     (This third criterion does not add any characters to the list
 *      for Unicode 3.2. Ignored.)
 *
 * D2. A character C is defined to be case-ignorable
 *     if it meets either of the following criteria:
 *
 *   - The general category of C is
 *     Nonspacing Mark (Mn), or Enclosing Mark (Me), or Format Control (Cf), or
 *     Letter Modifier (Lm), or Symbol Modifier (Sk)
 *   - C is one of the following characters
 *     U+0027 APOSTROPHE
 *     U+00AD SOFT HYPHEN (SHY)
 *     U+2019 RIGHT SINGLE QUOTATION MARK
 *            (the preferred character for apostrophe)
 *
 * D3. A case-ignorable sequence is a sequence of
 *     zero or more case-ignorable characters.
 */

#define is_d(c) ((c)=='d' || (c)=='D')
#define is_e(c) ((c)=='e' || (c)=='E')
#define is_i(c) ((c)=='i' || (c)=='I')
#define is_l(c) ((c)=='l' || (c)=='L')
#define is_r(c) ((c)=='r' || (c)=='R')
#define is_t(c) ((c)=='t' || (c)=='T')
#define is_u(c) ((c)=='u' || (c)=='U')
#define is_y(c) ((c)=='y' || (c)=='Y')
#define is_z(c) ((c)=='z' || (c)=='Z')

/* separator? */
#define is_sep(c) ((c)=='_' || (c)=='-' || (c)==0)

/**
 * Requires non-nullptr locale ID but otherwise does the equivalent of
 * checking for language codes as if uloc_getLanguage() were called:
 * Accepts both 2- and 3-letter codes and accepts case variants.
 */
U_CFUNC int32_t
ucase_getCaseLocale(const char *locale) {
    /*
     * This function used to use uloc_getLanguage(), but the current code
     * removes the dependency of this low-level code on uloc implementation code
     * and is faster because not the whole locale ID has to be
     * examined and copied/transformed.
     *
     * Because this code does not want to depend on uloc, the caller must
     * pass in a non-nullptr locale, i.e., may need to call uloc_getDefault().
     */
    char c=*locale++;
    // Fastpath for English "en" which is often used for default (=root locale) case mappings,
    // and for Chinese "zh": Very common but no special case mapping behavior.
    // Then check lowercase vs. uppercase to reduce the number of comparisons
    // for other locales without special behavior.
    if(c=='e') {
        /* el or ell? */
        c=*locale++;
        if(is_l(c)) {
            c=*locale++;
            if(is_l(c)) {
                c=*locale;
            }
            if(is_sep(c)) {
                return UCASE_LOC_GREEK;
            }
        }
        // en, es, ... -> root
    } else if(c=='z') {
        return UCASE_LOC_ROOT;
#if U_CHARSET_FAMILY==U_ASCII_FAMILY
    } else if(c>='a') {  // ASCII a-z = 0x61..0x7a, after A-Z
#elif U_CHARSET_FAMILY==U_EBCDIC_FAMILY
    } else if(c<='z') {  // EBCDIC a-z = 0x81..0xa9 with two gaps, before A-Z
#else
#   error Unknown charset family!
#endif
        // lowercase c
        if(c=='t') {
            /* tr or tur? */
            c=*locale++;
            if(is_u(c)) {
                c=*locale++;
            }
            if(is_r(c)) {
                c=*locale;
                if(is_sep(c)) {
                    return UCASE_LOC_TURKISH;
                }
            }
        } else if(c=='a') {
            /* az or aze? */
            c=*locale++;
            if(is_z(c)) {
                c=*locale++;
                if(is_e(c)) {
                    c=*locale;
                }
                if(is_sep(c)) {
                    return UCASE_LOC_TURKISH;
                }
            }
        } else if(c=='l') {
            /* lt or lit? */
            c=*locale++;
            if(is_i(c)) {
                c=*locale++;
            }
            if(is_t(c)) {
                c=*locale;
                if(is_sep(c)) {
                    return UCASE_LOC_LITHUANIAN;
                }
            }
        } else if(c=='n') {
            /* nl or nld? */
            c=*locale++;
            if(is_l(c)) {
                c=*locale++;
                if(is_d(c)) {
                    c=*locale;
                }
                if(is_sep(c)) {
                    return UCASE_LOC_DUTCH;
                }
            }
        } else if(c=='h') {
            /* hy or hye? *not* hyw */
            c=*locale++;
            if(is_y(c)) {
                c=*locale++;
                if(is_e(c)) {
                    c=*locale;
                }
                if(is_sep(c)) {
                    return UCASE_LOC_ARMENIAN;
                }
            }
        }
    } else {
        // uppercase c
        // Same code as for lowercase c but also check for 'E'.
        if(c=='T') {
            /* tr or tur? */
            c=*locale++;
            if(is_u(c)) {
                c=*locale++;
            }
            if(is_r(c)) {
                c=*locale;
                if(is_sep(c)) {
                    return UCASE_LOC_TURKISH;
                }
            }
        } else if(c=='A') {
            /* az or aze? */
            c=*locale++;
            if(is_z(c)) {
                c=*locale++;
                if(is_e(c)) {
                    c=*locale;
                }
                if(is_sep(c)) {
                    return UCASE_LOC_TURKISH;
                }
            }
        } else if(c=='L') {
            /* lt or lit? */
            c=*locale++;
            if(is_i(c)) {
                c=*locale++;
            }
            if(is_t(c)) {
                c=*locale;
                if(is_sep(c)) {
                    return UCASE_LOC_LITHUANIAN;
                }
            }
        } else if(c=='E') {
            /* el or ell? */
            c=*locale++;
            if(is_l(c)) {
                c=*locale++;
                if(is_l(c)) {
                    c=*locale;
                }
                if(is_sep(c)) {
                    return UCASE_LOC_GREEK;
                }
            }
        } else if(c=='N') {
            /* nl or nld? */
            c=*locale++;
            if(is_l(c)) {
                c=*locale++;
                if(is_d(c)) {
                    c=*locale;
                }
                if(is_sep(c)) {
                    return UCASE_LOC_DUTCH;
                }
            }
        } else if(c=='H') {
            /* hy or hye? *not* hyw */
            c=*locale++;
            if(is_y(c)) {
                c=*locale++;
                if(is_e(c)) {
                    c=*locale;
                }
                if(is_sep(c)) {
                    return UCASE_LOC_ARMENIAN;
                }
            }
        }
    }
    return UCASE_LOC_ROOT;
}

/*
 * Is followed by
 *   {case-ignorable}* cased
 * ?
 * (dir determines looking forward/backward)
 * If a character is case-ignorable, it is skipped regardless of whether
 * it is also cased or not.
 */
static UBool
isFollowedByCasedLetter(UCaseContextIterator *iter, void *context, int8_t dir) {
    UChar32 c;

    if(iter==nullptr) {
        return false;
    }

    for(/* dir!=0 sets direction */; (c=iter(context, dir))>=0; dir=0) {
        int32_t type=ucase_getTypeOrIgnorable(c);
        if(type&4) {
            /* case-ignorable, continue with the loop */
        } else if(type!=UCASE_NONE) {
            return true; /* followed by cased letter */
        } else {
            return false; /* uncased and not case-ignorable */
        }
    }

    return false; /* not followed by cased letter */
}

/* Is preceded by Soft_Dotted character with no intervening cc=230 ? */
static UBool
isPrecededBySoftDotted(UCaseContextIterator *iter, void *context) {
    UChar32 c;
    int32_t dotType;
    int8_t dir;

    if(iter==nullptr) {
        return false;
    }

    for(dir=-1; (c=iter(context, dir))>=0; dir=0) {
        dotType=getDotType(c);
        if(dotType==UCASE_SOFT_DOTTED) {
            return true; /* preceded by TYPE_i */
        } else if(dotType!=UCASE_OTHER_ACCENT) {
            return false; /* preceded by different base character (not TYPE_i), or intervening cc==230 */
        }
    }

    return false; /* not preceded by TYPE_i */
}

/*
 * See Jitterbug 2344:
 * The condition After_I for Turkic-lowercasing of U+0307 combining dot above
 * is checked in ICU 2.0, 2.1, 2.6 but was not in 2.2 & 2.4 because
 * we made those releases compatible with Unicode 3.2 which had not fixed
 * a related bug in SpecialCasing.txt.
 *
 * From the Jitterbug 2344 text:
 * ... this bug is listed as a Unicode erratum
 * from 2002-10-31 at http://www.unicode.org/uni2errata/UnicodeErrata.html
 * <quote>
 * There are two errors in SpecialCasing.txt.
 * 1. Missing semicolons on two lines. ... [irrelevant for ICU]
 * 2. An incorrect context definition. Correct as follows:
 * < 0307; ; 0307; 0307; tr After_Soft_Dotted; # COMBINING DOT ABOVE
 * < 0307; ; 0307; 0307; az After_Soft_Dotted; # COMBINING DOT ABOVE
 * ---
 * > 0307; ; 0307; 0307; tr After_I; # COMBINING DOT ABOVE
 * > 0307; ; 0307; 0307; az After_I; # COMBINING DOT ABOVE
 * where the context After_I is defined as:
 * The last preceding base character was an uppercase I, and there is no
 * intervening combining character class 230 (ABOVE).
 * </quote>
 *
 * Note that SpecialCasing.txt even in Unicode 3.2 described the condition as:
 *
 * # When lowercasing, remove dot_above in the sequence I + dot_above, which will turn into i.
 * # This matches the behavior of the canonically equivalent I-dot_above
 *
 * See also the description in this place in older versions of uchar.c (revision 1.100).
 *
 * Markus W. Scherer 2003-feb-15
 */

/* Is preceded by base character 'I' with no intervening cc=230 ? */
static UBool
isPrecededBy_I(UCaseContextIterator *iter, void *context) {
    UChar32 c;
    int32_t dotType;
    int8_t dir;

    if(iter==nullptr) {
        return false;
    }

    for(dir=-1; (c=iter(context, dir))>=0; dir=0) {
        if(c==0x49) {
            return true; /* preceded by I */
        }
        dotType=getDotType(c);
        if(dotType!=UCASE_OTHER_ACCENT) {
            return false; /* preceded by different base character (not I), or intervening cc==230 */
        }
    }

    return false; /* not preceded by I */
}

/* Is followed by one or more cc==230 ? */
static UBool
isFollowedByMoreAbove(UCaseContextIterator *iter, void *context) {
    UChar32 c;
    int32_t dotType;
    int8_t dir;

    if(iter==nullptr) {
        return false;
    }

    for(dir=1; (c=iter(context, dir))>=0; dir=0) {
        dotType=getDotType(c);
        if(dotType==UCASE_ABOVE) {
            return true; /* at least one cc==230 following */
        } else if(dotType!=UCASE_OTHER_ACCENT) {
            return false; /* next base character, no more cc==230 following */
        }
    }

    return false; /* no more cc==230 following */
}

/* Is followed by a dot above (without cc==230 in between) ? */
static UBool
isFollowedByDotAbove(UCaseContextIterator *iter, void *context) {
    UChar32 c;
    int32_t dotType;
    int8_t dir;

    if(iter==nullptr) {
        return false;
    }

    for(dir=1; (c=iter(context, dir))>=0; dir=0) {
        if(c==0x307) {
            return true;
        }
        dotType=getDotType(c);
        if(dotType!=UCASE_OTHER_ACCENT) {
            return false; /* next base character or cc==230 in between */
        }
    }

    return false; /* no dot above following */
}

U_CAPI int32_t U_EXPORT2
ucase_toFullLower(UChar32 c,
                  UCaseContextIterator *iter, void *context,
                  const char16_t **pString,
                  int32_t loc) {
    // The sign of the result has meaning, input must be non-negative so that it can be returned as is.
    U_ASSERT(c >= 0);
    UChar32 result=c;
    // Reset the output pointer in case it was uninitialized.
    *pString=nullptr;
    uint16_t props=UTRIE2_GET16(&ucase_props_singleton.trie, c);
    if(!UCASE_HAS_EXCEPTION(props)) {
        if(UCASE_IS_UPPER_OR_TITLE(props)) {
            result=c+UCASE_GET_DELTA(props);
        }
    } else {
        const uint16_t *pe=GET_EXCEPTIONS(&ucase_props_singleton, props), *pe2;
        uint16_t excWord=*pe++;
        int32_t full;

        pe2=pe;

        if(excWord&UCASE_EXC_CONDITIONAL_SPECIAL) {
            /* use hardcoded conditions and mappings */

            /*
             * Test for conditional mappings first
             *   (otherwise the unconditional default mappings are always taken),
             * then test for characters that have unconditional mappings in SpecialCasing.txt,
             * then get the UnicodeData.txt mappings.
             */
            if( loc==UCASE_LOC_LITHUANIAN &&
                    /* base characters, find accents above */
                    (((c==0x49 || c==0x4a || c==0x12e) &&
                        isFollowedByMoreAbove(iter, context)) ||
                    /* precomposed with accent above, no need to find one */
                    (c==0xcc || c==0xcd || c==0x128))
            ) {
                /*
                    # Lithuanian

                    # Lithuanian retains the dot in a lowercase i when followed by accents.

                    # Introduce an explicit dot above when lowercasing capital I's and J's
                    # whenever there are more accents above.
                    # (of the accents used in Lithuanian: grave, acute, tilde above, and ogonek)

                    0049; 0069 0307; 0049; 0049; lt More_Above; # LATIN CAPITAL LETTER I
                    004A; 006A 0307; 004A; 004A; lt More_Above; # LATIN CAPITAL LETTER J
                    012E; 012F 0307; 012E; 012E; lt More_Above; # LATIN CAPITAL LETTER I WITH OGONEK
                    00CC; 0069 0307 0300; 00CC; 00CC; lt; # LATIN CAPITAL LETTER I WITH GRAVE
                    00CD; 0069 0307 0301; 00CD; 00CD; lt; # LATIN CAPITAL LETTER I WITH ACUTE
                    0128; 0069 0307 0303; 0128; 0128; lt; # LATIN CAPITAL LETTER I WITH TILDE
                 */
                switch(c) {
                case 0x49:  /* LATIN CAPITAL LETTER I */
                    *pString=iDot;
                    return 2;
                case 0x4a:  /* LATIN CAPITAL LETTER J */
                    *pString=jDot;
                    return 2;
                case 0x12e: /* LATIN CAPITAL LETTER I WITH OGONEK */
                    *pString=iOgonekDot;
                    return 2;
                case 0xcc:  /* LATIN CAPITAL LETTER I WITH GRAVE */
                    *pString=iDotGrave;
                    return 3;
                case 0xcd:  /* LATIN CAPITAL LETTER I WITH ACUTE */
                    *pString=iDotAcute;
                    return 3;
                case 0x128: /* LATIN CAPITAL LETTER I WITH TILDE */
                    *pString=iDotTilde;
                    return 3;
                default:
                    return 0; /* will not occur */
                }
            /* # Turkish and Azeri */
            } else if(loc==UCASE_LOC_TURKISH && c==0x130) {
                /*
                    # I and i-dotless; I-dot and i are case pairs in Turkish and Azeri
                    # The following rules handle those cases.

                    0130; 0069; 0130; 0130; tr # LATIN CAPITAL LETTER I WITH DOT ABOVE
                    0130; 0069; 0130; 0130; az # LATIN CAPITAL LETTER I WITH DOT ABOVE
                 */
                return 0x69;
            } else if(loc==UCASE_LOC_TURKISH && c==0x307 && isPrecededBy_I(iter, context)) {
                /*
                    # When lowercasing, remove dot_above in the sequence I + dot_above, which will turn into i.
                    # This matches the behavior of the canonically equivalent I-dot_above

                    0307; ; 0307; 0307; tr After_I; # COMBINING DOT ABOVE
                    0307; ; 0307; 0307; az After_I; # COMBINING DOT ABOVE
                 */
                return 0; /* remove the dot (continue without output) */
            } else if(loc==UCASE_LOC_TURKISH && c==0x49 && !isFollowedByDotAbove(iter, context)) {
                /*
                    # When lowercasing, unless an I is before a dot_above, it turns into a dotless i.

                    0049; 0131; 0049; 0049; tr Not_Before_Dot; # LATIN CAPITAL LETTER I
                    0049; 0131; 0049; 0049; az Not_Before_Dot; # LATIN CAPITAL LETTER I
                 */
                return 0x131;
            } else if(c==0x130) {
                /*
                    # Preserve canonical equivalence for I with dot. Turkic is handled below.

                    0130; 0069 0307; 0130; 0130; # LATIN CAPITAL LETTER I WITH DOT ABOVE
                 */
                *pString=iDot;
                return 2;
            } else if(  c==0x3a3 &&
                        !isFollowedByCasedLetter(iter, context, 1) &&
                        isFollowedByCasedLetter(iter, context, -1) /* -1=preceded */
            ) {
                /* greek capital sigma maps depending on surrounding cased letters (see SpecialCasing.txt) */
                /*
                    # Special case for final form of sigma

                    03A3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK CAPITAL LETTER SIGMA
                 */
                return 0x3c2; /* greek small final sigma */
            } else {
                /* no known conditional special case mapping, use a normal mapping */
            }
        } else if(HAS_SLOT(excWord, UCASE_EXC_FULL_MAPPINGS)) {
            GET_SLOT_VALUE(excWord, UCASE_EXC_FULL_MAPPINGS, pe, full);
            full&=UCASE_FULL_LOWER;
            if(full!=0) {
                /* set the output pointer to the lowercase mapping */
                *pString=reinterpret_cast<const char16_t *>(pe+1);

                /* return the string length */
                return full;
            }
        }

        if(HAS_SLOT(excWord, UCASE_EXC_DELTA) && UCASE_IS_UPPER_OR_TITLE(props)) {
            int32_t delta;
            GET_SLOT_VALUE(excWord, UCASE_EXC_DELTA, pe2, delta);
            return (excWord&UCASE_EXC_DELTA_IS_NEGATIVE)==0 ? c+delta : c-delta;
        }
        if(HAS_SLOT(excWord, UCASE_EXC_LOWER)) {
            GET_SLOT_VALUE(excWord, UCASE_EXC_LOWER, pe2, result);
        }
    }

    return (result==c) ? ~result : result;
}

/* internal */
static int32_t
toUpperOrTitle(UChar32 c,
               UCaseContextIterator *iter, void *context,
               const char16_t **pString,
               int32_t loc,
               UBool upperNotTitle) {
    // The sign of the result has meaning, input must be non-negative so that it can be returned as is.
    U_ASSERT(c >= 0);
    UChar32 result=c;
    // Reset the output pointer in case it was uninitialized.
    *pString=nullptr;
    uint16_t props=UTRIE2_GET16(&ucase_props_singleton.trie, c);
    if(!UCASE_HAS_EXCEPTION(props)) {
        if(UCASE_GET_TYPE(props)==UCASE_LOWER) {
            result=c+UCASE_GET_DELTA(props);
        }
    } else {
        const uint16_t *pe=GET_EXCEPTIONS(&ucase_props_singleton, props), *pe2;
        uint16_t excWord=*pe++;
        int32_t full, idx;

        pe2=pe;

        if(excWord&UCASE_EXC_CONDITIONAL_SPECIAL) {
            /* use hardcoded conditions and mappings */
            if(loc==UCASE_LOC_TURKISH && c==0x69) {
                /*
                    # Turkish and Azeri

                    # I and i-dotless; I-dot and i are case pairs in Turkish and Azeri
                    # The following rules handle those cases.

                    # When uppercasing, i turns into a dotted capital I

                    0069; 0069; 0130; 0130; tr; # LATIN SMALL LETTER I
                    0069; 0069; 0130; 0130; az; # LATIN SMALL LETTER I
                */
                return 0x130;
            } else if(loc==UCASE_LOC_LITHUANIAN && c==0x307 && isPrecededBySoftDotted(iter, context)) {
                /*
                    # Lithuanian

                    # Lithuanian retains the dot in a lowercase i when followed by accents.

                    # Remove DOT ABOVE after "i" with upper or titlecase

                    0307; 0307; ; ; lt After_Soft_Dotted; # COMBINING DOT ABOVE
                 */
                return 0; /* remove the dot (continue without output) */
            } else if(c==0x0587) {
                // See ICU-13416:
                // և ligature ech-yiwn
                // uppercases to ԵՒ=ech+yiwn by default and in Western Armenian,
                // but to ԵՎ=ech+vew in Eastern Armenian.
                if(loc==UCASE_LOC_ARMENIAN) {
                    *pString=upperNotTitle ? u"ԵՎ" : u"Եվ";
                } else {
                    *pString=upperNotTitle ? u"ԵՒ" : u"Եւ";
                }
                return 2;
            } else {
                /* no known conditional special case mapping, use a normal mapping */
            }
        } else if(HAS_SLOT(excWord, UCASE_EXC_FULL_MAPPINGS)) {
            GET_SLOT_VALUE(excWord, UCASE_EXC_FULL_MAPPINGS, pe, full);

            /* start of full case mapping strings */
            ++pe;

            /* skip the lowercase and case-folding result strings */
            pe+=full&UCASE_FULL_LOWER;
            full>>=4;
            pe+=full&0xf;
            full>>=4;

            if(upperNotTitle) {
                full&=0xf;
            } else {
                /* skip the uppercase result string */
                pe+=full&0xf;
                full=(full>>4)&0xf;
            }

            if(full!=0) {
                /* set the output pointer to the result string */
                *pString=reinterpret_cast<const char16_t *>(pe);

                /* return the string length */
                return full;
            }
        }

        if(HAS_SLOT(excWord, UCASE_EXC_DELTA) && UCASE_GET_TYPE(props)==UCASE_LOWER) {
            int32_t delta;
            GET_SLOT_VALUE(excWord, UCASE_EXC_DELTA, pe2, delta);
            return (excWord&UCASE_EXC_DELTA_IS_NEGATIVE)==0 ? c+delta : c-delta;
        }
        if(!upperNotTitle && HAS_SLOT(excWord, UCASE_EXC_TITLE)) {
            idx=UCASE_EXC_TITLE;
        } else if(HAS_SLOT(excWord, UCASE_EXC_UPPER)) {
            /* here, titlecase is same as uppercase */
            idx=UCASE_EXC_UPPER;
        } else {
            return ~c;
        }
        GET_SLOT_VALUE(excWord, idx, pe2, result);
    }

    return (result==c) ? ~result : result;
}

U_CAPI int32_t U_EXPORT2
ucase_toFullUpper(UChar32 c,
                  UCaseContextIterator *iter, void *context,
                  const char16_t **pString,
                  int32_t caseLocale) {
    return toUpperOrTitle(c, iter, context, pString, caseLocale, true);
}

U_CAPI int32_t U_EXPORT2
ucase_toFullTitle(UChar32 c,
                  UCaseContextIterator *iter, void *context,
                  const char16_t **pString,
                  int32_t caseLocale) {
    return toUpperOrTitle(c, iter, context, pString, caseLocale, false);
}

/* case folding ------------------------------------------------------------- */

/*
 * Case folding is similar to lowercasing.
 * The result may be a simple mapping, i.e., a single code point, or
 * a full mapping, i.e., a string.
 * If the case folding for a code point is the same as its simple (1:1) lowercase mapping,
 * then only the lowercase mapping is stored.
 *
 * Some special cases are hardcoded because their conditions cannot be
 * parsed and processed from CaseFolding.txt.
 *
 * Unicode 3.2 CaseFolding.txt specifies for its status field:

# C: common case folding, common mappings shared by both simple and full mappings.
# F: full case folding, mappings that cause strings to grow in length. Multiple characters are separated by spaces.
# S: simple case folding, mappings to single characters where different from F.
# T: special case for uppercase I and dotted uppercase I
#    - For non-Turkic languages, this mapping is normally not used.
#    - For Turkic languages (tr, az), this mapping can be used instead of the normal mapping for these characters.
#
# Usage:
#  A. To do a simple case folding, use the mappings with status C + S.
#  B. To do a full case folding, use the mappings with status C + F.
#
#    The mappings with status T can be used or omitted depending on the desired case-folding
#    behavior. (The default option is to exclude them.)

 * Unicode 3.2 has 'T' mappings as follows:

0049; T; 0131; # LATIN CAPITAL LETTER I
0130; T; 0069; # LATIN CAPITAL LETTER I WITH DOT ABOVE

 * while the default mappings for these code points are:

0049; C; 0069; # LATIN CAPITAL LETTER I
0130; F; 0069 0307; # LATIN CAPITAL LETTER I WITH DOT ABOVE

 * U+0130 has no simple case folding (simple-case-folds to itself).
 */

/* return the simple case folding mapping for c */
U_CAPI UChar32 U_EXPORT2
ucase_fold(UChar32 c, uint32_t options) {
    uint16_t props=UTRIE2_GET16(&ucase_props_singleton.trie, c);
    if(!UCASE_HAS_EXCEPTION(props)) {
        if(UCASE_IS_UPPER_OR_TITLE(props)) {
            c+=UCASE_GET_DELTA(props);
        }
    } else {
        const uint16_t *pe=GET_EXCEPTIONS(&ucase_props_singleton, props);
        uint16_t excWord=*pe++;
        int32_t idx;
        if(excWord&UCASE_EXC_CONDITIONAL_FOLD) {
            /* special case folding mappings, hardcoded */
            if((options&_FOLD_CASE_OPTIONS_MASK)==U_FOLD_CASE_DEFAULT) {
                /* default mappings */
                if(c==0x49) {
                    /* 0049; C; 0069; # LATIN CAPITAL LETTER I */
                    return 0x69;
                } else if(c==0x130) {
                    /* no simple case folding for U+0130 */
                    return c;
                }
            } else {
                /* Turkic mappings */
                if(c==0x49) {
                    /* 0049; T; 0131; # LATIN CAPITAL LETTER I */
                    return 0x131;
                } else if(c==0x130) {
                    /* 0130; T; 0069; # LATIN CAPITAL LETTER I WITH DOT ABOVE */
                    return 0x69;
                }
            }
        }
        if((excWord&UCASE_EXC_NO_SIMPLE_CASE_FOLDING)!=0) {
            return c;
        }
        if(HAS_SLOT(excWord, UCASE_EXC_DELTA) && UCASE_IS_UPPER_OR_TITLE(props)) {
            int32_t delta;
            GET_SLOT_VALUE(excWord, UCASE_EXC_DELTA, pe, delta);
            return (excWord&UCASE_EXC_DELTA_IS_NEGATIVE)==0 ? c+delta : c-delta;
        }
        if(HAS_SLOT(excWord, UCASE_EXC_FOLD)) {
            idx=UCASE_EXC_FOLD;
        } else if(HAS_SLOT(excWord, UCASE_EXC_LOWER)) {
            idx=UCASE_EXC_LOWER;
        } else {
            return c;
        }
        GET_SLOT_VALUE(excWord, idx, pe, c);
    }
    return c;
}

/*
 * Issue for canonical caseless match (UAX #21):
 * Turkic casefolding (using "T" mappings in CaseFolding.txt) does not preserve
 * canonical equivalence, unlike default-option casefolding.
 * For example, I-grave and I + grave fold to strings that are not canonically
 * equivalent.
 * For more details, see the comment in unorm_compare() in unorm.cpp
 * and the intermediate prototype changes for Jitterbug 2021.
 * (For example, revision 1.104 of uchar.c and 1.4 of CaseFolding.txt.)
 *
 * This did not get fixed because it appears that it is not possible to fix
 * it for uppercase and lowercase characters (I-grave vs. i-grave)
 * together in a way that they still fold to common result strings.
 */

U_CAPI int32_t U_EXPORT2
ucase_toFullFolding(UChar32 c,
                    const char16_t **pString,
                    uint32_t options) {
    // The sign of the result has meaning, input must be non-negative so that it can be returned as is.
    U_ASSERT(c >= 0);
    UChar32 result=c;
    // Reset the output pointer in case it was uninitialized.
    *pString=nullptr;
    uint16_t props=UTRIE2_GET16(&ucase_props_singleton.trie, c);
    if(!UCASE_HAS_EXCEPTION(props)) {
        if(UCASE_IS_UPPER_OR_TITLE(props)) {
            result=c+UCASE_GET_DELTA(props);
        }
    } else {
        const uint16_t *pe=GET_EXCEPTIONS(&ucase_props_singleton, props), *pe2;
        uint16_t excWord=*pe++;
        int32_t full, idx;

        pe2=pe;

        if(excWord&UCASE_EXC_CONDITIONAL_FOLD) {
            /* use hardcoded conditions and mappings */
            if((options&_FOLD_CASE_OPTIONS_MASK)==U_FOLD_CASE_DEFAULT) {
                /* default mappings */
                if(c==0x49) {
                    /* 0049; C; 0069; # LATIN CAPITAL LETTER I */
                    return 0x69;
                } else if(c==0x130) {
                    /* 0130; F; 0069 0307; # LATIN CAPITAL LETTER I WITH DOT ABOVE */
                    *pString=iDot;
                    return 2;
                }
            } else {
                /* Turkic mappings */
                if(c==0x49) {
                    /* 0049; T; 0131; # LATIN CAPITAL LETTER I */
                    return 0x131;
                } else if(c==0x130) {
                    /* 0130; T; 0069; # LATIN CAPITAL LETTER I WITH DOT ABOVE */
                    return 0x69;
                }
            }
        } else if(HAS_SLOT(excWord, UCASE_EXC_FULL_MAPPINGS)) {
            GET_SLOT_VALUE(excWord, UCASE_EXC_FULL_MAPPINGS, pe, full);

            /* start of full case mapping strings */
            ++pe;

            /* skip the lowercase result string */
            pe+=full&UCASE_FULL_LOWER;
            full=(full>>4)&0xf;

            if(full!=0) {
                /* set the output pointer to the result string */
                *pString=reinterpret_cast<const char16_t *>(pe);

                /* return the string length */
                return full;
            }
        }

        if((excWord&UCASE_EXC_NO_SIMPLE_CASE_FOLDING)!=0) {
            return ~c;
        }
        if(HAS_SLOT(excWord, UCASE_EXC_DELTA) && UCASE_IS_UPPER_OR_TITLE(props)) {
            int32_t delta;
            GET_SLOT_VALUE(excWord, UCASE_EXC_DELTA, pe2, delta);
            return (excWord&UCASE_EXC_DELTA_IS_NEGATIVE)==0 ? c+delta : c-delta;
        }
        if(HAS_SLOT(excWord, UCASE_EXC_FOLD)) {
            idx=UCASE_EXC_FOLD;
        } else if(HAS_SLOT(excWord, UCASE_EXC_LOWER)) {
            idx=UCASE_EXC_LOWER;
        } else {
            return ~c;
        }
        GET_SLOT_VALUE(excWord, idx, pe2, result);
    }

    return (result==c) ? ~result : result;
}

/* case mapping properties API ---------------------------------------------- */

/* public API (see uchar.h) */

U_CAPI UBool U_EXPORT2
u_isULowercase(UChar32 c) {
    return (UBool)(UCASE_LOWER==ucase_getType(c));
}

U_CAPI UBool U_EXPORT2
u_isUUppercase(UChar32 c) {
    return (UBool)(UCASE_UPPER==ucase_getType(c));
}

/* Transforms the Unicode character to its lower case equivalent.*/
U_CAPI UChar32 U_EXPORT2
u_tolower(UChar32 c) {
    return ucase_tolower(c);
}

/* Transforms the Unicode character to its upper case equivalent.*/
U_CAPI UChar32 U_EXPORT2
u_toupper(UChar32 c) {
    return ucase_toupper(c);
}

/* Transforms the Unicode character to its title case equivalent.*/
U_CAPI UChar32 U_EXPORT2
u_totitle(UChar32 c) {
    return ucase_totitle(c);
}

/* return the simple case folding mapping for c */
U_CAPI UChar32 U_EXPORT2
u_foldCase(UChar32 c, uint32_t options) {
    return ucase_fold(c, options);
}

U_CFUNC int32_t U_EXPORT2
ucase_hasBinaryProperty(UChar32 c, UProperty which) {
    /* case mapping properties */
    const char16_t *resultString;
    switch(which) {
    case UCHAR_LOWERCASE:
        return (UBool)(UCASE_LOWER==ucase_getType(c));
    case UCHAR_UPPERCASE:
        return (UBool)(UCASE_UPPER==ucase_getType(c));
    case UCHAR_SOFT_DOTTED:
        return ucase_isSoftDotted(c);
    case UCHAR_CASE_SENSITIVE:
        return ucase_isCaseSensitive(c);
    case UCHAR_CASED:
        return (UBool)(UCASE_NONE!=ucase_getType(c));
    case UCHAR_CASE_IGNORABLE:
        return (UBool)(ucase_getTypeOrIgnorable(c)>>2);
    /*
     * Note: The following Changes_When_Xyz are defined as testing whether
     * the NFD form of the input changes when Xyz-case-mapped.
     * However, this simpler implementation of these properties,
     * ignoring NFD, passes the tests.
     * The implementation needs to be changed if the tests start failing.
     * When that happens, optimizations should be used to work with the
     * per-single-code point ucase_toFullXyz() functions unless
     * the NFD form has more than one code point,
     * and the property starts set needs to be the union of the
     * start sets for normalization and case mappings.
     */
    case UCHAR_CHANGES_WHEN_LOWERCASED:
        return (UBool)(ucase_toFullLower(c, nullptr, nullptr, &resultString, UCASE_LOC_ROOT)>=0);
    case UCHAR_CHANGES_WHEN_UPPERCASED:
        return (UBool)(ucase_toFullUpper(c, nullptr, nullptr, &resultString, UCASE_LOC_ROOT)>=0);
    case UCHAR_CHANGES_WHEN_TITLECASED:
        return (UBool)(ucase_toFullTitle(c, nullptr, nullptr, &resultString, UCASE_LOC_ROOT)>=0);
    /* case UCHAR_CHANGES_WHEN_CASEFOLDED: -- in uprops.c */
    case UCHAR_CHANGES_WHEN_CASEMAPPED:
        return (UBool)(
            ucase_toFullLower(c, nullptr, nullptr, &resultString, UCASE_LOC_ROOT)>=0 ||
            ucase_toFullUpper(c, nullptr, nullptr, &resultString, UCASE_LOC_ROOT)>=0 ||
            ucase_toFullTitle(c, nullptr, nullptr, &resultString, UCASE_LOC_ROOT)>=0);
    default:
        return false;
    }
}