summaryrefslogtreecommitdiff
path: root/utf8.c
blob: 3b5d5d4a9c5185ad6da7fb207759aaeb8a35f61c (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
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
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
/*    utf8.c
 *
 *    Copyright (C) 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007
 *    by Larry Wall and others
 *
 *    You may distribute under the terms of either the GNU General Public
 *    License or the Artistic License, as specified in the README file.
 *
 */

/*
 * 'What a fix!' said Sam. 'That's the one place in all the lands we've ever
 * heard of that we don't want to see any closer; and that's the one place
 * we're trying to get to!  And that's just where we can't get, nohow.'
 *
 * 'Well do I understand your speech,' he answered in the same language;
 * 'yet few strangers do so.  Why then do you not speak in the Common Tongue,
 * as is the custom in the West, if you wish to be answered?'
 *
 * ...the travellers perceived that the floor was paved with stones of many
 * hues; branching runes and strange devices intertwined beneath their feet.
 */

#include "EXTERN.h"
#define PERL_IN_UTF8_C
#include "perl.h"

#ifndef EBCDIC
/* Separate prototypes needed because in ASCII systems these
 * usually macros but they still are compiled as code, too. */
PERL_CALLCONV UV	Perl_utf8n_to_uvchr(pTHX_ const U8 *s, STRLEN curlen, STRLEN *retlen, U32 flags);
PERL_CALLCONV U8*	Perl_uvchr_to_utf8(pTHX_ U8 *d, UV uv);
#endif

static const char unees[] =
    "Malformed UTF-8 character (unexpected end of string)";

/* 
=head1 Unicode Support

This file contains various utility functions for manipulating UTF8-encoded
strings. For the uninitiated, this is a method of representing arbitrary
Unicode characters as a variable number of bytes, in such a way that
characters in the ASCII range are unmodified, and a zero byte never appears
within non-zero characters.

=for apidoc A|U8 *|uvuni_to_utf8_flags|U8 *d|UV uv|UV flags

Adds the UTF-8 representation of the Unicode codepoint C<uv> to the end
of the string C<d>; C<d> should be have at least C<UTF8_MAXBYTES+1> free
bytes available. The return value is the pointer to the byte after the
end of the new character. In other words,

    d = uvuni_to_utf8_flags(d, uv, flags);

or, in most cases,

    d = uvuni_to_utf8(d, uv);

(which is equivalent to)

    d = uvuni_to_utf8_flags(d, uv, 0);

is the recommended Unicode-aware way of saying

    *(d++) = uv;

=cut
*/

U8 *
Perl_uvuni_to_utf8_flags(pTHX_ U8 *d, UV uv, UV flags)
{
    PERL_ARGS_ASSERT_UVUNI_TO_UTF8_FLAGS;

    if (ckWARN(WARN_UTF8)) {
	 if (UNICODE_IS_SURROGATE(uv) &&
	     !(flags & UNICODE_ALLOW_SURROGATE))
	      Perl_warner(aTHX_ packWARN(WARN_UTF8), "UTF-16 surrogate 0x%04"UVxf, uv);
	 else if (
		  ((uv >= 0xFDD0 && uv <= 0xFDEF &&
		    !(flags & UNICODE_ALLOW_FDD0))
		   ||
		   ((uv & 0xFFFE) == 0xFFFE && /* Either FFFE or FFFF. */
		    !(flags & UNICODE_ALLOW_FFFF))) &&
		  /* UNICODE_ALLOW_SUPER includes
		   * FFFEs and FFFFs beyond 0x10FFFF. */
		  ((uv <= PERL_UNICODE_MAX) ||
		   !(flags & UNICODE_ALLOW_SUPER))
		  )
	      Perl_warner(aTHX_ packWARN(WARN_UTF8),
			 "Unicode character 0x%04"UVxf" is illegal", uv);
    }
    if (UNI_IS_INVARIANT(uv)) {
	*d++ = (U8)UTF_TO_NATIVE(uv);
	return d;
    }
#if defined(EBCDIC)
    else {
	STRLEN len  = UNISKIP(uv);
	U8 *p = d+len-1;
	while (p > d) {
	    *p-- = (U8)UTF_TO_NATIVE((uv & UTF_CONTINUATION_MASK) | UTF_CONTINUATION_MARK);
	    uv >>= UTF_ACCUMULATION_SHIFT;
	}
	*p = (U8)UTF_TO_NATIVE((uv & UTF_START_MASK(len)) | UTF_START_MARK(len));
	return d+len;
    }
#else /* Non loop style */
    if (uv < 0x800) {
	*d++ = (U8)(( uv >>  6)         | 0xc0);
	*d++ = (U8)(( uv        & 0x3f) | 0x80);
	return d;
    }
    if (uv < 0x10000) {
	*d++ = (U8)(( uv >> 12)         | 0xe0);
	*d++ = (U8)(((uv >>  6) & 0x3f) | 0x80);
	*d++ = (U8)(( uv        & 0x3f) | 0x80);
	return d;
    }
    if (uv < 0x200000) {
	*d++ = (U8)(( uv >> 18)         | 0xf0);
	*d++ = (U8)(((uv >> 12) & 0x3f) | 0x80);
	*d++ = (U8)(((uv >>  6) & 0x3f) | 0x80);
	*d++ = (U8)(( uv        & 0x3f) | 0x80);
	return d;
    }
    if (uv < 0x4000000) {
	*d++ = (U8)(( uv >> 24)         | 0xf8);
	*d++ = (U8)(((uv >> 18) & 0x3f) | 0x80);
	*d++ = (U8)(((uv >> 12) & 0x3f) | 0x80);
	*d++ = (U8)(((uv >>  6) & 0x3f) | 0x80);
	*d++ = (U8)(( uv        & 0x3f) | 0x80);
	return d;
    }
    if (uv < 0x80000000) {
	*d++ = (U8)(( uv >> 30)         | 0xfc);
	*d++ = (U8)(((uv >> 24) & 0x3f) | 0x80);
	*d++ = (U8)(((uv >> 18) & 0x3f) | 0x80);
	*d++ = (U8)(((uv >> 12) & 0x3f) | 0x80);
	*d++ = (U8)(((uv >>  6) & 0x3f) | 0x80);
	*d++ = (U8)(( uv        & 0x3f) | 0x80);
	return d;
    }
#ifdef HAS_QUAD
    if (uv < UTF8_QUAD_MAX)
#endif
    {
	*d++ =                            0xfe;	/* Can't match U+FEFF! */
	*d++ = (U8)(((uv >> 30) & 0x3f) | 0x80);
	*d++ = (U8)(((uv >> 24) & 0x3f) | 0x80);
	*d++ = (U8)(((uv >> 18) & 0x3f) | 0x80);
	*d++ = (U8)(((uv >> 12) & 0x3f) | 0x80);
	*d++ = (U8)(((uv >>  6) & 0x3f) | 0x80);
	*d++ = (U8)(( uv        & 0x3f) | 0x80);
	return d;
    }
#ifdef HAS_QUAD
    {
	*d++ =                            0xff;		/* Can't match U+FFFE! */
	*d++ =                            0x80;		/* 6 Reserved bits */
	*d++ = (U8)(((uv >> 60) & 0x0f) | 0x80);	/* 2 Reserved bits */
	*d++ = (U8)(((uv >> 54) & 0x3f) | 0x80);
	*d++ = (U8)(((uv >> 48) & 0x3f) | 0x80);
	*d++ = (U8)(((uv >> 42) & 0x3f) | 0x80);
	*d++ = (U8)(((uv >> 36) & 0x3f) | 0x80);
	*d++ = (U8)(((uv >> 30) & 0x3f) | 0x80);
	*d++ = (U8)(((uv >> 24) & 0x3f) | 0x80);
	*d++ = (U8)(((uv >> 18) & 0x3f) | 0x80);
	*d++ = (U8)(((uv >> 12) & 0x3f) | 0x80);
	*d++ = (U8)(((uv >>  6) & 0x3f) | 0x80);
	*d++ = (U8)(( uv        & 0x3f) | 0x80);
	return d;
    }
#endif
#endif /* Loop style */
}

/*

Tests if some arbitrary number of bytes begins in a valid UTF-8
character.  Note that an INVARIANT (i.e. ASCII) character is a valid
UTF-8 character.  The actual number of bytes in the UTF-8 character
will be returned if it is valid, otherwise 0.

This is the "slow" version as opposed to the "fast" version which is
the "unrolled" IS_UTF8_CHAR().  E.g. for t/uni/class.t the speed
difference is a factor of 2 to 3.  For lengths (UTF8SKIP(s)) of four
or less you should use the IS_UTF8_CHAR(), for lengths of five or more
you should use the _slow().  In practice this means that the _slow()
will be used very rarely, since the maximum Unicode code point (as of
Unicode 4.1) is U+10FFFF, which encodes in UTF-8 to four bytes.  Only
the "Perl extended UTF-8" (the infamous 'v-strings') will encode into
five bytes or more.

=cut */
STATIC STRLEN
S_is_utf8_char_slow(const U8 *s, const STRLEN len)
{
    U8 u = *s;
    STRLEN slen;
    UV uv, ouv;

    PERL_ARGS_ASSERT_IS_UTF8_CHAR_SLOW;

    if (UTF8_IS_INVARIANT(u))
	return 1;

    if (!UTF8_IS_START(u))
	return 0;

    if (len < 2 || !UTF8_IS_CONTINUATION(s[1]))
	return 0;

    slen = len - 1;
    s++;
#ifdef EBCDIC
    u = NATIVE_TO_UTF(u);
#endif
    u &= UTF_START_MASK(len);
    uv  = u;
    ouv = uv;
    while (slen--) {
	if (!UTF8_IS_CONTINUATION(*s))
	    return 0;
	uv = UTF8_ACCUMULATE(uv, *s);
	if (uv < ouv) 
	    return 0;
	ouv = uv;
	s++;
    }

    if ((STRLEN)UNISKIP(uv) < len)
	return 0;

    return len;
}

/*
=for apidoc A|STRLEN|is_utf8_char|const U8 *s

Tests if some arbitrary number of bytes begins in a valid UTF-8
character.  Note that an INVARIANT (i.e. ASCII) character is a valid
UTF-8 character.  The actual number of bytes in the UTF-8 character
will be returned if it is valid, otherwise 0.

=cut */
STRLEN
Perl_is_utf8_char(pTHX_ const U8 *s)
{
    const STRLEN len = UTF8SKIP(s);

    PERL_ARGS_ASSERT_IS_UTF8_CHAR;
    PERL_UNUSED_CONTEXT;
#ifdef IS_UTF8_CHAR
    if (IS_UTF8_CHAR_FAST(len))
        return IS_UTF8_CHAR(s, len) ? len : 0;
#endif /* #ifdef IS_UTF8_CHAR */
    return is_utf8_char_slow(s, len);
}

/*
=for apidoc A|bool|is_utf8_string|const U8 *s|STRLEN len

Returns true if first C<len> bytes of the given string form a valid
UTF-8 string, false otherwise.  Note that 'a valid UTF-8 string' does
not mean 'a string that contains code points above 0x7F encoded in UTF-8'
because a valid ASCII string is a valid UTF-8 string.

See also is_utf8_string_loclen() and is_utf8_string_loc().

=cut
*/

bool
Perl_is_utf8_string(pTHX_ const U8 *s, STRLEN len)
{
    const U8* const send = s + (len ? len : strlen((const char *)s));
    const U8* x = s;

    PERL_ARGS_ASSERT_IS_UTF8_STRING;
    PERL_UNUSED_CONTEXT;

    while (x < send) {
	STRLEN c;
	 /* Inline the easy bits of is_utf8_char() here for speed... */
	 if (UTF8_IS_INVARIANT(*x))
	      c = 1;
	 else if (!UTF8_IS_START(*x))
	     goto out;
	 else {
	      /* ... and call is_utf8_char() only if really needed. */
#ifdef IS_UTF8_CHAR
	     c = UTF8SKIP(x);
	     if (IS_UTF8_CHAR_FAST(c)) {
	         if (!IS_UTF8_CHAR(x, c))
		     c = 0;
	     }
	     else
		c = is_utf8_char_slow(x, c);
#else
	     c = is_utf8_char(x);
#endif /* #ifdef IS_UTF8_CHAR */
	      if (!c)
		  goto out;
	 }
        x += c;
    }

 out:
    if (x != send)
	return FALSE;

    return TRUE;
}

/*
Implemented as a macro in utf8.h

=for apidoc A|bool|is_utf8_string_loc|const U8 *s|STRLEN len|const U8 **ep

Like is_utf8_string() but stores the location of the failure (in the
case of "utf8ness failure") or the location s+len (in the case of
"utf8ness success") in the C<ep>.

See also is_utf8_string_loclen() and is_utf8_string().

=for apidoc A|bool|is_utf8_string_loclen|const U8 *s|STRLEN len|const U8 **ep|const STRLEN *el

Like is_utf8_string() but stores the location of the failure (in the
case of "utf8ness failure") or the location s+len (in the case of
"utf8ness success") in the C<ep>, and the number of UTF-8
encoded characters in the C<el>.

See also is_utf8_string_loc() and is_utf8_string().

=cut
*/

bool
Perl_is_utf8_string_loclen(pTHX_ const U8 *s, STRLEN len, const U8 **ep, STRLEN *el)
{
    const U8* const send = s + (len ? len : strlen((const char *)s));
    const U8* x = s;
    STRLEN c;
    STRLEN outlen = 0;

    PERL_ARGS_ASSERT_IS_UTF8_STRING_LOCLEN;
    PERL_UNUSED_CONTEXT;

    while (x < send) {
	 /* Inline the easy bits of is_utf8_char() here for speed... */
	 if (UTF8_IS_INVARIANT(*x))
	     c = 1;
	 else if (!UTF8_IS_START(*x))
	     goto out;
	 else {
	     /* ... and call is_utf8_char() only if really needed. */
#ifdef IS_UTF8_CHAR
	     c = UTF8SKIP(x);
	     if (IS_UTF8_CHAR_FAST(c)) {
	         if (!IS_UTF8_CHAR(x, c))
		     c = 0;
	     } else
	         c = is_utf8_char_slow(x, c);
#else
	     c = is_utf8_char(x);
#endif /* #ifdef IS_UTF8_CHAR */
	     if (!c)
	         goto out;
	 }
         x += c;
	 outlen++;
    }

 out:
    if (el)
        *el = outlen;

    if (ep)
        *ep = x;
    return (x == send);
}

/*

=for apidoc A|UV|utf8n_to_uvuni|const U8 *s|STRLEN curlen|STRLEN *retlen|U32 flags

Bottom level UTF-8 decode routine.
Returns the Unicode code point value of the first character in the string C<s>
which is assumed to be in UTF-8 encoding and no longer than C<curlen>;
C<retlen> will be set to the length, in bytes, of that character.

If C<s> does not point to a well-formed UTF-8 character, the behaviour
is dependent on the value of C<flags>: if it contains UTF8_CHECK_ONLY,
it is assumed that the caller will raise a warning, and this function
will silently just set C<retlen> to C<-1> and return zero.  If the
C<flags> does not contain UTF8_CHECK_ONLY, warnings about
malformations will be given, C<retlen> will be set to the expected
length of the UTF-8 character in bytes, and zero will be returned.

The C<flags> can also contain various flags to allow deviations from
the strict UTF-8 encoding (see F<utf8.h>).

Most code should use utf8_to_uvchr() rather than call this directly.

=cut
*/

UV
Perl_utf8n_to_uvuni(pTHX_ const U8 *s, STRLEN curlen, STRLEN *retlen, U32 flags)
{
    dVAR;
    const U8 * const s0 = s;
    UV uv = *s, ouv = 0;
    STRLEN len = 1;
    const bool dowarn = ckWARN_d(WARN_UTF8);
    const UV startbyte = *s;
    STRLEN expectlen = 0;
    U32 warning = 0;

    PERL_ARGS_ASSERT_UTF8N_TO_UVUNI;

/* This list is a superset of the UTF8_ALLOW_XXX. */

#define UTF8_WARN_EMPTY				 1
#define UTF8_WARN_CONTINUATION			 2
#define UTF8_WARN_NON_CONTINUATION	 	 3
#define UTF8_WARN_FE_FF				 4
#define UTF8_WARN_SHORT				 5
#define UTF8_WARN_OVERFLOW			 6
#define UTF8_WARN_SURROGATE			 7
#define UTF8_WARN_LONG				 8
#define UTF8_WARN_FFFF				 9 /* Also FFFE. */

    if (curlen == 0 &&
	!(flags & UTF8_ALLOW_EMPTY)) {
	warning = UTF8_WARN_EMPTY;
	goto malformed;
    }

    if (UTF8_IS_INVARIANT(uv)) {
	if (retlen)
	    *retlen = 1;
	return (UV) (NATIVE_TO_UTF(*s));
    }

    if (UTF8_IS_CONTINUATION(uv) &&
	!(flags & UTF8_ALLOW_CONTINUATION)) {
	warning = UTF8_WARN_CONTINUATION;
	goto malformed;
    }

    if (UTF8_IS_START(uv) && curlen > 1 && !UTF8_IS_CONTINUATION(s[1]) &&
	!(flags & UTF8_ALLOW_NON_CONTINUATION)) {
	warning = UTF8_WARN_NON_CONTINUATION;
	goto malformed;
    }

#ifdef EBCDIC
    uv = NATIVE_TO_UTF(uv);
#else
    if ((uv == 0xfe || uv == 0xff) &&
	!(flags & UTF8_ALLOW_FE_FF)) {
	warning = UTF8_WARN_FE_FF;
	goto malformed;
    }
#endif

    if      (!(uv & 0x20))	{ len =  2; uv &= 0x1f; }
    else if (!(uv & 0x10))	{ len =  3; uv &= 0x0f; }
    else if (!(uv & 0x08))	{ len =  4; uv &= 0x07; }
    else if (!(uv & 0x04))	{ len =  5; uv &= 0x03; }
#ifdef EBCDIC
    else if (!(uv & 0x02))	{ len =  6; uv &= 0x01; }
    else			{ len =  7; uv &= 0x01; }
#else
    else if (!(uv & 0x02))	{ len =  6; uv &= 0x01; }
    else if (!(uv & 0x01))	{ len =  7; uv = 0; }
    else			{ len = 13; uv = 0; } /* whoa! */
#endif

    if (retlen)
	*retlen = len;

    expectlen = len;

    if ((curlen < expectlen) &&
	!(flags & UTF8_ALLOW_SHORT)) {
	warning = UTF8_WARN_SHORT;
	goto malformed;
    }

    len--;
    s++;
    ouv = uv;

    while (len--) {
	if (!UTF8_IS_CONTINUATION(*s) &&
	    !(flags & UTF8_ALLOW_NON_CONTINUATION)) {
	    s--;
	    warning = UTF8_WARN_NON_CONTINUATION;
	    goto malformed;
	}
	else
	    uv = UTF8_ACCUMULATE(uv, *s);
	if (!(uv > ouv)) {
	    /* These cannot be allowed. */
	    if (uv == ouv) {
		if (expectlen != 13 && !(flags & UTF8_ALLOW_LONG)) {
		    warning = UTF8_WARN_LONG;
		    goto malformed;
		}
	    }
	    else { /* uv < ouv */
		/* This cannot be allowed. */
		warning = UTF8_WARN_OVERFLOW;
		goto malformed;
	    }
	}
	s++;
	ouv = uv;
    }

    if (UNICODE_IS_SURROGATE(uv) &&
	!(flags & UTF8_ALLOW_SURROGATE)) {
	warning = UTF8_WARN_SURROGATE;
	goto malformed;
    } else if ((expectlen > (STRLEN)UNISKIP(uv)) &&
	       !(flags & UTF8_ALLOW_LONG)) {
	warning = UTF8_WARN_LONG;
	goto malformed;
    } else if (UNICODE_IS_ILLEGAL(uv) &&
	       !(flags & UTF8_ALLOW_FFFF)) {
	warning = UTF8_WARN_FFFF;
	goto malformed;
    }

    return uv;

malformed:

    if (flags & UTF8_CHECK_ONLY) {
	if (retlen)
	    *retlen = ((STRLEN) -1);
	return 0;
    }

    if (dowarn) {
	SV* const sv = newSVpvs_flags("Malformed UTF-8 character ", SVs_TEMP);

	switch (warning) {
	case 0: /* Intentionally empty. */ break;
	case UTF8_WARN_EMPTY:
	    sv_catpvs(sv, "(empty string)");
	    break;
	case UTF8_WARN_CONTINUATION:
	    Perl_sv_catpvf(aTHX_ sv, "(unexpected continuation byte 0x%02"UVxf", with no preceding start byte)", uv);
	    break;
	case UTF8_WARN_NON_CONTINUATION:
	    if (s == s0)
	        Perl_sv_catpvf(aTHX_ sv, "(unexpected non-continuation byte 0x%02"UVxf", immediately after start byte 0x%02"UVxf")",
                           (UV)s[1], startbyte);
	    else {
		const int len = (int)(s-s0);
	        Perl_sv_catpvf(aTHX_ sv, "(unexpected non-continuation byte 0x%02"UVxf", %d byte%s after start byte 0x%02"UVxf", expected %d bytes)",
                           (UV)s[1], len, len > 1 ? "s" : "", startbyte, (int)expectlen);
	    }

	    break;
	case UTF8_WARN_FE_FF:
	    Perl_sv_catpvf(aTHX_ sv, "(byte 0x%02"UVxf")", uv);
	    break;
	case UTF8_WARN_SHORT:
	    Perl_sv_catpvf(aTHX_ sv, "(%d byte%s, need %d, after start byte 0x%02"UVxf")",
                           (int)curlen, curlen == 1 ? "" : "s", (int)expectlen, startbyte);
	    expectlen = curlen;		/* distance for caller to skip */
	    break;
	case UTF8_WARN_OVERFLOW:
	    Perl_sv_catpvf(aTHX_ sv, "(overflow at 0x%"UVxf", byte 0x%02x, after start byte 0x%02"UVxf")",
                           ouv, *s, startbyte);
	    break;
	case UTF8_WARN_SURROGATE:
	    Perl_sv_catpvf(aTHX_ sv, "(UTF-16 surrogate 0x%04"UVxf")", uv);
	    break;
	case UTF8_WARN_LONG:
	    Perl_sv_catpvf(aTHX_ sv, "(%d byte%s, need %d, after start byte 0x%02"UVxf")",
			   (int)expectlen, expectlen == 1 ? "": "s", UNISKIP(uv), startbyte);
	    break;
	case UTF8_WARN_FFFF:
	    Perl_sv_catpvf(aTHX_ sv, "(character 0x%04"UVxf")", uv);
	    break;
	default:
	    sv_catpvs(sv, "(unknown reason)");
	    break;
	}
	
	if (warning) {
	    const char * const s = SvPVX_const(sv);

	    if (PL_op)
		Perl_warner(aTHX_ packWARN(WARN_UTF8),
			    "%s in %s", s,  OP_DESC(PL_op));
	    else
		Perl_warner(aTHX_ packWARN(WARN_UTF8), "%s", s);
	}
    }

    if (retlen)
	*retlen = expectlen ? expectlen : len;

    return 0;
}

/*
=for apidoc A|UV|utf8_to_uvchr|const U8 *s|STRLEN *retlen

Returns the native character value of the first character in the string C<s>
which is assumed to be in UTF-8 encoding; C<retlen> will be set to the
length, in bytes, of that character.

If C<s> does not point to a well-formed UTF-8 character, zero is
returned and retlen is set, if possible, to -1.

=cut
*/

UV
Perl_utf8_to_uvchr(pTHX_ const U8 *s, STRLEN *retlen)
{
    PERL_ARGS_ASSERT_UTF8_TO_UVCHR;

    return utf8n_to_uvchr(s, UTF8_MAXBYTES, retlen,
			  ckWARN(WARN_UTF8) ? 0 : UTF8_ALLOW_ANY);
}

/*
=for apidoc A|UV|utf8_to_uvuni|const U8 *s|STRLEN *retlen

Returns the Unicode code point of the first character in the string C<s>
which is assumed to be in UTF-8 encoding; C<retlen> will be set to the
length, in bytes, of that character.

This function should only be used when returned UV is considered
an index into the Unicode semantic tables (e.g. swashes).

If C<s> does not point to a well-formed UTF-8 character, zero is
returned and retlen is set, if possible, to -1.

=cut
*/

UV
Perl_utf8_to_uvuni(pTHX_ const U8 *s, STRLEN *retlen)
{
    PERL_ARGS_ASSERT_UTF8_TO_UVUNI;

    /* Call the low level routine asking for checks */
    return Perl_utf8n_to_uvuni(aTHX_ s, UTF8_MAXBYTES, retlen,
			       ckWARN(WARN_UTF8) ? 0 : UTF8_ALLOW_ANY);
}

/*
=for apidoc A|STRLEN|utf8_length|const U8 *s|const U8 *e

Return the length of the UTF-8 char encoded string C<s> in characters.
Stops at C<e> (inclusive).  If C<e E<lt> s> or if the scan would end
up past C<e>, croaks.

=cut
*/

STRLEN
Perl_utf8_length(pTHX_ const U8 *s, const U8 *e)
{
    dVAR;
    STRLEN len = 0;
    U8 t = 0;

    PERL_ARGS_ASSERT_UTF8_LENGTH;

    /* Note: cannot use UTF8_IS_...() too eagerly here since e.g.
     * the bitops (especially ~) can create illegal UTF-8.
     * In other words: in Perl UTF-8 is not just for Unicode. */

    if (e < s)
	goto warn_and_return;
    while (s < e) {
	t = UTF8SKIP(s);
	if (e - s < t) {
	    warn_and_return:
	    if (ckWARN_d(WARN_UTF8)) {
	        if (PL_op)
		    Perl_warner(aTHX_ packWARN(WARN_UTF8),
			    "%s in %s", unees, OP_DESC(PL_op));
		else
		    Perl_warner(aTHX_ packWARN(WARN_UTF8), unees);
	    }
	    return len;
	}
	s += t;
	len++;
    }

    return len;
}

/*
=for apidoc A|IV|utf8_distance|const U8 *a|const U8 *b

Returns the number of UTF-8 characters between the UTF-8 pointers C<a>
and C<b>.

WARNING: use only if you *know* that the pointers point inside the
same UTF-8 buffer.

=cut
*/

IV
Perl_utf8_distance(pTHX_ const U8 *a, const U8 *b)
{
    PERL_ARGS_ASSERT_UTF8_DISTANCE;

    return (a < b) ? -1 * (IV) utf8_length(a, b) : (IV) utf8_length(b, a);
}

/*
=for apidoc A|U8 *|utf8_hop|U8 *s|I32 off

Return the UTF-8 pointer C<s> displaced by C<off> characters, either
forward or backward.

WARNING: do not use the following unless you *know* C<off> is within
the UTF-8 data pointed to by C<s> *and* that on entry C<s> is aligned
on the first byte of character or just after the last byte of a character.

=cut
*/

U8 *
Perl_utf8_hop(pTHX_ const U8 *s, I32 off)
{
    PERL_ARGS_ASSERT_UTF8_HOP;

    PERL_UNUSED_CONTEXT;
    /* Note: cannot use UTF8_IS_...() too eagerly here since e.g
     * the bitops (especially ~) can create illegal UTF-8.
     * In other words: in Perl UTF-8 is not just for Unicode. */

    if (off >= 0) {
	while (off--)
	    s += UTF8SKIP(s);
    }
    else {
	while (off++) {
	    s--;
	    while (UTF8_IS_CONTINUATION(*s))
		s--;
	}
    }
    return (U8 *)s;
}

/*
=for apidoc A|U8 *|utf8_to_bytes|U8 *s|STRLEN *len

Converts a string C<s> of length C<len> from UTF-8 into byte encoding.
Unlike C<bytes_to_utf8>, this over-writes the original string, and
updates len to contain the new length.
Returns zero on failure, setting C<len> to -1.

If you need a copy of the string, see C<bytes_from_utf8>.

=cut
*/

U8 *
Perl_utf8_to_bytes(pTHX_ U8 *s, STRLEN *len)
{
    U8 * const save = s;
    U8 * const send = s + *len;
    U8 *d;

    PERL_ARGS_ASSERT_UTF8_TO_BYTES;

    /* ensure valid UTF-8 and chars < 256 before updating string */
    while (s < send) {
        U8 c = *s++;

        if (!UTF8_IS_INVARIANT(c) &&
            (!UTF8_IS_DOWNGRADEABLE_START(c) || (s >= send)
	     || !(c = *s++) || !UTF8_IS_CONTINUATION(c))) {
            *len = ((STRLEN) -1);
            return 0;
        }
    }

    d = s = save;
    while (s < send) {
        STRLEN ulen;
        *d++ = (U8)utf8_to_uvchr(s, &ulen);
        s += ulen;
    }
    *d = '\0';
    *len = d - save;
    return save;
}

/*
=for apidoc A|U8 *|bytes_from_utf8|const U8 *s|STRLEN *len|bool *is_utf8

Converts a string C<s> of length C<len> from UTF-8 into byte encoding.
Unlike C<utf8_to_bytes> but like C<bytes_to_utf8>, returns a pointer to
the newly-created string, and updates C<len> to contain the new
length.  Returns the original string if no conversion occurs, C<len>
is unchanged. Do nothing if C<is_utf8> points to 0. Sets C<is_utf8> to
0 if C<s> is converted or contains all 7bit characters.

=cut
*/

U8 *
Perl_bytes_from_utf8(pTHX_ const U8 *s, STRLEN *len, bool *is_utf8)
{
    U8 *d;
    const U8 *start = s;
    const U8 *send;
    I32 count = 0;

    PERL_ARGS_ASSERT_BYTES_FROM_UTF8;

    PERL_UNUSED_CONTEXT;
    if (!*is_utf8)
        return (U8 *)start;

    /* ensure valid UTF-8 and chars < 256 before converting string */
    for (send = s + *len; s < send;) {
        U8 c = *s++;
	if (!UTF8_IS_INVARIANT(c)) {
	    if (UTF8_IS_DOWNGRADEABLE_START(c) && s < send &&
                (c = *s++) && UTF8_IS_CONTINUATION(c))
		count++;
	    else
                return (U8 *)start;
	}
    }

    *is_utf8 = FALSE;

    Newx(d, (*len) - count + 1, U8);
    s = start; start = d;
    while (s < send) {
	U8 c = *s++;
	if (!UTF8_IS_INVARIANT(c)) {
	    /* Then it is two-byte encoded */
	    c = UTF8_ACCUMULATE(NATIVE_TO_UTF(c), *s++);
	    c = ASCII_TO_NATIVE(c);
	}
	*d++ = c;
    }
    *d = '\0';
    *len = d - start;
    return (U8 *)start;
}

/*
=for apidoc A|U8 *|bytes_to_utf8|const U8 *s|STRLEN *len

Converts a string C<s> of length C<len> from ASCII into UTF-8 encoding.
Returns a pointer to the newly-created string, and sets C<len> to
reflect the new length.

If you want to convert to UTF-8 from other encodings than ASCII,
see sv_recode_to_utf8().

=cut
*/

U8*
Perl_bytes_to_utf8(pTHX_ const U8 *s, STRLEN *len)
{
    const U8 * const send = s + (*len);
    U8 *d;
    U8 *dst;

    PERL_ARGS_ASSERT_BYTES_TO_UTF8;
    PERL_UNUSED_CONTEXT;

    Newx(d, (*len) * 2 + 1, U8);
    dst = d;

    while (s < send) {
        const UV uv = NATIVE_TO_ASCII(*s++);
        if (UNI_IS_INVARIANT(uv))
            *d++ = (U8)UTF_TO_NATIVE(uv);
        else {
            *d++ = (U8)UTF8_EIGHT_BIT_HI(uv);
            *d++ = (U8)UTF8_EIGHT_BIT_LO(uv);
        }
    }
    *d = '\0';
    *len = d-dst;
    return dst;
}

/*
 * Convert native (big-endian) or reversed (little-endian) UTF-16 to UTF-8.
 *
 * Destination must be pre-extended to 3/2 source.  Do not use in-place.
 * We optimize for native, for obvious reasons. */

U8*
Perl_utf16_to_utf8(pTHX_ U8* p, U8* d, I32 bytelen, I32 *newlen)
{
    U8* pend;
    U8* dstart = d;

    PERL_ARGS_ASSERT_UTF16_TO_UTF8;

    if (bytelen == 1 && p[0] == 0) { /* Be understanding. */
	 d[0] = 0;
	 *newlen = 1;
	 return d;
    }

    if (bytelen & 1)
	Perl_croak(aTHX_ "panic: utf16_to_utf8: odd bytelen %"UVuf, (UV)bytelen);

    pend = p + bytelen;

    while (p < pend) {
	UV uv = (p[0] << 8) + p[1]; /* UTF-16BE */
	p += 2;
	if (uv < 0x80) {
#ifdef EBCDIC
	    *d++ = UNI_TO_NATIVE(uv);
#else
	    *d++ = (U8)uv;
#endif
	    continue;
	}
	if (uv < 0x800) {
	    *d++ = (U8)(( uv >>  6)         | 0xc0);
	    *d++ = (U8)(( uv        & 0x3f) | 0x80);
	    continue;
	}
	if (uv >= 0xd800 && uv < 0xdbff) {	/* surrogates */
	    UV low = (p[0] << 8) + p[1];
	    p += 2;
	    if (low < 0xdc00 || low >= 0xdfff)
		Perl_croak(aTHX_ "Malformed UTF-16 surrogate");
	    uv = ((uv - 0xd800) << 10) + (low - 0xdc00) + 0x10000;
	}
	if (uv < 0x10000) {
	    *d++ = (U8)(( uv >> 12)         | 0xe0);
	    *d++ = (U8)(((uv >>  6) & 0x3f) | 0x80);
	    *d++ = (U8)(( uv        & 0x3f) | 0x80);
	    continue;
	}
	else {
	    *d++ = (U8)(( uv >> 18)         | 0xf0);
	    *d++ = (U8)(((uv >> 12) & 0x3f) | 0x80);
	    *d++ = (U8)(((uv >>  6) & 0x3f) | 0x80);
	    *d++ = (U8)(( uv        & 0x3f) | 0x80);
	    continue;
	}
    }
    *newlen = d - dstart;
    return d;
}

/* Note: this one is slightly destructive of the source. */

U8*
Perl_utf16_to_utf8_reversed(pTHX_ U8* p, U8* d, I32 bytelen, I32 *newlen)
{
    U8* s = (U8*)p;
    U8* const send = s + bytelen;

    PERL_ARGS_ASSERT_UTF16_TO_UTF8_REVERSED;

    while (s < send) {
	const U8 tmp = s[0];
	s[0] = s[1];
	s[1] = tmp;
	s += 2;
    }
    return utf16_to_utf8(p, d, bytelen, newlen);
}

/* for now these are all defined (inefficiently) in terms of the utf8 versions */

bool
Perl_is_uni_alnum(pTHX_ UV c)
{
    U8 tmpbuf[UTF8_MAXBYTES+1];
    uvchr_to_utf8(tmpbuf, c);
    return is_utf8_alnum(tmpbuf);
}

bool
Perl_is_uni_alnumc(pTHX_ UV c)
{
    U8 tmpbuf[UTF8_MAXBYTES+1];
    uvchr_to_utf8(tmpbuf, c);
    return is_utf8_alnumc(tmpbuf);
}

bool
Perl_is_uni_idfirst(pTHX_ UV c)
{
    U8 tmpbuf[UTF8_MAXBYTES+1];
    uvchr_to_utf8(tmpbuf, c);
    return is_utf8_idfirst(tmpbuf);
}

bool
Perl_is_uni_alpha(pTHX_ UV c)
{
    U8 tmpbuf[UTF8_MAXBYTES+1];
    uvchr_to_utf8(tmpbuf, c);
    return is_utf8_alpha(tmpbuf);
}

bool
Perl_is_uni_ascii(pTHX_ UV c)
{
    U8 tmpbuf[UTF8_MAXBYTES+1];
    uvchr_to_utf8(tmpbuf, c);
    return is_utf8_ascii(tmpbuf);
}

bool
Perl_is_uni_space(pTHX_ UV c)
{
    U8 tmpbuf[UTF8_MAXBYTES+1];
    uvchr_to_utf8(tmpbuf, c);
    return is_utf8_space(tmpbuf);
}

bool
Perl_is_uni_digit(pTHX_ UV c)
{
    U8 tmpbuf[UTF8_MAXBYTES+1];
    uvchr_to_utf8(tmpbuf, c);
    return is_utf8_digit(tmpbuf);
}

bool
Perl_is_uni_upper(pTHX_ UV c)
{
    U8 tmpbuf[UTF8_MAXBYTES+1];
    uvchr_to_utf8(tmpbuf, c);
    return is_utf8_upper(tmpbuf);
}

bool
Perl_is_uni_lower(pTHX_ UV c)
{
    U8 tmpbuf[UTF8_MAXBYTES+1];
    uvchr_to_utf8(tmpbuf, c);
    return is_utf8_lower(tmpbuf);
}

bool
Perl_is_uni_cntrl(pTHX_ UV c)
{
    U8 tmpbuf[UTF8_MAXBYTES+1];
    uvchr_to_utf8(tmpbuf, c);
    return is_utf8_cntrl(tmpbuf);
}

bool
Perl_is_uni_graph(pTHX_ UV c)
{
    U8 tmpbuf[UTF8_MAXBYTES+1];
    uvchr_to_utf8(tmpbuf, c);
    return is_utf8_graph(tmpbuf);
}

bool
Perl_is_uni_print(pTHX_ UV c)
{
    U8 tmpbuf[UTF8_MAXBYTES+1];
    uvchr_to_utf8(tmpbuf, c);
    return is_utf8_print(tmpbuf);
}

bool
Perl_is_uni_punct(pTHX_ UV c)
{
    U8 tmpbuf[UTF8_MAXBYTES+1];
    uvchr_to_utf8(tmpbuf, c);
    return is_utf8_punct(tmpbuf);
}

bool
Perl_is_uni_xdigit(pTHX_ UV c)
{
    U8 tmpbuf[UTF8_MAXBYTES_CASE+1];
    uvchr_to_utf8(tmpbuf, c);
    return is_utf8_xdigit(tmpbuf);
}

UV
Perl_to_uni_upper(pTHX_ UV c, U8* p, STRLEN *lenp)
{
    PERL_ARGS_ASSERT_TO_UNI_UPPER;

    uvchr_to_utf8(p, c);
    return to_utf8_upper(p, p, lenp);
}

UV
Perl_to_uni_title(pTHX_ UV c, U8* p, STRLEN *lenp)
{
    PERL_ARGS_ASSERT_TO_UNI_TITLE;

    uvchr_to_utf8(p, c);
    return to_utf8_title(p, p, lenp);
}

UV
Perl_to_uni_lower(pTHX_ UV c, U8* p, STRLEN *lenp)
{
    PERL_ARGS_ASSERT_TO_UNI_LOWER;

    uvchr_to_utf8(p, c);
    return to_utf8_lower(p, p, lenp);
}

UV
Perl_to_uni_fold(pTHX_ UV c, U8* p, STRLEN *lenp)
{
    PERL_ARGS_ASSERT_TO_UNI_FOLD;

    uvchr_to_utf8(p, c);
    return to_utf8_fold(p, p, lenp);
}

/* for now these all assume no locale info available for Unicode > 255 */

bool
Perl_is_uni_alnum_lc(pTHX_ UV c)
{
    return is_uni_alnum(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_alnumc_lc(pTHX_ UV c)
{
    return is_uni_alnumc(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_idfirst_lc(pTHX_ UV c)
{
    return is_uni_idfirst(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_alpha_lc(pTHX_ UV c)
{
    return is_uni_alpha(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_ascii_lc(pTHX_ UV c)
{
    return is_uni_ascii(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_space_lc(pTHX_ UV c)
{
    return is_uni_space(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_digit_lc(pTHX_ UV c)
{
    return is_uni_digit(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_upper_lc(pTHX_ UV c)
{
    return is_uni_upper(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_lower_lc(pTHX_ UV c)
{
    return is_uni_lower(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_cntrl_lc(pTHX_ UV c)
{
    return is_uni_cntrl(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_graph_lc(pTHX_ UV c)
{
    return is_uni_graph(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_print_lc(pTHX_ UV c)
{
    return is_uni_print(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_punct_lc(pTHX_ UV c)
{
    return is_uni_punct(c);	/* XXX no locale support yet */
}

bool
Perl_is_uni_xdigit_lc(pTHX_ UV c)
{
    return is_uni_xdigit(c);	/* XXX no locale support yet */
}

U32
Perl_to_uni_upper_lc(pTHX_ U32 c)
{
    /* XXX returns only the first character -- do not use XXX */
    /* XXX no locale support yet */
    STRLEN len;
    U8 tmpbuf[UTF8_MAXBYTES_CASE+1];
    return (U32)to_uni_upper(c, tmpbuf, &len);
}

U32
Perl_to_uni_title_lc(pTHX_ U32 c)
{
    /* XXX returns only the first character XXX -- do not use XXX */
    /* XXX no locale support yet */
    STRLEN len;
    U8 tmpbuf[UTF8_MAXBYTES_CASE+1];
    return (U32)to_uni_title(c, tmpbuf, &len);
}

U32
Perl_to_uni_lower_lc(pTHX_ U32 c)
{
    /* XXX returns only the first character -- do not use XXX */
    /* XXX no locale support yet */
    STRLEN len;
    U8 tmpbuf[UTF8_MAXBYTES_CASE+1];
    return (U32)to_uni_lower(c, tmpbuf, &len);
}

static bool
S_is_utf8_common(pTHX_ const U8 *const p, SV **swash,
		 const char *const swashname)
{
    dVAR;

    PERL_ARGS_ASSERT_IS_UTF8_COMMON;

    if (!is_utf8_char(p))
	return FALSE;
    if (!*swash)
	*swash = swash_init("utf8", swashname, &PL_sv_undef, 1, 0);
    return swash_fetch(*swash, p, TRUE) != 0;
}

bool
Perl_is_utf8_alnum(pTHX_ const U8 *p)
{
    dVAR;

    PERL_ARGS_ASSERT_IS_UTF8_ALNUM;

    /* NOTE: "IsWord", not "IsAlnum", since Alnum is a true
     * descendant of isalnum(3), in other words, it doesn't
     * contain the '_'. --jhi */
    return is_utf8_common(p, &PL_utf8_alnum, "IsWord");
}

bool
Perl_is_utf8_alnumc(pTHX_ const U8 *p)
{
    dVAR;

    PERL_ARGS_ASSERT_IS_UTF8_ALNUMC;

    return is_utf8_common(p, &PL_utf8_alnumc, "IsAlnumC");
}

bool
Perl_is_utf8_idfirst(pTHX_ const U8 *p) /* The naming is historical. */
{
    dVAR;

    PERL_ARGS_ASSERT_IS_UTF8_IDFIRST;

    if (*p == '_')
	return TRUE;
    /* is_utf8_idstart would be more logical. */
    return is_utf8_common(p, &PL_utf8_idstart, "IdStart");
}

bool
Perl_is_utf8_idcont(pTHX_ const U8 *p)
{
    dVAR;

    PERL_ARGS_ASSERT_IS_UTF8_IDCONT;

    if (*p == '_')
	return TRUE;
    return is_utf8_common(p, &PL_utf8_idcont, "IdContinue");
}

bool
Perl_is_utf8_alpha(pTHX_ const U8 *p)
{
    dVAR;

    PERL_ARGS_ASSERT_IS_UTF8_ALPHA;

    return is_utf8_common(p, &PL_utf8_alpha, "IsAlpha");
}

bool
Perl_is_utf8_ascii(pTHX_ const U8 *p)
{
    dVAR;

    PERL_ARGS_ASSERT_IS_UTF8_ASCII;

    return is_utf8_common(p, &PL_utf8_ascii, "IsAscii");
}

bool
Perl_is_utf8_space(pTHX_ const U8 *p)
{
    dVAR;

    PERL_ARGS_ASSERT_IS_UTF8_SPACE;

    return is_utf8_common(p, &PL_utf8_space, "IsSpacePerl");
}

bool
Perl_is_utf8_digit(pTHX_ const U8 *p)
{
    dVAR;

    PERL_ARGS_ASSERT_IS_UTF8_DIGIT;

    return is_utf8_common(p, &PL_utf8_digit, "IsDigit");
}

bool
Perl_is_utf8_upper(pTHX_ const U8 *p)
{
    dVAR;

    PERL_ARGS_ASSERT_IS_UTF8_UPPER;

    return is_utf8_common(p, &PL_utf8_upper, "IsUppercase");
}

bool
Perl_is_utf8_lower(pTHX_ const U8 *p)
{
    dVAR;

    PERL_ARGS_ASSERT_IS_UTF8_LOWER;

    return is_utf8_common(p, &PL_utf8_lower, "IsLowercase");
}

bool
Perl_is_utf8_cntrl(pTHX_ const U8 *p)
{
    dVAR;

    PERL_ARGS_ASSERT_IS_UTF8_CNTRL;

    return is_utf8_common(p, &PL_utf8_cntrl, "IsCntrl");
}

bool
Perl_is_utf8_graph(pTHX_ const U8 *p)
{
    dVAR;

    PERL_ARGS_ASSERT_IS_UTF8_GRAPH;

    return is_utf8_common(p, &PL_utf8_graph, "IsGraph");
}

bool
Perl_is_utf8_print(pTHX_ const U8 *p)
{
    dVAR;

    PERL_ARGS_ASSERT_IS_UTF8_PRINT;

    return is_utf8_common(p, &PL_utf8_print, "IsPrint");
}

bool
Perl_is_utf8_punct(pTHX_ const U8 *p)
{
    dVAR;

    PERL_ARGS_ASSERT_IS_UTF8_PUNCT;

    return is_utf8_common(p, &PL_utf8_punct, "IsPunct");
}

bool
Perl_is_utf8_xdigit(pTHX_ const U8 *p)
{
    dVAR;

    PERL_ARGS_ASSERT_IS_UTF8_XDIGIT;

    return is_utf8_common(p, &PL_utf8_xdigit, "Isxdigit");
}

bool
Perl_is_utf8_mark(pTHX_ const U8 *p)
{
    dVAR;

    PERL_ARGS_ASSERT_IS_UTF8_MARK;

    return is_utf8_common(p, &PL_utf8_mark, "IsM");
}

/*
=for apidoc A|UV|to_utf8_case|U8 *p|U8* ustrp|STRLEN *lenp|SV **swash|char *normal|char *special

The "p" contains the pointer to the UTF-8 string encoding
the character that is being converted.

The "ustrp" is a pointer to the character buffer to put the
conversion result to.  The "lenp" is a pointer to the length
of the result.

The "swashp" is a pointer to the swash to use.

Both the special and normal mappings are stored lib/unicore/To/Foo.pl,
and loaded by SWASHNEW, using lib/utf8_heavy.pl.  The special (usually,
but not always, a multicharacter mapping), is tried first.

The "special" is a string like "utf8::ToSpecLower", which means the
hash %utf8::ToSpecLower.  The access to the hash is through
Perl_to_utf8_case().

The "normal" is a string like "ToLower" which means the swash
%utf8::ToLower.

=cut */

UV
Perl_to_utf8_case(pTHX_ const U8 *p, U8* ustrp, STRLEN *lenp,
			SV **swashp, const char *normal, const char *special)
{
    dVAR;
    U8 tmpbuf[UTF8_MAXBYTES_CASE+1];
    STRLEN len = 0;
    const UV uv0 = utf8_to_uvchr(p, NULL);
    /* The NATIVE_TO_UNI() and UNI_TO_NATIVE() mappings
     * are necessary in EBCDIC, they are redundant no-ops
     * in ASCII-ish platforms, and hopefully optimized away. */
    const UV uv1 = NATIVE_TO_UNI(uv0);

    PERL_ARGS_ASSERT_TO_UTF8_CASE;

    uvuni_to_utf8(tmpbuf, uv1);

    if (!*swashp) /* load on-demand */
         *swashp = swash_init("utf8", normal, &PL_sv_undef, 4, 0);

    /* The 0xDF is the only special casing Unicode code point below 0x100. */
    if (special && (uv1 == 0xDF || uv1 > 0xFF)) {
         /* It might be "special" (sometimes, but not always,
	  * a multicharacter mapping) */
	 HV * const hv = get_hv(special, FALSE);
	 SV **svp;

	 if (hv &&
	     (svp = hv_fetch(hv, (const char*)tmpbuf, UNISKIP(uv1), FALSE)) &&
	     (*svp)) {
	     const char *s;

	      s = SvPV_const(*svp, len);
	      if (len == 1)
		   len = uvuni_to_utf8(ustrp, NATIVE_TO_UNI(*(U8*)s)) - ustrp;
	      else {
#ifdef EBCDIC
		   /* If we have EBCDIC we need to remap the characters
		    * since any characters in the low 256 are Unicode
		    * code points, not EBCDIC. */
		   U8 *t = (U8*)s, *tend = t + len, *d;
		
		   d = tmpbuf;
		   if (SvUTF8(*svp)) {
			STRLEN tlen = 0;
			
			while (t < tend) {
			     const UV c = utf8_to_uvchr(t, &tlen);
			     if (tlen > 0) {
				  d = uvchr_to_utf8(d, UNI_TO_NATIVE(c));
				  t += tlen;
			     }
			     else
				  break;
			}
		   }
		   else {
			while (t < tend) {
			     d = uvchr_to_utf8(d, UNI_TO_NATIVE(*t));
			     t++;
			}
		   }
		   len = d - tmpbuf;
		   Copy(tmpbuf, ustrp, len, U8);
#else
		   Copy(s, ustrp, len, U8);
#endif
	      }
	 }
    }

    if (!len && *swashp) {
	const UV uv2 = swash_fetch(*swashp, tmpbuf, TRUE);

	 if (uv2) {
	      /* It was "normal" (a single character mapping). */
	      const UV uv3 = UNI_TO_NATIVE(uv2);
	      len = uvchr_to_utf8(ustrp, uv3) - ustrp;
	 }
    }

    if (!len) /* Neither: just copy. */
	 len = uvchr_to_utf8(ustrp, uv0) - ustrp;

    if (lenp)
	 *lenp = len;

    return len ? utf8_to_uvchr(ustrp, 0) : 0;
}

/*
=for apidoc A|UV|to_utf8_upper|const U8 *p|U8 *ustrp|STRLEN *lenp

Convert the UTF-8 encoded character at p to its uppercase version and
store that in UTF-8 in ustrp and its length in bytes in lenp.  Note
that the ustrp needs to be at least UTF8_MAXBYTES_CASE+1 bytes since
the uppercase version may be longer than the original character.

The first character of the uppercased version is returned
(but note, as explained above, that there may be more.)

=cut */

UV
Perl_to_utf8_upper(pTHX_ const U8 *p, U8* ustrp, STRLEN *lenp)
{
    dVAR;

    PERL_ARGS_ASSERT_TO_UTF8_UPPER;

    return Perl_to_utf8_case(aTHX_ p, ustrp, lenp,
                             &PL_utf8_toupper, "ToUpper", "utf8::ToSpecUpper");
}

/*
=for apidoc A|UV|to_utf8_title|const U8 *p|U8 *ustrp|STRLEN *lenp

Convert the UTF-8 encoded character at p to its titlecase version and
store that in UTF-8 in ustrp and its length in bytes in lenp.  Note
that the ustrp needs to be at least UTF8_MAXBYTES_CASE+1 bytes since the
titlecase version may be longer than the original character.

The first character of the titlecased version is returned
(but note, as explained above, that there may be more.)

=cut */

UV
Perl_to_utf8_title(pTHX_ const U8 *p, U8* ustrp, STRLEN *lenp)
{
    dVAR;

    PERL_ARGS_ASSERT_TO_UTF8_TITLE;

    return Perl_to_utf8_case(aTHX_ p, ustrp, lenp,
                             &PL_utf8_totitle, "ToTitle", "utf8::ToSpecTitle");
}

/*
=for apidoc A|UV|to_utf8_lower|const U8 *p|U8 *ustrp|STRLEN *lenp

Convert the UTF-8 encoded character at p to its lowercase version and
store that in UTF-8 in ustrp and its length in bytes in lenp.  Note
that the ustrp needs to be at least UTF8_MAXBYTES_CASE+1 bytes since the
lowercase version may be longer than the original character.

The first character of the lowercased version is returned
(but note, as explained above, that there may be more.)

=cut */

UV
Perl_to_utf8_lower(pTHX_ const U8 *p, U8* ustrp, STRLEN *lenp)
{
    dVAR;

    PERL_ARGS_ASSERT_TO_UTF8_LOWER;

    return Perl_to_utf8_case(aTHX_ p, ustrp, lenp,
                             &PL_utf8_tolower, "ToLower", "utf8::ToSpecLower");
}

/*
=for apidoc A|UV|to_utf8_fold|const U8 *p|U8 *ustrp|STRLEN *lenp

Convert the UTF-8 encoded character at p to its foldcase version and
store that in UTF-8 in ustrp and its length in bytes in lenp.  Note
that the ustrp needs to be at least UTF8_MAXBYTES_CASE+1 bytes since the
foldcase version may be longer than the original character (up to
three characters).

The first character of the foldcased version is returned
(but note, as explained above, that there may be more.)

=cut */

UV
Perl_to_utf8_fold(pTHX_ const U8 *p, U8* ustrp, STRLEN *lenp)
{
    dVAR;

    PERL_ARGS_ASSERT_TO_UTF8_FOLD;

    return Perl_to_utf8_case(aTHX_ p, ustrp, lenp,
                             &PL_utf8_tofold, "ToFold", "utf8::ToSpecFold");
}

/* Note:
 * A "swash" is a swatch hash.
 * A "swatch" is a bit vector generated by utf8.c:S_swash_get().
 * C<pkg> is a pointer to a package name for SWASHNEW, should be "utf8".
 * For other parameters, see utf8::SWASHNEW in lib/utf8_heavy.pl.
 */
SV*
Perl_swash_init(pTHX_ const char* pkg, const char* name, SV *listsv, I32 minbits, I32 none)
{
    dVAR;
    SV* retval;
    dSP;
    const size_t pkg_len = strlen(pkg);
    const size_t name_len = strlen(name);
    HV * const stash = gv_stashpvn(pkg, pkg_len, 0);
    SV* errsv_save;

    PERL_ARGS_ASSERT_SWASH_INIT;

    PUSHSTACKi(PERLSI_MAGIC);
    ENTER;
    SAVEI32(PL_hints);
    PL_hints = 0;
    save_re_context();
    if (!gv_fetchmeth(stash, "SWASHNEW", 8, -1)) {	/* demand load utf8 */
	ENTER;
	errsv_save = newSVsv(ERRSV);
	/* It is assumed that callers of this routine are not passing in any
	   user derived data.  */
	/* Need to do this after save_re_context() as it will set PL_tainted to
	   1 while saving $1 etc (see the code after getrx: in Perl_magic_get).
	   Even line to create errsv_save can turn on PL_tainted.  */
	SAVEBOOL(PL_tainted);
	PL_tainted = 0;
	Perl_load_module(aTHX_ PERL_LOADMOD_NOIMPORT, newSVpvn(pkg,pkg_len),
			 NULL);
	if (!SvTRUE(ERRSV))
	    sv_setsv(ERRSV, errsv_save);
	SvREFCNT_dec(errsv_save);
	LEAVE;
    }
    SPAGAIN;
    PUSHMARK(SP);
    EXTEND(SP,5);
    mPUSHp(pkg, pkg_len);
    mPUSHp(name, name_len);
    PUSHs(listsv);
    mPUSHi(minbits);
    mPUSHi(none);
    PUTBACK;
    errsv_save = newSVsv(ERRSV);
    if (call_method("SWASHNEW", G_SCALAR))
	retval = newSVsv(*PL_stack_sp--);
    else
	retval = &PL_sv_undef;
    if (!SvTRUE(ERRSV))
	sv_setsv(ERRSV, errsv_save);
    SvREFCNT_dec(errsv_save);
    LEAVE;
    POPSTACK;
    if (IN_PERL_COMPILETIME) {
	CopHINTS_set(PL_curcop, PL_hints);
    }
    if (!SvROK(retval) || SvTYPE(SvRV(retval)) != SVt_PVHV) {
        if (SvPOK(retval))
	    Perl_croak(aTHX_ "Can't find Unicode property definition \"%"SVf"\"",
		       SVfARG(retval));
	Perl_croak(aTHX_ "SWASHNEW didn't return an HV ref");
    }
    return retval;
}


/* This API is wrong for special case conversions since we may need to
 * return several Unicode characters for a single Unicode character
 * (see lib/unicore/SpecCase.txt) The SWASHGET in lib/utf8_heavy.pl is
 * the lower-level routine, and it is similarly broken for returning
 * multiple values.  --jhi */
/* Now SWASHGET is recasted into S_swash_get in this file. */

/* Note:
 * Returns the value of property/mapping C<swash> for the first character
 * of the string C<ptr>. If C<do_utf8> is true, the string C<ptr> is
 * assumed to be in utf8. If C<do_utf8> is false, the string C<ptr> is
 * assumed to be in native 8-bit encoding. Caches the swatch in C<swash>.
 */
UV
Perl_swash_fetch(pTHX_ SV *swash, const U8 *ptr, bool do_utf8)
{
    dVAR;
    HV* const hv = (HV*)SvRV(swash);
    U32 klen;
    U32 off;
    STRLEN slen;
    STRLEN needents;
    const U8 *tmps = NULL;
    U32 bit;
    SV *swatch;
    U8 tmputf8[2];
    const UV c = NATIVE_TO_ASCII(*ptr);

    PERL_ARGS_ASSERT_SWASH_FETCH;

    if (!do_utf8 && !UNI_IS_INVARIANT(c)) {
	tmputf8[0] = (U8)UTF8_EIGHT_BIT_HI(c);
	tmputf8[1] = (U8)UTF8_EIGHT_BIT_LO(c);
	ptr = tmputf8;
    }
    /* Given a UTF-X encoded char 0xAA..0xYY,0xZZ
     * then the "swatch" is a vec() for al the chars which start
     * with 0xAA..0xYY
     * So the key in the hash (klen) is length of encoded char -1
     */
    klen = UTF8SKIP(ptr) - 1;
    off  = ptr[klen];

    if (klen == 0) {
      /* If char in invariant then swatch is for all the invariant chars
       * In both UTF-8 and UTF-8-MOD that happens to be UTF_CONTINUATION_MARK
       */
	needents = UTF_CONTINUATION_MARK;
	off      = NATIVE_TO_UTF(ptr[klen]);
    }
    else {
      /* If char is encoded then swatch is for the prefix */
	needents = (1 << UTF_ACCUMULATION_SHIFT);
	off      = NATIVE_TO_UTF(ptr[klen]) & UTF_CONTINUATION_MASK;
    }

    /*
     * This single-entry cache saves about 1/3 of the utf8 overhead in test
     * suite.  (That is, only 7-8% overall over just a hash cache.  Still,
     * it's nothing to sniff at.)  Pity we usually come through at least
     * two function calls to get here...
     *
     * NB: this code assumes that swatches are never modified, once generated!
     */

    if (hv   == PL_last_swash_hv &&
	klen == PL_last_swash_klen &&
	(!klen || memEQ((char *)ptr, (char *)PL_last_swash_key, klen)) )
    {
	tmps = PL_last_swash_tmps;
	slen = PL_last_swash_slen;
    }
    else {
	/* Try our second-level swatch cache, kept in a hash. */
	SV** svp = hv_fetch(hv, (const char*)ptr, klen, FALSE);

	/* If not cached, generate it via swash_get */
	if (!svp || !SvPOK(*svp)
		 || !(tmps = (const U8*)SvPV_const(*svp, slen))) {
	    /* We use utf8n_to_uvuni() as we want an index into
	       Unicode tables, not a native character number.
	     */
	    const UV code_point = utf8n_to_uvuni(ptr, UTF8_MAXBYTES, 0,
					   ckWARN(WARN_UTF8) ?
					   0 : UTF8_ALLOW_ANY);
	    swatch = swash_get(swash,
		    /* On EBCDIC & ~(0xA0-1) isn't a useful thing to do */
				(klen) ? (code_point & ~(needents - 1)) : 0,
				needents);

	    if (IN_PERL_COMPILETIME)
		CopHINTS_set(PL_curcop, PL_hints);

	    svp = hv_store(hv, (const char *)ptr, klen, swatch, 0);

	    if (!svp || !(tmps = (U8*)SvPV(*svp, slen))
		     || (slen << 3) < needents)
		Perl_croak(aTHX_ "panic: swash_fetch got improper swatch");
	}

	PL_last_swash_hv = hv;
	assert(klen <= sizeof(PL_last_swash_key));
	PL_last_swash_klen = (U8)klen;
	/* FIXME change interpvar.h?  */
	PL_last_swash_tmps = (U8 *) tmps;
	PL_last_swash_slen = slen;
	if (klen)
	    Copy(ptr, PL_last_swash_key, klen, U8);
    }

    switch ((int)((slen << 3) / needents)) {
    case 1:
	bit = 1 << (off & 7);
	off >>= 3;
	return (tmps[off] & bit) != 0;
    case 8:
	return tmps[off];
    case 16:
	off <<= 1;
	return (tmps[off] << 8) + tmps[off + 1] ;
    case 32:
	off <<= 2;
	return (tmps[off] << 24) + (tmps[off+1] << 16) + (tmps[off+2] << 8) + tmps[off + 3] ;
    }
    Perl_croak(aTHX_ "panic: swash_fetch got swatch of unexpected bit width");
    NORETURN_FUNCTION_END;
}

/* Note:
 * Returns a swatch (a bit vector string) for a code point sequence
 * that starts from the value C<start> and comprises the number C<span>.
 * A C<swash> must be an object created by SWASHNEW (see lib/utf8_heavy.pl).
 * Should be used via swash_fetch, which will cache the swatch in C<swash>.
 */
STATIC SV*
S_swash_get(pTHX_ SV* swash, UV start, UV span)
{
    SV *swatch;
    U8 *l, *lend, *x, *xend, *s;
    STRLEN lcur, xcur, scur;
    HV* const hv = (HV*)SvRV(swash);
    SV** const listsvp = hv_fetchs(hv, "LIST", FALSE);
    SV** const typesvp = hv_fetchs(hv, "TYPE", FALSE);
    SV** const bitssvp = hv_fetchs(hv, "BITS", FALSE);
    SV** const nonesvp = hv_fetchs(hv, "NONE", FALSE);
    SV** const extssvp = hv_fetchs(hv, "EXTRAS", FALSE);
    const U8* const typestr = (U8*)SvPV_nolen(*typesvp);
    const int  typeto  = typestr[0] == 'T' && typestr[1] == 'o';
    const STRLEN bits  = SvUV(*bitssvp);
    const STRLEN octets = bits >> 3; /* if bits == 1, then octets == 0 */
    const UV     none  = SvUV(*nonesvp);
    const UV     end   = start + span;

    PERL_ARGS_ASSERT_SWASH_GET;

    if (bits != 1 && bits != 8 && bits != 16 && bits != 32) {
	Perl_croak(aTHX_ "panic: swash_get doesn't expect bits %"UVuf,
						 (UV)bits);
    }

    /* create and initialize $swatch */
    scur   = octets ? (span * octets) : (span + 7) / 8;
    swatch = newSV(scur);
    SvPOK_on(swatch);
    s = (U8*)SvPVX(swatch);
    if (octets && none) {
	const U8* const e = s + scur;
	while (s < e) {
	    if (bits == 8)
		*s++ = (U8)(none & 0xff);
	    else if (bits == 16) {
		*s++ = (U8)((none >>  8) & 0xff);
		*s++ = (U8)( none        & 0xff);
	    }
	    else if (bits == 32) {
		*s++ = (U8)((none >> 24) & 0xff);
		*s++ = (U8)((none >> 16) & 0xff);
		*s++ = (U8)((none >>  8) & 0xff);
		*s++ = (U8)( none        & 0xff);
	    }
	}
	*s = '\0';
    }
    else {
	(void)memzero((U8*)s, scur + 1);
    }
    SvCUR_set(swatch, scur);
    s = (U8*)SvPVX(swatch);

    /* read $swash->{LIST} */
    l = (U8*)SvPV(*listsvp, lcur);
    lend = l + lcur;
    while (l < lend) {
	UV min, max, val;
	STRLEN numlen;
	I32 flags = PERL_SCAN_SILENT_ILLDIGIT | PERL_SCAN_DISALLOW_PREFIX;

	U8* const nl = (U8*)memchr(l, '\n', lend - l);

	numlen = lend - l;
	min = grok_hex((char *)l, &numlen, &flags, NULL);
	if (numlen)
	    l += numlen;
	else if (nl) {
	    l = nl + 1; /* 1 is length of "\n" */
	    continue;
	}
	else {
	    l = lend; /* to LIST's end at which \n is not found */
	    break;
	}

	if (isBLANK(*l)) {
	    ++l;
	    flags = PERL_SCAN_SILENT_ILLDIGIT | PERL_SCAN_DISALLOW_PREFIX;
	    numlen = lend - l;
	    max = grok_hex((char *)l, &numlen, &flags, NULL);
	    if (numlen)
		l += numlen;
	    else
		max = min;

	    if (octets) {
		if (isBLANK(*l)) {
		    ++l;
		    flags = PERL_SCAN_SILENT_ILLDIGIT |
			    PERL_SCAN_DISALLOW_PREFIX;
		    numlen = lend - l;
		    val = grok_hex((char *)l, &numlen, &flags, NULL);
		    if (numlen)
			l += numlen;
		    else
			val = 0;
		}
		else {
		    val = 0;
		    if (typeto) {
			Perl_croak(aTHX_ "%s: illegal mapping '%s'",
					 typestr, l);
		    }
		}
	    }
	    else
		val = 0; /* bits == 1, then val should be ignored */
	}
	else {
	    max = min;
	    if (octets) {
		val = 0;
		if (typeto) {
		    Perl_croak(aTHX_ "%s: illegal mapping '%s'", typestr, l);
		}
	    }
	    else
		val = 0; /* bits == 1, then val should be ignored */
	}

	if (nl)
	    l = nl + 1;
	else
	    l = lend;

	if (max < start)
	    continue;

	if (octets) {
	    UV key;
	    if (min < start) {
		if (!none || val < none) {
		    val += start - min;
		}
		min = start;
	    }
	    for (key = min; key <= max; key++) {
		STRLEN offset;
		if (key >= end)
		    goto go_out_list;
		/* offset must be non-negative (start <= min <= key < end) */
		offset = octets * (key - start);
		if (bits == 8)
		    s[offset] = (U8)(val & 0xff);
		else if (bits == 16) {
		    s[offset    ] = (U8)((val >>  8) & 0xff);
		    s[offset + 1] = (U8)( val        & 0xff);
		}
		else if (bits == 32) {
		    s[offset    ] = (U8)((val >> 24) & 0xff);
		    s[offset + 1] = (U8)((val >> 16) & 0xff);
		    s[offset + 2] = (U8)((val >>  8) & 0xff);
		    s[offset + 3] = (U8)( val        & 0xff);
		}

		if (!none || val < none)
		    ++val;
	    }
	}
	else { /* bits == 1, then val should be ignored */
	    UV key;
	    if (min < start)
		min = start;
	    for (key = min; key <= max; key++) {
		const STRLEN offset = (STRLEN)(key - start);
		if (key >= end)
		    goto go_out_list;
		s[offset >> 3] |= 1 << (offset & 7);
	    }
	}
    } /* while */
  go_out_list:

    /* read $swash->{EXTRAS} */
    x = (U8*)SvPV(*extssvp, xcur);
    xend = x + xcur;
    while (x < xend) {
	STRLEN namelen;
	U8 *namestr;
	SV** othersvp;
	HV* otherhv;
	STRLEN otherbits;
	SV **otherbitssvp, *other;
	U8 *s, *o, *nl;
	STRLEN slen, olen;

	const U8 opc = *x++;
	if (opc == '\n')
	    continue;

	nl = (U8*)memchr(x, '\n', xend - x);

	if (opc != '-' && opc != '+' && opc != '!' && opc != '&') {
	    if (nl) {
		x = nl + 1; /* 1 is length of "\n" */
		continue;
	    }
	    else {
		x = xend; /* to EXTRAS' end at which \n is not found */
		break;
	    }
	}

	namestr = x;
	if (nl) {
	    namelen = nl - namestr;
	    x = nl + 1;
	}
	else {
	    namelen = xend - namestr;
	    x = xend;
	}

	othersvp = hv_fetch(hv, (char *)namestr, namelen, FALSE);
	otherhv = (HV*)SvRV(*othersvp);
	otherbitssvp = hv_fetchs(otherhv, "BITS", FALSE);
	otherbits = (STRLEN)SvUV(*otherbitssvp);
	if (bits < otherbits)
	    Perl_croak(aTHX_ "panic: swash_get found swatch size mismatch");

	/* The "other" swatch must be destroyed after. */
	other = swash_get(*othersvp, start, span);
	o = (U8*)SvPV(other, olen);

	if (!olen)
	    Perl_croak(aTHX_ "panic: swash_get got improper swatch");

	s = (U8*)SvPV(swatch, slen);
	if (bits == 1 && otherbits == 1) {
	    if (slen != olen)
		Perl_croak(aTHX_ "panic: swash_get found swatch length mismatch");

	    switch (opc) {
	    case '+':
		while (slen--)
		    *s++ |= *o++;
		break;
	    case '!':
		while (slen--)
		    *s++ |= ~*o++;
		break;
	    case '-':
		while (slen--)
		    *s++ &= ~*o++;
		break;
	    case '&':
		while (slen--)
		    *s++ &= *o++;
		break;
	    default:
		break;
	    }
	}
	else {
	    STRLEN otheroctets = otherbits >> 3;
	    STRLEN offset = 0;
	    U8* const send = s + slen;

	    while (s < send) {
		UV otherval = 0;

		if (otherbits == 1) {
		    otherval = (o[offset >> 3] >> (offset & 7)) & 1;
		    ++offset;
		}
		else {
		    STRLEN vlen = otheroctets;
		    otherval = *o++;
		    while (--vlen) {
			otherval <<= 8;
			otherval |= *o++;
		    }
		}

		if (opc == '+' && otherval)
		    NOOP;   /* replace with otherval */
		else if (opc == '!' && !otherval)
		    otherval = 1;
		else if (opc == '-' && otherval)
		    otherval = 0;
		else if (opc == '&' && !otherval)
		    otherval = 0;
		else {
		    s += octets; /* no replacement */
		    continue;
		}

		if (bits == 8)
		    *s++ = (U8)( otherval & 0xff);
		else if (bits == 16) {
		    *s++ = (U8)((otherval >>  8) & 0xff);
		    *s++ = (U8)( otherval        & 0xff);
		}
		else if (bits == 32) {
		    *s++ = (U8)((otherval >> 24) & 0xff);
		    *s++ = (U8)((otherval >> 16) & 0xff);
		    *s++ = (U8)((otherval >>  8) & 0xff);
		    *s++ = (U8)( otherval        & 0xff);
		}
	    }
	}
	sv_free(other); /* through with it! */
    } /* while */
    return swatch;
}

/*
=for apidoc A|U8 *|uvchr_to_utf8|U8 *d|UV uv

Adds the UTF-8 representation of the Native codepoint C<uv> to the end
of the string C<d>; C<d> should be have at least C<UTF8_MAXBYTES+1> free
bytes available. The return value is the pointer to the byte after the
end of the new character. In other words,

    d = uvchr_to_utf8(d, uv);

is the recommended wide native character-aware way of saying

    *(d++) = uv;

=cut
*/

/* On ASCII machines this is normally a macro but we want a
   real function in case XS code wants it
*/
U8 *
Perl_uvchr_to_utf8(pTHX_ U8 *d, UV uv)
{
    PERL_ARGS_ASSERT_UVCHR_TO_UTF8;

    return Perl_uvuni_to_utf8_flags(aTHX_ d, NATIVE_TO_UNI(uv), 0);
}

U8 *
Perl_uvchr_to_utf8_flags(pTHX_ U8 *d, UV uv, UV flags)
{
    PERL_ARGS_ASSERT_UVCHR_TO_UTF8_FLAGS;

    return Perl_uvuni_to_utf8_flags(aTHX_ d, NATIVE_TO_UNI(uv), flags);
}

/*
=for apidoc A|UV|utf8n_to_uvchr|U8 *s|STRLEN curlen|STRLEN *retlen|U32 
flags

Returns the native character value of the first character in the string 
C<s>
which is assumed to be in UTF-8 encoding; C<retlen> will be set to the
length, in bytes, of that character.

Allows length and flags to be passed to low level routine.

=cut
*/
/* On ASCII machines this is normally a macro but we want
   a real function in case XS code wants it
*/
UV
Perl_utf8n_to_uvchr(pTHX_ const U8 *s, STRLEN curlen, STRLEN *retlen, 
U32 flags)
{
    const UV uv = Perl_utf8n_to_uvuni(aTHX_ s, curlen, retlen, flags);

    PERL_ARGS_ASSERT_UTF8N_TO_UVCHR;

    return UNI_TO_NATIVE(uv);
}

/*
=for apidoc A|char *|pv_uni_display|SV *dsv|U8 *spv|STRLEN len|STRLEN pvlim|UV flags

Build to the scalar dsv a displayable version of the string spv,
length len, the displayable version being at most pvlim bytes long
(if longer, the rest is truncated and "..." will be appended).

The flags argument can have UNI_DISPLAY_ISPRINT set to display
isPRINT()able characters as themselves, UNI_DISPLAY_BACKSLASH
to display the \\[nrfta\\] as the backslashed versions (like '\n')
(UNI_DISPLAY_BACKSLASH is preferred over UNI_DISPLAY_ISPRINT for \\).
UNI_DISPLAY_QQ (and its alias UNI_DISPLAY_REGEX) have both
UNI_DISPLAY_BACKSLASH and UNI_DISPLAY_ISPRINT turned on.

The pointer to the PV of the dsv is returned.

=cut */
char *
Perl_pv_uni_display(pTHX_ SV *dsv, const U8 *spv, STRLEN len, STRLEN pvlim, UV flags)
{
    int truncated = 0;
    const char *s, *e;

    PERL_ARGS_ASSERT_PV_UNI_DISPLAY;

    sv_setpvn(dsv, "", 0);
    SvUTF8_off(dsv);
    for (s = (const char *)spv, e = s + len; s < e; s += UTF8SKIP(s)) {
	 UV u;
	  /* This serves double duty as a flag and a character to print after
	     a \ when flags & UNI_DISPLAY_BACKSLASH is true.
	  */
	 char ok = 0;

	 if (pvlim && SvCUR(dsv) >= pvlim) {
	      truncated++;
	      break;
	 }
	 u = utf8_to_uvchr((U8*)s, 0);
	 if (u < 256) {
	     const unsigned char c = (unsigned char)u & 0xFF;
	     if (flags & UNI_DISPLAY_BACKSLASH) {
	         switch (c) {
		 case '\n':
		     ok = 'n'; break;
		 case '\r':
		     ok = 'r'; break;
		 case '\t':
		     ok = 't'; break;
		 case '\f':
		     ok = 'f'; break;
		 case '\a':
		     ok = 'a'; break;
		 case '\\':
		     ok = '\\'; break;
		 default: break;
		 }
		 if (ok) {
		     const char string = ok;
		     sv_catpvn(dsv, &string, 1);
		 }
	     }
	     /* isPRINT() is the locale-blind version. */
	     if (!ok && (flags & UNI_DISPLAY_ISPRINT) && isPRINT(c)) {
		 const char string = c;
		 sv_catpvn(dsv, &string, 1);
		 ok = 1;
	     }
	 }
	 if (!ok)
	     Perl_sv_catpvf(aTHX_ dsv, "\\x{%"UVxf"}", u);
    }
    if (truncated)
	 sv_catpvs(dsv, "...");
    
    return SvPVX(dsv);
}

/*
=for apidoc A|char *|sv_uni_display|SV *dsv|SV *ssv|STRLEN pvlim|UV flags

Build to the scalar dsv a displayable version of the scalar sv,
the displayable version being at most pvlim bytes long
(if longer, the rest is truncated and "..." will be appended).

The flags argument is as in pv_uni_display().

The pointer to the PV of the dsv is returned.

=cut
*/
char *
Perl_sv_uni_display(pTHX_ SV *dsv, SV *ssv, STRLEN pvlim, UV flags)
{
    PERL_ARGS_ASSERT_SV_UNI_DISPLAY;

     return Perl_pv_uni_display(aTHX_ dsv, (const U8*)SvPVX_const(ssv),
				SvCUR(ssv), pvlim, flags);
}

/*
=for apidoc A|I32|ibcmp_utf8|const char *s1|char **pe1|register UV l1|bool u1|const char *s2|char **pe2|register UV l2|bool u2

Return true if the strings s1 and s2 differ case-insensitively, false
if not (if they are equal case-insensitively).  If u1 is true, the
string s1 is assumed to be in UTF-8-encoded Unicode.  If u2 is true,
the string s2 is assumed to be in UTF-8-encoded Unicode.  If u1 or u2
are false, the respective string is assumed to be in native 8-bit
encoding.

If the pe1 and pe2 are non-NULL, the scanning pointers will be copied
in there (they will point at the beginning of the I<next> character).
If the pointers behind pe1 or pe2 are non-NULL, they are the end
pointers beyond which scanning will not continue under any
circumstances.  If the byte lengths l1 and l2 are non-zero, s1+l1 and
s2+l2 will be used as goal end pointers that will also stop the scan,
and which qualify towards defining a successful match: all the scans
that define an explicit length must reach their goal pointers for
a match to succeed).

For case-insensitiveness, the "casefolding" of Unicode is used
instead of upper/lowercasing both the characters, see
http://www.unicode.org/unicode/reports/tr21/ (Case Mappings).

=cut */
I32
Perl_ibcmp_utf8(pTHX_ const char *s1, char **pe1, register UV l1, bool u1, const char *s2, char **pe2, register UV l2, bool u2)
{
     dVAR;
     register const U8 *p1  = (const U8*)s1;
     register const U8 *p2  = (const U8*)s2;
     register const U8 *f1 = NULL;
     register const U8 *f2 = NULL;
     register U8 *e1 = NULL;
     register U8 *q1 = NULL;
     register U8 *e2 = NULL;
     register U8 *q2 = NULL;
     STRLEN n1 = 0, n2 = 0;
     U8 foldbuf1[UTF8_MAXBYTES_CASE+1];
     U8 foldbuf2[UTF8_MAXBYTES_CASE+1];
     U8 natbuf[1+1];
     STRLEN foldlen1, foldlen2;
     bool match;

     PERL_ARGS_ASSERT_IBCMP_UTF8;
     
     if (pe1)
	  e1 = *(U8**)pe1;
     /* assert(e1 || l1); */
     if (e1 == 0 || (l1 && l1 < (UV)(e1 - (const U8*)s1)))
	  f1 = (const U8*)s1 + l1;
     if (pe2)
	  e2 = *(U8**)pe2;
     /* assert(e2 || l2); */
     if (e2 == 0 || (l2 && l2 < (UV)(e2 - (const U8*)s2)))
	  f2 = (const U8*)s2 + l2;

     /* This shouldn't happen. However, putting an assert() there makes some
      * tests fail. */
     /* assert((e1 == 0 && f1 == 0) || (e2 == 0 && f2 == 0) || (f1 == 0 && f2 == 0)); */
     if ((e1 == 0 && f1 == 0) || (e2 == 0 && f2 == 0) || (f1 == 0 && f2 == 0))
	  return 1; /* mismatch; possible infinite loop or false positive */

     if (!u1 || !u2)
	  natbuf[1] = 0; /* Need to terminate the buffer. */

     while ((e1 == 0 || p1 < e1) &&
	    (f1 == 0 || p1 < f1) &&
	    (e2 == 0 || p2 < e2) &&
	    (f2 == 0 || p2 < f2)) {
	  if (n1 == 0) {
	       if (u1)
		    to_utf8_fold(p1, foldbuf1, &foldlen1);
	       else {
		    uvuni_to_utf8(natbuf, (UV) NATIVE_TO_UNI(((UV)*p1)));
		    to_utf8_fold(natbuf, foldbuf1, &foldlen1);
	       }
	       q1 = foldbuf1;
	       n1 = foldlen1;
	  }
	  if (n2 == 0) {
	       if (u2)
		    to_utf8_fold(p2, foldbuf2, &foldlen2);
	       else {
		    uvuni_to_utf8(natbuf, (UV) NATIVE_TO_UNI(((UV)*p2)));
		    to_utf8_fold(natbuf, foldbuf2, &foldlen2);
	       }
	       q2 = foldbuf2;
	       n2 = foldlen2;
	  }
	  while (n1 && n2) {
	       if ( UTF8SKIP(q1) != UTF8SKIP(q2) ||
		   (UTF8SKIP(q1) == 1 && *q1 != *q2) ||
		    memNE((char*)q1, (char*)q2, UTF8SKIP(q1)) )
		   return 1; /* mismatch */
	       n1 -= UTF8SKIP(q1);
	       q1 += UTF8SKIP(q1);
	       n2 -= UTF8SKIP(q2);
	       q2 += UTF8SKIP(q2);
	  }
	  if (n1 == 0)
	       p1 += u1 ? UTF8SKIP(p1) : 1;
	  if (n2 == 0)
	       p2 += u2 ? UTF8SKIP(p2) : 1;

     }

     /* A match is defined by all the scans that specified
      * an explicit length reaching their final goals. */
     match = (f1 == 0 || p1 == f1) && (f2 == 0 || p2 == f2);

     if (match) {
	  if (pe1)
	       *pe1 = (char*)p1;
	  if (pe2)
	       *pe2 = (char*)p2;
     }

     return match ? 0 : 1; /* 0 match, 1 mismatch */
}

/*
 * Local variables:
 * c-indentation-style: bsd
 * c-basic-offset: 4
 * indent-tabs-mode: t
 * End:
 *
 * ex: set ts=8 sts=4 sw=4 noet:
 */