summaryrefslogtreecommitdiffstats
path: root/src/charset.c
blob: 0e4dbbe1dca99a76bb347863a4ccdd1265a40152 (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
2462
2463
2464
/* vi:set ts=8 sts=4 sw=4 noet:
 *
 * VIM - Vi IMproved	by Bram Moolenaar
 *
 * Do ":help uganda"  in Vim to read copying and usage conditions.
 * Do ":help credits" in Vim to see a list of people who contributed.
 * See README.txt for an overview of the Vim source code.
 */

#include "vim.h"

#if defined(HAVE_WCHAR_H)
# include <wchar.h>	    // for towupper() and towlower()
#endif

static int win_nolbr_chartabsize(chartabsize_T *cts, int *headp);
static unsigned nr2hex(unsigned c);

static int    chartab_initialized = FALSE;

// b_chartab[] is an array of 32 bytes, each bit representing one of the
// characters 0-255.
#define SET_CHARTAB(buf, c) (buf)->b_chartab[(unsigned)(c) >> 3] |= (1 << ((c) & 0x7))
#define RESET_CHARTAB(buf, c) (buf)->b_chartab[(unsigned)(c) >> 3] &= ~(1 << ((c) & 0x7))
#define GET_CHARTAB(buf, c) ((buf)->b_chartab[(unsigned)(c) >> 3] & (1 << ((c) & 0x7)))

// table used below, see init_chartab() for an explanation
static char_u	g_chartab[256];

/*
 * Flags for g_chartab[].
 */
#define CT_CELL_MASK	0x07	// mask: nr of display cells (1, 2 or 4)
#define CT_PRINT_CHAR	0x10	// flag: set for printable chars
#define CT_ID_CHAR	0x20	// flag: set for ID chars
#define CT_FNAME_CHAR	0x40	// flag: set for file name chars

static int in_win_border(win_T *wp, colnr_T vcol);

/*
 * Fill g_chartab[].  Also fills curbuf->b_chartab[] with flags for keyword
 * characters for current buffer.
 *
 * Depends on the option settings 'iskeyword', 'isident', 'isfname',
 * 'isprint' and 'encoding'.
 *
 * The index in g_chartab[] depends on 'encoding':
 * - For non-multi-byte index with the byte (same as the character).
 * - For DBCS index with the first byte.
 * - For UTF-8 index with the character (when first byte is up to 0x80 it is
 *   the same as the character, if the first byte is 0x80 and above it depends
 *   on further bytes).
 *
 * The contents of g_chartab[]:
 * - The lower two bits, masked by CT_CELL_MASK, give the number of display
 *   cells the character occupies (1 or 2).  Not valid for UTF-8 above 0x80.
 * - CT_PRINT_CHAR bit is set when the character is printable (no need to
 *   translate the character before displaying it).  Note that only DBCS
 *   characters can have 2 display cells and still be printable.
 * - CT_FNAME_CHAR bit is set when the character can be in a file name.
 * - CT_ID_CHAR bit is set when the character can be in an identifier.
 *
 * Return FAIL if 'iskeyword', 'isident', 'isfname' or 'isprint' option has an
 * error, OK otherwise.
 */
    int
init_chartab(void)
{
    return buf_init_chartab(curbuf, TRUE);
}

    int
buf_init_chartab(
    buf_T	*buf,
    int		global)		// FALSE: only set buf->b_chartab[]
{
    int		c;
    int		c2;
    char_u	*p;
    int		i;
    int		tilde;
    int		do_isalpha;

    if (global)
    {
	/*
	 * Set the default size for printable characters:
	 * From <Space> to '~' is 1 (printable), others are 2 (not printable).
	 * This also inits all 'isident' and 'isfname' flags to FALSE.
	 */
	c = 0;
	while (c < ' ')
	    g_chartab[c++] = (dy_flags & DY_UHEX) ? 4 : 2;
	while (c <= '~')
	    g_chartab[c++] = 1 + CT_PRINT_CHAR;
	while (c < 256)
	{
	    // UTF-8: bytes 0xa0 - 0xff are printable (latin1)
	    if (enc_utf8 && c >= 0xa0)
		g_chartab[c++] = CT_PRINT_CHAR + 1;
	    // euc-jp characters starting with 0x8e are single width
	    else if (enc_dbcs == DBCS_JPNU && c == 0x8e)
		g_chartab[c++] = CT_PRINT_CHAR + 1;
	    // other double-byte chars can be printable AND double-width
	    else if (enc_dbcs != 0 && MB_BYTE2LEN(c) == 2)
		g_chartab[c++] = CT_PRINT_CHAR + 2;
	    else
		// the rest is unprintable by default
		g_chartab[c++] = (dy_flags & DY_UHEX) ? 4 : 2;
	}

	// Assume that every multi-byte char is a filename character.
	for (c = 1; c < 256; ++c)
	    if ((enc_dbcs != 0 && MB_BYTE2LEN(c) > 1)
		    || (enc_dbcs == DBCS_JPNU && c == 0x8e)
		    || (enc_utf8 && c >= 0xa0))
		g_chartab[c] |= CT_FNAME_CHAR;
    }

    /*
     * Init word char flags all to FALSE
     */
    CLEAR_FIELD(buf->b_chartab);
    if (enc_dbcs != 0)
	for (c = 0; c < 256; ++c)
	{
	    // double-byte characters are probably word characters
	    if (MB_BYTE2LEN(c) == 2)
		SET_CHARTAB(buf, c);
	}

    /*
     * In lisp mode the '-' character is included in keywords.
     */
    if (buf->b_p_lisp)
	SET_CHARTAB(buf, '-');

    // Walk through the 'isident', 'iskeyword', 'isfname' and 'isprint'
    // options Each option is a list of characters, character numbers or
    // ranges, separated by commas, e.g.: "200-210,x,#-178,-"
    for (i = global ? 0 : 3; i <= 3; ++i)
    {
	if (i == 0)
	    p = p_isi;		// first round: 'isident'
	else if (i == 1)
	    p = p_isp;		// second round: 'isprint'
	else if (i == 2)
	    p = p_isf;		// third round: 'isfname'
	else	// i == 3
	    p = buf->b_p_isk;	// fourth round: 'iskeyword'

	while (*p)
	{
	    tilde = FALSE;
	    do_isalpha = FALSE;
	    if (*p == '^' && p[1] != NUL)
	    {
		tilde = TRUE;
		++p;
	    }
	    if (VIM_ISDIGIT(*p))
		c = getdigits(&p);
	    else if (has_mbyte)
		c = mb_ptr2char_adv(&p);
	    else
		c = *p++;
	    c2 = -1;
	    if (*p == '-' && p[1] != NUL)
	    {
		++p;
		if (VIM_ISDIGIT(*p))
		    c2 = getdigits(&p);
		else if (has_mbyte)
		    c2 = mb_ptr2char_adv(&p);
		else
		    c2 = *p++;
	    }
	    if (c <= 0 || c >= 256 || (c2 < c && c2 != -1) || c2 >= 256
						 || !(*p == NUL || *p == ','))
		return FAIL;

	    if (c2 == -1)	// not a range
	    {
		/*
		 * A single '@' (not "@-@"):
		 * Decide on letters being ID/printable/keyword chars with
		 * standard function isalpha(). This takes care of locale for
		 * single-byte characters).
		 */
		if (c == '@')
		{
		    do_isalpha = TRUE;
		    c = 1;
		    c2 = 255;
		}
		else
		    c2 = c;
	    }
	    while (c <= c2)
	    {
		// Use the MB_ functions here, because isalpha() doesn't
		// work properly when 'encoding' is "latin1" and the locale is
		// "C".
		if (!do_isalpha || MB_ISLOWER(c) || MB_ISUPPER(c))
		{
		    if (i == 0)			// (re)set ID flag
		    {
			if (tilde)
			    g_chartab[c] &= ~CT_ID_CHAR;
			else
			    g_chartab[c] |= CT_ID_CHAR;
		    }
		    else if (i == 1)		// (re)set printable
		    {
			if ((c < ' ' || c > '~'
				// For double-byte we keep the cell width, so
				// that we can detect it from the first byte.
			    ) && !(enc_dbcs && MB_BYTE2LEN(c) == 2))
			{
			    if (tilde)
			    {
				g_chartab[c] = (g_chartab[c] & ~CT_CELL_MASK)
					     + ((dy_flags & DY_UHEX) ? 4 : 2);
				g_chartab[c] &= ~CT_PRINT_CHAR;
			    }
			    else
			    {
				g_chartab[c] = (g_chartab[c] & ~CT_CELL_MASK)
									   + 1;
				g_chartab[c] |= CT_PRINT_CHAR;
			    }
			}
		    }
		    else if (i == 2)		// (re)set fname flag
		    {
			if (tilde)
			    g_chartab[c] &= ~CT_FNAME_CHAR;
			else
			    g_chartab[c] |= CT_FNAME_CHAR;
		    }
		    else // i == 3		 (re)set keyword flag
		    {
			if (tilde)
			    RESET_CHARTAB(buf, c);
			else
			    SET_CHARTAB(buf, c);
		    }
		}
		++c;
	    }

	    c = *p;
	    p = skip_to_option_part(p);
	    if (c == ',' && *p == NUL)
		// Trailing comma is not allowed.
		return FAIL;
	}
    }
    chartab_initialized = TRUE;
    return OK;
}

/*
 * Translate any special characters in buf[bufsize] in-place.
 * The result is a string with only printable characters, but if there is not
 * enough room, not all characters will be translated.
 */
    void
trans_characters(
    char_u	*buf,
    int		bufsize)
{
    int		len;		// length of string needing translation
    int		room;		// room in buffer after string
    char_u	*trs;		// translated character
    int		trs_len;	// length of trs[]

    len = (int)STRLEN(buf);
    room = bufsize - len;
    while (*buf != 0)
    {
	// Assume a multi-byte character doesn't need translation.
	if (has_mbyte && (trs_len = (*mb_ptr2len)(buf)) > 1)
	    len -= trs_len;
	else
	{
	    trs = transchar_byte(*buf);
	    trs_len = (int)STRLEN(trs);
	    if (trs_len > 1)
	    {
		room -= trs_len - 1;
		if (room <= 0)
		    return;
		mch_memmove(buf + trs_len, buf + 1, (size_t)len);
	    }
	    mch_memmove(buf, trs, (size_t)trs_len);
	    --len;
	}
	buf += trs_len;
    }
}

/*
 * Translate a string into allocated memory, replacing special chars with
 * printable chars.  Returns NULL when out of memory.
 */
    char_u *
transstr(char_u *s)
{
    char_u	*res;
    char_u	*p;
    int		l, len, c;
    char_u	hexbuf[11];

    if (has_mbyte)
    {
	// Compute the length of the result, taking account of unprintable
	// multi-byte characters.
	len = 0;
	p = s;
	while (*p != NUL)
	{
	    if ((l = (*mb_ptr2len)(p)) > 1)
	    {
		c = (*mb_ptr2char)(p);
		p += l;
		if (vim_isprintc(c))
		    len += l;
		else
		{
		    transchar_hex(hexbuf, c);
		    len += (int)STRLEN(hexbuf);
		}
	    }
	    else
	    {
		l = byte2cells(*p++);
		if (l > 0)
		    len += l;
		else
		    len += 4;	// illegal byte sequence
	    }
	}
	res = alloc(len + 1);
    }
    else
	res = alloc(vim_strsize(s) + 1);

    if (res == NULL)
	return NULL;

    *res = NUL;
    p = s;
    while (*p != NUL)
    {
	if (has_mbyte && (l = (*mb_ptr2len)(p)) > 1)
	{
	    c = (*mb_ptr2char)(p);
	    if (vim_isprintc(c))
		STRNCAT(res, p, l);	// append printable multi-byte char
	    else
		transchar_hex(res + STRLEN(res), c);
	    p += l;
	}
	else
	    STRCAT(res, transchar_byte(*p++));
    }
    return res;
}

/*
 * Convert the string "str[orglen]" to do ignore-case comparing.  Uses the
 * current locale.
 * When "buf" is NULL returns an allocated string (NULL for out-of-memory).
 * Otherwise puts the result in "buf[buflen]".
 */
    char_u *
str_foldcase(
    char_u	*str,
    int		orglen,
    char_u	*buf,
    int		buflen)
{
    garray_T	ga;
    int		i;
    int		len = orglen;

#define GA_CHAR(i)  ((char_u *)ga.ga_data)[i]
#define GA_PTR(i)   ((char_u *)ga.ga_data + (i))
#define STR_CHAR(i)  (buf == NULL ? GA_CHAR(i) : buf[i])
#define STR_PTR(i)   (buf == NULL ? GA_PTR(i) : buf + (i))

    // Copy "str" into "buf" or allocated memory, unmodified.
    if (buf == NULL)
    {
	ga_init2(&ga, 1, 10);
	if (ga_grow(&ga, len + 1) == FAIL)
	    return NULL;
	mch_memmove(ga.ga_data, str, (size_t)len);
	ga.ga_len = len;
    }
    else
    {
	if (len >= buflen)	    // Ugly!
	    len = buflen - 1;
	mch_memmove(buf, str, (size_t)len);
    }
    if (buf == NULL)
	GA_CHAR(len) = NUL;
    else
	buf[len] = NUL;

    // Make each character lower case.
    i = 0;
    while (STR_CHAR(i) != NUL)
    {
	if (enc_utf8 || (has_mbyte && MB_BYTE2LEN(STR_CHAR(i)) > 1))
	{
	    if (enc_utf8)
	    {
		int	c = utf_ptr2char(STR_PTR(i));
		int	olen = utf_ptr2len(STR_PTR(i));
		int	lc = utf_tolower(c);

		// Only replace the character when it is not an invalid
		// sequence (ASCII character or more than one byte) and
		// utf_tolower() doesn't return the original character.
		if ((c < 0x80 || olen > 1) && c != lc)
		{
		    int	    nlen = utf_char2len(lc);

		    // If the byte length changes need to shift the following
		    // characters forward or backward.
		    if (olen != nlen)
		    {
			if (nlen > olen)
			{
			    if (buf == NULL
				    ? ga_grow(&ga, nlen - olen + 1) == FAIL
				    : len + nlen - olen >= buflen)
			    {
				// out of memory, keep old char
				lc = c;
				nlen = olen;
			    }
			}
			if (olen != nlen)
			{
			    if (buf == NULL)
			    {
				STRMOVE(GA_PTR(i) + nlen, GA_PTR(i) + olen);
				ga.ga_len += nlen - olen;
			    }
			    else
			    {
				STRMOVE(buf + i + nlen, buf + i + olen);
				len += nlen - olen;
			    }
			}
		    }
		    (void)utf_char2bytes(lc, STR_PTR(i));
		}
	    }
	    // skip to next multi-byte char
	    i += (*mb_ptr2len)(STR_PTR(i));
	}
	else
	{
	    if (buf == NULL)
		GA_CHAR(i) = TOLOWER_LOC(GA_CHAR(i));
	    else
		buf[i] = TOLOWER_LOC(buf[i]);
	    ++i;
	}
    }

    if (buf == NULL)
	return (char_u *)ga.ga_data;
    return buf;
}

/*
 * Catch 22: g_chartab[] can't be initialized before the options are
 * initialized, and initializing options may cause transchar() to be called!
 * When chartab_initialized == FALSE don't use g_chartab[].
 * Does NOT work for multi-byte characters, c must be <= 255.
 * Also doesn't work for the first byte of a multi-byte, "c" must be a
 * character!
 */
static char_u	transchar_charbuf[7];

    char_u *
transchar(int c)
{
    return transchar_buf(curbuf, c);
}

    char_u *
transchar_buf(buf_T *buf, int c)
{
    int			i;

    i = 0;
    if (IS_SPECIAL(c))	    // special key code, display as ~@ char
    {
	transchar_charbuf[0] = '~';
	transchar_charbuf[1] = '@';
	i = 2;
	c = K_SECOND(c);
    }

    if ((!chartab_initialized && ((c >= ' ' && c <= '~')))
					|| (c < 256 && vim_isprintc_strict(c)))
    {
	// printable character
	transchar_charbuf[i] = c;
	transchar_charbuf[i + 1] = NUL;
    }
    else
	transchar_nonprint(buf, transchar_charbuf + i, c);
    return transchar_charbuf;
}

/*
 * Like transchar(), but called with a byte instead of a character.  Checks
 * for an illegal UTF-8 byte.  Uses 'fileformat' of the current buffer.
 */
    char_u *
transchar_byte(int c)
{
    return transchar_byte_buf(curbuf, c);
}

/*
 * Like transchar_buf(), but called with a byte instead of a character.  Checks
 * for an illegal UTF-8 byte.  Uses 'fileformat' of "buf", unless it is NULL.
 */
    char_u *
transchar_byte_buf(buf_T *buf, int c)
{
    if (enc_utf8 && c >= 0x80)
    {
	transchar_nonprint(buf, transchar_charbuf, c);
	return transchar_charbuf;
    }
    return transchar_buf(buf, c);
}
/*
 * Convert non-printable character to two or more printable characters in
 * "charbuf[]".  "charbuf" needs to be able to hold five bytes.
 * Does NOT work for multi-byte characters, c must be <= 255.
 */
    void
transchar_nonprint(buf_T *buf, char_u *charbuf, int c)
{
    if (c == NL)
	c = NUL;		// we use newline in place of a NUL
    else if (buf != NULL && c == CAR && get_fileformat(buf) == EOL_MAC)
	c = NL;			// we use CR in place of  NL in this case

    if (dy_flags & DY_UHEX)		// 'display' has "uhex"
	transchar_hex(charbuf, c);

    else if (c <= 0x7f)			// 0x00 - 0x1f and 0x7f
    {
	charbuf[0] = '^';
	charbuf[1] = c ^ 0x40;		// DEL displayed as ^?
	charbuf[2] = NUL;
    }
    else if (enc_utf8)
    {
	transchar_hex(charbuf, c);
    }
    else if (c >= ' ' + 0x80 && c <= '~' + 0x80)    // 0xa0 - 0xfe
    {
	charbuf[0] = '|';
	charbuf[1] = c - 0x80;
	charbuf[2] = NUL;
    }
    else					    // 0x80 - 0x9f and 0xff
    {
	charbuf[0] = '~';
	charbuf[1] = (c - 0x80) ^ 0x40;	// 0xff displayed as ~?
	charbuf[2] = NUL;
    }
}

    void
transchar_hex(char_u *buf, int c)
{
    int		i = 0;

    buf[0] = '<';
    if (c > 255)
    {
	buf[++i] = nr2hex((unsigned)c >> 12);
	buf[++i] = nr2hex((unsigned)c >> 8);
    }
    buf[++i] = nr2hex((unsigned)c >> 4);
    buf[++i] = nr2hex((unsigned)c);
    buf[++i] = '>';
    buf[++i] = NUL;
}

/*
 * Convert the lower 4 bits of byte "c" to its hex character.
 * Lower case letters are used to avoid the confusion of <F1> being 0xf1 or
 * function key 1.
 */
    static unsigned
nr2hex(unsigned c)
{
    if ((c & 0xf) <= 9)
	return (c & 0xf) + '0';
    return (c & 0xf) - 10 + 'a';
}

/*
 * Return number of display cells occupied by byte "b".
 * Caller must make sure 0 <= b <= 255.
 * For multi-byte mode "b" must be the first byte of a character.
 * A TAB is counted as two cells: "^I".
 * For UTF-8 mode this will return 0 for bytes >= 0x80, because the number of
 * cells depends on further bytes.
 */
    int
byte2cells(int b)
{
    if (enc_utf8 && b >= 0x80)
	return 0;
    return (g_chartab[b] & CT_CELL_MASK);
}

/*
 * Return number of display cells occupied by character "c".
 * "c" can be a special key (negative number) in which case 3 or 4 is returned.
 * A TAB is counted as two cells: "^I" or four: "<09>".
 */
    int
char2cells(int c)
{
    if (IS_SPECIAL(c))
	return char2cells(K_SECOND(c)) + 2;
    if (c >= 0x80)
    {
	// UTF-8: above 0x80 need to check the value
	if (enc_utf8)
	    return utf_char2cells(c);
	// DBCS: double-byte means double-width, except for euc-jp with first
	// byte 0x8e
	if (enc_dbcs != 0 && c >= 0x100)
	{
	    if (enc_dbcs == DBCS_JPNU && ((unsigned)c >> 8) == 0x8e)
		return 1;
	    return 2;
	}
    }
    return (g_chartab[c & 0xff] & CT_CELL_MASK);
}

/*
 * Return number of display cells occupied by character at "*p".
 * A TAB is counted as two cells: "^I" or four: "<09>".
 */
    int
ptr2cells(char_u *p)
{
    if (!has_mbyte)
	return byte2cells(*p);

    // For UTF-8 we need to look at more bytes if the first byte is >= 0x80.
    if (enc_utf8 && *p >= 0x80)
	return utf_ptr2cells(p);
    // For DBCS we can tell the cell count from the first byte.
    return (g_chartab[*p] & CT_CELL_MASK);
}

/*
 * Return the number of character cells string "s" will take on the screen,
 * counting TABs as two characters: "^I".
 */
    int
vim_strsize(char_u *s)
{
    return vim_strnsize(s, (int)MAXCOL);
}

/*
 * Return the number of character cells string "s[len]" will take on the
 * screen, counting TABs as two characters: "^I".
 */
    int
vim_strnsize(char_u *s, int len)
{
    int		size = 0;

    while (*s != NUL && --len >= 0)
    {
	int	    l = (*mb_ptr2len)(s);

	size += ptr2cells(s);
	s += l;
	len -= l - 1;
    }

    return size;
}

/*
 * Return the number of characters 'c' will take on the screen, taking
 * into account the size of a tab.
 * Use a define to make it fast, this is used very often!!!
 * Also see getvcol() below.
 */

#ifdef FEAT_VARTABS
# define RET_WIN_BUF_CHARTABSIZE(wp, buf, p, col) \
    if (*(p) == TAB && (!(wp)->w_p_list || (wp)->w_lcs_chars.tab1)) \
    { \
	return tabstop_padding(col, (buf)->b_p_ts, (buf)->b_p_vts_array); \
    } \
    else \
	return ptr2cells(p);
#else
# define RET_WIN_BUF_CHARTABSIZE(wp, buf, p, col) \
    if (*(p) == TAB && (!(wp)->w_p_list || wp->w_lcs_chars.tab1)) \
    { \
	int ts; \
	ts = (buf)->b_p_ts; \
	return (int)(ts - (col % ts)); \
    } \
    else \
	return ptr2cells(p);
#endif

    int
chartabsize(char_u *p, colnr_T col)
{
    RET_WIN_BUF_CHARTABSIZE(curwin, curbuf, p, col)
}

#ifdef FEAT_LINEBREAK
    static int
win_chartabsize(win_T *wp, char_u *p, colnr_T col)
{
    RET_WIN_BUF_CHARTABSIZE(wp, wp->w_buffer, p, col)
}
#endif

/*
 * Return the number of characters the string "s" will take on the screen,
 * taking into account the size of a tab.
 * Does not handle text properties, since "s" is not a buffer line.
 */
    int
linetabsize_str(char_u *s)
{
    return linetabsize_col(0, s);
}

/*
 * Like linetabsize_str(), but "s" starts at column "startcol".
 */
    int
linetabsize_col(int startcol, char_u *s)
{
    chartabsize_T cts;

    init_chartabsize_arg(&cts, curwin, 0, startcol, s, s);
    while (*cts.cts_ptr != NUL)
	cts.cts_vcol += lbr_chartabsize_adv(&cts);
    clear_chartabsize_arg(&cts);
    return (int)cts.cts_vcol;
}

/*
 * Like linetabsize_str(), but for a given window instead of the current one.
 */
    int
win_linetabsize(win_T *wp, linenr_T lnum, char_u *line, colnr_T len)
{
    chartabsize_T cts;

    init_chartabsize_arg(&cts, wp, lnum, 0, line, line);
    win_linetabsize_cts(&cts, len);
    clear_chartabsize_arg(&cts);
    return (int)cts.cts_vcol;
}

/*
 * Return the number of cells line "lnum" of window "wp" will take on the
 * screen, taking into account the size of a tab and text properties.
 */
  int
linetabsize(win_T *wp, linenr_T lnum)
{
    return win_linetabsize(wp, lnum,
		       ml_get_buf(wp->w_buffer, lnum, FALSE), (colnr_T)MAXCOL);
}

    void
win_linetabsize_cts(chartabsize_T *cts, colnr_T len)
{
#ifdef FEAT_PROP_POPUP
    cts->cts_with_trailing = len == MAXCOL;
#endif
    for ( ; *cts->cts_ptr != NUL && (len == MAXCOL || cts->cts_ptr < cts->cts_line + len);
						      MB_PTR_ADV(cts->cts_ptr))
	cts->cts_vcol += win_lbr_chartabsize(cts, NULL);
#ifdef FEAT_PROP_POPUP
    // check for a virtual text at the end of a line or on an empty line
    if (len == MAXCOL && cts->cts_has_prop_with_text && *cts->cts_ptr == NUL)
    {
	(void)win_lbr_chartabsize(cts, NULL);
	cts->cts_vcol += cts->cts_cur_text_width;
	// when properties are above or below the empty line must also be
	// counted
	if (cts->cts_ptr == cts->cts_line && cts->cts_prop_lines > 0)
	    ++cts->cts_vcol;
    }
#endif
}

/*
 * Return TRUE if 'c' is a normal identifier character:
 * Letters and characters from the 'isident' option.
 */
    int
vim_isIDc(int c)
{
    return (c > 0 && c < 0x100 && (g_chartab[c] & CT_ID_CHAR));
}

/*
 * Like vim_isIDc() but not using the 'isident' option: letters, numbers and
 * underscore.
 */
    int
vim_isNormalIDc(int c)
{
    return ASCII_ISALNUM(c) || c == '_';
}

/*
 * return TRUE if 'c' is a keyword character: Letters and characters from
 * 'iskeyword' option for the current buffer.
 * For multi-byte characters mb_get_class() is used (builtin rules).
 */
    int
vim_iswordc(int c)
{
    return vim_iswordc_buf(c, curbuf);
}

    int
vim_iswordc_buf(int c, buf_T *buf)
{
    if (c >= 0x100)
    {
	if (enc_dbcs != 0)
	    return dbcs_class((unsigned)c >> 8, (unsigned)(c & 0xff)) >= 2;
	if (enc_utf8)
	    return utf_class_buf(c, buf) >= 2;
	return FALSE;
    }
    return (c > 0 && GET_CHARTAB(buf, c) != 0);
}

/*
 * Just like vim_iswordc() but uses a pointer to the (multi-byte) character.
 */
    int
vim_iswordp(char_u *p)
{
    return vim_iswordp_buf(p, curbuf);
}

    int
vim_iswordp_buf(char_u *p, buf_T *buf)
{
    int	c = *p;

    if (has_mbyte && MB_BYTE2LEN(c) > 1)
	c = (*mb_ptr2char)(p);
    return vim_iswordc_buf(c, buf);
}

/*
 * Return TRUE if 'c' is a valid file-name character as specified with the
 * 'isfname' option.
 * Assume characters above 0x100 are valid (multi-byte).
 * To be used for commands like "gf".
 */
    int
vim_isfilec(int c)
{
    return (c >= 0x100 || (c > 0 && (g_chartab[c] & CT_FNAME_CHAR)));
}

#if defined(FEAT_SPELL) || defined(PROTO)
/*
 * Return TRUE if 'c' is a valid file-name character, including characters left
 * out of 'isfname' to make "gf" work, such as comma, space, '@', etc.
 */
    int
vim_is_fname_char(int c)
{
    return vim_isfilec(c) || c == ',' || c == ' ' || c == '@';
}
#endif

/*
 * return TRUE if 'c' is a valid file-name character or a wildcard character
 * Assume characters above 0x100 are valid (multi-byte).
 * Explicitly interpret ']' as a wildcard character as mch_has_wildcard("]")
 * returns false.
 */
    int
vim_isfilec_or_wc(int c)
{
    char_u buf[2];

    buf[0] = (char_u)c;
    buf[1] = NUL;
    return vim_isfilec(c) || c == ']' || mch_has_wildcard(buf);
}

/*
 * Return TRUE if 'c' is a printable character.
 * Assume characters above 0x100 are printable (multi-byte), except for
 * Unicode.
 */
    int
vim_isprintc(int c)
{
    if (enc_utf8 && c >= 0x100)
	return utf_printable(c);
    return (c >= 0x100 || (c > 0 && (g_chartab[c] & CT_PRINT_CHAR)));
}

/*
 * Strict version of vim_isprintc(c), don't return TRUE if "c" is the head
 * byte of a double-byte character.
 */
    int
vim_isprintc_strict(int c)
{
    if (enc_dbcs != 0 && c < 0x100 && MB_BYTE2LEN(c) > 1)
	return FALSE;
    if (enc_utf8 && c >= 0x100)
	return utf_printable(c);
    return (c >= 0x100 || (c > 0 && (g_chartab[c] & CT_PRINT_CHAR)));
}

/*
 * Prepare the structure passed to chartabsize functions.
 * "line" is the start of the line, "ptr" is the first relevant character.
 * When "lnum" is zero do not use text properties that insert text.
 */
    void
init_chartabsize_arg(
	chartabsize_T	*cts,
	win_T		*wp,
	linenr_T	lnum UNUSED,
	colnr_T		col,
	char_u		*line,
	char_u		*ptr)
{
    CLEAR_POINTER(cts);
    cts->cts_win = wp;
    cts->cts_vcol = col;
    cts->cts_line = line;
    cts->cts_ptr = ptr;
#ifdef FEAT_PROP_POPUP
    if (lnum > 0 && !ignore_text_props)
    {
	char_u	*prop_start;
	int	count;

	count = get_text_props(wp->w_buffer, lnum, &prop_start, FALSE);
	cts->cts_text_prop_count = count;
	if (count > 0)
	{
	    // Make a copy of the properties, so that they are properly
	    // aligned.  Make it twice as long for the sorting below.
	    cts->cts_text_props = ALLOC_MULT(textprop_T, count * 2);
	    if (cts->cts_text_props == NULL)
		cts->cts_text_prop_count = 0;
	    else
	    {
		int	i;

		mch_memmove(cts->cts_text_props + count, prop_start,
						   count * sizeof(textprop_T));
		for (i = 0; i < count; ++i)
		{
		    textprop_T *tp = cts->cts_text_props + i + count;
		    if (tp->tp_id < 0
				     && text_prop_type_valid(wp->w_buffer, tp))
		    {
			cts->cts_has_prop_with_text = TRUE;
			break;
		    }
		}
		if (!cts->cts_has_prop_with_text)
		{
		    // won't use the text properties, free them
		    VIM_CLEAR(cts->cts_text_props);
		    cts->cts_text_prop_count = 0;
		}
		else
		{
		    int	    *text_prop_idxs;

		    // Need to sort the array to get any truncation right.
		    // Do the sorting in the second part of the array, then
		    // move the sorted props to the first part of the array.
		    text_prop_idxs = ALLOC_MULT(int, count);
		    if (text_prop_idxs != NULL)
		    {
			for (i = 0; i < count; ++i)
			    text_prop_idxs[i] = i + count;
			sort_text_props(curbuf, cts->cts_text_props,
							text_prop_idxs, count);
			// Here we want the reverse order.
			for (i = 0; i < count; ++i)
			    cts->cts_text_props[count - i - 1] =
					cts->cts_text_props[text_prop_idxs[i]];
			vim_free(text_prop_idxs);
		    }
		}
	    }
	}
    }
#endif
}

/*
 * Free any allocated item in "cts".
 */
    void
clear_chartabsize_arg(chartabsize_T *cts UNUSED)
{
#ifdef FEAT_PROP_POPUP
    if (cts->cts_text_prop_count > 0)
    {
	VIM_CLEAR(cts->cts_text_props);
	cts->cts_text_prop_count = 0;
    }
#endif
}

/*
 * Like chartabsize(), but also check for line breaks on the screen and text
 * properties that insert text.
 */
    int
lbr_chartabsize(chartabsize_T *cts)
{
#if defined(FEAT_LINEBREAK) || defined(FEAT_PROP_POPUP)
    if (1
# ifdef FEAT_LINEBREAK
	&& !curwin->w_p_lbr && *get_showbreak_value(curwin) == NUL
							   && !curwin->w_p_bri
# endif
# ifdef FEAT_PROP_POPUP
	&& !cts->cts_has_prop_with_text
#endif
       )
    {
#endif
	if (curwin->w_p_wrap)
	    return win_nolbr_chartabsize(cts, NULL);
	RET_WIN_BUF_CHARTABSIZE(curwin, curbuf, cts->cts_ptr, cts->cts_vcol)
#if defined(FEAT_LINEBREAK) || defined(FEAT_PROP_POPUP)
    }
    return win_lbr_chartabsize(cts, NULL);
#endif
}

/*
 * Call lbr_chartabsize() and advance the pointer.
 */
    int
lbr_chartabsize_adv(chartabsize_T *cts)
{
    int		retval;

    retval = lbr_chartabsize(cts);
    MB_PTR_ADV(cts->cts_ptr);
    return retval;
}

/*
 * Return the screen size of the character indicated by "cts".
 * "cts->cts_cur_text_width" is set to the extra size for a text property that
 * inserts text.
 * This function is used very often, keep it fast!!!!
 *
 * If "headp" not NULL, set "*headp" to the size of 'showbreak'/'breakindent'
 * included in the return value.
 * When "cts->cts_max_head_vcol" is positive, only count in "*headp" the size
 * of 'showbreak'/'breakindent' before "cts->cts_max_head_vcol".
 * When "cts->cts_max_head_vcol" is negative, only count in "*headp" the size
 * of 'showbreak'/'breakindent' before where cursor should be placed.
 *
 * Warning: "*headp" may not be set if it's 0, init to 0 before calling.
 */
    int
win_lbr_chartabsize(
	chartabsize_T	*cts,
	int		*headp UNUSED)
{
    win_T	*wp = cts->cts_win;
#if defined(FEAT_PROP_POPUP) || defined(FEAT_LINEBREAK)
    char_u	*line = cts->cts_line; // start of the line
#endif
    char_u	*s = cts->cts_ptr;
    colnr_T	vcol = cts->cts_vcol;
#ifdef FEAT_LINEBREAK
    int		size;
    int		mb_added = 0;
    int		n;
    char_u	*sbr;
    int		no_sbr = FALSE;
    colnr_T	vcol_start = 0; // start from where to consider linebreak
#endif

#if defined(FEAT_PROP_POPUP)
    cts->cts_cur_text_width = 0;
    cts->cts_first_char = 0;
#endif

#if defined(FEAT_LINEBREAK) || defined(FEAT_PROP_POPUP)
    /*
     * No 'linebreak', 'showbreak', 'breakindent' and text properties that
     * insert text: return quickly.
     */
    if (1
# ifdef FEAT_LINEBREAK
	    && !wp->w_p_lbr && !wp->w_p_bri && *get_showbreak_value(wp) == NUL
# endif
# ifdef FEAT_PROP_POPUP
	    && !cts->cts_has_prop_with_text
# endif
	    )
#endif
    {
	if (wp->w_p_wrap)
	    return win_nolbr_chartabsize(cts, headp);
	RET_WIN_BUF_CHARTABSIZE(wp, wp->w_buffer, s, vcol)
    }

#if defined(FEAT_LINEBREAK) || defined(FEAT_PROP_POPUP)
    int has_lcs_eol = wp->w_p_list && wp->w_lcs_chars.eol != NUL;

    /*
     * First get the normal size, without 'linebreak' or text properties
     */
    size = win_chartabsize(wp, s, vcol);
    if (*s == NUL && !has_lcs_eol)
	size = 0;  // NUL is not displayed
# ifdef FEAT_LINEBREAK
    int is_doublewidth = has_mbyte && size == 2 && MB_BYTE2LEN(*s) > 1;
# endif

# ifdef FEAT_PROP_POPUP
    if (cts->cts_has_prop_with_text)
    {
	int	    tab_size = size;
	int	    charlen = *s == NUL ? 1 : mb_ptr2len(s);
	int	    i;
	int	    col = (int)(s - line);
	garray_T    *gap = &wp->w_buffer->b_textprop_text;

	// The "$" for 'list' mode will go between the EOL and
	// the text prop, account for that.
	if (has_lcs_eol)
	{
	    ++vcol;
	    --size;
	}

	for (i = 0; i < cts->cts_text_prop_count; ++i)
	{
	    textprop_T	*tp = cts->cts_text_props + i;
	    int		col_off = win_col_off(wp);

	    // Watch out for the text being deleted.  "cts_text_props" is a
	    // copy, the text prop may actually have been removed from the line.
	    if (tp->tp_id < 0
		    && ((tp->tp_col - 1 >= col
					     && tp->tp_col - 1 < col + charlen)
		       || (tp->tp_col == MAXCOL
			   && ((tp->tp_flags & TP_FLAG_ALIGN_ABOVE)
				? col == 0
				: s[0] == NUL && cts->cts_with_trailing)))
		    && -tp->tp_id - 1 < gap->ga_len)
	    {
		char_u *p = ((char_u **)gap->ga_data)[-tp->tp_id - 1];

		if (p != NULL)
		{
		    int	cells;

		    if (tp->tp_col == MAXCOL)
		    {
			int n_extra = (int)STRLEN(p);

			cells = text_prop_position(wp, tp, vcol,
			     (vcol + size) % (wp->w_width - col_off) + col_off,
					      &n_extra, &p, NULL, NULL, FALSE);
#  ifdef FEAT_LINEBREAK
			no_sbr = TRUE;  // don't use 'showbreak' now
#  endif
		    }
		    else
			cells = vim_strsize(p);
		    cts->cts_cur_text_width += cells;
		    if (tp->tp_flags & TP_FLAG_ALIGN_ABOVE)
			cts->cts_first_char += cells;
		    else
			size += cells;
		    cts->cts_start_incl = tp->tp_flags & TP_FLAG_START_INCL;
		    if (*s == TAB)
		    {
			// tab size changes because of the inserted text
			size -= tab_size;
			tab_size = win_chartabsize(wp, s, vcol + size);
			size += tab_size;
		    }
		    if (tp->tp_col == MAXCOL && (tp->tp_flags
				& (TP_FLAG_ALIGN_ABOVE | TP_FLAG_ALIGN_BELOW)))
			// count extra line for property above/below
			++cts->cts_prop_lines;
		}
	    }
	    if (tp->tp_col != MAXCOL && tp->tp_col - 1 > col)
		break;
	}
	if (has_lcs_eol)
	{
	    --vcol;
	    ++size;
	}
    }
# endif

# ifdef FEAT_LINEBREAK
    if (is_doublewidth && wp->w_p_wrap && in_win_border(wp, vcol + size - 2))
    {
	++size;		// Count the ">" in the last column.
	mb_added = 1;
    }

    /*
     * May have to add something for 'breakindent' and/or 'showbreak'
     * string at the start of a screen line.
     */
    int head = mb_added;
    sbr = no_sbr ? empty_option : get_showbreak_value(wp);
    // When "size" is 0, no new screen line is started.
    if (size > 0 && wp->w_p_wrap && (*sbr != NUL || wp->w_p_bri))
    {
	int	col_off_prev = win_col_off(wp);
	int	width2 = wp->w_width - col_off_prev + win_col_off2(wp);
	colnr_T	wcol = vcol + col_off_prev;
#  ifdef FEAT_PROP_POPUP
	wcol -= wp->w_virtcol_first_char;
#  endif
	colnr_T	max_head_vcol = cts->cts_max_head_vcol;
	int	added = 0;

	// cells taken by 'showbreak'/'breakindent' before current char
	int	head_prev = 0;
	if (wcol >= wp->w_width)
	{
	    wcol -= wp->w_width;
	    col_off_prev = wp->w_width - width2;
	    if (wcol >= width2 && width2 > 0)
		wcol %= width2;
	    if (*sbr != NUL)
		head_prev += vim_strsize(sbr);
	    if (wp->w_p_bri)
		head_prev += get_breakindent_win(wp, line);
	    if (wcol < head_prev)
	    {
		head_prev -= wcol;
		wcol += head_prev;
		added += head_prev;
		if (max_head_vcol <= 0 || vcol < max_head_vcol)
		    head += head_prev;
	    }
	    else
		head_prev = 0;
	    wcol += col_off_prev;
	}

	if (wcol + size > wp->w_width)
	{
	    // cells taken by 'showbreak'/'breakindent' halfway current char
	    int	head_mid = 0;
	    if (*sbr != NUL)
		head_mid += vim_strsize(sbr);
	    if (wp->w_p_bri)
		head_mid += get_breakindent_win(wp, line);
	    if (head_mid > 0 && wcol + size > wp->w_width)
	    {
		// Calculate effective window width.
		int prev_rem = wp->w_width - wcol;
		int width = width2 - head_mid;

		if (width <= 0)
		    width = 1;
		// Divide "size - prev_rem" by "width", rounding up.
		int cnt = (size - prev_rem + width - 1) / width;
		added += cnt * head_mid;

		if (max_head_vcol == 0 || vcol + size + added < max_head_vcol)
		    head += cnt * head_mid;
		else if (max_head_vcol > vcol + head_prev + prev_rem)
		    head += (max_head_vcol - (vcol + head_prev + prev_rem)
					     + width2 - 1) / width2 * head_mid;
#  ifdef FEAT_PROP_POPUP
		else if (max_head_vcol < 0)
		{
		    int off = 0;
		    if (*s != NUL
			     && ((State & MODE_NORMAL) || cts->cts_start_incl))
			off += cts->cts_cur_text_width;
		    if (off >= prev_rem)
			head += (1 + (off - prev_rem) / width) * head_mid;
		}
#  endif
	    }
	}

	size += added;
    }

    if (headp != NULL)
	*headp = head;

    /*
     * If 'linebreak' set check at a blank before a non-blank if the line
     * needs a break here
     */
    if (wp->w_p_lbr && wp->w_p_wrap && wp->w_width != 0)
    {
	char_u	*t = cts->cts_line;
	while (VIM_ISBREAK((int)t[0]))
	    t++;
	vcol_start = t - cts->cts_line;
    }
    if (wp->w_p_lbr && vcol_start <= vcol
	    && VIM_ISBREAK((int)s[0])
	    && !VIM_ISBREAK((int)s[1])
	    && wp->w_p_wrap
	    && wp->w_width != 0)
    {
	/*
	 * Count all characters from first non-blank after a blank up to next
	 * non-blank after a blank.
	 */
	int numberextra = win_col_off(wp);
	colnr_T col_adj = size - 1;
	colnr_T colmax = (colnr_T)(wp->w_width - numberextra - col_adj);
	if (vcol >= colmax)
	{
	    colmax += col_adj;
	    n = colmax +  win_col_off2(wp);
	    if (n > 0)
		colmax += (((vcol - colmax) / n) + 1) * n - col_adj;
	}

	colnr_T vcol2 = vcol;
	for (;;)
	{
	    char_u *ps = s;
	    MB_PTR_ADV(s);
	    int c = *s;
	    if (!(c != NUL
		    && (VIM_ISBREAK(c)
			|| (!VIM_ISBREAK(c)
			       && (vcol2 == vcol || !VIM_ISBREAK((int)*ps))))))
		break;

	    vcol2 += win_chartabsize(wp, s, vcol2);
	    if (vcol2 >= colmax)		// doesn't fit
	    {
		size = colmax - vcol + col_adj;
		break;
	    }
	}
    }

#  ifdef FEAT_PROP_POPUP
    size += cts->cts_first_char;
#  endif
    return size;
# endif
#endif
}

/*
 * Like win_lbr_chartabsize(), except that we know 'linebreak' is off, 'wrap'
 * is on and there are no properties that insert text.  This means we need to
 * check for a double-byte character that doesn't fit at the end of the screen
 * line.
 * Only uses "cts_win", "cts_ptr" and "cts_vcol" from "cts".
 */
    static int
win_nolbr_chartabsize(
	chartabsize_T	*cts,
	int		*headp)
{
    win_T	*wp = cts->cts_win;
    char_u	*s = cts->cts_ptr;
    colnr_T	col = cts->cts_vcol;
    int		n;

    if (*s == TAB && (!wp->w_p_list || wp->w_lcs_chars.tab1))
    {
# ifdef FEAT_VARTABS
	return tabstop_padding(col, wp->w_buffer->b_p_ts,
				    wp->w_buffer->b_p_vts_array);
# else
	n = wp->w_buffer->b_p_ts;
	return (int)(n - (col % n));
# endif
    }
    n = ptr2cells(s);
    // Add one cell for a double-width character in the last column of the
    // window, displayed with a ">".
    if (n == 2 && MB_BYTE2LEN(*s) > 1 && in_win_border(wp, col))
    {
	if (headp != NULL)
	    *headp = 1;
	return 3;
    }
    return n;
}

/*
 * Return TRUE if virtual column "vcol" is in the rightmost column of window
 * "wp".
 */
    static int
in_win_border(win_T *wp, colnr_T vcol)
{
    int		width1;		// width of first line (after line number)
    int		width2;		// width of further lines

    if (wp->w_width == 0)	// there is no border
	return FALSE;
    width1 = wp->w_width - win_col_off(wp);
    if ((int)vcol < width1 - 1)
	return FALSE;
    if ((int)vcol == width1 - 1)
	return TRUE;
    width2 = width1 + win_col_off2(wp);
    if (width2 <= 0)
	return FALSE;
    return ((vcol - width1) % width2 == width2 - 1);
}

/*
 * Get virtual column number of pos.
 *  start: on the first position of this character (TAB, ctrl)
 * cursor: where the cursor is on this character (first char, except for TAB)
 *    end: on the last position of this character (TAB, ctrl)
 *
 * This is used very often, keep it fast!
 */
    void
getvcol(
    win_T	*wp,
    pos_T	*pos,
    colnr_T	*start,
    colnr_T	*cursor,
    colnr_T	*end)
{
    colnr_T	vcol;
    char_u	*ptr;		// points to current char
    char_u	*posptr;	// points to char at pos->col
    char_u	*line;		// start of the line
    int		incr;
    int		head;
#ifdef FEAT_VARTABS
    int		*vts = wp->w_buffer->b_p_vts_array;
#endif
    int		ts = wp->w_buffer->b_p_ts;
    int		c;
    chartabsize_T cts;
#ifdef FEAT_PROP_POPUP
    int		on_NUL = FALSE;
#endif

    vcol = 0;
    line = ptr = ml_get_buf(wp->w_buffer, pos->lnum, FALSE);
    if (pos->col == MAXCOL)
	posptr = NULL;  // continue until the NUL
    else
    {
	colnr_T i;

	// In a few cases the position can be beyond the end of the line.
	for (i = 0; i < pos->col; ++i)
	    if (ptr[i] == NUL)
	    {
		pos->col = i;
		break;
	    }
	posptr = ptr + pos->col;
	if (has_mbyte)
	    // always start on the first byte
	    posptr -= (*mb_head_off)(line, posptr);
    }

    init_chartabsize_arg(&cts, wp, pos->lnum, 0, line, line);
    cts.cts_max_head_vcol = -1;

    /*
     * This function is used very often, do some speed optimizations.
     * When 'list', 'linebreak', 'showbreak' and 'breakindent' are not set
     * and there are no text properties with "text" use a simple loop.
     * Also use this when 'list' is set but tabs take their normal size.
     */
    if ((!wp->w_p_list || wp->w_lcs_chars.tab1 != NUL)
#ifdef FEAT_LINEBREAK
	    && !wp->w_p_lbr && *get_showbreak_value(wp) == NUL && !wp->w_p_bri
#endif
#ifdef FEAT_PROP_POPUP
	    && !cts.cts_has_prop_with_text
#endif
       )
    {
	for (;;)
	{
	    head = 0;
	    c = *ptr;
	    // make sure we don't go past the end of the line
	    if (c == NUL)
	    {
		incr = 1;	// NUL at end of line only takes one column
		break;
	    }
	    // A tab gets expanded, depending on the current column
	    if (c == TAB)
#ifdef FEAT_VARTABS
		incr = tabstop_padding(vcol, ts, vts);
#else
		incr = ts - (vcol % ts);
#endif
	    else
	    {
		if (has_mbyte)
		{
		    // For utf-8, if the byte is >= 0x80, need to look at
		    // further bytes to find the cell width.
		    if (enc_utf8 && c >= 0x80)
			incr = utf_ptr2cells(ptr);
		    else
			incr = g_chartab[c] & CT_CELL_MASK;

		    // If a double-cell char doesn't fit at the end of a line
		    // it wraps to the next line, it's like this char is three
		    // cells wide.
		    if (incr == 2 && wp->w_p_wrap && MB_BYTE2LEN(*ptr) > 1
			    && in_win_border(wp, vcol))
		    {
			++incr;
			head = 1;
		    }
		}
		else
		    incr = g_chartab[c] & CT_CELL_MASK;
	    }

	    if (posptr != NULL && ptr >= posptr) // character at pos->col
		break;

	    vcol += incr;
	    MB_PTR_ADV(ptr);
	}
    }
    else
    {
	for (;;)
	{
	    // A tab gets expanded, depending on the current column.
	    // Other things also take up space.
	    head = 0;
	    incr = win_lbr_chartabsize(&cts, &head);
	    // make sure we don't go past the end of the line
	    if (*cts.cts_ptr == NUL)
	    {
		incr = 1;	// NUL at end of line only takes one column
#ifdef FEAT_PROP_POPUP
		if (cts.cts_cur_text_width > 0)
		    incr = cts.cts_cur_text_width;
		on_NUL = TRUE;
#endif
		break;
	    }
#ifdef FEAT_PROP_POPUP
	    if (cursor == &wp->w_virtcol && cts.cts_ptr == cts.cts_line)
		// do not count the virtual text above for w_curswant
		wp->w_virtcol_first_char = cts.cts_first_char;
#endif

	    if (posptr != NULL && cts.cts_ptr >= posptr)
		// character at pos->col
		break;

	    cts.cts_vcol += incr;
	    MB_PTR_ADV(cts.cts_ptr);
	}
	vcol = cts.cts_vcol;
	ptr = cts.cts_ptr;
    }
    clear_chartabsize_arg(&cts);

    if (start != NULL)
	*start = vcol + head;
    if (end != NULL)
	*end = vcol + incr - 1;
    if (cursor != NULL)
    {
	if (*ptr == TAB
		&& (State & MODE_NORMAL)
		&& !wp->w_p_list
		&& !virtual_active()
		&& !(VIsual_active
				&& (*p_sel == 'e' || LTOREQ_POS(*pos, VIsual)))
		)
	    *cursor = vcol + incr - 1;	    // cursor at end
	else
	{
#ifdef FEAT_PROP_POPUP
	    // in Insert mode, if "start_incl" is true the text gets inserted
	    // after the virtual text, thus add its width
	    if (((State & MODE_INSERT) == 0 || cts.cts_start_incl) && !on_NUL)
		// cursor is after inserted text, unless on the NUL
		vcol += cts.cts_cur_text_width;
	    else
		// insertion also happens after the "above" virtual text
		vcol += cts.cts_first_char;
#endif
	    *cursor = vcol + head;	    // cursor at start
	}
    }
}

/*
 * Get virtual cursor column in the current window, pretending 'list' is off.
 */
    colnr_T
getvcol_nolist(pos_T *posp)
{
    int		list_save = curwin->w_p_list;
    colnr_T	vcol;

    curwin->w_p_list = FALSE;
    if (posp->coladd)
	getvvcol(curwin, posp, NULL, &vcol, NULL);
    else
	getvcol(curwin, posp, NULL, &vcol, NULL);
    curwin->w_p_list = list_save;
    return vcol;
}

/*
 * Get virtual column in virtual mode.
 */
    void
getvvcol(
    win_T	*wp,
    pos_T	*pos,
    colnr_T	*start,
    colnr_T	*cursor,
    colnr_T	*end)
{
    colnr_T	col;
    colnr_T	coladd;
    colnr_T	endadd;
    char_u	*ptr;

    if (virtual_active())
    {
	// For virtual mode, only want one value
	getvcol(wp, pos, &col, NULL, NULL);

	coladd = pos->coladd;
	endadd = 0;
	// Cannot put the cursor on part of a wide character.
	ptr = ml_get_buf(wp->w_buffer, pos->lnum, FALSE);
	if (pos->col < (colnr_T)STRLEN(ptr))
	{
	    int c = (*mb_ptr2char)(ptr + pos->col);

	    if (c != TAB && vim_isprintc(c))
	    {
		endadd = (colnr_T)(char2cells(c) - 1);
		if (coladd > endadd)	// past end of line
		    endadd = 0;
		else
		    coladd = 0;
	    }
	}
	col += coladd;
	if (start != NULL)
	    *start = col;
	if (cursor != NULL)
	    *cursor = col;
	if (end != NULL)
	    *end = col + endadd;
    }
    else
	getvcol(wp, pos, start, cursor, end);
}

/*
 * Get the leftmost and rightmost virtual column of pos1 and pos2.
 * Used for Visual block mode.
 */
    void
getvcols(
    win_T	*wp,
    pos_T	*pos1,
    pos_T	*pos2,
    colnr_T	*left,
    colnr_T	*right)
{
    colnr_T	from1, from2, to1, to2;

    if (LT_POSP(pos1, pos2))
    {
	getvvcol(wp, pos1, &from1, NULL, &to1);
	getvvcol(wp, pos2, &from2, NULL, &to2);
    }
    else
    {
	getvvcol(wp, pos2, &from1, NULL, &to1);
	getvvcol(wp, pos1, &from2, NULL, &to2);
    }
    if (from2 < from1)
	*left = from2;
    else
	*left = from1;
    if (to2 > to1)
    {
	if (*p_sel == 'e' && from2 - 1 >= to1)
	    *right = from2 - 1;
	else
	    *right = to2;
    }
    else
	*right = to1;
}

/*
 * Skip over ' ' and '\t'.
 */
    char_u *
skipwhite(char_u *q)
{
    char_u	*p = q;

    while (VIM_ISWHITE(*p))
	++p;
    return p;
}

#if defined(FEAT_EVAL) || defined(PROTO)
/*
 * skip over ' ', '\t' and '\n'.
 */
    char_u *
skipwhite_and_nl(char_u *q)
{
    char_u	*p = q;

    while (VIM_ISWHITE(*p) || *p == NL)
	++p;
    return p;
}
#endif

/*
 * getwhitecols: return the number of whitespace
 * columns (bytes) at the start of a given line
 */
    int
getwhitecols_curline(void)
{
    return getwhitecols(ml_get_curline());
}

    int
getwhitecols(char_u *p)
{
    return skipwhite(p) - p;
}

/*
 * skip over digits
 */
    char_u *
skipdigits(char_u *q)
{
    char_u	*p = q;

    while (VIM_ISDIGIT(*p))	// skip to next non-digit
	++p;
    return p;
}

#if defined(FEAT_SYN_HL) || defined(FEAT_SPELL) || defined(PROTO)
/*
 * skip over binary digits
 */
    char_u *
skipbin(char_u *q)
{
    char_u	*p = q;

    while (vim_isbdigit(*p))	// skip to next non-digit
	++p;
    return p;
}

/*
 * skip over digits and hex characters
 */
    char_u *
skiphex(char_u *q)
{
    char_u	*p = q;

    while (vim_isxdigit(*p))	// skip to next non-digit
	++p;
    return p;
}
#endif

/*
 * skip to bin digit (or NUL after the string)
 */
    char_u *
skiptobin(char_u *q)
{
    char_u	*p = q;

    while (*p != NUL && !vim_isbdigit(*p))	// skip to next digit
	++p;
    return p;
}

/*
 * skip to digit (or NUL after the string)
 */
    char_u *
skiptodigit(char_u *q)
{
    char_u	*p = q;

    while (*p != NUL && !VIM_ISDIGIT(*p))	// skip to next digit
	++p;
    return p;
}

/*
 * skip to hex character (or NUL after the string)
 */
    char_u *
skiptohex(char_u *q)
{
    char_u	*p = q;

    while (*p != NUL && !vim_isxdigit(*p))	// skip to next digit
	++p;
    return p;
}

/*
 * Variant of isdigit() that can handle characters > 0x100.
 * We don't use isdigit() here, because on some systems it also considers
 * superscript 1 to be a digit.
 * Use the VIM_ISDIGIT() macro for simple arguments.
 */
    int
vim_isdigit(int c)
{
    return (c >= '0' && c <= '9');
}

/*
 * Variant of isxdigit() that can handle characters > 0x100.
 * We don't use isxdigit() here, because on some systems it also considers
 * superscript 1 to be a digit.
 */
    int
vim_isxdigit(int c)
{
    return (c >= '0' && c <= '9')
	|| (c >= 'a' && c <= 'f')
	|| (c >= 'A' && c <= 'F');
}

/*
 * Corollary of vim_isdigit and vim_isxdigit() that can handle
 * characters > 0x100.
 */
    int
vim_isbdigit(int c)
{
    return (c == '0' || c == '1');
}

    static int
vim_isodigit(int c)
{
    return (c >= '0' && c <= '7');
}

/*
 * Vim's own character class functions.  These exist because many library
 * islower()/toupper() etc. do not work properly: they crash when used with
 * invalid values or can't handle latin1 when the locale is C.
 * Speed is most important here.
 */
#define LATIN1LOWER 'l'
#define LATIN1UPPER 'U'

static char_u latin1flags[257] = "                                                                 UUUUUUUUUUUUUUUUUUUUUUUUUU      llllllllllllllllllllllllll                                                                     UUUUUUUUUUUUUUUUUUUUUUU UUUUUUUllllllllllllllllllllllll llllllll";
static char_u latin1upper[257] = "                                 !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`ABCDEFGHIJKLMNOPQRSTUVWXYZ{|}~\x7f\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xf7\xd8\xd9\xda\xdb\xdc\xdd\xde\xff";
static char_u latin1lower[257] = "                                 !\"#$%&'()*+,-./0123456789:;<=>?@abcdefghijklmnopqrstuvwxyz[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xd7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff";

    int
vim_islower(int c)
{
    if (c <= '@')
	return FALSE;
    if (c >= 0x80)
    {
	if (enc_utf8)
	    return utf_islower(c);
	if (c >= 0x100)
	{
#ifdef HAVE_ISWLOWER
	    if (has_mbyte)
		return iswlower(c);
#endif
	    // islower() can't handle these chars and may crash
	    return FALSE;
	}
	if (enc_latin1like)
	    return (latin1flags[c] & LATIN1LOWER) == LATIN1LOWER;
    }
    return SAFE_islower(c);
}

    int
vim_isupper(int c)
{
    if (c <= '@')
	return FALSE;
    if (c >= 0x80)
    {
	if (enc_utf8)
	    return utf_isupper(c);
	if (c >= 0x100)
	{
#ifdef HAVE_ISWUPPER
	    if (has_mbyte)
		return iswupper(c);
#endif
	    // islower() can't handle these chars and may crash
	    return FALSE;
	}
	if (enc_latin1like)
	    return (latin1flags[c] & LATIN1UPPER) == LATIN1UPPER;
    }
    return SAFE_isupper(c);
}

    int
vim_isalpha(int c)
{
    return vim_islower(c) || vim_isupper(c);
}

    int
vim_toupper(int c)
{
    if (c <= '@')
	return c;
    if (c >= 0x80 || !(cmp_flags & CMP_KEEPASCII))
    {
	if (enc_utf8)
	    return utf_toupper(c);
	if (c >= 0x100)
	{
#ifdef HAVE_TOWUPPER
	    if (has_mbyte)
		return towupper(c);
#endif
	    // toupper() can't handle these chars and may crash
	    return c;
	}
	if (enc_latin1like)
	    return latin1upper[c];
    }
    if (c < 0x80 && (cmp_flags & CMP_KEEPASCII))
	return TOUPPER_ASC(c);
    return TOUPPER_LOC(c);
}

    int
vim_tolower(int c)
{
    if (c <= '@')
	return c;
    if (c >= 0x80 || !(cmp_flags & CMP_KEEPASCII))
    {
	if (enc_utf8)
	    return utf_tolower(c);
	if (c >= 0x100)
	{
#ifdef HAVE_TOWLOWER
	    if (has_mbyte)
		return towlower(c);
#endif
	    // tolower() can't handle these chars and may crash
	    return c;
	}
	if (enc_latin1like)
	    return latin1lower[c];
    }
    if (c < 0x80 && (cmp_flags & CMP_KEEPASCII))
	return TOLOWER_ASC(c);
    return TOLOWER_LOC(c);
}

/*
 * skiptowhite: skip over text until ' ' or '\t' or NUL.
 */
    char_u *
skiptowhite(char_u *p)
{
    while (*p != ' ' && *p != '\t' && *p != NUL)
	++p;
    return p;
}

/*
 * skiptowhite_esc: Like skiptowhite(), but also skip escaped chars
 */
    char_u *
skiptowhite_esc(char_u *p)
{
    while (*p != ' ' && *p != '\t' && *p != NUL)
    {
	if ((*p == '\\' || *p == Ctrl_V) && *(p + 1) != NUL)
	    ++p;
	++p;
    }
    return p;
}

/*
 * Get a number from a string and skip over it.
 * Note: the argument is a pointer to a char_u pointer!
 */
    long
getdigits(char_u **pp)
{
    char_u	*p;
    long	retval;

    p = *pp;
    retval = atol((char *)p);
    if (*p == '-')		// skip negative sign
	++p;
    p = skipdigits(p);		// skip to next non-digit
    *pp = p;
    return retval;
}

/*
 * Like getdigits() but allow for embedded single quotes.
 */
    long
getdigits_quoted(char_u **pp)
{
    char_u	*p = *pp;
    long	retval = 0;

    if (*p == '-')
	++p;
    while (VIM_ISDIGIT(*p))
    {
	if (retval >= LONG_MAX / 10 - 10)
	    retval = LONG_MAX;
	else
	    retval = retval * 10 - '0' + *p;
	++p;
	if (in_vim9script() && *p == '\'' && VIM_ISDIGIT(p[1]))
	    ++p;
    }
    if (**pp == '-')
    {
	if (retval == LONG_MAX)
	    retval = LONG_MIN;
	else
	    retval = -retval;
    }
    *pp = p;
    return retval;
}

/*
 * Return TRUE if "lbuf" is empty or only contains blanks.
 */
    int
vim_isblankline(char_u *lbuf)
{
    char_u	*p;

    p = skipwhite(lbuf);
    return (*p == NUL || *p == '\r' || *p == '\n');
}

/*
 * Convert a string into a long and/or unsigned long, taking care of
 * hexadecimal, octal, and binary numbers.  Accepts a '-' sign.
 * If "prep" is not NULL, returns a flag to indicate the type of the number:
 *  0	    decimal
 *  '0'	    octal
 *  'O'	    octal
 *  'o'	    octal
 *  'B'	    bin
 *  'b'	    bin
 *  'X'	    hex
 *  'x'	    hex
 * If "len" is not NULL, the length of the number in characters is returned.
 * If "nptr" is not NULL, the signed result is returned in it.
 * If "unptr" is not NULL, the unsigned result is returned in it.
 * If "what" contains STR2NR_BIN recognize binary numbers
 * If "what" contains STR2NR_OCT recognize octal numbers
 * If "what" contains STR2NR_HEX recognize hex numbers
 * If "what" contains STR2NR_FORCE always assume bin/oct/hex.
 * If "what" contains STR2NR_QUOTE ignore embedded single quotes
 * If maxlen > 0, check at a maximum maxlen chars.
 * If strict is TRUE, check the number strictly. return *len = 0 if fail.
 */
    void
vim_str2nr(
    char_u		*start,
    int			*prep,	    // return: type of number 0 = decimal, 'x'
				    // or 'X' is hex, '0', 'o' or 'O' is octal,
				    // 'b' or 'B' is bin
    int			*len,	    // return: detected length of number
    int			what,	    // what numbers to recognize
    varnumber_T		*nptr,	    // return: signed result
    uvarnumber_T	*unptr,	    // return: unsigned result
    int			maxlen,     // max length of string to check
    int			strict,     // check strictly
    int			*overflow)  // when not NULL set to TRUE for overflow
{
    char_u	    *ptr = start;
    int		    pre = 0;		// default is decimal
    int		    negative = FALSE;
    uvarnumber_T    un = 0;
    int		    n;

    if (len != NULL)
	*len = 0;

    if (ptr[0] == '-')
    {
	negative = TRUE;
	++ptr;
    }

    // Recognize hex, octal, and bin.
    if (ptr[0] == '0' && ptr[1] != '8' && ptr[1] != '9'
					       && (maxlen == 0 || maxlen > 1))
    {
	pre = ptr[1];
	if ((what & STR2NR_HEX)
		&& (pre == 'X' || pre == 'x') && vim_isxdigit(ptr[2])
		&& (maxlen == 0 || maxlen > 2))
	    // hexadecimal
	    ptr += 2;
	else if ((what & STR2NR_BIN)
		&& (pre == 'B' || pre == 'b') && vim_isbdigit(ptr[2])
		&& (maxlen == 0 || maxlen > 2))
	    // binary
	    ptr += 2;
	else if ((what & STR2NR_OOCT)
		&& (pre == 'O' || pre == 'o') && vim_isodigit(ptr[2])
		&& (maxlen == 0 || maxlen > 2))
	    // octal with prefix "0o"
	    ptr += 2;
	else
	{
	    // decimal or octal, default is decimal
	    pre = 0;
	    if (what & STR2NR_OCT)
	    {
		// Don't interpret "0", "08" or "0129" as octal.
		for (n = 1; n != maxlen && VIM_ISDIGIT(ptr[n]); ++n)
		{
		    if (ptr[n] > '7')
		    {
			pre = 0;	// can't be octal
			break;
		    }
		    pre = '0';	// assume octal
		}
	    }
	}
    }

    // Do the conversion manually to avoid sscanf() quirks.
    n = 1;
    if (pre == 'B' || pre == 'b'
			     || ((what & STR2NR_BIN) && (what & STR2NR_FORCE)))
    {
	// bin
	if (pre != 0)
	    n += 2;	    // skip over "0b"
	while ('0' <= *ptr && *ptr <= '1')
	{
	    // avoid ubsan error for overflow
	    if (un <= UVARNUM_MAX / 2)
		un = 2 * un + (uvarnumber_T)(*ptr - '0');
	    else
	    {
		un = UVARNUM_MAX;
		if (overflow != NULL)
		    *overflow = TRUE;
	    }
	    ++ptr;
	    if (n++ == maxlen)
		break;
	    if ((what & STR2NR_QUOTE) && *ptr == '\''
					     && '0' <= ptr[1] && ptr[1] <= '1')
	    {
		++ptr;
		if (n++ == maxlen)
		    break;
	    }
	}
    }
    else if (pre == 'O' || pre == 'o' ||
		pre == '0' || ((what & STR2NR_OCT) && (what & STR2NR_FORCE)))
    {
	// octal
	if (pre != 0 && pre != '0')
	    n += 2;	    // skip over "0o"
	while ('0' <= *ptr && *ptr <= '7')
	{
	    // avoid ubsan error for overflow
	    if (un <= UVARNUM_MAX / 8)
		un = 8 * un + (uvarnumber_T)(*ptr - '0');
	    else
	    {
		un = UVARNUM_MAX;
		if (overflow != NULL)
		    *overflow = TRUE;
	    }
	    ++ptr;
	    if (n++ == maxlen)
		break;
	    if ((what & STR2NR_QUOTE) && *ptr == '\''
					     && '0' <= ptr[1] && ptr[1] <= '7')
	    {
		++ptr;
		if (n++ == maxlen)
		    break;
	    }
	}
    }
    else if (pre != 0 || ((what & STR2NR_HEX) && (what & STR2NR_FORCE)))
    {
	// hex
	if (pre != 0)
	    n += 2;	    // skip over "0x"
	while (vim_isxdigit(*ptr))
	{
	    // avoid ubsan error for overflow
	    if (un <= UVARNUM_MAX / 16)
		un = 16 * un + (uvarnumber_T)hex2nr(*ptr);
	    else
	    {
		un = UVARNUM_MAX;
		if (overflow != NULL)
		    *overflow = TRUE;
	    }
	    ++ptr;
	    if (n++ == maxlen)
		break;
	    if ((what & STR2NR_QUOTE) && *ptr == '\'' && vim_isxdigit(ptr[1]))
	    {
		++ptr;
		if (n++ == maxlen)
		    break;
	    }
	}
    }
    else
    {
	// decimal
	while (VIM_ISDIGIT(*ptr))
	{
	    uvarnumber_T    digit = (uvarnumber_T)(*ptr - '0');

	    // avoid ubsan error for overflow
	    if (un < UVARNUM_MAX / 10
		    || (un == UVARNUM_MAX / 10 && digit <= UVARNUM_MAX % 10))
		un = 10 * un + digit;
	    else
	    {
		un = UVARNUM_MAX;
		if (overflow != NULL)
		    *overflow = TRUE;
	    }
	    ++ptr;
	    if (n++ == maxlen)
		break;
	    if ((what & STR2NR_QUOTE) && *ptr == '\'' && VIM_ISDIGIT(ptr[1]))
	    {
		++ptr;
		if (n++ == maxlen)
		    break;
	    }
	}
    }

    // Check for an alphanumeric character immediately following, that is
    // most likely a typo.
    if (strict && n - 1 != maxlen && ASCII_ISALNUM(*ptr))
	return;

    if (prep != NULL)
	*prep = pre;
    if (len != NULL)
	*len = (int)(ptr - start);
    if (nptr != NULL)
    {
	if (negative)   // account for leading '-' for decimal numbers
	{
	    // avoid ubsan error for overflow
	    if (un > VARNUM_MAX)
	    {
		*nptr = VARNUM_MIN;
		if (overflow != NULL)
		    *overflow = TRUE;
	    }
	    else
		*nptr = -(varnumber_T)un;
	}
	else
	{
	    // prevent a large unsigned number to become negative
	    if (un > VARNUM_MAX)
	    {
		un = VARNUM_MAX;
		if (overflow != NULL)
		    *overflow = TRUE;
	    }
	    *nptr = (varnumber_T)un;
	}
    }
    if (unptr != NULL)
	*unptr = un;
}

/*
 * Return the value of a single hex character.
 * Only valid when the argument is '0' - '9', 'A' - 'F' or 'a' - 'f'.
 */
    int
hex2nr(int c)
{
    if (c >= 'a' && c <= 'f')
	return c - 'a' + 10;
    if (c >= 'A' && c <= 'F')
	return c - 'A' + 10;
    return c - '0';
}

/*
 * Convert two hex characters to a byte.
 * Return -1 if one of the characters is not hex.
 */
    int
hexhex2nr(char_u *p)
{
    if (!vim_isxdigit(p[0]) || !vim_isxdigit(p[1]))
	return -1;
    return (hex2nr(p[0]) << 4) + hex2nr(p[1]);
}

/*
 * Return TRUE if "str" starts with a backslash that should be removed.
 * For MS-DOS, MSWIN and OS/2 this is only done when the character after the
 * backslash is not a normal file name character.
 * '$' is a valid file name character, we don't remove the backslash before
 * it.  This means it is not possible to use an environment variable after a
 * backslash.  "C:\$VIM\doc" is taken literally, only "$VIM\doc" works.
 * Although "\ name" is valid, the backslash in "Program\ files" must be
 * removed.  Assume a file name doesn't start with a space.
 * For multi-byte names, never remove a backslash before a non-ascii
 * character, assume that all multi-byte characters are valid file name
 * characters.
 */
    int
rem_backslash(char_u *str)
{
#ifdef BACKSLASH_IN_FILENAME
    return (str[0] == '\\'
	    && str[1] < 0x80
	    && (str[1] == ' '
		|| (str[1] != NUL
		    && str[1] != '*'
		    && str[1] != '?'
		    && !vim_isfilec(str[1]))));
#else
    return (str[0] == '\\' && str[1] != NUL);
#endif
}

/*
 * Halve the number of backslashes in a file name argument.
 * For MS-DOS we only do this if the character after the backslash
 * is not a normal file character.
 */
    void
backslash_halve(char_u *p)
{
    for ( ; *p; ++p)
	if (rem_backslash(p))
	    STRMOVE(p, p + 1);
}

/*
 * backslash_halve() plus save the result in allocated memory.
 * However, returns "p" when out of memory.
 */
    char_u *
backslash_halve_save(char_u *p)
{
    char_u	*res;

    res = vim_strsave(p);
    if (res == NULL)
	return p;
    backslash_halve(res);
    return res;
}