Tcl Source Code

Artifact [18caccb00b]
Login
Bounty program for improvements to Tcl and certain Tcl packages.

Artifact 18caccb00b6196fe42171ccfa9d6088ecf0def9ed39103b56d8587cdd13fbc10:


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
/*
 * tclUtf.c --
 *
 *	Routines for manipulating UTF-8 strings.
 *
 * Copyright (c) 1997-1998 Sun Microsystems, Inc.
 *
 * See the file "license.terms" for information on usage and redistribution of
 * this file, and for a DISCLAIMER OF ALL WARRANTIES.
 */

#include "tclInt.h"

/*
 * Include the static character classification tables and macros.
 */

#include "tclUniData.c"

/*
 * The following macros are used for fast character category tests. The x_BITS
 * values are shifted right by the category value to determine whether the
 * given category is included in the set.
 */

#define ALPHA_BITS ((1 << UPPERCASE_LETTER) | (1 << LOWERCASE_LETTER) \
	| (1 << TITLECASE_LETTER) | (1 << MODIFIER_LETTER) | (1<<OTHER_LETTER))

#define CONTROL_BITS ((1 << CONTROL) | (1 << FORMAT) | (1 << PRIVATE_USE))

#define DIGIT_BITS (1 << DECIMAL_DIGIT_NUMBER)

#define SPACE_BITS ((1 << SPACE_SEPARATOR) | (1 << LINE_SEPARATOR) \
	| (1 << PARAGRAPH_SEPARATOR))

#define WORD_BITS (ALPHA_BITS | DIGIT_BITS | (1 << CONNECTOR_PUNCTUATION))

#define PUNCT_BITS ((1 << CONNECTOR_PUNCTUATION) | \
	(1 << DASH_PUNCTUATION) | (1 << OPEN_PUNCTUATION) | \
	(1 << CLOSE_PUNCTUATION) | (1 << INITIAL_QUOTE_PUNCTUATION) | \
	(1 << FINAL_QUOTE_PUNCTUATION) | (1 << OTHER_PUNCTUATION))

#define GRAPH_BITS (WORD_BITS | PUNCT_BITS | \
	(1 << NON_SPACING_MARK) | (1 << ENCLOSING_MARK) | \
	(1 << COMBINING_SPACING_MARK) | (1 << LETTER_NUMBER) | \
	(1 << OTHER_NUMBER) | \
	(1 << MATH_SYMBOL) | (1 << CURRENCY_SYMBOL) | \
	(1 << MODIFIER_SYMBOL) | (1 << OTHER_SYMBOL))

/*
 * Unicode characters less than this value are represented by themselves in
 * UTF-8 strings.
 */

#define UNICODE_SELF	0x80

/*
 * The following structures are used when mapping between Unicode (UCS-2) and
 * UTF-8.
 */

static const unsigned char totalBytes[256] = {
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
    3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,
#if TCL_UTF_MAX > 3
    4,4,4,4,4,4,4,4,
#else
    1,1,1,1,1,1,1,1,
#endif
    1,1,1,1,1,1,1,1
};

/*
 * Functions used only in this module.
 */

static int		UtfCount(int ch);

/*
 *---------------------------------------------------------------------------
 *
 * UtfCount --
 *
 *	Find the number of bytes in the Utf character "ch".
 *
 * Results:
 *	The return values is the number of bytes in the Utf character "ch".
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */

static inline int
UtfCount(
    int ch)			/* The Unicode character whose size is returned. */
{
    if ((unsigned)(ch - 1) < (UNICODE_SELF - 1)) {
	return 1;
    }
    if (ch <= 0x7FF) {
	return 2;
    }
#if TCL_UTF_MAX > 3
    if (((unsigned)(ch - 0x10000) <= 0xFFFFF)) {
	return 4;
    }
#endif
    return 3;
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UniCharToUtf --
 *
 *	Store the given Tcl_UniChar as a sequence of UTF-8 bytes in the
 *	provided buffer. Equivalent to Plan 9 runetochar().
 *
 * Results:
 *	The return values is the number of bytes in the buffer that were
 *	consumed.
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */

int
Tcl_UniCharToUtf(
    int ch,			/* The Tcl_UniChar to be stored in the
				 * buffer. */
    char *buf)			/* Buffer in which the UTF-8 representation of
				 * the Tcl_UniChar is stored. Buffer must be
				 * large enough to hold the UTF-8 character
				 * (at most TCL_UTF_MAX bytes). */
{
    if ((unsigned)(ch - 1) < (UNICODE_SELF - 1)) {
	buf[0] = (char) ch;
	return 1;
    }
    if (ch >= 0) {
	if (ch <= 0x7FF) {
	    buf[1] = (char) ((ch | 0x80) & 0xBF);
	    buf[0] = (char) ((ch >> 6) | 0xC0);
	    return 2;
	}
	if (ch <= 0xFFFF) {
#if TCL_UTF_MAX > 3
	    if ((ch & 0xF800) == 0xD800) {
		if (ch & 0x0400) {
		    /* Low surrogate */
		    if (((buf[0] & 0xF8) == 0xF0) && ((buf[1] & 0xC0) == 0x80)
			    && ((buf[2] & 0xCF) == 0)) {
			/* Previous Tcl_UniChar was a High surrogate, so combine */
			buf[3] = (char) ((ch & 0x3F) | 0x80);
			buf[2] |= (char) (((ch >> 6) & 0x0F) | 0x80);
			return 4;
		    }
		    /* Previous Tcl_UniChar was not a High surrogate, so just output */
		} else {
		    /* High surrogate */
		    ch += 0x40;
		    /* Fill buffer with specific 3-byte (invalid) byte combination,
		       so following Low surrogate can recognize it and combine */
		    buf[2] = (char) ((ch << 4) & 0x30);
		    buf[1] = (char) (((ch >> 2) & 0x3F) | 0x80);
		    buf[0] = (char) (((ch >> 8) & 0x07) | 0xF0);
		    return 0;
		}
	    }
#endif
	    goto three;
	}

#if TCL_UTF_MAX > 3
	if (ch <= 0x10FFFF) {
	    buf[3] = (char) ((ch | 0x80) & 0xBF);
	    buf[2] = (char) (((ch >> 6) | 0x80) & 0xBF);
	    buf[1] = (char) (((ch >> 12) | 0x80) & 0xBF);
	    buf[0] = (char) ((ch >> 18) | 0xF0);
	    return 4;
	}
#endif
    }

    ch = 0xFFFD;
three:
    buf[2] = (char) ((ch | 0x80) & 0xBF);
    buf[1] = (char) (((ch >> 6) | 0x80) & 0xBF);
    buf[0] = (char) ((ch >> 12) | 0xE0);
    return 3;
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UniCharToUtfDString --
 *
 *	Convert the given Unicode string to UTF-8.
 *
 * Results:
 *	The return value is a pointer to the UTF-8 representation of the
 *	Unicode string. Storage for the return value is appended to the end of
 *	dsPtr.
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */

char *
Tcl_UniCharToUtfDString(
    const Tcl_UniChar *uniStr,	/* Unicode string to convert to UTF-8. */
    int uniLength,		/* Length of Unicode string in Tcl_UniChars
				 * (must be >= 0). */
    Tcl_DString *dsPtr)		/* UTF-8 representation of string is appended
				 * to this previously initialized DString. */
{
    const Tcl_UniChar *w, *wEnd;
    char *p, *string;
    int oldLength;

    /*
     * UTF-8 string length in bytes will be <= Unicode string length *
     * TCL_UTF_MAX.
     */

    oldLength = Tcl_DStringLength(dsPtr);
    Tcl_DStringSetLength(dsPtr, (oldLength + uniLength + 1) * TCL_UTF_MAX);
    string = Tcl_DStringValue(dsPtr) + oldLength;

    p = string;
    wEnd = uniStr + uniLength;
    for (w = uniStr; w < wEnd; ) {
	p += Tcl_UniCharToUtf(*w, p);
	w++;
    }
    Tcl_DStringSetLength(dsPtr, oldLength + (p - string));

    return string;
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfToUniChar --
 *
 *	Extract the Tcl_UniChar represented by the UTF-8 string. Bad UTF-8
 *	sequences are converted to valid Tcl_UniChars and processing
 *	continues. Equivalent to Plan 9 chartorune().
 *
 *	The caller must ensure that the source buffer is long enough that this
 *	routine does not run off the end and dereference non-existent memory
 *	looking for trail bytes. If the source buffer is known to be '\0'
 *	terminated, this cannot happen. Otherwise, the caller should call
 *	Tcl_UtfCharComplete() before calling this routine to ensure that
 *	enough bytes remain in the string.
 *
 *	If TCL_UTF_MAX == 4, special handling of Surrogate pairs is done:
 *	For any UTF-8 string containing a character outside of the BMP, the
 *	first call to this function will fill *chPtr with the high surrogate
 *	and generate a return value of 0. Calling Tcl_UtfToUniChar again
 *	will produce the low surrogate and a return value of 4. Because *chPtr
 *	is used to remember whether the high surrogate is already produced, it
 *	is recommended to initialize the variable it points to as 0 before
 *	the first call to Tcl_UtfToUniChar is done.
 *
 * Results:
 *	*chPtr is filled with the Tcl_UniChar, and the return value is the
 *	number of bytes from the UTF-8 string that were consumed.
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */

int
Tcl_UtfToUniChar(
    register const char *src,	/* The UTF-8 string. */
    register Tcl_UniChar *chPtr)/* Filled with the Tcl_UniChar represented by
				 * the UTF-8 string. */
{
    register int byte;

    /*
     * Unroll 1 to 3 (or 4) byte UTF-8 sequences.
     */

    byte = *((unsigned char *) src);
    if (byte < 0xC0) {
	/*
	 * Handles properly formed UTF-8 characters between 0x01 and 0x7F.
	 * Also treats \0 and naked trail bytes 0x80 to 0xBF as valid
	 * characters representing themselves.
	 */

	*chPtr = (Tcl_UniChar) byte;
	return 1;
    } else if (byte < 0xE0) {
	if ((src[1] & 0xC0) == 0x80) {
	    /*
	     * Two-byte-character lead-byte followed by a trail-byte.
	     */

	    *chPtr = (Tcl_UniChar) (((byte & 0x1F) << 6) | (src[1] & 0x3F));
	    if ((unsigned)(*chPtr - 1) >= (UNICODE_SELF - 1)) {
		return 2;
	    }
	}

	/*
	 * A two-byte-character lead-byte not followed by trail-byte
	 * represents itself.
	 */
    } else if (byte < 0xF0) {
	if (((src[1] & 0xC0) == 0x80) && ((src[2] & 0xC0) == 0x80)) {
	    /*
	     * Three-byte-character lead byte followed by two trail bytes.
	     */

	    *chPtr = (Tcl_UniChar) (((byte & 0x0F) << 12)
		    | ((src[1] & 0x3F) << 6) | (src[2] & 0x3F));
	    if (*chPtr > 0x7FF) {
		return 3;
	    }
	}

	/*
	 * A three-byte-character lead-byte not followed by two trail-bytes
	 * represents itself.
	 */
    }
#if TCL_UTF_MAX > 3
    else if (byte < 0xF8) {
	if (((src[1] & 0xC0) == 0x80) && ((src[2] & 0xC0) == 0x80) && ((src[3] & 0xC0) == 0x80)) {
	    /*
	     * Four-byte-character lead byte followed by three trail bytes.
	     */
#if TCL_UTF_MAX == 4
	    Tcl_UniChar surrogate;

	    byte = (((byte & 0x07) << 18) | ((src[1] & 0x3F) << 12)
		    | ((src[2] & 0x3F) << 6) | (src[3] & 0x3F)) - 0x10000;
	    surrogate = (Tcl_UniChar) (0xD800 + (byte >> 10));
	    if (byte & 0x100000) {
		/* out of range, < 0x10000 or > 0x10ffff */
	    } else if (*chPtr != surrogate) {
		/* produce high surrogate, but don't advance source pointer */
		*chPtr = surrogate;
		return 0;
	    } else {
		/* produce low surrogate, and advance source pointer */
		*chPtr = (Tcl_UniChar) (0xDC00 | (byte & 0x3FF));
		return 4;
	    }
#else
	    *chPtr = (Tcl_UniChar) (((byte & 0x07) << 18) | ((src[1] & 0x3F) << 12)
		    | ((src[2] & 0x3F) << 6) | (src[3] & 0x3F));
	    if ((unsigned)(*chPtr - 0x10000) <= 0xFFFFF) {
		return 4;
	    }
#endif
	}

	/*
	 * A four-byte-character lead-byte not followed by two trail-bytes
	 * represents itself.
	 */
    }
#endif

    *chPtr = (Tcl_UniChar) byte;
    return 1;
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfToUniCharDString --
 *
 *	Convert the UTF-8 string to Unicode.
 *
 * Results:
 *	The return value is a pointer to the Unicode representation of the
 *	UTF-8 string. Storage for the return value is appended to the end of
 *	dsPtr. The Unicode string is terminated with a Unicode NULL character.
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */

Tcl_UniChar *
Tcl_UtfToUniCharDString(
    const char *src,		/* UTF-8 string to convert to Unicode. */
    int length,			/* Length of UTF-8 string in bytes, or -1 for
				 * strlen(). */
    Tcl_DString *dsPtr)		/* Unicode representation of string is
				 * appended to this previously initialized
				 * DString. */
{
    Tcl_UniChar ch = 0, *w, *wString;
    const char *p, *end;
    int oldLength;

    if (length < 0) {
	length = strlen(src);
    }

    /*
     * Unicode string length in Tcl_UniChars will be <= UTF-8 string length in
     * bytes.
     */

    oldLength = Tcl_DStringLength(dsPtr);
/* TODO: fix overreach! */
    Tcl_DStringSetLength(dsPtr,
	    (int) ((oldLength + length + 1) * sizeof(Tcl_UniChar)));
    wString = (Tcl_UniChar *) (Tcl_DStringValue(dsPtr) + oldLength);

    w = wString;
    end = src + length;
    for (p = src; p < end; ) {
	p += TclUtfToUniChar(p, &ch);
	*w++ = ch;
    }
    *w = '\0';
    Tcl_DStringSetLength(dsPtr,
	    (oldLength + ((char *) w - (char *) wString)));

    return wString;
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfCharComplete --
 *
 *	Determine if the UTF-8 string of the given length is long enough to be
 *	decoded by Tcl_UtfToUniChar(). This does not ensure that the UTF-8
 *	string is properly formed. Equivalent to Plan 9 fullrune().
 *
 * Results:
 *	The return value is 0 if the string is not long enough, non-zero
 *	otherwise.
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */

int
Tcl_UtfCharComplete(
    const char *src,		/* String to check if first few bytes contain
				 * a complete UTF-8 character. */
    int length)			/* Length of above string in bytes. */
{
    return length >= totalBytes[(unsigned char)*src];
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_NumUtfChars --
 *
 *	Returns the number of characters (not bytes) in the UTF-8 string, not
 *	including the terminating NULL byte. This is equivalent to Plan 9
 *	utflen() and utfnlen().
 *
 * Results:
 *	As above.
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */

int
Tcl_NumUtfChars(
    register const char *src,	/* The UTF-8 string to measure. */
    int length)			/* The length of the string in bytes, or -1
				 * for strlen(string). */
{
    Tcl_UniChar ch = 0;
    register int i = 0;

    /*
     * The separate implementations are faster.
     *
     * Since this is a time-sensitive function, we also do the check for the
     * single-byte char case specially.
     */

    if (length < 0) {
	while (*src != '\0') {
	    src += TclUtfToUniChar(src, &ch);
	    i++;
	}
	if (i < 0) i = INT_MAX; /* Bug [2738427] */
    } else {
	register const char *endPtr = src + length - TCL_UTF_MAX;

	while (src < endPtr) {
	    src += TclUtfToUniChar(src, &ch);
	    i++;
	}
	endPtr += TCL_UTF_MAX;
	while ((src < endPtr) && Tcl_UtfCharComplete(src, endPtr - src)) {
	    src += TclUtfToUniChar(src, &ch);
	    i++;
	}
	if (src < endPtr) {
	    i += endPtr - src;
	}
    }
    return i;
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfFindFirst --
 *
 *	Returns a pointer to the first occurance of the given Unicode character
 *	in the NULL-terminated UTF-8 string. The NULL terminator is considered
 *	part of the UTF-8 string. Equivalent to Plan 9 utfrune().
 *
 * Results:
 *	As above. If the Unicode character does not exist in the given string,
 *	the return value is NULL.
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */

const char *
Tcl_UtfFindFirst(
    const char *src,		/* The UTF-8 string to be searched. */
    int ch)			/* The Unicode character to search for. */
{
    int len, fullchar;
    Tcl_UniChar find = 0;

    while (1) {
	len = TclUtfToUniChar(src, &find);
	fullchar = find;
#if TCL_UTF_MAX == 4
	if (!len) {
	    len += TclUtfToUniChar(src, &find);
	    fullchar = (((fullchar & 0x3ff) << 10) | (find & 0x3ff)) + 0x10000;
	}
#endif
	if (fullchar == ch) {
	    return src;
	}
	if (*src == '\0') {
	    return NULL;
	}
	src += len;
    }
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfFindLast --
 *
 *	Returns a pointer to the last occurance of the given Unicode character
 *	in the NULL-terminated UTF-8 string. The NULL terminator is considered
 *	part of the UTF-8 string. Equivalent to Plan 9 utfrrune().
 *
 * Results:
 *	As above. If the Unicode character does not exist in the given string, the
 *	return value is NULL.
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */

const char *
Tcl_UtfFindLast(
    const char *src,		/* The UTF-8 string to be searched. */
    int ch)			/* The Unicode character to search for. */
{
    int len, fullchar;
    Tcl_UniChar find = 0;
    const char *last;

    last = NULL;
    while (1) {
	len = TclUtfToUniChar(src, &find);
	fullchar = find;
#if TCL_UTF_MAX == 4
	if (!len) {
	    len += TclUtfToUniChar(src, &find);
	    fullchar = (((fullchar & 0x3ff) << 10) | (find & 0x3ff)) + 0x10000;
	}
#endif
	if (fullchar == ch) {
	    last = src;
	}
	if (*src == '\0') {
	    break;
	}
	src += len;
    }
    return last;
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfNext --
 *
 *	Given a pointer to some current location in a UTF-8 string, move
 *	forward one character. The caller must ensure that they are not asking
 *	for the next character after the last character in the string.
 *
 * Results:
 *	The return value is the pointer to the next character in the UTF-8
 *	string.
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */

const char *
Tcl_UtfNext(
    const char *src)		/* The current location in the string. */
{
    Tcl_UniChar ch = 0;
    int len = TclUtfToUniChar(src, &ch);

#if TCL_UTF_MAX == 4
    if (len == 0) {
      len = TclUtfToUniChar(src, &ch);
    }
#endif
    return src + len;
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfPrev --
 *
 *	Given a pointer to some current location in a UTF-8 string, move
 *	backwards one character. This works correctly when the pointer is in
 *	the middle of a UTF-8 character.
 *
 * Results:
 *	The return value is a pointer to the previous character in the UTF-8
 *	string. If the current location was already at the beginning of the
 *	string, the return value will also be a pointer to the beginning of
 *	the string.
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */

const char *
Tcl_UtfPrev(
    const char *src,		/* The current location in the string. */
    const char *start)		/* Pointer to the beginning of the string, to
				 * avoid going backwards too far. */
{
    const char *look;
    int i, byte;

    look = --src;
    for (i = 0; i < TCL_UTF_MAX; i++) {
	if (look < start) {
	    if (src < start) {
		src = start;
	    }
	    break;
	}
	byte = *((unsigned char *) look);
	if (byte < 0x80) {
	    break;
	}
	if (byte >= 0xC0) {
	    return look;
	}
	look--;
    }
    return src;
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UniCharAtIndex --
 *
 *	Returns the Tcl_UniChar represented at the specified character
 *	(not byte) position in the UTF-8 string.
 *
 * Results:
 *	As above.
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */

Tcl_UniChar
Tcl_UniCharAtIndex(
    register const char *src,	/* The UTF-8 string to dereference. */
    register int index)		/* The position of the desired character. */
{
    Tcl_UniChar ch = 0;

    while (index-- >= 0) {
	src += TclUtfToUniChar(src, &ch);
    }
    return ch;
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfAtIndex --
 *
 *	Returns a pointer to the specified character (not byte) position in
 *	the UTF-8 string.
 *
 * Results:
 *	As above.
 *
 * Side effects:
 *	None.
 *
 *---------------------------------------------------------------------------
 */

const char *
Tcl_UtfAtIndex(
    register const char *src,	/* The UTF-8 string. */
    register int index)		/* The position of the desired character. */
{
    Tcl_UniChar ch = 0;
    int len = 1;

    while (index-- > 0) {
	len = TclUtfToUniChar(src, &ch);
	src += len;
    }
#if TCL_UTF_MAX == 4
     if (!len) {
	/* Index points at character following High Surrogate */
	src += TclUtfToUniChar(src, &ch);
    }
#endif
    return src;
}

/*
 *---------------------------------------------------------------------------
 *
 * Tcl_UtfBackslash --
 *
 *	Figure out how to handle a backslash sequence.
 *
 * Results:
 *	Stores the bytes represented by the backslash sequence in dst and
 *	returns the number of bytes written to dst. At most TCL_UTF_MAX bytes
 *	are written to dst; dst must have been large enough to accept those
 *	bytes. If readPtr isn't NULL then it is filled in with a count of the
 *	number of bytes in the backslash sequence.
 *
 * Side effects:
 *	The maximum number of bytes it takes to represent a Unicode character
 *	in UTF-8 is guaranteed to be less than the number of bytes used to
 *	express the backslash sequence that represents that Unicode character.
 *	If the target buffer into which the caller is going to store the bytes
 *	that represent the Unicode character is at least as large as the
 *	source buffer from which the backslashed sequence was extracted, no
 *	buffer overruns should occur.
 *
 *---------------------------------------------------------------------------
 */

int
Tcl_UtfBackslash(
    const char *src,		/* Points to the backslash character of a
				 * backslash sequence. */
    int *readPtr,		/* Fill in with number of characters read from
				 * src, unless NULL. */
    char *dst)			/* Filled with the bytes represented by the
				 * backslash sequence. */
{
#define LINE_LENGTH 128
    int numRead;
    int result;

    result = TclParseBackslash(src, LINE_LENGTH, &numRead, dst);
    if (numRead == LINE_LENGTH) {
	/*
	 * We ate a whole line. Pay the price of a strlen()
	 */

	result = TclParseBackslash(src, (int)strlen(src), &numRead, dst);
    }
    if (readPtr != NULL) {
	*readPtr = numRead;
    }
    return result;
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UtfToUpper --
 *
 *	Convert lowercase characters to uppercase characters in a UTF string
 *	in place. The conversion may shrink the UTF string.
 *
 * Results:
 *	Returns the number of bytes in the resulting string excluding the
 *	trailing null.
 *
 * Side effects:
 *	Writes a terminating null after the last converted character.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UtfToUpper(
    char *str)			/* String to convert in place. */
{
    Tcl_UniChar ch = 0, upChar;
    char *src, *dst;
    int bytes;

    /*
     * Iterate over the string until we hit the terminating null.
     */

    src = dst = str;
    while (*src) {
	bytes = TclUtfToUniChar(src, &ch);
	upChar = Tcl_UniCharToUpper(ch);

	/*
	 * To keep badly formed Utf strings from getting inflated by the
	 * conversion (thereby causing a segfault), only copy the upper case
	 * char to dst if its size is <= the original char.
	 */

	if (bytes < UtfCount(upChar)) {
	    memcpy(dst, src, (size_t) bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(upChar, dst);
	}
	src += bytes;
    }
    *dst = '\0';
    return (dst - str);
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UtfToLower --
 *
 *	Convert uppercase characters to lowercase characters in a UTF string
 *	in place. The conversion may shrink the UTF string.
 *
 * Results:
 *	Returns the number of bytes in the resulting string excluding the
 *	trailing null.
 *
 * Side effects:
 *	Writes a terminating null after the last converted character.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UtfToLower(
    char *str)			/* String to convert in place. */
{
    Tcl_UniChar ch = 0, lowChar;
    char *src, *dst;
    int bytes;

    /*
     * Iterate over the string until we hit the terminating null.
     */

    src = dst = str;
    while (*src) {
	bytes = TclUtfToUniChar(src, &ch);
	lowChar = Tcl_UniCharToLower(ch);

	/*
	 * To keep badly formed Utf strings from getting inflated by the
	 * conversion (thereby causing a segfault), only copy the lower case
	 * char to dst if its size is <= the original char.
	 */

	if (bytes < UtfCount(lowChar)) {
	    memcpy(dst, src, (size_t) bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(lowChar, dst);
	}
	src += bytes;
    }
    *dst = '\0';
    return (dst - str);
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UtfToTitle --
 *
 *	Changes the first character of a UTF string to title case or uppercase
 *	and the rest of the string to lowercase. The conversion happens in
 *	place and may shrink the UTF string.
 *
 * Results:
 *	Returns the number of bytes in the resulting string excluding the
 *	trailing null.
 *
 * Side effects:
 *	Writes a terminating null after the last converted character.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UtfToTitle(
    char *str)			/* String to convert in place. */
{
    Tcl_UniChar ch = 0, titleChar, lowChar;
    char *src, *dst;
    int bytes;

    /*
     * Capitalize the first character and then lowercase the rest of the
     * characters until we get to a null.
     */

    src = dst = str;

    if (*src) {
	bytes = TclUtfToUniChar(src, &ch);
	titleChar = Tcl_UniCharToTitle(ch);

	if (bytes < UtfCount(titleChar)) {
	    memcpy(dst, src, (size_t) bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(titleChar, dst);
	}
	src += bytes;
    }
    while (*src) {
	bytes = TclUtfToUniChar(src, &ch);
	lowChar = ch;
	/* Special exception for Georgian Asomtavruli chars, no titlecase. */
	if ((unsigned)(lowChar - 0x1C90) >= 0x30) {
	    lowChar = Tcl_UniCharToLower(lowChar);
	}

	if (bytes < UtfCount(lowChar)) {
	    memcpy(dst, src, (size_t) bytes);
	    dst += bytes;
	} else {
	    dst += Tcl_UniCharToUtf(lowChar, dst);
	}
	src += bytes;
    }
    *dst = '\0';
    return (dst - str);
}

/*
 *----------------------------------------------------------------------
 *
 * TclpUtfNcmp2 --
 *
 *	Compare at most numBytes bytes of utf-8 strings cs and ct. Both cs and
 *	ct are assumed to be at least numBytes bytes long.
 *
 * Results:
 *	Return <0 if cs < ct, 0 if cs == ct, or >0 if cs > ct.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
TclpUtfNcmp2(
    const char *cs,		/* UTF string to compare to ct. */
    const char *ct,		/* UTF string cs is compared to. */
    unsigned long numBytes)	/* Number of *bytes* to compare. */
{
    /*
     * We can't simply call 'memcmp(cs, ct, numBytes);' because we need to
     * check for Tcl's \xC0\x80 non-utf-8 null encoding. Otherwise utf-8 lexes
     * fine in the strcmp manner.
     */

    register int result = 0;

    for ( ; numBytes != 0; numBytes--, cs++, ct++) {
	if (*cs != *ct) {
	    result = UCHAR(*cs) - UCHAR(*ct);
	    break;
	}
    }
    if (numBytes && ((UCHAR(*cs) == 0xC0) || (UCHAR(*ct) == 0xC0))) {
	unsigned char c1, c2;

	c1 = ((UCHAR(*cs) == 0xC0) && (UCHAR(cs[1]) == 0x80)) ? 0 : UCHAR(*cs);
	c2 = ((UCHAR(*ct) == 0xC0) && (UCHAR(ct[1]) == 0x80)) ? 0 : UCHAR(*ct);
	result = (c1 - c2);
    }
    return result;
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UtfNcmp --
 *
 *	Compare at most numChars UTF chars of string cs to string ct. Both cs
 *	and ct are assumed to be at least numChars UTF chars long.
 *
 * Results:
 *	Return <0 if cs < ct, 0 if cs == ct, or >0 if cs > ct.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UtfNcmp(
    const char *cs,		/* UTF string to compare to ct. */
    const char *ct,		/* UTF string cs is compared to. */
    unsigned long numChars)	/* Number of UTF chars to compare. */
{
    Tcl_UniChar ch1 = 0, ch2 = 0;

    /*
     * Cannot use 'memcmp(cs, ct, n);' as byte representation of \u0000 (the
     * pair of bytes 0xC0,0x80) is larger than byte representation of \u0001
     * (the byte 0x01.)
     */

    while (numChars-- > 0) {
	/*
	 * n must be interpreted as chars, not bytes. This should be called
	 * only when both strings are of at least n chars long (no need for \0
	 * check)
	 */

	cs += TclUtfToUniChar(cs, &ch1);
	ct += TclUtfToUniChar(ct, &ch2);
	if (ch1 != ch2) {
#if TCL_UTF_MAX == 4
	    /* Surrogates always report higher than non-surrogates */
	    if (((ch1 & 0xFC00) == 0xD800)) {
	    if ((ch2 & 0xFC00) != 0xD800) {
		return ch1;
	    }
	    } else if ((ch2 & 0xFC00) == 0xD800) {
		return -ch2;
	    }
#endif
	    return (ch1 - ch2);
	}
    }
    return 0;
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UtfNcasecmp --
 *
 *	Compare at most numChars UTF chars of string cs to string ct case
 *	insensitive. Both cs and ct are assumed to be at least numChars UTF
 *	chars long.
 *
 * Results:
 *	Return <0 if cs < ct, 0 if cs == ct, or >0 if cs > ct.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UtfNcasecmp(
    const char *cs,		/* UTF string to compare to ct. */
    const char *ct,		/* UTF string cs is compared to. */
    unsigned long numChars)	/* Number of UTF chars to compare. */
{
    Tcl_UniChar ch1 = 0, ch2 = 0;

    while (numChars-- > 0) {
	/*
	 * n must be interpreted as chars, not bytes.
	 * This should be called only when both strings are of
	 * at least n chars long (no need for \0 check)
	 */
	cs += TclUtfToUniChar(cs, &ch1);
	ct += TclUtfToUniChar(ct, &ch2);
	if (ch1 != ch2) {
#if TCL_UTF_MAX == 4
	    /* Surrogates always report higher than non-surrogates */
	    if (((ch1 & 0xFC00) == 0xD800)) {
	    if ((ch2 & 0xFC00) != 0xD800) {
		return ch1;
	    }
	    } else if ((ch2 & 0xFC00) == 0xD800) {
		return -ch2;
	    }
#endif
	    ch1 = Tcl_UniCharToLower(ch1);
	    ch2 = Tcl_UniCharToLower(ch2);
	    if (ch1 != ch2) {
		return (ch1 - ch2);
	    }
	}
    }
    return 0;
}

/*
 *----------------------------------------------------------------------
 *
 * TclUtfCasecmp --
 *
 *	Compare UTF chars of string cs to string ct case insensitively.
 *	Replacement for strcasecmp in Tcl core, in places where UTF-8 should
 *	be handled.
 *
 * Results:
 *	Return <0 if cs < ct, 0 if cs == ct, or >0 if cs > ct.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
TclUtfCasecmp(
    const char *cs,		/* UTF string to compare to ct. */
    const char *ct)		/* UTF string cs is compared to. */
{
    Tcl_UniChar ch1 = 0, ch2 = 0;

    while (*cs && *ct) {
	cs += TclUtfToUniChar(cs, &ch1);
	ct += TclUtfToUniChar(ct, &ch2);
	if (ch1 != ch2) {
#if TCL_UTF_MAX == 4
	    /* Surrogates always report higher than non-surrogates */
	    if (((ch1 & 0xFC00) == 0xD800)) {
	    if ((ch2 & 0xFC00) != 0xD800) {
		return ch1;
	    }
	    } else if ((ch2 & 0xFC00) == 0xD800) {
		return -ch2;
	    }
#endif
	    ch1 = Tcl_UniCharToLower(ch1);
	    ch2 = Tcl_UniCharToLower(ch2);
	    if (ch1 != ch2) {
		return ch1 - ch2;
	    }
	}
    }
    return UCHAR(*cs) - UCHAR(*ct);
}


/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharToUpper --
 *
 *	Compute the uppercase equivalent of the given Unicode character.
 *
 * Results:
 *	Returns the uppercase Unicode character.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

Tcl_UniChar
Tcl_UniCharToUpper(
    int ch)			/* Unicode character to convert. */
{
    int info = GetUniCharInfo(ch);

    if (GetCaseType(info) & 0x04) {
	ch -= GetDelta(info);
    }
    return (Tcl_UniChar) ch;
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharToLower --
 *
 *	Compute the lowercase equivalent of the given Unicode character.
 *
 * Results:
 *	Returns the lowercase Unicode character.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

Tcl_UniChar
Tcl_UniCharToLower(
    int ch)			/* Unicode character to convert. */
{
    int info = GetUniCharInfo(ch);
    int mode = GetCaseType(info);

    if ((mode & 0x02) && (mode != 0x7)) {
	ch += GetDelta(info);
    }
    return (Tcl_UniChar) ch;
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharToTitle --
 *
 *	Compute the titlecase equivalent of the given Unicode character.
 *
 * Results:
 *	Returns the titlecase Unicode character.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

Tcl_UniChar
Tcl_UniCharToTitle(
    int ch)			/* Unicode character to convert. */
{
    int info = GetUniCharInfo(ch);
    int mode = GetCaseType(info);

    if (mode & 0x1) {
	/*
	 * Subtract or add one depending on the original case.
	 */

	if (mode != 0x7) {
	    ch += ((mode & 0x4) ? -1 : 1);
	}
    } else if (mode == 0x4) {
	ch -= GetDelta(info);
    }
    return (Tcl_UniChar) ch;
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharLen --
 *
 *	Find the length of a UniChar string. The str input must be null
 *	terminated.
 *
 * Results:
 *	Returns the length of str in UniChars (not bytes).
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharLen(
    const Tcl_UniChar *uniStr)	/* Unicode string to find length of. */
{
    int len = 0;

    while (*uniStr != '\0') {
	len++;
	uniStr++;
    }
    return len;
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharNcmp --
 *
 *	Compare at most numChars unichars of string ucs to string uct.
 *	Both ucs and uct are assumed to be at least numChars unichars long.
 *
 * Results:
 *	Return <0 if ucs < uct, 0 if ucs == uct, or >0 if ucs > uct.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharNcmp(
    const Tcl_UniChar *ucs,	/* Unicode string to compare to uct. */
    const Tcl_UniChar *uct,	/* Unicode string ucs is compared to. */
    unsigned long numChars)	/* Number of unichars to compare. */
{
#ifdef WORDS_BIGENDIAN
    /*
     * We are definitely on a big-endian machine; memcmp() is safe
     */

    return memcmp(ucs, uct, numChars*sizeof(Tcl_UniChar));

#else /* !WORDS_BIGENDIAN */
    /*
     * We can't simply call memcmp() because that is not lexically correct.
     */

    for ( ; numChars != 0; ucs++, uct++, numChars--) {
	if (*ucs != *uct) {
	    return (*ucs - *uct);
	}
    }
    return 0;
#endif /* WORDS_BIGENDIAN */
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharNcasecmp --
 *
 *	Compare at most numChars unichars of string ucs to string uct case
 *	insensitive. Both ucs and uct are assumed to be at least numChars
 *	unichars long.
 *
 * Results:
 *	Return <0 if ucs < uct, 0 if ucs == uct, or >0 if ucs > uct.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharNcasecmp(
    const Tcl_UniChar *ucs,	/* Unicode string to compare to uct. */
    const Tcl_UniChar *uct,	/* Unicode string ucs is compared to. */
    unsigned long numChars)	/* Number of unichars to compare. */
{
    for ( ; numChars != 0; numChars--, ucs++, uct++) {
	if (*ucs != *uct) {
	    Tcl_UniChar lcs = Tcl_UniCharToLower(*ucs);
	    Tcl_UniChar lct = Tcl_UniCharToLower(*uct);

	    if (lcs != lct) {
		return (lcs - lct);
	    }
	}
    }
    return 0;
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsAlnum --
 *
 *	Test if a character is an alphanumeric Unicode character.
 *
 * Results:
 *	Returns 1 if character is alphanumeric.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsAlnum(
    int ch)			/* Unicode character to test. */
{
#if TCL_UTF_MAX > 3
    if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
    }
#endif
    return (((ALPHA_BITS | DIGIT_BITS) >> GetCategory(ch)) & 1);
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsAlpha --
 *
 *	Test if a character is an alphabetic Unicode character.
 *
 * Results:
 *	Returns 1 if character is alphabetic.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsAlpha(
    int ch)			/* Unicode character to test. */
{
#if TCL_UTF_MAX > 3
    if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
    }
#endif
    return ((ALPHA_BITS >> GetCategory(ch)) & 1);
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsControl --
 *
 *	Test if a character is a Unicode control character.
 *
 * Results:
 *	Returns non-zero if character is a control.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsControl(
    int ch)			/* Unicode character to test. */
{
#if TCL_UTF_MAX > 3
    if (UNICODE_OUT_OF_RANGE(ch)) {
	ch &= 0x1FFFFF;
	if ((ch == 0xE0001) || ((ch >= 0xE0020) && (ch <= 0xE007f))) {
	    return 1;
	}
	if ((ch >= 0xF0000) && ((ch & 0xFFFF) <= 0xFFFD)) {
	    return 1;
	}
	return 0;
    }
#endif
    return ((CONTROL_BITS >> GetCategory(ch)) & 1);
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsDigit --
 *
 *	Test if a character is a numeric Unicode character.
 *
 * Results:
 *	Returns non-zero if character is a digit.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsDigit(
    int ch)			/* Unicode character to test. */
{
#if TCL_UTF_MAX > 3
    if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
    }
#endif
    return (GetCategory(ch) == DECIMAL_DIGIT_NUMBER);
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsGraph --
 *
 *	Test if a character is any Unicode print character except space.
 *
 * Results:
 *	Returns non-zero if character is printable, but not space.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsGraph(
    int ch)			/* Unicode character to test. */
{
#if TCL_UTF_MAX > 3
    if (UNICODE_OUT_OF_RANGE(ch)) {
	ch &= 0x1FFFFF;
	return (ch >= 0xE0100) && (ch <= 0xE01EF);
    }
#endif
    return ((GRAPH_BITS >> GetCategory(ch)) & 1);
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsLower --
 *
 *	Test if a character is a lowercase Unicode character.
 *
 * Results:
 *	Returns non-zero if character is lowercase.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsLower(
    int ch)			/* Unicode character to test. */
{
#if TCL_UTF_MAX > 3
    if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
    }
#endif
    return (GetCategory(ch) == LOWERCASE_LETTER);
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsPrint --
 *
 *	Test if a character is a Unicode print character.
 *
 * Results:
 *	Returns non-zero if character is printable.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsPrint(
    int ch)			/* Unicode character to test. */
{
#if TCL_UTF_MAX > 3
    if (UNICODE_OUT_OF_RANGE(ch)) {
	ch &= 0x1FFFFF;
	return (ch >= 0xE0100) && (ch <= 0xE01EF);
    }
#endif
    return (((GRAPH_BITS|SPACE_BITS) >> GetCategory(ch)) & 1);
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsPunct --
 *
 *	Test if a character is a Unicode punctuation character.
 *
 * Results:
 *	Returns non-zero if character is punct.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsPunct(
    int ch)			/* Unicode character to test. */
{
#if TCL_UTF_MAX > 3
    if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
    }
#endif
    return ((PUNCT_BITS >> GetCategory(ch)) & 1);
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsSpace --
 *
 *	Test if a character is a whitespace Unicode character.
 *
 * Results:
 *	Returns non-zero if character is a space.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsSpace(
    int ch)			/* Unicode character to test. */
{
#if TCL_UTF_MAX > 3
    /* Ignore upper 11 bits. */
    ch &= 0x1FFFFF;
#else
    /* Ignore upper 16 bits. */
    ch &= 0xFFFF;
#endif

    /*
     * If the character is within the first 127 characters, just use the
     * standard C function, otherwise consult the Unicode table.
     */

    if (ch < 0x80) {
	return TclIsSpaceProc((char) ch);
#if TCL_UTF_MAX > 3
    } else if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
#endif
    } else if (ch == 0x0085 || ch == 0x180E || ch == 0x200B
	    || ch == 0x202F || ch == 0x2060 || ch == 0xFEFF) {
	return 1;
    } else {
	return ((SPACE_BITS >> GetCategory(ch)) & 1);
    }
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsUpper --
 *
 *	Test if a character is a uppercase Unicode character.
 *
 * Results:
 *	Returns non-zero if character is uppercase.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsUpper(
    int ch)			/* Unicode character to test. */
{
#if TCL_UTF_MAX > 3
    if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
    }
#endif
    return (GetCategory(ch) == UPPERCASE_LETTER);
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharIsWordChar --
 *
 *	Test if a character is alphanumeric or a connector punctuation mark.
 *
 * Results:
 *	Returns 1 if character is a word character.
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharIsWordChar(
    int ch)			/* Unicode character to test. */
{
#if TCL_UTF_MAX > 3
    if (UNICODE_OUT_OF_RANGE(ch)) {
	return 0;
    }
#endif
    return ((WORD_BITS >> GetCategory(ch)) & 1);
}

/*
 *----------------------------------------------------------------------
 *
 * Tcl_UniCharCaseMatch --
 *
 *	See if a particular Unicode string matches a particular pattern.
 *	Allows case insensitivity. This is the Unicode equivalent of the char*
 *	Tcl_StringCaseMatch. The UniChar strings must be NULL-terminated.
 *	This has no provision for counted UniChar strings, thus should not be
 *	used where NULLs are expected in the UniChar string. Use
 *	TclUniCharMatch where possible.
 *
 * Results:
 *	The return value is 1 if string matches pattern, and 0 otherwise. The
 *	matching operation permits the following special characters in the
 *	pattern: *?\[] (see the manual entry for details on what these mean).
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
Tcl_UniCharCaseMatch(
    const Tcl_UniChar *uniStr,	/* Unicode String. */
    const Tcl_UniChar *uniPattern,
				/* Pattern, which may contain special
				 * characters. */
    int nocase)			/* 0 for case sensitive, 1 for insensitive */
{
    Tcl_UniChar ch1 = 0, p;

    while (1) {
	p = *uniPattern;

	/*
	 * See if we're at the end of both the pattern and the string. If so,
	 * we succeeded. If we're at the end of the pattern but not at the end
	 * of the string, we failed.
	 */

	if (p == 0) {
	    return (*uniStr == 0);
	}
	if ((*uniStr == 0) && (p != '*')) {
	    return 0;
	}

	/*
	 * Check for a "*" as the next pattern character. It matches any
	 * substring. We handle this by skipping all the characters up to the
	 * next matching one in the pattern, and then calling ourselves
	 * recursively for each postfix of string, until either we match or we
	 * reach the end of the string.
	 */

	if (p == '*') {
	    /*
	     * Skip all successive *'s in the pattern
	     */

	    while (*(++uniPattern) == '*') {
		/* empty body */
	    }
	    p = *uniPattern;
	    if (p == 0) {
		return 1;
	    }
	    if (nocase) {
		p = Tcl_UniCharToLower(p);
	    }
	    while (1) {
		/*
		 * Optimization for matching - cruise through the string
		 * quickly if the next char in the pattern isn't a special
		 * character
		 */

		if ((p != '[') && (p != '?') && (p != '\\')) {
		    if (nocase) {
			while (*uniStr && (p != *uniStr)
				&& (p != Tcl_UniCharToLower(*uniStr))) {
			    uniStr++;
			}
		    } else {
			while (*uniStr && (p != *uniStr)) {
			    uniStr++;
			}
		    }
		}
		if (Tcl_UniCharCaseMatch(uniStr, uniPattern, nocase)) {
		    return 1;
		}
		if (*uniStr == 0) {
		    return 0;
		}
		uniStr++;
	    }
	}

	/*
	 * Check for a "?" as the next pattern character. It matches any
	 * single character.
	 */

	if (p == '?') {
	    uniPattern++;
	    uniStr++;
	    continue;
	}

	/*
	 * Check for a "[" as the next pattern character. It is followed by a
	 * list of characters that are acceptable, or by a range (two
	 * characters separated by "-").
	 */

	if (p == '[') {
	    Tcl_UniChar startChar, endChar;

	    uniPattern++;
	    ch1 = (nocase ? Tcl_UniCharToLower(*uniStr) : *uniStr);
	    uniStr++;
	    while (1) {
		if ((*uniPattern == ']') || (*uniPattern == 0)) {
		    return 0;
		}
		startChar = (nocase ? Tcl_UniCharToLower(*uniPattern)
			: *uniPattern);
		uniPattern++;
		if (*uniPattern == '-') {
		    uniPattern++;
		    if (*uniPattern == 0) {
			return 0;
		    }
		    endChar = (nocase ? Tcl_UniCharToLower(*uniPattern)
			    : *uniPattern);
		    uniPattern++;
		    if (((startChar <= ch1) && (ch1 <= endChar))
			    || ((endChar <= ch1) && (ch1 <= startChar))) {
			/*
			 * Matches ranges of form [a-z] or [z-a].
			 */
			break;
		    }
		} else if (startChar == ch1) {
		    break;
		}
	    }
	    while (*uniPattern != ']') {
		if (*uniPattern == 0) {
		    uniPattern--;
		    break;
		}
		uniPattern++;
	    }
	    uniPattern++;
	    continue;
	}

	/*
	 * If the next pattern character is '\', just strip off the '\' so we
	 * do exact matching on the character that follows.
	 */

	if (p == '\\') {
	    if (*(++uniPattern) == '\0') {
		return 0;
	    }
	}

	/*
	 * There's no special character. Just make sure that the next bytes of
	 * each string match.
	 */

	if (nocase) {
	    if (Tcl_UniCharToLower(*uniStr) !=
		    Tcl_UniCharToLower(*uniPattern)) {
		return 0;
	    }
	} else if (*uniStr != *uniPattern) {
	    return 0;
	}
	uniStr++;
	uniPattern++;
    }
}

/*
 *----------------------------------------------------------------------
 *
 * TclUniCharMatch --
 *
 *	See if a particular Unicode string matches a particular pattern.
 *	Allows case insensitivity. This is the Unicode equivalent of the char*
 *	Tcl_StringCaseMatch. This variant of Tcl_UniCharCaseMatch uses counted
 *	Strings, so embedded NULLs are allowed.
 *
 * Results:
 *	The return value is 1 if string matches pattern, and 0 otherwise. The
 *	matching operation permits the following special characters in the
 *	pattern: *?\[] (see the manual entry for details on what these mean).
 *
 * Side effects:
 *	None.
 *
 *----------------------------------------------------------------------
 */

int
TclUniCharMatch(
    const Tcl_UniChar *string,	/* Unicode String. */
    int strLen,			/* Length of String */
    const Tcl_UniChar *pattern,	/* Pattern, which may contain special
				 * characters. */
    int ptnLen,			/* Length of Pattern */
    int nocase)			/* 0 for case sensitive, 1 for insensitive */
{
    const Tcl_UniChar *stringEnd, *patternEnd;
    Tcl_UniChar p;

    stringEnd = string + strLen;
    patternEnd = pattern + ptnLen;

    while (1) {
	/*
	 * See if we're at the end of both the pattern and the string. If so,
	 * we succeeded. If we're at the end of the pattern but not at the end
	 * of the string, we failed.
	 */

	if (pattern == patternEnd) {
	    return (string == stringEnd);
	}
	p = *pattern;
	if ((string == stringEnd) && (p != '*')) {
	    return 0;
	}

	/*
	 * Check for a "*" as the next pattern character. It matches any
	 * substring. We handle this by skipping all the characters up to the
	 * next matching one in the pattern, and then calling ourselves
	 * recursively for each postfix of string, until either we match or we
	 * reach the end of the string.
	 */

	if (p == '*') {
	    /*
	     * Skip all successive *'s in the pattern.
	     */

	    while (*(++pattern) == '*') {
		/* empty body */
	    }
	    if (pattern == patternEnd) {
		return 1;
	    }
	    p = *pattern;
	    if (nocase) {
		p = Tcl_UniCharToLower(p);
	    }
	    while (1) {
		/*
		 * Optimization for matching - cruise through the string
		 * quickly if the next char in the pattern isn't a special
		 * character.
		 */

		if ((p != '[') && (p != '?') && (p != '\\')) {
		    if (nocase) {
			while ((string < stringEnd) && (p != *string)
				&& (p != Tcl_UniCharToLower(*string))) {
			    string++;
			}
		    } else {
			while ((string < stringEnd) && (p != *string)) {
			    string++;
			}
		    }
		}
		if (TclUniCharMatch(string, stringEnd - string,
			pattern, patternEnd - pattern, nocase)) {
		    return 1;
		}
		if (string == stringEnd) {
		    return 0;
		}
		string++;
	    }
	}

	/*
	 * Check for a "?" as the next pattern character. It matches any
	 * single character.
	 */

	if (p == '?') {
	    pattern++;
	    string++;
	    continue;
	}

	/*
	 * Check for a "[" as the next pattern character. It is followed by a
	 * list of characters that are acceptable, or by a range (two
	 * characters separated by "-").
	 */

	if (p == '[') {
	    Tcl_UniChar ch1, startChar, endChar;

	    pattern++;
	    ch1 = (nocase ? Tcl_UniCharToLower(*string) : *string);
	    string++;
	    while (1) {
		if ((*pattern == ']') || (pattern == patternEnd)) {
		    return 0;
		}
		startChar = (nocase ? Tcl_UniCharToLower(*pattern) : *pattern);
		pattern++;
		if (*pattern == '-') {
		    pattern++;
		    if (pattern == patternEnd) {
			return 0;
		    }
		    endChar = (nocase ? Tcl_UniCharToLower(*pattern)
			    : *pattern);
		    pattern++;
		    if (((startChar <= ch1) && (ch1 <= endChar))
			    || ((endChar <= ch1) && (ch1 <= startChar))) {
			/*
			 * Matches ranges of form [a-z] or [z-a].
			 */
			break;
		    }
		} else if (startChar == ch1) {
		    break;
		}
	    }
	    while (*pattern != ']') {
		if (pattern == patternEnd) {
		    pattern--;
		    break;
		}
		pattern++;
	    }
	    pattern++;
	    continue;
	}

	/*
	 * If the next pattern character is '\', just strip off the '\' so we
	 * do exact matching on the character that follows.
	 */

	if (p == '\\') {
	    if (++pattern == patternEnd) {
		return 0;
	    }
	}

	/*
	 * There's no special character. Just make sure that the next bytes of
	 * each string match.
	 */

	if (nocase) {
	    if (Tcl_UniCharToLower(*string) != Tcl_UniCharToLower(*pattern)) {
		return 0;
	    }
	} else if (*string != *pattern) {
	    return 0;
	}
	string++;
	pattern++;
    }
}

/*
 * Local Variables:
 * mode: c
 * c-basic-offset: 4
 * fill-column: 78
 * End:
 */