/usr/include/unicode/ustring.h is in libicu-dev 57.1-6+deb9u2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | /*
**********************************************************************
* Copyright (C) 1998-2014, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*
* File ustring.h
*
* Modification History:
*
* Date Name Description
* 12/07/98 bertrand Creation.
******************************************************************************
*/
#ifndef USTRING_H
#define USTRING_H
#include "unicode/utypes.h"
#include "unicode/putil.h"
#include "unicode/uiter.h"
/**
* \def UBRK_TYPEDEF_UBREAK_ITERATOR
* @internal
*/
#ifndef UBRK_TYPEDEF_UBREAK_ITERATOR
# define UBRK_TYPEDEF_UBREAK_ITERATOR
/** Simple declaration for u_strToTitle() to avoid including unicode/ubrk.h. @stable ICU 2.1*/
typedef struct UBreakIterator UBreakIterator;
#endif
/**
* \file
* \brief C API: Unicode string handling functions
*
* These C API functions provide general Unicode string handling.
*
* Some functions are equivalent in name, signature, and behavior to the ANSI C <string.h>
* functions. (For example, they do not check for bad arguments like NULL string pointers.)
* In some cases, only the thread-safe variant of such a function is implemented here
* (see u_strtok_r()).
*
* Other functions provide more Unicode-specific functionality like locale-specific
* upper/lower-casing and string comparison in code point order.
*
* ICU uses 16-bit Unicode (UTF-16) in the form of arrays of UChar code units.
* UTF-16 encodes each Unicode code point with either one or two UChar code units.
* (This is the default form of Unicode, and a forward-compatible extension of the original,
* fixed-width form that was known as UCS-2. UTF-16 superseded UCS-2 with Unicode 2.0
* in 1996.)
*
* Some APIs accept a 32-bit UChar32 value for a single code point.
*
* ICU also handles 16-bit Unicode text with unpaired surrogates.
* Such text is not well-formed UTF-16.
* Code-point-related functions treat unpaired surrogates as surrogate code points,
* i.e., as separate units.
*
* Although UTF-16 is a variable-width encoding form (like some legacy multi-byte encodings),
* it is much more efficient even for random access because the code unit values
* for single-unit characters vs. lead units vs. trail units are completely disjoint.
* This means that it is easy to determine character (code point) boundaries from
* random offsets in the string.
*
* Unicode (UTF-16) string processing is optimized for the single-unit case.
* Although it is important to support supplementary characters
* (which use pairs of lead/trail code units called "surrogates"),
* their occurrence is rare. Almost all characters in modern use require only
* a single UChar code unit (i.e., their code point values are <=0xffff).
*
* For more details see the User Guide Strings chapter (http://icu-project.org/userguide/strings.html).
* For a discussion of the handling of unpaired surrogates see also
* Jitterbug 2145 and its icu mailing list proposal on 2002-sep-18.
*/
/**
* \defgroup ustring_ustrlen String Length
* \ingroup ustring_strlen
*/
/*@{*/
/**
* Determine the length of an array of UChar.
*
* @param s The array of UChars, NULL (U+0000) terminated.
* @return The number of UChars in <code>chars</code>, minus the terminator.
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
u_strlen(const UChar *s);
/*@}*/
/**
* Count Unicode code points in the length UChar code units of the string.
* A code point may occupy either one or two UChar code units.
* Counting code points involves reading all code units.
*
* This functions is basically the inverse of the U16_FWD_N() macro (see utf.h).
*
* @param s The input string.
* @param length The number of UChar code units to be checked, or -1 to count all
* code points before the first NUL (U+0000).
* @return The number of code points in the specified code units.
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
u_countChar32(const UChar *s, int32_t length);
/**
* Check if the string contains more Unicode code points than a certain number.
* This is more efficient than counting all code points in the entire string
* and comparing that number with a threshold.
* This function may not need to scan the string at all if the length is known
* (not -1 for NUL-termination) and falls within a certain range, and
* never needs to count more than 'number+1' code points.
* Logically equivalent to (u_countChar32(s, length)>number).
* A Unicode code point may occupy either one or two UChar code units.
*
* @param s The input string.
* @param length The length of the string, or -1 if it is NUL-terminated.
* @param number The number of code points in the string is compared against
* the 'number' parameter.
* @return Boolean value for whether the string contains more Unicode code points
* than 'number'. Same as (u_countChar32(s, length)>number).
* @stable ICU 2.4
*/
U_STABLE UBool U_EXPORT2
u_strHasMoreChar32Than(const UChar *s, int32_t length, int32_t number);
/**
* Concatenate two ustrings. Appends a copy of <code>src</code>,
* including the null terminator, to <code>dst</code>. The initial copied
* character from <code>src</code> overwrites the null terminator in <code>dst</code>.
*
* @param dst The destination string.
* @param src The source string.
* @return A pointer to <code>dst</code>.
* @stable ICU 2.0
*/
U_STABLE UChar* U_EXPORT2
u_strcat(UChar *dst,
const UChar *src);
/**
* Concatenate two ustrings.
* Appends at most <code>n</code> characters from <code>src</code> to <code>dst</code>.
* Adds a terminating NUL.
* If src is too long, then only <code>n-1</code> characters will be copied
* before the terminating NUL.
* If <code>n<=0</code> then dst is not modified.
*
* @param dst The destination string.
* @param src The source string (can be NULL/invalid if n<=0).
* @param n The maximum number of characters to append; no-op if <=0.
* @return A pointer to <code>dst</code>.
* @stable ICU 2.0
*/
U_STABLE UChar* U_EXPORT2
u_strncat(UChar *dst,
const UChar *src,
int32_t n);
/**
* Find the first occurrence of a substring in a string.
* The substring is found at code point boundaries.
* That means that if the substring begins with
* a trail surrogate or ends with a lead surrogate,
* then it is found only if these surrogates stand alone in the text.
* Otherwise, the substring edge units would be matched against
* halves of surrogate pairs.
*
* @param s The string to search (NUL-terminated).
* @param substring The substring to find (NUL-terminated).
* @return A pointer to the first occurrence of <code>substring</code> in <code>s</code>,
* or <code>s</code> itself if the <code>substring</code> is empty,
* or <code>NULL</code> if <code>substring</code> is not in <code>s</code>.
* @stable ICU 2.0
*
* @see u_strrstr
* @see u_strFindFirst
* @see u_strFindLast
*/
U_STABLE UChar * U_EXPORT2
u_strstr(const UChar *s, const UChar *substring);
/**
* Find the first occurrence of a substring in a string.
* The substring is found at code point boundaries.
* That means that if the substring begins with
* a trail surrogate or ends with a lead surrogate,
* then it is found only if these surrogates stand alone in the text.
* Otherwise, the substring edge units would be matched against
* halves of surrogate pairs.
*
* @param s The string to search.
* @param length The length of s (number of UChars), or -1 if it is NUL-terminated.
* @param substring The substring to find (NUL-terminated).
* @param subLength The length of substring (number of UChars), or -1 if it is NUL-terminated.
* @return A pointer to the first occurrence of <code>substring</code> in <code>s</code>,
* or <code>s</code> itself if the <code>substring</code> is empty,
* or <code>NULL</code> if <code>substring</code> is not in <code>s</code>.
* @stable ICU 2.4
*
* @see u_strstr
* @see u_strFindLast
*/
U_STABLE UChar * U_EXPORT2
u_strFindFirst(const UChar *s, int32_t length, const UChar *substring, int32_t subLength);
/**
* Find the first occurrence of a BMP code point in a string.
* A surrogate code point is found only if its match in the text is not
* part of a surrogate pair.
* A NUL character is found at the string terminator.
*
* @param s The string to search (NUL-terminated).
* @param c The BMP code point to find.
* @return A pointer to the first occurrence of <code>c</code> in <code>s</code>
* or <code>NULL</code> if <code>c</code> is not in <code>s</code>.
* @stable ICU 2.0
*
* @see u_strchr32
* @see u_memchr
* @see u_strstr
* @see u_strFindFirst
*/
U_STABLE UChar * U_EXPORT2
u_strchr(const UChar *s, UChar c);
/**
* Find the first occurrence of a code point in a string.
* A surrogate code point is found only if its match in the text is not
* part of a surrogate pair.
* A NUL character is found at the string terminator.
*
* @param s The string to search (NUL-terminated).
* @param c The code point to find.
* @return A pointer to the first occurrence of <code>c</code> in <code>s</code>
* or <code>NULL</code> if <code>c</code> is not in <code>s</code>.
* @stable ICU 2.0
*
* @see u_strchr
* @see u_memchr32
* @see u_strstr
* @see u_strFindFirst
*/
U_STABLE UChar * U_EXPORT2
u_strchr32(const UChar *s, UChar32 c);
/**
* Find the last occurrence of a substring in a string.
* The substring is found at code point boundaries.
* That means that if the substring begins with
* a trail surrogate or ends with a lead surrogate,
* then it is found only if these surrogates stand alone in the text.
* Otherwise, the substring edge units would be matched against
* halves of surrogate pairs.
*
* @param s The string to search (NUL-terminated).
* @param substring The substring to find (NUL-terminated).
* @return A pointer to the last occurrence of <code>substring</code> in <code>s</code>,
* or <code>s</code> itself if the <code>substring</code> is empty,
* or <code>NULL</code> if <code>substring</code> is not in <code>s</code>.
* @stable ICU 2.4
*
* @see u_strstr
* @see u_strFindFirst
* @see u_strFindLast
*/
U_STABLE UChar * U_EXPORT2
u_strrstr(const UChar *s, const UChar *substring);
/**
* Find the last occurrence of a substring in a string.
* The substring is found at code point boundaries.
* That means that if the substring begins with
* a trail surrogate or ends with a lead surrogate,
* then it is found only if these surrogates stand alone in the text.
* Otherwise, the substring edge units would be matched against
* halves of surrogate pairs.
*
* @param s The string to search.
* @param length The length of s (number of UChars), or -1 if it is NUL-terminated.
* @param substring The substring to find (NUL-terminated).
* @param subLength The length of substring (number of UChars), or -1 if it is NUL-terminated.
* @return A pointer to the last occurrence of <code>substring</code> in <code>s</code>,
* or <code>s</code> itself if the <code>substring</code> is empty,
* or <code>NULL</code> if <code>substring</code> is not in <code>s</code>.
* @stable ICU 2.4
*
* @see u_strstr
* @see u_strFindLast
*/
U_STABLE UChar * U_EXPORT2
u_strFindLast(const UChar *s, int32_t length, const UChar *substring, int32_t subLength);
/**
* Find the last occurrence of a BMP code point in a string.
* A surrogate code point is found only if its match in the text is not
* part of a surrogate pair.
* A NUL character is found at the string terminator.
*
* @param s The string to search (NUL-terminated).
* @param c The BMP code point to find.
* @return A pointer to the last occurrence of <code>c</code> in <code>s</code>
* or <code>NULL</code> if <code>c</code> is not in <code>s</code>.
* @stable ICU 2.4
*
* @see u_strrchr32
* @see u_memrchr
* @see u_strrstr
* @see u_strFindLast
*/
U_STABLE UChar * U_EXPORT2
u_strrchr(const UChar *s, UChar c);
/**
* Find the last occurrence of a code point in a string.
* A surrogate code point is found only if its match in the text is not
* part of a surrogate pair.
* A NUL character is found at the string terminator.
*
* @param s The string to search (NUL-terminated).
* @param c The code point to find.
* @return A pointer to the last occurrence of <code>c</code> in <code>s</code>
* or <code>NULL</code> if <code>c</code> is not in <code>s</code>.
* @stable ICU 2.4
*
* @see u_strrchr
* @see u_memchr32
* @see u_strrstr
* @see u_strFindLast
*/
U_STABLE UChar * U_EXPORT2
u_strrchr32(const UChar *s, UChar32 c);
/**
* Locates the first occurrence in the string <code>string</code> of any of the characters
* in the string <code>matchSet</code>.
* Works just like C's strpbrk but with Unicode.
*
* @param string The string in which to search, NUL-terminated.
* @param matchSet A NUL-terminated string defining a set of code points
* for which to search in the text string.
* @return A pointer to the character in <code>string</code> that matches one of the
* characters in <code>matchSet</code>, or NULL if no such character is found.
* @stable ICU 2.0
*/
U_STABLE UChar * U_EXPORT2
u_strpbrk(const UChar *string, const UChar *matchSet);
/**
* Returns the number of consecutive characters in <code>string</code>,
* beginning with the first, that do not occur somewhere in <code>matchSet</code>.
* Works just like C's strcspn but with Unicode.
*
* @param string The string in which to search, NUL-terminated.
* @param matchSet A NUL-terminated string defining a set of code points
* for which to search in the text string.
* @return The number of initial characters in <code>string</code> that do not
* occur in <code>matchSet</code>.
* @see u_strspn
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
u_strcspn(const UChar *string, const UChar *matchSet);
/**
* Returns the number of consecutive characters in <code>string</code>,
* beginning with the first, that occur somewhere in <code>matchSet</code>.
* Works just like C's strspn but with Unicode.
*
* @param string The string in which to search, NUL-terminated.
* @param matchSet A NUL-terminated string defining a set of code points
* for which to search in the text string.
* @return The number of initial characters in <code>string</code> that do
* occur in <code>matchSet</code>.
* @see u_strcspn
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
u_strspn(const UChar *string, const UChar *matchSet);
/**
* The string tokenizer API allows an application to break a string into
* tokens. Unlike strtok(), the saveState (the current pointer within the
* original string) is maintained in saveState. In the first call, the
* argument src is a pointer to the string. In subsequent calls to
* return successive tokens of that string, src must be specified as
* NULL. The value saveState is set by this function to maintain the
* function's position within the string, and on each subsequent call
* you must give this argument the same variable. This function does
* handle surrogate pairs. This function is similar to the strtok_r()
* the POSIX Threads Extension (1003.1c-1995) version.
*
* @param src String containing token(s). This string will be modified.
* After the first call to u_strtok_r(), this argument must
* be NULL to get to the next token.
* @param delim Set of delimiter characters (Unicode code points).
* @param saveState The current pointer within the original string,
* which is set by this function. The saveState
* parameter should the address of a local variable of type
* UChar *. (i.e. defined "Uhar *myLocalSaveState" and use
* &myLocalSaveState for this parameter).
* @return A pointer to the next token found in src, or NULL
* when there are no more tokens.
* @stable ICU 2.0
*/
U_STABLE UChar * U_EXPORT2
u_strtok_r(UChar *src,
const UChar *delim,
UChar **saveState);
/**
* Compare two Unicode strings for bitwise equality (code unit order).
*
* @param s1 A string to compare.
* @param s2 A string to compare.
* @return 0 if <code>s1</code> and <code>s2</code> are bitwise equal; a negative
* value if <code>s1</code> is bitwise less than <code>s2,</code>; a positive
* value if <code>s1</code> is bitwise greater than <code>s2</code>.
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
u_strcmp(const UChar *s1,
const UChar *s2);
/**
* Compare two Unicode strings in code point order.
* See u_strCompare for details.
*
* @param s1 A string to compare.
* @param s2 A string to compare.
* @return a negative/zero/positive integer corresponding to whether
* the first string is less than/equal to/greater than the second one
* in code point order
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
u_strcmpCodePointOrder(const UChar *s1, const UChar *s2);
/**
* Compare two Unicode strings (binary order).
*
* The comparison can be done in code unit order or in code point order.
* They differ only in UTF-16 when
* comparing supplementary code points (U+10000..U+10ffff)
* to BMP code points near the end of the BMP (i.e., U+e000..U+ffff).
* In code unit order, high BMP code points sort after supplementary code points
* because they are stored as pairs of surrogates which are at U+d800..U+dfff.
*
* This functions works with strings of different explicitly specified lengths
* unlike the ANSI C-like u_strcmp() and u_memcmp() etc.
* NUL-terminated strings are possible with length arguments of -1.
*
* @param s1 First source string.
* @param length1 Length of first source string, or -1 if NUL-terminated.
*
* @param s2 Second source string.
* @param length2 Length of second source string, or -1 if NUL-terminated.
*
* @param codePointOrder Choose between code unit order (FALSE)
* and code point order (TRUE).
*
* @return <0 or 0 or >0 as usual for string comparisons
*
* @stable ICU 2.2
*/
U_STABLE int32_t U_EXPORT2
u_strCompare(const UChar *s1, int32_t length1,
const UChar *s2, int32_t length2,
UBool codePointOrder);
/**
* Compare two Unicode strings (binary order)
* as presented by UCharIterator objects.
* Works otherwise just like u_strCompare().
*
* Both iterators are reset to their start positions.
* When the function returns, it is undefined where the iterators
* have stopped.
*
* @param iter1 First source string iterator.
* @param iter2 Second source string iterator.
* @param codePointOrder Choose between code unit order (FALSE)
* and code point order (TRUE).
*
* @return <0 or 0 or >0 as usual for string comparisons
*
* @see u_strCompare
*
* @stable ICU 2.6
*/
U_STABLE int32_t U_EXPORT2
u_strCompareIter(UCharIterator *iter1, UCharIterator *iter2, UBool codePointOrder);
#ifndef U_COMPARE_CODE_POINT_ORDER
/* see also unistr.h and unorm.h */
/**
* Option bit for u_strCaseCompare, u_strcasecmp, unorm_compare, etc:
* Compare strings in code point order instead of code unit order.
* @stable ICU 2.2
*/
#define U_COMPARE_CODE_POINT_ORDER 0x8000
#endif
/**
* Compare two strings case-insensitively using full case folding.
* This is equivalent to
* u_strCompare(u_strFoldCase(s1, options),
* u_strFoldCase(s2, options),
* (options&U_COMPARE_CODE_POINT_ORDER)!=0).
*
* The comparison can be done in UTF-16 code unit order or in code point order.
* They differ only when comparing supplementary code points (U+10000..U+10ffff)
* to BMP code points near the end of the BMP (i.e., U+e000..U+ffff).
* In code unit order, high BMP code points sort after supplementary code points
* because they are stored as pairs of surrogates which are at U+d800..U+dfff.
*
* This functions works with strings of different explicitly specified lengths
* unlike the ANSI C-like u_strcmp() and u_memcmp() etc.
* NUL-terminated strings are possible with length arguments of -1.
*
* @param s1 First source string.
* @param length1 Length of first source string, or -1 if NUL-terminated.
*
* @param s2 Second source string.
* @param length2 Length of second source string, or -1 if NUL-terminated.
*
* @param options A bit set of options:
* - U_FOLD_CASE_DEFAULT or 0 is used for default options:
* Comparison in code unit order with default case folding.
*
* - U_COMPARE_CODE_POINT_ORDER
* Set to choose code point order instead of code unit order
* (see u_strCompare for details).
*
* - U_FOLD_CASE_EXCLUDE_SPECIAL_I
*
* @param pErrorCode Must be a valid pointer to an error code value,
* which must not indicate a failure before the function call.
*
* @return <0 or 0 or >0 as usual for string comparisons
*
* @stable ICU 2.2
*/
U_STABLE int32_t U_EXPORT2
u_strCaseCompare(const UChar *s1, int32_t length1,
const UChar *s2, int32_t length2,
uint32_t options,
UErrorCode *pErrorCode);
/**
* Compare two ustrings for bitwise equality.
* Compares at most <code>n</code> characters.
*
* @param ucs1 A string to compare (can be NULL/invalid if n<=0).
* @param ucs2 A string to compare (can be NULL/invalid if n<=0).
* @param n The maximum number of characters to compare; always returns 0 if n<=0.
* @return 0 if <code>s1</code> and <code>s2</code> are bitwise equal; a negative
* value if <code>s1</code> is bitwise less than <code>s2</code>; a positive
* value if <code>s1</code> is bitwise greater than <code>s2</code>.
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
u_strncmp(const UChar *ucs1,
const UChar *ucs2,
int32_t n);
/**
* Compare two Unicode strings in code point order.
* This is different in UTF-16 from u_strncmp() if supplementary characters are present.
* For details, see u_strCompare().
*
* @param s1 A string to compare.
* @param s2 A string to compare.
* @param n The maximum number of characters to compare.
* @return a negative/zero/positive integer corresponding to whether
* the first string is less than/equal to/greater than the second one
* in code point order
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
u_strncmpCodePointOrder(const UChar *s1, const UChar *s2, int32_t n);
/**
* Compare two strings case-insensitively using full case folding.
* This is equivalent to u_strcmp(u_strFoldCase(s1, options), u_strFoldCase(s2, options)).
*
* @param s1 A string to compare.
* @param s2 A string to compare.
* @param options A bit set of options:
* - U_FOLD_CASE_DEFAULT or 0 is used for default options:
* Comparison in code unit order with default case folding.
*
* - U_COMPARE_CODE_POINT_ORDER
* Set to choose code point order instead of code unit order
* (see u_strCompare for details).
*
* - U_FOLD_CASE_EXCLUDE_SPECIAL_I
*
* @return A negative, zero, or positive integer indicating the comparison result.
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
u_strcasecmp(const UChar *s1, const UChar *s2, uint32_t options);
/**
* Compare two strings case-insensitively using full case folding.
* This is equivalent to u_strcmp(u_strFoldCase(s1, at most n, options),
* u_strFoldCase(s2, at most n, options)).
*
* @param s1 A string to compare.
* @param s2 A string to compare.
* @param n The maximum number of characters each string to case-fold and then compare.
* @param options A bit set of options:
* - U_FOLD_CASE_DEFAULT or 0 is used for default options:
* Comparison in code unit order with default case folding.
*
* - U_COMPARE_CODE_POINT_ORDER
* Set to choose code point order instead of code unit order
* (see u_strCompare for details).
*
* - U_FOLD_CASE_EXCLUDE_SPECIAL_I
*
* @return A negative, zero, or positive integer indicating the comparison result.
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
u_strncasecmp(const UChar *s1, const UChar *s2, int32_t n, uint32_t options);
/**
* Compare two strings case-insensitively using full case folding.
* This is equivalent to u_strcmp(u_strFoldCase(s1, n, options),
* u_strFoldCase(s2, n, options)).
*
* @param s1 A string to compare.
* @param s2 A string to compare.
* @param length The number of characters in each string to case-fold and then compare.
* @param options A bit set of options:
* - U_FOLD_CASE_DEFAULT or 0 is used for default options:
* Comparison in code unit order with default case folding.
*
* - U_COMPARE_CODE_POINT_ORDER
* Set to choose code point order instead of code unit order
* (see u_strCompare for details).
*
* - U_FOLD_CASE_EXCLUDE_SPECIAL_I
*
* @return A negative, zero, or positive integer indicating the comparison result.
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
u_memcasecmp(const UChar *s1, const UChar *s2, int32_t length, uint32_t options);
/**
* Copy a ustring. Adds a null terminator.
*
* @param dst The destination string.
* @param src The source string.
* @return A pointer to <code>dst</code>.
* @stable ICU 2.0
*/
U_STABLE UChar* U_EXPORT2
u_strcpy(UChar *dst,
const UChar *src);
/**
* Copy a ustring.
* Copies at most <code>n</code> characters. The result will be null terminated
* if the length of <code>src</code> is less than <code>n</code>.
*
* @param dst The destination string.
* @param src The source string (can be NULL/invalid if n<=0).
* @param n The maximum number of characters to copy; no-op if <=0.
* @return A pointer to <code>dst</code>.
* @stable ICU 2.0
*/
U_STABLE UChar* U_EXPORT2
u_strncpy(UChar *dst,
const UChar *src,
int32_t n);
#if !UCONFIG_NO_CONVERSION
/**
* Copy a byte string encoded in the default codepage to a ustring.
* Adds a null terminator.
* Performs a host byte to UChar conversion
*
* @param dst The destination string.
* @param src The source string.
* @return A pointer to <code>dst</code>.
* @stable ICU 2.0
*/
U_STABLE UChar* U_EXPORT2 u_uastrcpy(UChar *dst,
const char *src );
/**
* Copy a byte string encoded in the default codepage to a ustring.
* Copies at most <code>n</code> characters. The result will be null terminated
* if the length of <code>src</code> is less than <code>n</code>.
* Performs a host byte to UChar conversion
*
* @param dst The destination string.
* @param src The source string.
* @param n The maximum number of characters to copy.
* @return A pointer to <code>dst</code>.
* @stable ICU 2.0
*/
U_STABLE UChar* U_EXPORT2 u_uastrncpy(UChar *dst,
const char *src,
int32_t n);
/**
* Copy ustring to a byte string encoded in the default codepage.
* Adds a null terminator.
* Performs a UChar to host byte conversion
*
* @param dst The destination string.
* @param src The source string.
* @return A pointer to <code>dst</code>.
* @stable ICU 2.0
*/
U_STABLE char* U_EXPORT2 u_austrcpy(char *dst,
const UChar *src );
/**
* Copy ustring to a byte string encoded in the default codepage.
* Copies at most <code>n</code> characters. The result will be null terminated
* if the length of <code>src</code> is less than <code>n</code>.
* Performs a UChar to host byte conversion
*
* @param dst The destination string.
* @param src The source string.
* @param n The maximum number of characters to copy.
* @return A pointer to <code>dst</code>.
* @stable ICU 2.0
*/
U_STABLE char* U_EXPORT2 u_austrncpy(char *dst,
const UChar *src,
int32_t n );
#endif
/**
* Synonym for memcpy(), but with UChars only.
* @param dest The destination string
* @param src The source string (can be NULL/invalid if count<=0)
* @param count The number of characters to copy; no-op if <=0
* @return A pointer to <code>dest</code>
* @stable ICU 2.0
*/
U_STABLE UChar* U_EXPORT2
u_memcpy(UChar *dest, const UChar *src, int32_t count);
/**
* Synonym for memmove(), but with UChars only.
* @param dest The destination string
* @param src The source string (can be NULL/invalid if count<=0)
* @param count The number of characters to move; no-op if <=0
* @return A pointer to <code>dest</code>
* @stable ICU 2.0
*/
U_STABLE UChar* U_EXPORT2
u_memmove(UChar *dest, const UChar *src, int32_t count);
/**
* Initialize <code>count</code> characters of <code>dest</code> to <code>c</code>.
*
* @param dest The destination string.
* @param c The character to initialize the string.
* @param count The maximum number of characters to set.
* @return A pointer to <code>dest</code>.
* @stable ICU 2.0
*/
U_STABLE UChar* U_EXPORT2
u_memset(UChar *dest, UChar c, int32_t count);
/**
* Compare the first <code>count</code> UChars of each buffer.
*
* @param buf1 The first string to compare.
* @param buf2 The second string to compare.
* @param count The maximum number of UChars to compare.
* @return When buf1 < buf2, a negative number is returned.
* When buf1 == buf2, 0 is returned.
* When buf1 > buf2, a positive number is returned.
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
u_memcmp(const UChar *buf1, const UChar *buf2, int32_t count);
/**
* Compare two Unicode strings in code point order.
* This is different in UTF-16 from u_memcmp() if supplementary characters are present.
* For details, see u_strCompare().
*
* @param s1 A string to compare.
* @param s2 A string to compare.
* @param count The maximum number of characters to compare.
* @return a negative/zero/positive integer corresponding to whether
* the first string is less than/equal to/greater than the second one
* in code point order
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
u_memcmpCodePointOrder(const UChar *s1, const UChar *s2, int32_t count);
/**
* Find the first occurrence of a BMP code point in a string.
* A surrogate code point is found only if its match in the text is not
* part of a surrogate pair.
* A NUL character is found at the string terminator.
*
* @param s The string to search (contains <code>count</code> UChars).
* @param c The BMP code point to find.
* @param count The length of the string.
* @return A pointer to the first occurrence of <code>c</code> in <code>s</code>
* or <code>NULL</code> if <code>c</code> is not in <code>s</code>.
* @stable ICU 2.0
*
* @see u_strchr
* @see u_memchr32
* @see u_strFindFirst
*/
U_STABLE UChar* U_EXPORT2
u_memchr(const UChar *s, UChar c, int32_t count);
/**
* Find the first occurrence of a code point in a string.
* A surrogate code point is found only if its match in the text is not
* part of a surrogate pair.
* A NUL character is found at the string terminator.
*
* @param s The string to search (contains <code>count</code> UChars).
* @param c The code point to find.
* @param count The length of the string.
* @return A pointer to the first occurrence of <code>c</code> in <code>s</code>
* or <code>NULL</code> if <code>c</code> is not in <code>s</code>.
* @stable ICU 2.0
*
* @see u_strchr32
* @see u_memchr
* @see u_strFindFirst
*/
U_STABLE UChar* U_EXPORT2
u_memchr32(const UChar *s, UChar32 c, int32_t count);
/**
* Find the last occurrence of a BMP code point in a string.
* A surrogate code point is found only if its match in the text is not
* part of a surrogate pair.
* A NUL character is found at the string terminator.
*
* @param s The string to search (contains <code>count</code> UChars).
* @param c The BMP code point to find.
* @param count The length of the string.
* @return A pointer to the last occurrence of <code>c</code> in <code>s</code>
* or <code>NULL</code> if <code>c</code> is not in <code>s</code>.
* @stable ICU 2.4
*
* @see u_strrchr
* @see u_memrchr32
* @see u_strFindLast
*/
U_STABLE UChar* U_EXPORT2
u_memrchr(const UChar *s, UChar c, int32_t count);
/**
* Find the last occurrence of a code point in a string.
* A surrogate code point is found only if its match in the text is not
* part of a surrogate pair.
* A NUL character is found at the string terminator.
*
* @param s The string to search (contains <code>count</code> UChars).
* @param c The code point to find.
* @param count The length of the string.
* @return A pointer to the last occurrence of <code>c</code> in <code>s</code>
* or <code>NULL</code> if <code>c</code> is not in <code>s</code>.
* @stable ICU 2.4
*
* @see u_strrchr32
* @see u_memrchr
* @see u_strFindLast
*/
U_STABLE UChar* U_EXPORT2
u_memrchr32(const UChar *s, UChar32 c, int32_t count);
/**
* Unicode String literals in C.
* We need one macro to declare a variable for the string
* and to statically preinitialize it if possible,
* and a second macro to dynamically intialize such a string variable if necessary.
*
* The macros are defined for maximum performance.
* They work only for strings that contain "invariant characters", i.e.,
* only latin letters, digits, and some punctuation.
* See utypes.h for details.
*
* A pair of macros for a single string must be used with the same
* parameters.
* The string parameter must be a C string literal.
* The length of the string, not including the terminating
* <code>NUL</code>, must be specified as a constant.
* The U_STRING_DECL macro should be invoked exactly once for one
* such string variable before it is used.
*
* Usage:
* <pre>
* U_STRING_DECL(ustringVar1, "Quick-Fox 2", 11);
* U_STRING_DECL(ustringVar2, "jumps 5%", 8);
* static UBool didInit=FALSE;
*
* int32_t function() {
* if(!didInit) {
* U_STRING_INIT(ustringVar1, "Quick-Fox 2", 11);
* U_STRING_INIT(ustringVar2, "jumps 5%", 8);
* didInit=TRUE;
* }
* return u_strcmp(ustringVar1, ustringVar2);
* }
* </pre>
*
* Note that the macros will NOT consistently work if their argument is another <code>#define</code>.
* The following will not work on all platforms, don't use it.
*
* <pre>
* #define GLUCK "Mr. Gluck"
* U_STRING_DECL(var, GLUCK, 9)
* U_STRING_INIT(var, GLUCK, 9)
* </pre>
*
* Instead, use the string literal "Mr. Gluck" as the argument to both macro
* calls.
*
*
* @stable ICU 2.0
*/
#if defined(U_DECLARE_UTF16)
# define U_STRING_DECL(var, cs, length) static const UChar *var=(const UChar *)U_DECLARE_UTF16(cs)
/**@stable ICU 2.0 */
# define U_STRING_INIT(var, cs, length)
#elif U_SIZEOF_WCHAR_T==U_SIZEOF_UCHAR && (U_CHARSET_FAMILY==U_ASCII_FAMILY || (U_SIZEOF_UCHAR == 2 && defined(U_WCHAR_IS_UTF16)))
# define U_STRING_DECL(var, cs, length) static const UChar var[(length)+1]=L ## cs
/**@stable ICU 2.0 */
# define U_STRING_INIT(var, cs, length)
#elif U_SIZEOF_UCHAR==1 && U_CHARSET_FAMILY==U_ASCII_FAMILY
# define U_STRING_DECL(var, cs, length) static const UChar var[(length)+1]=cs
/**@stable ICU 2.0 */
# define U_STRING_INIT(var, cs, length)
#else
# define U_STRING_DECL(var, cs, length) static UChar var[(length)+1]
/**@stable ICU 2.0 */
# define U_STRING_INIT(var, cs, length) u_charsToUChars(cs, var, length+1)
#endif
/**
* Unescape a string of characters and write the resulting
* Unicode characters to the destination buffer. The following escape
* sequences are recognized:
*
* \\uhhhh 4 hex digits; h in [0-9A-Fa-f]
* \\Uhhhhhhhh 8 hex digits
* \\xhh 1-2 hex digits
* \\x{h...} 1-8 hex digits
* \\ooo 1-3 octal digits; o in [0-7]
* \\cX control-X; X is masked with 0x1F
*
* as well as the standard ANSI C escapes:
*
* \\a => U+0007, \\b => U+0008, \\t => U+0009, \\n => U+000A,
* \\v => U+000B, \\f => U+000C, \\r => U+000D, \\e => U+001B,
* \\" => U+0022, \\' => U+0027, \\? => U+003F, \\\\ => U+005C
*
* Anything else following a backslash is generically escaped. For
* example, "[a\\-z]" returns "[a-z]".
*
* If an escape sequence is ill-formed, this method returns an empty
* string. An example of an ill-formed sequence is "\\u" followed by
* fewer than 4 hex digits.
*
* The above characters are recognized in the compiler's codepage,
* that is, they are coded as 'u', '\\', etc. Characters that are
* not parts of escape sequences are converted using u_charsToUChars().
*
* This function is similar to UnicodeString::unescape() but not
* identical to it. The latter takes a source UnicodeString, so it
* does escape recognition but no conversion.
*
* @param src a zero-terminated string of invariant characters
* @param dest pointer to buffer to receive converted and unescaped
* text and, if there is room, a zero terminator. May be NULL for
* preflighting, in which case no UChars will be written, but the
* return value will still be valid. On error, an empty string is
* stored here (if possible).
* @param destCapacity the number of UChars that may be written at
* dest. Ignored if dest == NULL.
* @return the length of unescaped string.
* @see u_unescapeAt
* @see UnicodeString#unescape()
* @see UnicodeString#unescapeAt()
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
u_unescape(const char *src,
UChar *dest, int32_t destCapacity);
U_CDECL_BEGIN
/**
* Callback function for u_unescapeAt() that returns a character of
* the source text given an offset and a context pointer. The context
* pointer will be whatever is passed into u_unescapeAt().
*
* @param offset pointer to the offset that will be passed to u_unescapeAt().
* @param context an opaque pointer passed directly into u_unescapeAt()
* @return the character represented by the escape sequence at
* offset
* @see u_unescapeAt
* @stable ICU 2.0
*/
typedef UChar (U_CALLCONV *UNESCAPE_CHAR_AT)(int32_t offset, void *context);
U_CDECL_END
/**
* Unescape a single sequence. The character at offset-1 is assumed
* (without checking) to be a backslash. This method takes a callback
* pointer to a function that returns the UChar at a given offset. By
* varying this callback, ICU functions are able to unescape char*
* strings, UnicodeString objects, and UFILE pointers.
*
* If offset is out of range, or if the escape sequence is ill-formed,
* (UChar32)0xFFFFFFFF is returned. See documentation of u_unescape()
* for a list of recognized sequences.
*
* @param charAt callback function that returns a UChar of the source
* text given an offset and a context pointer.
* @param offset pointer to the offset that will be passed to charAt.
* The offset value will be updated upon return to point after the
* last parsed character of the escape sequence. On error the offset
* is unchanged.
* @param length the number of characters in the source text. The
* last character of the source text is considered to be at offset
* length-1.
* @param context an opaque pointer passed directly into charAt.
* @return the character represented by the escape sequence at
* offset, or (UChar32)0xFFFFFFFF on error.
* @see u_unescape()
* @see UnicodeString#unescape()
* @see UnicodeString#unescapeAt()
* @stable ICU 2.0
*/
U_STABLE UChar32 U_EXPORT2
u_unescapeAt(UNESCAPE_CHAR_AT charAt,
int32_t *offset,
int32_t length,
void *context);
/**
* Uppercase the characters in a string.
* Casing is locale-dependent and context-sensitive.
* The result may be longer or shorter than the original.
* The source string and the destination buffer are allowed to overlap.
*
* @param dest A buffer for the result string. The result will be zero-terminated if
* the buffer is large enough.
* @param destCapacity The size of the buffer (number of UChars). If it is 0, then
* dest may be NULL and the function will only return the length of the result
* without writing any of the result string.
* @param src The original string
* @param srcLength The length of the original string. If -1, then src must be zero-terminated.
* @param locale The locale to consider, or "" for the root locale or NULL for the default locale.
* @param pErrorCode Must be a valid pointer to an error code value,
* which must not indicate a failure before the function call.
* @return The length of the result string. It may be greater than destCapacity. In that case,
* only some of the result was written to the destination buffer.
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
u_strToUpper(UChar *dest, int32_t destCapacity,
const UChar *src, int32_t srcLength,
const char *locale,
UErrorCode *pErrorCode);
/**
* Lowercase the characters in a string.
* Casing is locale-dependent and context-sensitive.
* The result may be longer or shorter than the original.
* The source string and the destination buffer are allowed to overlap.
*
* @param dest A buffer for the result string. The result will be zero-terminated if
* the buffer is large enough.
* @param destCapacity The size of the buffer (number of UChars). If it is 0, then
* dest may be NULL and the function will only return the length of the result
* without writing any of the result string.
* @param src The original string
* @param srcLength The length of the original string. If -1, then src must be zero-terminated.
* @param locale The locale to consider, or "" for the root locale or NULL for the default locale.
* @param pErrorCode Must be a valid pointer to an error code value,
* which must not indicate a failure before the function call.
* @return The length of the result string. It may be greater than destCapacity. In that case,
* only some of the result was written to the destination buffer.
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
u_strToLower(UChar *dest, int32_t destCapacity,
const UChar *src, int32_t srcLength,
const char *locale,
UErrorCode *pErrorCode);
#if !UCONFIG_NO_BREAK_ITERATION
/**
* Titlecase a string.
* Casing is locale-dependent and context-sensitive.
* Titlecasing uses a break iterator to find the first characters of words
* that are to be titlecased. It titlecases those characters and lowercases
* all others.
*
* The titlecase break iterator can be provided to customize for arbitrary
* styles, using rules and dictionaries beyond the standard iterators.
* It may be more efficient to always provide an iterator to avoid
* opening and closing one for each string.
* The standard titlecase iterator for the root locale implements the
* algorithm of Unicode TR 21.
*
* This function uses only the setText(), first() and next() methods of the
* provided break iterator.
*
* The result may be longer or shorter than the original.
* The source string and the destination buffer are allowed to overlap.
*
* @param dest A buffer for the result string. The result will be zero-terminated if
* the buffer is large enough.
* @param destCapacity The size of the buffer (number of UChars). If it is 0, then
* dest may be NULL and the function will only return the length of the result
* without writing any of the result string.
* @param src The original string
* @param srcLength The length of the original string. If -1, then src must be zero-terminated.
* @param titleIter A break iterator to find the first characters of words
* that are to be titlecased.
* If none is provided (NULL), then a standard titlecase
* break iterator is opened.
* @param locale The locale to consider, or "" for the root locale or NULL for the default locale.
* @param pErrorCode Must be a valid pointer to an error code value,
* which must not indicate a failure before the function call.
* @return The length of the result string. It may be greater than destCapacity. In that case,
* only some of the result was written to the destination buffer.
* @stable ICU 2.1
*/
U_STABLE int32_t U_EXPORT2
u_strToTitle(UChar *dest, int32_t destCapacity,
const UChar *src, int32_t srcLength,
UBreakIterator *titleIter,
const char *locale,
UErrorCode *pErrorCode);
#endif
/**
* Case-folds the characters in a string.
*
* Case-folding is locale-independent and not context-sensitive,
* but there is an option for whether to include or exclude mappings for dotted I
* and dotless i that are marked with 'T' in CaseFolding.txt.
*
* The result may be longer or shorter than the original.
* The source string and the destination buffer are allowed to overlap.
*
* @param dest A buffer for the result string. The result will be zero-terminated if
* the buffer is large enough.
* @param destCapacity The size of the buffer (number of UChars). If it is 0, then
* dest may be NULL and the function will only return the length of the result
* without writing any of the result string.
* @param src The original string
* @param srcLength The length of the original string. If -1, then src must be zero-terminated.
* @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I
* @param pErrorCode Must be a valid pointer to an error code value,
* which must not indicate a failure before the function call.
* @return The length of the result string. It may be greater than destCapacity. In that case,
* only some of the result was written to the destination buffer.
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
u_strFoldCase(UChar *dest, int32_t destCapacity,
const UChar *src, int32_t srcLength,
uint32_t options,
UErrorCode *pErrorCode);
#if defined(U_WCHAR_IS_UTF16) || defined(U_WCHAR_IS_UTF32) || !UCONFIG_NO_CONVERSION
/**
* Convert a UTF-16 string to a wchar_t string.
* If it is known at compile time that wchar_t strings are in UTF-16 or UTF-32, then
* this function simply calls the fast, dedicated function for that.
* Otherwise, two conversions UTF-16 -> default charset -> wchar_t* are performed.
*
* @param dest A buffer for the result string. The result will be zero-terminated if
* the buffer is large enough.
* @param destCapacity The size of the buffer (number of wchar_t's). If it is 0, then
* dest may be NULL and the function will only return the length of the
* result without writing any of the result string (pre-flighting).
* @param pDestLength A pointer to receive the number of units written to the destination. If
* pDestLength!=NULL then *pDestLength is always set to the
* number of output units corresponding to the transformation of
* all the input units, even in case of a buffer overflow.
* @param src The original source string
* @param srcLength The length of the original string. If -1, then src must be zero-terminated.
* @param pErrorCode Must be a valid pointer to an error code value,
* which must not indicate a failure before the function call.
* @return The pointer to destination buffer.
* @stable ICU 2.0
*/
U_STABLE wchar_t* U_EXPORT2
u_strToWCS(wchar_t *dest,
int32_t destCapacity,
int32_t *pDestLength,
const UChar *src,
int32_t srcLength,
UErrorCode *pErrorCode);
/**
* Convert a wchar_t string to UTF-16.
* If it is known at compile time that wchar_t strings are in UTF-16 or UTF-32, then
* this function simply calls the fast, dedicated function for that.
* Otherwise, two conversions wchar_t* -> default charset -> UTF-16 are performed.
*
* @param dest A buffer for the result string. The result will be zero-terminated if
* the buffer is large enough.
* @param destCapacity The size of the buffer (number of UChars). If it is 0, then
* dest may be NULL and the function will only return the length of the
* result without writing any of the result string (pre-flighting).
* @param pDestLength A pointer to receive the number of units written to the destination. If
* pDestLength!=NULL then *pDestLength is always set to the
* number of output units corresponding to the transformation of
* all the input units, even in case of a buffer overflow.
* @param src The original source string
* @param srcLength The length of the original string. If -1, then src must be zero-terminated.
* @param pErrorCode Must be a valid pointer to an error code value,
* which must not indicate a failure before the function call.
* @return The pointer to destination buffer.
* @stable ICU 2.0
*/
U_STABLE UChar* U_EXPORT2
u_strFromWCS(UChar *dest,
int32_t destCapacity,
int32_t *pDestLength,
const wchar_t *src,
int32_t srcLength,
UErrorCode *pErrorCode);
#endif /* defined(U_WCHAR_IS_UTF16) || defined(U_WCHAR_IS_UTF32) || !UCONFIG_NO_CONVERSION */
/**
* Convert a UTF-16 string to UTF-8.
* If the input string is not well-formed, then the U_INVALID_CHAR_FOUND error code is set.
*
* @param dest A buffer for the result string. The result will be zero-terminated if
* the buffer is large enough.
* @param destCapacity The size of the buffer (number of chars). If it is 0, then
* dest may be NULL and the function will only return the length of the
* result without writing any of the result string (pre-flighting).
* @param pDestLength A pointer to receive the number of units written to the destination. If
* pDestLength!=NULL then *pDestLength is always set to the
* number of output units corresponding to the transformation of
* all the input units, even in case of a buffer overflow.
* @param src The original source string
* @param srcLength The length of the original string. If -1, then src must be zero-terminated.
* @param pErrorCode Must be a valid pointer to an error code value,
* which must not indicate a failure before the function call.
* @return The pointer to destination buffer.
* @stable ICU 2.0
* @see u_strToUTF8WithSub
* @see u_strFromUTF8
*/
U_STABLE char* U_EXPORT2
u_strToUTF8(char *dest,
int32_t destCapacity,
int32_t *pDestLength,
const UChar *src,
int32_t srcLength,
UErrorCode *pErrorCode);
/**
* Convert a UTF-8 string to UTF-16.
* If the input string is not well-formed, then the U_INVALID_CHAR_FOUND error code is set.
*
* @param dest A buffer for the result string. The result will be zero-terminated if
* the buffer is large enough.
* @param destCapacity The size of the buffer (number of UChars). If it is 0, then
* dest may be NULL and the function will only return the length of the
* result without writing any of the result string (pre-flighting).
* @param pDestLength A pointer to receive the number of units written to the destination. If
* pDestLength!=NULL then *pDestLength is always set to the
* number of output units corresponding to the transformation of
* all the input units, even in case of a buffer overflow.
* @param src The original source string
* @param srcLength The length of the original string. If -1, then src must be zero-terminated.
* @param pErrorCode Must be a valid pointer to an error code value,
* which must not indicate a failure before the function call.
* @return The pointer to destination buffer.
* @stable ICU 2.0
* @see u_strFromUTF8WithSub
* @see u_strFromUTF8Lenient
*/
U_STABLE UChar* U_EXPORT2
u_strFromUTF8(UChar *dest,
int32_t destCapacity,
int32_t *pDestLength,
const char *src,
int32_t srcLength,
UErrorCode *pErrorCode);
/**
* Convert a UTF-16 string to UTF-8.
*
* Same as u_strToUTF8() except for the additional subchar which is output for
* illegal input sequences, instead of stopping with the U_INVALID_CHAR_FOUND error code.
* With subchar==U_SENTINEL, this function behaves exactly like u_strToUTF8().
*
* @param dest A buffer for the result string. The result will be zero-terminated if
* the buffer is large enough.
* @param destCapacity The size of the buffer (number of chars). If it is 0, then
* dest may be NULL and the function will only return the length of the
* result without writing any of the result string (pre-flighting).
* @param pDestLength A pointer to receive the number of units written to the destination. If
* pDestLength!=NULL then *pDestLength is always set to the
* number of output units corresponding to the transformation of
* all the input units, even in case of a buffer overflow.
* @param src The original source string
* @param srcLength The length of the original string. If -1, then src must be zero-terminated.
* @param subchar The substitution character to use in place of an illegal input sequence,
* or U_SENTINEL if the function is to return with U_INVALID_CHAR_FOUND instead.
* A substitution character can be any valid Unicode code point (up to U+10FFFF)
* except for surrogate code points (U+D800..U+DFFF).
* The recommended value is U+FFFD "REPLACEMENT CHARACTER".
* @param pNumSubstitutions Output parameter receiving the number of substitutions if subchar>=0.
* Set to 0 if no substitutions occur or subchar<0.
* pNumSubstitutions can be NULL.
* @param pErrorCode Pointer to a standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return The pointer to destination buffer.
* @see u_strToUTF8
* @see u_strFromUTF8WithSub
* @stable ICU 3.6
*/
U_STABLE char* U_EXPORT2
u_strToUTF8WithSub(char *dest,
int32_t destCapacity,
int32_t *pDestLength,
const UChar *src,
int32_t srcLength,
UChar32 subchar, int32_t *pNumSubstitutions,
UErrorCode *pErrorCode);
/**
* Convert a UTF-8 string to UTF-16.
*
* Same as u_strFromUTF8() except for the additional subchar which is output for
* illegal input sequences, instead of stopping with the U_INVALID_CHAR_FOUND error code.
* With subchar==U_SENTINEL, this function behaves exactly like u_strFromUTF8().
*
* @param dest A buffer for the result string. The result will be zero-terminated if
* the buffer is large enough.
* @param destCapacity The size of the buffer (number of UChars). If it is 0, then
* dest may be NULL and the function will only return the length of the
* result without writing any of the result string (pre-flighting).
* @param pDestLength A pointer to receive the number of units written to the destination. If
* pDestLength!=NULL then *pDestLength is always set to the
* number of output units corresponding to the transformation of
* all the input units, even in case of a buffer overflow.
* @param src The original source string
* @param srcLength The length of the original string. If -1, then src must be zero-terminated.
* @param subchar The substitution character to use in place of an illegal input sequence,
* or U_SENTINEL if the function is to return with U_INVALID_CHAR_FOUND instead.
* A substitution character can be any valid Unicode code point (up to U+10FFFF)
* except for surrogate code points (U+D800..U+DFFF).
* The recommended value is U+FFFD "REPLACEMENT CHARACTER".
* @param pNumSubstitutions Output parameter receiving the number of substitutions if subchar>=0.
* Set to 0 if no substitutions occur or subchar<0.
* pNumSubstitutions can be NULL.
* @param pErrorCode Pointer to a standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return The pointer to destination buffer.
* @see u_strFromUTF8
* @see u_strFromUTF8Lenient
* @see u_strToUTF8WithSub
* @stable ICU 3.6
*/
U_STABLE UChar* U_EXPORT2
u_strFromUTF8WithSub(UChar *dest,
int32_t destCapacity,
int32_t *pDestLength,
const char *src,
int32_t srcLength,
UChar32 subchar, int32_t *pNumSubstitutions,
UErrorCode *pErrorCode);
/**
* Convert a UTF-8 string to UTF-16.
*
* Same as u_strFromUTF8() except that this function is designed to be very fast,
* which it achieves by being lenient about malformed UTF-8 sequences.
* This function is intended for use in environments where UTF-8 text is
* expected to be well-formed.
*
* Its semantics are:
* - Well-formed UTF-8 text is correctly converted to well-formed UTF-16 text.
* - The function will not read beyond the input string, nor write beyond
* the destCapacity.
* - Malformed UTF-8 results in "garbage" 16-bit Unicode strings which may not
* be well-formed UTF-16.
* The function will resynchronize to valid code point boundaries
* within a small number of code points after an illegal sequence.
* - Non-shortest forms are not detected and will result in "spoofing" output.
*
* For further performance improvement, if srcLength is given (>=0),
* then it must be destCapacity>=srcLength.
*
* There is no inverse u_strToUTF8Lenient() function because there is practically
* no performance gain from not checking that a UTF-16 string is well-formed.
*
* @param dest A buffer for the result string. The result will be zero-terminated if
* the buffer is large enough.
* @param destCapacity The size of the buffer (number of UChars). If it is 0, then
* dest may be NULL and the function will only return the length of the
* result without writing any of the result string (pre-flighting).
* Unlike for other ICU functions, if srcLength>=0 then it
* must be destCapacity>=srcLength.
* @param pDestLength A pointer to receive the number of units written to the destination. If
* pDestLength!=NULL then *pDestLength is always set to the
* number of output units corresponding to the transformation of
* all the input units, even in case of a buffer overflow.
* Unlike for other ICU functions, if srcLength>=0 but
* destCapacity<srcLength, then *pDestLength will be set to srcLength
* (and U_BUFFER_OVERFLOW_ERROR will be set)
* regardless of the actual result length.
* @param src The original source string
* @param srcLength The length of the original string. If -1, then src must be zero-terminated.
* @param pErrorCode Pointer to a standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return The pointer to destination buffer.
* @see u_strFromUTF8
* @see u_strFromUTF8WithSub
* @see u_strToUTF8WithSub
* @stable ICU 3.6
*/
U_STABLE UChar * U_EXPORT2
u_strFromUTF8Lenient(UChar *dest,
int32_t destCapacity,
int32_t *pDestLength,
const char *src,
int32_t srcLength,
UErrorCode *pErrorCode);
/**
* Convert a UTF-16 string to UTF-32.
* If the input string is not well-formed, then the U_INVALID_CHAR_FOUND error code is set.
*
* @param dest A buffer for the result string. The result will be zero-terminated if
* the buffer is large enough.
* @param destCapacity The size of the buffer (number of UChar32s). If it is 0, then
* dest may be NULL and the function will only return the length of the
* result without writing any of the result string (pre-flighting).
* @param pDestLength A pointer to receive the number of units written to the destination. If
* pDestLength!=NULL then *pDestLength is always set to the
* number of output units corresponding to the transformation of
* all the input units, even in case of a buffer overflow.
* @param src The original source string
* @param srcLength The length of the original string. If -1, then src must be zero-terminated.
* @param pErrorCode Must be a valid pointer to an error code value,
* which must not indicate a failure before the function call.
* @return The pointer to destination buffer.
* @see u_strToUTF32WithSub
* @see u_strFromUTF32
* @stable ICU 2.0
*/
U_STABLE UChar32* U_EXPORT2
u_strToUTF32(UChar32 *dest,
int32_t destCapacity,
int32_t *pDestLength,
const UChar *src,
int32_t srcLength,
UErrorCode *pErrorCode);
/**
* Convert a UTF-32 string to UTF-16.
* If the input string is not well-formed, then the U_INVALID_CHAR_FOUND error code is set.
*
* @param dest A buffer for the result string. The result will be zero-terminated if
* the buffer is large enough.
* @param destCapacity The size of the buffer (number of UChars). If it is 0, then
* dest may be NULL and the function will only return the length of the
* result without writing any of the result string (pre-flighting).
* @param pDestLength A pointer to receive the number of units written to the destination. If
* pDestLength!=NULL then *pDestLength is always set to the
* number of output units corresponding to the transformation of
* all the input units, even in case of a buffer overflow.
* @param src The original source string
* @param srcLength The length of the original string. If -1, then src must be zero-terminated.
* @param pErrorCode Must be a valid pointer to an error code value,
* which must not indicate a failure before the function call.
* @return The pointer to destination buffer.
* @see u_strFromUTF32WithSub
* @see u_strToUTF32
* @stable ICU 2.0
*/
U_STABLE UChar* U_EXPORT2
u_strFromUTF32(UChar *dest,
int32_t destCapacity,
int32_t *pDestLength,
const UChar32 *src,
int32_t srcLength,
UErrorCode *pErrorCode);
/**
* Convert a UTF-16 string to UTF-32.
*
* Same as u_strToUTF32() except for the additional subchar which is output for
* illegal input sequences, instead of stopping with the U_INVALID_CHAR_FOUND error code.
* With subchar==U_SENTINEL, this function behaves exactly like u_strToUTF32().
*
* @param dest A buffer for the result string. The result will be zero-terminated if
* the buffer is large enough.
* @param destCapacity The size of the buffer (number of UChar32s). If it is 0, then
* dest may be NULL and the function will only return the length of the
* result without writing any of the result string (pre-flighting).
* @param pDestLength A pointer to receive the number of units written to the destination. If
* pDestLength!=NULL then *pDestLength is always set to the
* number of output units corresponding to the transformation of
* all the input units, even in case of a buffer overflow.
* @param src The original source string
* @param srcLength The length of the original string. If -1, then src must be zero-terminated.
* @param subchar The substitution character to use in place of an illegal input sequence,
* or U_SENTINEL if the function is to return with U_INVALID_CHAR_FOUND instead.
* A substitution character can be any valid Unicode code point (up to U+10FFFF)
* except for surrogate code points (U+D800..U+DFFF).
* The recommended value is U+FFFD "REPLACEMENT CHARACTER".
* @param pNumSubstitutions Output parameter receiving the number of substitutions if subchar>=0.
* Set to 0 if no substitutions occur or subchar<0.
* pNumSubstitutions can be NULL.
* @param pErrorCode Pointer to a standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return The pointer to destination buffer.
* @see u_strToUTF32
* @see u_strFromUTF32WithSub
* @stable ICU 4.2
*/
U_STABLE UChar32* U_EXPORT2
u_strToUTF32WithSub(UChar32 *dest,
int32_t destCapacity,
int32_t *pDestLength,
const UChar *src,
int32_t srcLength,
UChar32 subchar, int32_t *pNumSubstitutions,
UErrorCode *pErrorCode);
/**
* Convert a UTF-32 string to UTF-16.
*
* Same as u_strFromUTF32() except for the additional subchar which is output for
* illegal input sequences, instead of stopping with the U_INVALID_CHAR_FOUND error code.
* With subchar==U_SENTINEL, this function behaves exactly like u_strFromUTF32().
*
* @param dest A buffer for the result string. The result will be zero-terminated if
* the buffer is large enough.
* @param destCapacity The size of the buffer (number of UChars). If it is 0, then
* dest may be NULL and the function will only return the length of the
* result without writing any of the result string (pre-flighting).
* @param pDestLength A pointer to receive the number of units written to the destination. If
* pDestLength!=NULL then *pDestLength is always set to the
* number of output units corresponding to the transformation of
* all the input units, even in case of a buffer overflow.
* @param src The original source string
* @param srcLength The length of the original string. If -1, then src must be zero-terminated.
* @param subchar The substitution character to use in place of an illegal input sequence,
* or U_SENTINEL if the function is to return with U_INVALID_CHAR_FOUND instead.
* A substitution character can be any valid Unicode code point (up to U+10FFFF)
* except for surrogate code points (U+D800..U+DFFF).
* The recommended value is U+FFFD "REPLACEMENT CHARACTER".
* @param pNumSubstitutions Output parameter receiving the number of substitutions if subchar>=0.
* Set to 0 if no substitutions occur or subchar<0.
* pNumSubstitutions can be NULL.
* @param pErrorCode Pointer to a standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return The pointer to destination buffer.
* @see u_strFromUTF32
* @see u_strToUTF32WithSub
* @stable ICU 4.2
*/
U_STABLE UChar* U_EXPORT2
u_strFromUTF32WithSub(UChar *dest,
int32_t destCapacity,
int32_t *pDestLength,
const UChar32 *src,
int32_t srcLength,
UChar32 subchar, int32_t *pNumSubstitutions,
UErrorCode *pErrorCode);
/**
* Convert a 16-bit Unicode string to Java Modified UTF-8.
* See http://java.sun.com/javase/6/docs/api/java/io/DataInput.html#modified-utf-8
*
* This function behaves according to the documentation for Java DataOutput.writeUTF()
* except that it does not encode the output length in the destination buffer
* and does not have an output length restriction.
* See http://java.sun.com/javase/6/docs/api/java/io/DataOutput.html#writeUTF(java.lang.String)
*
* The input string need not be well-formed UTF-16.
* (Therefore there is no subchar parameter.)
*
* @param dest A buffer for the result string. The result will be zero-terminated if
* the buffer is large enough.
* @param destCapacity The size of the buffer (number of chars). If it is 0, then
* dest may be NULL and the function will only return the length of the
* result without writing any of the result string (pre-flighting).
* @param pDestLength A pointer to receive the number of units written to the destination. If
* pDestLength!=NULL then *pDestLength is always set to the
* number of output units corresponding to the transformation of
* all the input units, even in case of a buffer overflow.
* @param src The original source string
* @param srcLength The length of the original string. If -1, then src must be zero-terminated.
* @param pErrorCode Pointer to a standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return The pointer to destination buffer.
* @stable ICU 4.4
* @see u_strToUTF8WithSub
* @see u_strFromJavaModifiedUTF8WithSub
*/
U_STABLE char* U_EXPORT2
u_strToJavaModifiedUTF8(
char *dest,
int32_t destCapacity,
int32_t *pDestLength,
const UChar *src,
int32_t srcLength,
UErrorCode *pErrorCode);
/**
* Convert a Java Modified UTF-8 string to a 16-bit Unicode string.
* If the input string is not well-formed and no substitution char is specified,
* then the U_INVALID_CHAR_FOUND error code is set.
*
* This function behaves according to the documentation for Java DataInput.readUTF()
* except that it takes a length parameter rather than
* interpreting the first two input bytes as the length.
* See http://java.sun.com/javase/6/docs/api/java/io/DataInput.html#readUTF()
*
* The output string may not be well-formed UTF-16.
*
* @param dest A buffer for the result string. The result will be zero-terminated if
* the buffer is large enough.
* @param destCapacity The size of the buffer (number of UChars). If it is 0, then
* dest may be NULL and the function will only return the length of the
* result without writing any of the result string (pre-flighting).
* @param pDestLength A pointer to receive the number of units written to the destination. If
* pDestLength!=NULL then *pDestLength is always set to the
* number of output units corresponding to the transformation of
* all the input units, even in case of a buffer overflow.
* @param src The original source string
* @param srcLength The length of the original string. If -1, then src must be zero-terminated.
* @param subchar The substitution character to use in place of an illegal input sequence,
* or U_SENTINEL if the function is to return with U_INVALID_CHAR_FOUND instead.
* A substitution character can be any valid Unicode code point (up to U+10FFFF)
* except for surrogate code points (U+D800..U+DFFF).
* The recommended value is U+FFFD "REPLACEMENT CHARACTER".
* @param pNumSubstitutions Output parameter receiving the number of substitutions if subchar>=0.
* Set to 0 if no substitutions occur or subchar<0.
* pNumSubstitutions can be NULL.
* @param pErrorCode Pointer to a standard ICU error code. Its input value must
* pass the U_SUCCESS() test, or else the function returns
* immediately. Check for U_FAILURE() on output or use with
* function chaining. (See User Guide for details.)
* @return The pointer to destination buffer.
* @see u_strFromUTF8WithSub
* @see u_strFromUTF8Lenient
* @see u_strToJavaModifiedUTF8
* @stable ICU 4.4
*/
U_STABLE UChar* U_EXPORT2
u_strFromJavaModifiedUTF8WithSub(
UChar *dest,
int32_t destCapacity,
int32_t *pDestLength,
const char *src,
int32_t srcLength,
UChar32 subchar, int32_t *pNumSubstitutions,
UErrorCode *pErrorCode);
#endif
|