This file is indexed.

/usr/include/unicode/uchar.h is in libicu-dev 4.8.1.1-3ubuntu0.7.

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
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
/*
**********************************************************************
*   Copyright (C) 1997-2010, International Business Machines
*   Corporation and others.  All Rights Reserved.
**********************************************************************
*
* File UCHAR.H
*
* Modification History:
*
*   Date        Name        Description
*   04/02/97    aliu        Creation.
*   03/29/99    helena      Updated for C APIs.
*   4/15/99     Madhu       Updated for C Implementation and Javadoc
*   5/20/99     Madhu       Added the function u_getVersion()
*   8/19/1999   srl         Upgraded scripts to Unicode 3.0
*   8/27/1999   schererm    UCharDirection constants: U_...
*   11/11/1999  weiv        added u_isalnum(), cleaned comments
*   01/11/2000  helena      Renamed u_getVersion to u_getUnicodeVersion().
******************************************************************************
*/

#ifndef UCHAR_H
#define UCHAR_H

#include "unicode/utypes.h"

U_CDECL_BEGIN

/*==========================================================================*/
/* Unicode version number                                                   */
/*==========================================================================*/
/**
 * Unicode version number, default for the current ICU version.
 * The actual Unicode Character Database (UCD) data is stored in uprops.dat
 * and may be generated from UCD files from a different Unicode version.
 * Call u_getUnicodeVersion to get the actual Unicode version of the data.
 *
 * @see u_getUnicodeVersion
 * @stable ICU 2.0
 */
#define U_UNICODE_VERSION "6.0"

/**
 * \file
 * \brief C API: Unicode Properties
 *
 * This C API provides low-level access to the Unicode Character Database.
 * In addition to raw property values, some convenience functions calculate
 * derived properties, for example for Java-style programming.
 *
 * Unicode assigns each code point (not just assigned character) values for
 * many properties.
 * Most of them are simple boolean flags, or constants from a small enumerated list.
 * For some properties, values are strings or other relatively more complex types.
 *
 * For more information see
 * "About the Unicode Character Database" (http://www.unicode.org/ucd/)
 * and the ICU User Guide chapter on Properties (http://icu-project.org/userguide/properties.html).
 *
 * Many functions are designed to match java.lang.Character functions.
 * See the individual function documentation,
 * and see the JDK 1.4 java.lang.Character documentation
 * at http://java.sun.com/j2se/1.4/docs/api/java/lang/Character.html
 *
 * There are also functions that provide easy migration from C/POSIX functions
 * like isblank(). Their use is generally discouraged because the C/POSIX
 * standards do not define their semantics beyond the ASCII range, which means
 * that different implementations exhibit very different behavior.
 * Instead, Unicode properties should be used directly.
 *
 * There are also only a few, broad C/POSIX character classes, and they tend
 * to be used for conflicting purposes. For example, the "isalpha()" class
 * is sometimes used to determine word boundaries, while a more sophisticated
 * approach would at least distinguish initial letters from continuation
 * characters (the latter including combining marks).
 * (In ICU, BreakIterator is the most sophisticated API for word boundaries.)
 * Another example: There is no "istitle()" class for titlecase characters.
 *
 * ICU 3.4 and later provides API access for all twelve C/POSIX character classes.
 * ICU implements them according to the Standard Recommendations in
 * Annex C: Compatibility Properties of UTS #18 Unicode Regular Expressions
 * (http://www.unicode.org/reports/tr18/#Compatibility_Properties).
 *
 * API access for C/POSIX character classes is as follows:
 * - alpha:     u_isUAlphabetic(c) or u_hasBinaryProperty(c, UCHAR_ALPHABETIC)
 * - lower:     u_isULowercase(c) or u_hasBinaryProperty(c, UCHAR_LOWERCASE)
 * - upper:     u_isUUppercase(c) or u_hasBinaryProperty(c, UCHAR_UPPERCASE)
 * - punct:     u_ispunct(c)
 * - digit:     u_isdigit(c) or u_charType(c)==U_DECIMAL_DIGIT_NUMBER
 * - xdigit:    u_isxdigit(c) or u_hasBinaryProperty(c, UCHAR_POSIX_XDIGIT)
 * - alnum:     u_hasBinaryProperty(c, UCHAR_POSIX_ALNUM)
 * - space:     u_isUWhiteSpace(c) or u_hasBinaryProperty(c, UCHAR_WHITE_SPACE)
 * - blank:     u_isblank(c) or u_hasBinaryProperty(c, UCHAR_POSIX_BLANK)
 * - cntrl:     u_charType(c)==U_CONTROL_CHAR
 * - graph:     u_hasBinaryProperty(c, UCHAR_POSIX_GRAPH)
 * - print:     u_hasBinaryProperty(c, UCHAR_POSIX_PRINT)
 *
 * Note: Some of the u_isxyz() functions in uchar.h predate, and do not match,
 * the Standard Recommendations in UTS #18. Instead, they match Java
 * functions according to their API documentation.
 *
 * \htmlonly
 * The C/POSIX character classes are also available in UnicodeSet patterns,
 * using patterns like [:graph:] or \p{graph}.
 * \endhtmlonly
 *
 * Note: There are several ICU whitespace functions.
 * Comparison:
 * - u_isUWhiteSpace=UCHAR_WHITE_SPACE: Unicode White_Space property;
 *       most of general categories "Z" (separators) + most whitespace ISO controls
 *       (including no-break spaces, but excluding IS1..IS4 and ZWSP)
 * - u_isWhitespace: Java isWhitespace; Z + whitespace ISO controls but excluding no-break spaces
 * - u_isJavaSpaceChar: Java isSpaceChar; just Z (including no-break spaces)
 * - u_isspace: Z + whitespace ISO controls (including no-break spaces)
 * - u_isblank: "horizontal spaces" = TAB + Zs - ZWSP
 */

/**
 * Constants.
 */

/** The lowest Unicode code point value. Code points are non-negative. @stable ICU 2.0 */
#define UCHAR_MIN_VALUE 0

/**
 * The highest Unicode code point value (scalar value) according to
 * The Unicode Standard. This is a 21-bit value (20.1 bits, rounded up).
 * For a single character, UChar32 is a simple type that can hold any code point value.
 *
 * @see UChar32
 * @stable ICU 2.0
 */
#define UCHAR_MAX_VALUE 0x10ffff

/**
 * Get a single-bit bit set (a flag) from a bit number 0..31.
 * @stable ICU 2.1
 */
#define U_MASK(x) ((uint32_t)1<<(x))

/*
 * !! Note: Several comments in this file are machine-read by the
 * genpname tool.  These comments describe the correspondence between
 * icu enum constants and UCD entities.  Do not delete them.  Update
 * these comments as needed.
 *
 * Any comment of the form "/ *[name]* /" (spaces added) is such
 * a comment.
 *
 * The U_JG_* and U_GC_*_MASK constants are matched by their symbolic
 * name, which must match PropertyValueAliases.txt.
 */

/**
 * Selection constants for Unicode properties.
 * These constants are used in functions like u_hasBinaryProperty to select
 * one of the Unicode properties.
 *
 * The properties APIs are intended to reflect Unicode properties as defined
 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
 * For details about the properties see http://www.unicode.org/ucd/ .
 * For names of Unicode properties see the UCD file PropertyAliases.txt.
 *
 * Important: If ICU is built with UCD files from Unicode versions below, e.g., 3.2,
 * then properties marked with "new in Unicode 3.2" are not or not fully available.
 * Check u_getUnicodeVersion to be sure.
 *
 * @see u_hasBinaryProperty
 * @see u_getIntPropertyValue
 * @see u_getUnicodeVersion
 * @stable ICU 2.1
 */
typedef enum UProperty {
    /*  See note !!.  Comments of the form "Binary property Dash",
        "Enumerated property Script", "Double property Numeric_Value",
        and "String property Age" are read by genpname. */

    /*  Note: Place UCHAR_ALPHABETIC before UCHAR_BINARY_START so that
    debuggers display UCHAR_ALPHABETIC as the symbolic name for 0,
    rather than UCHAR_BINARY_START.  Likewise for other *_START
    identifiers. */

    /** Binary property Alphabetic. Same as u_isUAlphabetic, different from u_isalpha.
        Lu+Ll+Lt+Lm+Lo+Nl+Other_Alphabetic @stable ICU 2.1 */
    UCHAR_ALPHABETIC=0,
    /** First constant for binary Unicode properties. @stable ICU 2.1 */
    UCHAR_BINARY_START=UCHAR_ALPHABETIC,
    /** Binary property ASCII_Hex_Digit. 0-9 A-F a-f @stable ICU 2.1 */
    UCHAR_ASCII_HEX_DIGIT=1,
    /** Binary property Bidi_Control.
        Format controls which have specific functions
        in the Bidi Algorithm. @stable ICU 2.1 */
    UCHAR_BIDI_CONTROL=2,
    /** Binary property Bidi_Mirrored.
        Characters that may change display in RTL text.
        Same as u_isMirrored.
        See Bidi Algorithm, UTR 9. @stable ICU 2.1 */
    UCHAR_BIDI_MIRRORED=3,
    /** Binary property Dash. Variations of dashes. @stable ICU 2.1 */
    UCHAR_DASH=4,
    /** Binary property Default_Ignorable_Code_Point (new in Unicode 3.2).
        Ignorable in most processing.
        <2060..206F, FFF0..FFFB, E0000..E0FFF>+Other_Default_Ignorable_Code_Point+(Cf+Cc+Cs-White_Space) @stable ICU 2.1 */
    UCHAR_DEFAULT_IGNORABLE_CODE_POINT=5,
    /** Binary property Deprecated (new in Unicode 3.2).
        The usage of deprecated characters is strongly discouraged. @stable ICU 2.1 */
    UCHAR_DEPRECATED=6,
    /** Binary property Diacritic. Characters that linguistically modify
        the meaning of another character to which they apply. @stable ICU 2.1 */
    UCHAR_DIACRITIC=7,
    /** Binary property Extender.
        Extend the value or shape of a preceding alphabetic character,
        e.g., length and iteration marks. @stable ICU 2.1 */
    UCHAR_EXTENDER=8,
    /** Binary property Full_Composition_Exclusion.
        CompositionExclusions.txt+Singleton Decompositions+
        Non-Starter Decompositions. @stable ICU 2.1 */
    UCHAR_FULL_COMPOSITION_EXCLUSION=9,
    /** Binary property Grapheme_Base (new in Unicode 3.2).
        For programmatic determination of grapheme cluster boundaries.
        [0..10FFFF]-Cc-Cf-Cs-Co-Cn-Zl-Zp-Grapheme_Link-Grapheme_Extend-CGJ @stable ICU 2.1 */
    UCHAR_GRAPHEME_BASE=10,
    /** Binary property Grapheme_Extend (new in Unicode 3.2).
        For programmatic determination of grapheme cluster boundaries.
        Me+Mn+Mc+Other_Grapheme_Extend-Grapheme_Link-CGJ @stable ICU 2.1 */
    UCHAR_GRAPHEME_EXTEND=11,
    /** Binary property Grapheme_Link (new in Unicode 3.2).
        For programmatic determination of grapheme cluster boundaries. @stable ICU 2.1 */
    UCHAR_GRAPHEME_LINK=12,
    /** Binary property Hex_Digit.
        Characters commonly used for hexadecimal numbers. @stable ICU 2.1 */
    UCHAR_HEX_DIGIT=13,
    /** Binary property Hyphen. Dashes used to mark connections
        between pieces of words, plus the Katakana middle dot. @stable ICU 2.1 */
    UCHAR_HYPHEN=14,
    /** Binary property ID_Continue.
        Characters that can continue an identifier.
        DerivedCoreProperties.txt also says "NOTE: Cf characters should be filtered out."
        ID_Start+Mn+Mc+Nd+Pc @stable ICU 2.1 */
    UCHAR_ID_CONTINUE=15,
    /** Binary property ID_Start.
        Characters that can start an identifier.
        Lu+Ll+Lt+Lm+Lo+Nl @stable ICU 2.1 */
    UCHAR_ID_START=16,
    /** Binary property Ideographic.
        CJKV ideographs. @stable ICU 2.1 */
    UCHAR_IDEOGRAPHIC=17,
    /** Binary property IDS_Binary_Operator (new in Unicode 3.2).
        For programmatic determination of
        Ideographic Description Sequences. @stable ICU 2.1 */
    UCHAR_IDS_BINARY_OPERATOR=18,
    /** Binary property IDS_Trinary_Operator (new in Unicode 3.2).
        For programmatic determination of
        Ideographic Description Sequences. @stable ICU 2.1 */
    UCHAR_IDS_TRINARY_OPERATOR=19,
    /** Binary property Join_Control.
        Format controls for cursive joining and ligation. @stable ICU 2.1 */
    UCHAR_JOIN_CONTROL=20,
    /** Binary property Logical_Order_Exception (new in Unicode 3.2).
        Characters that do not use logical order and
        require special handling in most processing. @stable ICU 2.1 */
    UCHAR_LOGICAL_ORDER_EXCEPTION=21,
    /** Binary property Lowercase. Same as u_isULowercase, different from u_islower.
        Ll+Other_Lowercase @stable ICU 2.1 */
    UCHAR_LOWERCASE=22,
    /** Binary property Math. Sm+Other_Math @stable ICU 2.1 */
    UCHAR_MATH=23,
    /** Binary property Noncharacter_Code_Point.
        Code points that are explicitly defined as illegal
        for the encoding of characters. @stable ICU 2.1 */
    UCHAR_NONCHARACTER_CODE_POINT=24,
    /** Binary property Quotation_Mark. @stable ICU 2.1 */
    UCHAR_QUOTATION_MARK=25,
    /** Binary property Radical (new in Unicode 3.2).
        For programmatic determination of
        Ideographic Description Sequences. @stable ICU 2.1 */
    UCHAR_RADICAL=26,
    /** Binary property Soft_Dotted (new in Unicode 3.2).
        Characters with a "soft dot", like i or j.
        An accent placed on these characters causes
        the dot to disappear. @stable ICU 2.1 */
    UCHAR_SOFT_DOTTED=27,
    /** Binary property Terminal_Punctuation.
        Punctuation characters that generally mark
        the end of textual units. @stable ICU 2.1 */
    UCHAR_TERMINAL_PUNCTUATION=28,
    /** Binary property Unified_Ideograph (new in Unicode 3.2).
        For programmatic determination of
        Ideographic Description Sequences. @stable ICU 2.1 */
    UCHAR_UNIFIED_IDEOGRAPH=29,
    /** Binary property Uppercase. Same as u_isUUppercase, different from u_isupper.
        Lu+Other_Uppercase @stable ICU 2.1 */
    UCHAR_UPPERCASE=30,
    /** Binary property White_Space.
        Same as u_isUWhiteSpace, different from u_isspace and u_isWhitespace.
        Space characters+TAB+CR+LF-ZWSP-ZWNBSP @stable ICU 2.1 */
    UCHAR_WHITE_SPACE=31,
    /** Binary property XID_Continue.
        ID_Continue modified to allow closure under
        normalization forms NFKC and NFKD. @stable ICU 2.1 */
    UCHAR_XID_CONTINUE=32,
    /** Binary property XID_Start. ID_Start modified to allow
        closure under normalization forms NFKC and NFKD. @stable ICU 2.1 */
    UCHAR_XID_START=33,
    /** Binary property Case_Sensitive. Either the source of a case
        mapping or _in_ the target of a case mapping. Not the same as
        the general category Cased_Letter. @stable ICU 2.6 */
   UCHAR_CASE_SENSITIVE=34,
    /** Binary property STerm (new in Unicode 4.0.1).
        Sentence Terminal. Used in UAX #29: Text Boundaries
        (http://www.unicode.org/reports/tr29/)
        @stable ICU 3.0 */
    UCHAR_S_TERM=35,
    /** Binary property Variation_Selector (new in Unicode 4.0.1).
        Indicates all those characters that qualify as Variation Selectors.
        For details on the behavior of these characters,
        see StandardizedVariants.html and 15.6 Variation Selectors.
        @stable ICU 3.0 */
    UCHAR_VARIATION_SELECTOR=36,
    /** Binary property NFD_Inert.
        ICU-specific property for characters that are inert under NFD,
        i.e., they do not interact with adjacent characters.
        See the documentation for the Normalizer2 class and the
        Normalizer2::isInert() method.
        @stable ICU 3.0 */
    UCHAR_NFD_INERT=37,
    /** Binary property NFKD_Inert.
        ICU-specific property for characters that are inert under NFKD,
        i.e., they do not interact with adjacent characters.
        See the documentation for the Normalizer2 class and the
        Normalizer2::isInert() method.
        @stable ICU 3.0 */
    UCHAR_NFKD_INERT=38,
    /** Binary property NFC_Inert.
        ICU-specific property for characters that are inert under NFC,
        i.e., they do not interact with adjacent characters.
        See the documentation for the Normalizer2 class and the
        Normalizer2::isInert() method.
        @stable ICU 3.0 */
    UCHAR_NFC_INERT=39,
    /** Binary property NFKC_Inert.
        ICU-specific property for characters that are inert under NFKC,
        i.e., they do not interact with adjacent characters.
        See the documentation for the Normalizer2 class and the
        Normalizer2::isInert() method.
        @stable ICU 3.0 */
    UCHAR_NFKC_INERT=40,
    /** Binary Property Segment_Starter.
        ICU-specific property for characters that are starters in terms of
        Unicode normalization and combining character sequences.
        They have ccc=0 and do not occur in non-initial position of the
        canonical decomposition of any character
        (like a-umlaut in NFD and a Jamo T in an NFD(Hangul LVT)).
        ICU uses this property for segmenting a string for generating a set of
        canonically equivalent strings, e.g. for canonical closure while
        processing collation tailoring rules.
        @stable ICU 3.0 */
    UCHAR_SEGMENT_STARTER=41,
    /** Binary property Pattern_Syntax (new in Unicode 4.1).
        See UAX #31 Identifier and Pattern Syntax
        (http://www.unicode.org/reports/tr31/)
        @stable ICU 3.4 */
    UCHAR_PATTERN_SYNTAX=42,
    /** Binary property Pattern_White_Space (new in Unicode 4.1).
        See UAX #31 Identifier and Pattern Syntax
        (http://www.unicode.org/reports/tr31/)
        @stable ICU 3.4 */
    UCHAR_PATTERN_WHITE_SPACE=43,
    /** Binary property alnum (a C/POSIX character class).
        Implemented according to the UTS #18 Annex C Standard Recommendation.
        See the uchar.h file documentation.
        @stable ICU 3.4 */
    UCHAR_POSIX_ALNUM=44,
    /** Binary property blank (a C/POSIX character class).
        Implemented according to the UTS #18 Annex C Standard Recommendation.
        See the uchar.h file documentation.
        @stable ICU 3.4 */
    UCHAR_POSIX_BLANK=45,
    /** Binary property graph (a C/POSIX character class).
        Implemented according to the UTS #18 Annex C Standard Recommendation.
        See the uchar.h file documentation.
        @stable ICU 3.4 */
    UCHAR_POSIX_GRAPH=46,
    /** Binary property print (a C/POSIX character class).
        Implemented according to the UTS #18 Annex C Standard Recommendation.
        See the uchar.h file documentation.
        @stable ICU 3.4 */
    UCHAR_POSIX_PRINT=47,
    /** Binary property xdigit (a C/POSIX character class).
        Implemented according to the UTS #18 Annex C Standard Recommendation.
        See the uchar.h file documentation.
        @stable ICU 3.4 */
    UCHAR_POSIX_XDIGIT=48,
    /** Binary property Cased. For Lowercase, Uppercase and Titlecase characters. @stable ICU 4.4 */
    UCHAR_CASED=49,
    /** Binary property Case_Ignorable. Used in context-sensitive case mappings. @stable ICU 4.4 */
    UCHAR_CASE_IGNORABLE=50,
    /** Binary property Changes_When_Lowercased. @stable ICU 4.4 */
    UCHAR_CHANGES_WHEN_LOWERCASED=51,
    /** Binary property Changes_When_Uppercased. @stable ICU 4.4 */
    UCHAR_CHANGES_WHEN_UPPERCASED=52,
    /** Binary property Changes_When_Titlecased. @stable ICU 4.4 */
    UCHAR_CHANGES_WHEN_TITLECASED=53,
    /** Binary property Changes_When_Casefolded. @stable ICU 4.4 */
    UCHAR_CHANGES_WHEN_CASEFOLDED=54,
    /** Binary property Changes_When_Casemapped. @stable ICU 4.4 */
    UCHAR_CHANGES_WHEN_CASEMAPPED=55,
    /** Binary property Changes_When_NFKC_Casefolded. @stable ICU 4.4 */
    UCHAR_CHANGES_WHEN_NFKC_CASEFOLDED=56,
    /** One more than the last constant for binary Unicode properties. @stable ICU 2.1 */
    UCHAR_BINARY_LIMIT=57,

    /** Enumerated property Bidi_Class.
        Same as u_charDirection, returns UCharDirection values. @stable ICU 2.2 */
    UCHAR_BIDI_CLASS=0x1000,
    /** First constant for enumerated/integer Unicode properties. @stable ICU 2.2 */
    UCHAR_INT_START=UCHAR_BIDI_CLASS,
    /** Enumerated property Block.
        Same as ublock_getCode, returns UBlockCode values. @stable ICU 2.2 */
    UCHAR_BLOCK=0x1001,
    /** Enumerated property Canonical_Combining_Class.
        Same as u_getCombiningClass, returns 8-bit numeric values. @stable ICU 2.2 */
    UCHAR_CANONICAL_COMBINING_CLASS=0x1002,
    /** Enumerated property Decomposition_Type.
        Returns UDecompositionType values. @stable ICU 2.2 */
    UCHAR_DECOMPOSITION_TYPE=0x1003,
    /** Enumerated property East_Asian_Width.
        See http://www.unicode.org/reports/tr11/
        Returns UEastAsianWidth values. @stable ICU 2.2 */
    UCHAR_EAST_ASIAN_WIDTH=0x1004,
    /** Enumerated property General_Category.
        Same as u_charType, returns UCharCategory values. @stable ICU 2.2 */
    UCHAR_GENERAL_CATEGORY=0x1005,
    /** Enumerated property Joining_Group.
        Returns UJoiningGroup values. @stable ICU 2.2 */
    UCHAR_JOINING_GROUP=0x1006,
    /** Enumerated property Joining_Type.
        Returns UJoiningType values. @stable ICU 2.2 */
    UCHAR_JOINING_TYPE=0x1007,
    /** Enumerated property Line_Break.
        Returns ULineBreak values. @stable ICU 2.2 */
    UCHAR_LINE_BREAK=0x1008,
    /** Enumerated property Numeric_Type.
        Returns UNumericType values. @stable ICU 2.2 */
    UCHAR_NUMERIC_TYPE=0x1009,
    /** Enumerated property Script.
        Same as uscript_getScript, returns UScriptCode values. @stable ICU 2.2 */
    UCHAR_SCRIPT=0x100A,
    /** Enumerated property Hangul_Syllable_Type, new in Unicode 4.
        Returns UHangulSyllableType values. @stable ICU 2.6 */
    UCHAR_HANGUL_SYLLABLE_TYPE=0x100B,
    /** Enumerated property NFD_Quick_Check.
        Returns UNormalizationCheckResult values. @stable ICU 3.0 */
    UCHAR_NFD_QUICK_CHECK=0x100C,
    /** Enumerated property NFKD_Quick_Check.
        Returns UNormalizationCheckResult values. @stable ICU 3.0 */
    UCHAR_NFKD_QUICK_CHECK=0x100D,
    /** Enumerated property NFC_Quick_Check.
        Returns UNormalizationCheckResult values. @stable ICU 3.0 */
    UCHAR_NFC_QUICK_CHECK=0x100E,
    /** Enumerated property NFKC_Quick_Check.
        Returns UNormalizationCheckResult values. @stable ICU 3.0 */
    UCHAR_NFKC_QUICK_CHECK=0x100F,
    /** Enumerated property Lead_Canonical_Combining_Class.
        ICU-specific property for the ccc of the first code point
        of the decomposition, or lccc(c)=ccc(NFD(c)[0]).
        Useful for checking for canonically ordered text;
        see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD .
        Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */
    UCHAR_LEAD_CANONICAL_COMBINING_CLASS=0x1010,
    /** Enumerated property Trail_Canonical_Combining_Class.
        ICU-specific property for the ccc of the last code point
        of the decomposition, or tccc(c)=ccc(NFD(c)[last]).
        Useful for checking for canonically ordered text;
        see UNORM_FCD and http://www.unicode.org/notes/tn5/#FCD .
        Returns 8-bit numeric values like UCHAR_CANONICAL_COMBINING_CLASS. @stable ICU 3.0 */
    UCHAR_TRAIL_CANONICAL_COMBINING_CLASS=0x1011,
    /** Enumerated property Grapheme_Cluster_Break (new in Unicode 4.1).
        Used in UAX #29: Text Boundaries
        (http://www.unicode.org/reports/tr29/)
        Returns UGraphemeClusterBreak values. @stable ICU 3.4 */
    UCHAR_GRAPHEME_CLUSTER_BREAK=0x1012,
    /** Enumerated property Sentence_Break (new in Unicode 4.1).
        Used in UAX #29: Text Boundaries
        (http://www.unicode.org/reports/tr29/)
        Returns USentenceBreak values. @stable ICU 3.4 */
    UCHAR_SENTENCE_BREAK=0x1013,
    /** Enumerated property Word_Break (new in Unicode 4.1).
        Used in UAX #29: Text Boundaries
        (http://www.unicode.org/reports/tr29/)
        Returns UWordBreakValues values. @stable ICU 3.4 */
    UCHAR_WORD_BREAK=0x1014,
    /** One more than the last constant for enumerated/integer Unicode properties. @stable ICU 2.2 */
    UCHAR_INT_LIMIT=0x1015,

    /** Bitmask property General_Category_Mask.
        This is the General_Category property returned as a bit mask.
        When used in u_getIntPropertyValue(c), same as U_MASK(u_charType(c)),
        returns bit masks for UCharCategory values where exactly one bit is set.
        When used with u_getPropertyValueName() and u_getPropertyValueEnum(),
        a multi-bit mask is used for sets of categories like "Letters".
        Mask values should be cast to uint32_t.
        @stable ICU 2.4 */
    UCHAR_GENERAL_CATEGORY_MASK=0x2000,
    /** First constant for bit-mask Unicode properties. @stable ICU 2.4 */
    UCHAR_MASK_START=UCHAR_GENERAL_CATEGORY_MASK,
    /** One more than the last constant for bit-mask Unicode properties. @stable ICU 2.4 */
    UCHAR_MASK_LIMIT=0x2001,

    /** Double property Numeric_Value.
        Corresponds to u_getNumericValue. @stable ICU 2.4 */
    UCHAR_NUMERIC_VALUE=0x3000,
    /** First constant for double Unicode properties. @stable ICU 2.4 */
    UCHAR_DOUBLE_START=UCHAR_NUMERIC_VALUE,
    /** One more than the last constant for double Unicode properties. @stable ICU 2.4 */
    UCHAR_DOUBLE_LIMIT=0x3001,

    /** String property Age.
        Corresponds to u_charAge. @stable ICU 2.4 */
    UCHAR_AGE=0x4000,
    /** First constant for string Unicode properties. @stable ICU 2.4 */
    UCHAR_STRING_START=UCHAR_AGE,
    /** String property Bidi_Mirroring_Glyph.
        Corresponds to u_charMirror. @stable ICU 2.4 */
    UCHAR_BIDI_MIRRORING_GLYPH=0x4001,
    /** String property Case_Folding.
        Corresponds to u_strFoldCase in ustring.h. @stable ICU 2.4 */
    UCHAR_CASE_FOLDING=0x4002,
    /** String property ISO_Comment.
        Corresponds to u_getISOComment. @stable ICU 2.4 */
    UCHAR_ISO_COMMENT=0x4003,
    /** String property Lowercase_Mapping.
        Corresponds to u_strToLower in ustring.h. @stable ICU 2.4 */
    UCHAR_LOWERCASE_MAPPING=0x4004,
    /** String property Name.
        Corresponds to u_charName. @stable ICU 2.4 */
    UCHAR_NAME=0x4005,
    /** String property Simple_Case_Folding.
        Corresponds to u_foldCase. @stable ICU 2.4 */
    UCHAR_SIMPLE_CASE_FOLDING=0x4006,
    /** String property Simple_Lowercase_Mapping.
        Corresponds to u_tolower. @stable ICU 2.4 */
    UCHAR_SIMPLE_LOWERCASE_MAPPING=0x4007,
    /** String property Simple_Titlecase_Mapping.
        Corresponds to u_totitle. @stable ICU 2.4 */
    UCHAR_SIMPLE_TITLECASE_MAPPING=0x4008,
    /** String property Simple_Uppercase_Mapping.
        Corresponds to u_toupper. @stable ICU 2.4 */
    UCHAR_SIMPLE_UPPERCASE_MAPPING=0x4009,
    /** String property Titlecase_Mapping.
        Corresponds to u_strToTitle in ustring.h. @stable ICU 2.4 */
    UCHAR_TITLECASE_MAPPING=0x400A,
    /** String property Unicode_1_Name.
        Corresponds to u_charName. @stable ICU 2.4 */
    UCHAR_UNICODE_1_NAME=0x400B,
    /** String property Uppercase_Mapping.
        Corresponds to u_strToUpper in ustring.h. @stable ICU 2.4 */
    UCHAR_UPPERCASE_MAPPING=0x400C,
    /** One more than the last constant for string Unicode properties. @stable ICU 2.4 */
    UCHAR_STRING_LIMIT=0x400D,

    /** Provisional property Script_Extensions (new in Unicode 6.0).
        As a provisional property, it may be modified or removed
        in future versions of the Unicode Standard, and thus in ICU.
        Some characters are commonly used in multiple scripts.
        For more information, see UAX #24: http://www.unicode.org/reports/tr24/.
        Corresponds to uscript_hasScript and uscript_getScriptExtensions in uscript.h.
        @draft ICU 4.6 */
    UCHAR_SCRIPT_EXTENSIONS=0x7000,
    /** First constant for Unicode properties with unusual value types. @draft ICU 4.6 */
    UCHAR_OTHER_PROPERTY_START=UCHAR_SCRIPT_EXTENSIONS,
    /** One more than the last constant for Unicode properties with unusual value types.
     * @draft ICU 4.6 */
    UCHAR_OTHER_PROPERTY_LIMIT=0x7001,

    /** Represents a nonexistent or invalid property or property value. @stable ICU 2.4 */
    UCHAR_INVALID_CODE = -1
} UProperty;

/**
 * Data for enumerated Unicode general category types.
 * See http://www.unicode.org/Public/UNIDATA/UnicodeData.html .
 * @stable ICU 2.0
 */
typedef enum UCharCategory
{
    /** See note !!.  Comments of the form "Cn" are read by genpname. */

    /** Non-category for unassigned and non-character code points. @stable ICU 2.0 */
    U_UNASSIGNED              = 0,
    /** Cn "Other, Not Assigned (no characters in [UnicodeData.txt] have this property)" (same as U_UNASSIGNED!) @stable ICU 2.0 */
    U_GENERAL_OTHER_TYPES     = 0,
    /** Lu @stable ICU 2.0 */
    U_UPPERCASE_LETTER        = 1,
    /** Ll @stable ICU 2.0 */
    U_LOWERCASE_LETTER        = 2,
    /** Lt @stable ICU 2.0 */
    U_TITLECASE_LETTER        = 3,
    /** Lm @stable ICU 2.0 */
    U_MODIFIER_LETTER         = 4,
    /** Lo @stable ICU 2.0 */
    U_OTHER_LETTER            = 5,
    /** Mn @stable ICU 2.0 */
    U_NON_SPACING_MARK        = 6,
    /** Me @stable ICU 2.0 */
    U_ENCLOSING_MARK          = 7,
    /** Mc @stable ICU 2.0 */
    U_COMBINING_SPACING_MARK  = 8,
    /** Nd @stable ICU 2.0 */
    U_DECIMAL_DIGIT_NUMBER    = 9,
    /** Nl @stable ICU 2.0 */
    U_LETTER_NUMBER           = 10,
    /** No @stable ICU 2.0 */
    U_OTHER_NUMBER            = 11,
    /** Zs @stable ICU 2.0 */
    U_SPACE_SEPARATOR         = 12,
    /** Zl @stable ICU 2.0 */
    U_LINE_SEPARATOR          = 13,
    /** Zp @stable ICU 2.0 */
    U_PARAGRAPH_SEPARATOR     = 14,
    /** Cc @stable ICU 2.0 */
    U_CONTROL_CHAR            = 15,
    /** Cf @stable ICU 2.0 */
    U_FORMAT_CHAR             = 16,
    /** Co @stable ICU 2.0 */
    U_PRIVATE_USE_CHAR        = 17,
    /** Cs @stable ICU 2.0 */
    U_SURROGATE               = 18,
    /** Pd @stable ICU 2.0 */
    U_DASH_PUNCTUATION        = 19,
    /** Ps @stable ICU 2.0 */
    U_START_PUNCTUATION       = 20,
    /** Pe @stable ICU 2.0 */
    U_END_PUNCTUATION         = 21,
    /** Pc @stable ICU 2.0 */
    U_CONNECTOR_PUNCTUATION   = 22,
    /** Po @stable ICU 2.0 */
    U_OTHER_PUNCTUATION       = 23,
    /** Sm @stable ICU 2.0 */
    U_MATH_SYMBOL             = 24,
    /** Sc @stable ICU 2.0 */
    U_CURRENCY_SYMBOL         = 25,
    /** Sk @stable ICU 2.0 */
    U_MODIFIER_SYMBOL         = 26,
    /** So @stable ICU 2.0 */
    U_OTHER_SYMBOL            = 27,
    /** Pi @stable ICU 2.0 */
    U_INITIAL_PUNCTUATION     = 28,
    /** Pf @stable ICU 2.0 */
    U_FINAL_PUNCTUATION       = 29,
    /** One higher than the last enum UCharCategory constant. @stable ICU 2.0 */
    U_CHAR_CATEGORY_COUNT
} UCharCategory;

/**
 * U_GC_XX_MASK constants are bit flags corresponding to Unicode
 * general category values.
 * For each category, the nth bit is set if the numeric value of the
 * corresponding UCharCategory constant is n.
 *
 * There are also some U_GC_Y_MASK constants for groups of general categories
 * like L for all letter categories.
 *
 * @see u_charType
 * @see U_GET_GC_MASK
 * @see UCharCategory
 * @stable ICU 2.1
 */
#define U_GC_CN_MASK    U_MASK(U_GENERAL_OTHER_TYPES)

/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_LU_MASK    U_MASK(U_UPPERCASE_LETTER)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_LL_MASK    U_MASK(U_LOWERCASE_LETTER)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_LT_MASK    U_MASK(U_TITLECASE_LETTER)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_LM_MASK    U_MASK(U_MODIFIER_LETTER)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_LO_MASK    U_MASK(U_OTHER_LETTER)

/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_MN_MASK    U_MASK(U_NON_SPACING_MARK)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_ME_MASK    U_MASK(U_ENCLOSING_MARK)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_MC_MASK    U_MASK(U_COMBINING_SPACING_MARK)

/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_ND_MASK    U_MASK(U_DECIMAL_DIGIT_NUMBER)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_NL_MASK    U_MASK(U_LETTER_NUMBER)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_NO_MASK    U_MASK(U_OTHER_NUMBER)

/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_ZS_MASK    U_MASK(U_SPACE_SEPARATOR)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_ZL_MASK    U_MASK(U_LINE_SEPARATOR)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_ZP_MASK    U_MASK(U_PARAGRAPH_SEPARATOR)

/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_CC_MASK    U_MASK(U_CONTROL_CHAR)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_CF_MASK    U_MASK(U_FORMAT_CHAR)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_CO_MASK    U_MASK(U_PRIVATE_USE_CHAR)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_CS_MASK    U_MASK(U_SURROGATE)

/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_PD_MASK    U_MASK(U_DASH_PUNCTUATION)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_PS_MASK    U_MASK(U_START_PUNCTUATION)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_PE_MASK    U_MASK(U_END_PUNCTUATION)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_PC_MASK    U_MASK(U_CONNECTOR_PUNCTUATION)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_PO_MASK    U_MASK(U_OTHER_PUNCTUATION)

/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_SM_MASK    U_MASK(U_MATH_SYMBOL)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_SC_MASK    U_MASK(U_CURRENCY_SYMBOL)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_SK_MASK    U_MASK(U_MODIFIER_SYMBOL)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_SO_MASK    U_MASK(U_OTHER_SYMBOL)

/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_PI_MASK    U_MASK(U_INITIAL_PUNCTUATION)
/** Mask constant for a UCharCategory. @stable ICU 2.1 */
#define U_GC_PF_MASK    U_MASK(U_FINAL_PUNCTUATION)


/** Mask constant for multiple UCharCategory bits (L Letters). @stable ICU 2.1 */
#define U_GC_L_MASK \
            (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK|U_GC_LM_MASK|U_GC_LO_MASK)

/** Mask constant for multiple UCharCategory bits (LC Cased Letters). @stable ICU 2.1 */
#define U_GC_LC_MASK \
            (U_GC_LU_MASK|U_GC_LL_MASK|U_GC_LT_MASK)

/** Mask constant for multiple UCharCategory bits (M Marks). @stable ICU 2.1 */
#define U_GC_M_MASK (U_GC_MN_MASK|U_GC_ME_MASK|U_GC_MC_MASK)

/** Mask constant for multiple UCharCategory bits (N Numbers). @stable ICU 2.1 */
#define U_GC_N_MASK (U_GC_ND_MASK|U_GC_NL_MASK|U_GC_NO_MASK)

/** Mask constant for multiple UCharCategory bits (Z Separators). @stable ICU 2.1 */
#define U_GC_Z_MASK (U_GC_ZS_MASK|U_GC_ZL_MASK|U_GC_ZP_MASK)

/** Mask constant for multiple UCharCategory bits (C Others). @stable ICU 2.1 */
#define U_GC_C_MASK \
            (U_GC_CN_MASK|U_GC_CC_MASK|U_GC_CF_MASK|U_GC_CO_MASK|U_GC_CS_MASK)

/** Mask constant for multiple UCharCategory bits (P Punctuation). @stable ICU 2.1 */
#define U_GC_P_MASK \
            (U_GC_PD_MASK|U_GC_PS_MASK|U_GC_PE_MASK|U_GC_PC_MASK|U_GC_PO_MASK| \
             U_GC_PI_MASK|U_GC_PF_MASK)

/** Mask constant for multiple UCharCategory bits (S Symbols). @stable ICU 2.1 */
#define U_GC_S_MASK (U_GC_SM_MASK|U_GC_SC_MASK|U_GC_SK_MASK|U_GC_SO_MASK)

/**
 * This specifies the language directional property of a character set.
 * @stable ICU 2.0
 */
typedef enum UCharDirection {
    /** See note !!.  Comments of the form "EN" are read by genpname. */

    /** L @stable ICU 2.0 */
    U_LEFT_TO_RIGHT               = 0,
    /** R @stable ICU 2.0 */
    U_RIGHT_TO_LEFT               = 1,
    /** EN @stable ICU 2.0 */
    U_EUROPEAN_NUMBER             = 2,
    /** ES @stable ICU 2.0 */
    U_EUROPEAN_NUMBER_SEPARATOR   = 3,
    /** ET @stable ICU 2.0 */
    U_EUROPEAN_NUMBER_TERMINATOR  = 4,
    /** AN @stable ICU 2.0 */
    U_ARABIC_NUMBER               = 5,
    /** CS @stable ICU 2.0 */
    U_COMMON_NUMBER_SEPARATOR     = 6,
    /** B @stable ICU 2.0 */
    U_BLOCK_SEPARATOR             = 7,
    /** S @stable ICU 2.0 */
    U_SEGMENT_SEPARATOR           = 8,
    /** WS @stable ICU 2.0 */
    U_WHITE_SPACE_NEUTRAL         = 9,
    /** ON @stable ICU 2.0 */
    U_OTHER_NEUTRAL               = 10,
    /** LRE @stable ICU 2.0 */
    U_LEFT_TO_RIGHT_EMBEDDING     = 11,
    /** LRO @stable ICU 2.0 */
    U_LEFT_TO_RIGHT_OVERRIDE      = 12,
    /** AL @stable ICU 2.0 */
    U_RIGHT_TO_LEFT_ARABIC        = 13,
    /** RLE @stable ICU 2.0 */
    U_RIGHT_TO_LEFT_EMBEDDING     = 14,
    /** RLO @stable ICU 2.0 */
    U_RIGHT_TO_LEFT_OVERRIDE      = 15,
    /** PDF @stable ICU 2.0 */
    U_POP_DIRECTIONAL_FORMAT      = 16,
    /** NSM @stable ICU 2.0 */
    U_DIR_NON_SPACING_MARK        = 17,
    /** BN @stable ICU 2.0 */
    U_BOUNDARY_NEUTRAL            = 18,
    /** @stable ICU 2.0 */
    U_CHAR_DIRECTION_COUNT
} UCharDirection;

/**
 * Constants for Unicode blocks, see the Unicode Data file Blocks.txt
 * @stable ICU 2.0
 */
enum UBlockCode {

    /** New No_Block value in Unicode 4. @stable ICU 2.6 */
    UBLOCK_NO_BLOCK = 0, /*[none]*/ /* Special range indicating No_Block */

    /** @stable ICU 2.0 */
    UBLOCK_BASIC_LATIN = 1, /*[0000]*/ /*See note !!*/

    /** @stable ICU 2.0 */
    UBLOCK_LATIN_1_SUPPLEMENT=2, /*[0080]*/

    /** @stable ICU 2.0 */
    UBLOCK_LATIN_EXTENDED_A =3, /*[0100]*/

    /** @stable ICU 2.0 */
    UBLOCK_LATIN_EXTENDED_B =4, /*[0180]*/

    /** @stable ICU 2.0 */
    UBLOCK_IPA_EXTENSIONS =5, /*[0250]*/

    /** @stable ICU 2.0 */
    UBLOCK_SPACING_MODIFIER_LETTERS =6, /*[02B0]*/

    /** @stable ICU 2.0 */
    UBLOCK_COMBINING_DIACRITICAL_MARKS =7, /*[0300]*/

    /**
     * Unicode 3.2 renames this block to "Greek and Coptic".
     * @stable ICU 2.0
     */
    UBLOCK_GREEK =8, /*[0370]*/

    /** @stable ICU 2.0 */
    UBLOCK_CYRILLIC =9, /*[0400]*/

    /** @stable ICU 2.0 */
    UBLOCK_ARMENIAN =10, /*[0530]*/

    /** @stable ICU 2.0 */
    UBLOCK_HEBREW =11, /*[0590]*/

    /** @stable ICU 2.0 */
    UBLOCK_ARABIC =12, /*[0600]*/

    /** @stable ICU 2.0 */
    UBLOCK_SYRIAC =13, /*[0700]*/

    /** @stable ICU 2.0 */
    UBLOCK_THAANA =14, /*[0780]*/

    /** @stable ICU 2.0 */
    UBLOCK_DEVANAGARI =15, /*[0900]*/

    /** @stable ICU 2.0 */
    UBLOCK_BENGALI =16, /*[0980]*/

    /** @stable ICU 2.0 */
    UBLOCK_GURMUKHI =17, /*[0A00]*/

    /** @stable ICU 2.0 */
    UBLOCK_GUJARATI =18, /*[0A80]*/

    /** @stable ICU 2.0 */
    UBLOCK_ORIYA =19, /*[0B00]*/

    /** @stable ICU 2.0 */
    UBLOCK_TAMIL =20, /*[0B80]*/

    /** @stable ICU 2.0 */
    UBLOCK_TELUGU =21, /*[0C00]*/

    /** @stable ICU 2.0 */
    UBLOCK_KANNADA =22, /*[0C80]*/

    /** @stable ICU 2.0 */
    UBLOCK_MALAYALAM =23, /*[0D00]*/

    /** @stable ICU 2.0 */
    UBLOCK_SINHALA =24, /*[0D80]*/

    /** @stable ICU 2.0 */
    UBLOCK_THAI =25, /*[0E00]*/

    /** @stable ICU 2.0 */
    UBLOCK_LAO =26, /*[0E80]*/

    /** @stable ICU 2.0 */
    UBLOCK_TIBETAN =27, /*[0F00]*/

    /** @stable ICU 2.0 */
    UBLOCK_MYANMAR =28, /*[1000]*/

    /** @stable ICU 2.0 */
    UBLOCK_GEORGIAN =29, /*[10A0]*/

    /** @stable ICU 2.0 */
    UBLOCK_HANGUL_JAMO =30, /*[1100]*/

    /** @stable ICU 2.0 */
    UBLOCK_ETHIOPIC =31, /*[1200]*/

    /** @stable ICU 2.0 */
    UBLOCK_CHEROKEE =32, /*[13A0]*/

    /** @stable ICU 2.0 */
    UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS =33, /*[1400]*/

    /** @stable ICU 2.0 */
    UBLOCK_OGHAM =34, /*[1680]*/

    /** @stable ICU 2.0 */
    UBLOCK_RUNIC =35, /*[16A0]*/

    /** @stable ICU 2.0 */
    UBLOCK_KHMER =36, /*[1780]*/

    /** @stable ICU 2.0 */
    UBLOCK_MONGOLIAN =37, /*[1800]*/

    /** @stable ICU 2.0 */
    UBLOCK_LATIN_EXTENDED_ADDITIONAL =38, /*[1E00]*/

    /** @stable ICU 2.0 */
    UBLOCK_GREEK_EXTENDED =39, /*[1F00]*/

    /** @stable ICU 2.0 */
    UBLOCK_GENERAL_PUNCTUATION =40, /*[2000]*/

    /** @stable ICU 2.0 */
    UBLOCK_SUPERSCRIPTS_AND_SUBSCRIPTS =41, /*[2070]*/

    /** @stable ICU 2.0 */
    UBLOCK_CURRENCY_SYMBOLS =42, /*[20A0]*/

    /**
     * Unicode 3.2 renames this block to "Combining Diacritical Marks for Symbols".
     * @stable ICU 2.0
     */
    UBLOCK_COMBINING_MARKS_FOR_SYMBOLS =43, /*[20D0]*/

    /** @stable ICU 2.0 */
    UBLOCK_LETTERLIKE_SYMBOLS =44, /*[2100]*/

    /** @stable ICU 2.0 */
    UBLOCK_NUMBER_FORMS =45, /*[2150]*/

    /** @stable ICU 2.0 */
    UBLOCK_ARROWS =46, /*[2190]*/

    /** @stable ICU 2.0 */
    UBLOCK_MATHEMATICAL_OPERATORS =47, /*[2200]*/

    /** @stable ICU 2.0 */
    UBLOCK_MISCELLANEOUS_TECHNICAL =48, /*[2300]*/

    /** @stable ICU 2.0 */
    UBLOCK_CONTROL_PICTURES =49, /*[2400]*/

    /** @stable ICU 2.0 */
    UBLOCK_OPTICAL_CHARACTER_RECOGNITION =50, /*[2440]*/

    /** @stable ICU 2.0 */
    UBLOCK_ENCLOSED_ALPHANUMERICS =51, /*[2460]*/

    /** @stable ICU 2.0 */
    UBLOCK_BOX_DRAWING =52, /*[2500]*/

    /** @stable ICU 2.0 */
    UBLOCK_BLOCK_ELEMENTS =53, /*[2580]*/

    /** @stable ICU 2.0 */
    UBLOCK_GEOMETRIC_SHAPES =54, /*[25A0]*/

    /** @stable ICU 2.0 */
    UBLOCK_MISCELLANEOUS_SYMBOLS =55, /*[2600]*/

    /** @stable ICU 2.0 */
    UBLOCK_DINGBATS =56, /*[2700]*/

    /** @stable ICU 2.0 */
    UBLOCK_BRAILLE_PATTERNS =57, /*[2800]*/

    /** @stable ICU 2.0 */
    UBLOCK_CJK_RADICALS_SUPPLEMENT =58, /*[2E80]*/

    /** @stable ICU 2.0 */
    UBLOCK_KANGXI_RADICALS =59, /*[2F00]*/

    /** @stable ICU 2.0 */
    UBLOCK_IDEOGRAPHIC_DESCRIPTION_CHARACTERS =60, /*[2FF0]*/

    /** @stable ICU 2.0 */
    UBLOCK_CJK_SYMBOLS_AND_PUNCTUATION =61, /*[3000]*/

    /** @stable ICU 2.0 */
    UBLOCK_HIRAGANA =62, /*[3040]*/

    /** @stable ICU 2.0 */
    UBLOCK_KATAKANA =63, /*[30A0]*/

    /** @stable ICU 2.0 */
    UBLOCK_BOPOMOFO =64, /*[3100]*/

    /** @stable ICU 2.0 */
    UBLOCK_HANGUL_COMPATIBILITY_JAMO =65, /*[3130]*/

    /** @stable ICU 2.0 */
    UBLOCK_KANBUN =66, /*[3190]*/

    /** @stable ICU 2.0 */
    UBLOCK_BOPOMOFO_EXTENDED =67, /*[31A0]*/

    /** @stable ICU 2.0 */
    UBLOCK_ENCLOSED_CJK_LETTERS_AND_MONTHS =68, /*[3200]*/

    /** @stable ICU 2.0 */
    UBLOCK_CJK_COMPATIBILITY =69, /*[3300]*/

    /** @stable ICU 2.0 */
    UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A =70, /*[3400]*/

    /** @stable ICU 2.0 */
    UBLOCK_CJK_UNIFIED_IDEOGRAPHS =71, /*[4E00]*/

    /** @stable ICU 2.0 */
    UBLOCK_YI_SYLLABLES =72, /*[A000]*/

    /** @stable ICU 2.0 */
    UBLOCK_YI_RADICALS =73, /*[A490]*/

    /** @stable ICU 2.0 */
    UBLOCK_HANGUL_SYLLABLES =74, /*[AC00]*/

    /** @stable ICU 2.0 */
    UBLOCK_HIGH_SURROGATES =75, /*[D800]*/

    /** @stable ICU 2.0 */
    UBLOCK_HIGH_PRIVATE_USE_SURROGATES =76, /*[DB80]*/

    /** @stable ICU 2.0 */
    UBLOCK_LOW_SURROGATES =77, /*[DC00]*/

    /**
     * Same as UBLOCK_PRIVATE_USE_AREA.
     * Until Unicode 3.1.1, the corresponding block name was "Private Use",
     * and multiple code point ranges had this block.
     * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and
     * adds separate blocks for the supplementary PUAs.
     *
     * @stable ICU 2.0
     */
    UBLOCK_PRIVATE_USE = 78,
    /**
     * Same as UBLOCK_PRIVATE_USE.
     * Until Unicode 3.1.1, the corresponding block name was "Private Use",
     * and multiple code point ranges had this block.
     * Unicode 3.2 renames the block for the BMP PUA to "Private Use Area" and
     * adds separate blocks for the supplementary PUAs.
     *
     * @stable ICU 2.0
     */
    UBLOCK_PRIVATE_USE_AREA =UBLOCK_PRIVATE_USE, /*[E000]*/

    /** @stable ICU 2.0 */
    UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS =79, /*[F900]*/

    /** @stable ICU 2.0 */
    UBLOCK_ALPHABETIC_PRESENTATION_FORMS =80, /*[FB00]*/

    /** @stable ICU 2.0 */
    UBLOCK_ARABIC_PRESENTATION_FORMS_A =81, /*[FB50]*/

    /** @stable ICU 2.0 */
    UBLOCK_COMBINING_HALF_MARKS =82, /*[FE20]*/

    /** @stable ICU 2.0 */
    UBLOCK_CJK_COMPATIBILITY_FORMS =83, /*[FE30]*/

    /** @stable ICU 2.0 */
    UBLOCK_SMALL_FORM_VARIANTS =84, /*[FE50]*/

    /** @stable ICU 2.0 */
    UBLOCK_ARABIC_PRESENTATION_FORMS_B =85, /*[FE70]*/

    /** @stable ICU 2.0 */
    UBLOCK_SPECIALS =86, /*[FFF0]*/

    /** @stable ICU 2.0 */
    UBLOCK_HALFWIDTH_AND_FULLWIDTH_FORMS =87, /*[FF00]*/

    /* New blocks in Unicode 3.1 */

    /** @stable ICU 2.0 */
    UBLOCK_OLD_ITALIC = 88  , /*[10300]*/
    /** @stable ICU 2.0 */
    UBLOCK_GOTHIC = 89 , /*[10330]*/
    /** @stable ICU 2.0 */
    UBLOCK_DESERET = 90 , /*[10400]*/
    /** @stable ICU 2.0 */
    UBLOCK_BYZANTINE_MUSICAL_SYMBOLS = 91 , /*[1D000]*/
    /** @stable ICU 2.0 */
    UBLOCK_MUSICAL_SYMBOLS = 92 , /*[1D100]*/
    /** @stable ICU 2.0 */
    UBLOCK_MATHEMATICAL_ALPHANUMERIC_SYMBOLS = 93  , /*[1D400]*/
    /** @stable ICU 2.0 */
    UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B  = 94 , /*[20000]*/
    /** @stable ICU 2.0 */
    UBLOCK_CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT = 95 , /*[2F800]*/
    /** @stable ICU 2.0 */
    UBLOCK_TAGS = 96, /*[E0000]*/

    /* New blocks in Unicode 3.2 */

    /**
     * Unicode 4.0.1 renames the "Cyrillic Supplementary" block to "Cyrillic Supplement".
     * @stable ICU 2.2
     */
    UBLOCK_CYRILLIC_SUPPLEMENTARY = 97, 
    /** @stable ICU 3.0  */
    UBLOCK_CYRILLIC_SUPPLEMENT = UBLOCK_CYRILLIC_SUPPLEMENTARY, /*[0500]*/
    /** @stable ICU 2.2 */
    UBLOCK_TAGALOG = 98, /*[1700]*/
    /** @stable ICU 2.2 */
    UBLOCK_HANUNOO = 99, /*[1720]*/
    /** @stable ICU 2.2 */
    UBLOCK_BUHID = 100, /*[1740]*/
    /** @stable ICU 2.2 */
    UBLOCK_TAGBANWA = 101, /*[1760]*/
    /** @stable ICU 2.2 */
    UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_A = 102, /*[27C0]*/
    /** @stable ICU 2.2 */
    UBLOCK_SUPPLEMENTAL_ARROWS_A = 103, /*[27F0]*/
    /** @stable ICU 2.2 */
    UBLOCK_SUPPLEMENTAL_ARROWS_B = 104, /*[2900]*/
    /** @stable ICU 2.2 */
    UBLOCK_MISCELLANEOUS_MATHEMATICAL_SYMBOLS_B = 105, /*[2980]*/
    /** @stable ICU 2.2 */
    UBLOCK_SUPPLEMENTAL_MATHEMATICAL_OPERATORS = 106, /*[2A00]*/
    /** @stable ICU 2.2 */
    UBLOCK_KATAKANA_PHONETIC_EXTENSIONS = 107, /*[31F0]*/
    /** @stable ICU 2.2 */
    UBLOCK_VARIATION_SELECTORS = 108, /*[FE00]*/
    /** @stable ICU 2.2 */
    UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_A = 109, /*[F0000]*/
    /** @stable ICU 2.2 */
    UBLOCK_SUPPLEMENTARY_PRIVATE_USE_AREA_B = 110, /*[100000]*/

    /* New blocks in Unicode 4 */

    /** @stable ICU 2.6 */
    UBLOCK_LIMBU = 111, /*[1900]*/
    /** @stable ICU 2.6 */
    UBLOCK_TAI_LE = 112, /*[1950]*/
    /** @stable ICU 2.6 */
    UBLOCK_KHMER_SYMBOLS = 113, /*[19E0]*/
    /** @stable ICU 2.6 */
    UBLOCK_PHONETIC_EXTENSIONS = 114, /*[1D00]*/
    /** @stable ICU 2.6 */
    UBLOCK_MISCELLANEOUS_SYMBOLS_AND_ARROWS = 115, /*[2B00]*/
    /** @stable ICU 2.6 */
    UBLOCK_YIJING_HEXAGRAM_SYMBOLS = 116, /*[4DC0]*/
    /** @stable ICU 2.6 */
    UBLOCK_LINEAR_B_SYLLABARY = 117, /*[10000]*/
    /** @stable ICU 2.6 */
    UBLOCK_LINEAR_B_IDEOGRAMS = 118, /*[10080]*/
    /** @stable ICU 2.6 */
    UBLOCK_AEGEAN_NUMBERS = 119, /*[10100]*/
    /** @stable ICU 2.6 */
    UBLOCK_UGARITIC = 120, /*[10380]*/
    /** @stable ICU 2.6 */
    UBLOCK_SHAVIAN = 121, /*[10450]*/
    /** @stable ICU 2.6 */
    UBLOCK_OSMANYA = 122, /*[10480]*/
    /** @stable ICU 2.6 */
    UBLOCK_CYPRIOT_SYLLABARY = 123, /*[10800]*/
    /** @stable ICU 2.6 */
    UBLOCK_TAI_XUAN_JING_SYMBOLS = 124, /*[1D300]*/
    /** @stable ICU 2.6 */
    UBLOCK_VARIATION_SELECTORS_SUPPLEMENT = 125, /*[E0100]*/

    /* New blocks in Unicode 4.1 */

    /** @stable ICU 3.4 */
    UBLOCK_ANCIENT_GREEK_MUSICAL_NOTATION = 126, /*[1D200]*/
    /** @stable ICU 3.4 */
    UBLOCK_ANCIENT_GREEK_NUMBERS = 127, /*[10140]*/
    /** @stable ICU 3.4 */
    UBLOCK_ARABIC_SUPPLEMENT = 128, /*[0750]*/
    /** @stable ICU 3.4 */
    UBLOCK_BUGINESE = 129, /*[1A00]*/
    /** @stable ICU 3.4 */
    UBLOCK_CJK_STROKES = 130, /*[31C0]*/
    /** @stable ICU 3.4 */
    UBLOCK_COMBINING_DIACRITICAL_MARKS_SUPPLEMENT = 131, /*[1DC0]*/
    /** @stable ICU 3.4 */
    UBLOCK_COPTIC = 132, /*[2C80]*/
    /** @stable ICU 3.4 */
    UBLOCK_ETHIOPIC_EXTENDED = 133, /*[2D80]*/
    /** @stable ICU 3.4 */
    UBLOCK_ETHIOPIC_SUPPLEMENT = 134, /*[1380]*/
    /** @stable ICU 3.4 */
    UBLOCK_GEORGIAN_SUPPLEMENT = 135, /*[2D00]*/
    /** @stable ICU 3.4 */
    UBLOCK_GLAGOLITIC = 136, /*[2C00]*/
    /** @stable ICU 3.4 */
    UBLOCK_KHAROSHTHI = 137, /*[10A00]*/
    /** @stable ICU 3.4 */
    UBLOCK_MODIFIER_TONE_LETTERS = 138, /*[A700]*/
    /** @stable ICU 3.4 */
    UBLOCK_NEW_TAI_LUE = 139, /*[1980]*/
    /** @stable ICU 3.4 */
    UBLOCK_OLD_PERSIAN = 140, /*[103A0]*/
    /** @stable ICU 3.4 */
    UBLOCK_PHONETIC_EXTENSIONS_SUPPLEMENT = 141, /*[1D80]*/
    /** @stable ICU 3.4 */
    UBLOCK_SUPPLEMENTAL_PUNCTUATION = 142, /*[2E00]*/
    /** @stable ICU 3.4 */
    UBLOCK_SYLOTI_NAGRI = 143, /*[A800]*/
    /** @stable ICU 3.4 */
    UBLOCK_TIFINAGH = 144, /*[2D30]*/
    /** @stable ICU 3.4 */
    UBLOCK_VERTICAL_FORMS = 145, /*[FE10]*/

    /* New blocks in Unicode 5.0 */

    /** @stable ICU 3.6 */
    UBLOCK_NKO = 146, /*[07C0]*/
    /** @stable ICU 3.6 */
    UBLOCK_BALINESE = 147, /*[1B00]*/
    /** @stable ICU 3.6 */
    UBLOCK_LATIN_EXTENDED_C = 148, /*[2C60]*/
    /** @stable ICU 3.6 */
    UBLOCK_LATIN_EXTENDED_D = 149, /*[A720]*/
    /** @stable ICU 3.6 */
    UBLOCK_PHAGS_PA = 150, /*[A840]*/
    /** @stable ICU 3.6 */
    UBLOCK_PHOENICIAN = 151, /*[10900]*/
    /** @stable ICU 3.6 */
    UBLOCK_CUNEIFORM = 152, /*[12000]*/
    /** @stable ICU 3.6 */
    UBLOCK_CUNEIFORM_NUMBERS_AND_PUNCTUATION = 153, /*[12400]*/
    /** @stable ICU 3.6 */
    UBLOCK_COUNTING_ROD_NUMERALS = 154, /*[1D360]*/

    /* New blocks in Unicode 5.1 */

    /** @stable ICU 4.0 */
    UBLOCK_SUNDANESE = 155, /*[1B80]*/
    /** @stable ICU 4.0 */
    UBLOCK_LEPCHA = 156, /*[1C00]*/
    /** @stable ICU 4.0 */
    UBLOCK_OL_CHIKI = 157, /*[1C50]*/
    /** @stable ICU 4.0 */
    UBLOCK_CYRILLIC_EXTENDED_A = 158, /*[2DE0]*/
    /** @stable ICU 4.0 */
    UBLOCK_VAI = 159, /*[A500]*/
    /** @stable ICU 4.0 */
    UBLOCK_CYRILLIC_EXTENDED_B = 160, /*[A640]*/
    /** @stable ICU 4.0 */
    UBLOCK_SAURASHTRA = 161, /*[A880]*/
    /** @stable ICU 4.0 */
    UBLOCK_KAYAH_LI = 162, /*[A900]*/
    /** @stable ICU 4.0 */
    UBLOCK_REJANG = 163, /*[A930]*/
    /** @stable ICU 4.0 */
    UBLOCK_CHAM = 164, /*[AA00]*/
    /** @stable ICU 4.0 */
    UBLOCK_ANCIENT_SYMBOLS = 165, /*[10190]*/
    /** @stable ICU 4.0 */
    UBLOCK_PHAISTOS_DISC = 166, /*[101D0]*/
    /** @stable ICU 4.0 */
    UBLOCK_LYCIAN = 167, /*[10280]*/
    /** @stable ICU 4.0 */
    UBLOCK_CARIAN = 168, /*[102A0]*/
    /** @stable ICU 4.0 */
    UBLOCK_LYDIAN = 169, /*[10920]*/
    /** @stable ICU 4.0 */
    UBLOCK_MAHJONG_TILES = 170, /*[1F000]*/
    /** @stable ICU 4.0 */
    UBLOCK_DOMINO_TILES = 171, /*[1F030]*/

    /* New blocks in Unicode 5.2 */

    /** @stable ICU 4.4 */
    UBLOCK_SAMARITAN = 172, /*[0800]*/
    /** @stable ICU 4.4 */
    UBLOCK_UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED = 173, /*[18B0]*/
    /** @stable ICU 4.4 */
    UBLOCK_TAI_THAM = 174, /*[1A20]*/
    /** @stable ICU 4.4 */
    UBLOCK_VEDIC_EXTENSIONS = 175, /*[1CD0]*/
    /** @stable ICU 4.4 */
    UBLOCK_LISU = 176, /*[A4D0]*/
    /** @stable ICU 4.4 */
    UBLOCK_BAMUM = 177, /*[A6A0]*/
    /** @stable ICU 4.4 */
    UBLOCK_COMMON_INDIC_NUMBER_FORMS = 178, /*[A830]*/
    /** @stable ICU 4.4 */
    UBLOCK_DEVANAGARI_EXTENDED = 179, /*[A8E0]*/
    /** @stable ICU 4.4 */
    UBLOCK_HANGUL_JAMO_EXTENDED_A = 180, /*[A960]*/
    /** @stable ICU 4.4 */
    UBLOCK_JAVANESE = 181, /*[A980]*/
    /** @stable ICU 4.4 */
    UBLOCK_MYANMAR_EXTENDED_A = 182, /*[AA60]*/
    /** @stable ICU 4.4 */
    UBLOCK_TAI_VIET = 183, /*[AA80]*/
    /** @stable ICU 4.4 */
    UBLOCK_MEETEI_MAYEK = 184, /*[ABC0]*/
    /** @stable ICU 4.4 */
    UBLOCK_HANGUL_JAMO_EXTENDED_B = 185, /*[D7B0]*/
    /** @stable ICU 4.4 */
    UBLOCK_IMPERIAL_ARAMAIC = 186, /*[10840]*/
    /** @stable ICU 4.4 */
    UBLOCK_OLD_SOUTH_ARABIAN = 187, /*[10A60]*/
    /** @stable ICU 4.4 */
    UBLOCK_AVESTAN = 188, /*[10B00]*/
    /** @stable ICU 4.4 */
    UBLOCK_INSCRIPTIONAL_PARTHIAN = 189, /*[10B40]*/
    /** @stable ICU 4.4 */
    UBLOCK_INSCRIPTIONAL_PAHLAVI = 190, /*[10B60]*/
    /** @stable ICU 4.4 */
    UBLOCK_OLD_TURKIC = 191, /*[10C00]*/
    /** @stable ICU 4.4 */
    UBLOCK_RUMI_NUMERAL_SYMBOLS = 192, /*[10E60]*/
    /** @stable ICU 4.4 */
    UBLOCK_KAITHI = 193, /*[11080]*/
    /** @stable ICU 4.4 */
    UBLOCK_EGYPTIAN_HIEROGLYPHS = 194, /*[13000]*/
    /** @stable ICU 4.4 */
    UBLOCK_ENCLOSED_ALPHANUMERIC_SUPPLEMENT = 195, /*[1F100]*/
    /** @stable ICU 4.4 */
    UBLOCK_ENCLOSED_IDEOGRAPHIC_SUPPLEMENT = 196, /*[1F200]*/
    /** @stable ICU 4.4 */
    UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C = 197, /*[2A700]*/

    /* New blocks in Unicode 6.0 */

    /** @stable ICU 4.6 */
    UBLOCK_MANDAIC = 198, /*[0840]*/
    /** @stable ICU 4.6 */
    UBLOCK_BATAK = 199, /*[1BC0]*/
    /** @stable ICU 4.6 */
    UBLOCK_ETHIOPIC_EXTENDED_A = 200, /*[AB00]*/
    /** @stable ICU 4.6 */
    UBLOCK_BRAHMI = 201, /*[11000]*/
    /** @stable ICU 4.6 */
    UBLOCK_BAMUM_SUPPLEMENT = 202, /*[16800]*/
    /** @stable ICU 4.6 */
    UBLOCK_KANA_SUPPLEMENT = 203, /*[1B000]*/
    /** @stable ICU 4.6 */
    UBLOCK_PLAYING_CARDS = 204, /*[1F0A0]*/
    /** @stable ICU 4.6 */
    UBLOCK_MISCELLANEOUS_SYMBOLS_AND_PICTOGRAPHS = 205, /*[1F300]*/
    /** @stable ICU 4.6 */
    UBLOCK_EMOTICONS = 206, /*[1F600]*/
    /** @stable ICU 4.6 */
    UBLOCK_TRANSPORT_AND_MAP_SYMBOLS = 207, /*[1F680]*/
    /** @stable ICU 4.6 */
    UBLOCK_ALCHEMICAL_SYMBOLS = 208, /*[1F700]*/
    /** @stable ICU 4.6 */
    UBLOCK_CJK_UNIFIED_IDEOGRAPHS_EXTENSION_D = 209, /*[2B740]*/

    /** @stable ICU 2.0 */
    UBLOCK_COUNT = 210,

    /** @stable ICU 2.0 */
    UBLOCK_INVALID_CODE=-1
};

/** @stable ICU 2.0 */
typedef enum UBlockCode UBlockCode;

/**
 * East Asian Width constants.
 *
 * @see UCHAR_EAST_ASIAN_WIDTH
 * @see u_getIntPropertyValue
 * @stable ICU 2.2
 */
typedef enum UEastAsianWidth {
    U_EA_NEUTRAL,   /*[N]*/ /*See note !!*/
    U_EA_AMBIGUOUS, /*[A]*/
    U_EA_HALFWIDTH, /*[H]*/
    U_EA_FULLWIDTH, /*[F]*/
    U_EA_NARROW,    /*[Na]*/
    U_EA_WIDE,      /*[W]*/
    U_EA_COUNT
} UEastAsianWidth;
/*
 * Implementation note:
 * Keep UEastAsianWidth constant values in sync with names list in genprops/props2.c.
 */

/**
 * Selector constants for u_charName().
 * u_charName() returns the "modern" name of a
 * Unicode character; or the name that was defined in
 * Unicode version 1.0, before the Unicode standard merged
 * with ISO-10646; or an "extended" name that gives each
 * Unicode code point a unique name.
 *
 * @see u_charName
 * @stable ICU 2.0
 */
typedef enum UCharNameChoice {
    U_UNICODE_CHAR_NAME,
    U_UNICODE_10_CHAR_NAME,
    U_EXTENDED_CHAR_NAME,
    U_CHAR_NAME_ALIAS,          /**< Corrected name from NameAliases.txt. @stable ICU 4.4 */
    U_CHAR_NAME_CHOICE_COUNT
} UCharNameChoice;

/**
 * Selector constants for u_getPropertyName() and
 * u_getPropertyValueName().  These selectors are used to choose which
 * name is returned for a given property or value.  All properties and
 * values have a long name.  Most have a short name, but some do not.
 * Unicode allows for additional names, beyond the long and short
 * name, which would be indicated by U_LONG_PROPERTY_NAME + i, where
 * i=1, 2,...
 *
 * @see u_getPropertyName()
 * @see u_getPropertyValueName()
 * @stable ICU 2.4
 */
typedef enum UPropertyNameChoice {
    U_SHORT_PROPERTY_NAME,
    U_LONG_PROPERTY_NAME,
    U_PROPERTY_NAME_CHOICE_COUNT
} UPropertyNameChoice;

/**
 * Decomposition Type constants.
 *
 * @see UCHAR_DECOMPOSITION_TYPE
 * @stable ICU 2.2
 */
typedef enum UDecompositionType {
    U_DT_NONE,              /*[none]*/ /*See note !!*/
    U_DT_CANONICAL,         /*[can]*/
    U_DT_COMPAT,            /*[com]*/
    U_DT_CIRCLE,            /*[enc]*/
    U_DT_FINAL,             /*[fin]*/
    U_DT_FONT,              /*[font]*/
    U_DT_FRACTION,          /*[fra]*/
    U_DT_INITIAL,           /*[init]*/
    U_DT_ISOLATED,          /*[iso]*/
    U_DT_MEDIAL,            /*[med]*/
    U_DT_NARROW,            /*[nar]*/
    U_DT_NOBREAK,           /*[nb]*/
    U_DT_SMALL,             /*[sml]*/
    U_DT_SQUARE,            /*[sqr]*/
    U_DT_SUB,               /*[sub]*/
    U_DT_SUPER,             /*[sup]*/
    U_DT_VERTICAL,          /*[vert]*/
    U_DT_WIDE,              /*[wide]*/
    U_DT_COUNT /* 18 */
} UDecompositionType;

/**
 * Joining Type constants.
 *
 * @see UCHAR_JOINING_TYPE
 * @stable ICU 2.2
 */
typedef enum UJoiningType {
    U_JT_NON_JOINING,       /*[U]*/ /*See note !!*/
    U_JT_JOIN_CAUSING,      /*[C]*/
    U_JT_DUAL_JOINING,      /*[D]*/
    U_JT_LEFT_JOINING,      /*[L]*/
    U_JT_RIGHT_JOINING,     /*[R]*/
    U_JT_TRANSPARENT,       /*[T]*/
    U_JT_COUNT /* 6 */
} UJoiningType;

/**
 * Joining Group constants.
 *
 * @see UCHAR_JOINING_GROUP
 * @stable ICU 2.2
 */
typedef enum UJoiningGroup {
    U_JG_NO_JOINING_GROUP,
    U_JG_AIN,
    U_JG_ALAPH,
    U_JG_ALEF,
    U_JG_BEH,
    U_JG_BETH,
    U_JG_DAL,
    U_JG_DALATH_RISH,
    U_JG_E,
    U_JG_FEH,
    U_JG_FINAL_SEMKATH,
    U_JG_GAF,
    U_JG_GAMAL,
    U_JG_HAH,
    U_JG_TEH_MARBUTA_GOAL,  /**< @stable ICU 4.6 */
    U_JG_HAMZA_ON_HEH_GOAL=U_JG_TEH_MARBUTA_GOAL,
    U_JG_HE,
    U_JG_HEH,
    U_JG_HEH_GOAL,
    U_JG_HETH,
    U_JG_KAF,
    U_JG_KAPH,
    U_JG_KNOTTED_HEH,
    U_JG_LAM,
    U_JG_LAMADH,
    U_JG_MEEM,
    U_JG_MIM,
    U_JG_NOON,
    U_JG_NUN,
    U_JG_PE,
    U_JG_QAF,
    U_JG_QAPH,
    U_JG_REH,
    U_JG_REVERSED_PE,
    U_JG_SAD,
    U_JG_SADHE,
    U_JG_SEEN,
    U_JG_SEMKATH,
    U_JG_SHIN,
    U_JG_SWASH_KAF,
    U_JG_SYRIAC_WAW,
    U_JG_TAH,
    U_JG_TAW,
    U_JG_TEH_MARBUTA,
    U_JG_TETH,
    U_JG_WAW,
    U_JG_YEH,
    U_JG_YEH_BARREE,
    U_JG_YEH_WITH_TAIL,
    U_JG_YUDH,
    U_JG_YUDH_HE,
    U_JG_ZAIN,
    U_JG_FE,        /**< @stable ICU 2.6 */
    U_JG_KHAPH,     /**< @stable ICU 2.6 */
    U_JG_ZHAIN,     /**< @stable ICU 2.6 */
    U_JG_BURUSHASKI_YEH_BARREE, /**< @stable ICU 4.0 */
    U_JG_FARSI_YEH, /**< @stable ICU 4.4 */
    U_JG_NYA,       /**< @stable ICU 4.4 */
    U_JG_COUNT
} UJoiningGroup;

/**
 * Grapheme Cluster Break constants.
 *
 * @see UCHAR_GRAPHEME_CLUSTER_BREAK
 * @stable ICU 3.4
 */
typedef enum UGraphemeClusterBreak {
    U_GCB_OTHER = 0,            /*[XX]*/ /*See note !!*/
    U_GCB_CONTROL = 1,          /*[CN]*/
    U_GCB_CR = 2,               /*[CR]*/
    U_GCB_EXTEND = 3,           /*[EX]*/
    U_GCB_L = 4,                /*[L]*/
    U_GCB_LF = 5,               /*[LF]*/
    U_GCB_LV = 6,               /*[LV]*/
    U_GCB_LVT = 7,              /*[LVT]*/
    U_GCB_T = 8,                /*[T]*/
    U_GCB_V = 9,                /*[V]*/
    U_GCB_SPACING_MARK = 10,    /*[SM]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
    U_GCB_PREPEND = 11,         /*[PP]*/
    U_GCB_COUNT = 12
} UGraphemeClusterBreak;

/**
 * Word Break constants.
 * (UWordBreak is a pre-existing enum type in ubrk.h for word break status tags.)
 *
 * @see UCHAR_WORD_BREAK
 * @stable ICU 3.4
 */
typedef enum UWordBreakValues {
    U_WB_OTHER = 0,             /*[XX]*/ /*See note !!*/
    U_WB_ALETTER = 1,           /*[LE]*/
    U_WB_FORMAT = 2,            /*[FO]*/
    U_WB_KATAKANA = 3,          /*[KA]*/
    U_WB_MIDLETTER = 4,         /*[ML]*/
    U_WB_MIDNUM = 5,            /*[MN]*/
    U_WB_NUMERIC = 6,           /*[NU]*/
    U_WB_EXTENDNUMLET = 7,      /*[EX]*/
    U_WB_CR = 8,                /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
    U_WB_EXTEND = 9,            /*[Extend]*/
    U_WB_LF = 10,               /*[LF]*/
    U_WB_MIDNUMLET =11,         /*[MB]*/
    U_WB_NEWLINE =12,           /*[NL]*/
    U_WB_COUNT = 13
} UWordBreakValues;

/**
 * Sentence Break constants.
 *
 * @see UCHAR_SENTENCE_BREAK
 * @stable ICU 3.4
 */
typedef enum USentenceBreak {
    U_SB_OTHER = 0,             /*[XX]*/ /*See note !!*/
    U_SB_ATERM = 1,             /*[AT]*/
    U_SB_CLOSE = 2,             /*[CL]*/
    U_SB_FORMAT = 3,            /*[FO]*/
    U_SB_LOWER = 4,             /*[LO]*/
    U_SB_NUMERIC = 5,           /*[NU]*/
    U_SB_OLETTER = 6,           /*[LE]*/
    U_SB_SEP = 7,               /*[SE]*/
    U_SB_SP = 8,                /*[SP]*/
    U_SB_STERM = 9,             /*[ST]*/
    U_SB_UPPER = 10,            /*[UP]*/
    U_SB_CR = 11,               /*[CR]*/ /* from here on: new in Unicode 5.1/ICU 4.0 */
    U_SB_EXTEND = 12,           /*[EX]*/
    U_SB_LF = 13,               /*[LF]*/
    U_SB_SCONTINUE = 14,        /*[SC]*/
    U_SB_COUNT = 15
} USentenceBreak;

/**
 * Line Break constants.
 *
 * @see UCHAR_LINE_BREAK
 * @stable ICU 2.2
 */
typedef enum ULineBreak {
    U_LB_UNKNOWN = 0,           /*[XX]*/ /*See note !!*/
    U_LB_AMBIGUOUS = 1,         /*[AI]*/
    U_LB_ALPHABETIC = 2,        /*[AL]*/
    U_LB_BREAK_BOTH = 3,        /*[B2]*/
    U_LB_BREAK_AFTER = 4,       /*[BA]*/
    U_LB_BREAK_BEFORE = 5,      /*[BB]*/
    U_LB_MANDATORY_BREAK = 6,   /*[BK]*/
    U_LB_CONTINGENT_BREAK = 7,  /*[CB]*/
    U_LB_CLOSE_PUNCTUATION = 8, /*[CL]*/
    U_LB_COMBINING_MARK = 9,    /*[CM]*/
    U_LB_CARRIAGE_RETURN = 10,   /*[CR]*/
    U_LB_EXCLAMATION = 11,       /*[EX]*/
    U_LB_GLUE = 12,              /*[GL]*/
    U_LB_HYPHEN = 13,            /*[HY]*/
    U_LB_IDEOGRAPHIC = 14,       /*[ID]*/
    U_LB_INSEPERABLE = 15,
    /** Renamed from the misspelled "inseperable" in Unicode 4.0.1/ICU 3.0 @stable ICU 3.0 */
    U_LB_INSEPARABLE=U_LB_INSEPERABLE,/*[IN]*/
    U_LB_INFIX_NUMERIC = 16,     /*[IS]*/
    U_LB_LINE_FEED = 17,         /*[LF]*/
    U_LB_NONSTARTER = 18,        /*[NS]*/
    U_LB_NUMERIC = 19,           /*[NU]*/
    U_LB_OPEN_PUNCTUATION = 20,  /*[OP]*/
    U_LB_POSTFIX_NUMERIC = 21,   /*[PO]*/
    U_LB_PREFIX_NUMERIC = 22,    /*[PR]*/
    U_LB_QUOTATION = 23,         /*[QU]*/
    U_LB_COMPLEX_CONTEXT = 24,   /*[SA]*/
    U_LB_SURROGATE = 25,         /*[SG]*/
    U_LB_SPACE = 26,             /*[SP]*/
    U_LB_BREAK_SYMBOLS = 27,     /*[SY]*/
    U_LB_ZWSPACE = 28,           /*[ZW]*/
    U_LB_NEXT_LINE = 29,         /*[NL]*/ /* from here on: new in Unicode 4/ICU 2.6 */
    U_LB_WORD_JOINER = 30,       /*[WJ]*/
    U_LB_H2 = 31,                /*[H2]*/ /* from here on: new in Unicode 4.1/ICU 3.4 */
    U_LB_H3 = 32,                /*[H3]*/
    U_LB_JL = 33,                /*[JL]*/
    U_LB_JT = 34,                /*[JT]*/
    U_LB_JV = 35,                /*[JV]*/
    U_LB_CLOSE_PARENTHESIS = 36, /*[CP]*/ /* new in Unicode 5.2/ICU 4.4 */
    U_LB_COUNT = 37
} ULineBreak;

/**
 * Numeric Type constants.
 *
 * @see UCHAR_NUMERIC_TYPE
 * @stable ICU 2.2
 */
typedef enum UNumericType {
    U_NT_NONE,              /*[None]*/ /*See note !!*/
    U_NT_DECIMAL,           /*[de]*/
    U_NT_DIGIT,             /*[di]*/
    U_NT_NUMERIC,           /*[nu]*/
    U_NT_COUNT
} UNumericType;

/**
 * Hangul Syllable Type constants.
 *
 * @see UCHAR_HANGUL_SYLLABLE_TYPE
 * @stable ICU 2.6
 */
typedef enum UHangulSyllableType {
    U_HST_NOT_APPLICABLE,   /*[NA]*/ /*See note !!*/
    U_HST_LEADING_JAMO,     /*[L]*/
    U_HST_VOWEL_JAMO,       /*[V]*/
    U_HST_TRAILING_JAMO,    /*[T]*/
    U_HST_LV_SYLLABLE,      /*[LV]*/
    U_HST_LVT_SYLLABLE,     /*[LVT]*/
    U_HST_COUNT
} UHangulSyllableType;

/**
 * Check a binary Unicode property for a code point.
 *
 * Unicode, especially in version 3.2, defines many more properties than the
 * original set in UnicodeData.txt.
 *
 * The properties APIs are intended to reflect Unicode properties as defined
 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
 * For details about the properties see http://www.unicode.org/ucd/ .
 * For names of Unicode properties see the UCD file PropertyAliases.txt.
 *
 * Important: If ICU is built with UCD files from Unicode versions below 3.2,
 * then properties marked with "new in Unicode 3.2" are not or not fully available.
 *
 * @param c Code point to test.
 * @param which UProperty selector constant, identifies which binary property to check.
 *        Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT.
 * @return TRUE or FALSE according to the binary Unicode property value for c.
 *         Also FALSE if 'which' is out of bounds or if the Unicode version
 *         does not have data for the property at all, or not for this code point.
 *
 * @see UProperty
 * @see u_getIntPropertyValue
 * @see u_getUnicodeVersion
 * @stable ICU 2.1
 */
U_STABLE UBool U_EXPORT2
u_hasBinaryProperty(UChar32 c, UProperty which);

/**
 * Check if a code point has the Alphabetic Unicode property.
 * Same as u_hasBinaryProperty(c, UCHAR_ALPHABETIC).
 * This is different from u_isalpha!
 * @param c Code point to test
 * @return true if the code point has the Alphabetic Unicode property, false otherwise
 *
 * @see UCHAR_ALPHABETIC
 * @see u_isalpha
 * @see u_hasBinaryProperty
 * @stable ICU 2.1
 */
U_STABLE UBool U_EXPORT2
u_isUAlphabetic(UChar32 c);

/**
 * Check if a code point has the Lowercase Unicode property.
 * Same as u_hasBinaryProperty(c, UCHAR_LOWERCASE).
 * This is different from u_islower!
 * @param c Code point to test
 * @return true if the code point has the Lowercase Unicode property, false otherwise
 *
 * @see UCHAR_LOWERCASE
 * @see u_islower
 * @see u_hasBinaryProperty
 * @stable ICU 2.1
 */
U_STABLE UBool U_EXPORT2
u_isULowercase(UChar32 c);

/**
 * Check if a code point has the Uppercase Unicode property.
 * Same as u_hasBinaryProperty(c, UCHAR_UPPERCASE).
 * This is different from u_isupper!
 * @param c Code point to test
 * @return true if the code point has the Uppercase Unicode property, false otherwise
 *
 * @see UCHAR_UPPERCASE
 * @see u_isupper
 * @see u_hasBinaryProperty
 * @stable ICU 2.1
 */
U_STABLE UBool U_EXPORT2
u_isUUppercase(UChar32 c);

/**
 * Check if a code point has the White_Space Unicode property.
 * Same as u_hasBinaryProperty(c, UCHAR_WHITE_SPACE).
 * This is different from both u_isspace and u_isWhitespace!
 *
 * Note: There are several ICU whitespace functions; please see the uchar.h
 * file documentation for a detailed comparison.
 *
 * @param c Code point to test
 * @return true if the code point has the White_Space Unicode property, false otherwise.
 *
 * @see UCHAR_WHITE_SPACE
 * @see u_isWhitespace
 * @see u_isspace
 * @see u_isJavaSpaceChar
 * @see u_hasBinaryProperty
 * @stable ICU 2.1
 */
U_STABLE UBool U_EXPORT2
u_isUWhiteSpace(UChar32 c);

/**
 * Get the property value for an enumerated or integer Unicode property for a code point.
 * Also returns binary and mask property values.
 *
 * Unicode, especially in version 3.2, defines many more properties than the
 * original set in UnicodeData.txt.
 *
 * The properties APIs are intended to reflect Unicode properties as defined
 * in the Unicode Character Database (UCD) and Unicode Technical Reports (UTR).
 * For details about the properties see http://www.unicode.org/ .
 * For names of Unicode properties see the UCD file PropertyAliases.txt.
 *
 * Sample usage:
 * UEastAsianWidth ea=(UEastAsianWidth)u_getIntPropertyValue(c, UCHAR_EAST_ASIAN_WIDTH);
 * UBool b=(UBool)u_getIntPropertyValue(c, UCHAR_IDEOGRAPHIC);
 *
 * @param c Code point to test.
 * @param which UProperty selector constant, identifies which property to check.
 *        Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
 *        or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
 *        or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
 * @return Numeric value that is directly the property value or,
 *         for enumerated properties, corresponds to the numeric value of the enumerated
 *         constant of the respective property value enumeration type
 *         (cast to enum type if necessary).
 *         Returns 0 or 1 (for FALSE/TRUE) for binary Unicode properties.
 *         Returns a bit-mask for mask properties.
 *         Returns 0 if 'which' is out of bounds or if the Unicode version
 *         does not have data for the property at all, or not for this code point.
 *
 * @see UProperty
 * @see u_hasBinaryProperty
 * @see u_getIntPropertyMinValue
 * @see u_getIntPropertyMaxValue
 * @see u_getUnicodeVersion
 * @stable ICU 2.2
 */
U_STABLE int32_t U_EXPORT2
u_getIntPropertyValue(UChar32 c, UProperty which);

/**
 * Get the minimum value for an enumerated/integer/binary Unicode property.
 * Can be used together with u_getIntPropertyMaxValue
 * to allocate arrays of UnicodeSet or similar.
 *
 * @param which UProperty selector constant, identifies which binary property to check.
 *        Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
 *        or UCHAR_INT_START<=which<UCHAR_INT_LIMIT.
 * @return Minimum value returned by u_getIntPropertyValue for a Unicode property.
 *         0 if the property selector is out of range.
 *
 * @see UProperty
 * @see u_hasBinaryProperty
 * @see u_getUnicodeVersion
 * @see u_getIntPropertyMaxValue
 * @see u_getIntPropertyValue
 * @stable ICU 2.2
 */
U_STABLE int32_t U_EXPORT2
u_getIntPropertyMinValue(UProperty which);

/**
 * Get the maximum value for an enumerated/integer/binary Unicode property.
 * Can be used together with u_getIntPropertyMinValue
 * to allocate arrays of UnicodeSet or similar.
 *
 * Examples for min/max values (for Unicode 3.2):
 *
 * - UCHAR_BIDI_CLASS:    0/18 (U_LEFT_TO_RIGHT/U_BOUNDARY_NEUTRAL)
 * - UCHAR_SCRIPT:        0/45 (USCRIPT_COMMON/USCRIPT_TAGBANWA)
 * - UCHAR_IDEOGRAPHIC:   0/1  (FALSE/TRUE)
 *
 * For undefined UProperty constant values, min/max values will be 0/-1.
 *
 * @param which UProperty selector constant, identifies which binary property to check.
 *        Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
 *        or UCHAR_INT_START<=which<UCHAR_INT_LIMIT.
 * @return Maximum value returned by u_getIntPropertyValue for a Unicode property.
 *         <=0 if the property selector is out of range.
 *
 * @see UProperty
 * @see u_hasBinaryProperty
 * @see u_getUnicodeVersion
 * @see u_getIntPropertyMaxValue
 * @see u_getIntPropertyValue
 * @stable ICU 2.2
 */
U_STABLE int32_t U_EXPORT2
u_getIntPropertyMaxValue(UProperty which);

/**
 * Get the numeric value for a Unicode code point as defined in the
 * Unicode Character Database.
 *
 * A "double" return type is necessary because
 * some numeric values are fractions, negative, or too large for int32_t.
 *
 * For characters without any numeric values in the Unicode Character Database,
 * this function will return U_NO_NUMERIC_VALUE.
 *
 * Similar to java.lang.Character.getNumericValue(), but u_getNumericValue()
 * also supports negative values, large values, and fractions,
 * while Java's getNumericValue() returns values 10..35 for ASCII letters.
 *
 * @param c Code point to get the numeric value for.
 * @return Numeric value of c, or U_NO_NUMERIC_VALUE if none is defined.
 *
 * @see U_NO_NUMERIC_VALUE
 * @stable ICU 2.2
 */
U_STABLE double U_EXPORT2
u_getNumericValue(UChar32 c);

/**
 * Special value that is returned by u_getNumericValue when
 * no numeric value is defined for a code point.
 *
 * @see u_getNumericValue
 * @stable ICU 2.2
 */
#define U_NO_NUMERIC_VALUE ((double)-123456789.)

/**
 * Determines whether the specified code point has the general category "Ll"
 * (lowercase letter).
 *
 * Same as java.lang.Character.isLowerCase().
 *
 * This misses some characters that are also lowercase but
 * have a different general category value.
 * In order to include those, use UCHAR_LOWERCASE.
 *
 * In addition to being equivalent to a Java function, this also serves
 * as a C/POSIX migration function.
 * See the comments about C/POSIX character classification functions in the
 * documentation at the top of this header file.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is an Ll lowercase letter
 *
 * @see UCHAR_LOWERCASE
 * @see u_isupper
 * @see u_istitle
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_islower(UChar32 c);

/**
 * Determines whether the specified code point has the general category "Lu"
 * (uppercase letter).
 *
 * Same as java.lang.Character.isUpperCase().
 *
 * This misses some characters that are also uppercase but
 * have a different general category value.
 * In order to include those, use UCHAR_UPPERCASE.
 *
 * In addition to being equivalent to a Java function, this also serves
 * as a C/POSIX migration function.
 * See the comments about C/POSIX character classification functions in the
 * documentation at the top of this header file.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is an Lu uppercase letter
 *
 * @see UCHAR_UPPERCASE
 * @see u_islower
 * @see u_istitle
 * @see u_tolower
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_isupper(UChar32 c);

/**
 * Determines whether the specified code point is a titlecase letter.
 * True for general category "Lt" (titlecase letter).
 *
 * Same as java.lang.Character.isTitleCase().
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is an Lt titlecase letter
 *
 * @see u_isupper
 * @see u_islower
 * @see u_totitle
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_istitle(UChar32 c);

/**
 * Determines whether the specified code point is a digit character according to Java.
 * True for characters with general category "Nd" (decimal digit numbers).
 * Beginning with Unicode 4, this is the same as
 * testing for the Numeric_Type of Decimal.
 *
 * Same as java.lang.Character.isDigit().
 *
 * In addition to being equivalent to a Java function, this also serves
 * as a C/POSIX migration function.
 * See the comments about C/POSIX character classification functions in the
 * documentation at the top of this header file.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is a digit character according to Character.isDigit()
 *
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_isdigit(UChar32 c);

/**
 * Determines whether the specified code point is a letter character.
 * True for general categories "L" (letters).
 *
 * Same as java.lang.Character.isLetter().
 *
 * In addition to being equivalent to a Java function, this also serves
 * as a C/POSIX migration function.
 * See the comments about C/POSIX character classification functions in the
 * documentation at the top of this header file.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is a letter character
 *
 * @see u_isdigit
 * @see u_isalnum
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_isalpha(UChar32 c);

/**
 * Determines whether the specified code point is an alphanumeric character
 * (letter or digit) according to Java.
 * True for characters with general categories
 * "L" (letters) and "Nd" (decimal digit numbers).
 *
 * Same as java.lang.Character.isLetterOrDigit().
 *
 * In addition to being equivalent to a Java function, this also serves
 * as a C/POSIX migration function.
 * See the comments about C/POSIX character classification functions in the
 * documentation at the top of this header file.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is an alphanumeric character according to Character.isLetterOrDigit()
 *
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_isalnum(UChar32 c);

/**
 * Determines whether the specified code point is a hexadecimal digit.
 * This is equivalent to u_digit(c, 16)>=0.
 * True for characters with general category "Nd" (decimal digit numbers)
 * as well as Latin letters a-f and A-F in both ASCII and Fullwidth ASCII.
 * (That is, for letters with code points
 * 0041..0046, 0061..0066, FF21..FF26, FF41..FF46.)
 *
 * In order to narrow the definition of hexadecimal digits to only ASCII
 * characters, use (c<=0x7f && u_isxdigit(c)).
 *
 * This is a C/POSIX migration function.
 * See the comments about C/POSIX character classification functions in the
 * documentation at the top of this header file.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is a hexadecimal digit
 *
 * @stable ICU 2.6
 */
U_STABLE UBool U_EXPORT2
u_isxdigit(UChar32 c);

/**
 * Determines whether the specified code point is a punctuation character.
 * True for characters with general categories "P" (punctuation).
 *
 * This is a C/POSIX migration function.
 * See the comments about C/POSIX character classification functions in the
 * documentation at the top of this header file.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is a punctuation character
 *
 * @stable ICU 2.6
 */
U_STABLE UBool U_EXPORT2
u_ispunct(UChar32 c);

/**
 * Determines whether the specified code point is a "graphic" character
 * (printable, excluding spaces).
 * TRUE for all characters except those with general categories
 * "Cc" (control codes), "Cf" (format controls), "Cs" (surrogates),
 * "Cn" (unassigned), and "Z" (separators).
 *
 * This is a C/POSIX migration function.
 * See the comments about C/POSIX character classification functions in the
 * documentation at the top of this header file.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is a "graphic" character
 *
 * @stable ICU 2.6
 */
U_STABLE UBool U_EXPORT2
u_isgraph(UChar32 c);

/**
 * Determines whether the specified code point is a "blank" or "horizontal space",
 * a character that visibly separates words on a line.
 * The following are equivalent definitions:
 *
 * TRUE for Unicode White_Space characters except for "vertical space controls"
 * where "vertical space controls" are the following characters:
 * U+000A (LF) U+000B (VT) U+000C (FF) U+000D (CR) U+0085 (NEL) U+2028 (LS) U+2029 (PS)
 *
 * same as
 *
 * TRUE for U+0009 (TAB) and characters with general category "Zs" (space separators)
 * except Zero Width Space (ZWSP, U+200B).
 *
 * Note: There are several ICU whitespace functions; please see the uchar.h
 * file documentation for a detailed comparison.
 *
 * This is a C/POSIX migration function.
 * See the comments about C/POSIX character classification functions in the
 * documentation at the top of this header file.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is a "blank"
 *
 * @stable ICU 2.6
 */
U_STABLE UBool U_EXPORT2
u_isblank(UChar32 c);

/**
 * Determines whether the specified code point is "defined",
 * which usually means that it is assigned a character.
 * True for general categories other than "Cn" (other, not assigned),
 * i.e., true for all code points mentioned in UnicodeData.txt.
 *
 * Note that non-character code points (e.g., U+FDD0) are not "defined"
 * (they are Cn), but surrogate code points are "defined" (Cs).
 *
 * Same as java.lang.Character.isDefined().
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is assigned a character
 *
 * @see u_isdigit
 * @see u_isalpha
 * @see u_isalnum
 * @see u_isupper
 * @see u_islower
 * @see u_istitle
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_isdefined(UChar32 c);

/**
 * Determines if the specified character is a space character or not.
 *
 * Note: There are several ICU whitespace functions; please see the uchar.h
 * file documentation for a detailed comparison.
 *
 * This is a C/POSIX migration function.
 * See the comments about C/POSIX character classification functions in the
 * documentation at the top of this header file.
 *
 * @param c    the character to be tested
 * @return  true if the character is a space character; false otherwise.
 *
 * @see u_isJavaSpaceChar
 * @see u_isWhitespace
 * @see u_isUWhiteSpace
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_isspace(UChar32 c);

/**
 * Determine if the specified code point is a space character according to Java.
 * True for characters with general categories "Z" (separators),
 * which does not include control codes (e.g., TAB or Line Feed).
 *
 * Same as java.lang.Character.isSpaceChar().
 *
 * Note: There are several ICU whitespace functions; please see the uchar.h
 * file documentation for a detailed comparison.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is a space character according to Character.isSpaceChar()
 *
 * @see u_isspace
 * @see u_isWhitespace
 * @see u_isUWhiteSpace
 * @stable ICU 2.6
 */
U_STABLE UBool U_EXPORT2
u_isJavaSpaceChar(UChar32 c);

/**
 * Determines if the specified code point is a whitespace character according to Java/ICU.
 * A character is considered to be a Java whitespace character if and only
 * if it satisfies one of the following criteria:
 *
 * - It is a Unicode Separator character (categories "Z" = "Zs" or "Zl" or "Zp"), but is not
 *      also a non-breaking space (U+00A0 NBSP or U+2007 Figure Space or U+202F Narrow NBSP).
 * - It is U+0009 HORIZONTAL TABULATION.
 * - It is U+000A LINE FEED.
 * - It is U+000B VERTICAL TABULATION.
 * - It is U+000C FORM FEED.
 * - It is U+000D CARRIAGE RETURN.
 * - It is U+001C FILE SEPARATOR.
 * - It is U+001D GROUP SEPARATOR.
 * - It is U+001E RECORD SEPARATOR.
 * - It is U+001F UNIT SEPARATOR.
 *
 * This API tries to sync with the semantics of Java's
 * java.lang.Character.isWhitespace(), but it may not return
 * the exact same results because of the Unicode version
 * difference.
 *
 * Note: Unicode 4.0.1 changed U+200B ZERO WIDTH SPACE from a Space Separator (Zs)
 * to a Format Control (Cf). Since then, isWhitespace(0x200b) returns false.
 * See http://www.unicode.org/versions/Unicode4.0.1/
 *
 * Note: There are several ICU whitespace functions; please see the uchar.h
 * file documentation for a detailed comparison.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is a whitespace character according to Java/ICU
 *
 * @see u_isspace
 * @see u_isJavaSpaceChar
 * @see u_isUWhiteSpace
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_isWhitespace(UChar32 c);

/**
 * Determines whether the specified code point is a control character
 * (as defined by this function).
 * A control character is one of the following:
 * - ISO 8-bit control character (U+0000..U+001f and U+007f..U+009f)
 * - U_CONTROL_CHAR (Cc)
 * - U_FORMAT_CHAR (Cf)
 * - U_LINE_SEPARATOR (Zl)
 * - U_PARAGRAPH_SEPARATOR (Zp)
 *
 * This is a C/POSIX migration function.
 * See the comments about C/POSIX character classification functions in the
 * documentation at the top of this header file.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is a control character
 *
 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
 * @see u_isprint
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_iscntrl(UChar32 c);

/**
 * Determines whether the specified code point is an ISO control code.
 * True for U+0000..U+001f and U+007f..U+009f (general category "Cc").
 *
 * Same as java.lang.Character.isISOControl().
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is an ISO control code
 *
 * @see u_iscntrl
 * @stable ICU 2.6
 */
U_STABLE UBool U_EXPORT2
u_isISOControl(UChar32 c);

/**
 * Determines whether the specified code point is a printable character.
 * True for general categories <em>other</em> than "C" (controls).
 *
 * This is a C/POSIX migration function.
 * See the comments about C/POSIX character classification functions in the
 * documentation at the top of this header file.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is a printable character
 *
 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
 * @see u_iscntrl
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_isprint(UChar32 c);

/**
 * Determines whether the specified code point is a base character.
 * True for general categories "L" (letters), "N" (numbers),
 * "Mc" (spacing combining marks), and "Me" (enclosing marks).
 *
 * Note that this is different from the Unicode definition in
 * chapter 3.5, conformance clause D13,
 * which defines base characters to be all characters (not Cn)
 * that do not graphically combine with preceding characters (M)
 * and that are neither control (Cc) or format (Cf) characters.
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is a base character according to this function
 *
 * @see u_isalpha
 * @see u_isdigit
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_isbase(UChar32 c);

/**
 * Returns the bidirectional category value for the code point,
 * which is used in the Unicode bidirectional algorithm
 * (UAX #9 http://www.unicode.org/reports/tr9/).
 * Note that some <em>unassigned</em> code points have bidi values
 * of R or AL because they are in blocks that are reserved
 * for Right-To-Left scripts.
 *
 * Same as java.lang.Character.getDirectionality()
 *
 * @param c the code point to be tested
 * @return the bidirectional category (UCharDirection) value
 *
 * @see UCharDirection
 * @stable ICU 2.0
 */
U_STABLE UCharDirection U_EXPORT2
u_charDirection(UChar32 c);

/**
 * Determines whether the code point has the Bidi_Mirrored property.
 * This property is set for characters that are commonly used in
 * Right-To-Left contexts and need to be displayed with a "mirrored"
 * glyph.
 *
 * Same as java.lang.Character.isMirrored().
 * Same as UCHAR_BIDI_MIRRORED
 *
 * @param c the code point to be tested
 * @return TRUE if the character has the Bidi_Mirrored property
 *
 * @see UCHAR_BIDI_MIRRORED
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_isMirrored(UChar32 c);

/**
 * Maps the specified character to a "mirror-image" character.
 * For characters with the Bidi_Mirrored property, implementations
 * sometimes need a "poor man's" mapping to another Unicode
 * character (code point) such that the default glyph may serve
 * as the mirror-image of the default glyph of the specified
 * character. This is useful for text conversion to and from
 * codepages with visual order, and for displays without glyph
 * selecetion capabilities.
 *
 * @param c the code point to be mapped
 * @return another Unicode code point that may serve as a mirror-image
 *         substitute, or c itself if there is no such mapping or c
 *         does not have the Bidi_Mirrored property
 *
 * @see UCHAR_BIDI_MIRRORED
 * @see u_isMirrored
 * @stable ICU 2.0
 */
U_STABLE UChar32 U_EXPORT2
u_charMirror(UChar32 c);

/**
 * Returns the general category value for the code point.
 *
 * Same as java.lang.Character.getType().
 *
 * @param c the code point to be tested
 * @return the general category (UCharCategory) value
 *
 * @see UCharCategory
 * @stable ICU 2.0
 */
U_STABLE int8_t U_EXPORT2
u_charType(UChar32 c);

/**
 * Get a single-bit bit set for the general category of a character.
 * This bit set can be compared bitwise with U_GC_SM_MASK, U_GC_L_MASK, etc.
 * Same as U_MASK(u_charType(c)).
 *
 * @param c the code point to be tested
 * @return a single-bit mask corresponding to the general category (UCharCategory) value
 *
 * @see u_charType
 * @see UCharCategory
 * @see U_GC_CN_MASK
 * @stable ICU 2.1
 */
#define U_GET_GC_MASK(c) U_MASK(u_charType(c))

/**
 * Callback from u_enumCharTypes(), is called for each contiguous range
 * of code points c (where start<=c<limit)
 * with the same Unicode general category ("character type").
 *
 * The callback function can stop the enumeration by returning FALSE.
 *
 * @param context an opaque pointer, as passed into utrie_enum()
 * @param start the first code point in a contiguous range with value
 * @param limit one past the last code point in a contiguous range with value
 * @param type the general category for all code points in [start..limit[
 * @return FALSE to stop the enumeration
 *
 * @stable ICU 2.1
 * @see UCharCategory
 * @see u_enumCharTypes
 */
typedef UBool U_CALLCONV
UCharEnumTypeRange(const void *context, UChar32 start, UChar32 limit, UCharCategory type);

/**
 * Enumerate efficiently all code points with their Unicode general categories.
 *
 * This is useful for building data structures (e.g., UnicodeSet's),
 * for enumerating all assigned code points (type!=U_UNASSIGNED), etc.
 *
 * For each contiguous range of code points with a given general category ("character type"),
 * the UCharEnumTypeRange function is called.
 * Adjacent ranges have different types.
 * The Unicode Standard guarantees that the numeric value of the type is 0..31.
 *
 * @param enumRange a pointer to a function that is called for each contiguous range
 *                  of code points with the same general category
 * @param context an opaque pointer that is passed on to the callback function
 *
 * @stable ICU 2.1
 * @see UCharCategory
 * @see UCharEnumTypeRange
 */
U_STABLE void U_EXPORT2
u_enumCharTypes(UCharEnumTypeRange *enumRange, const void *context);

#if !UCONFIG_NO_NORMALIZATION

/**
 * Returns the combining class of the code point as specified in UnicodeData.txt.
 *
 * @param c the code point of the character
 * @return the combining class of the character
 * @stable ICU 2.0
 */
U_STABLE uint8_t U_EXPORT2
u_getCombiningClass(UChar32 c);

#endif

/**
 * Returns the decimal digit value of a decimal digit character.
 * Such characters have the general category "Nd" (decimal digit numbers)
 * and a Numeric_Type of Decimal.
 *
 * Unlike ICU releases before 2.6, no digit values are returned for any
 * Han characters because Han number characters are often used with a special
 * Chinese-style number format (with characters for powers of 10 in between)
 * instead of in decimal-positional notation.
 * Unicode 4 explicitly assigns Han number characters the Numeric_Type
 * Numeric instead of Decimal.
 * See Jitterbug 1483 for more details.
 *
 * Use u_getIntPropertyValue(c, UCHAR_NUMERIC_TYPE) and u_getNumericValue()
 * for complete numeric Unicode properties.
 *
 * @param c the code point for which to get the decimal digit value
 * @return the decimal digit value of c,
 *         or -1 if c is not a decimal digit character
 *
 * @see u_getNumericValue
 * @stable ICU 2.0
 */
U_STABLE int32_t U_EXPORT2
u_charDigitValue(UChar32 c);

/**
 * Returns the Unicode allocation block that contains the character.
 *
 * @param c the code point to be tested
 * @return the block value (UBlockCode) for c
 *
 * @see UBlockCode
 * @stable ICU 2.0
 */
U_STABLE UBlockCode U_EXPORT2
ublock_getCode(UChar32 c);

/**
 * Retrieve the name of a Unicode character.
 * Depending on <code>nameChoice</code>, the character name written
 * into the buffer is the "modern" name or the name that was defined
 * in Unicode version 1.0.
 * The name contains only "invariant" characters
 * like A-Z, 0-9, space, and '-'.
 * Unicode 1.0 names are only retrieved if they are different from the modern
 * names and if the data file contains the data for them. gennames may or may
 * not be called with a command line option to include 1.0 names in unames.dat.
 *
 * @param code The character (code point) for which to get the name.
 *             It must be <code>0<=code<=0x10ffff</code>.
 * @param nameChoice Selector for which name to get.
 * @param buffer Destination address for copying the name.
 *               The name will always be zero-terminated.
 *               If there is no name, then the buffer will be set to the empty string.
 * @param bufferLength <code>==sizeof(buffer)</code>
 * @param pErrorCode Pointer to a UErrorCode variable;
 *        check for <code>U_SUCCESS()</code> after <code>u_charName()</code>
 *        returns.
 * @return The length of the name, or 0 if there is no name for this character.
 *         If the bufferLength is less than or equal to the length, then the buffer
 *         contains the truncated name and the returned length indicates the full
 *         length of the name.
 *         The length does not include the zero-termination.
 *
 * @see UCharNameChoice
 * @see u_charFromName
 * @see u_enumCharNames
 * @stable ICU 2.0
 */
U_STABLE int32_t U_EXPORT2
u_charName(UChar32 code, UCharNameChoice nameChoice,
           char *buffer, int32_t bufferLength,
           UErrorCode *pErrorCode);

/**
 * Get the ISO 10646 comment for a character.
 * The ISO 10646 comment is an informative field in the Unicode Character
 * Database (UnicodeData.txt field 11) and is from the ISO 10646 names list.
 *
 * Note: Unicode 5.2 removes all ISO comment data, resulting in empty strings
 * returned for all characters.
 *
 * @param c The character (code point) for which to get the ISO comment.
 *             It must be <code>0<=c<=0x10ffff</code>.
 * @param dest Destination address for copying the comment.
 *             The comment will be zero-terminated if possible.
 *             If there is no comment, then the buffer will be set to the empty string.
 * @param destCapacity <code>==sizeof(dest)</code>
 * @param pErrorCode Pointer to a UErrorCode variable;
 *        check for <code>U_SUCCESS()</code> after <code>u_getISOComment()</code>
 *        returns.
 * @return The length of the comment, or 0 if there is no comment for this character.
 *         If the destCapacity is less than or equal to the length, then the buffer
 *         contains the truncated name and the returned length indicates the full
 *         length of the name.
 *         The length does not include the zero-termination.
 *
 * @stable ICU 2.2
 */
U_STABLE int32_t U_EXPORT2
u_getISOComment(UChar32 c,
                char *dest, int32_t destCapacity,
                UErrorCode *pErrorCode);

/**
 * Find a Unicode character by its name and return its code point value.
 * The name is matched exactly and completely.
 * If the name does not correspond to a code point, <i>pErrorCode</i>
 * is set to <code>U_INVALID_CHAR_FOUND</code>.
 * A Unicode 1.0 name is matched only if it differs from the modern name.
 * Unicode names are all uppercase. Extended names are lowercase followed
 * by an uppercase hexadecimal number, and within angle brackets.
 *
 * @param nameChoice Selector for which name to match.
 * @param name The name to match.
 * @param pErrorCode Pointer to a UErrorCode variable
 * @return The Unicode value of the code point with the given name,
 *         or an undefined value if there is no such code point.
 *
 * @see UCharNameChoice
 * @see u_charName
 * @see u_enumCharNames
 * @stable ICU 1.7
 */
U_STABLE UChar32 U_EXPORT2
u_charFromName(UCharNameChoice nameChoice,
               const char *name,
               UErrorCode *pErrorCode);

/**
 * Type of a callback function for u_enumCharNames() that gets called
 * for each Unicode character with the code point value and
 * the character name.
 * If such a function returns FALSE, then the enumeration is stopped.
 *
 * @param context The context pointer that was passed to u_enumCharNames().
 * @param code The Unicode code point for the character with this name.
 * @param nameChoice Selector for which kind of names is enumerated.
 * @param name The character's name, zero-terminated.
 * @param length The length of the name.
 * @return TRUE if the enumeration should continue, FALSE to stop it.
 *
 * @see UCharNameChoice
 * @see u_enumCharNames
 * @stable ICU 1.7
 */
typedef UBool U_CALLCONV UEnumCharNamesFn(void *context,
                               UChar32 code,
                               UCharNameChoice nameChoice,
                               const char *name,
                               int32_t length);

/**
 * Enumerate all assigned Unicode characters between the start and limit
 * code points (start inclusive, limit exclusive) and call a function
 * for each, passing the code point value and the character name.
 * For Unicode 1.0 names, only those are enumerated that differ from the
 * modern names.
 *
 * @param start The first code point in the enumeration range.
 * @param limit One more than the last code point in the enumeration range
 *              (the first one after the range).
 * @param fn The function that is to be called for each character name.
 * @param context An arbitrary pointer that is passed to the function.
 * @param nameChoice Selector for which kind of names to enumerate.
 * @param pErrorCode Pointer to a UErrorCode variable
 *
 * @see UCharNameChoice
 * @see UEnumCharNamesFn
 * @see u_charName
 * @see u_charFromName
 * @stable ICU 1.7
 */
U_STABLE void U_EXPORT2
u_enumCharNames(UChar32 start, UChar32 limit,
                UEnumCharNamesFn *fn,
                void *context,
                UCharNameChoice nameChoice,
                UErrorCode *pErrorCode);

/**
 * Return the Unicode name for a given property, as given in the
 * Unicode database file PropertyAliases.txt.
 *
 * In addition, this function maps the property
 * UCHAR_GENERAL_CATEGORY_MASK to the synthetic names "gcm" /
 * "General_Category_Mask".  These names are not in
 * PropertyAliases.txt.
 *
 * @param property UProperty selector other than UCHAR_INVALID_CODE.
 *         If out of range, NULL is returned.
 *
 * @param nameChoice selector for which name to get.  If out of range,
 *         NULL is returned.  All properties have a long name.  Most
 *         have a short name, but some do not.  Unicode allows for
 *         additional names; if present these will be returned by
 *         U_LONG_PROPERTY_NAME + i, where i=1, 2,...
 *
 * @return a pointer to the name, or NULL if either the
 *         property or the nameChoice is out of range.  If a given
 *         nameChoice returns NULL, then all larger values of
 *         nameChoice will return NULL, with one exception: if NULL is
 *         returned for U_SHORT_PROPERTY_NAME, then
 *         U_LONG_PROPERTY_NAME (and higher) may still return a
 *         non-NULL value.  The returned pointer is valid until
 *         u_cleanup() is called.
 *
 * @see UProperty
 * @see UPropertyNameChoice
 * @stable ICU 2.4
 */
U_STABLE const char* U_EXPORT2
u_getPropertyName(UProperty property,
                  UPropertyNameChoice nameChoice);

/**
 * Return the UProperty enum for a given property name, as specified
 * in the Unicode database file PropertyAliases.txt.  Short, long, and
 * any other variants are recognized.
 *
 * In addition, this function maps the synthetic names "gcm" /
 * "General_Category_Mask" to the property
 * UCHAR_GENERAL_CATEGORY_MASK.  These names are not in
 * PropertyAliases.txt.
 *
 * @param alias the property name to be matched.  The name is compared
 *         using "loose matching" as described in PropertyAliases.txt.
 *
 * @return a UProperty enum, or UCHAR_INVALID_CODE if the given name
 *         does not match any property.
 *
 * @see UProperty
 * @stable ICU 2.4
 */
U_STABLE UProperty U_EXPORT2
u_getPropertyEnum(const char* alias);

/**
 * Return the Unicode name for a given property value, as given in the
 * Unicode database file PropertyValueAliases.txt.
 *
 * Note: Some of the names in PropertyValueAliases.txt can only be
 * retrieved using UCHAR_GENERAL_CATEGORY_MASK, not
 * UCHAR_GENERAL_CATEGORY.  These include: "C" / "Other", "L" /
 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P"
 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator".
 *
 * @param property UProperty selector constant.
 *        Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
 *        or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
 *        or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
 *        If out of range, NULL is returned.
 *
 * @param value selector for a value for the given property.  If out
 *         of range, NULL is returned.  In general, valid values range
 *         from 0 up to some maximum.  There are a few exceptions:
 *         (1.) UCHAR_BLOCK values begin at the non-zero value
 *         UBLOCK_BASIC_LATIN.  (2.)  UCHAR_CANONICAL_COMBINING_CLASS
 *         values are not contiguous and range from 0..240.  (3.)
 *         UCHAR_GENERAL_CATEGORY_MASK values are not values of
 *         UCharCategory, but rather mask values produced by
 *         U_GET_GC_MASK().  This allows grouped categories such as
 *         [:L:] to be represented.  Mask values range
 *         non-contiguously from 1..U_GC_P_MASK.
 *
 * @param nameChoice selector for which name to get.  If out of range,
 *         NULL is returned.  All values have a long name.  Most have
 *         a short name, but some do not.  Unicode allows for
 *         additional names; if present these will be returned by
 *         U_LONG_PROPERTY_NAME + i, where i=1, 2,...

 * @return a pointer to the name, or NULL if either the
 *         property or the nameChoice is out of range.  If a given
 *         nameChoice returns NULL, then all larger values of
 *         nameChoice will return NULL, with one exception: if NULL is
 *         returned for U_SHORT_PROPERTY_NAME, then
 *         U_LONG_PROPERTY_NAME (and higher) may still return a
 *         non-NULL value.  The returned pointer is valid until
 *         u_cleanup() is called.
 *
 * @see UProperty
 * @see UPropertyNameChoice
 * @stable ICU 2.4
 */
U_STABLE const char* U_EXPORT2
u_getPropertyValueName(UProperty property,
                       int32_t value,
                       UPropertyNameChoice nameChoice);

/**
 * Return the property value integer for a given value name, as
 * specified in the Unicode database file PropertyValueAliases.txt.
 * Short, long, and any other variants are recognized.
 *
 * Note: Some of the names in PropertyValueAliases.txt will only be
 * recognized with UCHAR_GENERAL_CATEGORY_MASK, not
 * UCHAR_GENERAL_CATEGORY.  These include: "C" / "Other", "L" /
 * "Letter", "LC" / "Cased_Letter", "M" / "Mark", "N" / "Number", "P"
 * / "Punctuation", "S" / "Symbol", and "Z" / "Separator".
 *
 * @param property UProperty selector constant.
 *        Must be UCHAR_BINARY_START<=which<UCHAR_BINARY_LIMIT
 *        or UCHAR_INT_START<=which<UCHAR_INT_LIMIT
 *        or UCHAR_MASK_START<=which<UCHAR_MASK_LIMIT.
 *        If out of range, UCHAR_INVALID_CODE is returned.
 *
 * @param alias the value name to be matched.  The name is compared
 *         using "loose matching" as described in
 *         PropertyValueAliases.txt.
 *
 * @return a value integer or UCHAR_INVALID_CODE if the given name
 *         does not match any value of the given property, or if the
 *         property is invalid.  Note: UCHAR_GENERAL_CATEGORY_MASK values
 *         are not values of UCharCategory, but rather mask values
 *         produced by U_GET_GC_MASK().  This allows grouped
 *         categories such as [:L:] to be represented.
 *
 * @see UProperty
 * @stable ICU 2.4
 */
U_STABLE int32_t U_EXPORT2
u_getPropertyValueEnum(UProperty property,
                       const char* alias);

/**
 * Determines if the specified character is permissible as the
 * first character in an identifier according to Unicode
 * (The Unicode Standard, Version 3.0, chapter 5.16 Identifiers).
 * True for characters with general categories "L" (letters) and "Nl" (letter numbers).
 *
 * Same as java.lang.Character.isUnicodeIdentifierStart().
 * Same as UCHAR_ID_START
 *
 * @param c the code point to be tested
 * @return TRUE if the code point may start an identifier
 *
 * @see UCHAR_ID_START
 * @see u_isalpha
 * @see u_isIDPart
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_isIDStart(UChar32 c);

/**
 * Determines if the specified character is permissible
 * in an identifier according to Java.
 * True for characters with general categories "L" (letters),
 * "Nl" (letter numbers), "Nd" (decimal digits),
 * "Mc" and "Mn" (combining marks), "Pc" (connecting punctuation), and
 * u_isIDIgnorable(c).
 *
 * Same as java.lang.Character.isUnicodeIdentifierPart().
 * Almost the same as Unicode's ID_Continue (UCHAR_ID_CONTINUE)
 * except that Unicode recommends to ignore Cf which is less than
 * u_isIDIgnorable(c).
 *
 * @param c the code point to be tested
 * @return TRUE if the code point may occur in an identifier according to Java
 *
 * @see UCHAR_ID_CONTINUE
 * @see u_isIDStart
 * @see u_isIDIgnorable
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_isIDPart(UChar32 c);

/**
 * Determines if the specified character should be regarded
 * as an ignorable character in an identifier,
 * according to Java.
 * True for characters with general category "Cf" (format controls) as well as
 * non-whitespace ISO controls
 * (U+0000..U+0008, U+000E..U+001B, U+007F..U+009F).
 *
 * Same as java.lang.Character.isIdentifierIgnorable().
 *
 * Note that Unicode just recommends to ignore Cf (format controls).
 *
 * @param c the code point to be tested
 * @return TRUE if the code point is ignorable in identifiers according to Java
 *
 * @see UCHAR_DEFAULT_IGNORABLE_CODE_POINT
 * @see u_isIDStart
 * @see u_isIDPart
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_isIDIgnorable(UChar32 c);

/**
 * Determines if the specified character is permissible as the
 * first character in a Java identifier.
 * In addition to u_isIDStart(c), true for characters with
 * general categories "Sc" (currency symbols) and "Pc" (connecting punctuation).
 *
 * Same as java.lang.Character.isJavaIdentifierStart().
 *
 * @param c the code point to be tested
 * @return TRUE if the code point may start a Java identifier
 *
 * @see     u_isJavaIDPart
 * @see     u_isalpha
 * @see     u_isIDStart
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_isJavaIDStart(UChar32 c);

/**
 * Determines if the specified character is permissible
 * in a Java identifier.
 * In addition to u_isIDPart(c), true for characters with
 * general category "Sc" (currency symbols).
 *
 * Same as java.lang.Character.isJavaIdentifierPart().
 *
 * @param c the code point to be tested
 * @return TRUE if the code point may occur in a Java identifier
 *
 * @see     u_isIDIgnorable
 * @see     u_isJavaIDStart
 * @see     u_isalpha
 * @see     u_isdigit
 * @see     u_isIDPart
 * @stable ICU 2.0
 */
U_STABLE UBool U_EXPORT2
u_isJavaIDPart(UChar32 c);

/**
 * The given character is mapped to its lowercase equivalent according to
 * UnicodeData.txt; if the character has no lowercase equivalent, the character
 * itself is returned.
 *
 * Same as java.lang.Character.toLowerCase().
 *
 * This function only returns the simple, single-code point case mapping.
 * Full case mappings should be used whenever possible because they produce
 * better results by working on whole strings.
 * They take into account the string context and the language and can map
 * to a result string with a different length as appropriate.
 * Full case mappings are applied by the string case mapping functions,
 * see ustring.h and the UnicodeString class.
 * See also the User Guide chapter on C/POSIX migration:
 * http://icu-project.org/userguide/posix.html#case_mappings
 *
 * @param c the code point to be mapped
 * @return the Simple_Lowercase_Mapping of the code point, if any;
 *         otherwise the code point itself.
 * @stable ICU 2.0
 */
U_STABLE UChar32 U_EXPORT2
u_tolower(UChar32 c);

/**
 * The given character is mapped to its uppercase equivalent according to UnicodeData.txt;
 * if the character has no uppercase equivalent, the character itself is
 * returned.
 *
 * Same as java.lang.Character.toUpperCase().
 *
 * This function only returns the simple, single-code point case mapping.
 * Full case mappings should be used whenever possible because they produce
 * better results by working on whole strings.
 * They take into account the string context and the language and can map
 * to a result string with a different length as appropriate.
 * Full case mappings are applied by the string case mapping functions,
 * see ustring.h and the UnicodeString class.
 * See also the User Guide chapter on C/POSIX migration:
 * http://icu-project.org/userguide/posix.html#case_mappings
 *
 * @param c the code point to be mapped
 * @return the Simple_Uppercase_Mapping of the code point, if any;
 *         otherwise the code point itself.
 * @stable ICU 2.0
 */
U_STABLE UChar32 U_EXPORT2
u_toupper(UChar32 c);

/**
 * The given character is mapped to its titlecase equivalent
 * according to UnicodeData.txt;
 * if none is defined, the character itself is returned.
 *
 * Same as java.lang.Character.toTitleCase().
 *
 * This function only returns the simple, single-code point case mapping.
 * Full case mappings should be used whenever possible because they produce
 * better results by working on whole strings.
 * They take into account the string context and the language and can map
 * to a result string with a different length as appropriate.
 * Full case mappings are applied by the string case mapping functions,
 * see ustring.h and the UnicodeString class.
 * See also the User Guide chapter on C/POSIX migration:
 * http://icu-project.org/userguide/posix.html#case_mappings
 *
 * @param c the code point to be mapped
 * @return the Simple_Titlecase_Mapping of the code point, if any;
 *         otherwise the code point itself.
 * @stable ICU 2.0
 */
U_STABLE UChar32 U_EXPORT2
u_totitle(UChar32 c);

/** Option value for case folding: use default mappings defined in CaseFolding.txt. @stable ICU 2.0 */
#define U_FOLD_CASE_DEFAULT 0

/**
 * Option value for case folding:
 *
 * Use the modified set of mappings provided in CaseFolding.txt to handle dotted I
 * and dotless i appropriately for Turkic languages (tr, az).
 *
 * Before Unicode 3.2, CaseFolding.txt contains mappings marked with 'I' that
 * are to be included for default mappings and
 * excluded for the Turkic-specific mappings.
 *
 * Unicode 3.2 CaseFolding.txt instead contains mappings marked with 'T' that
 * are to be excluded for default mappings and
 * included for the Turkic-specific mappings.
 *
 * @stable ICU 2.0
 */
#define U_FOLD_CASE_EXCLUDE_SPECIAL_I 1

/**
 * The given character is mapped to its case folding equivalent according to
 * UnicodeData.txt and CaseFolding.txt;
 * if the character has no case folding equivalent, the character
 * itself is returned.
 *
 * This function only returns the simple, single-code point case mapping.
 * Full case mappings should be used whenever possible because they produce
 * better results by working on whole strings.
 * They take into account the string context and the language and can map
 * to a result string with a different length as appropriate.
 * Full case mappings are applied by the string case mapping functions,
 * see ustring.h and the UnicodeString class.
 * See also the User Guide chapter on C/POSIX migration:
 * http://icu-project.org/userguide/posix.html#case_mappings
 *
 * @param c the code point to be mapped
 * @param options Either U_FOLD_CASE_DEFAULT or U_FOLD_CASE_EXCLUDE_SPECIAL_I
 * @return the Simple_Case_Folding of the code point, if any;
 *         otherwise the code point itself.
 * @stable ICU 2.0
 */
U_STABLE UChar32 U_EXPORT2
u_foldCase(UChar32 c, uint32_t options);

/**
 * Returns the decimal digit value of the code point in the
 * specified radix.
 *
 * If the radix is not in the range <code>2<=radix<=36</code> or if the
 * value of <code>c</code> is not a valid digit in the specified
 * radix, <code>-1</code> is returned. A character is a valid digit
 * if at least one of the following is true:
 * <ul>
 * <li>The character has a decimal digit value.
 *     Such characters have the general category "Nd" (decimal digit numbers)
 *     and a Numeric_Type of Decimal.
 *     In this case the value is the character's decimal digit value.</li>
 * <li>The character is one of the uppercase Latin letters
 *     <code>'A'</code> through <code>'Z'</code>.
 *     In this case the value is <code>c-'A'+10</code>.</li>
 * <li>The character is one of the lowercase Latin letters
 *     <code>'a'</code> through <code>'z'</code>.
 *     In this case the value is <code>ch-'a'+10</code>.</li>
 * <li>Latin letters from both the ASCII range (0061..007A, 0041..005A)
 *     as well as from the Fullwidth ASCII range (FF41..FF5A, FF21..FF3A)
 *     are recognized.</li>
 * </ul>
 *
 * Same as java.lang.Character.digit().
 *
 * @param   ch      the code point to be tested.
 * @param   radix   the radix.
 * @return  the numeric value represented by the character in the
 *          specified radix,
 *          or -1 if there is no value or if the value exceeds the radix.
 *
 * @see     UCHAR_NUMERIC_TYPE
 * @see     u_forDigit
 * @see     u_charDigitValue
 * @see     u_isdigit
 * @stable ICU 2.0
 */
U_STABLE int32_t U_EXPORT2
u_digit(UChar32 ch, int8_t radix);

/**
 * Determines the character representation for a specific digit in
 * the specified radix. If the value of <code>radix</code> is not a
 * valid radix, or the value of <code>digit</code> is not a valid
 * digit in the specified radix, the null character
 * (<code>U+0000</code>) is returned.
 * <p>
 * The <code>radix</code> argument is valid if it is greater than or
 * equal to 2 and less than or equal to 36.
 * The <code>digit</code> argument is valid if
 * <code>0 <= digit < radix</code>.
 * <p>
 * If the digit is less than 10, then
 * <code>'0' + digit</code> is returned. Otherwise, the value
 * <code>'a' + digit - 10</code> is returned.
 *
 * Same as java.lang.Character.forDigit().
 *
 * @param   digit   the number to convert to a character.
 * @param   radix   the radix.
 * @return  the <code>char</code> representation of the specified digit
 *          in the specified radix.
 *
 * @see     u_digit
 * @see     u_charDigitValue
 * @see     u_isdigit
 * @stable ICU 2.0
 */
U_STABLE UChar32 U_EXPORT2
u_forDigit(int32_t digit, int8_t radix);

/**
 * Get the "age" of the code point.
 * The "age" is the Unicode version when the code point was first
 * designated (as a non-character or for Private Use)
 * or assigned a character.
 * This can be useful to avoid emitting code points to receiving
 * processes that do not accept newer characters.
 * The data is from the UCD file DerivedAge.txt.
 *
 * @param c The code point.
 * @param versionArray The Unicode version number array, to be filled in.
 *
 * @stable ICU 2.1
 */
U_STABLE void U_EXPORT2
u_charAge(UChar32 c, UVersionInfo versionArray);

/**
 * Gets the Unicode version information.
 * The version array is filled in with the version information
 * for the Unicode standard that is currently used by ICU.
 * For example, Unicode version 3.1.1 is represented as an array with
 * the values { 3, 1, 1, 0 }.
 *
 * @param versionArray an output array that will be filled in with
 *                     the Unicode version number
 * @stable ICU 2.0
 */
U_STABLE void U_EXPORT2
u_getUnicodeVersion(UVersionInfo versionArray);

#if !UCONFIG_NO_NORMALIZATION
/**
 * Get the FC_NFKC_Closure property string for a character.
 * See Unicode Standard Annex #15 for details, search for "FC_NFKC_Closure"
 * or for "FNC": http://www.unicode.org/reports/tr15/
 *
 * @param c The character (code point) for which to get the FC_NFKC_Closure string.
 *             It must be <code>0<=c<=0x10ffff</code>.
 * @param dest Destination address for copying the string.
 *             The string will be zero-terminated if possible.
 *             If there is no FC_NFKC_Closure string,
 *             then the buffer will be set to the empty string.
 * @param destCapacity <code>==sizeof(dest)</code>
 * @param pErrorCode Pointer to a UErrorCode variable.
 * @return The length of the string, or 0 if there is no FC_NFKC_Closure string for this character.
 *         If the destCapacity is less than or equal to the length, then the buffer
 *         contains the truncated name and the returned length indicates the full
 *         length of the name.
 *         The length does not include the zero-termination.
 *
 * @stable ICU 2.2
 */
U_STABLE int32_t U_EXPORT2
u_getFC_NFKC_Closure(UChar32 c, UChar *dest, int32_t destCapacity, UErrorCode *pErrorCode);

#endif


U_CDECL_END

#endif /*_UCHAR*/
/*eof*/