This file is indexed.

/usr/include/python3.7m/unicodeobject.h is in libpython3.7-dev 3.7.0~b3-1.

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
#ifndef Py_UNICODEOBJECT_H
#define Py_UNICODEOBJECT_H

#include <stdarg.h>

/*

Unicode implementation based on original code by Fredrik Lundh,
modified by Marc-Andre Lemburg (mal@lemburg.com) according to the
Unicode Integration Proposal. (See
http://www.egenix.com/files/python/unicode-proposal.txt).

Copyright (c) Corporation for National Research Initiatives.


 Original header:
 --------------------------------------------------------------------

 * Yet another Unicode string type for Python.  This type supports the
 * 16-bit Basic Multilingual Plane (BMP) only.
 *
 * Written by Fredrik Lundh, January 1999.
 *
 * Copyright (c) 1999 by Secret Labs AB.
 * Copyright (c) 1999 by Fredrik Lundh.
 *
 * fredrik@pythonware.com
 * http://www.pythonware.com
 *
 * --------------------------------------------------------------------
 * This Unicode String Type is
 *
 * Copyright (c) 1999 by Secret Labs AB
 * Copyright (c) 1999 by Fredrik Lundh
 *
 * By obtaining, using, and/or copying this software and/or its
 * associated documentation, you agree that you have read, understood,
 * and will comply with the following terms and conditions:
 *
 * Permission to use, copy, modify, and distribute this software and its
 * associated documentation for any purpose and without fee is hereby
 * granted, provided that the above copyright notice appears in all
 * copies, and that both that copyright notice and this permission notice
 * appear in supporting documentation, and that the name of Secret Labs
 * AB or the author not be used in advertising or publicity pertaining to
 * distribution of the software without specific, written prior
 * permission.
 *
 * SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD TO
 * THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
 * FITNESS.  IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR BE LIABLE FOR
 * ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
 * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
 * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT
 * OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
 * -------------------------------------------------------------------- */

#include <ctype.h>

/* === Internal API ======================================================= */

/* --- Internal Unicode Format -------------------------------------------- */

/* Python 3.x requires unicode */
#define Py_USING_UNICODE

#ifndef SIZEOF_WCHAR_T
#error Must define SIZEOF_WCHAR_T
#endif

#define Py_UNICODE_SIZE SIZEOF_WCHAR_T

/* If wchar_t can be used for UCS-4 storage, set Py_UNICODE_WIDE.
   Otherwise, Unicode strings are stored as UCS-2 (with limited support
   for UTF-16) */

#if Py_UNICODE_SIZE >= 4
#define Py_UNICODE_WIDE
#endif

/* Set these flags if the platform has "wchar.h" and the
   wchar_t type is a 16-bit unsigned type */
/* #define HAVE_WCHAR_H */
/* #define HAVE_USABLE_WCHAR_T */

/* Py_UNICODE was the native Unicode storage format (code unit) used by
   Python and represents a single Unicode element in the Unicode type.
   With PEP 393, Py_UNICODE is deprecated and replaced with a
   typedef to wchar_t. */

#ifndef Py_LIMITED_API
#define PY_UNICODE_TYPE wchar_t
typedef wchar_t Py_UNICODE /* Py_DEPRECATED(3.3) */;
#endif

/* If the compiler provides a wchar_t type we try to support it
   through the interface functions PyUnicode_FromWideChar(),
   PyUnicode_AsWideChar() and PyUnicode_AsWideCharString(). */

#ifdef HAVE_USABLE_WCHAR_T
# ifndef HAVE_WCHAR_H
#  define HAVE_WCHAR_H
# endif
#endif

#ifdef HAVE_WCHAR_H
#  include <wchar.h>
#endif

/* Py_UCS4 and Py_UCS2 are typedefs for the respective
   unicode representations. */
typedef uint32_t Py_UCS4;
typedef uint16_t Py_UCS2;
typedef uint8_t Py_UCS1;

/* --- Internal Unicode Operations ---------------------------------------- */

/* Since splitting on whitespace is an important use case, and
   whitespace in most situations is solely ASCII whitespace, we
   optimize for the common case by using a quick look-up table
   _Py_ascii_whitespace (see below) with an inlined check.

 */
#ifndef Py_LIMITED_API
#define Py_UNICODE_ISSPACE(ch) \
    ((ch) < 128U ? _Py_ascii_whitespace[(ch)] : _PyUnicode_IsWhitespace(ch))

#define Py_UNICODE_ISLOWER(ch) _PyUnicode_IsLowercase(ch)
#define Py_UNICODE_ISUPPER(ch) _PyUnicode_IsUppercase(ch)
#define Py_UNICODE_ISTITLE(ch) _PyUnicode_IsTitlecase(ch)
#define Py_UNICODE_ISLINEBREAK(ch) _PyUnicode_IsLinebreak(ch)

#define Py_UNICODE_TOLOWER(ch) _PyUnicode_ToLowercase(ch)
#define Py_UNICODE_TOUPPER(ch) _PyUnicode_ToUppercase(ch)
#define Py_UNICODE_TOTITLE(ch) _PyUnicode_ToTitlecase(ch)

#define Py_UNICODE_ISDECIMAL(ch) _PyUnicode_IsDecimalDigit(ch)
#define Py_UNICODE_ISDIGIT(ch) _PyUnicode_IsDigit(ch)
#define Py_UNICODE_ISNUMERIC(ch) _PyUnicode_IsNumeric(ch)
#define Py_UNICODE_ISPRINTABLE(ch) _PyUnicode_IsPrintable(ch)

#define Py_UNICODE_TODECIMAL(ch) _PyUnicode_ToDecimalDigit(ch)
#define Py_UNICODE_TODIGIT(ch) _PyUnicode_ToDigit(ch)
#define Py_UNICODE_TONUMERIC(ch) _PyUnicode_ToNumeric(ch)

#define Py_UNICODE_ISALPHA(ch) _PyUnicode_IsAlpha(ch)

#define Py_UNICODE_ISALNUM(ch) \
       (Py_UNICODE_ISALPHA(ch) || \
    Py_UNICODE_ISDECIMAL(ch) || \
    Py_UNICODE_ISDIGIT(ch) || \
    Py_UNICODE_ISNUMERIC(ch))

#define Py_UNICODE_COPY(target, source, length) \
    memcpy((target), (source), (length)*sizeof(Py_UNICODE))

#define Py_UNICODE_FILL(target, value, length) \
    do {Py_ssize_t i_; Py_UNICODE *t_ = (target); Py_UNICODE v_ = (value);\
        for (i_ = 0; i_ < (length); i_++) t_[i_] = v_;\
    } while (0)

/* macros to work with surrogates */
#define Py_UNICODE_IS_SURROGATE(ch) (0xD800 <= (ch) && (ch) <= 0xDFFF)
#define Py_UNICODE_IS_HIGH_SURROGATE(ch) (0xD800 <= (ch) && (ch) <= 0xDBFF)
#define Py_UNICODE_IS_LOW_SURROGATE(ch) (0xDC00 <= (ch) && (ch) <= 0xDFFF)
/* Join two surrogate characters and return a single Py_UCS4 value. */
#define Py_UNICODE_JOIN_SURROGATES(high, low)  \
    (((((Py_UCS4)(high) & 0x03FF) << 10) |      \
      ((Py_UCS4)(low) & 0x03FF)) + 0x10000)
/* high surrogate = top 10 bits added to D800 */
#define Py_UNICODE_HIGH_SURROGATE(ch) (0xD800 - (0x10000 >> 10) + ((ch) >> 10))
/* low surrogate = bottom 10 bits added to DC00 */
#define Py_UNICODE_LOW_SURROGATE(ch) (0xDC00 + ((ch) & 0x3FF))

/* Check if substring matches at given offset.  The offset must be
   valid, and the substring must not be empty. */

#define Py_UNICODE_MATCH(string, offset, substring) \
    ((*((string)->wstr + (offset)) == *((substring)->wstr)) && \
     ((*((string)->wstr + (offset) + (substring)->wstr_length-1) == *((substring)->wstr + (substring)->wstr_length-1))) && \
     !memcmp((string)->wstr + (offset), (substring)->wstr, (substring)->wstr_length*sizeof(Py_UNICODE)))

#endif /* Py_LIMITED_API */

#ifdef __cplusplus
extern "C" {
#endif

/* --- Unicode Type ------------------------------------------------------- */

#ifndef Py_LIMITED_API

/* ASCII-only strings created through PyUnicode_New use the PyASCIIObject
   structure. state.ascii and state.compact are set, and the data
   immediately follow the structure. utf8_length and wstr_length can be found
   in the length field; the utf8 pointer is equal to the data pointer. */
typedef struct {
    /* There are 4 forms of Unicode strings:

       - compact ascii:

         * structure = PyASCIIObject
         * test: PyUnicode_IS_COMPACT_ASCII(op)
         * kind = PyUnicode_1BYTE_KIND
         * compact = 1
         * ascii = 1
         * ready = 1
         * (length is the length of the utf8 and wstr strings)
         * (data starts just after the structure)
         * (since ASCII is decoded from UTF-8, the utf8 string are the data)

       - compact:

         * structure = PyCompactUnicodeObject
         * test: PyUnicode_IS_COMPACT(op) && !PyUnicode_IS_ASCII(op)
         * kind = PyUnicode_1BYTE_KIND, PyUnicode_2BYTE_KIND or
           PyUnicode_4BYTE_KIND
         * compact = 1
         * ready = 1
         * ascii = 0
         * utf8 is not shared with data
         * utf8_length = 0 if utf8 is NULL
         * wstr is shared with data and wstr_length=length
           if kind=PyUnicode_2BYTE_KIND and sizeof(wchar_t)=2
           or if kind=PyUnicode_4BYTE_KIND and sizeof(wchar_t)=4
         * wstr_length = 0 if wstr is NULL
         * (data starts just after the structure)

       - legacy string, not ready:

         * structure = PyUnicodeObject
         * test: kind == PyUnicode_WCHAR_KIND
         * length = 0 (use wstr_length)
         * hash = -1
         * kind = PyUnicode_WCHAR_KIND
         * compact = 0
         * ascii = 0
         * ready = 0
         * interned = SSTATE_NOT_INTERNED
         * wstr is not NULL
         * data.any is NULL
         * utf8 is NULL
         * utf8_length = 0

       - legacy string, ready:

         * structure = PyUnicodeObject structure
         * test: !PyUnicode_IS_COMPACT(op) && kind != PyUnicode_WCHAR_KIND
         * kind = PyUnicode_1BYTE_KIND, PyUnicode_2BYTE_KIND or
           PyUnicode_4BYTE_KIND
         * compact = 0
         * ready = 1
         * data.any is not NULL
         * utf8 is shared and utf8_length = length with data.any if ascii = 1
         * utf8_length = 0 if utf8 is NULL
         * wstr is shared with data.any and wstr_length = length
           if kind=PyUnicode_2BYTE_KIND and sizeof(wchar_t)=2
           or if kind=PyUnicode_4BYTE_KIND and sizeof(wchar_4)=4
         * wstr_length = 0 if wstr is NULL

       Compact strings use only one memory block (structure + characters),
       whereas legacy strings use one block for the structure and one block
       for characters.

       Legacy strings are created by PyUnicode_FromUnicode() and
       PyUnicode_FromStringAndSize(NULL, size) functions. They become ready
       when PyUnicode_READY() is called.

       See also _PyUnicode_CheckConsistency().
    */
    PyObject_HEAD
    Py_ssize_t length;          /* Number of code points in the string */
    Py_hash_t hash;             /* Hash value; -1 if not set */
    struct {
        /*
           SSTATE_NOT_INTERNED (0)
           SSTATE_INTERNED_MORTAL (1)
           SSTATE_INTERNED_IMMORTAL (2)

           If interned != SSTATE_NOT_INTERNED, the two references from the
           dictionary to this object are *not* counted in ob_refcnt.
         */
        unsigned int interned:2;
        /* Character size:

           - PyUnicode_WCHAR_KIND (0):

             * character type = wchar_t (16 or 32 bits, depending on the
               platform)

           - PyUnicode_1BYTE_KIND (1):

             * character type = Py_UCS1 (8 bits, unsigned)
             * all characters are in the range U+0000-U+00FF (latin1)
             * if ascii is set, all characters are in the range U+0000-U+007F
               (ASCII), otherwise at least one character is in the range
               U+0080-U+00FF

           - PyUnicode_2BYTE_KIND (2):

             * character type = Py_UCS2 (16 bits, unsigned)
             * all characters are in the range U+0000-U+FFFF (BMP)
             * at least one character is in the range U+0100-U+FFFF

           - PyUnicode_4BYTE_KIND (4):

             * character type = Py_UCS4 (32 bits, unsigned)
             * all characters are in the range U+0000-U+10FFFF
             * at least one character is in the range U+10000-U+10FFFF
         */
        unsigned int kind:3;
        /* Compact is with respect to the allocation scheme. Compact unicode
           objects only require one memory block while non-compact objects use
           one block for the PyUnicodeObject struct and another for its data
           buffer. */
        unsigned int compact:1;
        /* The string only contains characters in the range U+0000-U+007F (ASCII)
           and the kind is PyUnicode_1BYTE_KIND. If ascii is set and compact is
           set, use the PyASCIIObject structure. */
        unsigned int ascii:1;
        /* The ready flag indicates whether the object layout is initialized
           completely. This means that this is either a compact object, or
           the data pointer is filled out. The bit is redundant, and helps
           to minimize the test in PyUnicode_IS_READY(). */
        unsigned int ready:1;
        /* Padding to ensure that PyUnicode_DATA() is always aligned to
           4 bytes (see issue #19537 on m68k). */
        unsigned int :24;
    } state;
    wchar_t *wstr;              /* wchar_t representation (null-terminated) */
} PyASCIIObject;

/* Non-ASCII strings allocated through PyUnicode_New use the
   PyCompactUnicodeObject structure. state.compact is set, and the data
   immediately follow the structure. */
typedef struct {
    PyASCIIObject _base;
    Py_ssize_t utf8_length;     /* Number of bytes in utf8, excluding the
                                 * terminating \0. */
    char *utf8;                 /* UTF-8 representation (null-terminated) */
    Py_ssize_t wstr_length;     /* Number of code points in wstr, possible
                                 * surrogates count as two code points. */
} PyCompactUnicodeObject;

/* Strings allocated through PyUnicode_FromUnicode(NULL, len) use the
   PyUnicodeObject structure. The actual string data is initially in the wstr
   block, and copied into the data block using _PyUnicode_Ready. */
typedef struct {
    PyCompactUnicodeObject _base;
    union {
        void *any;
        Py_UCS1 *latin1;
        Py_UCS2 *ucs2;
        Py_UCS4 *ucs4;
    } data;                     /* Canonical, smallest-form Unicode buffer */
} PyUnicodeObject;
#endif

PyAPI_DATA(PyTypeObject) PyUnicode_Type;
PyAPI_DATA(PyTypeObject) PyUnicodeIter_Type;

#define PyUnicode_Check(op) \
                 PyType_FastSubclass(Py_TYPE(op), Py_TPFLAGS_UNICODE_SUBCLASS)
#define PyUnicode_CheckExact(op) (Py_TYPE(op) == &PyUnicode_Type)

/* Fast access macros */
#ifndef Py_LIMITED_API

#define PyUnicode_WSTR_LENGTH(op) \
    (PyUnicode_IS_COMPACT_ASCII(op) ?                  \
     ((PyASCIIObject*)op)->length :                    \
     ((PyCompactUnicodeObject*)op)->wstr_length)

/* Returns the deprecated Py_UNICODE representation's size in code units
   (this includes surrogate pairs as 2 units).
   If the Py_UNICODE representation is not available, it will be computed
   on request.  Use PyUnicode_GET_LENGTH() for the length in code points. */

#define PyUnicode_GET_SIZE(op)                       \
    (assert(PyUnicode_Check(op)),                    \
     (((PyASCIIObject *)(op))->wstr) ?               \
      PyUnicode_WSTR_LENGTH(op) :                    \
      ((void)PyUnicode_AsUnicode((PyObject *)(op)),  \
       assert(((PyASCIIObject *)(op))->wstr),        \
       PyUnicode_WSTR_LENGTH(op)))
    /* Py_DEPRECATED(3.3) */

#define PyUnicode_GET_DATA_SIZE(op) \
    (PyUnicode_GET_SIZE(op) * Py_UNICODE_SIZE)
    /* Py_DEPRECATED(3.3) */

/* Alias for PyUnicode_AsUnicode().  This will create a wchar_t/Py_UNICODE
   representation on demand.  Using this macro is very inefficient now,
   try to port your code to use the new PyUnicode_*BYTE_DATA() macros or
   use PyUnicode_WRITE() and PyUnicode_READ(). */

#define PyUnicode_AS_UNICODE(op) \
    (assert(PyUnicode_Check(op)), \
     (((PyASCIIObject *)(op))->wstr) ? (((PyASCIIObject *)(op))->wstr) : \
      PyUnicode_AsUnicode((PyObject *)(op)))
    /* Py_DEPRECATED(3.3) */

#define PyUnicode_AS_DATA(op) \
    ((const char *)(PyUnicode_AS_UNICODE(op)))
    /* Py_DEPRECATED(3.3) */


/* --- Flexible String Representation Helper Macros (PEP 393) -------------- */

/* Values for PyASCIIObject.state: */

/* Interning state. */
#define SSTATE_NOT_INTERNED 0
#define SSTATE_INTERNED_MORTAL 1
#define SSTATE_INTERNED_IMMORTAL 2

/* Return true if the string contains only ASCII characters, or 0 if not. The
   string may be compact (PyUnicode_IS_COMPACT_ASCII) or not, but must be
   ready. */
#define PyUnicode_IS_ASCII(op)                   \
    (assert(PyUnicode_Check(op)),                \
     assert(PyUnicode_IS_READY(op)),             \
     ((PyASCIIObject*)op)->state.ascii)

/* Return true if the string is compact or 0 if not.
   No type checks or Ready calls are performed. */
#define PyUnicode_IS_COMPACT(op) \
    (((PyASCIIObject*)(op))->state.compact)

/* Return true if the string is a compact ASCII string (use PyASCIIObject
   structure), or 0 if not.  No type checks or Ready calls are performed. */
#define PyUnicode_IS_COMPACT_ASCII(op)                 \
    (((PyASCIIObject*)op)->state.ascii && PyUnicode_IS_COMPACT(op))

enum PyUnicode_Kind {
/* String contains only wstr byte characters.  This is only possible
   when the string was created with a legacy API and _PyUnicode_Ready()
   has not been called yet.  */
    PyUnicode_WCHAR_KIND = 0,
/* Return values of the PyUnicode_KIND() macro: */
    PyUnicode_1BYTE_KIND = 1,
    PyUnicode_2BYTE_KIND = 2,
    PyUnicode_4BYTE_KIND = 4
};

/* Return pointers to the canonical representation cast to unsigned char,
   Py_UCS2, or Py_UCS4 for direct character access.
   No checks are performed, use PyUnicode_KIND() before to ensure
   these will work correctly. */

#define PyUnicode_1BYTE_DATA(op) ((Py_UCS1*)PyUnicode_DATA(op))
#define PyUnicode_2BYTE_DATA(op) ((Py_UCS2*)PyUnicode_DATA(op))
#define PyUnicode_4BYTE_DATA(op) ((Py_UCS4*)PyUnicode_DATA(op))

/* Return one of the PyUnicode_*_KIND values defined above. */
#define PyUnicode_KIND(op) \
    (assert(PyUnicode_Check(op)), \
     assert(PyUnicode_IS_READY(op)),            \
     ((PyASCIIObject *)(op))->state.kind)

/* Return a void pointer to the raw unicode buffer. */
#define _PyUnicode_COMPACT_DATA(op)                     \
    (PyUnicode_IS_ASCII(op) ?                   \
     ((void*)((PyASCIIObject*)(op) + 1)) :              \
     ((void*)((PyCompactUnicodeObject*)(op) + 1)))

#define _PyUnicode_NONCOMPACT_DATA(op)                  \
    (assert(((PyUnicodeObject*)(op))->data.any),        \
     ((((PyUnicodeObject *)(op))->data.any)))

#define PyUnicode_DATA(op) \
    (assert(PyUnicode_Check(op)), \
     PyUnicode_IS_COMPACT(op) ? _PyUnicode_COMPACT_DATA(op) :   \
     _PyUnicode_NONCOMPACT_DATA(op))

/* In the access macros below, "kind" may be evaluated more than once.
   All other macro parameters are evaluated exactly once, so it is safe
   to put side effects into them (such as increasing the index). */

/* Write into the canonical representation, this macro does not do any sanity
   checks and is intended for usage in loops.  The caller should cache the
   kind and data pointers obtained from other macro calls.
   index is the index in the string (starts at 0) and value is the new
   code point value which should be written to that location. */
#define PyUnicode_WRITE(kind, data, index, value) \
    do { \
        switch ((kind)) { \
        case PyUnicode_1BYTE_KIND: { \
            ((Py_UCS1 *)(data))[(index)] = (Py_UCS1)(value); \
            break; \
        } \
        case PyUnicode_2BYTE_KIND: { \
            ((Py_UCS2 *)(data))[(index)] = (Py_UCS2)(value); \
            break; \
        } \
        default: { \
            assert((kind) == PyUnicode_4BYTE_KIND); \
            ((Py_UCS4 *)(data))[(index)] = (Py_UCS4)(value); \
        } \
        } \
    } while (0)

/* Read a code point from the string's canonical representation.  No checks
   or ready calls are performed. */
#define PyUnicode_READ(kind, data, index) \
    ((Py_UCS4) \
    ((kind) == PyUnicode_1BYTE_KIND ? \
        ((const Py_UCS1 *)(data))[(index)] : \
        ((kind) == PyUnicode_2BYTE_KIND ? \
            ((const Py_UCS2 *)(data))[(index)] : \
            ((const Py_UCS4 *)(data))[(index)] \
        ) \
    ))

/* PyUnicode_READ_CHAR() is less efficient than PyUnicode_READ() because it
   calls PyUnicode_KIND() and might call it twice.  For single reads, use
   PyUnicode_READ_CHAR, for multiple consecutive reads callers should
   cache kind and use PyUnicode_READ instead. */
#define PyUnicode_READ_CHAR(unicode, index) \
    (assert(PyUnicode_Check(unicode)),          \
     assert(PyUnicode_IS_READY(unicode)),       \
     (Py_UCS4)                                  \
        (PyUnicode_KIND((unicode)) == PyUnicode_1BYTE_KIND ? \
            ((const Py_UCS1 *)(PyUnicode_DATA((unicode))))[(index)] : \
            (PyUnicode_KIND((unicode)) == PyUnicode_2BYTE_KIND ? \
                ((const Py_UCS2 *)(PyUnicode_DATA((unicode))))[(index)] : \
                ((const Py_UCS4 *)(PyUnicode_DATA((unicode))))[(index)] \
            ) \
        ))

/* Returns the length of the unicode string. The caller has to make sure that
   the string has it's canonical representation set before calling
   this macro.  Call PyUnicode_(FAST_)Ready to ensure that. */
#define PyUnicode_GET_LENGTH(op)                \
    (assert(PyUnicode_Check(op)),               \
     assert(PyUnicode_IS_READY(op)),            \
     ((PyASCIIObject *)(op))->length)


/* Fast check to determine whether an object is ready. Equivalent to
   PyUnicode_IS_COMPACT(op) || ((PyUnicodeObject*)(op))->data.any) */

#define PyUnicode_IS_READY(op) (((PyASCIIObject*)op)->state.ready)

/* PyUnicode_READY() does less work than _PyUnicode_Ready() in the best
   case.  If the canonical representation is not yet set, it will still call
   _PyUnicode_Ready().
   Returns 0 on success and -1 on errors. */
#define PyUnicode_READY(op)                        \
    (assert(PyUnicode_Check(op)),                       \
     (PyUnicode_IS_READY(op) ?                          \
      0 : _PyUnicode_Ready((PyObject *)(op))))

/* Return a maximum character value which is suitable for creating another
   string based on op.  This is always an approximation but more efficient
   than iterating over the string. */
#define PyUnicode_MAX_CHAR_VALUE(op) \
    (assert(PyUnicode_IS_READY(op)),                                    \
     (PyUnicode_IS_ASCII(op) ?                                          \
      (0x7f) :                                                          \
      (PyUnicode_KIND(op) == PyUnicode_1BYTE_KIND ?                     \
       (0xffU) :                                                        \
       (PyUnicode_KIND(op) == PyUnicode_2BYTE_KIND ?                    \
        (0xffffU) :                                                     \
        (0x10ffffU)))))

#endif

/* --- Constants ---------------------------------------------------------- */

/* This Unicode character will be used as replacement character during
   decoding if the errors argument is set to "replace". Note: the
   Unicode character U+FFFD is the official REPLACEMENT CHARACTER in
   Unicode 3.0. */

#define Py_UNICODE_REPLACEMENT_CHARACTER ((Py_UCS4) 0xFFFD)

/* === Public API ========================================================= */

/* --- Plain Py_UNICODE --------------------------------------------------- */

/* With PEP 393, this is the recommended way to allocate a new unicode object.
   This function will allocate the object and its buffer in a single memory
   block.  Objects created using this function are not resizable. */
#ifndef Py_LIMITED_API
PyAPI_FUNC(PyObject*) PyUnicode_New(
    Py_ssize_t size,            /* Number of code points in the new string */
    Py_UCS4 maxchar             /* maximum code point value in the string */
    );
#endif

/* Initializes the canonical string representation from the deprecated
   wstr/Py_UNICODE representation. This function is used to convert Unicode
   objects which were created using the old API to the new flexible format
   introduced with PEP 393.

   Don't call this function directly, use the public PyUnicode_READY() macro
   instead. */
#ifndef Py_LIMITED_API
PyAPI_FUNC(int) _PyUnicode_Ready(
    PyObject *unicode           /* Unicode object */
    );
#endif

/* Get a copy of a Unicode string. */
#ifndef Py_LIMITED_API
PyAPI_FUNC(PyObject*) _PyUnicode_Copy(
    PyObject *unicode
    );
#endif

/* Copy character from one unicode object into another, this function performs
   character conversion when necessary and falls back to memcpy() if possible.

   Fail if to is too small (smaller than *how_many* or smaller than
   len(from)-from_start), or if kind(from[from_start:from_start+how_many]) >
   kind(to), or if *to* has more than 1 reference.

   Return the number of written character, or return -1 and raise an exception
   on error.

   Pseudo-code:

       how_many = min(how_many, len(from) - from_start)
       to[to_start:to_start+how_many] = from[from_start:from_start+how_many]
       return how_many

   Note: The function doesn't write a terminating null character.
   */
#ifndef Py_LIMITED_API
PyAPI_FUNC(Py_ssize_t) PyUnicode_CopyCharacters(
    PyObject *to,
    Py_ssize_t to_start,
    PyObject *from,
    Py_ssize_t from_start,
    Py_ssize_t how_many
    );

/* Unsafe version of PyUnicode_CopyCharacters(): don't check arguments and so
   may crash if parameters are invalid (e.g. if the output string
   is too short). */
PyAPI_FUNC(void) _PyUnicode_FastCopyCharacters(
    PyObject *to,
    Py_ssize_t to_start,
    PyObject *from,
    Py_ssize_t from_start,
    Py_ssize_t how_many
    );
#endif

#ifndef Py_LIMITED_API
/* Fill a string with a character: write fill_char into
   unicode[start:start+length].

   Fail if fill_char is bigger than the string maximum character, or if the
   string has more than 1 reference.

   Return the number of written character, or return -1 and raise an exception
   on error. */
PyAPI_FUNC(Py_ssize_t) PyUnicode_Fill(
    PyObject *unicode,
    Py_ssize_t start,
    Py_ssize_t length,
    Py_UCS4 fill_char
    );

/* Unsafe version of PyUnicode_Fill(): don't check arguments and so may crash
   if parameters are invalid (e.g. if length is longer than the string). */
PyAPI_FUNC(void) _PyUnicode_FastFill(
    PyObject *unicode,
    Py_ssize_t start,
    Py_ssize_t length,
    Py_UCS4 fill_char
    );
#endif

/* Create a Unicode Object from the Py_UNICODE buffer u of the given
   size.

   u may be NULL which causes the contents to be undefined. It is the
   user's responsibility to fill in the needed data afterwards. Note
   that modifying the Unicode object contents after construction is
   only allowed if u was set to NULL.

   The buffer is copied into the new object. */

#ifndef Py_LIMITED_API
PyAPI_FUNC(PyObject*) PyUnicode_FromUnicode(
    const Py_UNICODE *u,        /* Unicode buffer */
    Py_ssize_t size             /* size of buffer */
    ) /* Py_DEPRECATED(3.3) */;
#endif

/* Similar to PyUnicode_FromUnicode(), but u points to UTF-8 encoded bytes */
PyAPI_FUNC(PyObject*) PyUnicode_FromStringAndSize(
    const char *u,             /* UTF-8 encoded string */
    Py_ssize_t size            /* size of buffer */
    );

/* Similar to PyUnicode_FromUnicode(), but u points to null-terminated
   UTF-8 encoded bytes.  The size is determined with strlen(). */
PyAPI_FUNC(PyObject*) PyUnicode_FromString(
    const char *u              /* UTF-8 encoded string */
    );

#ifndef Py_LIMITED_API
/* Create a new string from a buffer of Py_UCS1, Py_UCS2 or Py_UCS4 characters.
   Scan the string to find the maximum character. */
PyAPI_FUNC(PyObject*) PyUnicode_FromKindAndData(
    int kind,
    const void *buffer,
    Py_ssize_t size);

/* Create a new string from a buffer of ASCII characters.
   WARNING: Don't check if the string contains any non-ASCII character. */
PyAPI_FUNC(PyObject*) _PyUnicode_FromASCII(
    const char *buffer,
    Py_ssize_t size);
#endif

#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
PyAPI_FUNC(PyObject*) PyUnicode_Substring(
    PyObject *str,
    Py_ssize_t start,
    Py_ssize_t end);
#endif

#ifndef Py_LIMITED_API
/* Compute the maximum character of the substring unicode[start:end].
   Return 127 for an empty string. */
PyAPI_FUNC(Py_UCS4) _PyUnicode_FindMaxChar (
    PyObject *unicode,
    Py_ssize_t start,
    Py_ssize_t end);
#endif

#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
/* Copy the string into a UCS4 buffer including the null character if copy_null
   is set. Return NULL and raise an exception on error. Raise a SystemError if
   the buffer is smaller than the string. Return buffer on success.

   buflen is the length of the buffer in (Py_UCS4) characters. */
PyAPI_FUNC(Py_UCS4*) PyUnicode_AsUCS4(
    PyObject *unicode,
    Py_UCS4* buffer,
    Py_ssize_t buflen,
    int copy_null);

/* Copy the string into a UCS4 buffer. A new buffer is allocated using
 * PyMem_Malloc; if this fails, NULL is returned with a memory error
   exception set. */
PyAPI_FUNC(Py_UCS4*) PyUnicode_AsUCS4Copy(PyObject *unicode);
#endif

#ifndef Py_LIMITED_API
/* Return a read-only pointer to the Unicode object's internal
   Py_UNICODE buffer.
   If the wchar_t/Py_UNICODE representation is not yet available, this
   function will calculate it. */

PyAPI_FUNC(Py_UNICODE *) PyUnicode_AsUnicode(
    PyObject *unicode           /* Unicode object */
    ) /* Py_DEPRECATED(3.3) */;

/* Similar to PyUnicode_AsUnicode(), but raises a ValueError if the string
   contains null characters. */
PyAPI_FUNC(const Py_UNICODE *) _PyUnicode_AsUnicode(
    PyObject *unicode           /* Unicode object */
    );

/* Return a read-only pointer to the Unicode object's internal
   Py_UNICODE buffer and save the length at size.
   If the wchar_t/Py_UNICODE representation is not yet available, this
   function will calculate it. */

PyAPI_FUNC(Py_UNICODE *) PyUnicode_AsUnicodeAndSize(
    PyObject *unicode,          /* Unicode object */
    Py_ssize_t *size            /* location where to save the length */
    )  /* Py_DEPRECATED(3.3) */;
#endif

#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
/* Get the length of the Unicode object. */

PyAPI_FUNC(Py_ssize_t) PyUnicode_GetLength(
    PyObject *unicode
);
#endif

/* Get the number of Py_UNICODE units in the
   string representation. */

PyAPI_FUNC(Py_ssize_t) PyUnicode_GetSize(
    PyObject *unicode           /* Unicode object */
    ) Py_DEPRECATED(3.3);

#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
/* Read a character from the string. */

PyAPI_FUNC(Py_UCS4) PyUnicode_ReadChar(
    PyObject *unicode,
    Py_ssize_t index
    );

/* Write a character to the string. The string must have been created through
   PyUnicode_New, must not be shared, and must not have been hashed yet.

   Return 0 on success, -1 on error. */

PyAPI_FUNC(int) PyUnicode_WriteChar(
    PyObject *unicode,
    Py_ssize_t index,
    Py_UCS4 character
    );
#endif

#ifndef Py_LIMITED_API
/* Get the maximum ordinal for a Unicode character. */
PyAPI_FUNC(Py_UNICODE) PyUnicode_GetMax(void) Py_DEPRECATED(3.3);
#endif

/* Resize a Unicode object. The length is the number of characters, except
   if the kind of the string is PyUnicode_WCHAR_KIND: in this case, the length
   is the number of Py_UNICODE characters.

   *unicode is modified to point to the new (resized) object and 0
   returned on success.

   Try to resize the string in place (which is usually faster than allocating
   a new string and copy characters), or create a new string.

   Error handling is implemented as follows: an exception is set, -1
   is returned and *unicode left untouched.

   WARNING: The function doesn't check string content, the result may not be a
            string in canonical representation. */

PyAPI_FUNC(int) PyUnicode_Resize(
    PyObject **unicode,         /* Pointer to the Unicode object */
    Py_ssize_t length           /* New length */
    );

/* Decode obj to a Unicode object.

   bytes, bytearray and other bytes-like objects are decoded according to the
   given encoding and error handler. The encoding and error handler can be
   NULL to have the interface use UTF-8 and "strict".

   All other objects (including Unicode objects) raise an exception.

   The API returns NULL in case of an error. The caller is responsible
   for decref'ing the returned objects.

*/

PyAPI_FUNC(PyObject*) PyUnicode_FromEncodedObject(
    PyObject *obj,              /* Object */
    const char *encoding,       /* encoding */
    const char *errors          /* error handling */
    );

/* Copy an instance of a Unicode subtype to a new true Unicode object if
   necessary. If obj is already a true Unicode object (not a subtype), return
   the reference with *incremented* refcount.

   The API returns NULL in case of an error. The caller is responsible
   for decref'ing the returned objects.

*/

PyAPI_FUNC(PyObject*) PyUnicode_FromObject(
    PyObject *obj      /* Object */
    );

PyAPI_FUNC(PyObject *) PyUnicode_FromFormatV(
    const char *format,   /* ASCII-encoded string  */
    va_list vargs
    );
PyAPI_FUNC(PyObject *) PyUnicode_FromFormat(
    const char *format,   /* ASCII-encoded string  */
    ...
    );

#ifndef Py_LIMITED_API
typedef struct {
    PyObject *buffer;
    void *data;
    enum PyUnicode_Kind kind;
    Py_UCS4 maxchar;
    Py_ssize_t size;
    Py_ssize_t pos;

    /* minimum number of allocated characters (default: 0) */
    Py_ssize_t min_length;

    /* minimum character (default: 127, ASCII) */
    Py_UCS4 min_char;

    /* If non-zero, overallocate the buffer (default: 0). */
    unsigned char overallocate;

    /* If readonly is 1, buffer is a shared string (cannot be modified)
       and size is set to 0. */
    unsigned char readonly;
} _PyUnicodeWriter ;

/* Initialize a Unicode writer.
 *
 * By default, the minimum buffer size is 0 character and overallocation is
 * disabled. Set min_length, min_char and overallocate attributes to control
 * the allocation of the buffer. */
PyAPI_FUNC(void)
_PyUnicodeWriter_Init(_PyUnicodeWriter *writer);

/* Prepare the buffer to write 'length' characters
   with the specified maximum character.

   Return 0 on success, raise an exception and return -1 on error. */
#define _PyUnicodeWriter_Prepare(WRITER, LENGTH, MAXCHAR)             \
    (((MAXCHAR) <= (WRITER)->maxchar                                  \
      && (LENGTH) <= (WRITER)->size - (WRITER)->pos)                  \
     ? 0                                                              \
     : (((LENGTH) == 0)                                               \
        ? 0                                                           \
        : _PyUnicodeWriter_PrepareInternal((WRITER), (LENGTH), (MAXCHAR))))

/* Don't call this function directly, use the _PyUnicodeWriter_Prepare() macro
   instead. */
PyAPI_FUNC(int)
_PyUnicodeWriter_PrepareInternal(_PyUnicodeWriter *writer,
                                 Py_ssize_t length, Py_UCS4 maxchar);

/* Prepare the buffer to have at least the kind KIND.
   For example, kind=PyUnicode_2BYTE_KIND ensures that the writer will
   support characters in range U+000-U+FFFF.

   Return 0 on success, raise an exception and return -1 on error. */
#define _PyUnicodeWriter_PrepareKind(WRITER, KIND)                    \
    (assert((KIND) != PyUnicode_WCHAR_KIND),                          \
     (KIND) <= (WRITER)->kind                                         \
     ? 0                                                              \
     : _PyUnicodeWriter_PrepareKindInternal((WRITER), (KIND)))

/* Don't call this function directly, use the _PyUnicodeWriter_PrepareKind()
   macro instead. */
PyAPI_FUNC(int)
_PyUnicodeWriter_PrepareKindInternal(_PyUnicodeWriter *writer,
                                     enum PyUnicode_Kind kind);

/* Append a Unicode character.
   Return 0 on success, raise an exception and return -1 on error. */
PyAPI_FUNC(int)
_PyUnicodeWriter_WriteChar(_PyUnicodeWriter *writer,
    Py_UCS4 ch
    );

/* Append a Unicode string.
   Return 0 on success, raise an exception and return -1 on error. */
PyAPI_FUNC(int)
_PyUnicodeWriter_WriteStr(_PyUnicodeWriter *writer,
    PyObject *str               /* Unicode string */
    );

/* Append a substring of a Unicode string.
   Return 0 on success, raise an exception and return -1 on error. */
PyAPI_FUNC(int)
_PyUnicodeWriter_WriteSubstring(_PyUnicodeWriter *writer,
    PyObject *str,              /* Unicode string */
    Py_ssize_t start,
    Py_ssize_t end
    );

/* Append an ASCII-encoded byte string.
   Return 0 on success, raise an exception and return -1 on error. */
PyAPI_FUNC(int)
_PyUnicodeWriter_WriteASCIIString(_PyUnicodeWriter *writer,
    const char *str,           /* ASCII-encoded byte string */
    Py_ssize_t len             /* number of bytes, or -1 if unknown */
    );

/* Append a latin1-encoded byte string.
   Return 0 on success, raise an exception and return -1 on error. */
PyAPI_FUNC(int)
_PyUnicodeWriter_WriteLatin1String(_PyUnicodeWriter *writer,
    const char *str,           /* latin1-encoded byte string */
    Py_ssize_t len             /* length in bytes */
    );

/* Get the value of the writer as a Unicode string. Clear the
   buffer of the writer. Raise an exception and return NULL
   on error. */
PyAPI_FUNC(PyObject *)
_PyUnicodeWriter_Finish(_PyUnicodeWriter *writer);

/* Deallocate memory of a writer (clear its internal buffer). */
PyAPI_FUNC(void)
_PyUnicodeWriter_Dealloc(_PyUnicodeWriter *writer);
#endif

#ifndef Py_LIMITED_API
/* Format the object based on the format_spec, as defined in PEP 3101
   (Advanced String Formatting). */
PyAPI_FUNC(int) _PyUnicode_FormatAdvancedWriter(
    _PyUnicodeWriter *writer,
    PyObject *obj,
    PyObject *format_spec,
    Py_ssize_t start,
    Py_ssize_t end);
#endif

PyAPI_FUNC(void) PyUnicode_InternInPlace(PyObject **);
PyAPI_FUNC(void) PyUnicode_InternImmortal(PyObject **);
PyAPI_FUNC(PyObject *) PyUnicode_InternFromString(
    const char *u              /* UTF-8 encoded string */
    );
#ifndef Py_LIMITED_API
PyAPI_FUNC(void) _Py_ReleaseInternedUnicodeStrings(void);
#endif

/* Use only if you know it's a string */
#define PyUnicode_CHECK_INTERNED(op) \
    (((PyASCIIObject *)(op))->state.interned)

/* --- wchar_t support for platforms which support it --------------------- */

#ifdef HAVE_WCHAR_H

/* Create a Unicode Object from the wchar_t buffer w of the given
   size.

   The buffer is copied into the new object. */

PyAPI_FUNC(PyObject*) PyUnicode_FromWideChar(
    const wchar_t *w,           /* wchar_t buffer */
    Py_ssize_t size             /* size of buffer */
    );

/* Copies the Unicode Object contents into the wchar_t buffer w.  At
   most size wchar_t characters are copied.

   Note that the resulting wchar_t string may or may not be
   0-terminated.  It is the responsibility of the caller to make sure
   that the wchar_t string is 0-terminated in case this is required by
   the application.

   Returns the number of wchar_t characters copied (excluding a
   possibly trailing 0-termination character) or -1 in case of an
   error. */

PyAPI_FUNC(Py_ssize_t) PyUnicode_AsWideChar(
    PyObject *unicode,          /* Unicode object */
    wchar_t *w,                 /* wchar_t buffer */
    Py_ssize_t size             /* size of buffer */
    );

/* Convert the Unicode object to a wide character string. The output string
   always ends with a nul character. If size is not NULL, write the number of
   wide characters (excluding the null character) into *size.

   Returns a buffer allocated by PyMem_Malloc() (use PyMem_Free() to free it)
   on success. On error, returns NULL, *size is undefined and raises a
   MemoryError. */

PyAPI_FUNC(wchar_t*) PyUnicode_AsWideCharString(
    PyObject *unicode,          /* Unicode object */
    Py_ssize_t *size            /* number of characters of the result */
    );

#ifndef Py_LIMITED_API
PyAPI_FUNC(void*) _PyUnicode_AsKind(PyObject *s, unsigned int kind);
#endif

#endif

/* --- Unicode ordinals --------------------------------------------------- */

/* Create a Unicode Object from the given Unicode code point ordinal.

   The ordinal must be in range(0x110000). A ValueError is
   raised in case it is not.

*/

PyAPI_FUNC(PyObject*) PyUnicode_FromOrdinal(int ordinal);

/* --- Free-list management ----------------------------------------------- */

/* Clear the free list used by the Unicode implementation.

   This can be used to release memory used for objects on the free
   list back to the Python memory allocator.

*/

PyAPI_FUNC(int) PyUnicode_ClearFreeList(void);

/* === Builtin Codecs =====================================================

   Many of these APIs take two arguments encoding and errors. These
   parameters encoding and errors have the same semantics as the ones
   of the builtin str() API.

   Setting encoding to NULL causes the default encoding (UTF-8) to be used.

   Error handling is set by errors which may also be set to NULL
   meaning to use the default handling defined for the codec. Default
   error handling for all builtin codecs is "strict" (ValueErrors are
   raised).

   The codecs all use a similar interface. Only deviation from the
   generic ones are documented.

*/

/* --- Manage the default encoding ---------------------------------------- */

/* Returns a pointer to the default encoding (UTF-8) of the
   Unicode object unicode and the size of the encoded representation
   in bytes stored in *size.

   In case of an error, no *size is set.

   This function caches the UTF-8 encoded string in the unicodeobject
   and subsequent calls will return the same string.  The memory is released
   when the unicodeobject is deallocated.

   _PyUnicode_AsStringAndSize is a #define for PyUnicode_AsUTF8AndSize to
   support the previous internal function with the same behaviour.

   *** This API is for interpreter INTERNAL USE ONLY and will likely
   *** be removed or changed in the future.

   *** If you need to access the Unicode object as UTF-8 bytes string,
   *** please use PyUnicode_AsUTF8String() instead.
*/

#ifndef Py_LIMITED_API
PyAPI_FUNC(const char *) PyUnicode_AsUTF8AndSize(
    PyObject *unicode,
    Py_ssize_t *size);
#define _PyUnicode_AsStringAndSize PyUnicode_AsUTF8AndSize
#endif

/* Returns a pointer to the default encoding (UTF-8) of the
   Unicode object unicode.

   Like PyUnicode_AsUTF8AndSize(), this also caches the UTF-8 representation
   in the unicodeobject.

   _PyUnicode_AsString is a #define for PyUnicode_AsUTF8 to
   support the previous internal function with the same behaviour.

   Use of this API is DEPRECATED since no size information can be
   extracted from the returned data.

   *** This API is for interpreter INTERNAL USE ONLY and will likely
   *** be removed or changed for Python 3.1.

   *** If you need to access the Unicode object as UTF-8 bytes string,
   *** please use PyUnicode_AsUTF8String() instead.

*/

#ifndef Py_LIMITED_API
PyAPI_FUNC(const char *) PyUnicode_AsUTF8(PyObject *unicode);
#define _PyUnicode_AsString PyUnicode_AsUTF8
#endif

/* Returns "utf-8".  */

PyAPI_FUNC(const char*) PyUnicode_GetDefaultEncoding(void);

/* --- Generic Codecs ----------------------------------------------------- */

/* Create a Unicode object by decoding the encoded string s of the
   given size. */

PyAPI_FUNC(PyObject*) PyUnicode_Decode(
    const char *s,              /* encoded string */
    Py_ssize_t size,            /* size of buffer */
    const char *encoding,       /* encoding */
    const char *errors          /* error handling */
    );

/* Decode a Unicode object unicode and return the result as Python
   object.

   This API is DEPRECATED. The only supported standard encoding is rot13.
   Use PyCodec_Decode() to decode with rot13 and non-standard codecs
   that decode from str. */

PyAPI_FUNC(PyObject*) PyUnicode_AsDecodedObject(
    PyObject *unicode,          /* Unicode object */
    const char *encoding,       /* encoding */
    const char *errors          /* error handling */
    ) Py_DEPRECATED(3.6);

/* Decode a Unicode object unicode and return the result as Unicode
   object.

   This API is DEPRECATED. The only supported standard encoding is rot13.
   Use PyCodec_Decode() to decode with rot13 and non-standard codecs
   that decode from str to str. */

PyAPI_FUNC(PyObject*) PyUnicode_AsDecodedUnicode(
    PyObject *unicode,          /* Unicode object */
    const char *encoding,       /* encoding */
    const char *errors          /* error handling */
    ) Py_DEPRECATED(3.6);

/* Encodes a Py_UNICODE buffer of the given size and returns a
   Python string object. */

#ifndef Py_LIMITED_API
PyAPI_FUNC(PyObject*) PyUnicode_Encode(
    const Py_UNICODE *s,        /* Unicode char buffer */
    Py_ssize_t size,            /* number of Py_UNICODE chars to encode */
    const char *encoding,       /* encoding */
    const char *errors          /* error handling */
    ) Py_DEPRECATED(3.3);
#endif

/* Encodes a Unicode object and returns the result as Python
   object.

   This API is DEPRECATED.  It is superseded by PyUnicode_AsEncodedString()
   since all standard encodings (except rot13) encode str to bytes.
   Use PyCodec_Encode() for encoding with rot13 and non-standard codecs
   that encode form str to non-bytes. */

PyAPI_FUNC(PyObject*) PyUnicode_AsEncodedObject(
    PyObject *unicode,          /* Unicode object */
    const char *encoding,       /* encoding */
    const char *errors          /* error handling */
    ) Py_DEPRECATED(3.6);

/* Encodes a Unicode object and returns the result as Python string
   object. */

PyAPI_FUNC(PyObject*) PyUnicode_AsEncodedString(
    PyObject *unicode,          /* Unicode object */
    const char *encoding,       /* encoding */
    const char *errors          /* error handling */
    );

/* Encodes a Unicode object and returns the result as Unicode
   object.

   This API is DEPRECATED.  The only supported standard encodings is rot13.
   Use PyCodec_Encode() to encode with rot13 and non-standard codecs
   that encode from str to str. */

PyAPI_FUNC(PyObject*) PyUnicode_AsEncodedUnicode(
    PyObject *unicode,          /* Unicode object */
    const char *encoding,       /* encoding */
    const char *errors          /* error handling */
    ) Py_DEPRECATED(3.6);

/* Build an encoding map. */

PyAPI_FUNC(PyObject*) PyUnicode_BuildEncodingMap(
    PyObject* string            /* 256 character map */
   );

/* --- UTF-7 Codecs ------------------------------------------------------- */

PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF7(
    const char *string,         /* UTF-7 encoded string */
    Py_ssize_t length,          /* size of string */
    const char *errors          /* error handling */
    );

PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF7Stateful(
    const char *string,         /* UTF-7 encoded string */
    Py_ssize_t length,          /* size of string */
    const char *errors,         /* error handling */
    Py_ssize_t *consumed        /* bytes consumed */
    );

#ifndef Py_LIMITED_API
PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF7(
    const Py_UNICODE *data,     /* Unicode char buffer */
    Py_ssize_t length,          /* number of Py_UNICODE chars to encode */
    int base64SetO,             /* Encode RFC2152 Set O characters in base64 */
    int base64WhiteSpace,       /* Encode whitespace (sp, ht, nl, cr) in base64 */
    const char *errors          /* error handling */
    ) Py_DEPRECATED(3.3);
PyAPI_FUNC(PyObject*) _PyUnicode_EncodeUTF7(
    PyObject *unicode,          /* Unicode object */
    int base64SetO,             /* Encode RFC2152 Set O characters in base64 */
    int base64WhiteSpace,       /* Encode whitespace (sp, ht, nl, cr) in base64 */
    const char *errors          /* error handling */
    );
#endif

/* --- UTF-8 Codecs ------------------------------------------------------- */

PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF8(
    const char *string,         /* UTF-8 encoded string */
    Py_ssize_t length,          /* size of string */
    const char *errors          /* error handling */
    );

PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF8Stateful(
    const char *string,         /* UTF-8 encoded string */
    Py_ssize_t length,          /* size of string */
    const char *errors,         /* error handling */
    Py_ssize_t *consumed        /* bytes consumed */
    );

PyAPI_FUNC(PyObject*) PyUnicode_AsUTF8String(
    PyObject *unicode           /* Unicode object */
    );

#ifndef Py_LIMITED_API
PyAPI_FUNC(PyObject*) _PyUnicode_AsUTF8String(
    PyObject *unicode,
    const char *errors);

PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF8(
    const Py_UNICODE *data,     /* Unicode char buffer */
    Py_ssize_t length,          /* number of Py_UNICODE chars to encode */
    const char *errors          /* error handling */
    ) Py_DEPRECATED(3.3);
#endif

/* --- UTF-32 Codecs ------------------------------------------------------ */

/* Decodes length bytes from a UTF-32 encoded buffer string and returns
   the corresponding Unicode object.

   errors (if non-NULL) defines the error handling. It defaults
   to "strict".

   If byteorder is non-NULL, the decoder starts decoding using the
   given byte order:

    *byteorder == -1: little endian
    *byteorder == 0:  native order
    *byteorder == 1:  big endian

   In native mode, the first four bytes of the stream are checked for a
   BOM mark. If found, the BOM mark is analysed, the byte order
   adjusted and the BOM skipped.  In the other modes, no BOM mark
   interpretation is done. After completion, *byteorder is set to the
   current byte order at the end of input data.

   If byteorder is NULL, the codec starts in native order mode.

*/

PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF32(
    const char *string,         /* UTF-32 encoded string */
    Py_ssize_t length,          /* size of string */
    const char *errors,         /* error handling */
    int *byteorder              /* pointer to byteorder to use
                                   0=native;-1=LE,1=BE; updated on
                                   exit */
    );

PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF32Stateful(
    const char *string,         /* UTF-32 encoded string */
    Py_ssize_t length,          /* size of string */
    const char *errors,         /* error handling */
    int *byteorder,             /* pointer to byteorder to use
                                   0=native;-1=LE,1=BE; updated on
                                   exit */
    Py_ssize_t *consumed        /* bytes consumed */
    );

/* Returns a Python string using the UTF-32 encoding in native byte
   order. The string always starts with a BOM mark.  */

PyAPI_FUNC(PyObject*) PyUnicode_AsUTF32String(
    PyObject *unicode           /* Unicode object */
    );

/* Returns a Python string object holding the UTF-32 encoded value of
   the Unicode data.

   If byteorder is not 0, output is written according to the following
   byte order:

   byteorder == -1: little endian
   byteorder == 0:  native byte order (writes a BOM mark)
   byteorder == 1:  big endian

   If byteorder is 0, the output string will always start with the
   Unicode BOM mark (U+FEFF). In the other two modes, no BOM mark is
   prepended.

*/

#ifndef Py_LIMITED_API
PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF32(
    const Py_UNICODE *data,     /* Unicode char buffer */
    Py_ssize_t length,          /* number of Py_UNICODE chars to encode */
    const char *errors,         /* error handling */
    int byteorder               /* byteorder to use 0=BOM+native;-1=LE,1=BE */
    ) Py_DEPRECATED(3.3);
PyAPI_FUNC(PyObject*) _PyUnicode_EncodeUTF32(
    PyObject *object,           /* Unicode object */
    const char *errors,         /* error handling */
    int byteorder               /* byteorder to use 0=BOM+native;-1=LE,1=BE */
    );
#endif

/* --- UTF-16 Codecs ------------------------------------------------------ */

/* Decodes length bytes from a UTF-16 encoded buffer string and returns
   the corresponding Unicode object.

   errors (if non-NULL) defines the error handling. It defaults
   to "strict".

   If byteorder is non-NULL, the decoder starts decoding using the
   given byte order:

    *byteorder == -1: little endian
    *byteorder == 0:  native order
    *byteorder == 1:  big endian

   In native mode, the first two bytes of the stream are checked for a
   BOM mark. If found, the BOM mark is analysed, the byte order
   adjusted and the BOM skipped.  In the other modes, no BOM mark
   interpretation is done. After completion, *byteorder is set to the
   current byte order at the end of input data.

   If byteorder is NULL, the codec starts in native order mode.

*/

PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF16(
    const char *string,         /* UTF-16 encoded string */
    Py_ssize_t length,          /* size of string */
    const char *errors,         /* error handling */
    int *byteorder              /* pointer to byteorder to use
                                   0=native;-1=LE,1=BE; updated on
                                   exit */
    );

PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF16Stateful(
    const char *string,         /* UTF-16 encoded string */
    Py_ssize_t length,          /* size of string */
    const char *errors,         /* error handling */
    int *byteorder,             /* pointer to byteorder to use
                                   0=native;-1=LE,1=BE; updated on
                                   exit */
    Py_ssize_t *consumed        /* bytes consumed */
    );

/* Returns a Python string using the UTF-16 encoding in native byte
   order. The string always starts with a BOM mark.  */

PyAPI_FUNC(PyObject*) PyUnicode_AsUTF16String(
    PyObject *unicode           /* Unicode object */
    );

/* Returns a Python string object holding the UTF-16 encoded value of
   the Unicode data.

   If byteorder is not 0, output is written according to the following
   byte order:

   byteorder == -1: little endian
   byteorder == 0:  native byte order (writes a BOM mark)
   byteorder == 1:  big endian

   If byteorder is 0, the output string will always start with the
   Unicode BOM mark (U+FEFF). In the other two modes, no BOM mark is
   prepended.

   Note that Py_UNICODE data is being interpreted as UTF-16 reduced to
   UCS-2. This trick makes it possible to add full UTF-16 capabilities
   at a later point without compromising the APIs.

*/

#ifndef Py_LIMITED_API
PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF16(
    const Py_UNICODE *data,     /* Unicode char buffer */
    Py_ssize_t length,          /* number of Py_UNICODE chars to encode */
    const char *errors,         /* error handling */
    int byteorder               /* byteorder to use 0=BOM+native;-1=LE,1=BE */
    ) Py_DEPRECATED(3.3);
PyAPI_FUNC(PyObject*) _PyUnicode_EncodeUTF16(
    PyObject* unicode,          /* Unicode object */
    const char *errors,         /* error handling */
    int byteorder               /* byteorder to use 0=BOM+native;-1=LE,1=BE */
    );
#endif

/* --- Unicode-Escape Codecs ---------------------------------------------- */

PyAPI_FUNC(PyObject*) PyUnicode_DecodeUnicodeEscape(
    const char *string,         /* Unicode-Escape encoded string */
    Py_ssize_t length,          /* size of string */
    const char *errors          /* error handling */
    );

#ifndef Py_LIMITED_API
/* Helper for PyUnicode_DecodeUnicodeEscape that detects invalid escape
   chars. */
PyAPI_FUNC(PyObject*) _PyUnicode_DecodeUnicodeEscape(
        const char *string,     /* Unicode-Escape encoded string */
        Py_ssize_t length,      /* size of string */
        const char *errors,     /* error handling */
        const char **first_invalid_escape  /* on return, points to first
                                              invalid escaped char in
                                              string. */
);
#endif

PyAPI_FUNC(PyObject*) PyUnicode_AsUnicodeEscapeString(
    PyObject *unicode           /* Unicode object */
    );

#ifndef Py_LIMITED_API
PyAPI_FUNC(PyObject*) PyUnicode_EncodeUnicodeEscape(
    const Py_UNICODE *data,     /* Unicode char buffer */
    Py_ssize_t length           /* Number of Py_UNICODE chars to encode */
    ) Py_DEPRECATED(3.3);
#endif

/* --- Raw-Unicode-Escape Codecs ------------------------------------------ */

PyAPI_FUNC(PyObject*) PyUnicode_DecodeRawUnicodeEscape(
    const char *string,         /* Raw-Unicode-Escape encoded string */
    Py_ssize_t length,          /* size of string */
    const char *errors          /* error handling */
    );

PyAPI_FUNC(PyObject*) PyUnicode_AsRawUnicodeEscapeString(
    PyObject *unicode           /* Unicode object */
    );

#ifndef Py_LIMITED_API
PyAPI_FUNC(PyObject*) PyUnicode_EncodeRawUnicodeEscape(
    const Py_UNICODE *data,     /* Unicode char buffer */
    Py_ssize_t length           /* Number of Py_UNICODE chars to encode */
    ) Py_DEPRECATED(3.3);
#endif

/* --- Unicode Internal Codec ---------------------------------------------

    Only for internal use in _codecsmodule.c */

#ifndef Py_LIMITED_API
PyObject *_PyUnicode_DecodeUnicodeInternal(
    const char *string,
    Py_ssize_t length,
    const char *errors
    );
#endif

/* --- Latin-1 Codecs -----------------------------------------------------

   Note: Latin-1 corresponds to the first 256 Unicode ordinals.

*/

PyAPI_FUNC(PyObject*) PyUnicode_DecodeLatin1(
    const char *string,         /* Latin-1 encoded string */
    Py_ssize_t length,          /* size of string */
    const char *errors          /* error handling */
    );

PyAPI_FUNC(PyObject*) PyUnicode_AsLatin1String(
    PyObject *unicode           /* Unicode object */
    );

#ifndef Py_LIMITED_API
PyAPI_FUNC(PyObject*) _PyUnicode_AsLatin1String(
    PyObject* unicode,
    const char* errors);

PyAPI_FUNC(PyObject*) PyUnicode_EncodeLatin1(
    const Py_UNICODE *data,     /* Unicode char buffer */
    Py_ssize_t length,          /* Number of Py_UNICODE chars to encode */
    const char *errors          /* error handling */
    ) Py_DEPRECATED(3.3);
#endif

/* --- ASCII Codecs -------------------------------------------------------

   Only 7-bit ASCII data is excepted. All other codes generate errors.

*/

PyAPI_FUNC(PyObject*) PyUnicode_DecodeASCII(
    const char *string,         /* ASCII encoded string */
    Py_ssize_t length,          /* size of string */
    const char *errors          /* error handling */
    );

PyAPI_FUNC(PyObject*) PyUnicode_AsASCIIString(
    PyObject *unicode           /* Unicode object */
    );

#ifndef Py_LIMITED_API
PyAPI_FUNC(PyObject*) _PyUnicode_AsASCIIString(
    PyObject* unicode,
    const char* errors);

PyAPI_FUNC(PyObject*) PyUnicode_EncodeASCII(
    const Py_UNICODE *data,     /* Unicode char buffer */
    Py_ssize_t length,          /* Number of Py_UNICODE chars to encode */
    const char *errors          /* error handling */
    ) Py_DEPRECATED(3.3);
#endif

/* --- Character Map Codecs -----------------------------------------------

   This codec uses mappings to encode and decode characters.

   Decoding mappings must map byte ordinals (integers in the range from 0 to
   255) to Unicode strings, integers (which are then interpreted as Unicode
   ordinals) or None.  Unmapped data bytes (ones which cause a LookupError)
   as well as mapped to None, 0xFFFE or '\ufffe' are treated as "undefined
   mapping" and cause an error.

   Encoding mappings must map Unicode ordinal integers to bytes objects,
   integers in the range from 0 to 255 or None.  Unmapped character
   ordinals (ones which cause a LookupError) as well as mapped to
   None are treated as "undefined mapping" and cause an error.

*/

PyAPI_FUNC(PyObject*) PyUnicode_DecodeCharmap(
    const char *string,         /* Encoded string */
    Py_ssize_t length,          /* size of string */
    PyObject *mapping,          /* decoding mapping */
    const char *errors          /* error handling */
    );

PyAPI_FUNC(PyObject*) PyUnicode_AsCharmapString(
    PyObject *unicode,          /* Unicode object */
    PyObject *mapping           /* encoding mapping */
    );

#ifndef Py_LIMITED_API
PyAPI_FUNC(PyObject*) PyUnicode_EncodeCharmap(
    const Py_UNICODE *data,     /* Unicode char buffer */
    Py_ssize_t length,          /* Number of Py_UNICODE chars to encode */
    PyObject *mapping,          /* encoding mapping */
    const char *errors          /* error handling */
    ) Py_DEPRECATED(3.3);
PyAPI_FUNC(PyObject*) _PyUnicode_EncodeCharmap(
    PyObject *unicode,          /* Unicode object */
    PyObject *mapping,          /* encoding mapping */
    const char *errors          /* error handling */
    );
#endif

/* Translate a Py_UNICODE buffer of the given length by applying a
   character mapping table to it and return the resulting Unicode
   object.

   The mapping table must map Unicode ordinal integers to Unicode strings,
   Unicode ordinal integers or None (causing deletion of the character).

   Mapping tables may be dictionaries or sequences. Unmapped character
   ordinals (ones which cause a LookupError) are left untouched and
   are copied as-is.

*/

#ifndef Py_LIMITED_API
PyAPI_FUNC(PyObject *) PyUnicode_TranslateCharmap(
    const Py_UNICODE *data,     /* Unicode char buffer */
    Py_ssize_t length,          /* Number of Py_UNICODE chars to encode */
    PyObject *table,            /* Translate table */
    const char *errors          /* error handling */
    ) Py_DEPRECATED(3.3);
#endif

#ifdef MS_WINDOWS

/* --- MBCS codecs for Windows -------------------------------------------- */

PyAPI_FUNC(PyObject*) PyUnicode_DecodeMBCS(
    const char *string,         /* MBCS encoded string */
    Py_ssize_t length,          /* size of string */
    const char *errors          /* error handling */
    );

PyAPI_FUNC(PyObject*) PyUnicode_DecodeMBCSStateful(
    const char *string,         /* MBCS encoded string */
    Py_ssize_t length,          /* size of string */
    const char *errors,         /* error handling */
    Py_ssize_t *consumed        /* bytes consumed */
    );

#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
PyAPI_FUNC(PyObject*) PyUnicode_DecodeCodePageStateful(
    int code_page,              /* code page number */
    const char *string,         /* encoded string */
    Py_ssize_t length,          /* size of string */
    const char *errors,         /* error handling */
    Py_ssize_t *consumed        /* bytes consumed */
    );
#endif

PyAPI_FUNC(PyObject*) PyUnicode_AsMBCSString(
    PyObject *unicode           /* Unicode object */
    );

#ifndef Py_LIMITED_API
PyAPI_FUNC(PyObject*) PyUnicode_EncodeMBCS(
    const Py_UNICODE *data,     /* Unicode char buffer */
    Py_ssize_t length,          /* number of Py_UNICODE chars to encode */
    const char *errors          /* error handling */
    ) Py_DEPRECATED(3.3);
#endif

#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
PyAPI_FUNC(PyObject*) PyUnicode_EncodeCodePage(
    int code_page,              /* code page number */
    PyObject *unicode,          /* Unicode object */
    const char *errors          /* error handling */
    );
#endif

#endif /* MS_WINDOWS */

#ifndef Py_LIMITED_API
/* --- Decimal Encoder ---------------------------------------------------- */

/* Takes a Unicode string holding a decimal value and writes it into
   an output buffer using standard ASCII digit codes.

   The output buffer has to provide at least length+1 bytes of storage
   area. The output string is 0-terminated.

   The encoder converts whitespace to ' ', decimal characters to their
   corresponding ASCII digit and all other Latin-1 characters except
   \0 as-is. Characters outside this range (Unicode ordinals 1-256)
   are treated as errors. This includes embedded NULL bytes.

   Error handling is defined by the errors argument:

      NULL or "strict": raise a ValueError
      "ignore": ignore the wrong characters (these are not copied to the
                output buffer)
      "replace": replaces illegal characters with '?'

   Returns 0 on success, -1 on failure.

*/

PyAPI_FUNC(int) PyUnicode_EncodeDecimal(
    Py_UNICODE *s,              /* Unicode buffer */
    Py_ssize_t length,          /* Number of Py_UNICODE chars to encode */
    char *output,               /* Output buffer; must have size >= length */
    const char *errors          /* error handling */
    ) /* Py_DEPRECATED(3.3) */;

/* Transforms code points that have decimal digit property to the
   corresponding ASCII digit code points.

   Returns a new Unicode string on success, NULL on failure.
*/

PyAPI_FUNC(PyObject*) PyUnicode_TransformDecimalToASCII(
    Py_UNICODE *s,              /* Unicode buffer */
    Py_ssize_t length           /* Number of Py_UNICODE chars to transform */
    ) /* Py_DEPRECATED(3.3) */;

/* Coverts a Unicode object holding a decimal value to an ASCII string
   for using in int, float and complex parsers.
   Transforms code points that have decimal digit property to the
   corresponding ASCII digit code points.  Transforms spaces to ASCII.
   Transforms code points starting from the first non-ASCII code point that
   is neither a decimal digit nor a space to the end into '?'. */

PyAPI_FUNC(PyObject*) _PyUnicode_TransformDecimalAndSpaceToASCII(
    PyObject *unicode           /* Unicode object */
    );
#endif

/* --- Locale encoding --------------------------------------------------- */

#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
/* Decode a string from the current locale encoding. The decoder is strict if
   *surrogateescape* is equal to zero, otherwise it uses the 'surrogateescape'
   error handler (PEP 383) to escape undecodable bytes. If a byte sequence can
   be decoded as a surrogate character and *surrogateescape* is not equal to
   zero, the byte sequence is escaped using the 'surrogateescape' error handler
   instead of being decoded. *str* must end with a null character but cannot
   contain embedded null characters. */

PyAPI_FUNC(PyObject*) PyUnicode_DecodeLocaleAndSize(
    const char *str,
    Py_ssize_t len,
    const char *errors);

/* Similar to PyUnicode_DecodeLocaleAndSize(), but compute the string
   length using strlen(). */

PyAPI_FUNC(PyObject*) PyUnicode_DecodeLocale(
    const char *str,
    const char *errors);

/* Encode a Unicode object to the current locale encoding. The encoder is
   strict is *surrogateescape* is equal to zero, otherwise the
   "surrogateescape" error handler is used. Return a bytes object. The string
   cannot contain embedded null characters. */

PyAPI_FUNC(PyObject*) PyUnicode_EncodeLocale(
    PyObject *unicode,
    const char *errors
    );
#endif

/* --- File system encoding ---------------------------------------------- */

/* ParseTuple converter: encode str objects to bytes using
   PyUnicode_EncodeFSDefault(); bytes objects are output as-is. */

PyAPI_FUNC(int) PyUnicode_FSConverter(PyObject*, void*);

/* ParseTuple converter: decode bytes objects to unicode using
   PyUnicode_DecodeFSDefaultAndSize(); str objects are output as-is. */

PyAPI_FUNC(int) PyUnicode_FSDecoder(PyObject*, void*);

/* Decode a null-terminated string using Py_FileSystemDefaultEncoding
   and the "surrogateescape" error handler.

   If Py_FileSystemDefaultEncoding is not set, fall back to the locale
   encoding.

   Use PyUnicode_DecodeFSDefaultAndSize() if the string length is known.
*/

PyAPI_FUNC(PyObject*) PyUnicode_DecodeFSDefault(
    const char *s               /* encoded string */
    );

/* Decode a string using Py_FileSystemDefaultEncoding
   and the "surrogateescape" error handler.

   If Py_FileSystemDefaultEncoding is not set, fall back to the locale
   encoding.
*/

PyAPI_FUNC(PyObject*) PyUnicode_DecodeFSDefaultAndSize(
    const char *s,               /* encoded string */
    Py_ssize_t size              /* size */
    );

/* Encode a Unicode object to Py_FileSystemDefaultEncoding with the
   "surrogateescape" error handler, and return bytes.

   If Py_FileSystemDefaultEncoding is not set, fall back to the locale
   encoding.
*/

PyAPI_FUNC(PyObject*) PyUnicode_EncodeFSDefault(
    PyObject *unicode
    );

/* --- Methods & Slots ----------------------------------------------------

   These are capable of handling Unicode objects and strings on input
   (we refer to them as strings in the descriptions) and return
   Unicode objects or integers as appropriate. */

/* Concat two strings giving a new Unicode string. */

PyAPI_FUNC(PyObject*) PyUnicode_Concat(
    PyObject *left,             /* Left string */
    PyObject *right             /* Right string */
    );

/* Concat two strings and put the result in *pleft
   (sets *pleft to NULL on error) */

PyAPI_FUNC(void) PyUnicode_Append(
    PyObject **pleft,           /* Pointer to left string */
    PyObject *right             /* Right string */
    );

/* Concat two strings, put the result in *pleft and drop the right object
   (sets *pleft to NULL on error) */

PyAPI_FUNC(void) PyUnicode_AppendAndDel(
    PyObject **pleft,           /* Pointer to left string */
    PyObject *right             /* Right string */
    );

/* Split a string giving a list of Unicode strings.

   If sep is NULL, splitting will be done at all whitespace
   substrings. Otherwise, splits occur at the given separator.

   At most maxsplit splits will be done. If negative, no limit is set.

   Separators are not included in the resulting list.

*/

PyAPI_FUNC(PyObject*) PyUnicode_Split(
    PyObject *s,                /* String to split */
    PyObject *sep,              /* String separator */
    Py_ssize_t maxsplit         /* Maxsplit count */
    );

/* Dito, but split at line breaks.

   CRLF is considered to be one line break. Line breaks are not
   included in the resulting list. */

PyAPI_FUNC(PyObject*) PyUnicode_Splitlines(
    PyObject *s,                /* String to split */
    int keepends                /* If true, line end markers are included */
    );

/* Partition a string using a given separator. */

PyAPI_FUNC(PyObject*) PyUnicode_Partition(
    PyObject *s,                /* String to partition */
    PyObject *sep               /* String separator */
    );

/* Partition a string using a given separator, searching from the end of the
   string. */

PyAPI_FUNC(PyObject*) PyUnicode_RPartition(
    PyObject *s,                /* String to partition */
    PyObject *sep               /* String separator */
    );

/* Split a string giving a list of Unicode strings.

   If sep is NULL, splitting will be done at all whitespace
   substrings. Otherwise, splits occur at the given separator.

   At most maxsplit splits will be done. But unlike PyUnicode_Split
   PyUnicode_RSplit splits from the end of the string. If negative,
   no limit is set.

   Separators are not included in the resulting list.

*/

PyAPI_FUNC(PyObject*) PyUnicode_RSplit(
    PyObject *s,                /* String to split */
    PyObject *sep,              /* String separator */
    Py_ssize_t maxsplit         /* Maxsplit count */
    );

/* Translate a string by applying a character mapping table to it and
   return the resulting Unicode object.

   The mapping table must map Unicode ordinal integers to Unicode strings,
   Unicode ordinal integers or None (causing deletion of the character).

   Mapping tables may be dictionaries or sequences. Unmapped character
   ordinals (ones which cause a LookupError) are left untouched and
   are copied as-is.

*/

PyAPI_FUNC(PyObject *) PyUnicode_Translate(
    PyObject *str,              /* String */
    PyObject *table,            /* Translate table */
    const char *errors          /* error handling */
    );

/* Join a sequence of strings using the given separator and return
   the resulting Unicode string. */

PyAPI_FUNC(PyObject*) PyUnicode_Join(
    PyObject *separator,        /* Separator string */
    PyObject *seq               /* Sequence object */
    );

#ifndef Py_LIMITED_API
PyAPI_FUNC(PyObject *) _PyUnicode_JoinArray(
    PyObject *separator,
    PyObject *const *items,
    Py_ssize_t seqlen
    );
#endif /* Py_LIMITED_API */

/* Return 1 if substr matches str[start:end] at the given tail end, 0
   otherwise. */

PyAPI_FUNC(Py_ssize_t) PyUnicode_Tailmatch(
    PyObject *str,              /* String */
    PyObject *substr,           /* Prefix or Suffix string */
    Py_ssize_t start,           /* Start index */
    Py_ssize_t end,             /* Stop index */
    int direction               /* Tail end: -1 prefix, +1 suffix */
    );

/* Return the first position of substr in str[start:end] using the
   given search direction or -1 if not found. -2 is returned in case
   an error occurred and an exception is set. */

PyAPI_FUNC(Py_ssize_t) PyUnicode_Find(
    PyObject *str,              /* String */
    PyObject *substr,           /* Substring to find */
    Py_ssize_t start,           /* Start index */
    Py_ssize_t end,             /* Stop index */
    int direction               /* Find direction: +1 forward, -1 backward */
    );

#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
/* Like PyUnicode_Find, but search for single character only. */
PyAPI_FUNC(Py_ssize_t) PyUnicode_FindChar(
    PyObject *str,
    Py_UCS4 ch,
    Py_ssize_t start,
    Py_ssize_t end,
    int direction
    );
#endif

/* Count the number of occurrences of substr in str[start:end]. */

PyAPI_FUNC(Py_ssize_t) PyUnicode_Count(
    PyObject *str,              /* String */
    PyObject *substr,           /* Substring to count */
    Py_ssize_t start,           /* Start index */
    Py_ssize_t end              /* Stop index */
    );

/* Replace at most maxcount occurrences of substr in str with replstr
   and return the resulting Unicode object. */

PyAPI_FUNC(PyObject *) PyUnicode_Replace(
    PyObject *str,              /* String */
    PyObject *substr,           /* Substring to find */
    PyObject *replstr,          /* Substring to replace */
    Py_ssize_t maxcount         /* Max. number of replacements to apply;
                                   -1 = all */
    );

/* Compare two strings and return -1, 0, 1 for less than, equal,
   greater than resp.
   Raise an exception and return -1 on error. */

PyAPI_FUNC(int) PyUnicode_Compare(
    PyObject *left,             /* Left string */
    PyObject *right             /* Right string */
    );

#ifndef Py_LIMITED_API
/* Test whether a unicode is equal to ASCII identifier.  Return 1 if true,
   0 otherwise.  The right argument must be ASCII identifier.
   Any error occurs inside will be cleared before return. */

PyAPI_FUNC(int) _PyUnicode_EqualToASCIIId(
    PyObject *left,             /* Left string */
    _Py_Identifier *right       /* Right identifier */
    );
#endif

/* Compare a Unicode object with C string and return -1, 0, 1 for less than,
   equal, and greater than, respectively.  It is best to pass only
   ASCII-encoded strings, but the function interprets the input string as
   ISO-8859-1 if it contains non-ASCII characters.
   This function does not raise exceptions. */

PyAPI_FUNC(int) PyUnicode_CompareWithASCIIString(
    PyObject *left,
    const char *right           /* ASCII-encoded string */
    );

#ifndef Py_LIMITED_API
/* Test whether a unicode is equal to ASCII string.  Return 1 if true,
   0 otherwise.  The right argument must be ASCII-encoded string.
   Any error occurs inside will be cleared before return. */

PyAPI_FUNC(int) _PyUnicode_EqualToASCIIString(
    PyObject *left,
    const char *right           /* ASCII-encoded string */
    );
#endif

/* Rich compare two strings and return one of the following:

   - NULL in case an exception was raised
   - Py_True or Py_False for successful comparisons
   - Py_NotImplemented in case the type combination is unknown

   Possible values for op:

     Py_GT, Py_GE, Py_EQ, Py_NE, Py_LT, Py_LE

*/

PyAPI_FUNC(PyObject *) PyUnicode_RichCompare(
    PyObject *left,             /* Left string */
    PyObject *right,            /* Right string */
    int op                      /* Operation: Py_EQ, Py_NE, Py_GT, etc. */
    );

/* Apply an argument tuple or dictionary to a format string and return
   the resulting Unicode string. */

PyAPI_FUNC(PyObject *) PyUnicode_Format(
    PyObject *format,           /* Format string */
    PyObject *args              /* Argument tuple or dictionary */
    );

/* Checks whether element is contained in container and return 1/0
   accordingly.

   element has to coerce to a one element Unicode string. -1 is
   returned in case of an error. */

PyAPI_FUNC(int) PyUnicode_Contains(
    PyObject *container,        /* Container string */
    PyObject *element           /* Element string */
    );

/* Checks whether argument is a valid identifier. */

PyAPI_FUNC(int) PyUnicode_IsIdentifier(PyObject *s);

#ifndef Py_LIMITED_API
/* Externally visible for str.strip(unicode) */
PyAPI_FUNC(PyObject *) _PyUnicode_XStrip(
    PyObject *self,
    int striptype,
    PyObject *sepobj
    );
#endif

/* Using explicit passed-in values, insert the thousands grouping
   into the string pointed to by buffer.  For the argument descriptions,
   see Objects/stringlib/localeutil.h */
#ifndef Py_LIMITED_API
PyAPI_FUNC(Py_ssize_t) _PyUnicode_InsertThousandsGrouping(
    PyObject *unicode,
    Py_ssize_t index,
    Py_ssize_t n_buffer,
    void *digits,
    Py_ssize_t n_digits,
    Py_ssize_t min_width,
    const char *grouping,
    PyObject *thousands_sep,
    Py_UCS4 *maxchar);
#endif
/* === Characters Type APIs =============================================== */

/* Helper array used by Py_UNICODE_ISSPACE(). */

#ifndef Py_LIMITED_API
PyAPI_DATA(const unsigned char) _Py_ascii_whitespace[];

/* These should not be used directly. Use the Py_UNICODE_IS* and
   Py_UNICODE_TO* macros instead.

   These APIs are implemented in Objects/unicodectype.c.

*/

PyAPI_FUNC(int) _PyUnicode_IsLowercase(
    Py_UCS4 ch       /* Unicode character */
    );

PyAPI_FUNC(int) _PyUnicode_IsUppercase(
    Py_UCS4 ch       /* Unicode character */
    );

PyAPI_FUNC(int) _PyUnicode_IsTitlecase(
    Py_UCS4 ch       /* Unicode character */
    );

PyAPI_FUNC(int) _PyUnicode_IsXidStart(
    Py_UCS4 ch       /* Unicode character */
    );

PyAPI_FUNC(int) _PyUnicode_IsXidContinue(
    Py_UCS4 ch       /* Unicode character */
    );

PyAPI_FUNC(int) _PyUnicode_IsWhitespace(
    const Py_UCS4 ch         /* Unicode character */
    );

PyAPI_FUNC(int) _PyUnicode_IsLinebreak(
    const Py_UCS4 ch         /* Unicode character */
    );

PyAPI_FUNC(Py_UCS4) _PyUnicode_ToLowercase(
    Py_UCS4 ch       /* Unicode character */
    ) /* Py_DEPRECATED(3.3) */;

PyAPI_FUNC(Py_UCS4) _PyUnicode_ToUppercase(
    Py_UCS4 ch       /* Unicode character */
    ) /* Py_DEPRECATED(3.3) */;

PyAPI_FUNC(Py_UCS4) _PyUnicode_ToTitlecase(
    Py_UCS4 ch       /* Unicode character */
    ) Py_DEPRECATED(3.3);

PyAPI_FUNC(int) _PyUnicode_ToLowerFull(
    Py_UCS4 ch,       /* Unicode character */
    Py_UCS4 *res
    );

PyAPI_FUNC(int) _PyUnicode_ToTitleFull(
    Py_UCS4 ch,       /* Unicode character */
    Py_UCS4 *res
    );

PyAPI_FUNC(int) _PyUnicode_ToUpperFull(
    Py_UCS4 ch,       /* Unicode character */
    Py_UCS4 *res
    );

PyAPI_FUNC(int) _PyUnicode_ToFoldedFull(
    Py_UCS4 ch,       /* Unicode character */
    Py_UCS4 *res
    );

PyAPI_FUNC(int) _PyUnicode_IsCaseIgnorable(
    Py_UCS4 ch         /* Unicode character */
    );

PyAPI_FUNC(int) _PyUnicode_IsCased(
    Py_UCS4 ch         /* Unicode character */
    );

PyAPI_FUNC(int) _PyUnicode_ToDecimalDigit(
    Py_UCS4 ch       /* Unicode character */
    );

PyAPI_FUNC(int) _PyUnicode_ToDigit(
    Py_UCS4 ch       /* Unicode character */
    );

PyAPI_FUNC(double) _PyUnicode_ToNumeric(
    Py_UCS4 ch       /* Unicode character */
    );

PyAPI_FUNC(int) _PyUnicode_IsDecimalDigit(
    Py_UCS4 ch       /* Unicode character */
    );

PyAPI_FUNC(int) _PyUnicode_IsDigit(
    Py_UCS4 ch       /* Unicode character */
    );

PyAPI_FUNC(int) _PyUnicode_IsNumeric(
    Py_UCS4 ch       /* Unicode character */
    );

PyAPI_FUNC(int) _PyUnicode_IsPrintable(
    Py_UCS4 ch       /* Unicode character */
    );

PyAPI_FUNC(int) _PyUnicode_IsAlpha(
    Py_UCS4 ch       /* Unicode character */
    );

PyAPI_FUNC(size_t) Py_UNICODE_strlen(
    const Py_UNICODE *u
    ) Py_DEPRECATED(3.3);

PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strcpy(
    Py_UNICODE *s1,
    const Py_UNICODE *s2) Py_DEPRECATED(3.3);

PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strcat(
    Py_UNICODE *s1, const Py_UNICODE *s2) Py_DEPRECATED(3.3);

PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strncpy(
    Py_UNICODE *s1,
    const Py_UNICODE *s2,
    size_t n) Py_DEPRECATED(3.3);

PyAPI_FUNC(int) Py_UNICODE_strcmp(
    const Py_UNICODE *s1,
    const Py_UNICODE *s2
    ) Py_DEPRECATED(3.3);

PyAPI_FUNC(int) Py_UNICODE_strncmp(
    const Py_UNICODE *s1,
    const Py_UNICODE *s2,
    size_t n
    ) Py_DEPRECATED(3.3);

PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strchr(
    const Py_UNICODE *s,
    Py_UNICODE c
    ) Py_DEPRECATED(3.3);

PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strrchr(
    const Py_UNICODE *s,
    Py_UNICODE c
    ) Py_DEPRECATED(3.3);

PyAPI_FUNC(PyObject*) _PyUnicode_FormatLong(PyObject *, int, int, int);

/* Create a copy of a unicode string ending with a nul character. Return NULL
   and raise a MemoryError exception on memory allocation failure, otherwise
   return a new allocated buffer (use PyMem_Free() to free the buffer). */

PyAPI_FUNC(Py_UNICODE*) PyUnicode_AsUnicodeCopy(
    PyObject *unicode
    ) Py_DEPRECATED(3.3);
#endif /* Py_LIMITED_API */

#if defined(Py_DEBUG) && !defined(Py_LIMITED_API)
PyAPI_FUNC(int) _PyUnicode_CheckConsistency(
    PyObject *op,
    int check_content);
#elif !defined(NDEBUG)
/* For asserts that call _PyUnicode_CheckConsistency(), which would
 * otherwise be a problem when building with asserts but without Py_DEBUG. */
#define _PyUnicode_CheckConsistency(op, check_content) PyUnicode_Check(op)
#endif

#ifndef Py_LIMITED_API
/* Return an interned Unicode object for an Identifier; may fail if there is no memory.*/
PyAPI_FUNC(PyObject*) _PyUnicode_FromId(_Py_Identifier*);
/* Clear all static strings. */
PyAPI_FUNC(void) _PyUnicode_ClearStaticStrings(void);

/* Fast equality check when the inputs are known to be exact unicode types
   and where the hash values are equal (i.e. a very probable match) */
PyAPI_FUNC(int) _PyUnicode_EQ(PyObject *, PyObject *);
#endif /* !Py_LIMITED_API */

#ifdef __cplusplus
}
#endif
#endif /* !Py_UNICODEOBJECT_H */