pypy / pypy / rlib / runicode.py

   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
import sys
from pypy.rlib.bitmanipulation import splitter
from pypy.rpython.lltypesystem import lltype, rffi
from pypy.rlib.objectmodel import we_are_translated, specialize, enforceargs
from pypy.rlib.rstring import StringBuilder, UnicodeBuilder
from pypy.rlib.rarithmetic import r_uint, intmask
from pypy.module.unicodedata import unicodedb

if rffi.sizeof(lltype.UniChar) == 4:
    MAXUNICODE = 0x10ffff
else:
    MAXUNICODE = 0xffff
BYTEORDER = sys.byteorder

if MAXUNICODE > sys.maxunicode:
    # A version of unichr which allows codes outside the BMP
    # even on narrow unicode builds.
    # It will be used when interpreting code on top of a UCS2 CPython,
    # when sizeof(wchar_t) == 4.
    # Note that Python3 uses a similar implementation.
    def UNICHR(c):
        assert not we_are_translated()
        if c <= sys.maxunicode or c > MAXUNICODE:
            return unichr(c)
        else:
            c -= 0x10000
            return (unichr(0xD800 + (c >> 10)) +
                    unichr(0xDC00 + (c & 0x03FF)))
    UNICHR._flowspace_rewrite_directly_as_ = unichr
    # ^^^ NB.: for translation, it's essential to use this hack instead
    # of calling unichr() from UNICHR(), because unichr() detects if there
    # is a "try:except ValueError" immediately around it.

    def ORD(u):
        assert not we_are_translated()
        if isinstance(u, unicode) and len(u) == 2:
            ch1 = ord(u[0])
            ch2 = ord(u[1])
            if 0xD800 <= ch1 <= 0xDBFF and 0xDC00 <= ch2 <= 0xDFFF:
                return (((ch1 - 0xD800) << 10) | (ch2 - 0xDC00)) + 0x10000
        return ord(u)
    ORD._flowspace_rewrite_directly_as_ = ord

else:
    UNICHR = unichr
    ORD = ord


def default_unicode_error_decode(errors, encoding, msg, s,
                                 startingpos, endingpos):
    if errors == 'replace':
        return u'\ufffd', endingpos
    if errors == 'ignore':
        return u'', endingpos
    raise UnicodeDecodeError(encoding, s, startingpos, endingpos, msg)

def default_unicode_error_encode(errors, encoding, msg, u,
                                 startingpos, endingpos):
    if errors == 'replace':
        return u'?', None, endingpos
    if errors == 'ignore':
        return u'', None, endingpos
    raise UnicodeEncodeError(encoding, u, startingpos, endingpos, msg)

# ____________________________________________________________
# utf-8

utf8_code_length = [
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, # 00-0F
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
    1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, # 70-7F
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, # 80-8F
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, # B0-BF
    0, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, # C0-C1 + C2-CF
    2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, # D0-DF
    3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, # E0-EF
    4, 4, 4, 4, 4, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0  # F0-F4 - F5-FF
]

def str_decode_utf_8(s, size, errors, final=False,
                     errorhandler=None, allow_surrogates=False):
    if errorhandler is None:
        errorhandler = default_unicode_error_decode
    return str_decode_utf_8_impl(s, size, errors, final, errorhandler,
                                 allow_surrogates=allow_surrogates)

def str_decode_utf_8_impl(s, size, errors, final, errorhandler,
                          allow_surrogates):
    if size == 0:
        return u'', 0

    result = UnicodeBuilder(size)
    pos = 0
    while pos < size:
        ordch1 = ord(s[pos])
        # fast path for ASCII
        # XXX maybe use a while loop here
        if ordch1 < 0x80:
            result.append(unichr(ordch1))
            pos += 1
            continue

        n = utf8_code_length[ordch1]
        if pos + n > size:
            if not final:
                break
            charsleft = size - pos - 1 # either 0, 1, 2
            # note: when we get the 'unexpected end of data' we don't care
            # about the pos anymore and we just ignore the value
            if not charsleft:
                # there's only the start byte and nothing else
                r, pos = errorhandler(errors, 'utf-8',
                                      'unexpected end of data',
                                      s, pos, pos+1)
                result.append(r)
                break
            ordch2 = ord(s[pos+1])
            if n == 3:
                # 3-bytes seq with only a continuation byte
                if (ordch2>>6 != 0x2 or   # 0b10
                    (ordch1 == 0xe0 and ordch2 < 0xa0)):
                    # or (ordch1 == 0xed and ordch2 > 0x9f)
                    # second byte invalid, take the first and continue
                    r, pos = errorhandler(errors, 'utf-8',
                                          'invalid continuation byte',
                                          s, pos, pos+1)
                    result.append(r)
                    continue
                else:
                    # second byte valid, but third byte missing
                    r, pos = errorhandler(errors, 'utf-8',
                                      'unexpected end of data',
                                      s, pos, pos+2)
                    result.append(r)
                    break
            elif n == 4:
                # 4-bytes seq with 1 or 2 continuation bytes
                if (ordch2>>6 != 0x2 or    # 0b10
                    (ordch1 == 0xf0 and ordch2 < 0x90) or
                    (ordch1 == 0xf4 and ordch2 > 0x8f)):
                    # second byte invalid, take the first and continue
                    r, pos = errorhandler(errors, 'utf-8',
                                          'invalid continuation byte',
                                          s, pos, pos+1)
                    result.append(r)
                    continue
                elif charsleft == 2 and ord(s[pos+2])>>6 != 0x2:   # 0b10
                    # third byte invalid, take the first two and continue
                    r, pos = errorhandler(errors, 'utf-8',
                                          'invalid continuation byte',
                                          s, pos, pos+2)
                    result.append(r)
                    continue
                else:
                    # there's only 1 or 2 valid cb, but the others are missing
                    r, pos = errorhandler(errors, 'utf-8',
                                      'unexpected end of data',
                                      s, pos, pos+charsleft+1)
                    result.append(r)
                    break

        if n == 0:
            r, pos = errorhandler(errors, 'utf-8',
                                  'invalid start byte',
                                  s, pos, pos+1)
            result.append(r)

        elif n == 1:
            assert 0, "ascii should have gone through the fast path"

        elif n == 2:
            ordch2 = ord(s[pos+1])
            if ordch2>>6 != 0x2:   # 0b10
                r, pos = errorhandler(errors, 'utf-8',
                                      'invalid continuation byte',
                                      s, pos, pos+1)
                result.append(r)
                continue
            # 110yyyyy 10zzzzzz -> 00000000 00000yyy yyzzzzzz
            result.append(unichr(((ordch1 & 0x1F) << 6) +    # 0b00011111
                                 (ordch2 & 0x3F)))           # 0b00111111
            pos += 2

        elif n == 3:
            ordch2 = ord(s[pos+1])
            ordch3 = ord(s[pos+2])
            if (ordch2>>6 != 0x2 or    # 0b10
                (ordch1 == 0xe0 and ordch2 < 0xa0)
                # surrogates shouldn't be valid UTF-8!
                or (not allow_surrogates and ordch1 == 0xed and ordch2 > 0x9f)
                ):
                r, pos = errorhandler(errors, 'utf-8',
                                      'invalid continuation byte',
                                      s, pos, pos+1)
                result.append(r)
                continue
            elif ordch3>>6 != 0x2:     # 0b10
                r, pos = errorhandler(errors, 'utf-8',
                                      'invalid continuation byte',
                                      s, pos, pos+2)
                result.append(r)
                continue
            # 1110xxxx 10yyyyyy 10zzzzzz -> 00000000 xxxxyyyy yyzzzzzz
            result.append(unichr(((ordch1 & 0x0F) << 12) +     # 0b00001111
                                 ((ordch2 & 0x3F) << 6) +      # 0b00111111
                                 (ordch3 & 0x3F)))             # 0b00111111
            pos += 3

        elif n == 4:
            ordch2 = ord(s[pos+1])
            ordch3 = ord(s[pos+2])
            ordch4 = ord(s[pos+3])
            if (ordch2>>6 != 0x2 or     # 0b10
                (ordch1 == 0xf0 and ordch2 < 0x90) or
                (ordch1 == 0xf4 and ordch2 > 0x8f)):
                r, pos = errorhandler(errors, 'utf-8',
                                      'invalid continuation byte',
                                      s, pos, pos+1)
                result.append(r)
                continue
            elif ordch3>>6 != 0x2:     # 0b10
                r, pos = errorhandler(errors, 'utf-8',
                                      'invalid continuation byte',
                                      s, pos, pos+2)
                result.append(r)
                continue
            elif ordch4>>6 != 0x2:     # 0b10
                r, pos = errorhandler(errors, 'utf-8',
                                      'invalid continuation byte',
                                      s, pos, pos+3)
                result.append(r)
                continue
            # 11110www 10xxxxxx 10yyyyyy 10zzzzzz -> 000wwwxx xxxxyyyy yyzzzzzz
            c = (((ordch1 & 0x07) << 18) +      # 0b00000111
                 ((ordch2 & 0x3F) << 12) +      # 0b00111111
                 ((ordch3 & 0x3F) << 6) +       # 0b00111111
                 (ordch4 & 0x3F))               # 0b00111111
            if c <= MAXUNICODE:
                result.append(UNICHR(c))
            else:
                # compute and append the two surrogates:
                # translate from 10000..10FFFF to 0..FFFF
                c -= 0x10000
                # high surrogate = top 10 bits added to D800
                result.append(unichr(0xD800 + (c >> 10)))
                # low surrogate = bottom 10 bits added to DC00
                result.append(unichr(0xDC00 + (c & 0x03FF)))
            pos += 4

    return result.build(), pos

def _encodeUCS4(result, ch):
    # Encode UCS4 Unicode ordinals
    result.append((chr((0xf0 | (ch >> 18)))))
    result.append((chr((0x80 | ((ch >> 12) & 0x3f)))))
    result.append((chr((0x80 | ((ch >> 6) & 0x3f)))))
    result.append((chr((0x80 | (ch & 0x3f)))))

def unicode_encode_utf_8(s, size, errors, errorhandler=None,
                         allow_surrogates=False):
    if errorhandler is None:
        errorhandler = default_unicode_error_encode
    return unicode_encode_utf_8_impl(s, size, errors, errorhandler,
                                     allow_surrogates=allow_surrogates)

def unicode_encode_utf_8_impl(s, size, errors, errorhandler,
                              allow_surrogates=False):
    assert(size >= 0)
    result = StringBuilder(size)
    pos = 0
    while pos < size:
        ch = ord(s[pos])
        pos += 1
        if ch < 0x80:
            # Encode ASCII
            result.append(chr(ch))
        elif ch < 0x0800:
            # Encode Latin-1
            result.append(chr((0xc0 | (ch >> 6))))
            result.append(chr((0x80 | (ch & 0x3f))))
        else:
            # Encode UCS2 Unicode ordinals
            if ch < 0x10000:
                # Special case: check for high surrogate
                if 0xD800 <= ch <= 0xDFFF:
                    if pos != size:
                        ch2 = ord(s[pos])
                        # Check for low surrogate and combine the two to
                        # form a UCS4 value
                        if ch <= 0xDBFF and 0xDC00 <= ch2 <= 0xDFFF:
                            ch3 = ((ch - 0xD800) << 10 | (ch2 - 0xDC00)) + 0x10000
                            pos += 1
                            _encodeUCS4(result, ch3)
                            continue
                    if not allow_surrogates:
                        ru, rs, pos = errorhandler(errors, 'utf-8',
                                                   'surrogates not allowed',
                                                   s, pos-1, pos)
                        if rs is not None:
                            # py3k only
                            result.append(rs)
                            continue
                        for ch in ru:
                            if ord(ch) < 0x80:
                                result.append(chr(ord(ch)))
                            else:
                                errorhandler('strict', 'utf-8',
                                             'surrogates not allowed',
                                             s, pos-1, pos)
                        continue
                    # else: Fall through and handles isolated high surrogates
                result.append((chr((0xe0 | (ch >> 12)))))
                result.append((chr((0x80 | ((ch >> 6) & 0x3f)))))
                result.append((chr((0x80 | (ch & 0x3f)))))
            else:
                _encodeUCS4(result, ch)
    return result.build()

# ____________________________________________________________
# utf-16

def str_decode_utf_16(s, size, errors, final=True,
                      errorhandler=None):
    result, length, byteorder = str_decode_utf_16_helper(s, size, errors, final,
                                                         errorhandler, "native")
    return result, length

def str_decode_utf_16_be(s, size, errors, final=True,
                         errorhandler=None):
    result, length, byteorder = str_decode_utf_16_helper(s, size, errors, final,
                                                         errorhandler, "big")
    return result, length

def str_decode_utf_16_le(s, size, errors, final=True,
                         errorhandler=None):
    result, length, byteorder = str_decode_utf_16_helper(s, size, errors, final,
                                                         errorhandler, "little")
    return result, length

def str_decode_utf_16_helper(s, size, errors, final=True,
                             errorhandler=None,
                             byteorder="native"):
    if errorhandler is None:
        errorhandler = default_unicode_error_decode
    bo = 0

    if BYTEORDER == 'little':
        ihi = 1
        ilo = 0
    else:
        ihi = 0
        ilo = 1

    #  Check for BOM marks (U+FEFF) in the input and adjust current
    #  byte order setting accordingly. In native mode, the leading BOM
    #  mark is skipped, in all other modes, it is copied to the output
    #  stream as-is (giving a ZWNBSP character).
    pos = 0
    if byteorder == 'native':
        if size >= 2:
            bom = (ord(s[ihi]) << 8) | ord(s[ilo])
            if BYTEORDER == 'little':
                if bom == 0xFEFF:
                    pos += 2
                    bo = -1
                elif bom == 0xFFFE:
                    pos += 2
                    bo = 1
            else:
                if bom == 0xFEFF:
                    pos += 2
                    bo = 1
                elif bom == 0xFFFE:
                    pos += 2
                    bo = -1
    elif byteorder == 'little':
        bo = -1
    else:
        bo = 1
    if size == 0:
        return u'', 0, bo
    if bo == -1:
        # force little endian
        ihi = 1
        ilo = 0

    elif bo == 1:
        # force big endian
        ihi = 0
        ilo = 1

    result = UnicodeBuilder(size // 2)

    #XXX I think the errors are not correctly handled here
    while pos < size:
        # remaining bytes at the end? (size should be even)
        if len(s) - pos < 2:
            if not final:
                break
            r, pos = errorhandler(errors, 'utf-16', "truncated data",
                                  s, pos, len(s))
            result.append(r)
            if len(s) - pos < 2:
                break
        ch = (ord(s[pos + ihi]) << 8) | ord(s[pos + ilo])
        pos += 2
        if ch < 0xD800 or ch > 0xDFFF:
            result.append(unichr(ch))
            continue
        # UTF-16 code pair:
        if len(s) - pos < 2:
            if not final:
                break
            errmsg = "unexpected end of data"
            r, pos = errorhandler(errors, 'utf-16', errmsg, s, pos - 2, len(s))
            result.append(r)
            if len(s) - pos < 2:
                break
        elif 0xD800 <= ch <= 0xDBFF:
            ch2 = (ord(s[pos+ihi]) << 8) | ord(s[pos+ilo])
            pos += 2
            if 0xDC00 <= ch2 <= 0xDFFF:
                if MAXUNICODE < 65536:
                    result.append(unichr(ch))
                    result.append(unichr(ch2))
                else:
                    result.append(UNICHR((((ch & 0x3FF)<<10) |
                                           (ch2 & 0x3FF)) + 0x10000))
                continue
            else:
                r, pos = errorhandler(errors, 'utf-16',
                                      "illegal UTF-16 surrogate",
                                      s, pos - 4, pos - 2)
                result.append(r)
        else:
            r, pos = errorhandler(errors, 'utf-16',
                                  "illegal encoding",
                                  s, pos - 2, pos)
            result.append(r)
    return result.build(), pos, bo

def _STORECHAR(result, CH, byteorder):
    hi = chr(((CH) >> 8) & 0xff)
    lo = chr((CH) & 0xff)
    if byteorder == 'little':
        result.append(lo)
        result.append(hi)
    else:
        result.append(hi)
        result.append(lo)

def unicode_encode_utf_16_helper(s, size, errors,
                                 errorhandler=None,
                                 byteorder='little'):
    if size == 0:
        return ""

    result = StringBuilder(size * 2 + 2)
    if byteorder == 'native':
        _STORECHAR(result, 0xFEFF, BYTEORDER)
        byteorder = BYTEORDER

    i = 0
    while i < size:
        ch = ord(s[i])
        i += 1
        ch2 = 0
        if ch >= 0x10000:
            ch2 = 0xDC00 | ((ch-0x10000) & 0x3FF)
            ch  = 0xD800 | ((ch-0x10000) >> 10)

        _STORECHAR(result, ch, byteorder)
        if ch2:
            _STORECHAR(result, ch2, byteorder)

    return result.build()

def unicode_encode_utf_16(s, size, errors,
                          errorhandler=None):
    return unicode_encode_utf_16_helper(s, size, errors, errorhandler, "native")


def unicode_encode_utf_16_be(s, size, errors,
                             errorhandler=None):
    return unicode_encode_utf_16_helper(s, size, errors, errorhandler, "big")


def unicode_encode_utf_16_le(s, size, errors,
                             errorhandler=None):
    return unicode_encode_utf_16_helper(s, size, errors, errorhandler, "little")


# ____________________________________________________________
# utf-32

def str_decode_utf_32(s, size, errors, final=True,
                      errorhandler=None):
    result, length, byteorder = str_decode_utf_32_helper(s, size, errors, final,
                                                         errorhandler, "native")
    return result, length

def str_decode_utf_32_be(s, size, errors, final=True,
                         errorhandler=None):
    result, length, byteorder = str_decode_utf_32_helper(s, size, errors, final,
                                                         errorhandler, "big")
    return result, length

def str_decode_utf_32_le(s, size, errors, final=True,
                         errorhandler=None):
    result, length, byteorder = str_decode_utf_32_helper(s, size, errors, final,
                                                         errorhandler, "little")
    return result, length

BOM32_DIRECT  = intmask(0x0000FEFF)
BOM32_REVERSE = intmask(0xFFFE0000)

def str_decode_utf_32_helper(s, size, errors, final=True,
                             errorhandler=None,
                             byteorder="native"):
    if errorhandler is None:
        errorhandler = default_unicode_error_decode
    bo = 0

    if BYTEORDER == 'little':
        iorder = [0, 1, 2, 3]
    else:
        iorder = [3, 2, 1, 0]

    #  Check for BOM marks (U+FEFF) in the input and adjust current
    #  byte order setting accordingly. In native mode, the leading BOM
    #  mark is skipped, in all other modes, it is copied to the output
    #  stream as-is (giving a ZWNBSP character).
    pos = 0
    if byteorder == 'native':
        if size >= 4:
            bom = intmask(
                (ord(s[iorder[3]]) << 24) | (ord(s[iorder[2]]) << 16) |
                (ord(s[iorder[1]]) << 8)  | ord(s[iorder[0]]))
            if BYTEORDER == 'little':
                if bom == BOM32_DIRECT:
                    pos += 4
                    bo = -1
                elif bom == BOM32_REVERSE:
                    pos += 4
                    bo = 1
            else:
                if bom == BOM32_DIRECT:
                    pos += 4
                    bo = 1
                elif bom == BOM32_REVERSE:
                    pos += 4
                    bo = -1
    elif byteorder == 'little':
        bo = -1
    else:
        bo = 1
    if size == 0:
        return u'', 0, bo
    if bo == -1:
        # force little endian
        iorder = [0, 1, 2, 3]

    elif bo == 1:
        # force big endian
        iorder = [3, 2, 1, 0]

    result = UnicodeBuilder(size // 4)

    while pos < size:
        # remaining bytes at the end? (size should be divisible by 4)
        if len(s) - pos < 4:
            if not final:
                break
            r, pos = errorhandler(errors, 'utf-32', "truncated data",
                                  s, pos, len(s))
            result.append(r)
            if len(s) - pos < 4:
                break
            continue
        ch = ((ord(s[pos + iorder[3]]) << 24) | (ord(s[pos + iorder[2]]) << 16) |
              (ord(s[pos + iorder[1]]) << 8)  | ord(s[pos + iorder[0]]))
        if ch >= 0x110000:
            r, pos = errorhandler(errors, 'utf-32', "codepoint not in range(0x110000)",
                                  s, pos, len(s))
            result.append(r)
            continue

        if MAXUNICODE < 65536 and ch >= 0x10000:
            ch -= 0x10000L
            result.append(unichr(0xD800 + (ch >> 10)))
            result.append(unichr(0xDC00 + (ch & 0x03FF)))
        else:
            result.append(UNICHR(ch))
        pos += 4
    return result.build(), pos, bo

def _STORECHAR32(result, CH, byteorder):
    c0 = chr(((CH) >> 24) & 0xff)
    c1 = chr(((CH) >> 16) & 0xff)
    c2 = chr(((CH) >> 8) & 0xff)
    c3 = chr((CH) & 0xff)
    if byteorder == 'little':
        result.append(c3)
        result.append(c2)
        result.append(c1)
        result.append(c0)
    else:
        result.append(c0)
        result.append(c1)
        result.append(c2)
        result.append(c3)

def unicode_encode_utf_32_helper(s, size, errors,
                                 errorhandler=None,
                                 byteorder='little'):
    if size == 0:
        return ""

    result = StringBuilder(size * 4 + 4)
    if byteorder == 'native':
        _STORECHAR32(result, 0xFEFF, BYTEORDER)
        byteorder = BYTEORDER

    i = 0
    while i < size:
        ch = ord(s[i])
        i += 1
        ch2 = 0
        if MAXUNICODE < 65536 and 0xD800 <= ch <= 0xDBFF and i < size:
            ch2 = ord(s[i])
            if 0xDC00 <= ch2 <= 0xDFFF:
                ch = (((ch & 0x3FF)<<10) | (ch2 & 0x3FF)) + 0x10000;
                i += 1
        _STORECHAR32(result, ch, byteorder)

    return result.build()

def unicode_encode_utf_32(s, size, errors,
                          errorhandler=None):
    return unicode_encode_utf_32_helper(s, size, errors, errorhandler, "native")


def unicode_encode_utf_32_be(s, size, errors,
                             errorhandler=None):
    return unicode_encode_utf_32_helper(s, size, errors, errorhandler, "big")


def unicode_encode_utf_32_le(s, size, errors,
                             errorhandler=None):
    return unicode_encode_utf_32_helper(s, size, errors, errorhandler, "little")


# ____________________________________________________________
# utf-7

# Three simple macros defining base-64

def _utf7_IS_BASE64(oc):
    "Is c a base-64 character?"
    c = chr(oc)
    return c.isalnum() or c == '+' or c == '/'
def _utf7_TO_BASE64(n):
    "Returns the base-64 character of the bottom 6 bits of n"
    return "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"[n & 0x3f]
def _utf7_FROM_BASE64(c):
    "given that c is a base-64 character, what is its base-64 value?"
    if c >= 'a':
        return ord(c) - 71
    elif c >= 'A':
        return ord(c) - 65
    elif c >= '0':
        return ord(c) + 4
    elif c == '+':
        return 62
    else: # c == '/'
        return 63

def _utf7_DECODE_DIRECT(oc):
    return oc <= 127 and oc != ord('+')

# The UTF-7 encoder treats ASCII characters differently according to
# whether they are Set D, Set O, Whitespace, or special (i.e. none of
# the above).  See RFC2152.  This array identifies these different
# sets:
# 0 : "Set D"
#      alphanumeric and '(),-./:?
# 1 : "Set O"
#     !"#$%&*;<=>@[]^_`{|}
# 2 : "whitespace"
#     ht nl cr sp
# 3 : special (must be base64 encoded)
#     everything else (i.e. +\~ and non-printing codes 0-8 11-12 14-31 127)

utf7_category = [
#  nul soh stx etx eot enq ack bel bs  ht  nl  vt  np  cr  so  si
    3,  3,  3,  3,  3,  3,  3,  3,  3,  2,  2,  3,  3,  2,  3,  3,
#  dle dc1 dc2 dc3 dc4 nak syn etb can em  sub esc fs  gs  rs  us
    3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,  3,
#  sp   !   "   #   $   %   &   '   (   )   *   +   ,   -   .   /
    2,  1,  1,  1,  1,  1,  1,  0,  0,  0,  1,  3,  0,  0,  0,  0,
#   0   1   2   3   4   5   6   7   8   9   :   ;   <   =   >   ?
    0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  1,  1,  1,  1,  0,
#   @   A   B   C   D   E   F   G   H   I   J   K   L   M   N   O
    1,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
#   P   Q   R   S   T   U   V   W   X   Y   Z   [   \   ]   ^   _
    0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  1,  3,  1,  1,  1,
#   `   a   b   c   d   e   f   g   h   i   j   k   l   m   n   o
    1,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,
#   p   q   r   s   t   u   v   w   x   y   z   {   |   }   ~  del
    0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  0,  1,  1,  1,  3,  3,
]

# ENCODE_DIRECT: this character should be encoded as itself.  The
# answer depends on whether we are encoding set O as itself, and also
# on whether we are encoding whitespace as itself.  RFC2152 makes it
# clear that the answers to these questions vary between
# applications, so this code needs to be flexible.

def _utf7_ENCODE_DIRECT(oc, directO, directWS):
    return(oc < 128 and oc > 0 and
           (utf7_category[oc] == 0 or
            (directWS and utf7_category[oc] == 2) or
            (directO and utf7_category[oc] == 1)))

def _utf7_ENCODE_CHAR(result, oc, base64bits, base64buffer):
    if MAXUNICODE > 65535 and oc >= 0x10000:
        # code first surrogate
        base64bits += 16
        base64buffer = (base64buffer << 16) | 0xd800 | ((oc-0x10000) >> 10)
        while base64bits >= 6:
            result.append(_utf7_TO_BASE64(base64buffer >> (base64bits-6)))
            base64bits -= 6
        # prepare second surrogate
        oc = 0xDC00 | ((oc-0x10000) & 0x3FF)
    base64bits += 16
    base64buffer = (base64buffer << 16) | oc
    while base64bits >= 6:
        result.append(_utf7_TO_BASE64(base64buffer >> (base64bits-6)))
        base64bits -= 6
    return base64bits, base64buffer

def str_decode_utf_7(s, size, errors, final=False,
                     errorhandler=None):
    if errorhandler is None:
        errorhandler = default_unicode_error_decode
    if size == 0:
        return u'', 0

    inShift = False
    base64bits = 0
    base64buffer = 0
    surrogate = 0

    result = UnicodeBuilder(size)
    pos = 0
    shiftOutStartPos = 0
    while pos < size:
        ch = s[pos]
        oc = ord(ch)

        if inShift: # in a base-64 section
            if _utf7_IS_BASE64(oc): #consume a base-64 character
                base64buffer = (base64buffer << 6) | _utf7_FROM_BASE64(ch)
                base64bits += 6
                pos += 1

                if base64bits >= 16:
                    # enough bits for a UTF-16 value
                    outCh = base64buffer >> (base64bits - 16)
                    base64bits -= 16
                    base64buffer &= (1 << base64bits) - 1 # clear high bits
                    if surrogate:
                        # expecting a second surrogate
                        if outCh >= 0xDC00 and outCh <= 0xDFFFF:
                            if MAXUNICODE < 65536:
                                result.append(unichr(surrogate))
                                result.append(unichr(outCh))
                            else:
                                result.append(
                                    UNICHR((((surrogate & 0x3FF)<<10) |
                                            (outCh & 0x3FF)) + 0x10000))
                            surrogate = 0
                            continue
                        else:
                            result.append(unichr(surrogate))
                            surrogate = 0
                            # Not done with outCh: falls back to next line
                    if outCh >= 0xD800 and outCh <= 0xDBFF:
                        # first surrogate
                        surrogate = outCh
                    else:
                        result.append(unichr(outCh))

            else:
                # now leaving a base-64 section
                inShift = False
                pos += 1

                if surrogate:
                    result.append(unichr(surrogate))
                    surrogate = 0

                if base64bits > 0: # left-over bits
                    if base64bits >= 6:
                        # We've seen at least one base-64 character
                        msg = "partial character in shift sequence"
                        res, pos = errorhandler(errors, 'utf-7',
                                                msg, s, pos-1, pos)
                        result.append(res)
                        continue
                    else:
                        # Some bits remain; they should be zero
                        if base64buffer != 0:
                            msg = "non-zero padding bits in shift sequence"
                            res, pos = errorhandler(errors, 'utf-7',
                                                    msg, s, pos-1, pos)
                            result.append(res)
                            continue

                if ch == '-':
                    # '-' is absorbed; other terminating characters are
                    # preserved
                    base64bits = 0
                    base64buffer = 0
                    surrogate = 0
                else:
                    result.append(unichr(ord(ch)))

        elif ch == '+':
            pos += 1 # consume '+'
            if pos < size and s[pos] == '-': # '+-' encodes '+'
                pos += 1
                result.append(u'+')
            else: # begin base64-encoded section
                inShift = 1
                shiftOutStartPos = pos - 1
                bitsleft = 0

        elif _utf7_DECODE_DIRECT(oc): # character decodes at itself
            result.append(unichr(oc))
            pos += 1
        else:
            pos += 1
            msg = "unexpected special character"
            res, pos = errorhandler(errors, 'utf-7', msg, s, pos-1, pos)
            result.append(res)

    # end of string

    if inShift and final: # in shift sequence, no more to follow
        # if we're in an inconsistent state, that's an error
        if (surrogate or
            base64bits >= 6 or
            (base64bits > 0 and base64buffer != 0)):
            endinpos = size
            msg = "unterminated shift sequence"
            res, pos = errorhandler(errors, 'utf-7', msg, s, shiftOutStartPos, pos)
            result.append(res)
    elif inShift:
        pos = shiftOutStartPos # back off output

    return result.build(), pos

def unicode_encode_utf_7(s, size, errors, errorhandler=None):
    if size == 0:
        return ''
    result = StringBuilder(size)

    encodeSetO = encodeWhiteSpace = False

    inShift = False
    base64bits = 0
    base64buffer = 0

    pos = 0
    while pos < size:
        ch = s[pos]
        oc = ord(ch)
        if not inShift:
            if ch == u'+':
                result.append('+-')
            elif _utf7_ENCODE_DIRECT(oc, not encodeSetO, not encodeWhiteSpace):
                result.append(chr(oc))
            else:
                result.append('+')
                inShift = True
                base64bits, base64buffer = _utf7_ENCODE_CHAR(
                    result, oc, base64bits, base64buffer)
        else:
            if _utf7_ENCODE_DIRECT(oc, not encodeSetO, not encodeWhiteSpace):
                # shifting out
                if base64bits: # output remaining bits
                    result.append(_utf7_TO_BASE64(base64buffer << (6-base64bits)))
                    base64buffer = 0
                    base64bits = 0

                inShift = False
                ## Characters not in the BASE64 set implicitly unshift the
                ## sequence so no '-' is required, except if the character is
                ## itself a '-'
                if _utf7_IS_BASE64(oc) or ch == u'-':
                    result.append('-')
                result.append(chr(oc))
            else:
                base64bits, base64buffer = _utf7_ENCODE_CHAR(
                    result, oc, base64bits, base64buffer)
        pos += 1

    if base64bits:
        result.append(_utf7_TO_BASE64(base64buffer << (6 - base64bits)))
    if inShift:
        result.append('-')

    return result.build()

# ____________________________________________________________
# ascii and latin-1

def str_decode_latin_1(s, size, errors, final=False,
                       errorhandler=None):
    # latin1 is equivalent to the first 256 ordinals in Unicode.
    pos = 0
    result = UnicodeBuilder(size)
    while pos < size:
        result.append(unichr(ord(s[pos])))
        pos += 1
    return result.build(), pos


def str_decode_ascii(s, size, errors, final=False,
                     errorhandler=None):
    if errorhandler is None:
        errorhandler = default_unicode_error_decode
    # ASCII is equivalent to the first 128 ordinals in Unicode.
    result = UnicodeBuilder(size)
    pos = 0
    while pos < size:
        c = s[pos]
        if ord(c) < 128:
            result.append(unichr(ord(c)))
            pos += 1
        else:
            r, pos = errorhandler(errors, "ascii", "ordinal not in range(128)",
                                  s,  pos, pos + 1)
            result.append(r)
    return result.build(), pos


def unicode_encode_ucs1_helper(p, size, errors,
                               errorhandler=None, limit=256):
    if errorhandler is None:
        errorhandler = default_unicode_error_encode
    if limit == 256:
        reason = "ordinal not in range(256)"
        encoding = "latin-1"
    else:
        reason = "ordinal not in range(128)"
        encoding = "ascii"

    if size == 0:
        return ''
    result = StringBuilder(size)
    pos = 0
    while pos < size:
        ch = p[pos]

        if ord(ch) < limit:
            result.append(chr(ord(ch)))
            pos += 1
        else:
            # startpos for collecting unencodable chars
            collstart = pos
            collend = pos+1
            while collend < len(p) and ord(p[collend]) >= limit:
                collend += 1
            ru, rs, pos = errorhandler(errors, encoding, reason, p,
                                       collstart, collend)
            if rs is not None:
                # py3k only
                result.append(rs)
                continue
            for ch in ru:
                if ord(ch) < limit:
                    result.append(chr(ord(ch)))
                else:
                    errorhandler("strict", encoding, reason, p,
                                 collstart, collend)

    return result.build()

def unicode_encode_latin_1(p, size, errors, errorhandler=None):
    res = unicode_encode_ucs1_helper(p, size, errors, errorhandler, 256)
    return res

def unicode_encode_ascii(p, size, errors, errorhandler=None):
    res = unicode_encode_ucs1_helper(p, size, errors, errorhandler, 128)
    return res

# ____________________________________________________________
# Charmap

ERROR_CHAR = u'\ufffe'

@specialize.argtype(5)
def str_decode_charmap(s, size, errors, final=False,
                       errorhandler=None, mapping=None):
    "mapping can be a rpython dictionary, or a dict-like object."

    # Default to Latin-1
    if mapping is None:
        return str_decode_latin_1(s, size, errors, final=final,
                                  errorhandler=errorhandler)
    if errorhandler is None:
        errorhandler = default_unicode_error_decode
    if size == 0:
        return u'', 0

    pos = 0
    result = UnicodeBuilder(size)
    while pos < size:
        ch = s[pos]

        c = mapping.get(ch, ERROR_CHAR)
        if c == ERROR_CHAR:
            r, pos = errorhandler(errors, "charmap",
                                  "character maps to <undefined>",
                                  s,  pos, pos + 1)
            result.append(r)
            continue
        result.append(c)
        pos += 1
    return result.build(), pos

def unicode_encode_charmap(s, size, errors, errorhandler=None,
                           mapping=None):
    if mapping is None:
        return unicode_encode_latin_1(s, size, errors,
                                      errorhandler=errorhandler)

    if errorhandler is None:
        errorhandler = default_unicode_error_encode

    if size == 0:
        return ''
    result = StringBuilder(size)
    pos = 0
    while pos < size:
        ch = s[pos]

        c = mapping.get(ch, '')
        if len(c) == 0:
            ru, rs, pos = errorhandler(errors, "charmap",
                                       "character maps to <undefined>",
                                       s, pos, pos + 1)
            if rs is not None:
                # py3k only
                result.append(rs)
                continue
            for ch2 in ru:
                c2 = mapping.get(ch2, '')
                if len(c2) == 0:
                    errorhandler(
                        "strict", "charmap",
                        "character maps to <undefined>",
                        s,  pos, pos + 1)
                result.append(c2)
            continue
        result.append(c)
        pos += 1
    return result.build()

# ____________________________________________________________
# Unicode escape

hexdigits = "0123456789ABCDEFabcdef"

def hexescape(builder, s, pos, digits,
              encoding, errorhandler, message, errors):
    import sys
    chr = 0
    if pos + digits > len(s):
        message = "end of string in escape sequence"
        res, pos = errorhandler(errors, "unicodeescape",
                                message, s, pos-2, len(s))
        builder.append(res)
    else:
        try:
            chr = r_uint(int(s[pos:pos+digits], 16))
        except ValueError:
            endinpos = pos
            while s[endinpos] in hexdigits:
                endinpos += 1
            res, pos = errorhandler(errors, encoding,
                                    message, s, pos-2, endinpos+1)
            builder.append(res)
        else:
            # when we get here, chr is a 32-bit unicode character
            if chr <= MAXUNICODE:
                builder.append(UNICHR(chr))
                pos += digits

            elif chr <= 0x10ffff:
                chr -= 0x10000L
                builder.append(unichr(0xD800 + (chr >> 10)))
                builder.append(unichr(0xDC00 + (chr & 0x03FF)))
                pos += digits
            else:
                message = "illegal Unicode character"
                res, pos = errorhandler(errors, encoding,
                                        message, s, pos-2, pos+digits)
                builder.append(res)
    return pos

def str_decode_unicode_escape(s, size, errors, final=False,
                              errorhandler=False,
                              unicodedata_handler=None):
    if errorhandler is None:
        errorhandler = default_unicode_error_decode

    if size == 0:
        return u'', 0

    builder = UnicodeBuilder(size)
    pos = 0
    while pos < size:
        ch = s[pos]

        # Non-escape characters are interpreted as Unicode ordinals
        if ch != '\\':
            builder.append(unichr(ord(ch)))
            pos += 1
            continue

        # - Escapes
        pos += 1
        if pos >= size:
            message = "\\ at end of string"
            res, pos = errorhandler(errors, "unicodeescape",
                                    message, s, pos-1, size)
            builder.append(res)
            continue

        ch = s[pos]
        pos += 1
        # \x escapes
        if ch == '\n': pass
        elif ch == '\\': builder.append(u'\\')
        elif ch == '\'': builder.append(u'\'')
        elif ch == '\"': builder.append(u'\"')
        elif ch == 'b' : builder.append(u'\b')
        elif ch == 'f' : builder.append(u'\f')
        elif ch == 't' : builder.append(u'\t')
        elif ch == 'n' : builder.append(u'\n')
        elif ch == 'r' : builder.append(u'\r')
        elif ch == 'v' : builder.append(u'\v')
        elif ch == 'a' : builder.append(u'\a')
        elif '0' <= ch <= '7':
            x = ord(ch) - ord('0')
            if pos < size:
                ch = s[pos]
                if '0' <= ch <= '7':
                    pos += 1
                    x = (x<<3) + ord(ch) - ord('0')
                    if pos < size:
                        ch = s[pos]
                        if '0' <= ch <= '7':
                            pos += 1
                            x = (x<<3) + ord(ch) - ord('0')
            builder.append(unichr(x))
        # hex escapes
        # \xXX
        elif ch == 'x':
            digits = 2
            message = "truncated \\xXX escape"
            pos = hexescape(builder, s, pos, digits,
                            "unicodeescape", errorhandler, message, errors)

        # \uXXXX
        elif ch == 'u':
            digits = 4
            message = "truncated \\uXXXX escape"
            pos = hexescape(builder, s, pos, digits,
                            "unicodeescape", errorhandler, message, errors)

        #  \UXXXXXXXX
        elif ch == 'U':
            digits = 8
            message = "truncated \\UXXXXXXXX escape"
            pos = hexescape(builder, s, pos, digits,
                            "unicodeescape", errorhandler, message, errors)

        # \N{name}
        elif ch == 'N':
            message = "malformed \\N character escape"
            look = pos
            if unicodedata_handler is None:
                message = ("\\N escapes not supported "
                           "(can't load unicodedata module)")
                res, pos = errorhandler(errors, "unicodeescape",
                                        message, s, pos-1, size)
                builder.append(res)
                continue

            if look < size and s[look] == '{':
                # look for the closing brace
                while look < size and s[look] != '}':
                    look += 1
                if look < size and s[look] == '}':
                    # found a name.  look it up in the unicode database
                    message = "unknown Unicode character name"
                    name = s[pos+1:look]
                    code = unicodedata_handler.call(name)
                    if code < 0:
                        res, pos = errorhandler(errors, "unicodeescape",
                                                message, s, pos-1, look+1)
                        builder.append(res)
                        continue
                    pos = look + 1
                    if code <= MAXUNICODE:
                        builder.append(UNICHR(code))
                    else:
                        code -= 0x10000L
                        builder.append(unichr(0xD800 + (code >> 10)))
                        builder.append(unichr(0xDC00 + (code & 0x03FF)))
                else:
                    res, pos = errorhandler(errors, "unicodeescape",
                                            message, s, pos-1, look+1)
                    builder.append(res)
            else:
                res, pos = errorhandler(errors, "unicodeescape",
                                        message, s, pos-1, look+1)
                builder.append(res)
        else:
            builder.append(u'\\')
            builder.append(unichr(ord(ch)))

    return builder.build(), pos

def make_unicode_escape_function(pass_printable=False, unicode_output=False,
                                 quotes=False, prefix=None):
    # Python3 has two similar escape functions: One to implement
    # encode('unicode_escape') and which outputs bytes, and unicode.__repr__
    # which outputs unicode.  They cannot share RPython code, so we generate
    # them with the template below.
    # Python2 does not really need this, but it reduces diffs between branches.

    if unicode_output:
        STRING_BUILDER = UnicodeBuilder
        STR = unicode
        CHR = UNICHR
    else:
        STRING_BUILDER = StringBuilder
        STR = str
        CHR = chr

    def unicode_escape(s, size, errors, errorhandler=None):
        # errorhandler is not used: this function cannot cause Unicode errors
        result = STRING_BUILDER(size)

        if quotes:
            if prefix:
                result.append(STR(prefix))
            if s.find(u'\'') != -1 and s.find(u'\"') == -1:
                quote = ord('\"')
                result.append(STR('"'))
            else:
                quote = ord('\'')
                result.append(STR('\''))
        else:
            quote = 0

            if size == 0:
                return STR('')

        pos = 0
        while pos < size:
            ch = s[pos]
            oc = ord(ch)

            # Escape quotes
            if quotes and (oc == quote or ch == '\\'):
                result.append(STR('\\'))
                result.append(CHR(oc))
                pos += 1
                continue

            # The following logic is enabled only if MAXUNICODE == 0xffff, or
            # for testing on top of a host Python where sys.maxunicode == 0xffff
            if ((MAXUNICODE < 65536 or
                    (not we_are_translated() and sys.maxunicode < 65536))
                and 0xD800 <= oc < 0xDC00 and pos + 1 < size):
                # Map UTF-16 surrogate pairs to Unicode \UXXXXXXXX escapes
                pos += 1
                oc2 = ord(s[pos])

                if 0xDC00 <= oc2 <= 0xDFFF:
                    ucs = (((oc & 0x03FF) << 10) | (oc2 & 0x03FF)) + 0x00010000
                    char_escape_helper(result, ucs)
                    pos += 1
                    continue
                # Fall through: isolated surrogates are copied as-is
                pos -= 1

            # Map special whitespace to '\t', \n', '\r'
            if ch == '\t':
                result.append(STR('\\t'))
            elif ch == '\n':
                result.append(STR('\\n'))
            elif ch == '\r':
                result.append(STR('\\r'))
            elif ch == '\\':
                result.append(STR('\\\\'))

            # Map non-printable or non-ascii to '\xhh' or '\uhhhh'
            elif pass_printable and not unicodedb.isprintable(oc):
                char_escape_helper(result, oc)
            elif not pass_printable and (oc < 32 or oc >= 0x7F):
                char_escape_helper(result, oc)

            # Copy everything else as-is
            else:
                result.append(CHR(oc))
            pos += 1

        if quotes:
            result.append(CHR(quote))
        return result.build()

    def char_escape_helper(result, char):
        num = hex(char)
        if STR is unicode:
            num = num.decode('ascii')
        if char >= 0x10000:
            result.append(STR("\\U"))
            zeros = 8
        elif char >= 0x100:
            result.append(STR("\\u"))
            zeros = 4
        else:
            result.append(STR("\\x"))
            zeros = 2
        lnum = len(num)
        nb = zeros + 2 - lnum # num starts with '0x'
        if nb > 0:
            result.append_multiple_char(STR('0'), nb)
        result.append_slice(num, 2, lnum)

    return unicode_escape, char_escape_helper

# This function is also used by _codecs/interp_codecs.py
(unicode_encode_unicode_escape, raw_unicode_escape_helper
 ) = make_unicode_escape_function()

# ____________________________________________________________
# Raw unicode escape

def str_decode_raw_unicode_escape(s, size, errors, final=False,
                                  errorhandler=None):
    if errorhandler is None:
        errorhandler = default_unicode_error_decode
    if size == 0:
        return u'', 0

    result = UnicodeBuilder(size)
    pos = 0
    while pos < size:
        ch = s[pos]

        # Non-escape characters are interpreted as Unicode ordinals
        if ch != '\\':
            result.append(unichr(ord(ch)))
            pos += 1
            continue

        # \u-escapes are only interpreted iff the number of leading
        # backslashes is odd
        bs = pos
        while pos < size:
            pos += 1
            if pos == size or s[pos] != '\\':
                break
            result.append(u'\\')

        # we have a backslash at the end of the string, stop here
        if pos >= size:
            result.append(u'\\')
            break

        if ((pos - bs) & 1 == 0 or
            pos >= size or
            (s[pos] != 'u' and s[pos] != 'U')):
            result.append(u'\\')
            result.append(unichr(ord(s[pos])))
            pos += 1
            continue

        if s[pos] == 'u':
            digits = 4
            message = "truncated \\uXXXX escape"
        else:
            digits = 8
            message = "truncated \\UXXXXXXXX escape"
        pos += 1
        pos = hexescape(result, s, pos, digits,
                        "rawunicodeescape", errorhandler, message, errors)

    return result.build(), pos

def unicode_encode_raw_unicode_escape(s, size, errors, errorhandler=None):
    # errorhandler is not used: this function cannot cause Unicode errors
    if size == 0:
        return ''
    result = StringBuilder(size)
    pos = 0
    while pos < size:
        oc = ord(s[pos])

        if MAXUNICODE < 65536 and 0xD800 <= oc < 0xDC00 and pos + 1 < size:
            # Map UTF-16 surrogate pairs to Unicode \UXXXXXXXX escapes
            pos += 1
            oc2 = ord(s[pos])

            if 0xDC00 <= oc2 <= 0xDFFF:
                ucs = (((oc & 0x03FF) << 10) | (oc2 & 0x03FF)) + 0x00010000
                raw_unicode_escape_helper(result, ucs)
                pos += 1
                continue
            # Fall through: isolated surrogates are copied as-is
            pos -= 1

        if oc < 0x100:
            result.append(chr(oc))
        else:
            raw_unicode_escape_helper(result, oc)
        pos += 1

    return result.build()

# ____________________________________________________________
# unicode-internal

def str_decode_unicode_internal(s, size, errors, final=False,
                                errorhandler=None):
    if errorhandler is None:
        errorhandler = default_unicode_error_decode
    if size == 0:
        return u'', 0

    if MAXUNICODE < 65536:
        unicode_bytes = 2
    else:
        unicode_bytes = 4
    if BYTEORDER == "little":
        start = 0
        stop = unicode_bytes
        step = 1
    else:
        start = unicode_bytes - 1
        stop = -1
        step = -1

    result = UnicodeBuilder(size // unicode_bytes)
    pos = 0
    while pos < size:
        if pos > size - unicode_bytes:
            res, pos = errorhandler(errors, "unicode_internal",
                                    "truncated input",
                                    s, pos, size)
            result.append(res)
            if pos > size - unicode_bytes:
                break
            continue
        t = r_uint(0)
        h = 0
        for j in range(start, stop, step):
            t += r_uint(ord(s[pos + j])) << (h*8)
            h += 1
        if t > MAXUNICODE:
            res, pos = errorhandler(errors, "unicode_internal",
                                    "unichr(%d) not in range" % (t,),
                                    s, pos, pos + unicode_bytes)
            result.append(res)
            continue
        result.append(UNICHR(t))
        pos += unicode_bytes
    return result.build(), pos

def unicode_encode_unicode_internal(s, size, errors, errorhandler=None):
    if size == 0:
        return ''

    if MAXUNICODE < 65536:
        unicode_bytes = 2
    else:
        unicode_bytes = 4

    result = StringBuilder(size * unicode_bytes)
    pos = 0
    while pos < size:
        oc = ord(s[pos])
        if MAXUNICODE < 65536:
            if BYTEORDER == "little":
                result.append(chr(oc       & 0xFF))
                result.append(chr(oc >>  8 & 0xFF))
            else:
                result.append(chr(oc >>  8 & 0xFF))
                result.append(chr(oc       & 0xFF))
        else:
            if BYTEORDER == "little":
                result.append(chr(oc       & 0xFF))
                result.append(chr(oc >>  8 & 0xFF))
                result.append(chr(oc >> 16 & 0xFF))
                result.append(chr(oc >> 24 & 0xFF))
            else:
                result.append(chr(oc >> 24 & 0xFF))
                result.append(chr(oc >> 16 & 0xFF))
                result.append(chr(oc >>  8 & 0xFF))
                result.append(chr(oc       & 0xFF))
        pos += 1

    return result.build()

# ____________________________________________________________
# MBCS codecs for Windows

if sys.platform == 'win32':
    from pypy.rpython.lltypesystem import lltype, rffi
    from pypy.rlib import rwin32
    CP_ACP = 0

    MultiByteToWideChar = rffi.llexternal('MultiByteToWideChar',
                                          [rffi.UINT, rwin32.DWORD,
                                           rwin32.LPCSTR, rffi.INT,
                                           rffi.CWCHARP, rffi.INT],
                                          rffi.INT,
                                          calling_conv='win')

    WideCharToMultiByte = rffi.llexternal('WideCharToMultiByte',
                                          [rffi.UINT, rwin32.DWORD,
                                           rffi.CWCHARP, rffi.INT,
                                           rwin32.LPCSTR, rffi.INT,
                                           rwin32.LPCSTR, rffi.VOIDP],
                                          rffi.INT,
                                          calling_conv='win')

    def is_dbcs_lead_byte(c):
        # XXX don't know how to test this
        return False

    def str_decode_mbcs(s, size, errors, final=False,
                        errorhandler=None):
        if size == 0:
            return u"", 0

        if errorhandler is None:
            errorhandler = default_unicode_error_decode

        # Skip trailing lead-byte unless 'final' is set
        if not final and is_dbcs_lead_byte(s[size-1]):
            size -= 1

        dataptr = rffi.get_nonmovingbuffer(s)
        try:
            # first get the size of the result
            usize = MultiByteToWideChar(CP_ACP, 0,
                                        dataptr, size,
                                        lltype.nullptr(rffi.CWCHARP.TO), 0)
            if usize == 0:
                raise rwin32.lastWindowsError()

            raw_buf, gc_buf = rffi.alloc_unicodebuffer(usize)
            try:
                # do the conversion
                if MultiByteToWideChar(CP_ACP, 0,
                                       dataptr, size, raw_buf, usize) == 0:
                    raise rwin32.lastWindowsError()

                return (rffi.unicode_from_buffer(raw_buf, gc_buf, usize, usize),
                        size)
            finally:
                rffi.keep_unicodebuffer_alive_until_here(raw_buf, gc_buf)
        finally:
            rffi.free_nonmovingbuffer(s, dataptr)

    def unicode_encode_mbcs(p, size, errors, errorhandler=None):
        if size == 0:
            return ''
        dataptr = rffi.get_nonmoving_unicodebuffer(p)
        try:
            # first get the size of the result
            mbcssize = WideCharToMultiByte(CP_ACP, 0,
                                           dataptr, size, None, 0,
                                           None, None)
            if mbcssize == 0:
                raise rwin32.lastWindowsError()

            raw_buf, gc_buf = rffi.alloc_buffer(mbcssize)
            try:
                # do the conversion
                if WideCharToMultiByte(CP_ACP, 0,
                                       dataptr, size, raw_buf, mbcssize,
                                       None, None) == 0:
                    raise rwin32.lastWindowsError()

                return rffi.str_from_buffer(raw_buf, gc_buf, mbcssize, mbcssize)
            finally:
                rffi.keep_buffer_alive_until_here(raw_buf, gc_buf)
        finally:
            rffi.free_nonmoving_unicodebuffer(p, dataptr)

# ____________________________________________________________
# Decimal Encoder
def unicode_encode_decimal(s, size, errors, errorhandler=None):
    """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.
    """
    if errorhandler is None:
        errorhandler = default_unicode_error_encode
    if size == 0:
        return ''
    result = StringBuilder(size)
    pos = 0
    while pos < size:
        ch = ord(s[pos])
        if unicodedb.isspace(ch):
            result.append(' ')
            pos += 1
            continue
        try:
            decimal = unicodedb.decimal(ch)
        except KeyError:
            pass
        else:
            result.append(chr(48 + decimal))
            pos += 1
            continue
        if 0 < ch < 256:
            result.append(chr(ch))
            pos += 1
            continue
        # All other characters are considered unencodable
        collstart = pos
        collend = collstart + 1
        while collend < size:
            ch = ord(s[collend])
            try:
                if (0 < ch < 256 or
                    unicodedb.isspace(ch) or
                    unicodedb.decimal(ch) >= 0):
                    break
            except KeyError:
                # not a decimal
                pass
            collend += 1
        msg = "invalid decimal Unicode string"
        ru, rs, pos = errorhandler(errors, 'decimal',
                                   msg, s, collstart, collend)
        if rs is not None:
            # py3k only
            errorhandler('strict', 'decimal', msg, s, collstart, collend)
        for char in ru:
            ch = ord(char)
            if unicodedb.isspace(ch):
                result.append(' ')
                continue
            try:
                decimal = unicodedb.decimal(ch)
            except KeyError:
                pass
            else:
                result.append(chr(48 + decimal))
                continue
            if 0 < ch < 256:
                result.append(chr(ch))
                continue
            errorhandler('strict', 'decimal',
                         msg, s, collstart, collend)
    return result.build()
Tip: Filter by directory path e.g. /media app.js to search for public/media/app.js.
Tip: Use camelCasing e.g. ProjME to search for ProjectModifiedEvent.java.
Tip: Filter by extension type e.g. /repo .js to search for all .js files in the /repo directory.
Tip: Separate your search with spaces e.g. /ssh pom.xml to search for src/ssh/pom.xml.
Tip: Use ↑ and ↓ arrow keys to navigate and return to view the file.
Tip: You can also navigate files with Ctrl+j (next) and Ctrl+k (previous) and view the file with Ctrl+o.
Tip: You can also navigate files with Alt+j (next) and Alt+k (previous) and view the file with Alt+o.