pypy /pypy/objspace/std/unicodeobject.py

Language Python Lines 1146
MD5 Hash 96150e2b429e92309e2a554d1d76733c Estimated Cost $17,965 (why?)
Repository https://bitbucket.org/pypy/pypy/ View Raw File View Project SPDX
   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
"""The builtin unicode implementation"""

from rpython.rlib.objectmodel import (
    compute_hash, compute_unique_id, import_from_mixin)
from rpython.rlib.buffer import StringBuffer
from rpython.rlib.rstring import StringBuilder, UnicodeBuilder
from rpython.rlib.runicode import (
    make_unicode_escape_function, str_decode_ascii, str_decode_utf_8,
    unicode_encode_ascii, unicode_encode_utf_8, fast_str_decode_ascii)

from pypy.interpreter import unicodehelper
from pypy.interpreter.baseobjspace import W_Root
from pypy.interpreter.error import OperationError, oefmt
from pypy.interpreter.gateway import WrappedDefault, interp2app, unwrap_spec
from pypy.interpreter.typedef import TypeDef
from pypy.module.unicodedata import unicodedb
from pypy.objspace.std import newformat
from pypy.objspace.std.basestringtype import basestring_typedef
from pypy.objspace.std.formatting import mod_format
from pypy.objspace.std.stringmethods import StringMethods
from pypy.objspace.std.util import IDTAG_SPECIAL, IDTAG_SHIFT

__all__ = ['W_UnicodeObject', 'wrapunicode', 'plain_str2unicode',
           'encode_object', 'decode_object', 'unicode_from_object',
           'unicode_from_string', 'unicode_to_decimal_w']


class W_UnicodeObject(W_Root):
    import_from_mixin(StringMethods)
    _immutable_fields_ = ['_value']

    def __init__(self, unistr):
        assert isinstance(unistr, unicode)
        self._value = unistr

    def __repr__(self):
        """representation for debugging purposes"""
        return "%s(%r)" % (self.__class__.__name__, self._value)

    def unwrap(self, space):
        # for testing
        return self._value

    def create_if_subclassed(self):
        if type(self) is W_UnicodeObject:
            return self
        return W_UnicodeObject(self._value)

    def is_w(self, space, w_other):
        if not isinstance(w_other, W_UnicodeObject):
            return False
        if self is w_other:
            return True
        if self.user_overridden_class or w_other.user_overridden_class:
            return False
        s1 = space.unicode_w(self)
        s2 = space.unicode_w(w_other)
        if len(s2) > 1:
            return s1 is s2
        else:            # strings of len <= 1 are unique-ified
            return s1 == s2

    def immutable_unique_id(self, space):
        if self.user_overridden_class:
            return None
        s = space.unicode_w(self)
        if len(s) > 1:
            uid = compute_unique_id(s)
        else:            # strings of len <= 1 are unique-ified
            if len(s) == 1:
                base = ~ord(s[0])      # negative base values
            else:
                base = 257       # empty unicode string: base value 257
            uid = (base << IDTAG_SHIFT) | IDTAG_SPECIAL
        return space.wrap(uid)

    def str_w(self, space):
        return space.str_w(space.str(self))

    def unicode_w(self, space):
        return self._value

    def readbuf_w(self, space):
        from rpython.rlib.rstruct.unichar import pack_unichar, UNICODE_SIZE
        builder = StringBuilder(len(self._value) * UNICODE_SIZE)
        for unich in self._value:
            pack_unichar(unich, builder)
        return StringBuffer(builder.build())

    def writebuf_w(self, space):
        raise oefmt(space.w_TypeError,
                    "cannot use unicode as modifiable buffer")

    charbuf_w = str_w

    def listview_unicode(self):
        return _create_list_from_unicode(self._value)

    def ord(self, space):
        if len(self._value) != 1:
            raise oefmt(space.w_TypeError,
                         "ord() expected a character, but string of length %d "
                         "found", len(self._value))
        return space.wrap(ord(self._value[0]))

    def _new(self, value):
        return W_UnicodeObject(value)

    def _new_from_list(self, value):
        return W_UnicodeObject(u''.join(value))

    def _empty(self):
        return W_UnicodeObject.EMPTY

    def _len(self):
        return len(self._value)

    _val = unicode_w

    @staticmethod
    def _use_rstr_ops(space, w_other):
        # Always return true because we always need to copy the other
        # operand(s) before we can do comparisons
        return True

    @staticmethod
    def _op_val(space, w_other):
        if isinstance(w_other, W_UnicodeObject):
            return w_other._value
        if space.isinstance_w(w_other, space.w_str):
            return unicode_from_string(space, w_other)._value
        return unicode_from_encoded_object(
            space, w_other, None, "strict")._value

    def _chr(self, char):
        assert len(char) == 1
        return unicode(char)[0]

    _builder = UnicodeBuilder

    def _isupper(self, ch):
        return unicodedb.isupper(ord(ch))

    def _islower(self, ch):
        return unicodedb.islower(ord(ch))

    def _isnumeric(self, ch):
        return unicodedb.isnumeric(ord(ch))

    def _istitle(self, ch):
        return unicodedb.isupper(ord(ch)) or unicodedb.istitle(ord(ch))

    def _isspace(self, ch):
        return unicodedb.isspace(ord(ch))

    def _isalpha(self, ch):
        return unicodedb.isalpha(ord(ch))

    def _isalnum(self, ch):
        return unicodedb.isalnum(ord(ch))

    def _isdigit(self, ch):
        return unicodedb.isdigit(ord(ch))

    def _isdecimal(self, ch):
        return unicodedb.isdecimal(ord(ch))

    def _iscased(self, ch):
        return unicodedb.iscased(ord(ch))

    def _islinebreak(self, ch):
        return unicodedb.islinebreak(ord(ch))

    def _upper(self, ch):
        return unichr(unicodedb.toupper(ord(ch)))

    def _lower(self, ch):
        return unichr(unicodedb.tolower(ord(ch)))

    def _title(self, ch):
        return unichr(unicodedb.totitle(ord(ch)))

    def _newlist_unwrapped(self, space, lst):
        return space.newlist_unicode(lst)

    @staticmethod
    @unwrap_spec(w_string=WrappedDefault(""))
    def descr_new(space, w_unicodetype, w_string, w_encoding=None,
                  w_errors=None):
        # NB. the default value of w_obj is really a *wrapped* empty string:
        #     there is gateway magic at work
        w_obj = w_string

        encoding, errors = _get_encoding_and_errors(space, w_encoding,
                                                    w_errors)
        # convoluted logic for the case when unicode subclass has a __unicode__
        # method, we need to call this method
        is_precisely_unicode = space.is_w(space.type(w_obj), space.w_unicode)
        if (is_precisely_unicode or
            (space.isinstance_w(w_obj, space.w_unicode) and
             space.findattr(w_obj, space.wrap('__unicode__')) is None)):
            if encoding is not None or errors is not None:
                raise oefmt(space.w_TypeError,
                            "decoding Unicode is not supported")
            if (is_precisely_unicode and
                space.is_w(w_unicodetype, space.w_unicode)):
                return w_obj
            w_value = w_obj
        else:
            if encoding is None and errors is None:
                w_value = unicode_from_object(space, w_obj)
            else:
                w_value = unicode_from_encoded_object(space, w_obj,
                                                      encoding, errors)
            if space.is_w(w_unicodetype, space.w_unicode):
                return w_value

        assert isinstance(w_value, W_UnicodeObject)
        w_newobj = space.allocate_instance(W_UnicodeObject, w_unicodetype)
        W_UnicodeObject.__init__(w_newobj, w_value._value)
        return w_newobj

    def descr_repr(self, space):
        chars = self._value
        size = len(chars)
        s = _repr_function(chars, size, "strict")
        return space.wrap(s)

    def descr_str(self, space):
        return encode_object(space, self, None, None)

    def descr_hash(self, space):
        x = compute_hash(self._value)
        return space.wrap(x)

    def descr_eq(self, space, w_other):
        try:
            res = self._val(space) == self._op_val(space, w_other)
        except OperationError as e:
            if e.match(space, space.w_TypeError):
                return space.w_NotImplemented
            if (e.match(space, space.w_UnicodeDecodeError) or
                e.match(space, space.w_UnicodeEncodeError)):
                msg = ("Unicode equal comparison failed to convert both "
                       "arguments to Unicode - interpreting them as being "
                       "unequal")
                space.warn(space.wrap(msg), space.w_UnicodeWarning)
                return space.w_False
            raise
        return space.newbool(res)

    def descr_ne(self, space, w_other):
        try:
            res = self._val(space) != self._op_val(space, w_other)
        except OperationError as e:
            if e.match(space, space.w_TypeError):
                return space.w_NotImplemented
            if (e.match(space, space.w_UnicodeDecodeError) or
                e.match(space, space.w_UnicodeEncodeError)):
                msg = ("Unicode unequal comparison failed to convert both "
                       "arguments to Unicode - interpreting them as being "
                       "unequal")
                space.warn(space.wrap(msg), space.w_UnicodeWarning)
                return space.w_True
            raise
        return space.newbool(res)

    def descr_lt(self, space, w_other):
        try:
            res = self._val(space) < self._op_val(space, w_other)
        except OperationError as e:
            if e.match(space, space.w_TypeError):
                return space.w_NotImplemented
            raise
        return space.newbool(res)

    def descr_le(self, space, w_other):
        try:
            res = self._val(space) <= self._op_val(space, w_other)
        except OperationError as e:
            if e.match(space, space.w_TypeError):
                return space.w_NotImplemented
            raise
        return space.newbool(res)

    def descr_gt(self, space, w_other):
        try:
            res = self._val(space) > self._op_val(space, w_other)
        except OperationError as e:
            if e.match(space, space.w_TypeError):
                return space.w_NotImplemented
            raise
        return space.newbool(res)

    def descr_ge(self, space, w_other):
        try:
            res = self._val(space) >= self._op_val(space, w_other)
        except OperationError as e:
            if e.match(space, space.w_TypeError):
                return space.w_NotImplemented
            raise
        return space.newbool(res)

    def descr_format(self, space, __args__):
        return newformat.format_method(space, self, __args__, is_unicode=True)

    def descr__format__(self, space, w_format_spec):
        if not space.isinstance_w(w_format_spec, space.w_unicode):
            w_format_spec = space.call_function(space.w_unicode, w_format_spec)
        spec = space.unicode_w(w_format_spec)
        formatter = newformat.unicode_formatter(space, spec)
        self2 = unicode_from_object(space, self)
        assert isinstance(self2, W_UnicodeObject)
        return formatter.format_string(self2._value)

    def descr_mod(self, space, w_values):
        return mod_format(space, self, w_values, do_unicode=True)

    def descr_translate(self, space, w_table):
        selfvalue = self._value
        w_sys = space.getbuiltinmodule('sys')
        maxunicode = space.int_w(space.getattr(w_sys,
                                               space.wrap("maxunicode")))
        result = []
        for unichar in selfvalue:
            try:
                w_newval = space.getitem(w_table, space.wrap(ord(unichar)))
            except OperationError as e:
                if e.match(space, space.w_LookupError):
                    result.append(unichar)
                else:
                    raise
            else:
                if space.is_w(w_newval, space.w_None):
                    continue
                elif space.isinstance_w(w_newval, space.w_int):
                    newval = space.int_w(w_newval)
                    if newval < 0 or newval > maxunicode:
                        raise oefmt(space.w_TypeError,
                                    "character mapping must be in range(%s)",
                                    hex(maxunicode + 1))
                    result.append(unichr(newval))
                elif space.isinstance_w(w_newval, space.w_unicode):
                    result.append(space.unicode_w(w_newval))
                else:
                    raise oefmt(space.w_TypeError,
                                "character mapping must return integer, None "
                                "or unicode")
        return W_UnicodeObject(u''.join(result))

    def descr_encode(self, space, w_encoding=None, w_errors=None):
        encoding, errors = _get_encoding_and_errors(space, w_encoding,
                                                    w_errors)
        return encode_object(space, self, encoding, errors)

    _StringMethods_descr_join = descr_join
    def descr_join(self, space, w_list):
        l = space.listview_unicode(w_list)
        if l is not None:
            if len(l) == 1:
                return space.wrap(l[0])
            return space.wrap(self._val(space).join(l))
        return self._StringMethods_descr_join(space, w_list)

    def _join_return_one(self, space, w_obj):
        return space.is_w(space.type(w_obj), space.w_unicode)

    def _join_check_item(self, space, w_obj):
        if (space.isinstance_w(w_obj, space.w_str) or
            space.isinstance_w(w_obj, space.w_unicode)):
            return 0
        return 1

    def descr_formatter_parser(self, space):
        from pypy.objspace.std.newformat import unicode_template_formatter
        tformat = unicode_template_formatter(space, space.unicode_w(self))
        return tformat.formatter_parser()

    def descr_formatter_field_name_split(self, space):
        from pypy.objspace.std.newformat import unicode_template_formatter
        tformat = unicode_template_formatter(space, space.unicode_w(self))
        return tformat.formatter_field_name_split()

    def descr_isdecimal(self, space):
        return self._is_generic(space, '_isdecimal')

    def descr_isnumeric(self, space):
        return self._is_generic(space, '_isnumeric')

    def descr_islower(self, space):
        cased = False
        for uchar in self._value:
            if (unicodedb.isupper(ord(uchar)) or
                unicodedb.istitle(ord(uchar))):
                return space.w_False
            if not cased and unicodedb.islower(ord(uchar)):
                cased = True
        return space.newbool(cased)

    def descr_isupper(self, space):
        cased = False
        for uchar in self._value:
            if (unicodedb.islower(ord(uchar)) or
                unicodedb.istitle(ord(uchar))):
                return space.w_False
            if not cased and unicodedb.isupper(ord(uchar)):
                cased = True
        return space.newbool(cased)

    def _starts_ends_overflow(self, prefix):
        return len(prefix) == 0


def wrapunicode(space, uni):
    return W_UnicodeObject(uni)


def plain_str2unicode(space, s):
    try:
        return unicode(s)
    except UnicodeDecodeError:
        for i in range(len(s)):
            if ord(s[i]) > 127:
                raise OperationError(
                    space.w_UnicodeDecodeError,
                    space.newtuple([
                    space.wrap('ascii'),
                    space.wrap(s),
                    space.wrap(i),
                    space.wrap(i+1),
                    space.wrap("ordinal not in range(128)")]))
        assert False, "unreachable"


# stuff imported from bytesobject for interoperability


# ____________________________________________________________

def getdefaultencoding(space):
    return space.sys.defaultencoding


def _get_encoding_and_errors(space, w_encoding, w_errors):
    encoding = None if w_encoding is None else space.str_w(w_encoding)
    errors = None if w_errors is None else space.str_w(w_errors)
    return encoding, errors


def encode_object(space, w_object, encoding, errors):
    if encoding is None:
        # Get the encoder functions as a wrapped object.
        # This lookup is cached.
        w_encoder = space.sys.get_w_default_encoder()
    else:
        if errors is None or errors == 'strict':
            try:
                if encoding == 'ascii':
                    u = space.unicode_w(w_object)
                    eh = unicodehelper.raise_unicode_exception_encode
                    return space.wrap(unicode_encode_ascii(
                            u, len(u), None, errorhandler=eh))
                if encoding == 'utf-8':
                    u = space.unicode_w(w_object)
                    eh = unicodehelper.raise_unicode_exception_encode
                    return space.wrap(unicode_encode_utf_8(
                            u, len(u), None, errorhandler=eh,
                            allow_surrogates=True))
            except unicodehelper.RUnicodeEncodeError as ue:
                raise OperationError(space.w_UnicodeEncodeError,
                                     space.newtuple([
                    space.wrap(ue.encoding),
                    space.wrap(ue.object),
                    space.wrap(ue.start),
                    space.wrap(ue.end),
                    space.wrap(ue.reason)]))
        from pypy.module._codecs.interp_codecs import lookup_codec
        w_encoder = space.getitem(lookup_codec(space, encoding), space.wrap(0))
    if errors is None:
        w_errors = space.wrap('strict')
    else:
        w_errors = space.wrap(errors)
    w_restuple = space.call_function(w_encoder, w_object, w_errors)
    w_retval = space.getitem(w_restuple, space.wrap(0))
    if not space.isinstance_w(w_retval, space.w_str):
        raise oefmt(space.w_TypeError,
                    "encoder did not return an string object (type '%T')",
                    w_retval)
    return w_retval


def decode_object(space, w_obj, encoding, errors):
    if encoding is None:
        encoding = getdefaultencoding(space)
    if errors is None or errors == 'strict':
        if encoding == 'ascii':
            # XXX error handling
            s = space.charbuf_w(w_obj)
            try:
                u = fast_str_decode_ascii(s)
            except ValueError:
                eh = unicodehelper.decode_error_handler(space)
                u = str_decode_ascii(     # try again, to get the error right
                    s, len(s), None, final=True, errorhandler=eh)[0]
            return space.wrap(u)
        if encoding == 'utf-8':
            s = space.charbuf_w(w_obj)
            eh = unicodehelper.decode_error_handler(space)
            return space.wrap(str_decode_utf_8(
                    s, len(s), None, final=True, errorhandler=eh,
                    allow_surrogates=True)[0])
    w_codecs = space.getbuiltinmodule("_codecs")
    w_decode = space.getattr(w_codecs, space.wrap("decode"))
    if errors is None:
        w_retval = space.call_function(w_decode, w_obj, space.wrap(encoding))
    else:
        w_retval = space.call_function(w_decode, w_obj, space.wrap(encoding),
                                       space.wrap(errors))
    return w_retval


def unicode_from_encoded_object(space, w_obj, encoding, errors):
    # explicitly block bytearray on 2.7
    from .bytearrayobject import W_BytearrayObject
    if isinstance(w_obj, W_BytearrayObject):
        raise oefmt(space.w_TypeError, "decoding bytearray is not supported")

    w_retval = decode_object(space, w_obj, encoding, errors)
    if not space.isinstance_w(w_retval, space.w_unicode):
        raise oefmt(space.w_TypeError,
                    "decoder did not return an unicode object (type '%T')",
                    w_retval)
    assert isinstance(w_retval, W_UnicodeObject)
    return w_retval


def unicode_from_object(space, w_obj):
    if space.is_w(space.type(w_obj), space.w_unicode):
        return w_obj
    elif space.is_w(space.type(w_obj), space.w_str):
        w_res = w_obj
    else:
        w_unicode_method = space.lookup(w_obj, "__unicode__")
        # obscure workaround: for the next two lines see
        # test_unicode_conversion_with__str__
        if w_unicode_method is None:
            if space.isinstance_w(w_obj, space.w_unicode):
                return space.wrap(space.unicode_w(w_obj))
            w_unicode_method = space.lookup(w_obj, "__str__")
        if w_unicode_method is not None:
            w_res = space.get_and_call_function(w_unicode_method, w_obj)
        else:
            w_res = space.str(w_obj)
        if space.isinstance_w(w_res, space.w_unicode):
            return w_res
    return unicode_from_encoded_object(space, w_res, None, "strict")


def unicode_from_string(space, w_str):
    # this is a performance and bootstrapping hack
    encoding = getdefaultencoding(space)
    if encoding != 'ascii':
        return unicode_from_encoded_object(space, w_str, encoding, "strict")
    s = space.str_w(w_str)
    try:
        return W_UnicodeObject(s.decode("ascii"))
    except UnicodeDecodeError:
        # raising UnicodeDecodeError is messy, "please crash for me"
        return unicode_from_encoded_object(space, w_str, "ascii", "strict")


class UnicodeDocstrings:
    """unicode(object='') -> unicode object
    unicode(string[, encoding[, errors]]) -> unicode object

    Create a new Unicode object from the given encoded string.
    encoding defaults to the current default string encoding.
    errors can be 'strict', 'replace' or 'ignore' and defaults to 'strict'.

    """

    def __add__():
        """x.__add__(y) <==> x+y"""

    def __contains__():
        """x.__contains__(y) <==> y in x"""

    def __eq__():
        """x.__eq__(y) <==> x==y"""

    def __format__():
        """S.__format__(format_spec) -> unicode

        Return a formatted version of S as described by format_spec.
        """

    def __ge__():
        """x.__ge__(y) <==> x>=y"""

    def __getattribute__():
        """x.__getattribute__('name') <==> x.name"""

    def __getitem__():
        """x.__getitem__(y) <==> x[y]"""

    def __getnewargs__():
        ""

    def __getslice__():
        """x.__getslice__(i, j) <==> x[i:j]

        Use of negative indices is not supported.
        """

    def __gt__():
        """x.__gt__(y) <==> x>y"""

    def __hash__():
        """x.__hash__() <==> hash(x)"""

    def __le__():
        """x.__le__(y) <==> x<=y"""

    def __len__():
        """x.__len__() <==> len(x)"""

    def __lt__():
        """x.__lt__(y) <==> x<y"""

    def __mod__():
        """x.__mod__(y) <==> x%y"""

    def __mul__():
        """x.__mul__(n) <==> x*n"""

    def __ne__():
        """x.__ne__(y) <==> x!=y"""

    def __repr__():
        """x.__repr__() <==> repr(x)"""

    def __rmod__():
        """x.__rmod__(y) <==> y%x"""

    def __rmul__():
        """x.__rmul__(n) <==> n*x"""

    def __sizeof__():
        """S.__sizeof__() -> size of S in memory, in bytes"""

    def __str__():
        """x.__str__() <==> str(x)"""

    def capitalize():
        """S.capitalize() -> unicode

        Return a capitalized version of S, i.e. make the first character
        have upper case and the rest lower case.
        """

    def center():
        """S.center(width[, fillchar]) -> unicode

        Return S centered in a Unicode string of length width. Padding is
        done using the specified fill character (default is a space).
        """

    def count():
        """S.count(sub[, start[, end]]) -> int

        Return the number of non-overlapping occurrences of substring sub in
        Unicode string S[start:end].  Optional arguments start and end are
        interpreted as in slice notation.
        """

    def decode():
        """S.decode(encoding=None, errors='strict') -> string or unicode

        Decode S using the codec registered for encoding. encoding defaults
        to the default encoding. errors may be given to set a different error
        handling scheme. Default is 'strict' meaning that encoding errors raise
        a UnicodeDecodeError. Other possible values are 'ignore' and 'replace'
        as well as any other name registered with codecs.register_error that is
        able to handle UnicodeDecodeErrors.
        """

    def encode():
        """S.encode(encoding=None, errors='strict') -> string or unicode

        Encode S using the codec registered for encoding. encoding defaults
        to the default encoding. errors may be given to set a different error
        handling scheme. Default is 'strict' meaning that encoding errors raise
        a UnicodeEncodeError. Other possible values are 'ignore', 'replace' and
        'xmlcharrefreplace' as well as any other name registered with
        codecs.register_error that can handle UnicodeEncodeErrors.
        """

    def endswith():
        """S.endswith(suffix[, start[, end]]) -> bool

        Return True if S ends with the specified suffix, False otherwise.
        With optional start, test S beginning at that position.
        With optional end, stop comparing S at that position.
        suffix can also be a tuple of strings to try.
        """

    def expandtabs():
        """S.expandtabs([tabsize]) -> unicode

        Return a copy of S where all tab characters are expanded using spaces.
        If tabsize is not given, a tab size of 8 characters is assumed.
        """

    def find():
        """S.find(sub[, start[, end]]) -> int

        Return the lowest index in S where substring sub is found,
        such that sub is contained within S[start:end].  Optional
        arguments start and end are interpreted as in slice notation.

        Return -1 on failure.
        """

    def format():
        """S.format(*args, **kwargs) -> unicode

        Return a formatted version of S, using substitutions from args and
        kwargs.  The substitutions are identified by braces ('{' and '}').
        """

    def index():
        """S.index(sub[, start[, end]]) -> int

        Like S.find() but raise ValueError when the substring is not found.
        """

    def isalnum():
        """S.isalnum() -> bool

        Return True if all characters in S are alphanumeric
        and there is at least one character in S, False otherwise.
        """

    def isalpha():
        """S.isalpha() -> bool

        Return True if all characters in S are alphabetic
        and there is at least one character in S, False otherwise.
        """

    def isdecimal():
        """S.isdecimal() -> bool

        Return True if there are only decimal characters in S,
        False otherwise.
        """

    def isdigit():
        """S.isdigit() -> bool

        Return True if all characters in S are digits
        and there is at least one character in S, False otherwise.
        """

    def islower():
        """S.islower() -> bool

        Return True if all cased characters in S are lowercase and there is
        at least one cased character in S, False otherwise.
        """

    def isnumeric():
        """S.isnumeric() -> bool

        Return True if there are only numeric characters in S,
        False otherwise.
        """

    def isspace():
        """S.isspace() -> bool

        Return True if all characters in S are whitespace
        and there is at least one character in S, False otherwise.
        """

    def istitle():
        """S.istitle() -> bool

        Return True if S is a titlecased string and there is at least one
        character in S, i.e. upper- and titlecase characters may only
        follow uncased characters and lowercase characters only cased ones.
        Return False otherwise.
        """

    def isupper():
        """S.isupper() -> bool

        Return True if all cased characters in S are uppercase and there is
        at least one cased character in S, False otherwise.
        """

    def join():
        """S.join(iterable) -> unicode

        Return a string which is the concatenation of the strings in the
        iterable.  The separator between elements is S.
        """

    def ljust():
        """S.ljust(width[, fillchar]) -> int

        Return S left-justified in a Unicode string of length width. Padding is
        done using the specified fill character (default is a space).
        """

    def lower():
        """S.lower() -> unicode

        Return a copy of the string S converted to lowercase.
        """

    def lstrip():
        """S.lstrip([chars]) -> unicode

        Return a copy of the string S with leading whitespace removed.
        If chars is given and not None, remove characters in chars instead.
        If chars is a str, it will be converted to unicode before stripping
        """

    def partition():
        """S.partition(sep) -> (head, sep, tail)

        Search for the separator sep in S, and return the part before it,
        the separator itself, and the part after it.  If the separator is not
        found, return S and two empty strings.
        """

    def replace():
        """S.replace(old, new[, count]) -> unicode

        Return a copy of S with all occurrences of substring
        old replaced by new.  If the optional argument count is
        given, only the first count occurrences are replaced.
        """

    def rfind():
        """S.rfind(sub[, start[, end]]) -> int

        Return the highest index in S where substring sub is found,
        such that sub is contained within S[start:end].  Optional
        arguments start and end are interpreted as in slice notation.

        Return -1 on failure.
        """

    def rindex():
        """S.rindex(sub[, start[, end]]) -> int

        Like S.rfind() but raise ValueError when the substring is not found.
        """

    def rjust():
        """S.rjust(width[, fillchar]) -> unicode

        Return S right-justified in a Unicode string of length width. Padding
        is done using the specified fill character (default is a space).
        """

    def rpartition():
        """S.rpartition(sep) -> (head, sep, tail)

        Search for the separator sep in S, starting at the end of S, and return
        the part before it, the separator itself, and the part after it.  If
        the separator is not found, return two empty strings and S.
        """

    def rsplit():
        """S.rsplit(sep=None, maxsplit=-1) -> list of strings

        Return a list of the words in S, using sep as the
        delimiter string, starting at the end of the string and
        working to the front.  If maxsplit is given, at most maxsplit
        splits are done. If sep is not specified, any whitespace string
        is a separator.
        """

    def rstrip():
        """S.rstrip([chars]) -> unicode

        Return a copy of the string S with trailing whitespace removed.
        If chars is given and not None, remove characters in chars instead.
        If chars is a str, it will be converted to unicode before stripping
        """

    def split():
        """S.split(sep=None, maxsplit=-1) -> list of strings

        Return a list of the words in S, using sep as the
        delimiter string.  If maxsplit is given, at most maxsplit
        splits are done. If sep is not specified or is None, any
        whitespace string is a separator and empty strings are
        removed from the result.
        """

    def splitlines():
        """S.splitlines(keepends=False) -> list of strings

        Return a list of the lines in S, breaking at line boundaries.
        Line breaks are not included in the resulting list unless keepends
        is given and true.
        """

    def startswith():
        """S.startswith(prefix[, start[, end]]) -> bool

        Return True if S starts with the specified prefix, False otherwise.
        With optional start, test S beginning at that position.
        With optional end, stop comparing S at that position.
        prefix can also be a tuple of strings to try.
        """

    def strip():
        """S.strip([chars]) -> unicode

        Return a copy of the string S with leading and trailing
        whitespace removed.
        If chars is given and not None, remove characters in chars instead.
        If chars is a str, it will be converted to unicode before stripping
        """

    def swapcase():
        """S.swapcase() -> unicode

        Return a copy of S with uppercase characters converted to lowercase
        and vice versa.
        """

    def title():
        """S.title() -> unicode

        Return a titlecased version of S, i.e. words start with title case
        characters, all remaining cased characters have lower case.
        """

    def translate():
        """S.translate(table) -> unicode

        Return a copy of the string S, where all characters have been mapped
        through the given translation table, which must be a mapping of
        Unicode ordinals to Unicode ordinals, Unicode strings or None.
        Unmapped characters are left untouched. Characters mapped to None
        are deleted.
        """

    def upper():
        """S.upper() -> unicode

        Return a copy of S converted to uppercase.
        """

    def zfill():
        """S.zfill(width) -> unicode

        Pad a numeric string S with zeros on the left, to fill a field
        of the specified width. The string S is never truncated.
        """


W_UnicodeObject.typedef = TypeDef(
    "unicode", basestring_typedef,
    __new__ = interp2app(W_UnicodeObject.descr_new),
    __doc__ = UnicodeDocstrings.__doc__,

    __repr__ = interp2app(W_UnicodeObject.descr_repr,
                          doc=UnicodeDocstrings.__repr__.__doc__),
    __str__ = interp2app(W_UnicodeObject.descr_str,
                         doc=UnicodeDocstrings.__str__.__doc__),
    __hash__ = interp2app(W_UnicodeObject.descr_hash,
                          doc=UnicodeDocstrings.__hash__.__doc__),

    __eq__ = interp2app(W_UnicodeObject.descr_eq,
                        doc=UnicodeDocstrings.__eq__.__doc__),
    __ne__ = interp2app(W_UnicodeObject.descr_ne,
                        doc=UnicodeDocstrings.__ne__.__doc__),
    __lt__ = interp2app(W_UnicodeObject.descr_lt,
                        doc=UnicodeDocstrings.__lt__.__doc__),
    __le__ = interp2app(W_UnicodeObject.descr_le,
                        doc=UnicodeDocstrings.__le__.__doc__),
    __gt__ = interp2app(W_UnicodeObject.descr_gt,
                        doc=UnicodeDocstrings.__gt__.__doc__),
    __ge__ = interp2app(W_UnicodeObject.descr_ge,
                        doc=UnicodeDocstrings.__ge__.__doc__),

    __len__ = interp2app(W_UnicodeObject.descr_len,
                         doc=UnicodeDocstrings.__len__.__doc__),
    __contains__ = interp2app(W_UnicodeObject.descr_contains,
                              doc=UnicodeDocstrings.__contains__.__doc__),

    __add__ = interp2app(W_UnicodeObject.descr_add,
                         doc=UnicodeDocstrings.__add__.__doc__),
    __mul__ = interp2app(W_UnicodeObject.descr_mul,
                         doc=UnicodeDocstrings.__mul__.__doc__),
    __rmul__ = interp2app(W_UnicodeObject.descr_mul,
                          doc=UnicodeDocstrings.__rmul__.__doc__),

    __getitem__ = interp2app(W_UnicodeObject.descr_getitem,
                             doc=UnicodeDocstrings.__getitem__.__doc__),
    __getslice__ = interp2app(W_UnicodeObject.descr_getslice,
                              doc=UnicodeDocstrings.__getslice__.__doc__),

    capitalize = interp2app(W_UnicodeObject.descr_capitalize,
                            doc=UnicodeDocstrings.capitalize.__doc__),
    center = interp2app(W_UnicodeObject.descr_center,
                        doc=UnicodeDocstrings.center.__doc__),
    count = interp2app(W_UnicodeObject.descr_count,
                       doc=UnicodeDocstrings.count.__doc__),
    decode = interp2app(W_UnicodeObject.descr_decode,
                        doc=UnicodeDocstrings.decode.__doc__),
    encode = interp2app(W_UnicodeObject.descr_encode,
                        doc=UnicodeDocstrings.encode.__doc__),
    expandtabs = interp2app(W_UnicodeObject.descr_expandtabs,
                            doc=UnicodeDocstrings.expandtabs.__doc__),
    find = interp2app(W_UnicodeObject.descr_find,
                      doc=UnicodeDocstrings.find.__doc__),
    rfind = interp2app(W_UnicodeObject.descr_rfind,
                       doc=UnicodeDocstrings.rfind.__doc__),
    index = interp2app(W_UnicodeObject.descr_index,
                       doc=UnicodeDocstrings.index.__doc__),
    rindex = interp2app(W_UnicodeObject.descr_rindex,
                        doc=UnicodeDocstrings.rindex.__doc__),
    isalnum = interp2app(W_UnicodeObject.descr_isalnum,
                         doc=UnicodeDocstrings.isalnum.__doc__),
    isalpha = interp2app(W_UnicodeObject.descr_isalpha,
                         doc=UnicodeDocstrings.isalpha.__doc__),
    isdecimal = interp2app(W_UnicodeObject.descr_isdecimal,
                           doc=UnicodeDocstrings.isdecimal.__doc__),
    isdigit = interp2app(W_UnicodeObject.descr_isdigit,
                         doc=UnicodeDocstrings.isdigit.__doc__),
    islower = interp2app(W_UnicodeObject.descr_islower,
                         doc=UnicodeDocstrings.islower.__doc__),
    isnumeric = interp2app(W_UnicodeObject.descr_isnumeric,
                           doc=UnicodeDocstrings.isnumeric.__doc__),
    isspace = interp2app(W_UnicodeObject.descr_isspace,
                         doc=UnicodeDocstrings.isspace.__doc__),
    istitle = interp2app(W_UnicodeObject.descr_istitle,
                         doc=UnicodeDocstrings.istitle.__doc__),
    isupper = interp2app(W_UnicodeObject.descr_isupper,
                         doc=UnicodeDocstrings.isupper.__doc__),
    join = interp2app(W_UnicodeObject.descr_join,
                      doc=UnicodeDocstrings.join.__doc__),
    ljust = interp2app(W_UnicodeObject.descr_ljust,
                       doc=UnicodeDocstrings.ljust.__doc__),
    rjust = interp2app(W_UnicodeObject.descr_rjust,
                       doc=UnicodeDocstrings.rjust.__doc__),
    lower = interp2app(W_UnicodeObject.descr_lower,
                       doc=UnicodeDocstrings.lower.__doc__),
    partition = interp2app(W_UnicodeObject.descr_partition,
                           doc=UnicodeDocstrings.partition.__doc__),
    rpartition = interp2app(W_UnicodeObject.descr_rpartition,
                            doc=UnicodeDocstrings.rpartition.__doc__),
    replace = interp2app(W_UnicodeObject.descr_replace,
                         doc=UnicodeDocstrings.replace.__doc__),
    split = interp2app(W_UnicodeObject.descr_split,
                       doc=UnicodeDocstrings.split.__doc__),
    rsplit = interp2app(W_UnicodeObject.descr_rsplit,
                        doc=UnicodeDocstrings.rsplit.__doc__),
    splitlines = interp2app(W_UnicodeObject.descr_splitlines,
                            doc=UnicodeDocstrings.splitlines.__doc__),
    startswith = interp2app(W_UnicodeObject.descr_startswith,
                            doc=UnicodeDocstrings.startswith.__doc__),
    endswith = interp2app(W_UnicodeObject.descr_endswith,
                          doc=UnicodeDocstrings.endswith.__doc__),
    strip = interp2app(W_UnicodeObject.descr_strip,
                       doc=UnicodeDocstrings.strip.__doc__),
    lstrip = interp2app(W_UnicodeObject.descr_lstrip,
                        doc=UnicodeDocstrings.lstrip.__doc__),
    rstrip = interp2app(W_UnicodeObject.descr_rstrip,
                        doc=UnicodeDocstrings.rstrip.__doc__),
    swapcase = interp2app(W_UnicodeObject.descr_swapcase,
                          doc=UnicodeDocstrings.swapcase.__doc__),
    title = interp2app(W_UnicodeObject.descr_title,
                       doc=UnicodeDocstrings.title.__doc__),
    translate = interp2app(W_UnicodeObject.descr_translate,
                           doc=UnicodeDocstrings.translate.__doc__),
    upper = interp2app(W_UnicodeObject.descr_upper,
                       doc=UnicodeDocstrings.upper.__doc__),
    zfill = interp2app(W_UnicodeObject.descr_zfill,
                       doc=UnicodeDocstrings.zfill.__doc__),

    format = interp2app(W_UnicodeObject.descr_format,
                        doc=UnicodeDocstrings.format.__doc__),
    __format__ = interp2app(W_UnicodeObject.descr__format__,
                            doc=UnicodeDocstrings.__format__.__doc__),
    __mod__ = interp2app(W_UnicodeObject.descr_mod,
                         doc=UnicodeDocstrings.__mod__.__doc__),
    __getnewargs__ = interp2app(W_UnicodeObject.descr_getnewargs,
                                doc=UnicodeDocstrings.__getnewargs__.__doc__),
    _formatter_parser = interp2app(W_UnicodeObject.descr_formatter_parser),
    _formatter_field_name_split =
        interp2app(W_UnicodeObject.descr_formatter_field_name_split),
)
W_UnicodeObject.typedef.flag_sequence_bug_compat = True


def _create_list_from_unicode(value):
    # need this helper function to allow the jit to look inside and inline
    # listview_unicode
    return [s for s in value]


W_UnicodeObject.EMPTY = W_UnicodeObject(u'')


# Helper for converting int/long
def unicode_to_decimal_w(space, w_unistr):
    if not isinstance(w_unistr, W_UnicodeObject):
        raise oefmt(space.w_TypeError, "expected unicode, got '%T'", w_unistr)
    unistr = w_unistr._value
    result = ['\0'] * len(unistr)
    digits = ['0', '1', '2', '3', '4',
              '5', '6', '7', '8', '9']
    for i in xrange(len(unistr)):
        uchr = ord(unistr[i])
        if unicodedb.isspace(uchr):
            result[i] = ' '
            continue
        try:
            result[i] = digits[unicodedb.decimal(uchr)]
        except KeyError:
            if 0 < uchr < 256:
                result[i] = chr(uchr)
            else:
                w_encoding = space.wrap('decimal')
                w_start = space.wrap(i)
                w_end = space.wrap(i+1)
                w_reason = space.wrap('invalid decimal Unicode string')
                raise OperationError(space.w_UnicodeEncodeError,
                                     space.newtuple([w_encoding, w_unistr,
                                                     w_start, w_end,
                                                     w_reason]))
    return ''.join(result)


_repr_function, _ = make_unicode_escape_function(
    pass_printable=False, unicode_output=False, quotes=True, prefix='u')
Back to Top