From b25a791802a1915097e02bfba04e27a41ae55ebf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=C5=81ukasz=20Langa?= Date: Fri, 17 Dec 2010 01:32:29 +0000 Subject: =?UTF-8?q?configparser=20API=20cleanup:=20default=20values=20now?= =?UTF-8?q?=20sensible,=20slightly=20incompatible.=20Backwards=20compatibl?= =?UTF-8?q?e=20alternative=20values=20possible=20as=20documented.=20Done?= =?UTF-8?q?=20by=20=C5=81ukasz=20Langa,=20approved=20by=20Raymond=20and=20?= =?UTF-8?q?Fred.?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- Doc/library/configparser.rst | 127 ++++++++++++++++++++++++++++++------------- Lib/configparser.py | 42 +++++++------- Lib/test/test_cfgparser.py | 12 +++- 3 files changed, 117 insertions(+), 64 deletions(-) diff --git a/Doc/library/configparser.rst b/Doc/library/configparser.rst index 421015a..9472b88 100644 --- a/Doc/library/configparser.rst +++ b/Doc/library/configparser.rst @@ -230,21 +230,18 @@ may be treated as parts of multiline values or ignored. Configuration files may include comments, prefixed by specific characters (``#`` and ``;`` by default [1]_). Comments may appear on -their own on an otherwise empty line, or may be entered on lines holding -values or section names. In the latter case, they need to be preceded -by a whitespace character to be recognized as a comment. For backwards -compatibility, by default only ``;`` starts an inline comment, while -``#`` does not [1]_. +their own on an otherwise empty line, possibly indented. [1]_ For example: .. code-block:: ini [Simple Values] - key: value - spaces in keys: allowed - spaces in values: allowed as well - you can also use = to delimit keys from values + key=value + spaces in keys=allowed + spaces in values=allowed as well + spaces around the delimiter = obviously + you can also use : to delimit keys from values [All Values Are Strings] values like this: 1000000 @@ -261,12 +258,14 @@ For example: key_without_value empty string value here = - [You can use comments] ; after a useful line - ; in an empty line - after: a_value ; here's another comment - inside: a ;comment - multiline ;comment - value! ;comment + [You can use comments] + # like this + ; or this + + # By default only in an empty line. + # Inline comments can be harmful because they prevent users + # from using the delimiting characters as parts of values. + # That being said, this can be customized. [Sections Can Be Indented] can_values_be_as_well = True @@ -509,7 +508,8 @@ the :meth:`__init__` options: ... skip-external-locking ... old_passwords = 1 ... skip-bdb - ... skip-innodb # we don't need ACID today + ... # we don't need ACID today + ... skip-innodb ... """ >>> config = configparser.ConfigParser(allow_no_value=True) >>> config.read_string(sample_config) @@ -536,28 +536,78 @@ the :meth:`__init__` options: See also the *space_around_delimiters* argument to :meth:`ConfigParser.write`. -* *comment_prefixes*, default value: ``_COMPATIBLE`` (``'#'`` valid on empty - lines, ``';'`` valid also on non-empty lines) +* *comment_prefixes*, default value: ``('#', ';')`` - Comment prefixes are strings that indicate the start of a valid comment - within a config file. The peculiar default value allows for comments starting - with ``'#'`` or ``';'`` but only the latter can be used in a non-empty line. - This is obviously dictated by backwards compatibiliy. A more predictable - approach would be to specify prefixes as ``('#', ';')`` which will allow for - both prefixes to be used in non-empty lines. +* *inline_comment_prefixes*, default value: ``None`` - Please note that config parsers don't support escaping of comment prefixes so - leaving characters out of *comment_prefixes* is a way of ensuring they can be - used as parts of keys or values. + Comment prefixes are strings that indicate the start of a valid comment within + a config file. *comment_prefixes* are used only on otherwise empty lines + (optionally indented) whereas *inline_comment_prefixes* can be used after + every valid value (e.g. section names, options and empty lines as well). By + default inline comments are disabled and ``'#'`` and ``';'`` are used as + prefixes for whole line comments. -* *strict*, default value: ``False`` + .. versionchanged:: 3.2 + In previous versions of :mod:`configparser` behaviour matched + ``comment_prefixes=('#',';')`` and ``inline_comment_prefixes=(';',)``. - If set to ``True``, the parser will not allow for any section or option + Please note that config parsers don't support escaping of comment prefixes so + using *inline_comment_prefixes* may prevent users from specifying option + values with characters used as comment prefixes. When in doubt, avoid setting + *inline_comment_prefixes*. In any circumstances, the only way of storing + comment prefix characters at the beginning of a line in multiline values is to + interpolate the prefix, for example:: + + >>> from configparser import ConfigParser, ExtendedInterpolation + >>> parser = ConfigParser(interpolation=ExtendedInterpolation()) + >>> # the default BasicInterpolation could be used as well + >>> parser.read_string(""" + ... [DEFAULT] + ... hash = # + ... + ... [hashes] + ... shebang = + ... ${hash}!/usr/bin/env python + ... ${hash} -*- coding: utf-8 -*- + ... + ... extensions = + ... enabled_extension + ... another_extension + ... #disabled_by_comment + ... yet_another_extension + ... + ... interpolation not necessary = if # is not at line start + ... even in multiline values = line #1 + ... line #2 + ... line #3 + ... """) + >>> print(parser['hashes']['shebang']) + + #!/usr/bin/env python + # -*- coding: utf-8 -*- + >>> print(parser['hashes']['extensions']) + + enabled_extension + another_extension + yet_another_extension + >>> print(parser['hashes']['interpolation not necessary']) + if # is not at line start + >>> print(parser['hashes']['even in multiline values']) + line #1 + line #2 + line #3 + +* *strict*, default value: ``True`` + + When set to ``True``, the parser will not allow for any section or option duplicates while reading from a single source (using :meth:`read_file`, - :meth:`read_string` or :meth:`read_dict`). The default is ``False`` only - because of backwards compatibility reasons. It is recommended to use strict + :meth:`read_string` or :meth:`read_dict`). It is recommended to use strict parsers in new applications. + .. versionchanged:: 3.2 + In previous versions of :mod:`configparser` behaviour matched + ``strict=False``. + * *empty_lines_in_values*, default value: ``True`` In config parsers, values can span multiple lines as long as they are @@ -575,7 +625,6 @@ the :meth:`__init__` options: this = is still a part of the multiline value of 'key' - This can be especially problematic for the user to see if she's using a proportional font to edit the file. That is why when your application does not need values with empty lines, you should consider disallowing them. This @@ -603,8 +652,7 @@ the :meth:`__init__` options: interpolation completely, ``ExtendedInterpolation()`` provides a more advanced variant inspired by ``zc.buildout``. More on the subject in the `dedicated documentation section <#interpolation-of-values>`_. - - .. note:: :class:`RawConfigParser` is using ``None`` by default. + :class:`RawConfigParser` has a default value of ``None``. More advanced customization may be achieved by overriding default values of @@ -769,7 +817,7 @@ interpolation if an option used is not defined elsewhere. :: ConfigParser Objects -------------------- -.. class:: ConfigParser(defaults=None, dict_type=collections.OrderedDict, allow_no_value=False, delimiters=('=', ':'), comment_prefixes=_COMPATIBLE, strict=False, empty_lines_in_values=True, default_section=configparser.DEFAULTSECT, interpolation=BasicInterpolation()) +.. class:: ConfigParser(defaults=None, dict_type=collections.OrderedDict, allow_no_value=False, delimiters=('=', ':'), comment_prefixes=('#', ';'), inline_comment_prefixes=None, strict=True, empty_lines_in_values=True, default_section=configparser.DEFAULTSECT, interpolation=BasicInterpolation()) The main configuration parser. When *defaults* is given, it is initialized into the dictionary of intrinsic defaults. When *dict_type* is given, it @@ -778,12 +826,15 @@ ConfigParser Objects When *delimiters* is given, it is used as the set of substrings that divide keys from values. When *comment_prefixes* is given, it will be used - as the set of substrings that prefix comments in a line, both for the whole + as the set of substrings that prefix comments in otherwise empty lines. + Comments can be indented. When *inline_comment_prefixes* is given, it will be + used as the set of substrings that prefix comments in non-empty lines. + line and inline comments. For backwards compatibility, the default value for *comment_prefixes* is a special value that indicates that ``;`` and ``#`` can start whole line comments while only ``;`` can start inline comments. - When *strict* is ``True`` (default: ``False``), the parser won't allow for + When *strict* is ``True`` (the default), the parser won't allow for any section or option duplicates while reading from a single source (file, string or dictionary), raising :exc:`DuplicateSectionError` or :exc:`DuplicateOptionError`. When *empty_lines_in_values* is ``False`` @@ -1043,7 +1094,7 @@ ConfigParser Objects RawConfigParser Objects ----------------------- -.. class:: RawConfigParser(defaults=None, dict_type=collections.OrderedDict, allow_no_value=False, delimiters=('=', ':'), comment_prefixes=_COMPATIBLE, strict=False, empty_lines_in_values=True, default_section=configaparser.DEFAULTSECT, interpolation=None) +.. class:: RawConfigParser(defaults=None, dict_type=collections.OrderedDict, allow_no_value=False, delimiters=('=', ':'), comment_prefixes=('#', ';'), inline_comment_prefixes=None, strict=True, empty_lines_in_values=True, default_section=configaparser.DEFAULTSECT, interpolation=None) Legacy variant of the :class:`ConfigParser` with interpolation disabled by default and unsafe ``add_section`` and ``set`` methods. diff --git a/Lib/configparser.py b/Lib/configparser.py index aba444c..0e41d2f 100644 --- a/Lib/configparser.py +++ b/Lib/configparser.py @@ -15,8 +15,9 @@ ConfigParser -- responsible for parsing a list of methods: __init__(defaults=None, dict_type=_default_dict, allow_no_value=False, - delimiters=('=', ':'), comment_prefixes=_COMPATIBLE, - strict=False, empty_lines_in_values=True): + delimiters=('=', ':'), comment_prefixes=('#', ';'), + inline_comment_prefixes=None, strict=True, + empty_lines_in_values=True): Create the parser. When `defaults' is given, it is initialized into the dictionary or intrinsic defaults. The keys must be strings, the values must be appropriate for %()s string interpolation. @@ -29,11 +30,15 @@ ConfigParser -- responsible for parsing a list of that divide keys from values. When `comment_prefixes' is given, it will be used as the set of - substrings that prefix comments in a line. + substrings that prefix comments in empty lines. Comments can be + indented. + + When `inline_comment_prefixes' is given, it will be used as the set of + substrings that prefix comments in non-empty lines. When `strict` is True, the parser won't allow for any section or option duplicates while reading from a single source (file, string or - dictionary). Default is False. + dictionary). Default is True. When `empty_lines_in_values' is False (default: True), each empty line marks the end of an option. Otherwise, internal empty lines of @@ -340,11 +345,6 @@ class MissingSectionHeaderError(ParsingError): self.args = (filename, lineno, line) -# Used in parsers to denote selecting a backwards-compatible inline comment -# character behavior (; and # are comments at the start of a line, but ; only -# inline) -_COMPATIBLE = object() - # Used in parser getters to indicate the default behaviour when a specific # option is not found it to raise an exception. Created to enable `None' as # a valid fallback value. @@ -592,8 +592,8 @@ class RawConfigParser(MutableMapping): def __init__(self, defaults=None, dict_type=_default_dict, allow_no_value=False, *, delimiters=('=', ':'), - comment_prefixes=_COMPATIBLE, strict=False, - empty_lines_in_values=True, + comment_prefixes=('#', ';'), inline_comment_prefixes=None, + strict=True, empty_lines_in_values=True, default_section=DEFAULTSECT, interpolation=_UNSET): @@ -616,12 +616,8 @@ class RawConfigParser(MutableMapping): else: self._optcre = re.compile(self._OPT_TMPL.format(delim=d), re.VERBOSE) - if comment_prefixes is _COMPATIBLE: - self._startonly_comment_prefixes = ('#',) - self._comment_prefixes = (';',) - else: - self._startonly_comment_prefixes = () - self._comment_prefixes = tuple(comment_prefixes or ()) + self._comment_prefixes = tuple(comment_prefixes or ()) + self._inline_comment_prefixes = tuple(inline_comment_prefixes or ()) self._strict = strict self._allow_no_value = allow_no_value self._empty_lines_in_values = empty_lines_in_values @@ -989,18 +985,18 @@ class RawConfigParser(MutableMapping): indent_level = 0 e = None # None, or an exception for lineno, line in enumerate(fp, start=1): - # strip full line comments comment_start = None - for prefix in self._startonly_comment_prefixes: - if line.strip().startswith(prefix): - comment_start = 0 - break # strip inline comments - for prefix in self._comment_prefixes: + for prefix in self._inline_comment_prefixes: index = line.find(prefix) if index == 0 or (index > 0 and line[index-1].isspace()): comment_start = index break + # strip full line comments + for prefix in self._comment_prefixes: + if line.strip().startswith(prefix): + comment_start = 0 + break value = line[:comment_start].strip() if not value: if self._empty_lines_in_values: diff --git a/Lib/test/test_cfgparser.py b/Lib/test/test_cfgparser.py index 08a313a..4b2d2df 100644 --- a/Lib/test/test_cfgparser.py +++ b/Lib/test/test_cfgparser.py @@ -29,6 +29,7 @@ class CfgParserTestCaseClass(unittest.TestCase): allow_no_value = False delimiters = ('=', ':') comment_prefixes = (';', '#') + inline_comment_prefixes = (';', '#') empty_lines_in_values = True dict_type = configparser._default_dict strict = False @@ -41,6 +42,7 @@ class CfgParserTestCaseClass(unittest.TestCase): allow_no_value=self.allow_no_value, delimiters=self.delimiters, comment_prefixes=self.comment_prefixes, + inline_comment_prefixes=self.inline_comment_prefixes, empty_lines_in_values=self.empty_lines_in_values, dict_type=self.dict_type, strict=self.strict, @@ -812,6 +814,7 @@ class ConfigParserTestCaseLegacyInterpolation(ConfigParserTestCase): class ConfigParserTestCaseNonStandardDelimiters(ConfigParserTestCase): delimiters = (':=', '$') comment_prefixes = ('//', '"') + inline_comment_prefixes = ('//', '"') class ConfigParserTestCaseNonStandardDefaultSection(ConfigParserTestCase): default_section = 'general' @@ -888,10 +891,12 @@ class RawConfigParserTestCase(BasicTestCase): class RawConfigParserTestCaseNonStandardDelimiters(RawConfigParserTestCase): delimiters = (':=', '$') comment_prefixes = ('//', '"') + inline_comment_prefixes = ('//', '"') -class RawConfigParserTestSambaConf(BasicTestCase): +class RawConfigParserTestSambaConf(CfgParserTestCaseClass): config_class = configparser.RawConfigParser - comment_prefixes = ('#', ';', '//', '----') + comment_prefixes = ('#', ';', '----') + inline_comment_prefixes = ('//',) empty_lines_in_values = False def test_reading(self): @@ -1074,7 +1079,8 @@ class SortedTestCase(RawConfigParserTestCase): class CompatibleTestCase(CfgParserTestCaseClass): config_class = configparser.RawConfigParser - comment_prefixes = configparser._COMPATIBLE + comment_prefixes = '#;' + inline_comment_prefixes = ';' def test_comment_handling(self): config_string = textwrap.dedent("""\ -- cgit v0.12 a> 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 
"""
Common tests shared by test_str, test_unicode, test_userstring and test_string.
"""

import unittest, string, sys, struct
from test import support
from collections import UserList

class Sequence:
    def __init__(self, seq='wxyz'): self.seq = seq
    def __len__(self): return len(self.seq)
    def __getitem__(self, i): return self.seq[i]

class BadSeq1(Sequence):
    def __init__(self): self.seq = [7, 'hello', 123]
    def __str__(self): return '{0} {1} {2}'.format(*self.seq)

class BadSeq2(Sequence):
    def __init__(self): self.seq = ['a', 'b', 'c']
    def __len__(self): return 8

class BaseTest(unittest.TestCase):
    # These tests are for buffers of values (bytes) and not
    # specific to character interpretation, used for bytes objects
    # and various string implementations

    # The type to be tested
    # Change in subclasses to change the behaviour of fixtesttype()
    type2test = None

    # All tests pass their arguments to the testing methods
    # as str objects. fixtesttype() can be used to propagate
    # these arguments to the appropriate type
    def fixtype(self, obj):
        if isinstance(obj, str):
            return self.__class__.type2test(obj)
        elif isinstance(obj, list):
            return [self.fixtype(x) for x in obj]
        elif isinstance(obj, tuple):
            return tuple([self.fixtype(x) for x in obj])
        elif isinstance(obj, dict):
            return dict([
               (self.fixtype(key), self.fixtype(value))
               for (key, value) in obj.items()
            ])
        else:
            return obj

    # check that obj.method(*args) returns result
    def checkequal(self, result, obj, methodname, *args):
        result = self.fixtype(result)
        obj = self.fixtype(obj)
        args = self.fixtype(args)
        realresult = getattr(obj, methodname)(*args)
        self.assertEqual(
            result,
            realresult
        )
        # if the original is returned make sure that
        # this doesn't happen with subclasses
        if obj is realresult:
            try:
                class subtype(self.__class__.type2test):
                    pass
            except TypeError:
                pass  # Skip this if we can't subclass
            else:
                obj = subtype(obj)
                realresult = getattr(obj, methodname)(*args)
                self.assertIsNot(obj, realresult)

    # check that obj.method(*args) raises exc
    def checkraises(self, exc, obj, methodname, *args):
        obj = self.fixtype(obj)
        args = self.fixtype(args)
        self.assertRaises(
            exc,
            getattr(obj, methodname),
            *args
        )

    # call obj.method(*args) without any checks
    def checkcall(self, obj, methodname, *args):
        obj = self.fixtype(obj)
        args = self.fixtype(args)
        getattr(obj, methodname)(*args)

    def test_count(self):
        self.checkequal(3, 'aaa', 'count', 'a')
        self.checkequal(0, 'aaa', 'count', 'b')
        self.checkequal(3, 'aaa', 'count', 'a')
        self.checkequal(0, 'aaa', 'count', 'b')
        self.checkequal(3, 'aaa', 'count', 'a')
        self.checkequal(0, 'aaa', 'count', 'b')
        self.checkequal(0, 'aaa', 'count', 'b')
        self.checkequal(2, 'aaa', 'count', 'a', 1)
        self.checkequal(0, 'aaa', 'count', 'a', 10)
        self.checkequal(1, 'aaa', 'count', 'a', -1)
        self.checkequal(3, 'aaa', 'count', 'a', -10)
        self.checkequal(1, 'aaa', 'count', 'a', 0, 1)
        self.checkequal(3, 'aaa', 'count', 'a', 0, 10)
        self.checkequal(2, 'aaa', 'count', 'a', 0, -1)
        self.checkequal(0, 'aaa', 'count', 'a', 0, -10)
        self.checkequal(3, 'aaa', 'count', '', 1)
        self.checkequal(1, 'aaa', 'count', '', 3)
        self.checkequal(0, 'aaa', 'count', '', 10)
        self.checkequal(2, 'aaa', 'count', '', -1)
        self.checkequal(4, 'aaa', 'count', '', -10)

        self.checkequal(1, '', 'count', '')
        self.checkequal(0, '', 'count', '', 1, 1)
        self.checkequal(0, '', 'count', '', sys.maxsize, 0)

        self.checkequal(0, '', 'count', 'xx')
        self.checkequal(0, '', 'count', 'xx', 1, 1)
        self.checkequal(0, '', 'count', 'xx', sys.maxsize, 0)

        self.checkraises(TypeError, 'hello', 'count')
        self.checkraises(TypeError, 'hello', 'count', 42)

        # For a variety of combinations,
        #    verify that str.count() matches an equivalent function
        #    replacing all occurrences and then differencing the string lengths
        charset = ['', 'a', 'b']
        digits = 7
        base = len(charset)
        teststrings = set()
        for i in range(base ** digits):
            entry = []
            for j in range(digits):
                i, m = divmod(i, base)
                entry.append(charset[m])
            teststrings.add(''.join(entry))
        teststrings = [self.fixtype(ts) for ts in teststrings]
        for i in teststrings:
            n = len(i)
            for j in teststrings:
                r1 = i.count(j)
                if j:
                    r2, rem = divmod(n - len(i.replace(j, self.fixtype(''))),
                                     len(j))
                else:
                    r2, rem = len(i)+1, 0
                if rem or r1 != r2:
                    self.assertEqual(rem, 0, '%s != 0 for %s' % (rem, i))
                    self.assertEqual(r1, r2, '%s != %s for %s' % (r1, r2, i))

    def test_find(self):
        self.checkequal(0, 'abcdefghiabc', 'find', 'abc')
        self.checkequal(9, 'abcdefghiabc', 'find', 'abc', 1)
        self.checkequal(-1, 'abcdefghiabc', 'find', 'def', 4)

        self.checkequal(0, 'abc', 'find', '', 0)
        self.checkequal(3, 'abc', 'find', '', 3)
        self.checkequal(-1, 'abc', 'find', '', 4)

        # to check the ability to pass None as defaults
        self.checkequal( 2, 'rrarrrrrrrrra', 'find', 'a')
        self.checkequal(12, 'rrarrrrrrrrra', 'find', 'a', 4)
        self.checkequal(-1, 'rrarrrrrrrrra', 'find', 'a', 4, 6)
        self.checkequal(12, 'rrarrrrrrrrra', 'find', 'a', 4, None)
        self.checkequal( 2, 'rrarrrrrrrrra', 'find', 'a', None, 6)

        self.checkraises(TypeError, 'hello', 'find')
        self.checkraises(TypeError, 'hello', 'find', 42)

        self.checkequal(0, '', 'find', '')
        self.checkequal(-1, '', 'find', '', 1, 1)
        self.checkequal(-1, '', 'find', '', sys.maxsize, 0)

        self.checkequal(-1, '', 'find', 'xx')
        self.checkequal(-1, '', 'find', 'xx', 1, 1)
        self.checkequal(-1, '', 'find', 'xx', sys.maxsize, 0)

        # issue 7458
        self.checkequal(-1, 'ab', 'find', 'xxx', sys.maxsize + 1, 0)

        # For a variety of combinations,
        #    verify that str.find() matches __contains__
        #    and that the found substring is really at that location
        charset = ['', 'a', 'b', 'c']
        digits = 5
        base = len(charset)
        teststrings = set()
        for i in range(base ** digits):
            entry = []
            for j in range(digits):
                i, m = divmod(i, base)
                entry.append(charset[m])
            teststrings.add(''.join(entry))
        teststrings = [self.fixtype(ts) for ts in teststrings]
        for i in teststrings:
            for j in teststrings:
                loc = i.find(j)
                r1 = (loc != -1)
                r2 = j in i
                self.assertEqual(r1, r2)
                if loc != -1:
                    self.assertEqual(i[loc:loc+len(j)], j)

    def test_rfind(self):
        self.checkequal(9,  'abcdefghiabc', 'rfind', 'abc')
        self.checkequal(12, 'abcdefghiabc', 'rfind', '')
        self.checkequal(0, 'abcdefghiabc', 'rfind', 'abcd')
        self.checkequal(-1, 'abcdefghiabc', 'rfind', 'abcz')

        self.checkequal(3, 'abc', 'rfind', '', 0)
        self.checkequal(3, 'abc', 'rfind', '', 3)
        self.checkequal(-1, 'abc', 'rfind', '', 4)

        # to check the ability to pass None as defaults
        self.checkequal(12, 'rrarrrrrrrrra', 'rfind', 'a')
        self.checkequal(12, 'rrarrrrrrrrra', 'rfind', 'a', 4)
        self.checkequal(-1, 'rrarrrrrrrrra', 'rfind', 'a', 4, 6)
        self.checkequal(12, 'rrarrrrrrrrra', 'rfind', 'a', 4, None)
        self.checkequal( 2, 'rrarrrrrrrrra', 'rfind', 'a', None, 6)

        self.checkraises(TypeError, 'hello', 'rfind')
        self.checkraises(TypeError, 'hello', 'rfind', 42)

        # For a variety of combinations,
        #    verify that str.rfind() matches __contains__
        #    and that the found substring is really at that location
        charset = ['', 'a', 'b', 'c']
        digits = 5
        base = len(charset)
        teststrings = set()
        for i in range(base ** digits):
            entry = []
            for j in range(digits):
                i, m = divmod(i, base)
                entry.append(charset[m])
            teststrings.add(''.join(entry))
        teststrings = [self.fixtype(ts) for ts in teststrings]
        for i in teststrings:
            for j in teststrings:
                loc = i.rfind(j)
                r1 = (loc != -1)
                r2 = j in i
                self.assertEqual(r1, r2)
                if loc != -1:
                    self.assertEqual(i[loc:loc+len(j)], j)

        # issue 7458
        self.checkequal(-1, 'ab', 'rfind', 'xxx', sys.maxsize + 1, 0)

    def test_index(self):
        self.checkequal(0, 'abcdefghiabc', 'index', '')
        self.checkequal(3, 'abcdefghiabc', 'index', 'def')
        self.checkequal(0, 'abcdefghiabc', 'index', 'abc')
        self.checkequal(9, 'abcdefghiabc', 'index', 'abc', 1)

        self.checkraises(ValueError, 'abcdefghiabc', 'index', 'hib')
        self.checkraises(ValueError, 'abcdefghiab', 'index', 'abc', 1)
        self.checkraises(ValueError, 'abcdefghi', 'index', 'ghi', 8)
        self.checkraises(ValueError, 'abcdefghi', 'index', 'ghi', -1)

        # to check the ability to pass None as defaults
        self.checkequal( 2, 'rrarrrrrrrrra', 'index', 'a')
        self.checkequal(12, 'rrarrrrrrrrra', 'index', 'a', 4)
        self.checkraises(ValueError, 'rrarrrrrrrrra', 'index', 'a', 4, 6)
        self.checkequal(12, 'rrarrrrrrrrra', 'index', 'a', 4, None)
        self.checkequal( 2, 'rrarrrrrrrrra', 'index', 'a', None, 6)

        self.checkraises(TypeError, 'hello', 'index')
        self.checkraises(TypeError, 'hello', 'index', 42)

    def test_rindex(self):
        self.checkequal(12, 'abcdefghiabc', 'rindex', '')
        self.checkequal(3,  'abcdefghiabc', 'rindex', 'def')
        self.checkequal(9,  'abcdefghiabc', 'rindex', 'abc')
        self.checkequal(0,  'abcdefghiabc', 'rindex', 'abc', 0, -1)

        self.checkraises(ValueError, 'abcdefghiabc', 'rindex', 'hib')
        self.checkraises(ValueError, 'defghiabc', 'rindex', 'def', 1)
        self.checkraises(ValueError, 'defghiabc', 'rindex', 'abc', 0, -1)
        self.checkraises(ValueError, 'abcdefghi', 'rindex', 'ghi', 0, 8)
        self.checkraises(ValueError, 'abcdefghi', 'rindex', 'ghi', 0, -1)

        # to check the ability to pass None as defaults
        self.checkequal(12, 'rrarrrrrrrrra', 'rindex', 'a')
        self.checkequal(12, 'rrarrrrrrrrra', 'rindex', 'a', 4)
        self.checkraises(ValueError, 'rrarrrrrrrrra', 'rindex', 'a', 4, 6)
        self.checkequal(12, 'rrarrrrrrrrra', 'rindex', 'a', 4, None)
        self.checkequal( 2, 'rrarrrrrrrrra', 'rindex', 'a', None, 6)

        self.checkraises(TypeError, 'hello', 'rindex')
        self.checkraises(TypeError, 'hello', 'rindex', 42)

    def test_lower(self):
        self.checkequal('hello', 'HeLLo', 'lower')
        self.checkequal('hello', 'hello', 'lower')
        self.checkraises(TypeError, 'hello', 'lower', 42)

    def test_upper(self):
        self.checkequal('HELLO', 'HeLLo', 'upper')
        self.checkequal('HELLO', 'HELLO', 'upper')
        self.checkraises(TypeError, 'hello', 'upper', 42)

    def test_expandtabs(self):
        self.checkequal('abc\rab      def\ng       hi', 'abc\rab\tdef\ng\thi', 'expandtabs')
        self.checkequal('abc\rab      def\ng       hi', 'abc\rab\tdef\ng\thi', 'expandtabs', 8)
        self.checkequal('abc\rab  def\ng   hi', 'abc\rab\tdef\ng\thi', 'expandtabs', 4)
        self.checkequal('abc\r\nab  def\ng   hi', 'abc\r\nab\tdef\ng\thi', 'expandtabs', 4)
        self.checkequal('abc\rab      def\ng       hi', 'abc\rab\tdef\ng\thi', 'expandtabs')
        self.checkequal('abc\rab      def\ng       hi', 'abc\rab\tdef\ng\thi', 'expandtabs', 8)
        self.checkequal('abc\r\nab\r\ndef\ng\r\nhi', 'abc\r\nab\r\ndef\ng\r\nhi', 'expandtabs', 4)
        self.checkequal('  a\n b', ' \ta\n\tb', 'expandtabs', 1)

        self.checkraises(TypeError, 'hello', 'expandtabs', 42, 42)
        # This test is only valid when sizeof(int) == sizeof(void*) == 4.
        if sys.maxsize < (1 << 32) and struct.calcsize('P') == 4:
            self.checkraises(OverflowError,
                             '\ta\n\tb', 'expandtabs', sys.maxsize)

    def test_split(self):
        # by a char
        self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|')
        self.checkequal(['a|b|c|d'], 'a|b|c|d', 'split', '|', 0)
        self.checkequal(['a', 'b|c|d'], 'a|b|c|d', 'split', '|', 1)
        self.checkequal(['a', 'b', 'c|d'], 'a|b|c|d', 'split', '|', 2)
        self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|', 3)
        self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|', 4)
        self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|',
                        sys.maxsize-2)
        self.checkequal(['a|b|c|d'], 'a|b|c|d', 'split', '|', 0)
        self.checkequal(['a', '', 'b||c||d'], 'a||b||c||d', 'split', '|', 2)
        self.checkequal(['endcase ', ''], 'endcase |', 'split', '|')
        self.checkequal(['', ' startcase'], '| startcase', 'split', '|')
        self.checkequal(['', 'bothcase', ''], '|bothcase|', 'split', '|')
        self.checkequal(['a', '', 'b\x00c\x00d'], 'a\x00\x00b\x00c\x00d', 'split', '\x00', 2)

        self.checkequal(['a']*20, ('a|'*20)[:-1], 'split', '|')
        self.checkequal(['a']*15 +['a|a|a|a|a'],
                                   ('a|'*20)[:-1], 'split', '|', 15)

        # by string
        self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//')
        self.checkequal(['a', 'b//c//d'], 'a//b//c//d', 'split', '//', 1)
        self.checkequal(['a', 'b', 'c//d'], 'a//b//c//d', 'split', '//', 2)
        self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//', 3)
        self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//', 4)
        self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//',
                        sys.maxsize-10)
        self.checkequal(['a//b//c//d'], 'a//b//c//d', 'split', '//', 0)
        self.checkequal(['a', '', 'b////c////d'], 'a////b////c////d', 'split', '//', 2)
        self.checkequal(['endcase ', ''], 'endcase test', 'split', 'test')
        self.checkequal(['', ' begincase'], 'test begincase', 'split', 'test')
        self.checkequal(['', ' bothcase ', ''], 'test bothcase test',
                        'split', 'test')
        self.checkequal(['a', 'bc'], 'abbbc', 'split', 'bb')
        self.checkequal(['', ''], 'aaa', 'split', 'aaa')
        self.checkequal(['aaa'], 'aaa', 'split', 'aaa', 0)
        self.checkequal(['ab', 'ab'], 'abbaab', 'split', 'ba')
        self.checkequal(['aaaa'], 'aaaa', 'split', 'aab')
        self.checkequal([''], '', 'split', 'aaa')
        self.checkequal(['aa'], 'aa', 'split', 'aaa')
        self.checkequal(['A', 'bobb'], 'Abbobbbobb', 'split', 'bbobb')
        self.checkequal(['A', 'B', ''], 'AbbobbBbbobb', 'split', 'bbobb')

        self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'split', 'BLAH')
        self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'split', 'BLAH', 19)
        self.checkequal(['a']*18 + ['aBLAHa'], ('aBLAH'*20)[:-4],
                        'split', 'BLAH', 18)

        # argument type
        self.checkraises(TypeError, 'hello', 'split', 42, 42, 42)

        # null case
        self.checkraises(ValueError, 'hello', 'split', '')
        self.checkraises(ValueError, 'hello', 'split', '', 0)

    def test_rsplit(self):
        # by a char
        self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|')
        self.checkequal(['a|b|c', 'd'], 'a|b|c|d', 'rsplit', '|', 1)
        self.checkequal(['a|b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 2)
        self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 3)
        self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 4)
        self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|',
                        sys.maxsize-100)
        self.checkequal(['a|b|c|d'], 'a|b|c|d', 'rsplit', '|', 0)
        self.checkequal(['a||b||c', '', 'd'], 'a||b||c||d', 'rsplit', '|', 2)
        self.checkequal(['', ' begincase'], '| begincase', 'rsplit', '|')
        self.checkequal(['endcase ', ''], 'endcase |', 'rsplit', '|')
        self.checkequal(['', 'bothcase', ''], '|bothcase|', 'rsplit', '|')

        self.checkequal(['a\x00\x00b', 'c', 'd'], 'a\x00\x00b\x00c\x00d', 'rsplit', '\x00', 2)

        self.checkequal(['a']*20, ('a|'*20)[:-1], 'rsplit', '|')
        self.checkequal(['a|a|a|a|a']+['a']*15,
                        ('a|'*20)[:-1], 'rsplit', '|', 15)

        # by string
        self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//')
        self.checkequal(['a//b//c', 'd'], 'a//b//c//d', 'rsplit', '//', 1)
        self.checkequal(['a//b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//', 2)
        self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//', 3)
        self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//', 4)
        self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//',
                        sys.maxsize-5)
        self.checkequal(['a//b//c//d'], 'a//b//c//d', 'rsplit', '//', 0)
        self.checkequal(['a////b////c', '', 'd'], 'a////b////c////d', 'rsplit', '//', 2)
        self.checkequal(['', ' begincase'], 'test begincase', 'rsplit', 'test')
        self.checkequal(['endcase ', ''], 'endcase test', 'rsplit', 'test')
        self.checkequal(['', ' bothcase ', ''], 'test bothcase test',
                        'rsplit', 'test')
        self.checkequal(['ab', 'c'], 'abbbc', 'rsplit', 'bb')
        self.checkequal(['', ''], 'aaa', 'rsplit', 'aaa')
        self.checkequal(['aaa'], 'aaa', 'rsplit', 'aaa', 0)
        self.checkequal(['ab', 'ab'], 'abbaab', 'rsplit', 'ba')
        self.checkequal(['aaaa'], 'aaaa', 'rsplit', 'aab')
        self.checkequal([''], '', 'rsplit', 'aaa')
        self.checkequal(['aa'], 'aa', 'rsplit', 'aaa')
        self.checkequal(['bbob', 'A'], 'bbobbbobbA', 'rsplit', 'bbobb')
        self.checkequal(['', 'B', 'A'], 'bbobbBbbobbA', 'rsplit', 'bbobb')

        self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'rsplit', 'BLAH')
        self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'rsplit', 'BLAH', 19)
        self.checkequal(['aBLAHa'] + ['a']*18, ('aBLAH'*20)[:-4],
                        'rsplit', 'BLAH', 18)

        # argument type
        self.checkraises(TypeError, 'hello', 'rsplit', 42, 42, 42)

        # null case
        self.checkraises(ValueError, 'hello', 'rsplit', '')
        self.checkraises(ValueError, 'hello', 'rsplit', '', 0)

    def test_replace(self):
        EQ = self.checkequal

        # Operations on the empty string
        EQ("", "", "replace", "", "")
        EQ("A", "", "replace", "", "A")
        EQ("", "", "replace", "A", "")
        EQ("", "", "replace", "A", "A")
        EQ("", "", "replace", "", "", 100)
        EQ("", "", "replace", "", "", sys.maxsize)

        # interleave (from=="", 'to' gets inserted everywhere)
        EQ("A", "A", "replace", "", "")
        EQ("*A*", "A", "replace", "", "*")
        EQ("*1A*1", "A", "replace", "", "*1")
        EQ("*-#A*-#", "A", "replace", "", "*-#")
        EQ("*-A*-A*-", "AA", "replace", "", "*-")
        EQ("*-A*-A*-", "AA", "replace", "", "*-", -1)
        EQ("*-A*-A*-", "AA", "replace", "", "*-", sys.maxsize)
        EQ("*-A*-A*-", "AA", "replace", "", "*-", 4)
        EQ("*-A*-A*-", "AA", "replace", "", "*-", 3)
        EQ("*-A*-A", "AA", "replace", "", "*-", 2)
        EQ("*-AA", "AA", "replace", "", "*-", 1)
        EQ("AA", "AA", "replace", "", "*-", 0)

        # single character deletion (from=="A", to=="")
        EQ("", "A", "replace", "A", "")
        EQ("", "AAA", "replace", "A", "")
        EQ("", "AAA", "replace", "A", "", -1)
        EQ("", "AAA", "replace", "A", "", sys.maxsize)
        EQ("", "AAA", "replace", "A", "", 4)
        EQ("", "AAA", "replace", "A", "", 3)
        EQ("A", "AAA", "replace", "A", "", 2)
        EQ("AA", "AAA", "replace", "A", "", 1)
        EQ("AAA", "AAA", "replace", "A", "", 0)
        EQ("", "AAAAAAAAAA", "replace", "A", "")
        EQ("BCD", "ABACADA", "replace", "A", "")
        EQ("BCD", "ABACADA", "replace", "A", "", -1)
        EQ("BCD", "ABACADA", "replace", "A", "", sys.maxsize)
        EQ("BCD", "ABACADA", "replace", "A", "", 5)
        EQ("BCD", "ABACADA", "replace", "A", "", 4)
        EQ("BCDA", "ABACADA", "replace", "A", "", 3)
        EQ("BCADA", "ABACADA", "replace", "A", "", 2)
        EQ("BACADA", "ABACADA", "replace", "A", "", 1)
        EQ("ABACADA", "ABACADA", "replace", "A", "", 0)
        EQ("BCD", "ABCAD", "replace", "A", "")
        EQ("BCD", "ABCADAA", "replace", "A", "")
        EQ("BCD", "BCD", "replace", "A", "")
        EQ("*************", "*************", "replace", "A", "")
        EQ("^A^", "^"+"A"*1000+"^", "replace", "A", "", 999)

        # substring deletion (from=="the", to=="")
        EQ("", "the", "replace", "the", "")
        EQ("ater", "theater", "replace", "the", "")
        EQ("", "thethe", "replace", "the", "")
        EQ("", "thethethethe", "replace", "the", "")
        EQ("aaaa", "theatheatheathea", "replace", "the", "")
        EQ("that", "that", "replace", "the", "")
        EQ("thaet", "thaet", "replace", "the", "")
        EQ("here and re", "here and there", "replace", "the", "")
        EQ("here and re and re", "here and there and there",
           "replace", "the", "", sys.maxsize)
        EQ("here and re and re", "here and there and there",
           "replace", "the", "", -1)
        EQ("here and re and re", "here and there and there",
           "replace", "the", "", 3)
        EQ("here and re and re", "here and there and there",
           "replace", "the", "", 2)
        EQ("here and re and there", "here and there and there",
           "replace", "the", "", 1)
        EQ("here and there and there", "here and there and there",
           "replace", "the", "", 0)
        EQ("here and re and re", "here and there and there", "replace", "the", "")

        EQ("abc", "abc", "replace", "the", "")
        EQ("abcdefg", "abcdefg", "replace", "the", "")

        # substring deletion (from=="bob", to=="")
        EQ("bob", "bbobob", "replace", "bob", "")
        EQ("bobXbob", "bbobobXbbobob", "replace", "bob", "")
        EQ("aaaaaaa", "aaaaaaabob", "replace", "bob", "")
        EQ("aaaaaaa", "aaaaaaa", "replace", "bob", "")

        # single character replace in place (len(from)==len(to)==1)
        EQ("Who goes there?", "Who goes there?", "replace", "o", "o")
        EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O")
        EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", sys.maxsize)
        EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", -1)
        EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", 3)
        EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", 2)
        EQ("WhO goes there?", "Who goes there?", "replace", "o", "O", 1)
        EQ("Who goes there?", "Who goes there?", "replace", "o", "O", 0)

        EQ("Who goes there?", "Who goes there?", "replace", "a", "q")
        EQ("who goes there?", "Who goes there?", "replace", "W", "w")
        EQ("wwho goes there?ww", "WWho goes there?WW", "replace", "W", "w")
        EQ("Who goes there!", "Who goes there?", "replace", "?", "!")
        EQ("Who goes there!!", "Who goes there??", "replace", "?", "!")

        EQ("Who goes there?", "Who goes there?", "replace", ".", "!")

        # substring replace in place (len(from)==len(to) > 1)
        EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**")
        EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", sys.maxsize)
        EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", -1)
        EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", 4)
        EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", 3)
        EQ("Th** ** a tissue", "This is a tissue", "replace", "is", "**", 2)
        EQ("Th** is a tissue", "This is a tissue", "replace", "is", "**", 1)
        EQ("This is a tissue", "This is a tissue", "replace", "is", "**", 0)
        EQ("cobob", "bobob", "replace", "bob", "cob")
        EQ("cobobXcobocob", "bobobXbobobob", "replace", "bob", "cob")
        EQ("bobob", "bobob", "replace", "bot", "bot")

        # replace single character (len(from)==1, len(to)>1)
        EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK")
        EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK", -1)
        EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK", sys.maxsize)
        EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK", 2)
        EQ("ReyKKjavik", "Reykjavik", "replace", "k", "KK", 1)
        EQ("Reykjavik", "Reykjavik", "replace", "k", "KK", 0)
        EQ("A----B----C----", "A.B.C.", "replace", ".", "----")

        EQ("Reykjavik", "Reykjavik", "replace", "q", "KK")

        # replace substring (len(from)>1, len(to)!=len(from))
        EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
           "replace", "spam", "ham")
        EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
           "replace", "spam", "ham", sys.maxsize)
        EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
           "replace", "spam", "ham", -1)
        EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
           "replace", "spam", "ham", 4)
        EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
           "replace", "spam", "ham", 3)
        EQ("ham, ham, eggs and spam", "spam, spam, eggs and spam",
           "replace", "spam", "ham", 2)
        EQ("ham, spam, eggs and spam", "spam, spam, eggs and spam",
           "replace", "spam", "ham", 1)
        EQ("spam, spam, eggs and spam", "spam, spam, eggs and spam",
           "replace", "spam", "ham", 0)

        EQ("bobob", "bobobob", "replace", "bobob", "bob")
        EQ("bobobXbobob", "bobobobXbobobob", "replace", "bobob", "bob")
        EQ("BOBOBOB", "BOBOBOB", "replace", "bob", "bobby")

        # XXX Commented out. Is there any reason to support buffer objects
        # as arguments for str.replace()?  GvR
##         ba = bytearray('a')
##         bb = bytearray('b')
##         EQ("bbc", "abc", "replace", ba, bb)
##         EQ("aac", "abc", "replace", bb, ba)

        #
        self.checkequal('one@two!three!', 'one!two!three!', 'replace', '!', '@', 1)
        self.checkequal('onetwothree', 'one!two!three!', 'replace', '!', '')
        self.checkequal('one@two@three!', 'one!two!three!', 'replace', '!', '@', 2)
        self.checkequal('one@two@three@', 'one!two!three!', 'replace', '!', '@', 3)
        self.checkequal('one@two@three@', 'one!two!three!', 'replace', '!', '@', 4)
        self.checkequal('one!two!three!', 'one!two!three!', 'replace', '!', '@', 0)
        self.checkequal('one@two@three@', 'one!two!three!', 'replace', '!', '@')
        self.checkequal('one!two!three!', 'one!two!three!', 'replace', 'x', '@')
        self.checkequal('one!two!three!', 'one!two!three!', 'replace', 'x', '@', 2)
        self.checkequal('-a-b-c-', 'abc', 'replace', '', '-')
        self.checkequal('-a-b-c', 'abc', 'replace', '', '-', 3)
        self.checkequal('abc', 'abc', 'replace', '', '-', 0)
        self.checkequal('', '', 'replace', '', '')
        self.checkequal('abc', 'abc', 'replace', 'ab', '--', 0)
        self.checkequal('abc', 'abc', 'replace', 'xy', '--')
        # Next three for SF bug 422088: [OSF1 alpha] string.replace(); died with
        # MemoryError due to empty result (platform malloc issue when requesting
        # 0 bytes).
        self.checkequal('', '123', 'replace', '123', '')
        self.checkequal('', '123123', 'replace', '123', '')
        self.checkequal('x', '123x123', 'replace', '123', '')

        self.checkraises(TypeError, 'hello', 'replace')
        self.checkraises(TypeError, 'hello', 'replace', 42)
        self.checkraises(TypeError, 'hello', 'replace', 42, 'h')
        self.checkraises(TypeError, 'hello', 'replace', 'h', 42)

    def test_replace_overflow(self):
        # Check for overflow checking on 32 bit machines
        if sys.maxsize != 2147483647 or struct.calcsize("P") > 4:
            return
        A2_16 = "A" * (2**16)
        self.checkraises(OverflowError, A2_16, "replace", "", A2_16)
        self.checkraises(OverflowError, A2_16, "replace", "A", A2_16)
        self.checkraises(OverflowError, A2_16, "replace", "AA", A2_16+A2_16)



class CommonTest(BaseTest):
    # This testcase contains test that can be used in all
    # stringlike classes. Currently this is str, unicode
    # UserString and the string module.

    def test_hash(self):
        # SF bug 1054139:  += optimization was not invalidating cached hash value
        a = self.type2test('DNSSEC')
        b = self.type2test('')
        for c in a:
            b += c
            hash(b)
        self.assertEqual(hash(a), hash(b))

    def test_capitalize(self):
        self.checkequal(' hello ', ' hello ', 'capitalize')
        self.checkequal('Hello ', 'Hello ','capitalize')
        self.checkequal('Hello ', 'hello ','capitalize')
        self.checkequal('Aaaa', 'aaaa', 'capitalize')
        self.checkequal('Aaaa', 'AaAa', 'capitalize')

        # check that titlecased chars are lowered correctly
        # \u1ffc is the titlecased char
        self.checkequal('\u1ffc\u1ff3\u1ff3\u1ff3',
                        '\u1ff3\u1ff3\u1ffc\u1ffc', 'capitalize')
        # check with cased non-letter chars
        self.checkequal('\u24c5\u24e8\u24e3\u24d7\u24de\u24dd',
                        '\u24c5\u24ce\u24c9\u24bd\u24c4\u24c3', 'capitalize')
        self.checkequal('\u24c5\u24e8\u24e3\u24d7\u24de\u24dd',
                        '\u24df\u24e8\u24e3\u24d7\u24de\u24dd', 'capitalize')
        self.checkequal('\u2160\u2171\u2172',
                        '\u2160\u2161\u2162', 'capitalize')
        self.checkequal('\u2160\u2171\u2172',
                        '\u2170\u2171\u2172', 'capitalize')
        # check with Ll chars with no upper - nothing changes here
        self.checkequal('\u019b\u1d00\u1d86\u0221\u1fb7',
                        '\u019b\u1d00\u1d86\u0221\u1fb7', 'capitalize')

        self.checkraises(TypeError, 'hello', 'capitalize', 42)

    def test_lower(self):
        self.checkequal('hello', 'HeLLo', 'lower')
        self.checkequal('hello', 'hello', 'lower')
        self.checkraises(TypeError, 'hello', 'lower', 42)

    def test_upper(self):
        self.checkequal('HELLO', 'HeLLo', 'upper')
        self.checkequal('HELLO', 'HELLO', 'upper')
        self.checkraises(TypeError, 'hello', 'upper', 42)

    def test_expandtabs(self):
        self.checkequal('abc\rab      def\ng       hi', 'abc\rab\tdef\ng\thi', 'expandtabs')
        self.checkequal('abc\rab      def\ng       hi', 'abc\rab\tdef\ng\thi', 'expandtabs', 8)
        self.checkequal('abc\rab  def\ng   hi', 'abc\rab\tdef\ng\thi', 'expandtabs', 4)
        self.checkequal('abc\r\nab  def\ng   hi', 'abc\r\nab\tdef\ng\thi', 'expandtabs', 4)
        self.checkequal('abc\rab      def\ng       hi', 'abc\rab\tdef\ng\thi', 'expandtabs')
        self.checkequal('abc\rab      def\ng       hi', 'abc\rab\tdef\ng\thi', 'expandtabs', 8)
        self.checkequal('abc\r\nab\r\ndef\ng\r\nhi', 'abc\r\nab\r\ndef\ng\r\nhi', 'expandtabs', 4)

        self.checkraises(TypeError, 'hello', 'expandtabs', 42, 42)

    def test_additional_split(self):
        self.checkequal(['this', 'is', 'the', 'split', 'function'],
            'this is the split function', 'split')

        # by whitespace
        self.checkequal(['a', 'b', 'c', 'd'], 'a b c d ', 'split')
        self.checkequal(['a', 'b c d'], 'a b c d', 'split', None, 1)
        self.checkequal(['a', 'b', 'c d'], 'a b c d', 'split', None, 2)
        self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'split', None, 3)
        self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'split', None, 4)
        self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'split', None,
                        sys.maxsize-1)
        self.checkequal(['a b c d'], 'a b c d', 'split', None, 0)
        self.checkequal(['a b c d'], '  a b c d', 'split', None, 0)
        self.checkequal(['a', 'b', 'c  d'], 'a  b  c  d', 'split', None, 2)

        self.checkequal([], '         ', 'split')
        self.checkequal(['a'], '  a    ', 'split')
        self.checkequal(['a', 'b'], '  a    b   ', 'split')
        self.checkequal(['a', 'b   '], '  a    b   ', 'split', None, 1)
        self.checkequal(['a', 'b   c   '], '  a    b   c   ', 'split', None, 1)
        self.checkequal(['a', 'b', 'c   '], '  a    b   c   ', 'split', None, 2)
        self.checkequal(['a', 'b'], '\n\ta \t\r b \v ', 'split')
        aaa = ' a '*20
        self.checkequal(['a']*20, aaa, 'split')
        self.checkequal(['a'] + [aaa[4:]], aaa, 'split', None, 1)
        self.checkequal(['a']*19 + ['a '], aaa, 'split', None, 19)

        # mixed use of str and unicode
        self.checkequal(['a', 'b', 'c d'], 'a b c d', 'split', ' ', 2)

    def test_additional_rsplit(self):
        self.checkequal(['this', 'is', 'the', 'rsplit', 'function'],
                         'this is the rsplit function', 'rsplit')

        # by whitespace
        self.checkequal(['a', 'b', 'c', 'd'], 'a b c d ', 'rsplit')
        self.checkequal(['a b c', 'd'], 'a b c d', 'rsplit', None, 1)
        self.checkequal(['a b', 'c', 'd'], 'a b c d', 'rsplit', None, 2)
        self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'rsplit', None, 3)
        self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'rsplit', None, 4)
        self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'rsplit', None,
                        sys.maxsize-20)
        self.checkequal(['a b c d'], 'a b c d', 'rsplit', None, 0)
        self.checkequal(['a b c d'], 'a b c d  ', 'rsplit', None, 0)
        self.checkequal(['a  b', 'c', 'd'], 'a  b  c  d', 'rsplit', None, 2)

        self.checkequal([], '         ', 'rsplit')
        self.checkequal(['a'], '  a    ', 'rsplit')
        self.checkequal(['a', 'b'], '  a    b   ', 'rsplit')
        self.checkequal(['  a', 'b'], '  a    b   ', 'rsplit', None, 1)
        self.checkequal(['  a    b','c'], '  a    b   c   ', 'rsplit',
                        None, 1)
        self.checkequal(['  a', 'b', 'c'], '  a    b   c   ', 'rsplit',
                        None, 2)
        self.checkequal(['a', 'b'], '\n\ta \t\r b \v ', 'rsplit', None, 88)
        aaa = ' a '*20
        self.checkequal(['a']*20, aaa, 'rsplit')
        self.checkequal([aaa[:-4]] + ['a'], aaa, 'rsplit', None, 1)
        self.checkequal([' a  a'] + ['a']*18, aaa, 'rsplit', None, 18)

        # mixed use of str and unicode
        self.checkequal(['a b', 'c', 'd'], 'a b c d', 'rsplit', ' ', 2)

    def test_strip(self):
        self.checkequal('hello', '   hello   ', 'strip')
        self.checkequal('hello   ', '   hello   ', 'lstrip')
        self.checkequal('   hello', '   hello   ', 'rstrip')
        self.checkequal('hello', 'hello', 'strip')

        # strip/lstrip/rstrip with None arg
        self.checkequal('hello', '   hello   ', 'strip', None)
        self.checkequal('hello   ', '   hello   ', 'lstrip', None)
        self.checkequal('   hello', '   hello   ', 'rstrip', None)
        self.checkequal('hello', 'hello', 'strip', None)

        # strip/lstrip/rstrip with str arg
        self.checkequal('hello', 'xyzzyhelloxyzzy', 'strip', 'xyz')
        self.checkequal('helloxyzzy', 'xyzzyhelloxyzzy', 'lstrip', 'xyz')
        self.checkequal('xyzzyhello', 'xyzzyhelloxyzzy', 'rstrip', 'xyz')
        self.checkequal('hello', 'hello', 'strip', 'xyz')

        self.checkraises(TypeError, 'hello', 'strip', 42, 42)
        self.checkraises(TypeError, 'hello', 'lstrip', 42, 42)
        self.checkraises(TypeError, 'hello', 'rstrip', 42, 42)

    def test_ljust(self):
        self.checkequal('abc       ', 'abc', 'ljust', 10)
        self.checkequal('abc   ', 'abc', 'ljust', 6)
        self.checkequal('abc', 'abc', 'ljust', 3)
        self.checkequal('abc', 'abc', 'ljust', 2)
        self.checkequal('abc*******', 'abc', 'ljust', 10, '*')
        self.checkraises(TypeError, 'abc', 'ljust')

    def test_rjust(self):
        self.checkequal('       abc', 'abc', 'rjust', 10)
        self.checkequal('   abc', 'abc', 'rjust', 6)
        self.checkequal('abc', 'abc', 'rjust', 3)
        self.checkequal('abc', 'abc', 'rjust', 2)
        self.checkequal('*******abc', 'abc', 'rjust', 10, '*')
        self.checkraises(TypeError, 'abc', 'rjust')

    def test_center(self):
        self.checkequal('   abc    ', 'abc', 'center', 10)
        self.checkequal(' abc  ', 'abc', 'center', 6)
        self.checkequal('abc', 'abc', 'center', 3)
        self.checkequal('abc', 'abc', 'center', 2)
        self.checkequal('***abc****', 'abc', 'center', 10, '*')
        self.checkraises(TypeError, 'abc', 'center')

    def test_swapcase(self):
        self.checkequal('hEllO CoMPuTErS', 'HeLLo cOmpUteRs', 'swapcase')

        self.checkraises(TypeError, 'hello', 'swapcase', 42)

    def test_zfill(self):
        self.checkequal('123', '123', 'zfill', 2)
        self.checkequal('123', '123', 'zfill', 3)
        self.checkequal('0123', '123', 'zfill', 4)
        self.checkequal('+123', '+123', 'zfill', 3)
        self.checkequal('+123', '+123', 'zfill', 4)
        self.checkequal('+0123', '+123', 'zfill', 5)
        self.checkequal('-123', '-123', 'zfill', 3)
        self.checkequal('-123', '-123', 'zfill', 4)
        self.checkequal('-0123', '-123', 'zfill', 5)
        self.checkequal('000', '', 'zfill', 3)
        self.checkequal('34', '34', 'zfill', 1)
        self.checkequal('0034', '34', 'zfill', 4)

        self.checkraises(TypeError, '123', 'zfill')

class MixinStrUnicodeUserStringTest:
    # additional tests that only work for
    # stringlike objects, i.e. str, unicode, UserString
    # (but not the string module)

    def test_islower(self):
        self.checkequal(False, '', 'islower')
        self.checkequal(True, 'a', 'islower')
        self.checkequal(False, 'A', 'islower')
        self.checkequal(False, '\n', 'islower')
        self.checkequal(True, 'abc', 'islower')
        self.checkequal(False, 'aBc', 'islower')
        self.checkequal(True, 'abc\n', 'islower')
        self.checkraises(TypeError, 'abc', 'islower', 42)

    def test_isupper(self):
        self.checkequal(False, '', 'isupper')
        self.checkequal(False, 'a', 'isupper')
        self.checkequal(True, 'A', 'isupper')
        self.checkequal(False, '\n', 'isupper')
        self.checkequal(True, 'ABC', 'isupper')
        self.checkequal(False, 'AbC', 'isupper')
        self.checkequal(True, 'ABC\n', 'isupper')
        self.checkraises(TypeError, 'abc', 'isupper', 42)

    def test_istitle(self):
        self.checkequal(False, '', 'istitle')
        self.checkequal(False, 'a', 'istitle')
        self.checkequal(True, 'A', 'istitle')
        self.checkequal(False, '\n', 'istitle')
        self.checkequal(True, 'A Titlecased Line', 'istitle')
        self.checkequal(True, 'A\nTitlecased Line', 'istitle')
        self.checkequal(True, 'A Titlecased, Line', 'istitle')
        self.checkequal(False, 'Not a capitalized String', 'istitle')
        self.checkequal(False, 'Not\ta Titlecase String', 'istitle')
        self.checkequal(False, 'Not--a Titlecase String', 'istitle')
        self.checkequal(False, 'NOT', 'istitle')
        self.checkraises(TypeError, 'abc', 'istitle', 42)

    def test_isspace(self):
        self.checkequal(False, '', 'isspace')
        self.checkequal(False, 'a', 'isspace')
        self.checkequal(True, ' ', 'isspace')
        self.checkequal(True, '\t', 'isspace')
        self.checkequal(True, '\r', 'isspace')
        self.checkequal(True, '\n', 'isspace')
        self.checkequal(True, ' \t\r\n', 'isspace')
        self.checkequal(False, ' \t\r\na', 'isspace')
        self.checkraises(TypeError, 'abc', 'isspace', 42)

    def test_isalpha(self):
        self.checkequal(False, '', 'isalpha')
        self.checkequal(True, 'a', 'isalpha')
        self.checkequal(True, 'A', 'isalpha')
        self.checkequal(False, '\n', 'isalpha')
        self.checkequal(True, 'abc', 'isalpha')
        self.checkequal(False, 'aBc123', 'isalpha')
        self.checkequal(False, 'abc\n', 'isalpha')
        self.checkraises(TypeError, 'abc', 'isalpha', 42)

    def test_isalnum(self):
        self.checkequal(False, '', 'isalnum')
        self.checkequal(True, 'a', 'isalnum')
        self.checkequal(True, 'A', 'isalnum')
        self.checkequal(False, '\n', 'isalnum')
        self.checkequal(True, '123abc456', 'isalnum')
        self.checkequal(True, 'a1b3c', 'isalnum')
        self.checkequal(False, 'aBc000 ', 'isalnum')
        self.checkequal(False, 'abc\n', 'isalnum')
        self.checkraises(TypeError, 'abc', 'isalnum', 42)

    def test_isdigit(self):
        self.checkequal(False, '', 'isdigit')
        self.checkequal(False, 'a', 'isdigit')
        self.checkequal(True, '0', 'isdigit')
        self.checkequal(True, '0123456789', 'isdigit')
        self.checkequal(False, '0123456789a', 'isdigit')

        self.checkraises(TypeError, 'abc', 'isdigit', 42)

    def test_title(self):
        self.checkequal(' Hello ', ' hello ', 'title')
        self.checkequal('Hello ', 'hello ', 'title')
        self.checkequal('Hello ', 'Hello ', 'title')
        self.checkequal('Format This As Title String', "fOrMaT thIs aS titLe String", 'title')
        self.checkequal('Format,This-As*Title;String', "fOrMaT,thIs-aS*titLe;String", 'title', )
        self.checkequal('Getint', "getInt", 'title')
        self.checkraises(TypeError, 'hello', 'title', 42)

    def test_splitlines(self):
        self.checkequal(['abc', 'def', '', 'ghi'], "abc\ndef\n\rghi", 'splitlines')
        self.checkequal(['abc', 'def', '', 'ghi'], "abc\ndef\n\r\nghi", 'splitlines')
        self.checkequal(['abc', 'def', 'ghi'], "abc\ndef\r\nghi", 'splitlines')
        self.checkequal(['abc', 'def', 'ghi'], "abc\ndef\r\nghi\n", 'splitlines')
        self.checkequal(['abc', 'def', 'ghi', ''], "abc\ndef\r\nghi\n\r", 'splitlines')
        self.checkequal(['', 'abc', 'def', 'ghi', ''], "\nabc\ndef\r\nghi\n\r", 'splitlines')
        self.checkequal(['\n', 'abc\n', 'def\r\n', 'ghi\n', '\r'], "\nabc\ndef\r\nghi\n\r", 'splitlines', 1)

        self.checkraises(TypeError, 'abc', 'splitlines', 42, 42)

    def test_startswith(self):
        self.checkequal(True, 'hello', 'startswith', 'he')
        self.checkequal(True, 'hello', 'startswith', 'hello')
        self.checkequal(False, 'hello', 'startswith', 'hello world')
        self.checkequal(True, 'hello', 'startswith', '')
        self.checkequal(False, 'hello', 'startswith', 'ello')
        self.checkequal(True, 'hello', 'startswith', 'ello', 1)
        self.checkequal(True, 'hello', 'startswith', 'o', 4)
        self.checkequal(False, 'hello', 'startswith', 'o', 5)
        self.checkequal(True, 'hello', 'startswith', '', 5)
        self.checkequal(False, 'hello', 'startswith', 'lo', 6)
        self.checkequal(True, 'helloworld', 'startswith', 'lowo', 3)
        self.checkequal(True, 'helloworld', 'startswith', 'lowo', 3, 7)
        self.checkequal(False, 'helloworld', 'startswith', 'lowo', 3, 6)

        # test negative indices
        self.checkequal(True, 'hello', 'startswith', 'he', 0, -1)
        self.checkequal(True, 'hello', 'startswith', 'he', -53, -1)
        self.checkequal(False, 'hello', 'startswith', 'hello', 0, -1)
        self.checkequal(False, 'hello', 'startswith', 'hello world', -1, -10)
        self.checkequal(False, 'hello', 'startswith', 'ello', -5)
        self.checkequal(True, 'hello', 'startswith', 'ello', -4)
        self.checkequal(False, 'hello', 'startswith', 'o', -2)
        self.checkequal(True, 'hello', 'startswith', 'o', -1)
        self.checkequal(True, 'hello', 'startswith', '', -3, -3)
        self.checkequal(False, 'hello', 'startswith', 'lo', -9)

        self.checkraises(TypeError, 'hello', 'startswith')
        self.checkraises(TypeError, 'hello', 'startswith', 42)

        # test tuple arguments
        self.checkequal(True, 'hello', 'startswith', ('he', 'ha'))
        self.checkequal(False, 'hello', 'startswith', ('lo', 'llo'))
        self.checkequal(True, 'hello', 'startswith', ('hellox', 'hello'))
        self.checkequal(False, 'hello', 'startswith', ())
        self.checkequal(True, 'helloworld', 'startswith', ('hellowo',
                                                           'rld', 'lowo'), 3)
        self.checkequal(False, 'helloworld', 'startswith', ('hellowo', 'ello',
                                                            'rld'), 3)
        self.checkequal(True, 'hello', 'startswith', ('lo', 'he'), 0, -1)
        self.checkequal(False, 'hello', 'startswith', ('he', 'hel'), 0, 1)
        self.checkequal(True, 'hello', 'startswith', ('he', 'hel'), 0, 2)

        self.checkraises(TypeError, 'hello', 'startswith', (42,))

    def test_endswith(self):
        self.checkequal(True, 'hello', 'endswith', 'lo')
        self.checkequal(False, 'hello', 'endswith', 'he')
        self.checkequal(True, 'hello', 'endswith', '')
        self.checkequal(False, 'hello', 'endswith', 'hello world')
        self.checkequal(False, 'helloworld', 'endswith', 'worl')
        self.checkequal(True, 'helloworld', 'endswith', 'worl', 3, 9)
        self.checkequal(True, 'helloworld', 'endswith', 'world', 3, 12)
        self.checkequal(True, 'helloworld', 'endswith', 'lowo', 1, 7)
        self.checkequal(True, 'helloworld', 'endswith', 'lowo', 2, 7)
        self.checkequal(True, 'helloworld', 'endswith', 'lowo', 3, 7)
        self.checkequal(False, 'helloworld', 'endswith', 'lowo', 4, 7)
        self.checkequal(False, 'helloworld', 'endswith', 'lowo', 3, 8)
        self.checkequal(False, 'ab', 'endswith', 'ab', 0, 1)
        self.checkequal(False, 'ab', 'endswith', 'ab', 0, 0)

        # test negative indices
        self.checkequal(True, 'hello', 'endswith', 'lo', -2)
        self.checkequal(False, 'hello', 'endswith', 'he', -2)
        self.checkequal(True, 'hello', 'endswith', '', -3, -3)
        self.checkequal(False, 'hello', 'endswith', 'hello world', -10, -2)
        self.checkequal(False, 'helloworld', 'endswith', 'worl', -6)
        self.checkequal(True, 'helloworld', 'endswith', 'worl', -5, -1)
        self.checkequal(True, 'helloworld', 'endswith', 'worl', -5, 9)
        self.checkequal(True, 'helloworld', 'endswith', 'world', -7, 12)
        self.checkequal(True, 'helloworld', 'endswith', 'lowo', -99, -3)
        self.checkequal(True, 'helloworld', 'endswith', 'lowo', -8, -3)
        self.checkequal(True, 'helloworld', 'endswith', 'lowo', -7, -3)
        self.checkequal(False, 'helloworld', 'endswith', 'lowo', 3, -4)
        self.checkequal(False, 'helloworld', 'endswith', 'lowo', -8, -2)

        self.checkraises(TypeError, 'hello', 'endswith')
        self.checkraises(TypeError, 'hello', 'endswith', 42)

        # test tuple arguments
        self.checkequal(False, 'hello', 'endswith', ('he', 'ha'))
        self.checkequal(True, 'hello', 'endswith', ('lo', 'llo'))
        self.checkequal(True, 'hello', 'endswith', ('hellox', 'hello'))
        self.checkequal(False, 'hello', 'endswith', ())
        self.checkequal(True, 'helloworld', 'endswith', ('hellowo',
                                                           'rld', 'lowo'), 3)
        self.checkequal(False, 'helloworld', 'endswith', ('hellowo', 'ello',
                                                            'rld'), 3, -1)
        self.checkequal(True, 'hello', 'endswith', ('hell', 'ell'), 0, -1)
        self.checkequal(False, 'hello', 'endswith', ('he', 'hel'), 0, 1)
        self.checkequal(True, 'hello', 'endswith', ('he', 'hell'), 0, 4)

        self.checkraises(TypeError, 'hello', 'endswith', (42,))

    def test___contains__(self):
        self.checkequal(True, '', '__contains__', '')
        self.checkequal(True, 'abc', '__contains__', '')
        self.checkequal(False, 'abc', '__contains__', '\0')
        self.checkequal(True, '\0abc', '__contains__', '\0')
        self.checkequal(True, 'abc\0', '__contains__', '\0')
        self.checkequal(True, '\0abc', '__contains__', 'a')
        self.checkequal(True, 'asdf', '__contains__', 'asdf')
        self.checkequal(False, 'asd', '__contains__', 'asdf')
        self.checkequal(False, '', '__contains__', 'asdf')

    def test_subscript(self):
        self.checkequal('a', 'abc', '__getitem__', 0)
        self.checkequal('c', 'abc', '__getitem__', -1)
        self.checkequal('a', 'abc', '__getitem__', 0)
        self.checkequal('abc', 'abc', '__getitem__', slice(0, 3))
        self.checkequal('abc', 'abc', '__getitem__', slice(0, 1000))
        self.checkequal('a', 'abc', '__getitem__', slice(0, 1))
        self.checkequal('', 'abc', '__getitem__', slice(0, 0))

        self.checkraises(TypeError, 'abc', '__getitem__', 'def')

    def test_slice(self):
        self.checkequal('abc', 'abc', '__getitem__', slice(0, 1000))
        self.checkequal('abc', 'abc', '__getitem__', slice(0, 3))
        self.checkequal('ab', 'abc', '__getitem__', slice(0, 2))
        self.checkequal('bc', 'abc', '__getitem__', slice(1, 3))
        self.checkequal('b', 'abc', '__getitem__', slice(1, 2))
        self.checkequal('', 'abc', '__getitem__', slice(2, 2))
        self.checkequal('', 'abc', '__getitem__', slice(1000, 1000))
        self.checkequal('', 'abc', '__getitem__', slice(2000, 1000))
        self.checkequal('', 'abc', '__getitem__', slice(2, 1))

        self.checkraises(TypeError, 'abc', '__getitem__', 'def')

    def test_extended_getslice(self):
        # Test extended slicing by comparing with list slicing.
        s = string.ascii_letters + string.digits
        indices = (0, None, 1, 3, 41, -1, -2, -37)
        for start in indices:
            for stop in indices:
                # Skip step 0 (invalid)
                for step in indices[1:]:
                    L = list(s)[start:stop:step]
                    self.checkequal("".join(L), s, '__getitem__',
                                    slice(start, stop, step))

    def test_mul(self):
        self.checkequal('', 'abc', '__mul__', -1)
        self.checkequal('', 'abc', '__mul__', 0)
        self.checkequal('abc', 'abc', '__mul__', 1)
        self.checkequal('abcabcabc', 'abc', '__mul__', 3)
        self.checkraises(TypeError, 'abc', '__mul__')
        self.checkraises(TypeError, 'abc', '__mul__', '')
        # XXX: on a 64-bit system, this doesn't raise an overflow error,
        # but either raises a MemoryError, or succeeds (if you have 54TiB)
        #self.checkraises(OverflowError, 10000*'abc', '__mul__', 2000000000)

    def test_join(self):
        # join now works with any sequence type
        # moved here, because the argument order is
        # different in string.join (see the test in
        # test.test_string.StringTest.test_join)
        self.checkequal('a b c d', ' ', 'join', ['a', 'b', 'c', 'd'])
        self.checkequal('abcd', '', 'join', ('a', 'b', 'c', 'd'))
        self.checkequal('bd', '', 'join', ('', 'b', '', 'd'))
        self.checkequal('ac', '', 'join', ('a', '', 'c', ''))
        self.checkequal('w x y z', ' ', 'join', Sequence())
        self.checkequal('abc', 'a', 'join', ('abc',))
        self.checkequal('z', 'a', 'join', UserList(['z']))
        self.checkequal('a.b.c', '.', 'join', ['a', 'b', 'c'])
        self.assertRaises(TypeError, '.'.join, ['a', 'b', 3])
        for i in [5, 25, 125]:
            self.checkequal(((('a' * i) + '-') * i)[:-1], '-', 'join',
                 ['a' * i] * i)
            self.checkequal(((('a' * i) + '-') * i)[:-1], '-', 'join',
                 ('a' * i,) * i)

        #self.checkequal(str(BadSeq1()), ' ', 'join', BadSeq1())
        self.checkequal('a b c', ' ', 'join', BadSeq2())

        self.checkraises(TypeError, ' ', 'join')
        self.checkraises(TypeError, ' ', 'join', 7)
        self.checkraises(TypeError, ' ', 'join', [1, 2, bytes()])
        try:
            def f():
                yield 4 + ""
            self.fixtype(' ').join(f())
        except TypeError as e:
            if '+' not in str(e):
                self.fail('join() ate exception message')
        else:
            self.fail('exception not raised')

    def test_formatting(self):
        self.checkequal('+hello+', '+%s+', '__mod__', 'hello')
        self.checkequal('+10+', '+%d+', '__mod__', 10)
        self.checkequal('a', "%c", '__mod__', "a")
        self.checkequal('a', "%c", '__mod__', "a")
        self.checkequal('"', "%c", '__mod__', 34)
        self.checkequal('$', "%c", '__mod__', 36)
        self.checkequal('10', "%d", '__mod__', 10)
        self.checkequal('\x7f', "%c", '__mod__', 0x7f)

        for ordinal in (-100, 0x200000):
            # unicode raises ValueError, str raises OverflowError
            self.checkraises((ValueError, OverflowError), '%c', '__mod__', ordinal)

        longvalue = sys.maxsize + 10
        slongvalue = str(longvalue)
        self.checkequal(' 42', '%3ld', '__mod__', 42)
        self.checkequal('42', '%d', '__mod__', 42.0)
        self.checkequal(slongvalue, '%d', '__mod__', longvalue)
        self.checkcall('%d', '__mod__', float(longvalue))
        self.checkequal('0042.00', '%07.2f', '__mod__', 42)
        self.checkequal('0042.00', '%07.2F', '__mod__', 42)

        self.checkraises(TypeError, 'abc', '__mod__')
        self.checkraises(TypeError, '%(foo)s', '__mod__', 42)
        self.checkraises(TypeError, '%s%s', '__mod__', (42,))
        self.checkraises(TypeError, '%c', '__mod__', (None,))
        self.checkraises(ValueError, '%(foo', '__mod__', {})
        self.checkraises(TypeError, '%(foo)s %(bar)s', '__mod__', ('foo', 42))
        self.checkraises(TypeError, '%d', '__mod__', "42") # not numeric
        self.checkraises(TypeError, '%d', '__mod__', (42+0j)) # no int conversion provided

        # argument names with properly nested brackets are supported
        self.checkequal('bar', '%((foo))s', '__mod__', {'(foo)': 'bar'})

        # 100 is a magic number in PyUnicode_Format, this forces a resize
        self.checkequal(103*'a'+'x', '%sx', '__mod__', 103*'a')

        self.checkraises(TypeError, '%*s', '__mod__', ('foo', 'bar'))
        self.checkraises(TypeError, '%10.*f', '__mod__', ('foo', 42.))
        self.checkraises(ValueError, '%10', '__mod__', (42,))

        class X(object): pass
        self.checkraises(TypeError, 'abc', '__mod__', X())

    def test_floatformatting(self):
        # float formatting
        for prec in range(100):
            format = '%%.%if' % prec
            value = 0.01
            for x in range(60):
                value = value * 3.14159265359 / 3.0 * 10.0
                self.checkcall(format, "__mod__", value)

    def test_inplace_rewrites(self):
        # Check that strings don't copy and modify cached single-character strings
        self.checkequal('a', 'A', 'lower')
        self.checkequal(True, 'A', 'isupper')
        self.checkequal('A', 'a', 'upper')
        self.checkequal(True, 'a', 'islower')

        self.checkequal('a', 'A', 'replace', 'A', 'a')
        self.checkequal(True, 'A', 'isupper')

        self.checkequal('A', 'a', 'capitalize')
        self.checkequal(True, 'a', 'islower')

        self.checkequal('A', 'a', 'swapcase')
        self.checkequal(True, 'a', 'islower')

        self.checkequal('A', 'a', 'title')
        self.checkequal(True, 'a', 'islower')

    def test_partition(self):

        self.checkequal(('this is the par', 'ti', 'tion method'),
            'this is the partition method', 'partition', 'ti')

        # from raymond's original specification
        S = 'http://www.python.org'
        self.checkequal(('http', '://', 'www.python.org'), S, 'partition', '://')
        self.checkequal(('http://www.python.org', '', ''), S, 'partition', '?')
        self.checkequal(('', 'http://', 'www.python.org'), S, 'partition', 'http://')
        self.checkequal(('http://www.python.', 'org', ''), S, 'partition', 'org')

        self.checkraises(ValueError, S, 'partition', '')
        self.checkraises(TypeError, S, 'partition', None)

    def test_rpartition(self):

        self.checkequal(('this is the rparti', 'ti', 'on method'),
            'this is the rpartition method', 'rpartition', 'ti')

        # from raymond's original specification
        S = 'http://www.python.org'
        self.checkequal(('http', '://', 'www.python.org'), S, 'rpartition', '://')
        self.checkequal(('', '', 'http://www.python.org'), S, 'rpartition', '?')
        self.checkequal(('', 'http://', 'www.python.org'), S, 'rpartition', 'http://')
        self.checkequal(('http://www.python.', 'org', ''), S, 'rpartition', 'org')

        self.checkraises(ValueError, S, 'rpartition', '')
        self.checkraises(TypeError, S, 'rpartition', None)

    def test_none_arguments(self):
        # issue 11828
        s = 'hello'
        self.checkequal(2, s, 'find', 'l', None)
        self.checkequal(3, s, 'find', 'l', -2, None)
        self.checkequal(2, s, 'find', 'l', None, -2)
        self.checkequal(0, s, 'find', 'h', None, None)

        self.checkequal(3, s, 'rfind', 'l', None)
        self.checkequal(3, s, 'rfind', 'l', -2, None)
        self.checkequal(2, s, 'rfind', 'l', None, -2)
        self.checkequal(0, s, 'rfind', 'h', None, None)

        self.checkequal(2, s, 'index', 'l', None)
        self.checkequal(3, s, 'index', 'l', -2, None)
        self.checkequal(2, s, 'index', 'l', None, -2)
        self.checkequal(0, s, 'index', 'h', None, None)

        self.checkequal(3, s, 'rindex', 'l', None)
        self.checkequal(3, s, 'rindex', 'l', -2, None)
        self.checkequal(2, s, 'rindex', 'l', None, -2)
        self.checkequal(0, s, 'rindex', 'h', None, None)

        self.checkequal(2, s, 'count', 'l', None)
        self.checkequal(1, s, 'count', 'l', -2, None)
        self.checkequal(1, s, 'count', 'l', None, -2)
        self.checkequal(0, s, 'count', 'x', None, None)

        self.checkequal(True, s, 'endswith', 'o', None)
        self.checkequal(True, s, 'endswith', 'lo', -2, None)
        self.checkequal(True, s, 'endswith', 'l', None, -2)
        self.checkequal(False, s, 'endswith', 'x', None, None)

        self.checkequal(True, s, 'startswith', 'h', None)
        self.checkequal(True, s, 'startswith', 'l', -2, None)
        self.checkequal(True, s, 'startswith', 'h', None, -2)
        self.checkequal(False, s, 'startswith', 'x', None, None)

    def test_find_etc_raise_correct_error_messages(self):
        # issue 11828
        s = 'hello'
        x = 'x'
        self.assertRaisesRegex(TypeError, r'^find\(', s.find,
                                x, None, None, None)
        self.assertRaisesRegex(TypeError, r'^rfind\(', s.rfind,
                                x, None, None, None)
        self.assertRaisesRegex(TypeError, r'^index\(', s.index,
                                x, None, None, None)
        self.assertRaisesRegex(TypeError, r'^rindex\(', s.rindex,
                                x, None, None, None)
        self.assertRaisesRegex(TypeError, r'^count\(', s.count,
                                x, None, None, None)
        self.assertRaisesRegex(TypeError, r'^startswith\(', s.startswith,
                                x, None, None, None)
        self.assertRaisesRegex(TypeError, r'^endswith\(', s.endswith,
                                x, None, None, None)


class MixinStrUnicodeTest:
    # Additional tests that only work with str and unicode.

    def test_bug1001011(self):
        # Make sure join returns a NEW object for single item sequences
        # involving a subclass.
        # Make sure that it is of the appropriate type.
        # Check the optimisation still occurs for standard objects.
        t = self.type2test
        class subclass(t):
            pass
        s1 = subclass("abcd")
        s2 = t().join([s1])
        self.assertIsNot(s1, s2)
        self.assertIs(type(s2), t)

        s1 = t("abcd")
        s2 = t().join([s1])
        self.assertIs(s1, s2)

        # Should also test mixed-type join.
        if t is str:
            s1 = subclass("abcd")
            s2 = "".join([s1])
            self.assertIsNot(s1, s2)
            self.assertIs(type(s2), t)

            s1 = t("abcd")
            s2 = "".join([s1])
            self.assertIs(s1, s2)

##         elif t is str8:
##             s1 = subclass("abcd")
##             s2 = "".join([s1])
##             self.assertIsNot(s1, s2)
##             self.assertIs(type(s2), str) # promotes!

##             s1 = t("abcd")
##             s2 = "".join([s1])
##             self.assertIsNot(s1, s2)
##             self.assertIs(type(s2), str) # promotes!

        else:
            self.fail("unexpected type for MixinStrUnicodeTest %r" % t)
generated by cgit v0.12 at 2025-11-22 15:04:20 (GMT)