Skip to content

C
cython
Commit bc96d01c authored by Stefan Behnel's avatar Stefan Behnel
Browse files
Options

Adapt test_unicode.py test from CPython 3.7 and disable some unrelated tests (capi etc.).

parent 04b4af1a
Show whitespace changes
Inline Side-by-side
Showing with 1474 additions and 33 deletions
runtests.py
View file @ bc96d01c
...@@ -425,6 +425,7 @@ VER_DEP_MODULES = { ...@@ -425,6 +425,7 @@ VER_DEP_MODULES = {
'pyximport.pyximport_namespace', 'pyximport.pyximport_namespace',
]), ]),
(3,4): (operator.lt, lambda x: x in ['run.py34_signature', (3,4): (operator.lt, lambda x: x in ['run.py34_signature',
'run.test_unicode', # taken from Py3.7, difficult to backport
]), ]),
(3,4,999): (operator.gt, lambda x: x in ['run.initial_file_path', (3,4,999): (operator.gt, lambda x: x in ['run.initial_file_path',
]), ]),
......
tests/run/test_unicode.pyx
View file @ bc96d01c
...@@ -7,15 +7,42 @@ Written by Marc-Andre Lemburg (mal@lemburg.com). ...@@ -7,15 +7,42 @@ Written by Marc-Andre Lemburg (mal@lemburg.com).
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY. (c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
""" """
import _string #import _string
import codecs import codecs
import itertools import itertools
import operator import operator
import struct #import struct
import sys #import sys
import unittest #import unittest
import warnings import warnings
from test import support, string_tests # from test import support, string_tests
from contextlib import contextmanager
class support(object):
@staticmethod
def _ignore(func):
return unittest.skip("Ignoring CPython-only test")(func)
def run_with_locale(*args):
return support._ignore
cpython_only = _ignore
def check_free_after_iterating(*args):
pass
@contextmanager
def check_warnings(*args):
yield # ignore any warnings
support = support()
include "test_unicode_string_tests.pxi"
############### ORIGINAL TESTS START HERE #################
# Error handling (bad decoder return) # Error handling (bad decoder return)
def search_function(encoding): def search_function(encoding):
...@@ -48,9 +75,9 @@ def duplicate_string(text): ...@@ -48,9 +75,9 @@ def duplicate_string(text):
class StrSubclass(str): class StrSubclass(str):
pass pass
class UnicodeTest(string_tests.CommonTest, class UnicodeTest(CommonTest,
string_tests.MixinStrUnicodeUserStringTest, MixinStrUnicodeUserStringTest,
string_tests.MixinStrUnicodeTest, MixinStrUnicodeTest,
unittest.TestCase): unittest.TestCase):
type2test = str type2test = str
...@@ -175,7 +202,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -175,7 +202,7 @@ class UnicodeTest(string_tests.CommonTest,
self.assertRaises(StopIteration, next, it) self.assertRaises(StopIteration, next, it)
def test_count(self): def test_count(self):
string_tests.CommonTest.test_count(self) CommonTest.test_count(self)
# check mixed argument types # check mixed argument types
self.checkequalnofix(3, 'aaa', 'count', 'a') self.checkequalnofix(3, 'aaa', 'count', 'a')
self.checkequalnofix(0, 'aaa', 'count', 'b') self.checkequalnofix(0, 'aaa', 'count', 'b')
...@@ -201,7 +228,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -201,7 +228,7 @@ class UnicodeTest(string_tests.CommonTest,
self.checkequal(0, '\u0102' * 10, 'count', '\u0102\U00100304') self.checkequal(0, '\u0102' * 10, 'count', '\u0102\U00100304')
def test_find(self): def test_find(self):
string_tests.CommonTest.test_find(self) CommonTest.test_find(self)
# test implementation details of the memchr fast path # test implementation details of the memchr fast path
self.checkequal(100, 'a' * 100 + '\u0102', 'find', '\u0102') self.checkequal(100, 'a' * 100 + '\u0102', 'find', '\u0102')
self.checkequal(-1, 'a' * 100 + '\u0102', 'find', '\u0201') self.checkequal(-1, 'a' * 100 + '\u0102', 'find', '\u0201')
...@@ -232,7 +259,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -232,7 +259,7 @@ class UnicodeTest(string_tests.CommonTest,
self.checkequal(-1, '\u0102' * 100, 'find', '\u0102\U00100304') self.checkequal(-1, '\u0102' * 100, 'find', '\u0102\U00100304')
def test_rfind(self): def test_rfind(self):
string_tests.CommonTest.test_rfind(self) CommonTest.test_rfind(self)
# test implementation details of the memrchr fast path # test implementation details of the memrchr fast path
self.checkequal(0, '\u0102' + 'a' * 100 , 'rfind', '\u0102') self.checkequal(0, '\u0102' + 'a' * 100 , 'rfind', '\u0102')
self.checkequal(-1, '\u0102' + 'a' * 100 , 'rfind', '\u0201') self.checkequal(-1, '\u0102' + 'a' * 100 , 'rfind', '\u0201')
...@@ -260,7 +287,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -260,7 +287,7 @@ class UnicodeTest(string_tests.CommonTest,
self.checkequal(-1, '\u0102' * 100, 'rfind', '\U00100304\u0102') self.checkequal(-1, '\u0102' * 100, 'rfind', '\U00100304\u0102')
def test_index(self): def test_index(self):
string_tests.CommonTest.test_index(self) CommonTest.test_index(self)
self.checkequalnofix(0, 'abcdefghiabc', 'index', '') self.checkequalnofix(0, 'abcdefghiabc', 'index', '')
self.checkequalnofix(3, 'abcdefghiabc', 'index', 'def') self.checkequalnofix(3, 'abcdefghiabc', 'index', 'def')
self.checkequalnofix(0, 'abcdefghiabc', 'index', 'abc') self.checkequalnofix(0, 'abcdefghiabc', 'index', 'abc')
...@@ -284,7 +311,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -284,7 +311,7 @@ class UnicodeTest(string_tests.CommonTest,
self.assertRaises(ValueError, ('\u0102' * 100).index, '\u0102\U00100304') self.assertRaises(ValueError, ('\u0102' * 100).index, '\u0102\U00100304')
def test_rindex(self): def test_rindex(self):
string_tests.CommonTest.test_rindex(self) CommonTest.test_rindex(self)
self.checkequalnofix(12, 'abcdefghiabc', 'rindex', '') self.checkequalnofix(12, 'abcdefghiabc', 'rindex', '')
self.checkequalnofix(3, 'abcdefghiabc', 'rindex', 'def') self.checkequalnofix(3, 'abcdefghiabc', 'rindex', 'def')
self.checkequalnofix(9, 'abcdefghiabc', 'rindex', 'abc') self.checkequalnofix(9, 'abcdefghiabc', 'rindex', 'abc')
...@@ -309,6 +336,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -309,6 +336,7 @@ class UnicodeTest(string_tests.CommonTest,
self.assertRaises(ValueError, ('a' * 100).rindex, '\U00100304a') self.assertRaises(ValueError, ('a' * 100).rindex, '\U00100304a')
self.assertRaises(ValueError, ('\u0102' * 100).rindex, '\U00100304\u0102') self.assertRaises(ValueError, ('\u0102' * 100).rindex, '\U00100304\u0102')
@unittest.skipIf(sys.version_info < (3, 6), 'Python str.translate() test requires Py3.6+')
def test_maketrans_translate(self): def test_maketrans_translate(self):
# these work with plain translate() # these work with plain translate()
self.checkequalnofix('bbbc', 'abababc', 'translate', self.checkequalnofix('bbbc', 'abababc', 'translate',
...@@ -380,7 +408,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -380,7 +408,7 @@ class UnicodeTest(string_tests.CommonTest,
self.assertRaises(TypeError, 'abababc'.translate, 'abc', 'xyz') self.assertRaises(TypeError, 'abababc'.translate, 'abc', 'xyz')
def test_split(self): def test_split(self):
string_tests.CommonTest.test_split(self) CommonTest.test_split(self)
# test mixed kinds # test mixed kinds
for left, right in ('ba', '\u0101\u0100', '\U00010301\U00010300'): for left, right in ('ba', '\u0101\u0100', '\U00010301\U00010300'):
...@@ -397,7 +425,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -397,7 +425,7 @@ class UnicodeTest(string_tests.CommonTest,
left + delim * 2 + right, 'split', delim *2) left + delim * 2 + right, 'split', delim *2)
def test_rsplit(self): def test_rsplit(self):
string_tests.CommonTest.test_rsplit(self) CommonTest.test_rsplit(self)
# test mixed kinds # test mixed kinds
for left, right in ('ba', '\u0101\u0100', '\U00010301\U00010300'): for left, right in ('ba', '\u0101\u0100', '\U00010301\U00010300'):
left *= 9 left *= 9
...@@ -413,7 +441,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -413,7 +441,7 @@ class UnicodeTest(string_tests.CommonTest,
left + delim * 2 + right, 'rsplit', delim *2) left + delim * 2 + right, 'rsplit', delim *2)
def test_partition(self): def test_partition(self):
string_tests.MixinStrUnicodeUserStringTest.test_partition(self) MixinStrUnicodeUserStringTest.test_partition(self)
# test mixed kinds # test mixed kinds
self.checkequal(('ABCDEFGH', '', ''), 'ABCDEFGH', 'partition', '\u4200') self.checkequal(('ABCDEFGH', '', ''), 'ABCDEFGH', 'partition', '\u4200')
for left, right in ('ba', '\u0101\u0100', '\U00010301\U00010300'): for left, right in ('ba', '\u0101\u0100', '\U00010301\U00010300'):
...@@ -430,7 +458,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -430,7 +458,7 @@ class UnicodeTest(string_tests.CommonTest,
left + delim * 2 + right, 'partition', delim * 2) left + delim * 2 + right, 'partition', delim * 2)
def test_rpartition(self): def test_rpartition(self):
string_tests.MixinStrUnicodeUserStringTest.test_rpartition(self) MixinStrUnicodeUserStringTest.test_rpartition(self)
# test mixed kinds # test mixed kinds
self.checkequal(('', '', 'ABCDEFGH'), 'ABCDEFGH', 'rpartition', '\u4200') self.checkequal(('', '', 'ABCDEFGH'), 'ABCDEFGH', 'rpartition', '\u4200')
for left, right in ('ba', '\u0101\u0100', '\U00010301\U00010300'): for left, right in ('ba', '\u0101\u0100', '\U00010301\U00010300'):
...@@ -447,7 +475,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -447,7 +475,7 @@ class UnicodeTest(string_tests.CommonTest,
left + delim * 2 + right, 'rpartition', delim * 2) left + delim * 2 + right, 'rpartition', delim * 2)
def test_join(self): def test_join(self):
string_tests.MixinStrUnicodeUserStringTest.test_join(self) MixinStrUnicodeUserStringTest.test_join(self)
class MyWrapper: class MyWrapper:
def __init__(self, sval): self.sval = sval def __init__(self, sval): self.sval = sval
...@@ -456,11 +484,11 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -456,11 +484,11 @@ class UnicodeTest(string_tests.CommonTest,
# mixed arguments # mixed arguments
self.checkequalnofix('a b c d', ' ', 'join', ['a', 'b', 'c', 'd']) self.checkequalnofix('a b c d', ' ', 'join', ['a', 'b', 'c', 'd'])
self.checkequalnofix('abcd', '', 'join', ('a', 'b', 'c', 'd')) self.checkequalnofix('abcd', '', 'join', ('a', 'b', 'c', 'd'))
self.checkequalnofix('w x y z', ' ', 'join', string_tests.Sequence('wxyz')) self.checkequalnofix('w x y z', ' ', 'join', Sequence('wxyz'))
self.checkequalnofix('a b c d', ' ', 'join', ['a', 'b', 'c', 'd']) self.checkequalnofix('a b c d', ' ', 'join', ['a', 'b', 'c', 'd'])
self.checkequalnofix('a b c d', ' ', 'join', ['a', 'b', 'c', 'd']) self.checkequalnofix('a b c d', ' ', 'join', ['a', 'b', 'c', 'd'])
self.checkequalnofix('abcd', '', 'join', ('a', 'b', 'c', 'd')) self.checkequalnofix('abcd', '', 'join', ('a', 'b', 'c', 'd'))
self.checkequalnofix('w x y z', ' ', 'join', string_tests.Sequence('wxyz')) self.checkequalnofix('w x y z', ' ', 'join', Sequence('wxyz'))
self.checkraises(TypeError, ' ', 'join', ['1', '2', MyWrapper('foo')]) self.checkraises(TypeError, ' ', 'join', ['1', '2', MyWrapper('foo')])
self.checkraises(TypeError, ' ', 'join', ['1', '2', '3', bytes()]) self.checkraises(TypeError, ' ', 'join', ['1', '2', '3', bytes()])
self.checkraises(TypeError, ' ', 'join', [1, 2, 3]) self.checkraises(TypeError, ' ', 'join', [1, 2, 3])
...@@ -474,7 +502,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -474,7 +502,7 @@ class UnicodeTest(string_tests.CommonTest,
self.assertRaises(OverflowError, ''.join, seq) self.assertRaises(OverflowError, ''.join, seq)
def test_replace(self): def test_replace(self):
string_tests.CommonTest.test_replace(self) CommonTest.test_replace(self)
# method call forwarded from str implementation because of unicode argument # method call forwarded from str implementation because of unicode argument
self.checkequalnofix('one@two!three!', 'one!two!three!', 'replace', '!', '@', 1) self.checkequalnofix('one@two!three!', 'one!two!three!', 'replace', '!', '@', 1)
...@@ -640,6 +668,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -640,6 +668,7 @@ class UnicodeTest(string_tests.CommonTest,
self.assertFalse('\U0001F40D'.isalpha()) self.assertFalse('\U0001F40D'.isalpha())
self.assertFalse('\U0001F46F'.isalpha()) self.assertFalse('\U0001F46F'.isalpha())
@unittest.skipIf(sys.version_info < (3, 7), 'Python lacks str.isascii()')
def test_isascii(self): def test_isascii(self):
super().test_isascii() super().test_isascii()
self.assertFalse("\u20ac".isascii()) self.assertFalse("\u20ac".isascii())
...@@ -752,7 +781,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -752,7 +781,7 @@ class UnicodeTest(string_tests.CommonTest,
def test_lower(self): def test_lower(self):
string_tests.CommonTest.test_lower(self) CommonTest.test_lower(self)
self.assertEqual('\U00010427'.lower(), '\U0001044F') self.assertEqual('\U00010427'.lower(), '\U0001044F')
self.assertEqual('\U00010427\U00010427'.lower(), self.assertEqual('\U00010427\U00010427'.lower(),
'\U0001044F\U0001044F') '\U0001044F\U0001044F')
...@@ -783,7 +812,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -783,7 +812,7 @@ class UnicodeTest(string_tests.CommonTest,
self.assertEqual('\u00b5'.casefold(), '\u03bc') self.assertEqual('\u00b5'.casefold(), '\u03bc')
def test_upper(self): def test_upper(self):
string_tests.CommonTest.test_upper(self) CommonTest.test_upper(self)
self.assertEqual('\U0001044F'.upper(), '\U00010427') self.assertEqual('\U0001044F'.upper(), '\U00010427')
self.assertEqual('\U0001044F\U0001044F'.upper(), self.assertEqual('\U0001044F\U0001044F'.upper(),
'\U00010427\U00010427') '\U00010427\U00010427')
...@@ -800,7 +829,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -800,7 +829,7 @@ class UnicodeTest(string_tests.CommonTest,
self.assertEqual('\u2177'.upper(), '\u2167') self.assertEqual('\u2177'.upper(), '\u2167')
def test_capitalize(self): def test_capitalize(self):
string_tests.CommonTest.test_capitalize(self) CommonTest.test_capitalize(self)
self.assertEqual('\U0001044F'.capitalize(), '\U00010427') self.assertEqual('\U0001044F'.capitalize(), '\U00010427')
self.assertEqual('\U0001044F\U0001044F'.capitalize(), self.assertEqual('\U0001044F\U0001044F'.capitalize(),
'\U00010427\U0001044F') '\U00010427\U0001044F')
...@@ -834,7 +863,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -834,7 +863,7 @@ class UnicodeTest(string_tests.CommonTest,
self.assertEqual('A\u03a3A'.title(), 'A\u03c3a') self.assertEqual('A\u03a3A'.title(), 'A\u03c3a')
def test_swapcase(self): def test_swapcase(self):
string_tests.CommonTest.test_swapcase(self) CommonTest.test_swapcase(self)
self.assertEqual('\U0001044F'.swapcase(), '\U00010427') self.assertEqual('\U0001044F'.swapcase(), '\U00010427')
self.assertEqual('\U00010427'.swapcase(), '\U0001044F') self.assertEqual('\U00010427'.swapcase(), '\U0001044F')
self.assertEqual('\U0001044F\U0001044F'.swapcase(), self.assertEqual('\U0001044F\U0001044F'.swapcase(),
...@@ -860,7 +889,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -860,7 +889,7 @@ class UnicodeTest(string_tests.CommonTest,
self.assertEqual('\u1fd2'.swapcase(), '\u0399\u0308\u0300') self.assertEqual('\u1fd2'.swapcase(), '\u0399\u0308\u0300')
def test_center(self): def test_center(self):
string_tests.CommonTest.test_center(self) CommonTest.test_center(self)
self.assertEqual('x'.center(2, '\U0010FFFF'), self.assertEqual('x'.center(2, '\U0010FFFF'),
'x\U0010FFFF') 'x\U0010FFFF')
self.assertEqual('x'.center(3, '\U0010FFFF'), self.assertEqual('x'.center(3, '\U0010FFFF'),
...@@ -1237,6 +1266,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -1237,6 +1266,7 @@ class UnicodeTest(string_tests.CommonTest,
self.assertEqual("{!s}".format(n), 'N(data)') self.assertEqual("{!s}".format(n), 'N(data)')
self.assertRaises(TypeError, "{}".format, n) self.assertRaises(TypeError, "{}".format, n)
@unittest.skipIf(sys.version_info < (3, 6), 'Python str.format_map() test requires Py3.6+')
def test_format_map(self): def test_format_map(self):
self.assertEqual(''.format_map({}), '') self.assertEqual(''.format_map({}), '')
self.assertEqual('a'.format_map({}), 'a') self.assertEqual('a'.format_map({}), 'a')
...@@ -1338,7 +1368,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -1338,7 +1368,7 @@ class UnicodeTest(string_tests.CommonTest,
self.assertEqual('{f:{}}{}{g}'.format(2, 4, f=1, g='g'), ' 14g') self.assertEqual('{f:{}}{}{g}'.format(2, 4, f=1, g='g'), ' 14g')
def test_formatting(self): def test_formatting(self):
string_tests.MixinStrUnicodeUserStringTest.test_formatting(self) MixinStrUnicodeUserStringTest.test_formatting(self)
# Testing Unicode formatting strings... # Testing Unicode formatting strings...
self.assertEqual("%s, %s" % ("abc", "abc"), 'abc, abc') self.assertEqual("%s, %s" % ("abc", "abc"), 'abc, abc')
self.assertEqual("%s, %s, %i, %f, %5.2f" % ("abc", "abc", 1, 2, 3), 'abc, abc, 1, 2.000000, 3.00') self.assertEqual("%s, %s, %i, %f, %5.2f" % ("abc", "abc", 1, 2, 3), 'abc, abc, 1, 2.000000, 3.00')
...@@ -1418,6 +1448,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -1418,6 +1448,7 @@ class UnicodeTest(string_tests.CommonTest,
self.assertEqual('%X' % letter_m, '6D') self.assertEqual('%X' % letter_m, '6D')
self.assertEqual('%o' % letter_m, '155') self.assertEqual('%o' % letter_m, '155')
self.assertEqual('%c' % letter_m, 'm') self.assertEqual('%c' % letter_m, 'm')
if sys.version_info >= (3, 5):
self.assertRaisesRegex(TypeError, '%x format: an integer is required, not float', operator.mod, '%x', 3.14), self.assertRaisesRegex(TypeError, '%x format: an integer is required, not float', operator.mod, '%x', 3.14),
self.assertRaisesRegex(TypeError, '%X format: an integer is required, not float', operator.mod, '%X', 2.11), self.assertRaisesRegex(TypeError, '%X format: an integer is required, not float', operator.mod, '%X', 2.11),
self.assertRaisesRegex(TypeError, '%o format: an integer is required, not float', operator.mod, '%o', 1.79), self.assertRaisesRegex(TypeError, '%o format: an integer is required, not float', operator.mod, '%o', 1.79),
...@@ -1461,6 +1492,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -1461,6 +1492,7 @@ class UnicodeTest(string_tests.CommonTest,
with self.assertRaises(ValueError): with self.assertRaises(ValueError):
result = format_string % 2.34 result = format_string % 2.34
@unittest.skip('BROKEN!')
def test_issue28598_strsubclass_rhs(self): def test_issue28598_strsubclass_rhs(self):
# A subclass of str with an __rmod__ method should be able to hook # A subclass of str with an __rmod__ method should be able to hook
# into the % operator # into the % operator
...@@ -1585,6 +1617,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -1585,6 +1617,7 @@ class UnicodeTest(string_tests.CommonTest,
# The errors argument defaults to strict. # The errors argument defaults to strict.
self.assertRaises(UnicodeDecodeError, str, utf8_cent, encoding='ascii') self.assertRaises(UnicodeDecodeError, str, utf8_cent, encoding='ascii')
@unittest.skipIf(sys.version_info < (3, 6), 'Python utf-7 codec test requires Py3.6+')
def test_codecs_utf7(self): def test_codecs_utf7(self):
utfTests = [ utfTests = [
('A\u2262\u0391.', b'A+ImIDkQ.'), # RFC2152 example ('A\u2262\u0391.', b'A+ImIDkQ.'), # RFC2152 example
...@@ -2139,6 +2172,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -2139,6 +2172,7 @@ class UnicodeTest(string_tests.CommonTest,
for encoding in ('utf-8',): for encoding in ('utf-8',):
self.assertEqual(str(u.encode(encoding),encoding), u) self.assertEqual(str(u.encode(encoding),encoding), u)
@unittest.skipIf(sys.version_info < (3, 5), 'codecs test requires Py3.5+')
def test_codecs_charmap(self): def test_codecs_charmap(self):
# 0-127 # 0-127
s = bytes(range(128)) s = bytes(range(128))
...@@ -2340,7 +2374,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -2340,7 +2374,7 @@ class UnicodeTest(string_tests.CommonTest,
s += "4" s += "4"
self.assertEqual(s, "3") self.assertEqual(s, "3")
def test_getnewargs(self): def _test_getnewargs(self):
text = 'abc' text = 'abc'
args = text.__getnewargs__() args = text.__getnewargs__()
self.assertIsNot(args[0], text) self.assertIsNot(args[0], text)
...@@ -2443,6 +2477,7 @@ class UnicodeTest(string_tests.CommonTest, ...@@ -2443,6 +2477,7 @@ class UnicodeTest(string_tests.CommonTest,
support.check_free_after_iterating(self, reversed, str) support.check_free_after_iterating(self, reversed, str)
u"""
class CAPITest(unittest.TestCase): class CAPITest(unittest.TestCase):
# Test PyUnicode_FromFormat() # Test PyUnicode_FromFormat()
...@@ -2867,8 +2902,10 @@ class CAPITest(unittest.TestCase): ...@@ -2867,8 +2902,10 @@ class CAPITest(unittest.TestCase):
self.assertEqual(getargs_s_hash(s), chr(k).encode() * (i + 1)) self.assertEqual(getargs_s_hash(s), chr(k).encode() * (i + 1))
# Check that the second call returns the same result # Check that the second call returns the same result
self.assertEqual(getargs_s_hash(s), chr(k).encode() * (i + 1)) self.assertEqual(getargs_s_hash(s), chr(k).encode() * (i + 1))
"""
u"""
class StringModuleTest(unittest.TestCase): class StringModuleTest(unittest.TestCase):
def test_formatter_parser(self): def test_formatter_parser(self):
def parse(format): def parse(format):
...@@ -2918,6 +2955,7 @@ class StringModuleTest(unittest.TestCase): ...@@ -2918,6 +2955,7 @@ class StringModuleTest(unittest.TestCase):
(False, 'key2'), (False, 'key2'),
]]) ]])
self.assertRaises(TypeError, _string.formatter_field_name_split, 1) self.assertRaises(TypeError, _string.formatter_field_name_split, 1)
"""
if __name__ == "__main__": if __name__ == "__main__":
......
tests/run/test_unicode_string_tests.pxi 0 → 100644
View file @ bc96d01c
"""
Common tests shared by test_unicode, test_userstring and test_bytes.
"""
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:
# 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
# Whether the "contained items" of the container are integers in
# range(0, 256) (i.e. bytes, bytearray) or strings of length 1
# (str)
contains_bytes = False
# 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
def test_fixtype(self):
self.assertIs(type(self.fixtype("123")), self.type2test)
# check that obj.method(*args) returns result
def checkequal(self, result, obj, methodname, *args, **kwargs):
result = self.fixtype(result)
obj = self.fixtype(obj)
args = self.fixtype(args)
kwargs = {k: self.fixtype(v) for k,v in kwargs.items()}
realresult = getattr(obj, methodname)(*args, **kwargs)
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)
with self.assertRaises(exc) as cm:
getattr(obj, methodname)(*args)
self.assertNotEqual(str(cm.exception), '')
# 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')
if self.contains_bytes:
self.checkequal(0, 'hello', 'count', 42)
else:
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')
if self.contains_bytes:
self.checkequal(-1, 'hello', 'find', 42)
else:
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')
if self.contains_bytes:
self.checkequal(-1, 'hello', 'rfind', 42)
else:
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)
# issue #15534
self.checkequal(0, '<......\u043c...', "rfind", "<")
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')
if self.contains_bytes:
self.checkraises(ValueError, 'hello', 'index', 42)
else:
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')
if self.contains_bytes:
self.checkraises(ValueError, 'hello', 'rindex', 42)
else:
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')
self.checkequal('abc\r\nab def\ng hi', 'abc\r\nab\tdef\ng\thi',
'expandtabs', 8)
self.checkequal('abc\r\nab def\ng hi', 'abc\r\nab\tdef\ng\thi',
'expandtabs', 4)
self.checkequal('abc\r\nab\r\ndef\ng\r\nhi', 'abc\r\nab\r\ndef\ng\r\nhi',
'expandtabs', 4)
# check keyword args
self.checkequal('abc\rab def\ng hi', 'abc\rab\tdef\ng\thi',
'expandtabs', tabsize=8)
self.checkequal('abc\rab def\ng hi', 'abc\rab\tdef\ng\thi',
'expandtabs', tabsize=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(['abcd'], 'abcd', 'split', '|')
self.checkequal([''], '', 'split', '|')
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)
# with keyword args
self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', sep='|')
self.checkequal(['a', 'b|c|d'],
'a|b|c|d', 'split', '|', maxsplit=1)
self.checkequal(['a', 'b|c|d'],
'a|b|c|d', 'split', sep='|', maxsplit=1)
self.checkequal(['a', 'b|c|d'],
'a|b|c|d', 'split', maxsplit=1, sep='|')
self.checkequal(['a', 'b c d'],
'a b c d', 'split', maxsplit=1)
# 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(['abcd'], 'abcd', 'rsplit', '|')
self.checkequal([''], '', 'rsplit', '|')
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)
# with keyword args
self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', sep='|')
self.checkequal(['a|b|c', 'd'],
'a|b|c|d', 'rsplit', '|', maxsplit=1)
self.checkequal(['a|b|c', 'd'],
'a|b|c|d', 'rsplit', sep='|', maxsplit=1)
self.checkequal(['a|b|c', 'd'],
'a|b|c|d', 'rsplit', maxsplit=1, sep='|')
self.checkequal(['a b c', 'd'],
'a b c d', 'rsplit', maxsplit=1)
# 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", ".", "----")
# issue #15534
EQ('...\u043c......&lt;', '...\u043c......<', "replace", "<", "&lt;")
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")
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)
@unittest.skipIf(sys.maxsize > (1 << 32) or struct.calcsize('P') != 4,
'only applies to 32-bit platforms')
def test_replace_overflow(self):
# Check for overflow checking on 32 bit machines
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)
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')
self.checkraises(TypeError, 'hello', 'capitalize', 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, 0)
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', 'c'], ' a b c ', 'split', None, 3)
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)
for b in ('arf\tbarf', 'arf\nbarf', 'arf\rbarf',
'arf\fbarf', 'arf\vbarf'):
self.checkequal(['arf', 'barf'], b, 'split')
self.checkequal(['arf', 'barf'], b, 'split', None)
self.checkequal(['arf', 'barf'], b, 'split', None, 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, 0)
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', 'c'], ' a b c ', 'rsplit',
None, 3)
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)
for b in ('arf\tbarf', 'arf\nbarf', 'arf\rbarf',
'arf\fbarf', 'arf\vbarf'):
self.checkequal(['arf', 'barf'], b, 'rsplit')
self.checkequal(['arf', 'barf'], b, 'rsplit', None)
self.checkequal(['arf', 'barf'], b, 'rsplit', None, 2)
def test_strip_whitespace(self):
self.checkequal('hello', ' hello ', 'strip')
self.checkequal('hello ', ' hello ', 'lstrip')
self.checkequal(' hello', ' hello ', 'rstrip')
self.checkequal('hello', 'hello', 'strip')
b = ' \t\n\r\f\vabc \t\n\r\f\v'
self.checkequal('abc', b, 'strip')
self.checkequal('abc \t\n\r\f\v', b, 'lstrip')
self.checkequal(' \t\n\r\f\vabc', b, 'rstrip')
# 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)
def test_strip(self):
# 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.checkequal('', 'mississippi', 'strip', 'mississippi')
# only trim the start and end; does not strip internal characters
self.checkequal('mississipp', 'mississippi', 'strip', 'i')
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')
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_isascii(self):
self.checkequal(True, '', 'isascii')
self.checkequal(True, '\x00', 'isascii')
self.checkequal(True, '\x7f', 'isascii')
self.checkequal(True, '\x00\x7f', 'isascii')
self.checkequal(False, '\x80', 'isascii')
self.checkequal(False, '\xe9', 'isascii')
# bytes.isascii() and bytearray.isascii() has optimization which
# check 4 or 8 bytes at once. So check some alignments.
for p in range(8):
self.checkequal(True, ' '*p + '\x7f', 'isascii')
self.checkequal(False, ' '*p + '\x80', 'isascii')
self.checkequal(True, ' '*p + '\x7f' + ' '*8, 'isascii')
self.checkequal(False, ' '*p + '\x80' + ' '*8, 'isascii')
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(['', 'abc', 'def', 'ghi', ''],
"\nabc\ndef\r\nghi\n\r", 'splitlines', False)
self.checkequal(['\n', 'abc\n', 'def\r\n', 'ghi\n', '\r'],
"\nabc\ndef\r\nghi\n\r", 'splitlines', True)
self.checkequal(['', 'abc', 'def', 'ghi', ''], "\nabc\ndef\r\nghi\n\r",
'splitlines', keepends=False)
self.checkequal(['\n', 'abc\n', 'def\r\n', 'ghi\n', '\r'],
"\nabc\ndef\r\nghi\n\r", 'splitlines', keepends=True)
self.checkraises(TypeError, 'abc', 'splitlines', 42, 42)
class CommonTest(BaseTest):
# This testcase contains tests that can be used in all
# stringlike classes. Currently this is str and UserString.
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_nonascii(self):
# check that titlecased chars are lowered correctly
# \u1ffc is the titlecased char
self.checkequal('\u03a9\u0399\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')
class MixinStrUnicodeUserStringTest:
# additional tests that only work for
# stringlike objects, i.e. str, UserString
@unittest.skipIf(sys.version_info < (3, 5), 'Python str.startswith() test requires Py3.5+')
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)
self.checkequal(True, '', 'startswith', '', 0, 1)
self.checkequal(True, '', 'startswith', '', 0, 0)
self.checkequal(False, '', 'startswith', '', 1, 0)
# 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,))
@unittest.skipIf(sys.version_info < (3, 5), 'Python str.endswith() test requires Py3.5+')
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)
self.checkequal(True, '', 'endswith', '', 0, 1)
self.checkequal(True, '', 'endswith', '', 0, 0)
self.checkequal(False, '', 'endswith', '', 1, 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
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', None)
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,))
# Outrageously large width or precision should raise ValueError.
self.checkraises(ValueError, '%%%df' % (2**64), '__mod__', (3.2))
self.checkraises(ValueError, '%%.%df' % (2**64), '__mod__', (3.2))
self.checkraises(OverflowError, '%*s', '__mod__',
(sys.maxsize + 1, ''))
self.checkraises(OverflowError, '%.*f', '__mod__',
(sys.maxsize + 1, 1. / 7))
class X(object): pass
self.checkraises(TypeError, 'abc', '__mod__', X())
@support.cpython_only
def test_formatting_c_limits(self):
from _testcapi import PY_SSIZE_T_MAX, INT_MAX, UINT_MAX
SIZE_MAX = (1 << (PY_SSIZE_T_MAX.bit_length() + 1)) - 1
self.checkraises(OverflowError, '%*s', '__mod__',
(PY_SSIZE_T_MAX + 1, ''))
self.checkraises(OverflowError, '%.*f', '__mod__',
(INT_MAX + 1, 1. / 7))
# Issue 15989
self.checkraises(OverflowError, '%*s', '__mod__',
(SIZE_MAX + 1, ''))
self.checkraises(OverflowError, '%.*f', '__mod__',
(UINT_MAX + 1, 1. / 7))
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')
@unittest.skipIf(sys.version_info < (3, 5), 'Python str.partition() test requires Py3.5+')
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)
@unittest.skipIf(sys.version_info < (3, 5), 'Python str.rpartition() test requires Py3.5+')
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)
# issue #15534
self.checkequal(10, "...\u043c......<", "find", "<")
class MixinStrUnicodeTest:
# Additional tests that only work with str.
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)
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7