cpython/Lib/test/test_str.py

2728 lines
123 KiB
Python
Raw Normal View History

""" Test script for the Unicode implementation.
Written by Marc-Andre Lemburg (mal@lemburg.com).
(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
"""
import _string
import codecs
import itertools
import operator
import pickle
import struct
import sys
import textwrap
import unicodedata
import unittest
import warnings
from test.support import warnings_helper
from test import support, string_tests
from test.support.script_helper import assert_python_failure
try:
import _testcapi
except ImportError:
_testcapi = None
# Error handling (bad decoder return)
def search_function(encoding):
def decode1(input, errors="strict"):
return 42 # not a tuple
def encode1(input, errors="strict"):
return 42 # not a tuple
def encode2(input, errors="strict"):
return (42, 42) # no unicode
def decode2(input, errors="strict"):
return (42, 42) # no unicode
if encoding=="test.unicode1":
return (encode1, decode1, None, None)
elif encoding=="test.unicode2":
return (encode2, decode2, None, None)
else:
return None
def duplicate_string(text):
"""
Try to get a fresh clone of the specified text:
new object with a reference count of 1.
This is a best-effort: latin1 single letters and the empty
string ('') are singletons and cannot be cloned.
"""
return text.encode().decode()
class StrSubclass(str):
pass
class StrTest(string_tests.StringLikeTest,
string_tests.MixinStrUnicodeTest,
unittest.TestCase):
type2test = str
def setUp(self):
codecs.register(search_function)
self.addCleanup(codecs.unregister, search_function)
def checkequalnofix(self, result, object, methodname, *args):
method = getattr(object, methodname)
realresult = method(*args)
self.assertEqual(realresult, result)
self.assertTrue(type(realresult) is type(result))
# if the original is returned make sure that
# this doesn't happen with subclasses
if realresult is object:
class usub(str):
def __repr__(self):
return 'usub(%r)' % str.__repr__(self)
object = usub(object)
method = getattr(object, methodname)
realresult = method(*args)
self.assertEqual(realresult, result)
self.assertTrue(object is not realresult)
def test_literals(self):
self.assertEqual('\xff', '\u00ff')
self.assertEqual('\uffff', '\U0000ffff')
Merged revisions 56443-56466 via svnmerge from svn+ssh://pythondev@svn.python.org/python/branches/p3yk ................ r56454 | kurt.kaiser | 2007-07-18 22:26:14 -0700 (Wed, 18 Jul 2007) | 2 lines Make relative imports explicit for py3k ................ r56455 | kurt.kaiser | 2007-07-18 23:12:15 -0700 (Wed, 18 Jul 2007) | 2 lines Was modifying dict during iteration. ................ r56457 | guido.van.rossum | 2007-07-19 07:33:19 -0700 (Thu, 19 Jul 2007) | 2 lines Fix failing test. ................ r56466 | guido.van.rossum | 2007-07-19 20:58:16 -0700 (Thu, 19 Jul 2007) | 35 lines Merged revisions 56413-56465 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r56439 | georg.brandl | 2007-07-17 23:37:55 -0700 (Tue, 17 Jul 2007) | 2 lines Use "Unix" as platform name, not "UNIX". ........ r56441 | guido.van.rossum | 2007-07-18 10:19:14 -0700 (Wed, 18 Jul 2007) | 3 lines SF patch# 1755885 by Kurt Kaiser: show location of Unicode escape errors. (Slightly tweaked for style and refcounts.) ........ r56444 | kurt.kaiser | 2007-07-18 12:58:42 -0700 (Wed, 18 Jul 2007) | 2 lines Fix failing unicode test caused by change to ast.c at r56441 ........ r56451 | georg.brandl | 2007-07-18 15:36:53 -0700 (Wed, 18 Jul 2007) | 2 lines Add description for wave.setcomptype() values ........ r56456 | walter.doerwald | 2007-07-19 06:04:38 -0700 (Thu, 19 Jul 2007) | 3 lines Document that codecs.lookup() returns a CodecInfo object. (fixes SF bug #1754453). ........ r56463 | facundo.batista | 2007-07-19 16:57:38 -0700 (Thu, 19 Jul 2007) | 6 lines Added a select.select call in the test server loop to make sure the socket is ready to be read from before attempting a read (this prevents an error 10035 on some Windows platforms). [GSoC - Alan McIntyre] ........ ................
2007-07-20 01:05:57 -03:00
self.assertRaises(SyntaxError, eval, '\'\\Ufffffffe\'')
self.assertRaises(SyntaxError, eval, '\'\\Uffffffff\'')
self.assertRaises(SyntaxError, eval, '\'\\U%08x\'' % 0x110000)
# raw strings should not have unicode escapes
self.assertNotEqual(r"\u0020", " ")
def test_ascii(self):
self.assertEqual(ascii('abc'), "'abc'")
self.assertEqual(ascii('ab\\c'), "'ab\\\\c'")
self.assertEqual(ascii('ab\\'), "'ab\\\\'")
self.assertEqual(ascii('\\c'), "'\\\\c'")
self.assertEqual(ascii('\\'), "'\\\\'")
self.assertEqual(ascii('\n'), "'\\n'")
self.assertEqual(ascii('\r'), "'\\r'")
self.assertEqual(ascii('\t'), "'\\t'")
self.assertEqual(ascii('\b'), "'\\x08'")
self.assertEqual(ascii("'\""), """'\\'"'""")
self.assertEqual(ascii("'\""), """'\\'"'""")
self.assertEqual(ascii("'"), '''"'"''')
self.assertEqual(ascii('"'), """'"'""")
latin1repr = (
"'\\x00\\x01\\x02\\x03\\x04\\x05\\x06\\x07\\x08\\t\\n\\x0b\\x0c\\r"
"\\x0e\\x0f\\x10\\x11\\x12\\x13\\x14\\x15\\x16\\x17\\x18\\x19\\x1a"
"\\x1b\\x1c\\x1d\\x1e\\x1f !\"#$%&\\'()*+,-./0123456789:;<=>?@ABCDEFGHI"
"JKLMNOPQRSTUVWXYZ[\\\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\\x7f"
"\\x80\\x81\\x82\\x83\\x84\\x85\\x86\\x87\\x88\\x89\\x8a\\x8b\\x8c\\x8d"
"\\x8e\\x8f\\x90\\x91\\x92\\x93\\x94\\x95\\x96\\x97\\x98\\x99\\x9a\\x9b"
"\\x9c\\x9d\\x9e\\x9f\\xa0\\xa1\\xa2\\xa3\\xa4\\xa5\\xa6\\xa7\\xa8\\xa9"
"\\xaa\\xab\\xac\\xad\\xae\\xaf\\xb0\\xb1\\xb2\\xb3\\xb4\\xb5\\xb6\\xb7"
"\\xb8\\xb9\\xba\\xbb\\xbc\\xbd\\xbe\\xbf\\xc0\\xc1\\xc2\\xc3\\xc4\\xc5"
"\\xc6\\xc7\\xc8\\xc9\\xca\\xcb\\xcc\\xcd\\xce\\xcf\\xd0\\xd1\\xd2\\xd3"
"\\xd4\\xd5\\xd6\\xd7\\xd8\\xd9\\xda\\xdb\\xdc\\xdd\\xde\\xdf\\xe0\\xe1"
"\\xe2\\xe3\\xe4\\xe5\\xe6\\xe7\\xe8\\xe9\\xea\\xeb\\xec\\xed\\xee\\xef"
"\\xf0\\xf1\\xf2\\xf3\\xf4\\xf5\\xf6\\xf7\\xf8\\xf9\\xfa\\xfb\\xfc\\xfd"
"\\xfe\\xff'")
testrepr = ascii(''.join(map(chr, range(256))))
self.assertEqual(testrepr, latin1repr)
# Test ascii works on wide unicode escapes without overflow.
self.assertEqual(ascii("\U00010000" * 39 + "\uffff" * 4096),
ascii("\U00010000" * 39 + "\uffff" * 4096))
class WrongRepr:
def __repr__(self):
return b'byte-repr'
self.assertRaises(TypeError, ascii, WrongRepr())
def test_repr(self):
# Test basic sanity of repr()
self.assertEqual(repr('abc'), "'abc'")
self.assertEqual(repr('ab\\c'), "'ab\\\\c'")
self.assertEqual(repr('ab\\'), "'ab\\\\'")
self.assertEqual(repr('\\c'), "'\\\\c'")
self.assertEqual(repr('\\'), "'\\\\'")
self.assertEqual(repr('\n'), "'\\n'")
self.assertEqual(repr('\r'), "'\\r'")
self.assertEqual(repr('\t'), "'\\t'")
self.assertEqual(repr('\b'), "'\\x08'")
self.assertEqual(repr("'\""), """'\\'"'""")
self.assertEqual(repr("'\""), """'\\'"'""")
self.assertEqual(repr("'"), '''"'"''')
self.assertEqual(repr('"'), """'"'""")
latin1repr = (
"'\\x00\\x01\\x02\\x03\\x04\\x05\\x06\\x07\\x08\\t\\n\\x0b\\x0c\\r"
"\\x0e\\x0f\\x10\\x11\\x12\\x13\\x14\\x15\\x16\\x17\\x18\\x19\\x1a"
"\\x1b\\x1c\\x1d\\x1e\\x1f !\"#$%&\\'()*+,-./0123456789:;<=>?@ABCDEFGHI"
"JKLMNOPQRSTUVWXYZ[\\\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\\x7f"
"\\x80\\x81\\x82\\x83\\x84\\x85\\x86\\x87\\x88\\x89\\x8a\\x8b\\x8c\\x8d"
"\\x8e\\x8f\\x90\\x91\\x92\\x93\\x94\\x95\\x96\\x97\\x98\\x99\\x9a\\x9b"
"\\x9c\\x9d\\x9e\\x9f\\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9"
"\xaa\xab\xac\\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7"
"\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5"
"\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3"
"\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1"
"\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef"
"\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd"
"\xfe\xff'")
testrepr = repr(''.join(map(chr, range(256))))
self.assertEqual(testrepr, latin1repr)
# Test repr works on wide unicode escapes without overflow.
self.assertEqual(repr("\U00010000" * 39 + "\uffff" * 4096),
repr("\U00010000" * 39 + "\uffff" * 4096))
class WrongRepr:
def __repr__(self):
return b'byte-repr'
self.assertRaises(TypeError, repr, WrongRepr())
def test_iterators(self):
# Make sure unicode objects have an __iter__ method
it = "\u1111\u2222\u3333".__iter__()
self.assertEqual(next(it), "\u1111")
self.assertEqual(next(it), "\u2222")
self.assertEqual(next(it), "\u3333")
self.assertRaises(StopIteration, next, it)
def test_iterators_invocation(self):
cases = [type(iter('abc')), type(iter('🚀'))]
for cls in cases:
with self.subTest(cls=cls):
self.assertRaises(TypeError, cls)
def test_iteration(self):
cases = ['abc', '🚀🚀🚀', "\u1111\u2222\u3333"]
for case in cases:
with self.subTest(string=case):
self.assertEqual(case, "".join(iter(case)))
def test_exhausted_iterator(self):
cases = ['abc', '🚀🚀🚀', "\u1111\u2222\u3333"]
for case in cases:
with self.subTest(case=case):
iterator = iter(case)
tuple(iterator)
self.assertRaises(StopIteration, next, iterator)
def test_pickle_iterator(self):
cases = ['abc', '🚀🚀🚀', "\u1111\u2222\u3333"]
for case in cases:
with self.subTest(case=case):
for proto in range(pickle.HIGHEST_PROTOCOL + 1):
it = iter(case)
with self.subTest(proto=proto):
pickled = "".join(pickle.loads(pickle.dumps(it, proto)))
self.assertEqual(case, pickled)
def test_count(self):
string_tests.StringLikeTest.test_count(self)
# check mixed argument types
self.checkequalnofix(3, 'aaa', 'count', 'a')
self.checkequalnofix(0, 'aaa', 'count', 'b')
self.checkequalnofix(3, 'aaa', 'count', 'a')
self.checkequalnofix(0, 'aaa', 'count', 'b')
self.checkequalnofix(0, 'aaa', 'count', 'b')
self.checkequalnofix(1, 'aaa', 'count', 'a', -1)
self.checkequalnofix(3, 'aaa', 'count', 'a', -10)
self.checkequalnofix(2, 'aaa', 'count', 'a', 0, -1)
self.checkequalnofix(0, 'aaa', 'count', 'a', 0, -10)
# test mixed kinds
self.checkequal(10, '\u0102' + 'a' * 10, 'count', 'a')
self.checkequal(10, '\U00100304' + 'a' * 10, 'count', 'a')
self.checkequal(10, '\U00100304' + '\u0102' * 10, 'count', '\u0102')
self.checkequal(0, 'a' * 10, 'count', '\u0102')
self.checkequal(0, 'a' * 10, 'count', '\U00100304')
self.checkequal(0, '\u0102' * 10, 'count', '\U00100304')
self.checkequal(10, '\u0102' + 'a_' * 10, 'count', 'a_')
self.checkequal(10, '\U00100304' + 'a_' * 10, 'count', 'a_')
self.checkequal(10, '\U00100304' + '\u0102_' * 10, 'count', '\u0102_')
self.checkequal(0, 'a' * 10, 'count', 'a\u0102')
self.checkequal(0, 'a' * 10, 'count', 'a\U00100304')
self.checkequal(0, '\u0102' * 10, 'count', '\u0102\U00100304')
# test subclass
class MyStr(str):
pass
self.checkequal(3, MyStr('aaa'), 'count', 'a')
def test_find(self):
string_tests.StringLikeTest.test_find(self)
# test implementation details of the memchr fast path
self.checkequal(100, 'a' * 100 + '\u0102', 'find', '\u0102')
self.checkequal(-1, 'a' * 100 + '\u0102', 'find', '\u0201')
self.checkequal(-1, 'a' * 100 + '\u0102', 'find', '\u0120')
self.checkequal(-1, 'a' * 100 + '\u0102', 'find', '\u0220')
self.checkequal(100, 'a' * 100 + '\U00100304', 'find', '\U00100304')
self.checkequal(-1, 'a' * 100 + '\U00100304', 'find', '\U00100204')
self.checkequal(-1, 'a' * 100 + '\U00100304', 'find', '\U00102004')
# check mixed argument types
self.checkequalnofix(0, 'abcdefghiabc', 'find', 'abc')
self.checkequalnofix(9, 'abcdefghiabc', 'find', 'abc', 1)
self.checkequalnofix(-1, 'abcdefghiabc', 'find', 'def', 4)
# test utf-8 non-ascii char
self.checkequal(0, 'тест', 'find', 'т')
self.checkequal(3, 'тест', 'find', 'т', 1)
self.checkequal(-1, 'тест', 'find', 'т', 1, 3)
self.checkequal(-1, 'тест', 'find', 'e') # english `e`
# test utf-8 non-ascii slice
self.checkequal(1, 'тест тест', 'find', 'ес')
self.checkequal(1, 'тест тест', 'find', 'ес', 1)
self.checkequal(1, 'тест тест', 'find', 'ес', 1, 3)
self.checkequal(6, 'тест тест', 'find', 'ес', 2)
self.checkequal(-1, 'тест тест', 'find', 'ес', 6, 7)
self.checkequal(-1, 'тест тест', 'find', 'ес', 7)
self.checkequal(-1, 'тест тест', 'find', 'ec') # english `ec`
self.assertRaises(TypeError, 'hello'.find)
self.assertRaises(TypeError, 'hello'.find, 42)
# test mixed kinds
self.checkequal(100, '\u0102' * 100 + 'a', 'find', 'a')
self.checkequal(100, '\U00100304' * 100 + 'a', 'find', 'a')
self.checkequal(100, '\U00100304' * 100 + '\u0102', 'find', '\u0102')
self.checkequal(-1, 'a' * 100, 'find', '\u0102')
self.checkequal(-1, 'a' * 100, 'find', '\U00100304')
self.checkequal(-1, '\u0102' * 100, 'find', '\U00100304')
self.checkequal(100, '\u0102' * 100 + 'a_', 'find', 'a_')
self.checkequal(100, '\U00100304' * 100 + 'a_', 'find', 'a_')
self.checkequal(100, '\U00100304' * 100 + '\u0102_', 'find', '\u0102_')
self.checkequal(-1, 'a' * 100, 'find', 'a\u0102')
self.checkequal(-1, 'a' * 100, 'find', 'a\U00100304')
self.checkequal(-1, '\u0102' * 100, 'find', '\u0102\U00100304')
def test_rfind(self):
string_tests.StringLikeTest.test_rfind(self)
# test implementation details of the memrchr fast path
self.checkequal(0, '\u0102' + 'a' * 100 , 'rfind', '\u0102')
self.checkequal(-1, '\u0102' + 'a' * 100 , 'rfind', '\u0201')
self.checkequal(-1, '\u0102' + 'a' * 100 , 'rfind', '\u0120')
self.checkequal(-1, '\u0102' + 'a' * 100 , 'rfind', '\u0220')
self.checkequal(0, '\U00100304' + 'a' * 100, 'rfind', '\U00100304')
self.checkequal(-1, '\U00100304' + 'a' * 100, 'rfind', '\U00100204')
self.checkequal(-1, '\U00100304' + 'a' * 100, 'rfind', '\U00102004')
# check mixed argument types
self.checkequalnofix(9, 'abcdefghiabc', 'rfind', 'abc')
self.checkequalnofix(12, 'abcdefghiabc', 'rfind', '')
self.checkequalnofix(12, 'abcdefghiabc', 'rfind', '')
# test utf-8 non-ascii char
self.checkequal(1, 'тест', 'rfind', 'е')
self.checkequal(1, 'тест', 'rfind', 'е', 1)
self.checkequal(-1, 'тест', 'rfind', 'е', 2)
self.checkequal(-1, 'тест', 'rfind', 'e') # english `e`
# test utf-8 non-ascii slice
self.checkequal(6, 'тест тест', 'rfind', 'ес')
self.checkequal(6, 'тест тест', 'rfind', 'ес', 1)
self.checkequal(1, 'тест тест', 'rfind', 'ес', 1, 3)
self.checkequal(6, 'тест тест', 'rfind', 'ес', 2)
self.checkequal(-1, 'тест тест', 'rfind', 'ес', 6, 7)
self.checkequal(-1, 'тест тест', 'rfind', 'ес', 7)
self.checkequal(-1, 'тест тест', 'rfind', 'ec') # english `ec`
# test mixed kinds
self.checkequal(0, 'a' + '\u0102' * 100, 'rfind', 'a')
self.checkequal(0, 'a' + '\U00100304' * 100, 'rfind', 'a')
self.checkequal(0, '\u0102' + '\U00100304' * 100, 'rfind', '\u0102')
self.checkequal(-1, 'a' * 100, 'rfind', '\u0102')
self.checkequal(-1, 'a' * 100, 'rfind', '\U00100304')
self.checkequal(-1, '\u0102' * 100, 'rfind', '\U00100304')
self.checkequal(0, '_a' + '\u0102' * 100, 'rfind', '_a')
self.checkequal(0, '_a' + '\U00100304' * 100, 'rfind', '_a')
self.checkequal(0, '_\u0102' + '\U00100304' * 100, 'rfind', '_\u0102')
self.checkequal(-1, 'a' * 100, 'rfind', '\u0102a')
self.checkequal(-1, 'a' * 100, 'rfind', '\U00100304a')
self.checkequal(-1, '\u0102' * 100, 'rfind', '\U00100304\u0102')
def test_index(self):
string_tests.StringLikeTest.test_index(self)
self.checkequalnofix(0, 'abcdefghiabc', 'index', '')
self.checkequalnofix(3, 'abcdefghiabc', 'index', 'def')
self.checkequalnofix(0, 'abcdefghiabc', 'index', 'abc')
self.checkequalnofix(9, 'abcdefghiabc', 'index', 'abc', 1)
self.assertRaises(ValueError, 'abcdefghiabc'.index, 'hib')
self.assertRaises(ValueError, 'abcdefghiab'.index, 'abc', 1)
self.assertRaises(ValueError, 'abcdefghi'.index, 'ghi', 8)
self.assertRaises(ValueError, 'abcdefghi'.index, 'ghi', -1)
# test mixed kinds
self.checkequal(100, '\u0102' * 100 + 'a', 'index', 'a')
self.checkequal(100, '\U00100304' * 100 + 'a', 'index', 'a')
self.checkequal(100, '\U00100304' * 100 + '\u0102', 'index', '\u0102')
self.assertRaises(ValueError, ('a' * 100).index, '\u0102')
self.assertRaises(ValueError, ('a' * 100).index, '\U00100304')
self.assertRaises(ValueError, ('\u0102' * 100).index, '\U00100304')
self.checkequal(100, '\u0102' * 100 + 'a_', 'index', 'a_')
self.checkequal(100, '\U00100304' * 100 + 'a_', 'index', 'a_')
self.checkequal(100, '\U00100304' * 100 + '\u0102_', 'index', '\u0102_')
self.assertRaises(ValueError, ('a' * 100).index, 'a\u0102')
self.assertRaises(ValueError, ('a' * 100).index, 'a\U00100304')
self.assertRaises(ValueError, ('\u0102' * 100).index, '\u0102\U00100304')
def test_rindex(self):
string_tests.StringLikeTest.test_rindex(self)
self.checkequalnofix(12, 'abcdefghiabc', 'rindex', '')
self.checkequalnofix(3, 'abcdefghiabc', 'rindex', 'def')
self.checkequalnofix(9, 'abcdefghiabc', 'rindex', 'abc')
self.checkequalnofix(0, 'abcdefghiabc', 'rindex', 'abc', 0, -1)
self.assertRaises(ValueError, 'abcdefghiabc'.rindex, 'hib')
self.assertRaises(ValueError, 'defghiabc'.rindex, 'def', 1)
self.assertRaises(ValueError, 'defghiabc'.rindex, 'abc', 0, -1)
self.assertRaises(ValueError, 'abcdefghi'.rindex, 'ghi', 0, 8)
self.assertRaises(ValueError, 'abcdefghi'.rindex, 'ghi', 0, -1)
# test mixed kinds
self.checkequal(0, 'a' + '\u0102' * 100, 'rindex', 'a')
self.checkequal(0, 'a' + '\U00100304' * 100, 'rindex', 'a')
self.checkequal(0, '\u0102' + '\U00100304' * 100, 'rindex', '\u0102')
self.assertRaises(ValueError, ('a' * 100).rindex, '\u0102')
self.assertRaises(ValueError, ('a' * 100).rindex, '\U00100304')
self.assertRaises(ValueError, ('\u0102' * 100).rindex, '\U00100304')
self.checkequal(0, '_a' + '\u0102' * 100, 'rindex', '_a')
self.checkequal(0, '_a' + '\U00100304' * 100, 'rindex', '_a')
self.checkequal(0, '_\u0102' + '\U00100304' * 100, 'rindex', '_\u0102')
self.assertRaises(ValueError, ('a' * 100).rindex, '\u0102a')
self.assertRaises(ValueError, ('a' * 100).rindex, '\U00100304a')
self.assertRaises(ValueError, ('\u0102' * 100).rindex, '\U00100304\u0102')
def test_maketrans_translate(self):
# these work with plain translate()
self.checkequalnofix('bbbc', 'abababc', 'translate',
{ord('a'): None})
self.checkequalnofix('iiic', 'abababc', 'translate',
{ord('a'): None, ord('b'): ord('i')})
self.checkequalnofix('iiix', 'abababc', 'translate',
{ord('a'): None, ord('b'): ord('i'), ord('c'): 'x'})
self.checkequalnofix('c', 'abababc', 'translate',
{ord('a'): None, ord('b'): ''})
self.checkequalnofix('xyyx', 'xzx', 'translate',
{ord('z'): 'yy'})
# this needs maketrans()
self.checkequalnofix('abababc', 'abababc', 'translate',
{'b': '<i>'})
tbl = self.type2test.maketrans({'a': None, 'b': '<i>'})
self.checkequalnofix('<i><i><i>c', 'abababc', 'translate', tbl)
# test alternative way of calling maketrans()
tbl = self.type2test.maketrans('abc', 'xyz', 'd')
self.checkequalnofix('xyzzy', 'abdcdcbdddd', 'translate', tbl)
# various tests switching from ASCII to latin1 or the opposite;
# same length, remove a letter, or replace with a longer string.
self.assertEqual("[a]".translate(str.maketrans('a', 'X')),
"[X]")
self.assertEqual("[a]".translate(str.maketrans({'a': 'X'})),
"[X]")
self.assertEqual("[a]".translate(str.maketrans({'a': None})),
"[]")
self.assertEqual("[a]".translate(str.maketrans({'a': 'XXX'})),
"[XXX]")
self.assertEqual("[a]".translate(str.maketrans({'a': '\xe9'})),
"[\xe9]")
self.assertEqual('axb'.translate(str.maketrans({'a': None, 'b': '123'})),
"x123")
self.assertEqual('axb'.translate(str.maketrans({'a': None, 'b': '\xe9'})),
"x\xe9")
# test non-ASCII (don't take the fast-path)
self.assertEqual("[a]".translate(str.maketrans({'a': '<\xe9>'})),
"[<\xe9>]")
self.assertEqual("[\xe9]".translate(str.maketrans({'\xe9': 'a'})),
"[a]")
self.assertEqual("[\xe9]".translate(str.maketrans({'\xe9': None})),
"[]")
self.assertEqual("[\xe9]".translate(str.maketrans({'\xe9': '123'})),
"[123]")
self.assertEqual("[a\xe9]".translate(str.maketrans({'a': '<\u20ac>'})),
"[<\u20ac>\xe9]")
# invalid Unicode characters
invalid_char = 0x10ffff+1
for before in "a\xe9\u20ac\U0010ffff":
mapping = str.maketrans({before: invalid_char})
text = "[%s]" % before
self.assertRaises(ValueError, text.translate, mapping)
# errors
self.assertRaises(TypeError, self.type2test.maketrans)
self.assertRaises(ValueError, self.type2test.maketrans, 'abc', 'defg')
self.assertRaises(TypeError, self.type2test.maketrans, 2, 'def')
self.assertRaises(TypeError, self.type2test.maketrans, 'abc', 2)
self.assertRaises(TypeError, self.type2test.maketrans, 'abc', 'def', 2)
self.assertRaises(ValueError, self.type2test.maketrans, {'xy': 2})
self.assertRaises(TypeError, self.type2test.maketrans, {(1,): 2})
self.assertRaises(TypeError, 'hello'.translate)
self.assertRaises(TypeError, 'abababc'.translate, 'abc', 'xyz')
def test_split(self):
string_tests.StringLikeTest.test_split(self)
# test mixed kinds
for left, right in ('ba', '\u0101\u0100', '\U00010301\U00010300'):
left *= 9
right *= 9
for delim in ('c', '\u0102', '\U00010302'):
self.checkequal([left + right],
left + right, 'split', delim)
self.checkequal([left, right],
left + delim + right, 'split', delim)
self.checkequal([left + right],
left + right, 'split', delim * 2)
self.checkequal([left, right],
left + delim * 2 + right, 'split', delim *2)
def test_rsplit(self):
string_tests.StringLikeTest.test_rsplit(self)
# test mixed kinds
for left, right in ('ba', 'юё', '\u0101\u0100', '\U00010301\U00010300'):
left *= 9
right *= 9
for delim in ('c', 'ы', '\u0102', '\U00010302'):
self.checkequal([left + right],
left + right, 'rsplit', delim)
self.checkequal([left, right],
left + delim + right, 'rsplit', delim)
self.checkequal([left + right],
left + right, 'rsplit', delim * 2)
self.checkequal([left, right],
left + delim * 2 + right, 'rsplit', delim *2)
# Check `None` as well:
self.checkequal([left + right],
left + right, 'rsplit', None)
def test_partition(self):
string_tests.StringLikeTest.test_partition(self)
# test mixed kinds
self.checkequal(('ABCDEFGH', '', ''), 'ABCDEFGH', 'partition', '\u4200')
for left, right in ('ba', '\u0101\u0100', '\U00010301\U00010300'):
left *= 9
right *= 9
for delim in ('c', '\u0102', '\U00010302'):
self.checkequal((left + right, '', ''),
left + right, 'partition', delim)
self.checkequal((left, delim, right),
left + delim + right, 'partition', delim)
self.checkequal((left + right, '', ''),
left + right, 'partition', delim * 2)
self.checkequal((left, delim * 2, right),
left + delim * 2 + right, 'partition', delim * 2)
def test_rpartition(self):
string_tests.StringLikeTest.test_rpartition(self)
# test mixed kinds
self.checkequal(('', '', 'ABCDEFGH'), 'ABCDEFGH', 'rpartition', '\u4200')
for left, right in ('ba', '\u0101\u0100', '\U00010301\U00010300'):
left *= 9
right *= 9
for delim in ('c', '\u0102', '\U00010302'):
self.checkequal(('', '', left + right),
left + right, 'rpartition', delim)
self.checkequal((left, delim, right),
left + delim + right, 'rpartition', delim)
self.checkequal(('', '', left + right),
left + right, 'rpartition', delim * 2)
self.checkequal((left, delim * 2, right),
left + delim * 2 + right, 'rpartition', delim * 2)
def test_join(self):
string_tests.StringLikeTest.test_join(self)
class MyWrapper:
def __init__(self, sval): self.sval = sval
def __str__(self): return self.sval
# mixed arguments
self.checkequalnofix('a b c d', ' ', '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('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('w x y z', ' ', 'join', string_tests.Sequence('wxyz'))
self.checkraises(TypeError, ' ', 'join', ['1', '2', MyWrapper('foo')])
self.checkraises(TypeError, ' ', 'join', ['1', '2', '3', bytes()])
self.checkraises(TypeError, ' ', 'join', [1, 2, 3])
self.checkraises(TypeError, ' ', 'join', ['1', '2', 3])
@unittest.skipIf(sys.maxsize > 2**32,
'needs too much memory on a 64-bit platform')
def test_join_overflow(self):
size = int(sys.maxsize**0.5) + 1
seq = ('A' * size,) * size
self.assertRaises(OverflowError, ''.join, seq)
def test_replace(self):
string_tests.StringLikeTest.test_replace(self)
# method call forwarded from str implementation because of unicode argument
self.checkequalnofix('one@two!three!', 'one!two!three!', 'replace', '!', '@', 1)
self.assertRaises(TypeError, 'replace'.replace, "r", 42)
# test mixed kinds
for left, right in ('ba', '\u0101\u0100', '\U00010301\U00010300'):
left *= 9
right *= 9
for delim in ('c', '\u0102', '\U00010302'):
for repl in ('d', '\u0103', '\U00010303'):
self.checkequal(left + right,
left + right, 'replace', delim, repl)
self.checkequal(left + repl + right,
left + delim + right,
'replace', delim, repl)
self.checkequal(left + right,
left + right, 'replace', delim * 2, repl)
self.checkequal(left + repl + right,
left + delim * 2 + right,
'replace', delim * 2, repl)
@support.cpython_only
def test_replace_id(self):
pattern = 'abc'
text = 'abc def'
self.assertIs(text.replace(pattern, pattern), text)
def test_repeat_id_preserving(self):
a = '123abc1@'
b = '456zyx-+'
self.assertEqual(id(a), id(a))
self.assertNotEqual(id(a), id(b))
self.assertNotEqual(id(a), id(a * -4))
self.assertNotEqual(id(a), id(a * 0))
self.assertEqual(id(a), id(a * 1))
self.assertEqual(id(a), id(1 * a))
self.assertNotEqual(id(a), id(a * 2))
class SubStr(str):
pass
s = SubStr('qwerty()')
self.assertEqual(id(s), id(s))
self.assertNotEqual(id(s), id(s * -4))
self.assertNotEqual(id(s), id(s * 0))
self.assertNotEqual(id(s), id(s * 1))
self.assertNotEqual(id(s), id(1 * s))
self.assertNotEqual(id(s), id(s * 2))
def test_bytes_comparison(self):
with warnings_helper.check_warnings():
warnings.simplefilter('ignore', BytesWarning)
self.assertEqual('abc' == b'abc', False)
self.assertEqual('abc' != b'abc', True)
self.assertEqual('abc' == bytearray(b'abc'), False)
self.assertEqual('abc' != bytearray(b'abc'), True)
def test_comparison(self):
# Comparisons:
self.assertEqual('abc', 'abc')
self.assertTrue('abcd' > 'abc')
self.assertTrue('abc' < 'abcd')
if 0:
# Move these tests to a Unicode collation module test...
# Testing UTF-16 code point order comparisons...
# No surrogates, no fixup required.
self.assertTrue('\u0061' < '\u20ac')
# Non surrogate below surrogate value, no fixup required
self.assertTrue('\u0061' < '\ud800\udc02')
# Non surrogate above surrogate value, fixup required
def test_lecmp(s, s2):
self.assertTrue(s < s2)
def test_fixup(s):
s2 = '\ud800\udc01'
test_lecmp(s, s2)
s2 = '\ud900\udc01'
test_lecmp(s, s2)
s2 = '\uda00\udc01'
test_lecmp(s, s2)
s2 = '\udb00\udc01'
test_lecmp(s, s2)
s2 = '\ud800\udd01'
test_lecmp(s, s2)
s2 = '\ud900\udd01'
test_lecmp(s, s2)
s2 = '\uda00\udd01'
test_lecmp(s, s2)
s2 = '\udb00\udd01'
test_lecmp(s, s2)
s2 = '\ud800\ude01'
test_lecmp(s, s2)
s2 = '\ud900\ude01'
test_lecmp(s, s2)
s2 = '\uda00\ude01'
test_lecmp(s, s2)
s2 = '\udb00\ude01'
test_lecmp(s, s2)
s2 = '\ud800\udfff'
test_lecmp(s, s2)
s2 = '\ud900\udfff'
test_lecmp(s, s2)
s2 = '\uda00\udfff'
test_lecmp(s, s2)
s2 = '\udb00\udfff'
test_lecmp(s, s2)
test_fixup('\ue000')
test_fixup('\uff61')
# Surrogates on both sides, no fixup required
self.assertTrue('\ud800\udc02' < '\ud84d\udc56')
def test_islower(self):
super().test_islower()
self.checkequalnofix(False, '\u1FFc', 'islower')
self.assertFalse('\u2167'.islower())
self.assertTrue('\u2177'.islower())
# non-BMP, uppercase
self.assertFalse('\U00010401'.islower())
self.assertFalse('\U00010427'.islower())
# non-BMP, lowercase
self.assertTrue('\U00010429'.islower())
self.assertTrue('\U0001044E'.islower())
# non-BMP, non-cased
self.assertFalse('\U0001F40D'.islower())
self.assertFalse('\U0001F46F'.islower())
def test_isupper(self):
super().test_isupper()
self.checkequalnofix(False, '\u1FFc', 'isupper')
self.assertTrue('\u2167'.isupper())
self.assertFalse('\u2177'.isupper())
# non-BMP, uppercase
self.assertTrue('\U00010401'.isupper())
self.assertTrue('\U00010427'.isupper())
# non-BMP, lowercase
self.assertFalse('\U00010429'.isupper())
self.assertFalse('\U0001044E'.isupper())
# non-BMP, non-cased
self.assertFalse('\U0001F40D'.isupper())
self.assertFalse('\U0001F46F'.isupper())
def test_istitle(self):
super().test_istitle()
self.checkequalnofix(True, '\u1FFc', 'istitle')
self.checkequalnofix(True, 'Greek \u1FFcitlecases ...', 'istitle')
# non-BMP, uppercase + lowercase
self.assertTrue('\U00010401\U00010429'.istitle())
self.assertTrue('\U00010427\U0001044E'.istitle())
# apparently there are no titlecased (Lt) non-BMP chars in Unicode 6
for ch in ['\U00010429', '\U0001044E', '\U0001F40D', '\U0001F46F']:
self.assertFalse(ch.istitle(), '{!a} is not title'.format(ch))
def test_isspace(self):
super().test_isspace()
self.checkequalnofix(True, '\u2000', 'isspace')
self.checkequalnofix(True, '\u200a', 'isspace')
self.checkequalnofix(False, '\u2014', 'isspace')
# There are no non-BMP whitespace chars as of Unicode 12.
for ch in ['\U00010401', '\U00010427', '\U00010429', '\U0001044E',
'\U0001F40D', '\U0001F46F']:
self.assertFalse(ch.isspace(), '{!a} is not space.'.format(ch))
@support.requires_resource('cpu')
def test_isspace_invariant(self):
for codepoint in range(sys.maxunicode + 1):
char = chr(codepoint)
bidirectional = unicodedata.bidirectional(char)
category = unicodedata.category(char)
self.assertEqual(char.isspace(),
(bidirectional in ('WS', 'B', 'S')
or category == 'Zs'))
def test_isalnum(self):
super().test_isalnum()
for ch in ['\U00010401', '\U00010427', '\U00010429', '\U0001044E',
'\U0001D7F6', '\U00011066', '\U000104A0', '\U0001F107']:
self.assertTrue(ch.isalnum(), '{!a} is alnum.'.format(ch))
def test_isalpha(self):
super().test_isalpha()
self.checkequalnofix(True, '\u1FFc', 'isalpha')
# non-BMP, cased
self.assertTrue('\U00010401'.isalpha())
self.assertTrue('\U00010427'.isalpha())
self.assertTrue('\U00010429'.isalpha())
self.assertTrue('\U0001044E'.isalpha())
# non-BMP, non-cased
self.assertFalse('\U0001F40D'.isalpha())
self.assertFalse('\U0001F46F'.isalpha())
def test_isascii(self):
super().test_isascii()
self.assertFalse("\u20ac".isascii())
self.assertFalse("\U0010ffff".isascii())
def test_isdecimal(self):
self.checkequalnofix(False, '', 'isdecimal')
self.checkequalnofix(False, 'a', 'isdecimal')
self.checkequalnofix(True, '0', 'isdecimal')
self.checkequalnofix(False, '\u2460', 'isdecimal') # CIRCLED DIGIT ONE
self.checkequalnofix(False, '\xbc', 'isdecimal') # VULGAR FRACTION ONE QUARTER
self.checkequalnofix(True, '\u0660', 'isdecimal') # ARABIC-INDIC DIGIT ZERO
self.checkequalnofix(True, '0123456789', 'isdecimal')
self.checkequalnofix(False, '0123456789a', 'isdecimal')
self.checkraises(TypeError, 'abc', 'isdecimal', 42)
for ch in ['\U00010401', '\U00010427', '\U00010429', '\U0001044E',
'\U0001F40D', '\U0001F46F', '\U00011065', '\U0001F107']:
self.assertFalse(ch.isdecimal(), '{!a} is not decimal.'.format(ch))
for ch in ['\U0001D7F6', '\U00011066', '\U000104A0']:
self.assertTrue(ch.isdecimal(), '{!a} is decimal.'.format(ch))
def test_isdigit(self):
super().test_isdigit()
self.checkequalnofix(True, '\u2460', 'isdigit')
self.checkequalnofix(False, '\xbc', 'isdigit')
self.checkequalnofix(True, '\u0660', 'isdigit')
for ch in ['\U00010401', '\U00010427', '\U00010429', '\U0001044E',
'\U0001F40D', '\U0001F46F', '\U00011065']:
self.assertFalse(ch.isdigit(), '{!a} is not a digit.'.format(ch))
for ch in ['\U0001D7F6', '\U00011066', '\U000104A0', '\U0001F107']:
self.assertTrue(ch.isdigit(), '{!a} is a digit.'.format(ch))
def test_isnumeric(self):
self.checkequalnofix(False, '', 'isnumeric')
self.checkequalnofix(False, 'a', 'isnumeric')
self.checkequalnofix(True, '0', 'isnumeric')
self.checkequalnofix(True, '\u2460', 'isnumeric')
self.checkequalnofix(True, '\xbc', 'isnumeric')
self.checkequalnofix(True, '\u0660', 'isnumeric')
self.checkequalnofix(True, '0123456789', 'isnumeric')
self.checkequalnofix(False, '0123456789a', 'isnumeric')
self.assertRaises(TypeError, "abc".isnumeric, 42)
for ch in ['\U00010401', '\U00010427', '\U00010429', '\U0001044E',
'\U0001F40D', '\U0001F46F']:
self.assertFalse(ch.isnumeric(), '{!a} is not numeric.'.format(ch))
for ch in ['\U00011065', '\U0001D7F6', '\U00011066',
'\U000104A0', '\U0001F107']:
self.assertTrue(ch.isnumeric(), '{!a} is numeric.'.format(ch))
def test_isidentifier(self):
self.assertTrue("a".isidentifier())
self.assertTrue("Z".isidentifier())
self.assertTrue("_".isidentifier())
self.assertTrue("b0".isidentifier())
self.assertTrue("bc".isidentifier())
self.assertTrue("b_".isidentifier())
2010-10-27 15:52:48 -03:00
self.assertTrue("µ".isidentifier())
self.assertTrue("𝔘𝔫𝔦𝔠𝔬𝔡𝔢".isidentifier())
self.assertFalse(" ".isidentifier())
self.assertFalse("[".isidentifier())
2010-10-27 15:52:48 -03:00
self.assertFalse("©".isidentifier())
self.assertFalse("0".isidentifier())
@support.cpython_only
@support.requires_legacy_unicode_capi
@unittest.skipIf(_testcapi is None, 'need _testcapi module')
def test_isidentifier_legacy(self):
u = '𝖀𝖓𝖎𝖈𝖔𝖉𝖊'
self.assertTrue(u.isidentifier())
with warnings_helper.check_warnings():
warnings.simplefilter('ignore', DeprecationWarning)
self.assertTrue(_testcapi.unicode_legacy_string(u).isidentifier())
def test_isprintable(self):
self.assertTrue("".isprintable())
self.assertTrue(" ".isprintable())
self.assertTrue("abcdefg".isprintable())
self.assertFalse("abcdefg\n".isprintable())
# some defined Unicode character
self.assertTrue("\u0374".isprintable())
# undefined character
self.assertFalse("\u0378".isprintable())
# single surrogate character
self.assertFalse("\ud800".isprintable())
self.assertTrue('\U0001F46F'.isprintable())
self.assertFalse('\U000E0020'.isprintable())
def test_surrogates(self):
for s in ('a\uD800b\uDFFF', 'a\uDFFFb\uD800',
'a\uD800b\uDFFFa', 'a\uDFFFb\uD800a'):
self.assertTrue(s.islower())
self.assertFalse(s.isupper())
self.assertFalse(s.istitle())
for s in ('A\uD800B\uDFFF', 'A\uDFFFB\uD800',
'A\uD800B\uDFFFA', 'A\uDFFFB\uD800A'):
self.assertFalse(s.islower())
self.assertTrue(s.isupper())
self.assertTrue(s.istitle())
for meth_name in ('islower', 'isupper', 'istitle'):
meth = getattr(str, meth_name)
for s in ('\uD800', '\uDFFF', '\uD800\uD800', '\uDFFF\uDFFF'):
self.assertFalse(meth(s), '%a.%s() is False' % (s, meth_name))
for meth_name in ('isalpha', 'isalnum', 'isdigit', 'isspace',
'isdecimal', 'isnumeric',
'isidentifier', 'isprintable'):
meth = getattr(str, meth_name)
for s in ('\uD800', '\uDFFF', '\uD800\uD800', '\uDFFF\uDFFF',
'a\uD800b\uDFFF', 'a\uDFFFb\uD800',
'a\uD800b\uDFFFa', 'a\uDFFFb\uD800a'):
self.assertFalse(meth(s), '%a.%s() is False' % (s, meth_name))
def test_lower(self):
string_tests.StringLikeTest.test_lower(self)
self.assertEqual('\U00010427'.lower(), '\U0001044F')
self.assertEqual('\U00010427\U00010427'.lower(),
'\U0001044F\U0001044F')
self.assertEqual('\U00010427\U0001044F'.lower(),
'\U0001044F\U0001044F')
self.assertEqual('X\U00010427x\U0001044F'.lower(),
'x\U0001044Fx\U0001044F')
self.assertEqual(''.lower(), '')
self.assertEqual('\u0130'.lower(), '\u0069\u0307')
# Special case for GREEK CAPITAL LETTER SIGMA U+03A3
self.assertEqual('\u03a3'.lower(), '\u03c3')
self.assertEqual('\u0345\u03a3'.lower(), '\u0345\u03c3')
self.assertEqual('A\u0345\u03a3'.lower(), 'a\u0345\u03c2')
self.assertEqual('A\u0345\u03a3a'.lower(), 'a\u0345\u03c3a')
self.assertEqual('A\u0345\u03a3'.lower(), 'a\u0345\u03c2')
self.assertEqual('A\u03a3\u0345'.lower(), 'a\u03c2\u0345')
self.assertEqual('\u03a3\u0345 '.lower(), '\u03c3\u0345 ')
self.assertEqual('\U0008fffe'.lower(), '\U0008fffe')
self.assertEqual('\u2177'.lower(), '\u2177')
2012-01-14 14:23:30 -04:00
def test_casefold(self):
self.assertEqual('hello'.casefold(), 'hello')
self.assertEqual('hELlo'.casefold(), 'hello')
self.assertEqual('ß'.casefold(), 'ss')
self.assertEqual(''.casefold(), 'fi')
self.assertEqual('\u03a3'.casefold(), '\u03c3')
self.assertEqual('A\u0345\u03a3'.casefold(), 'a\u03b9\u03c3')
2012-08-05 19:05:34 -03:00
self.assertEqual('\u00b5'.casefold(), '\u03bc')
2012-01-14 14:23:30 -04:00
def test_upper(self):
string_tests.StringLikeTest.test_upper(self)
self.assertEqual('\U0001044F'.upper(), '\U00010427')
self.assertEqual('\U0001044F\U0001044F'.upper(),
'\U00010427\U00010427')
self.assertEqual('\U00010427\U0001044F'.upper(),
'\U00010427\U00010427')
self.assertEqual('X\U00010427x\U0001044F'.upper(),
'X\U00010427X\U00010427')
self.assertEqual(''.upper(), 'FI')
self.assertEqual('\u0130'.upper(), '\u0130')
self.assertEqual('\u03a3'.upper(), '\u03a3')
self.assertEqual('ß'.upper(), 'SS')
self.assertEqual('\u1fd2'.upper(), '\u0399\u0308\u0300')
self.assertEqual('\U0008fffe'.upper(), '\U0008fffe')
self.assertEqual('\u2177'.upper(), '\u2167')
def test_capitalize(self):
string_tests.StringLikeTest.test_capitalize(self)
self.assertEqual('\U0001044F'.capitalize(), '\U00010427')
self.assertEqual('\U0001044F\U0001044F'.capitalize(),
'\U00010427\U0001044F')
self.assertEqual('\U00010427\U0001044F'.capitalize(),
'\U00010427\U0001044F')
self.assertEqual('\U0001044F\U00010427'.capitalize(),
'\U00010427\U0001044F')
self.assertEqual('X\U00010427x\U0001044F'.capitalize(),
'X\U0001044Fx\U0001044F')
self.assertEqual('h\u0130'.capitalize(), 'H\u0069\u0307')
exp = '\u0399\u0308\u0300\u0069\u0307'
self.assertEqual('\u1fd2\u0130'.capitalize(), exp)
self.assertEqual('finnish'.capitalize(), 'Finnish')
self.assertEqual('A\u0345\u03a3'.capitalize(), 'A\u0345\u03c2')
def test_title(self):
super().test_title()
self.assertEqual('\U0001044F'.title(), '\U00010427')
self.assertEqual('\U0001044F\U0001044F'.title(),
'\U00010427\U0001044F')
self.assertEqual('\U0001044F\U0001044F \U0001044F\U0001044F'.title(),
'\U00010427\U0001044F \U00010427\U0001044F')
self.assertEqual('\U00010427\U0001044F \U00010427\U0001044F'.title(),
'\U00010427\U0001044F \U00010427\U0001044F')
self.assertEqual('\U0001044F\U00010427 \U0001044F\U00010427'.title(),
'\U00010427\U0001044F \U00010427\U0001044F')
self.assertEqual('X\U00010427x\U0001044F X\U00010427x\U0001044F'.title(),
'X\U0001044Fx\U0001044F X\U0001044Fx\U0001044F')
self.assertEqual('fiNNISH'.title(), 'Finnish')
self.assertEqual('A\u03a3 \u1fa1xy'.title(), 'A\u03c2 \u1fa9xy')
self.assertEqual('A\u03a3A'.title(), 'A\u03c3a')
def test_swapcase(self):
string_tests.StringLikeTest.test_swapcase(self)
self.assertEqual('\U0001044F'.swapcase(), '\U00010427')
self.assertEqual('\U00010427'.swapcase(), '\U0001044F')
self.assertEqual('\U0001044F\U0001044F'.swapcase(),
'\U00010427\U00010427')
self.assertEqual('\U00010427\U0001044F'.swapcase(),
'\U0001044F\U00010427')
self.assertEqual('\U0001044F\U00010427'.swapcase(),
'\U00010427\U0001044F')
self.assertEqual('X\U00010427x\U0001044F'.swapcase(),
'x\U0001044FX\U00010427')
self.assertEqual(''.swapcase(), 'FI')
self.assertEqual('\u0130'.swapcase(), '\u0069\u0307')
# Special case for GREEK CAPITAL LETTER SIGMA U+03A3
self.assertEqual('\u03a3'.swapcase(), '\u03c3')
self.assertEqual('\u0345\u03a3'.swapcase(), '\u0399\u03c3')
self.assertEqual('A\u0345\u03a3'.swapcase(), 'a\u0399\u03c2')
self.assertEqual('A\u0345\u03a3a'.swapcase(), 'a\u0399\u03c3A')
self.assertEqual('A\u0345\u03a3'.swapcase(), 'a\u0399\u03c2')
self.assertEqual('A\u03a3\u0345'.swapcase(), 'a\u03c2\u0399')
self.assertEqual('\u03a3\u0345 '.swapcase(), '\u03c3\u0399 ')
self.assertEqual('\u03a3'.swapcase(), '\u03c3')
self.assertEqual('ß'.swapcase(), 'SS')
self.assertEqual('\u1fd2'.swapcase(), '\u0399\u0308\u0300')
def test_center(self):
string_tests.StringLikeTest.test_center(self)
self.assertEqual('x'.center(2, '\U0010FFFF'),
'x\U0010FFFF')
self.assertEqual('x'.center(3, '\U0010FFFF'),
'\U0010FFFFx\U0010FFFF')
self.assertEqual('x'.center(4, '\U0010FFFF'),
'\U0010FFFFx\U0010FFFF\U0010FFFF')
@unittest.skipUnless(sys.maxsize == 2**31 - 1, "requires 32-bit system")
2014-10-15 14:39:46 -03:00
@support.cpython_only
def test_case_operation_overflow(self):
# Issue #22643
size = 2**32//12 + 1
try:
s = "ü" * size
except MemoryError:
self.skipTest('no enough memory (%.0f MiB required)' % (size / 2**20))
try:
self.assertRaises(OverflowError, s.upper)
finally:
del s
def test_contains(self):
# Testing Unicode contains method
self.assertIn('a', 'abdb')
self.assertIn('a', 'bdab')
self.assertIn('a', 'bdaba')
self.assertIn('a', 'bdba')
self.assertNotIn('a', 'bdb')
self.assertIn('a', 'bdba')
self.assertIn('a', ('a',1,None))
self.assertIn('a', (1,None,'a'))
self.assertIn('a', ('a',1,None))
self.assertIn('a', (1,None,'a'))
self.assertNotIn('a', ('x',1,'y'))
self.assertNotIn('a', ('x',1,None))
self.assertNotIn('abcd', 'abcxxxx')
self.assertIn('ab', 'abcd')
self.assertIn('ab', 'abc')
self.assertIn('ab', (1,None,'ab'))
self.assertIn('', 'abc')
self.assertIn('', '')
self.assertIn('', 'abc')
self.assertNotIn('\0', 'abc')
self.assertIn('\0', '\0abc')
self.assertIn('\0', 'abc\0')
self.assertIn('a', '\0abc')
self.assertIn('asdf', 'asdf')
self.assertNotIn('asdf', 'asd')
self.assertNotIn('asdf', '')
self.assertRaises(TypeError, "abc".__contains__)
# test mixed kinds
for fill in ('a', '\u0100', '\U00010300'):
fill *= 9
for delim in ('c', '\u0102', '\U00010302'):
self.assertNotIn(delim, fill)
self.assertIn(delim, fill + delim)
self.assertNotIn(delim * 2, fill)
self.assertIn(delim * 2, fill + delim * 2)
2013-06-12 03:20:44 -03:00
def test_issue18183(self):
'\U00010000\U00100000'.lower()
'\U00010000\U00100000'.casefold()
'\U00010000\U00100000'.upper()
'\U00010000\U00100000'.capitalize()
'\U00010000\U00100000'.title()
'\U00010000\U00100000'.swapcase()
'\U00100000'.center(3, '\U00010000')
'\U00100000'.ljust(3, '\U00010000')
'\U00100000'.rjust(3, '\U00010000')
def test_format(self):
self.assertEqual(''.format(), '')
self.assertEqual('a'.format(), 'a')
self.assertEqual('ab'.format(), 'ab')
self.assertEqual('a{{'.format(), 'a{')
self.assertEqual('a}}'.format(), 'a}')
self.assertEqual('{{b'.format(), '{b')
self.assertEqual('}}b'.format(), '}b')
self.assertEqual('a{{b'.format(), 'a{b')
# examples from the PEP:
import datetime
self.assertEqual("My name is {0}".format('Fred'), "My name is Fred")
self.assertEqual("My name is {0[name]}".format(dict(name='Fred')),
"My name is Fred")
self.assertEqual("My name is {0} :-{{}}".format('Fred'),
"My name is Fred :-{}")
d = datetime.date(2007, 8, 18)
self.assertEqual("The year is {0.year}".format(d),
"The year is 2007")
# classes we'll use for testing
class C:
def __init__(self, x=100):
self._x = x
def __format__(self, spec):
return spec
class D:
def __init__(self, x):
self.x = x
def __format__(self, spec):
return str(self.x)
# class with __str__, but no __format__
class E:
def __init__(self, x):
self.x = x
def __str__(self):
return 'E(' + self.x + ')'
# class with __repr__, but no __format__ or __str__
class F:
def __init__(self, x):
self.x = x
def __repr__(self):
return 'F(' + self.x + ')'
# class with __format__ that forwards to string, for some format_spec's
class G:
def __init__(self, x):
self.x = x
def __str__(self):
return "string is " + self.x
def __format__(self, format_spec):
if format_spec == 'd':
return 'G(' + self.x + ')'
return object.__format__(self, format_spec)
2007-08-27 16:07:22 -03:00
class I(datetime.date):
def __format__(self, format_spec):
return self.strftime(format_spec)
class J(int):
def __format__(self, format_spec):
return int.__format__(self * 2, format_spec)
class M:
def __init__(self, x):
self.x = x
def __repr__(self):
return 'M(' + self.x + ')'
__str__ = None
class N:
def __init__(self, x):
self.x = x
def __repr__(self):
return 'N(' + self.x + ')'
__format__ = None
self.assertEqual(''.format(), '')
self.assertEqual('abc'.format(), 'abc')
self.assertEqual('{0}'.format('abc'), 'abc')
self.assertEqual('{0:}'.format('abc'), 'abc')
# self.assertEqual('{ 0 }'.format('abc'), 'abc')
self.assertEqual('X{0}'.format('abc'), 'Xabc')
self.assertEqual('{0}X'.format('abc'), 'abcX')
self.assertEqual('X{0}Y'.format('abc'), 'XabcY')
self.assertEqual('{1}'.format(1, 'abc'), 'abc')
self.assertEqual('X{1}'.format(1, 'abc'), 'Xabc')
self.assertEqual('{1}X'.format(1, 'abc'), 'abcX')
self.assertEqual('X{1}Y'.format(1, 'abc'), 'XabcY')
self.assertEqual('{0}'.format(-15), '-15')
self.assertEqual('{0}{1}'.format(-15, 'abc'), '-15abc')
self.assertEqual('{0}X{1}'.format(-15, 'abc'), '-15Xabc')
self.assertEqual('{{'.format(), '{')
self.assertEqual('}}'.format(), '}')
self.assertEqual('{{}}'.format(), '{}')
self.assertEqual('{{x}}'.format(), '{x}')
self.assertEqual('{{{0}}}'.format(123), '{123}')
self.assertEqual('{{{{0}}}}'.format(), '{{0}}')
self.assertEqual('}}{{'.format(), '}{')
self.assertEqual('}}x{{'.format(), '}x{')
# weird field names
self.assertEqual("{0[foo-bar]}".format({'foo-bar':'baz'}), 'baz')
self.assertEqual("{0[foo bar]}".format({'foo bar':'baz'}), 'baz')
self.assertEqual("{0[ ]}".format({' ':3}), '3')
self.assertEqual('{foo._x}'.format(foo=C(20)), '20')
self.assertEqual('{1}{0}'.format(D(10), D(20)), '2010')
self.assertEqual('{0._x.x}'.format(C(D('abc'))), 'abc')
self.assertEqual('{0[0]}'.format(['abc', 'def']), 'abc')
self.assertEqual('{0[1]}'.format(['abc', 'def']), 'def')
self.assertEqual('{0[1][0]}'.format(['abc', ['def']]), 'def')
self.assertEqual('{0[1][0].x}'.format(['abc', [D('def')]]), 'def')
# strings
self.assertEqual('{0:.3s}'.format('abc'), 'abc')
self.assertEqual('{0:.3s}'.format('ab'), 'ab')
self.assertEqual('{0:.3s}'.format('abcdef'), 'abc')
self.assertEqual('{0:.0s}'.format('abcdef'), '')
self.assertEqual('{0:3.3s}'.format('abc'), 'abc')
self.assertEqual('{0:2.3s}'.format('abc'), 'abc')
self.assertEqual('{0:2.2s}'.format('abc'), 'ab')
self.assertEqual('{0:3.2s}'.format('abc'), 'ab ')
self.assertEqual('{0:x<0s}'.format('result'), 'result')
self.assertEqual('{0:x<5s}'.format('result'), 'result')
self.assertEqual('{0:x<6s}'.format('result'), 'result')
self.assertEqual('{0:x<7s}'.format('result'), 'resultx')
self.assertEqual('{0:x<8s}'.format('result'), 'resultxx')
self.assertEqual('{0: <7s}'.format('result'), 'result ')
self.assertEqual('{0:<7s}'.format('result'), 'result ')
self.assertEqual('{0:>7s}'.format('result'), ' result')
self.assertEqual('{0:>8s}'.format('result'), ' result')
self.assertEqual('{0:^8s}'.format('result'), ' result ')
self.assertEqual('{0:^9s}'.format('result'), ' result ')
self.assertEqual('{0:^10s}'.format('result'), ' result ')
self.assertEqual('{0:8s}'.format('result'), 'result ')
self.assertEqual('{0:0s}'.format('result'), 'result')
self.assertEqual('{0:08s}'.format('result'), 'result00')
self.assertEqual('{0:<08s}'.format('result'), 'result00')
self.assertEqual('{0:>08s}'.format('result'), '00result')
self.assertEqual('{0:^08s}'.format('result'), '0result0')
self.assertEqual('{0:10000}'.format('a'), 'a' + ' ' * 9999)
self.assertEqual('{0:10000}'.format(''), ' ' * 10000)
self.assertEqual('{0:10000000}'.format(''), ' ' * 10000000)
# issue 12546: use \x00 as a fill character
self.assertEqual('{0:\x00<6s}'.format('foo'), 'foo\x00\x00\x00')
self.assertEqual('{0:\x01<6s}'.format('foo'), 'foo\x01\x01\x01')
self.assertEqual('{0:\x00^6s}'.format('foo'), '\x00foo\x00\x00')
self.assertEqual('{0:^6s}'.format('foo'), ' foo ')
self.assertEqual('{0:\x00<6}'.format(3), '3\x00\x00\x00\x00\x00')
self.assertEqual('{0:\x01<6}'.format(3), '3\x01\x01\x01\x01\x01')
self.assertEqual('{0:\x00^6}'.format(3), '\x00\x003\x00\x00\x00')
self.assertEqual('{0:<6}'.format(3), '3 ')
self.assertEqual('{0:\x00<6}'.format(3.14), '3.14\x00\x00')
self.assertEqual('{0:\x01<6}'.format(3.14), '3.14\x01\x01')
self.assertEqual('{0:\x00^6}'.format(3.14), '\x003.14\x00')
self.assertEqual('{0:^6}'.format(3.14), ' 3.14 ')
self.assertEqual('{0:\x00<12}'.format(3+2.0j), '(3+2j)\x00\x00\x00\x00\x00\x00')
self.assertEqual('{0:\x01<12}'.format(3+2.0j), '(3+2j)\x01\x01\x01\x01\x01\x01')
self.assertEqual('{0:\x00^12}'.format(3+2.0j), '\x00\x00\x00(3+2j)\x00\x00\x00')
self.assertEqual('{0:^12}'.format(3+2.0j), ' (3+2j) ')
# format specifiers for user defined type
self.assertEqual('{0:abc}'.format(C()), 'abc')
# !r, !s and !a coercions
self.assertEqual('{0!s}'.format('Hello'), 'Hello')
self.assertEqual('{0!s:}'.format('Hello'), 'Hello')
self.assertEqual('{0!s:15}'.format('Hello'), 'Hello ')
self.assertEqual('{0!s:15s}'.format('Hello'), 'Hello ')
self.assertEqual('{0!r}'.format('Hello'), "'Hello'")
self.assertEqual('{0!r:}'.format('Hello'), "'Hello'")
self.assertEqual('{0!r}'.format(F('Hello')), 'F(Hello)')
self.assertEqual('{0!r}'.format('\u0378'), "'\\u0378'") # nonprintable
self.assertEqual('{0!r}'.format('\u0374'), "'\u0374'") # printable
self.assertEqual('{0!r}'.format(F('\u0374')), 'F(\u0374)')
self.assertEqual('{0!a}'.format('Hello'), "'Hello'")
self.assertEqual('{0!a}'.format('\u0378'), "'\\u0378'") # nonprintable
self.assertEqual('{0!a}'.format('\u0374'), "'\\u0374'") # printable
self.assertEqual('{0!a:}'.format('Hello'), "'Hello'")
self.assertEqual('{0!a}'.format(F('Hello')), 'F(Hello)')
self.assertEqual('{0!a}'.format(F('\u0374')), 'F(\\u0374)')
# test fallback to object.__format__
self.assertEqual('{0}'.format({}), '{}')
self.assertEqual('{0}'.format([]), '[]')
self.assertEqual('{0}'.format([1]), '[1]')
self.assertEqual('{0:d}'.format(G('data')), 'G(data)')
self.assertEqual('{0!s}'.format(G('data')), 'string is data')
self.assertRaises(TypeError, '{0:^10}'.format, E('data'))
self.assertRaises(TypeError, '{0:^10s}'.format, E('data'))
self.assertRaises(TypeError, '{0:>15s}'.format, G('data'))
2007-08-27 16:07:22 -03:00
self.assertEqual("{0:date: %Y-%m-%d}".format(I(year=2007,
month=8,
day=27)),
"date: 2007-08-27")
# test deriving from a builtin type and overriding __format__
self.assertEqual("{0}".format(J(10)), "20")
# string format specifiers
self.assertEqual('{0:}'.format('a'), 'a')
# computed format specifiers
self.assertEqual("{0:.{1}}".format('hello world', 5), 'hello')
self.assertEqual("{0:.{1}s}".format('hello world', 5), 'hello')
self.assertEqual("{0:.{precision}s}".format('hello world', precision=5), 'hello')
self.assertEqual("{0:{width}.{precision}s}".format('hello world', width=10, precision=5), 'hello ')
self.assertEqual("{0:{width}.{precision}s}".format('hello world', width='10', precision='5'), 'hello ')
# test various errors
self.assertRaises(ValueError, '{'.format)
self.assertRaises(ValueError, '}'.format)
self.assertRaises(ValueError, 'a{'.format)
self.assertRaises(ValueError, 'a}'.format)
self.assertRaises(ValueError, '{a'.format)
self.assertRaises(ValueError, '}a'.format)
self.assertRaises(IndexError, '{0}'.format)
self.assertRaises(IndexError, '{1}'.format, 'abc')
self.assertRaises(KeyError, '{x}'.format)
self.assertRaises(ValueError, "}{".format)
self.assertRaises(ValueError, "abc{0:{}".format)
self.assertRaises(ValueError, "{0".format)
self.assertRaises(IndexError, "{0.}".format)
self.assertRaises(ValueError, "{0.}".format, 0)
self.assertRaises(ValueError, "{0[}".format)
self.assertRaises(ValueError, "{0[}".format, [])
self.assertRaises(KeyError, "{0]}".format)
self.assertRaises(ValueError, "{0.[]}".format, 0)
self.assertRaises(ValueError, "{0..foo}".format, 0)
self.assertRaises(ValueError, "{0[0}".format, 0)
self.assertRaises(ValueError, "{0[0:foo}".format, 0)
self.assertRaises(KeyError, "{c]}".format)
self.assertRaises(ValueError, "{{ {{{0}}".format, 0)
self.assertRaises(ValueError, "{0}}".format, 0)
self.assertRaises(KeyError, "{foo}".format, bar=3)
self.assertRaises(ValueError, "{0!x}".format, 3)
self.assertRaises(ValueError, "{0!}".format, 0)
self.assertRaises(ValueError, "{0!rs}".format, 0)
self.assertRaises(ValueError, "{!}".format)
self.assertRaises(IndexError, "{:}".format)
self.assertRaises(IndexError, "{:s}".format)
self.assertRaises(IndexError, "{}".format)
big = "23098475029384702983476098230754973209482573"
self.assertRaises(ValueError, ("{" + big + "}").format)
self.assertRaises(ValueError, ("{[" + big + "]}").format, [0])
# test number formatter errors:
self.assertRaises(ValueError, '{0:x}'.format, 1j)
self.assertRaises(ValueError, '{0:x}'.format, 1.0)
self.assertRaises(ValueError, '{0:X}'.format, 1j)
self.assertRaises(ValueError, '{0:X}'.format, 1.0)
self.assertRaises(ValueError, '{0:o}'.format, 1j)
self.assertRaises(ValueError, '{0:o}'.format, 1.0)
self.assertRaises(ValueError, '{0:u}'.format, 1j)
self.assertRaises(ValueError, '{0:u}'.format, 1.0)
self.assertRaises(ValueError, '{0:i}'.format, 1j)
self.assertRaises(ValueError, '{0:i}'.format, 1.0)
self.assertRaises(ValueError, '{0:d}'.format, 1j)
self.assertRaises(ValueError, '{0:d}'.format, 1.0)
# issue 6089
self.assertRaises(ValueError, "{0[0]x}".format, [None])
self.assertRaises(ValueError, "{0[0](10)}".format, [None])
# can't have a replacement on the field name portion
self.assertRaises(TypeError, '{0[{1}]}'.format, 'abcdefg', 4)
# exceed maximum recursion depth
self.assertRaises(ValueError, "{0:{1:{2}}}".format, 'abc', 's', '')
self.assertRaises(ValueError, "{0:{1:{2:{3:{4:{5:{6}}}}}}}".format,
0, 1, 2, 3, 4, 5, 6, 7)
# string format spec errors
sign_msg = "Sign not allowed in string format specifier"
self.assertRaisesRegex(ValueError, sign_msg, "{0:-s}".format, '')
self.assertRaisesRegex(ValueError, sign_msg, format, "", "-")
space_msg = "Space not allowed in string format specifier"
self.assertRaisesRegex(ValueError, space_msg, "{: }".format, '')
self.assertRaises(ValueError, "{0:=s}".format, '')
# Alternate formatting is not supported
self.assertRaises(ValueError, format, '', '#')
self.assertRaises(ValueError, format, '', '#20')
# Non-ASCII
self.assertEqual("{0:s}{1:s}".format("ABC", "\u0410\u0411\u0412"),
'ABC\u0410\u0411\u0412')
self.assertEqual("{0:.3s}".format("ABC\u0410\u0411\u0412"),
'ABC')
self.assertEqual("{0:.0s}".format("ABC\u0410\u0411\u0412"),
'')
self.assertEqual("{[{}]}".format({"{}": 5}), "5")
self.assertEqual("{[{}]}".format({"{}" : "a"}), "a")
self.assertEqual("{[{]}".format({"{" : "a"}), "a")
self.assertEqual("{[}]}".format({"}" : "a"}), "a")
self.assertEqual("{[[]}".format({"[" : "a"}), "a")
self.assertEqual("{[!]}".format({"!" : "a"}), "a")
self.assertRaises(ValueError, "{a{}b}".format, 42)
self.assertRaises(ValueError, "{a{b}".format, 42)
self.assertRaises(ValueError, "{[}".format, 42)
self.assertEqual("0x{:0{:d}X}".format(0x0,16), "0x0000000000000000")
# Blocking fallback
m = M('data')
self.assertEqual("{!r}".format(m), 'M(data)')
self.assertRaises(TypeError, "{!s}".format, m)
self.assertRaises(TypeError, "{}".format, m)
n = N('data')
self.assertEqual("{!r}".format(n), 'N(data)')
self.assertEqual("{!s}".format(n), 'N(data)')
self.assertRaises(TypeError, "{}".format, n)
def test_format_map(self):
self.assertEqual(''.format_map({}), '')
self.assertEqual('a'.format_map({}), 'a')
self.assertEqual('ab'.format_map({}), 'ab')
self.assertEqual('a{{'.format_map({}), 'a{')
self.assertEqual('a}}'.format_map({}), 'a}')
self.assertEqual('{{b'.format_map({}), '{b')
self.assertEqual('}}b'.format_map({}), '}b')
self.assertEqual('a{{b'.format_map({}), 'a{b')
# using mappings
class Mapping(dict):
def __missing__(self, key):
return key
self.assertEqual('{hello}'.format_map(Mapping()), 'hello')
self.assertEqual('{a} {world}'.format_map(Mapping(a='hello')), 'hello world')
class InternalMapping:
def __init__(self):
self.mapping = {'a': 'hello'}
def __getitem__(self, key):
return self.mapping[key]
self.assertEqual('{a}'.format_map(InternalMapping()), 'hello')
class C:
def __init__(self, x=100):
self._x = x
def __format__(self, spec):
return spec
self.assertEqual('{foo._x}'.format_map({'foo': C(20)}), '20')
# test various errors
self.assertRaises(TypeError, ''.format_map)
self.assertRaises(TypeError, 'a'.format_map)
self.assertRaises(ValueError, '{'.format_map, {})
self.assertRaises(ValueError, '}'.format_map, {})
self.assertRaises(ValueError, 'a{'.format_map, {})
self.assertRaises(ValueError, 'a}'.format_map, {})
self.assertRaises(ValueError, '{a'.format_map, {})
self.assertRaises(ValueError, '}a'.format_map, {})
# issue #12579: can't supply positional params to format_map
self.assertRaises(ValueError, '{}'.format_map, {'a' : 2})
self.assertRaises(ValueError, '{}'.format_map, 'a')
self.assertRaises(ValueError, '{a} {}'.format_map, {"a" : 2, "b" : 1})
class BadMapping:
def __getitem__(self, key):
return 1/0
self.assertRaises(KeyError, '{a}'.format_map, {})
self.assertRaises(TypeError, '{a}'.format_map, [])
self.assertRaises(ZeroDivisionError, '{a}'.format_map, BadMapping())
def test_format_huge_precision(self):
format_string = ".{}f".format(sys.maxsize + 1)
with self.assertRaises(ValueError):
result = format(2.34, format_string)
def test_format_huge_width(self):
format_string = "{}f".format(sys.maxsize + 1)
with self.assertRaises(ValueError):
result = format(2.34, format_string)
def test_format_huge_item_number(self):
format_string = "{{{}:.6f}}".format(sys.maxsize + 1)
with self.assertRaises(ValueError):
result = format_string.format(2.34)
def test_format_auto_numbering(self):
class C:
def __init__(self, x=100):
self._x = x
def __format__(self, spec):
return spec
self.assertEqual('{}'.format(10), '10')
self.assertEqual('{:5}'.format('s'), 's ')
self.assertEqual('{!r}'.format('s'), "'s'")
self.assertEqual('{._x}'.format(C(10)), '10')
self.assertEqual('{[1]}'.format([1, 2]), '2')
self.assertEqual('{[a]}'.format({'a':4, 'b':2}), '4')
self.assertEqual('a{}b{}c'.format(0, 1), 'a0b1c')
self.assertEqual('a{:{}}b'.format('x', '^10'), 'a x b')
self.assertEqual('a{:{}x}b'.format(20, '#'), 'a0x14b')
# can't mix and match numbering and auto-numbering
self.assertRaises(ValueError, '{}{1}'.format, 1, 2)
self.assertRaises(ValueError, '{1}{}'.format, 1, 2)
self.assertRaises(ValueError, '{:{1}}'.format, 1, 2)
self.assertRaises(ValueError, '{0:{}}'.format, 1, 2)
# can mix and match auto-numbering and named
self.assertEqual('{f}{}'.format(4, f='test'), 'test4')
self.assertEqual('{}{f}'.format(4, f='test'), '4test')
self.assertEqual('{:{f}}{g}{}'.format(1, 3, g='g', f=2), ' 1g3')
self.assertEqual('{f:{}}{}{g}'.format(2, 4, f=1, g='g'), ' 14g')
def test_formatting(self):
string_tests.StringLikeTest.test_formatting(self)
# Testing Unicode formatting strings...
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')
self.assertEqual("%s, %s, %i, %f, %5.2f" % ("abc", "abc", -1, -2, 3.5), 'abc, abc, -1, -2.000000, 3.50')
self.assertEqual("%s, %s, %i, %f, %5.2f" % ("abc", "abc", -1, -2, 3.57), 'abc, abc, -1, -2.000000, 3.57')
self.assertEqual("%s, %s, %i, %f, %5.2f" % ("abc", "abc", -1, -2, 1003.57), 'abc, abc, -1, -2.000000, 1003.57')
self.assertEqual("%r, %r" % (b"abc", "abc"), "b'abc', 'abc'")
self.assertEqual("%r" % ("\u1234",), "'\u1234'")
self.assertEqual("%a" % ("\u1234",), "'\\u1234'")
self.assertEqual("%(x)s, %(y)s" % {'x':"abc", 'y':"def"}, 'abc, def')
self.assertEqual("%(x)s, %(\xfc)s" % {'x':"abc", '\xfc':"def"}, 'abc, def')
2003-03-31 14:18:41 -04:00
self.assertEqual('%c' % 0x1234, '\u1234')
self.assertEqual('%c' % 0x21483, '\U00021483')
self.assertRaises(OverflowError, "%c".__mod__, (0x110000,))
self.assertEqual('%c' % '\U00021483', '\U00021483')
self.assertRaises(TypeError, "%c".__mod__, "aa")
self.assertRaises(ValueError, "%.1\u1032f".__mod__, (1.0/3))
self.assertRaises(TypeError, "%i".__mod__, "aa")
# formatting jobs delegated from the string implementation:
self.assertEqual('...%(foo)s...' % {'foo':"abc"}, '...abc...')
self.assertEqual('...%(foo)s...' % {'foo':"abc"}, '...abc...')
self.assertEqual('...%(foo)s...' % {'foo':"abc"}, '...abc...')
self.assertEqual('...%(foo)s...' % {'foo':"abc"}, '...abc...')
self.assertEqual('...%(foo)s...' % {'foo':"abc",'def':123}, '...abc...')
self.assertEqual('...%(foo)s...' % {'foo':"abc",'def':123}, '...abc...')
self.assertEqual('...%s...%s...%s...%s...' % (1,2,3,"abc"), '...1...2...3...abc...')
self.assertEqual('...%%...%%s...%s...%s...%s...%s...' % (1,2,3,"abc"), '...%...%s...1...2...3...abc...')
self.assertEqual('...%s...' % "abc", '...abc...')
self.assertEqual('%*s' % (5,'abc',), ' abc')
self.assertEqual('%*s' % (-5,'abc',), 'abc ')
self.assertEqual('%*.*s' % (5,2,'abc',), ' ab')
self.assertEqual('%*.*s' % (5,3,'abc',), ' abc')
self.assertEqual('%i %*.*s' % (10, 5,3,'abc',), '10 abc')
self.assertEqual('%i%s %*.*s' % (10, 3, 5, 3, 'abc',), '103 abc')
self.assertEqual('%c' % 'a', 'a')
class Wrapper:
def __str__(self):
return '\u1234'
self.assertEqual('%s' % Wrapper(), '\u1234')
# issue 3382
NAN = float('nan')
INF = float('inf')
self.assertEqual('%f' % NAN, 'nan')
self.assertEqual('%F' % NAN, 'NAN')
self.assertEqual('%f' % INF, 'inf')
self.assertEqual('%F' % INF, 'INF')
# PEP 393
self.assertEqual('%.1s' % "a\xe9\u20ac", 'a')
self.assertEqual('%.2s' % "a\xe9\u20ac", 'a\xe9')
#issue 19995
class PseudoInt:
def __init__(self, value):
self.value = int(value)
def __int__(self):
return self.value
def __index__(self):
return self.value
class PseudoFloat:
def __init__(self, value):
self.value = float(value)
def __int__(self):
return int(self.value)
pi = PseudoFloat(3.1415)
letter_m = PseudoInt(109)
self.assertEqual('%x' % 42, '2a')
self.assertEqual('%X' % 15, 'F')
self.assertEqual('%o' % 9, '11')
self.assertEqual('%c' % 109, 'm')
self.assertEqual('%x' % letter_m, '6d')
self.assertEqual('%X' % letter_m, '6D')
self.assertEqual('%o' % letter_m, '155')
self.assertEqual('%c' % letter_m, 'm')
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, '%o format: an integer is required, not float', operator.mod, '%o', 1.79)
self.assertRaisesRegex(TypeError, '%x format: an integer is required, not PseudoFloat', operator.mod, '%x', pi)
self.assertRaisesRegex(TypeError, '%x format: an integer is required, not complex', operator.mod, '%x', 3j)
self.assertRaisesRegex(TypeError, '%X format: an integer is required, not complex', operator.mod, '%X', 2j)
self.assertRaisesRegex(TypeError, '%o format: an integer is required, not complex', operator.mod, '%o', 1j)
self.assertRaisesRegex(TypeError, '%u format: a real number is required, not complex', operator.mod, '%u', 3j)
self.assertRaisesRegex(TypeError, '%i format: a real number is required, not complex', operator.mod, '%i', 2j)
self.assertRaisesRegex(TypeError, '%d format: a real number is required, not complex', operator.mod, '%d', 1j)
self.assertRaisesRegex(TypeError, '%c requires int or char', operator.mod, '%c', pi)
class RaisingNumber:
def __int__(self):
raise RuntimeError('int') # should not be `TypeError`
def __index__(self):
raise RuntimeError('index') # should not be `TypeError`
rn = RaisingNumber()
self.assertRaisesRegex(RuntimeError, 'int', operator.mod, '%d', rn)
self.assertRaisesRegex(RuntimeError, 'int', operator.mod, '%i', rn)
self.assertRaisesRegex(RuntimeError, 'int', operator.mod, '%u', rn)
self.assertRaisesRegex(RuntimeError, 'index', operator.mod, '%x', rn)
self.assertRaisesRegex(RuntimeError, 'index', operator.mod, '%X', rn)
self.assertRaisesRegex(RuntimeError, 'index', operator.mod, '%o', rn)
def test_formatting_with_enum(self):
# issue18780
import enum
class Float(float, enum.Enum):
# a mixed-in type will use the name for %s etc.
PI = 3.1415926
class Int(enum.IntEnum):
# IntEnum uses the value and not the name for %s etc.
IDES = 15
class Str(enum.StrEnum):
# StrEnum uses the value and not the name for %s etc.
ABC = 'abc'
# Testing Unicode formatting strings...
2013-08-31 16:48:51 -03:00
self.assertEqual("%s, %s" % (Str.ABC, Str.ABC),
'abc, abc')
2013-08-31 16:48:51 -03:00
self.assertEqual("%s, %s, %d, %i, %u, %f, %5.2f" %
(Str.ABC, Str.ABC,
Int.IDES, Int.IDES, Int.IDES,
Float.PI, Float.PI),
'abc, abc, 15, 15, 15, 3.141593, 3.14')
# formatting jobs delegated from the string implementation:
2013-08-31 16:48:51 -03:00
self.assertEqual('...%(foo)s...' % {'foo':Str.ABC},
'...abc...')
self.assertEqual('...%(foo)r...' % {'foo':Int.IDES},
'...<Int.IDES: 15>...')
2013-08-31 16:48:51 -03:00
self.assertEqual('...%(foo)s...' % {'foo':Int.IDES},
'...15...')
2013-08-31 16:48:51 -03:00
self.assertEqual('...%(foo)i...' % {'foo':Int.IDES},
'...15...')
self.assertEqual('...%(foo)d...' % {'foo':Int.IDES},
'...15...')
self.assertEqual('...%(foo)u...' % {'foo':Int.IDES, 'def':Float.PI},
'...15...')
self.assertEqual('...%(foo)f...' % {'foo':Float.PI,'def':123},
'...3.141593...')
def test_formatting_huge_precision(self):
format_string = "%.{}f".format(sys.maxsize + 1)
with self.assertRaises(ValueError):
result = format_string % 2.34
def test_issue28598_strsubclass_rhs(self):
# A subclass of str with an __rmod__ method should be able to hook
# into the % operator
class SubclassedStr(str):
def __rmod__(self, other):
return 'Success, self.__rmod__({!r}) was called'.format(other)
self.assertEqual('lhs %% %r' % SubclassedStr('rhs'),
"Success, self.__rmod__('lhs %% %r') was called")
@support.cpython_only
@unittest.skipIf(_testcapi is None, 'need _testcapi module')
def test_formatting_huge_precision_c_limits(self):
format_string = "%.{}f".format(_testcapi.INT_MAX + 1)
with self.assertRaises(ValueError):
result = format_string % 2.34
def test_formatting_huge_width(self):
format_string = "%{}f".format(sys.maxsize + 1)
with self.assertRaises(ValueError):
result = format_string % 2.34
def test_startswith_endswith_errors(self):
for meth in ('foo'.startswith, 'foo'.endswith):
2011-04-26 00:40:59 -03:00
with self.assertRaises(TypeError) as cm:
meth(['f'])
2011-04-26 00:40:59 -03:00
exc = str(cm.exception)
self.assertIn('str', exc)
self.assertIn('tuple', exc)
@support.run_with_locale('LC_ALL', 'de_DE', 'fr_FR')
2006-01-20 13:48:54 -04:00
def test_format_float(self):
Much-needed merge (using svnmerge.py this time) of trunk changes into p3yk. Inherits test_gzip/test_tarfile failures on 64-bit platforms from the trunk, but I don't want the merge to hang around too long (even though the regular p3yk-contributors are/have been busy with other things.) Merged revisions 45621-46490 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r45621 | george.yoshida | 2006-04-21 18:34:17 +0200 (Fri, 21 Apr 2006) | 2 lines Correct the grammar ........ r45622 | tim.peters | 2006-04-21 18:34:54 +0200 (Fri, 21 Apr 2006) | 2 lines Whitespace normalization. ........ r45624 | thomas.heller | 2006-04-21 18:48:56 +0200 (Fri, 21 Apr 2006) | 1 line Merge in changes from ctypes 0.9.9.6 upstream version. ........ r45625 | thomas.heller | 2006-04-21 18:51:04 +0200 (Fri, 21 Apr 2006) | 1 line Merge in changes from ctypes 0.9.9.6 upstream version. ........ r45630 | thomas.heller | 2006-04-21 20:29:17 +0200 (Fri, 21 Apr 2006) | 8 lines Documentation for ctypes. I think that 'generic operating system services' is the best category. Note that the Doc/lib/libctypes.latex file is generated from reST sources. You are welcome to make typo fixes, and I'll try to keep the reST sources in sync, but markup changes would be lost - they should be fixed in the tool that creates the latex file. The conversion script is external/ctypes/docs/manual/mkpydoc.py. ........ r45631 | tim.peters | 2006-04-21 23:18:10 +0200 (Fri, 21 Apr 2006) | 24 lines SF bug #1473760 TempFile can hang on Windows. Python 2.4 changed ntpath.abspath to do an import inside the function. As a result, due to Python's import lock, anything calling abspath on Windows (directly, or indirectly like tempfile.TemporaryFile) hung when it was called from a thread spawned as a side effect of importing a module. This is a depressingly frequent problem, and deserves a more general fix. I'm settling for a micro-fix here because this specific one accounts for a report of Zope Corp's ZEO hanging on Windows, and it was an odd way to change abspath to begin with (ntpath needs a different implementation depending on whether we're actually running on Windows, and the _obvious_ way to arrange for that is not to bury a possibly-failing import _inside_ the function). Note that if/when other micro-fixes of this kind get made, the new Lib/test/threaded_import_hangers.py is a convenient place to add tests for them. ........ r45634 | phillip.eby | 2006-04-21 23:53:37 +0200 (Fri, 21 Apr 2006) | 2 lines Guido wrote contextlib, not me, but thanks anyway. ;) ........ r45636 | andrew.kuchling | 2006-04-22 03:51:41 +0200 (Sat, 22 Apr 2006) | 1 line Typo fixes ........ r45638 | andrew.kuchling | 2006-04-22 03:58:40 +0200 (Sat, 22 Apr 2006) | 1 line Fix comment typo ........ r45639 | andrew.kuchling | 2006-04-22 04:06:03 +0200 (Sat, 22 Apr 2006) | 8 lines Make copy of test_mailbox.py. We'll still want to check the backward compatibility classes in the new mailbox.py that I'll be committing in a few minutes. One change has been made: the tests use len(mbox) instead of len(mbox.boxes). The 'boxes' attribute was never documented and contains some internal state that seems unlikely to have been useful. ........ r45640 | andrew.kuchling | 2006-04-22 04:32:43 +0200 (Sat, 22 Apr 2006) | 16 lines Add Gregory K. Johnson's revised version of mailbox.py (funded by the 2005 Summer of Code). The revision adds a number of new mailbox classes that support adding and removing messages; these classes also support mailbox locking and default to using email.Message instead of rfc822.Message. The old mailbox classes are largely left alone for backward compatibility. The exception is the Maildir class, which was present in the old module and now inherits from the new classes. The Maildir class's interface is pretty simple, though, so I think it'll be compatible with existing code. (The change to the NEWS file also adds a missing word to a different news item, which unfortunately required rewrapping the line.) ........ r45641 | tim.peters | 2006-04-22 07:52:59 +0200 (Sat, 22 Apr 2006) | 2 lines Whitespace normalization. ........ r45642 | neal.norwitz | 2006-04-22 08:07:46 +0200 (Sat, 22 Apr 2006) | 1 line Add libctypes as a dep ........ r45643 | martin.v.loewis | 2006-04-22 13:15:41 +0200 (Sat, 22 Apr 2006) | 1 line Fix more ssize_t problems. ........ r45644 | martin.v.loewis | 2006-04-22 13:40:03 +0200 (Sat, 22 Apr 2006) | 1 line Fix more ssize_t issues. ........ r45645 | george.yoshida | 2006-04-22 17:10:49 +0200 (Sat, 22 Apr 2006) | 2 lines Typo fixes ........ r45647 | martin.v.loewis | 2006-04-22 17:19:54 +0200 (Sat, 22 Apr 2006) | 1 line Port to Python 2.5. Drop .DEF file. Change output file names to .pyd. ........ r45648 | george.yoshida | 2006-04-22 17:27:14 +0200 (Sat, 22 Apr 2006) | 3 lines - add versionadded tag - make arbitrary arguments come last ........ r45649 | hyeshik.chang | 2006-04-22 17:48:15 +0200 (Sat, 22 Apr 2006) | 3 lines Remove $CJKCodecs$ RCS tags. The CJKCodecs isn't maintained outside anymore. ........ r45654 | greg.ward | 2006-04-23 05:47:58 +0200 (Sun, 23 Apr 2006) | 2 lines Update optparse to Optik 1.5.1. ........ r45658 | george.yoshida | 2006-04-23 11:27:10 +0200 (Sun, 23 Apr 2006) | 2 lines wrap SyntaxError with \exception{} ........ r45660 | ronald.oussoren | 2006-04-23 13:59:25 +0200 (Sun, 23 Apr 2006) | 6 lines Patch 1471925 - Weak linking support for OSX This patch causes several symbols in the socket and posix module to be weakly linked on OSX and disables usage of ftime on OSX. These changes make it possible to use a binary build on OSX 10.4 on a 10.3 system. ........ r45661 | ronald.oussoren | 2006-04-23 14:36:23 +0200 (Sun, 23 Apr 2006) | 5 lines Patch 1471761 - test for broken poll at runtime This patch checks if poll is broken when the select module is loaded instead of doing so at configure-time. This functionality is only active on Mac OS X. ........ r45662 | nick.coghlan | 2006-04-23 17:13:32 +0200 (Sun, 23 Apr 2006) | 1 line Add a Context Types section to parallel the Iterator Types section (uses the same terminology as the 2.5a1 implementation) ........ r45663 | nick.coghlan | 2006-04-23 17:14:37 +0200 (Sun, 23 Apr 2006) | 1 line Update contextlib documentation to use the same terminology as the module implementation ........ r45664 | gerhard.haering | 2006-04-23 17:24:26 +0200 (Sun, 23 Apr 2006) | 2 lines Updated the sqlite3 module to the external pysqlite 2.2.2 version. ........ r45666 | nick.coghlan | 2006-04-23 17:39:16 +0200 (Sun, 23 Apr 2006) | 1 line Update with statement documentation to use same terminology as 2.5a1 implementation ........ r45667 | nick.coghlan | 2006-04-23 18:05:04 +0200 (Sun, 23 Apr 2006) | 1 line Add a (very) brief mention of the with statement to the end of chapter 8 ........ r45668 | nick.coghlan | 2006-04-23 18:35:19 +0200 (Sun, 23 Apr 2006) | 1 line Take 2 on mentioning the with statement, this time without inadvertently killing the Unicode examples ........ r45669 | nick.coghlan | 2006-04-23 19:04:07 +0200 (Sun, 23 Apr 2006) | 1 line Backdated NEWS entry to record the implementation of PEP 338 for alpha 1 ........ r45670 | tim.peters | 2006-04-23 20:13:45 +0200 (Sun, 23 Apr 2006) | 2 lines Whitespace normalization. ........ r45671 | skip.montanaro | 2006-04-23 21:14:27 +0200 (Sun, 23 Apr 2006) | 1 line first cut at trace module doc ........ r45672 | skip.montanaro | 2006-04-23 21:26:33 +0200 (Sun, 23 Apr 2006) | 1 line minor tweak ........ r45673 | skip.montanaro | 2006-04-23 21:30:50 +0200 (Sun, 23 Apr 2006) | 1 line it's always helpful if the example works... ........ r45674 | skip.montanaro | 2006-04-23 21:32:14 +0200 (Sun, 23 Apr 2006) | 1 line correct example ........ r45675 | andrew.kuchling | 2006-04-23 23:01:04 +0200 (Sun, 23 Apr 2006) | 1 line Edits to the PEP 343 section ........ r45676 | andrew.kuchling | 2006-04-23 23:51:10 +0200 (Sun, 23 Apr 2006) | 1 line Add two items ........ r45677 | tim.peters | 2006-04-24 04:03:16 +0200 (Mon, 24 Apr 2006) | 5 lines Bug #1337990: clarified that `doctest` does not support examples requiring both expected output and an exception. I'll backport to 2.4 next. ........ r45679 | nick.coghlan | 2006-04-24 05:04:43 +0200 (Mon, 24 Apr 2006) | 1 line Note changes made to PEP 343 related documentation ........ r45681 | nick.coghlan | 2006-04-24 06:17:02 +0200 (Mon, 24 Apr 2006) | 1 line Change PEP 343 related documentation to use the term context specifier instead of context object ........ r45682 | nick.coghlan | 2006-04-24 06:32:47 +0200 (Mon, 24 Apr 2006) | 1 line Add unit tests for the -m and -c command line switches ........ r45683 | nick.coghlan | 2006-04-24 06:37:15 +0200 (Mon, 24 Apr 2006) | 1 line Fix contextlib.nested to cope with exit methods raising and handling exceptions ........ r45685 | nick.coghlan | 2006-04-24 06:59:28 +0200 (Mon, 24 Apr 2006) | 1 line Fix broken contextlib test from last checkin (I'd've sworn I tested that before checking it in. . .) ........ r45686 | nick.coghlan | 2006-04-24 07:24:26 +0200 (Mon, 24 Apr 2006) | 1 line Back out new command line tests (broke buildbot) ........ r45687 | nick.coghlan | 2006-04-24 07:52:15 +0200 (Mon, 24 Apr 2006) | 1 line More reliable version of new command line tests that just checks the exit codes ........ r45688 | thomas.wouters | 2006-04-24 13:37:13 +0200 (Mon, 24 Apr 2006) | 4 lines Stop test_tcl's testLoadTk from leaking the Tk commands 'loadtk' registers. ........ r45690 | andrew.kuchling | 2006-04-24 16:30:47 +0200 (Mon, 24 Apr 2006) | 2 lines Edits, using the new term 'context specifier' in a few places ........ r45697 | phillip.eby | 2006-04-24 22:53:13 +0200 (Mon, 24 Apr 2006) | 2 lines Revert addition of setuptools ........ r45698 | tim.peters | 2006-04-25 00:45:13 +0200 (Tue, 25 Apr 2006) | 2 lines Whitespace normalization. ........ r45700 | trent.mick | 2006-04-25 02:34:50 +0200 (Tue, 25 Apr 2006) | 4 lines Put break at correct level so *all* root HKEYs acutally get checked for an installed VC6. Otherwise only the first such tree gets checked and this warning doesn't get displayed. ........ r45701 | tim.peters | 2006-04-25 05:31:36 +0200 (Tue, 25 Apr 2006) | 3 lines Patch #1475231: add a new SKIP doctest option, thanks to Edward Loper. ........ r45702 | neal.norwitz | 2006-04-25 07:04:35 +0200 (Tue, 25 Apr 2006) | 1 line versionadded for SKIP ........ r45703 | neal.norwitz | 2006-04-25 07:05:03 +0200 (Tue, 25 Apr 2006) | 1 line Restore Walters name ........ r45704 | neal.norwitz | 2006-04-25 07:49:42 +0200 (Tue, 25 Apr 2006) | 1 line Revert previous change, SKIP had a versionadded elsewhere ........ r45706 | nick.coghlan | 2006-04-25 12:56:51 +0200 (Tue, 25 Apr 2006) | 31 lines Move the PEP 343 documentation and implementation closer to the terminology in the alpha 1 documentation. - "context manager" reverts to its alpha 1 definition - the term "context specifier" goes away entirely - contextlib.GeneratorContextManager is renamed GeneratorContext There are still a number of changes relative to alpha 1: - the expression in the with statement is explicitly called the "context expression" in the language reference - the terms 'with statement context', 'context object' or 'with statement context' are used in several places instead of a bare 'context'. The aim of this is to avoid ambiguity in relation to the runtime context set up when the block is executed, and the context objects that already exist in various application domains (such as decimal.Context) - contextlib.contextmanager is renamed to contextfactory This best reflects the nature of the function resulting from the use of that decorator - decimal.ContextManager is renamed to WithStatementContext Simple dropping the 'Manager' part wasn't possible due to the fact that decimal.Context already exists and means something different. WithStatementContext is ugly but workable. A technically unrelated change snuck into this commit: contextlib.closing now avoids the overhead of creating a generator, since it's trivial to implement that particular context manager directly. ........ r45707 | nick.coghlan | 2006-04-25 13:05:56 +0200 (Tue, 25 Apr 2006) | 1 line Fix latex typo ........ r45708 | thomas.wouters | 2006-04-25 14:28:56 +0200 (Tue, 25 Apr 2006) | 4 lines Fix markup glitch in unittest docs. Will backport. ........ r45710 | andrew.kuchling | 2006-04-25 14:31:38 +0200 (Tue, 25 Apr 2006) | 1 line Add two items; easy_install is now off the table, though pkgutil still is ........ r45711 | andrew.kuchling | 2006-04-25 14:47:25 +0200 (Tue, 25 Apr 2006) | 1 line Rework context terminology ........ r45712 | thomas.wouters | 2006-04-25 15:53:23 +0200 (Tue, 25 Apr 2006) | 9 lines SF bug/patch #1433877: string parameter to ioctl not null terminated The new char-array used in ioctl calls wasn't explicitly NUL-terminated; quite probably the cause for the test_pty failures on Solaris that we circumvented earlier. (I wasn't able to reproduce it with this patch, but it has been somewhat elusive to start with.) ........ r45713 | george.yoshida | 2006-04-25 16:09:58 +0200 (Tue, 25 Apr 2006) | 2 lines minor tweak ........ r45714 | thomas.wouters | 2006-04-25 17:08:10 +0200 (Tue, 25 Apr 2006) | 7 lines Fix SF bug #1476111: SystemError in socket sendto. The AF_INET6 and AF_PACKET cases in getsockaddrarg were missing their own checks for tuple-ness of the address argument, which means a confusing SystemError was raised by PyArg_ParseTuple instead. ........ r45715 | thomas.wouters | 2006-04-25 17:29:46 +0200 (Tue, 25 Apr 2006) | 10 lines Define MAXPATHLEN to be at least PATH_MAX, if that's defined. Python uses MAXPATHLEN-sized buffers for various output-buffers (like to realpath()), and that's correct on BSD platforms, but not Linux (which uses PATH_MAX, and does not define MAXPATHLEN.) Cursory googling suggests Linux is following a newer standard than BSD, but in cases like this, who knows. Using the greater of PATH_MAX and 1024 as a fallback for MAXPATHLEN seems to be the most portable solution. ........ r45717 | thomas.heller | 2006-04-25 20:26:08 +0200 (Tue, 25 Apr 2006) | 3 lines Fix compiler warnings on Darwin. Patch by Brett Canon, see https://sourceforge.net/tracker/?func=detail&atid=532156&aid=1475959&group_id=71702 ........ r45718 | guido.van.rossum | 2006-04-25 22:12:45 +0200 (Tue, 25 Apr 2006) | 4 lines Implement MvL's improvement on __context__ in Condition; this can just call __context__ on the underlying lock. (The same change for Semaphore does *not* work!) ........ r45721 | tim.peters | 2006-04-26 03:15:53 +0200 (Wed, 26 Apr 2006) | 13 lines Rev 45706 renamed stuff in contextlib.py, but didn't rename uses of it in test_with.py. As a result, test_with has been skipped (due to failing imports) on all buildbot boxes since. Alas, that's not a test failure -- you have to pay attention to the 1 skip unexpected on PLATFORM: test_with kinds of output at the ends of test runs to notice that this got broken. It's likely that more renaming in test_with.py would be desirable. ........ r45722 | fred.drake | 2006-04-26 07:15:41 +0200 (Wed, 26 Apr 2006) | 1 line markup fixes, cleanup ........ r45723 | fred.drake | 2006-04-26 07:19:39 +0200 (Wed, 26 Apr 2006) | 1 line minor adjustment suggested by Peter Gephardt ........ r45724 | neal.norwitz | 2006-04-26 07:34:03 +0200 (Wed, 26 Apr 2006) | 10 lines Patch from Aldo Cortesi (OpenBSD buildbot owner). After the patch (45590) to add extra debug stats to the gc module, Python was crashing on OpenBSD due to: Fatal Python error: Interpreter not initialized (version mismatch?) This seems to occur due to calling collect() when initialized (in pythonrun.c) is set to 0. Now, the import will occur in the init function which shouldn't suffer this problem. ........ r45725 | neal.norwitz | 2006-04-26 08:26:12 +0200 (Wed, 26 Apr 2006) | 3 lines Fix this test on Solaris. There can be embedded \r, so don't just replace the one at the end. ........ r45727 | nick.coghlan | 2006-04-26 13:50:04 +0200 (Wed, 26 Apr 2006) | 1 line Fix an error in the last contextlib.closing example ........ r45728 | andrew.kuchling | 2006-04-26 14:21:06 +0200 (Wed, 26 Apr 2006) | 1 line [Bug #1475080] Fix example ........ r45729 | andrew.kuchling | 2006-04-26 14:23:39 +0200 (Wed, 26 Apr 2006) | 1 line Add labels to all sections ........ r45730 | thomas.wouters | 2006-04-26 17:53:30 +0200 (Wed, 26 Apr 2006) | 7 lines The result of SF patch #1471578: big-memory tests for strings, lists and tuples. Lots to be added, still, but this will give big-memory people something to play with in 2.5 alpha 2, and hopefully get more people to write these tests. ........ r45731 | tim.peters | 2006-04-26 19:11:16 +0200 (Wed, 26 Apr 2006) | 2 lines Whitespace normalization. ........ r45732 | martin.v.loewis | 2006-04-26 19:19:44 +0200 (Wed, 26 Apr 2006) | 1 line Use GS- and bufferoverlowU.lib where appropriate, for AMD64. ........ r45733 | thomas.wouters | 2006-04-26 20:46:01 +0200 (Wed, 26 Apr 2006) | 5 lines Add tests for += and *= on strings, and fix the memory-use estimate for the list.extend tests (they were estimating half the actual use.) ........ r45734 | thomas.wouters | 2006-04-26 21:14:46 +0200 (Wed, 26 Apr 2006) | 5 lines Some more test-size-estimate fixes: test_append and test_insert trigger a list resize, which overallocates. ........ r45735 | hyeshik.chang | 2006-04-26 21:20:26 +0200 (Wed, 26 Apr 2006) | 3 lines Fix build on MIPS for libffi. I haven't tested this yet because I don't have an access on MIPS machines. Will be tested by buildbot. :) ........ r45737 | fred.drake | 2006-04-27 01:40:32 +0200 (Thu, 27 Apr 2006) | 1 line one more place to use the current Python version ........ r45738 | fred.drake | 2006-04-27 02:02:24 +0200 (Thu, 27 Apr 2006) | 3 lines - update version numbers in file names again, until we have a better way - elaborate instructions for Cygwin support (closes SF #839709) ........ r45739 | fred.drake | 2006-04-27 02:20:14 +0200 (Thu, 27 Apr 2006) | 1 line add missing word ........ r45740 | anthony.baxter | 2006-04-27 04:11:24 +0200 (Thu, 27 Apr 2006) | 2 lines 2.5a2 ........ r45741 | anthony.baxter | 2006-04-27 04:13:13 +0200 (Thu, 27 Apr 2006) | 1 line 2.5a2 ........ r45749 | andrew.kuchling | 2006-04-27 14:22:37 +0200 (Thu, 27 Apr 2006) | 1 line Now that 2.5a2 is out, revert to the current date ........ r45750 | andrew.kuchling | 2006-04-27 14:23:07 +0200 (Thu, 27 Apr 2006) | 1 line Bump document version ........ r45751 | andrew.kuchling | 2006-04-27 14:34:39 +0200 (Thu, 27 Apr 2006) | 6 lines [Bug #1477102] Add necessary import to example This may be a useful style question for the docs -- should examples show the necessary imports, or should it be assumed that the reader will figure it out? In the What's New, I'm not consistent but usually opt for omitting the imports. ........ r45753 | andrew.kuchling | 2006-04-27 14:38:35 +0200 (Thu, 27 Apr 2006) | 1 line [Bug #1477140] Import Error base class ........ r45754 | andrew.kuchling | 2006-04-27 14:42:54 +0200 (Thu, 27 Apr 2006) | 1 line Mention the xmlrpclib.Error base class, which is used in one of the examples ........ r45756 | george.yoshida | 2006-04-27 15:41:07 +0200 (Thu, 27 Apr 2006) | 2 lines markup fix ........ r45757 | thomas.wouters | 2006-04-27 15:46:59 +0200 (Thu, 27 Apr 2006) | 4 lines Some more size-estimate fixes, for large-list-tests. ........ r45758 | thomas.heller | 2006-04-27 17:50:42 +0200 (Thu, 27 Apr 2006) | 3 lines Rerun the libffi configuration if any of the files used for that are newer then fficonfig.py. ........ r45766 | thomas.wouters | 2006-04-28 00:37:50 +0200 (Fri, 28 Apr 2006) | 6 lines Some style fixes and size-calculation fixes. Also do the small-memory run using a prime number, rather than a convenient power-of-2-and-multiple-of-5, so incorrect testing algorithms fail more easily. ........ r45767 | thomas.wouters | 2006-04-28 00:38:32 +0200 (Fri, 28 Apr 2006) | 6 lines Do the small-memory run of big-meormy tests using a prime number, rather than a convenient power-of-2-and-multiple-of-5, so incorrect testing algorithms fail more easily. ........ r45768 | david.goodger | 2006-04-28 00:53:05 +0200 (Fri, 28 Apr 2006) | 1 line Added SVN access for Steven Bethard and Talin, for PEP updating. ........ r45770 | thomas.wouters | 2006-04-28 01:13:20 +0200 (Fri, 28 Apr 2006) | 16 lines - Add new Warning class, ImportWarning - Warn-raise ImportWarning when importing would have picked up a directory as package, if only it'd had an __init__.py. This swaps two tests (for case-ness and __init__-ness), but case-test is not really more expensive, and it's not in a speed-critical section. - Test for the new warning by importing a common non-package directory on sys.path: site-packages - In regrtest.py, silence warnings generated by the build-environment because Modules/ (which is added to sys.path for Setup-created modules) has 'zlib' and '_ctypes' directories without __init__.py's. ........ r45771 | thomas.wouters | 2006-04-28 01:41:27 +0200 (Fri, 28 Apr 2006) | 6 lines Add more ignores of ImportWarnings; these are all just potential triggers (since they won't trigger if zlib is already sucessfully imported); they were found by grepping .py files, instead of looking at warning output :) ........ r45773 | neal.norwitz | 2006-04-28 06:32:20 +0200 (Fri, 28 Apr 2006) | 1 line Add some whitespace to be more consistent. ........ r45774 | neal.norwitz | 2006-04-28 06:34:43 +0200 (Fri, 28 Apr 2006) | 5 lines Try to really fix the slow buildbots this time. Printing to stdout, doesn't mean the data was actually written. It depends on the buffering, so we need to flush. This will hopefully really fix the buildbots getting killed due to no output on the slow bots. ........ r45775 | neal.norwitz | 2006-04-28 07:28:05 +0200 (Fri, 28 Apr 2006) | 1 line Fix some warnings on Mac OS X 10.4 ........ r45776 | neal.norwitz | 2006-04-28 07:28:30 +0200 (Fri, 28 Apr 2006) | 1 line Fix a warning on alpha ........ r45777 | neal.norwitz | 2006-04-28 07:28:54 +0200 (Fri, 28 Apr 2006) | 1 line Fix a warning on ppc (debian) ........ r45778 | george.yoshida | 2006-04-28 18:09:45 +0200 (Fri, 28 Apr 2006) | 2 lines fix markup glitch ........ r45780 | georg.brandl | 2006-04-28 18:31:17 +0200 (Fri, 28 Apr 2006) | 3 lines Add SeaMonkey to the list of Mozilla browsers. ........ r45781 | georg.brandl | 2006-04-28 18:36:55 +0200 (Fri, 28 Apr 2006) | 2 lines Bug #1475009: clarify ntpath.join behavior with absolute components ........ r45783 | george.yoshida | 2006-04-28 18:40:14 +0200 (Fri, 28 Apr 2006) | 2 lines correct a dead link ........ r45785 | georg.brandl | 2006-04-28 18:54:25 +0200 (Fri, 28 Apr 2006) | 4 lines Bug #1472949: stringify IOErrors in shutil.copytree when appending them to the Error errors list. ........ r45786 | georg.brandl | 2006-04-28 18:58:52 +0200 (Fri, 28 Apr 2006) | 3 lines Bug #1478326: don't allow '/' in distutils.util.get_platform machine names since this value is used to name the build directory. ........ r45788 | thomas.heller | 2006-04-28 19:02:18 +0200 (Fri, 28 Apr 2006) | 1 line Remove a duplicated test (the same test is in test_incomplete.py). ........ r45792 | georg.brandl | 2006-04-28 21:09:24 +0200 (Fri, 28 Apr 2006) | 3 lines Bug #1478429: make datetime.datetime.fromtimestamp accept every float, possibly "rounding up" to the next whole second. ........ r45796 | george.yoshida | 2006-04-29 04:43:30 +0200 (Sat, 29 Apr 2006) | 2 lines grammar fix ........ r45800 | ronald.oussoren | 2006-04-29 13:31:35 +0200 (Sat, 29 Apr 2006) | 2 lines Patch 1471883: --enable-universalsdk on Mac OS X ........ r45801 | andrew.kuchling | 2006-04-29 13:53:15 +0200 (Sat, 29 Apr 2006) | 1 line Add item ........ r45802 | andrew.kuchling | 2006-04-29 14:10:28 +0200 (Sat, 29 Apr 2006) | 1 line Make case of 'ZIP' consistent ........ r45803 | andrew.kuchling | 2006-04-29 14:10:43 +0200 (Sat, 29 Apr 2006) | 1 line Add item ........ r45808 | martin.v.loewis | 2006-04-29 14:37:25 +0200 (Sat, 29 Apr 2006) | 3 lines Further changes for #1471883: Edit Misc/NEWS, and add expat_config.h. ........ r45809 | brett.cannon | 2006-04-29 23:29:50 +0200 (Sat, 29 Apr 2006) | 2 lines Fix docstring for contextfactory; mentioned old contextmanager name. ........ r45810 | gerhard.haering | 2006-04-30 01:12:41 +0200 (Sun, 30 Apr 2006) | 3 lines This is the start of documentation for the sqlite3 module. Please feel free to find a better place for the link to it than alongside bsddb & friends. ........ r45811 | andrew.kuchling | 2006-04-30 03:07:09 +0200 (Sun, 30 Apr 2006) | 1 line Add two items ........ r45814 | george.yoshida | 2006-04-30 05:49:56 +0200 (Sun, 30 Apr 2006) | 2 lines Use \versionchanged instead of \versionadded for new parameter support. ........ r45815 | georg.brandl | 2006-04-30 09:06:11 +0200 (Sun, 30 Apr 2006) | 2 lines Patch #1470846: fix urllib2 ProxyBasicAuthHandler. ........ r45817 | georg.brandl | 2006-04-30 10:57:35 +0200 (Sun, 30 Apr 2006) | 3 lines In stdlib, use hashlib instead of deprecated md5 and sha modules. ........ r45819 | georg.brandl | 2006-04-30 11:23:59 +0200 (Sun, 30 Apr 2006) | 3 lines Patch #1470976: don't NLST files when retrieving over FTP. ........ r45821 | georg.brandl | 2006-04-30 13:13:56 +0200 (Sun, 30 Apr 2006) | 6 lines Bug #1473625: stop cPickle making float dumps locale dependent in protocol 0. On the way, add a decorator to test_support to facilitate running single test functions in different locales with automatic cleanup. ........ r45822 | phillip.eby | 2006-04-30 17:59:26 +0200 (Sun, 30 Apr 2006) | 2 lines Fix infinite regress when inspecting <string> or <stdin> frames. ........ r45824 | georg.brandl | 2006-04-30 19:42:26 +0200 (Sun, 30 Apr 2006) | 3 lines Fix another problem in inspect: if the module for an object cannot be found, don't try to give its __dict__ to linecache. ........ r45825 | georg.brandl | 2006-04-30 20:14:54 +0200 (Sun, 30 Apr 2006) | 3 lines Patch #1472854: make the rlcompleter.Completer class usable on non- UNIX platforms. ........ r45826 | georg.brandl | 2006-04-30 21:34:19 +0200 (Sun, 30 Apr 2006) | 3 lines Patch #1479438: add \keyword markup for "with". ........ r45827 | andrew.kuchling | 2006-04-30 23:19:31 +0200 (Sun, 30 Apr 2006) | 1 line Add urllib2 HOWTO from Michael Foord ........ r45828 | andrew.kuchling | 2006-04-30 23:19:49 +0200 (Sun, 30 Apr 2006) | 1 line Add item ........ r45830 | barry.warsaw | 2006-05-01 05:03:02 +0200 (Mon, 01 May 2006) | 11 lines Port forward from 2.4 branch: Patch #1464708 from William McVey: fixed handling of nested comments in mail addresses. E.g. "Foo ((Foo Bar)) <foo@example.com>" Fixes for both rfc822.py and email package. This patch needs to be back ported to Python 2.3 for email 2.5. ........ r45832 | fred.drake | 2006-05-01 08:25:58 +0200 (Mon, 01 May 2006) | 4 lines - minor clarification in section title - markup adjustments (there is clearly much to be done in this section) ........ r45833 | martin.v.loewis | 2006-05-01 08:28:01 +0200 (Mon, 01 May 2006) | 2 lines Work around deadlock risk. Will backport. ........ r45836 | andrew.kuchling | 2006-05-01 14:45:02 +0200 (Mon, 01 May 2006) | 1 line Some ElementTree fixes: import from xml, not xmlcore; fix case of module name; mention list() instead of getchildren() ........ r45837 | gerhard.haering | 2006-05-01 17:14:48 +0200 (Mon, 01 May 2006) | 3 lines Further integration of the documentation for the sqlite3 module. There's still quite some content to move over from the pysqlite manual, but it's a start now. ........ r45838 | martin.v.loewis | 2006-05-01 17:56:03 +0200 (Mon, 01 May 2006) | 2 lines Rename uisample to text, drop all non-text tables. ........ r45839 | martin.v.loewis | 2006-05-01 18:12:44 +0200 (Mon, 01 May 2006) | 2 lines Add msilib documentation. ........ r45840 | martin.v.loewis | 2006-05-01 18:14:16 +0200 (Mon, 01 May 2006) | 4 lines Rename parameters to match the documentation (which in turn matches Microsoft's documentation). Drop unused parameter in CAB.append. ........ r45841 | fred.drake | 2006-05-01 18:28:54 +0200 (Mon, 01 May 2006) | 1 line add dependency ........ r45842 | andrew.kuchling | 2006-05-01 18:30:25 +0200 (Mon, 01 May 2006) | 1 line Markup fixes; add some XXX comments noting problems ........ r45843 | andrew.kuchling | 2006-05-01 18:32:49 +0200 (Mon, 01 May 2006) | 1 line Add item ........ r45844 | andrew.kuchling | 2006-05-01 19:06:54 +0200 (Mon, 01 May 2006) | 1 line Markup fixes ........ r45850 | neal.norwitz | 2006-05-02 06:43:14 +0200 (Tue, 02 May 2006) | 3 lines SF #1479181: split open() and file() from being aliases for each other. ........ r45852 | neal.norwitz | 2006-05-02 08:23:22 +0200 (Tue, 02 May 2006) | 1 line Try to fix breakage caused by patch #1479181, r45850 ........ r45853 | fred.drake | 2006-05-02 08:53:59 +0200 (Tue, 02 May 2006) | 3 lines SF #1479988: add methods to allow access to weakrefs for the weakref.WeakKeyDictionary and weakref.WeakValueDictionary ........ r45854 | neal.norwitz | 2006-05-02 09:27:47 +0200 (Tue, 02 May 2006) | 5 lines Fix breakage from patch 1471883 (r45800 & r45808) on OSF/1. The problem was that pyconfig.h was being included before some system headers which caused redefinitions and other breakage. This moves system headers after expat_config.h which includes pyconfig.h. ........ r45855 | vinay.sajip | 2006-05-02 10:35:36 +0200 (Tue, 02 May 2006) | 1 line Replaced my dumb way of calculating seconds to midnight with Tim Peters' much more sensible suggestion. What was I thinking ?!? ........ r45856 | andrew.kuchling | 2006-05-02 13:30:03 +0200 (Tue, 02 May 2006) | 1 line Provide encoding as keyword argument; soften warning paragraph about encodings ........ r45858 | guido.van.rossum | 2006-05-02 19:36:09 +0200 (Tue, 02 May 2006) | 2 lines Fix the formatting of KeyboardInterrupt -- a bad issubclass() call. ........ r45862 | guido.van.rossum | 2006-05-02 21:47:52 +0200 (Tue, 02 May 2006) | 7 lines Get rid of __context__, per the latest changes to PEP 343 and python-dev discussion. There are two places of documentation that still mention __context__: Doc/lib/libstdtypes.tex -- I wasn't quite sure how to rewrite that without spending a whole lot of time thinking about it; and whatsnew, which Andrew usually likes to change himself. ........ r45863 | armin.rigo | 2006-05-02 21:52:32 +0200 (Tue, 02 May 2006) | 4 lines Documentation bug: PySet_Pop() returns a new reference (because the caller becomes the owner of that reference). ........ r45864 | guido.van.rossum | 2006-05-02 22:47:36 +0200 (Tue, 02 May 2006) | 4 lines Hopefully this will fix the spurious failures of test_mailbox.py that I'm experiencing. (This code and mailbox.py itself are full of calls to file() that should be calls to open() -- but I'm not fixing those.) ........ r45865 | andrew.kuchling | 2006-05-02 23:44:33 +0200 (Tue, 02 May 2006) | 1 line Use open() instead of file() ........ r45866 | andrew.kuchling | 2006-05-03 00:47:49 +0200 (Wed, 03 May 2006) | 1 line Update context manager section for removal of __context__ ........ r45867 | fred.drake | 2006-05-03 03:46:52 +0200 (Wed, 03 May 2006) | 1 line remove unnecessary assignment ........ r45868 | fred.drake | 2006-05-03 03:48:24 +0200 (Wed, 03 May 2006) | 4 lines tell LaTeX2HTML to: - use UTF-8 output - not mess with the >>> prompt! ........ r45869 | fred.drake | 2006-05-03 04:04:40 +0200 (Wed, 03 May 2006) | 3 lines avoid ugly markup based on the unfortunate conversions of ">>" and "<<" to guillemets; no need for magic here ........ r45870 | fred.drake | 2006-05-03 04:12:47 +0200 (Wed, 03 May 2006) | 1 line at least comment on why curly-quotes are not enabled ........ r45871 | fred.drake | 2006-05-03 04:27:40 +0200 (Wed, 03 May 2006) | 1 line one more place to avoid extra markup ........ r45872 | fred.drake | 2006-05-03 04:29:09 +0200 (Wed, 03 May 2006) | 1 line one more place to avoid extra markup (how many will there be?) ........ r45873 | fred.drake | 2006-05-03 04:29:39 +0200 (Wed, 03 May 2006) | 1 line fix up whitespace in prompt strings ........ r45876 | tim.peters | 2006-05-03 06:46:14 +0200 (Wed, 03 May 2006) | 2 lines Whitespace normalization. ........ r45877 | martin.v.loewis | 2006-05-03 06:52:04 +0200 (Wed, 03 May 2006) | 2 lines Correct some formulations, fix XXX comments. ........ r45879 | georg.brandl | 2006-05-03 07:05:02 +0200 (Wed, 03 May 2006) | 2 lines Patch #1480067: don't redirect HTTP digest auth in urllib2 ........ r45881 | georg.brandl | 2006-05-03 07:15:10 +0200 (Wed, 03 May 2006) | 3 lines Move network tests from test_urllib2 to test_urllib2net. ........ r45887 | nick.coghlan | 2006-05-03 15:02:47 +0200 (Wed, 03 May 2006) | 1 line Finish bringing SVN into line with latest version of PEP 343 by getting rid of all remaining references to context objects that I could find. Without a __context__() method context objects no longer exist. Also get test_with working again, and adopt a suggestion from Neal for decimal.Context.get_manager() ........ r45888 | nick.coghlan | 2006-05-03 15:17:49 +0200 (Wed, 03 May 2006) | 1 line Get rid of a couple more context object references, fix some markup and clarify what happens when a generator context function swallows an exception. ........ r45889 | georg.brandl | 2006-05-03 19:46:13 +0200 (Wed, 03 May 2006) | 3 lines Add seamonkey to list of Windows browsers too. ........ r45890 | georg.brandl | 2006-05-03 20:03:22 +0200 (Wed, 03 May 2006) | 3 lines RFE #1472176: In httplib, don't encode the netloc and hostname with "idna" if not necessary. ........ r45891 | georg.brandl | 2006-05-03 20:12:33 +0200 (Wed, 03 May 2006) | 2 lines Bug #1472191: convert breakpoint indices to ints before comparing them to ints ........ r45893 | georg.brandl | 2006-05-03 20:18:32 +0200 (Wed, 03 May 2006) | 3 lines Bug #1385040: don't allow "def foo(a=1, b): pass" in the compiler package. ........ r45894 | thomas.heller | 2006-05-03 20:35:39 +0200 (Wed, 03 May 2006) | 1 line Don't fail the tests when libglut.so or libgle.so cannot be loaded. ........ r45895 | georg.brandl | 2006-05-04 07:08:10 +0200 (Thu, 04 May 2006) | 2 lines Bug #1481530: allow "from os.path import ..." with imputil ........ r45897 | martin.v.loewis | 2006-05-04 07:51:03 +0200 (Thu, 04 May 2006) | 2 lines Patch #1475845: Raise IndentationError for unexpected indent. ........ r45898 | martin.v.loewis | 2006-05-04 12:08:42 +0200 (Thu, 04 May 2006) | 1 line Implement os.{chdir,rename,rmdir,remove} using Win32 directly. ........ r45899 | martin.v.loewis | 2006-05-04 14:04:27 +0200 (Thu, 04 May 2006) | 2 lines Drop now-unnecessary arguments to posix_2str. ........ r45900 | martin.v.loewis | 2006-05-04 16:27:52 +0200 (Thu, 04 May 2006) | 1 line Update checks to consider Windows error numbers. ........ r45913 | thomas.heller | 2006-05-05 20:42:14 +0200 (Fri, 05 May 2006) | 2 lines Export the 'free' standard C function for use in the test suite. ........ r45914 | thomas.heller | 2006-05-05 20:43:24 +0200 (Fri, 05 May 2006) | 3 lines Fix memory leaks in the ctypes test suite, reported by valgrind, by free()ing the memory we allocate. ........ r45915 | thomas.heller | 2006-05-05 20:46:27 +0200 (Fri, 05 May 2006) | 1 line oops - the function is exported as 'my_free', not 'free'. ........ r45916 | thomas.heller | 2006-05-05 21:14:24 +0200 (Fri, 05 May 2006) | 2 lines Clean up. ........ r45920 | george.yoshida | 2006-05-06 15:09:45 +0200 (Sat, 06 May 2006) | 2 lines describe optional arguments for DocFileSuite ........ r45924 | george.yoshida | 2006-05-06 16:16:51 +0200 (Sat, 06 May 2006) | 2 lines Use \versionchanged for the feature change ........ r45925 | martin.v.loewis | 2006-05-06 18:32:54 +0200 (Sat, 06 May 2006) | 1 line Port access, chmod, parts of getcwdu, mkdir, and utime to direct Win32 API. ........ r45926 | martin.v.loewis | 2006-05-06 22:04:08 +0200 (Sat, 06 May 2006) | 2 lines Handle ERROR_ALREADY_EXISTS. ........ r45931 | andrew.kuchling | 2006-05-07 19:12:12 +0200 (Sun, 07 May 2006) | 1 line [Patch #1479977] Revised version of urllib2 HOWTO, edited by John J. Lee ........ r45932 | andrew.kuchling | 2006-05-07 19:14:53 +0200 (Sun, 07 May 2006) | 1 line Minor language edit ........ r45934 | georg.brandl | 2006-05-07 22:44:34 +0200 (Sun, 07 May 2006) | 3 lines Patch #1483395: add new TLDs to cookielib ........ r45936 | martin.v.loewis | 2006-05-08 07:25:56 +0200 (Mon, 08 May 2006) | 2 lines Add missing PyMem_Free. ........ r45938 | georg.brandl | 2006-05-08 19:28:47 +0200 (Mon, 08 May 2006) | 3 lines Add test for rev. 45934. ........ r45939 | georg.brandl | 2006-05-08 19:36:08 +0200 (Mon, 08 May 2006) | 3 lines Patch #1479302: Make urllib2 digest auth and basic auth play together. ........ r45940 | georg.brandl | 2006-05-08 19:48:01 +0200 (Mon, 08 May 2006) | 3 lines Patch #1478993: take advantage of BaseException/Exception split in cookielib ........ r45941 | neal.norwitz | 2006-05-09 07:38:56 +0200 (Tue, 09 May 2006) | 5 lines Micro optimization. In the first case, we know that frame->f_exc_type is NULL, so there's no reason to do anything with it. In the second case, we know frame->f_exc_type is not NULL, so we can just do an INCREF. ........ r45943 | thomas.heller | 2006-05-09 22:20:15 +0200 (Tue, 09 May 2006) | 2 lines Disable a test that is unreliable. ........ r45944 | tim.peters | 2006-05-10 04:43:01 +0200 (Wed, 10 May 2006) | 4 lines Variant of patch #1478292. doctest.register_optionflag(name) shouldn't create a new flag when `name` is already the name of an option flag. ........ r45947 | neal.norwitz | 2006-05-10 08:57:58 +0200 (Wed, 10 May 2006) | 14 lines Fix problems found by Coverity. longobject.c: also fix an ssize_t problem <a> could have been NULL, so hoist the size calc to not use <a>. _ssl.c: under fail: self is DECREF'd, but it would have been NULL. _elementtree.c: delete self if there was an error. _csv.c: I'm not sure if lineterminator could have been anything other than a string. However, other string method calls are checked, so check this one too. ........ r45948 | thomas.wouters | 2006-05-10 17:04:11 +0200 (Wed, 10 May 2006) | 4 lines Ignore reflog.txt, too. ........ r45949 | georg.brandl | 2006-05-10 17:59:06 +0200 (Wed, 10 May 2006) | 3 lines Bug #1482988: indicate more prominently that the Stats class is in the pstats module. ........ r45950 | georg.brandl | 2006-05-10 18:09:03 +0200 (Wed, 10 May 2006) | 2 lines Bug #1485447: subprocess: document that the "cwd" parameter isn't used to find the executable. Misc. other markup fixes. ........ r45952 | georg.brandl | 2006-05-10 18:11:44 +0200 (Wed, 10 May 2006) | 2 lines Bug #1484978: curses.panel: clarify that Panel objects are destroyed on garbage collection. ........ r45954 | georg.brandl | 2006-05-10 18:26:03 +0200 (Wed, 10 May 2006) | 4 lines Patch #1484695: Update the tarfile module to version 0.8. This fixes a couple of issues, notably handling of long file names using the GNU LONGNAME extension. ........ r45955 | georg.brandl | 2006-05-10 19:13:20 +0200 (Wed, 10 May 2006) | 4 lines Patch #721464: pdb.Pdb instances can now be given explicit stdin and stdout arguments, making it possible to redirect input and output for remote debugging. ........ r45956 | andrew.kuchling | 2006-05-10 19:19:04 +0200 (Wed, 10 May 2006) | 1 line Clarify description of exception handling ........ r45957 | georg.brandl | 2006-05-10 22:09:23 +0200 (Wed, 10 May 2006) | 2 lines Fix two small errors in argument lists. ........ r45960 | brett.cannon | 2006-05-11 07:11:33 +0200 (Thu, 11 May 2006) | 5 lines Detect if %zd is supported by printf() during configure and sets PY_FORMAT_SIZE_T appropriately. Removes warnings on OS X under gcc 4.0.1 when PY_FORMAT_SIZE_T is set to "" instead of "z" as is needed. ........ r45963 | neal.norwitz | 2006-05-11 09:51:59 +0200 (Thu, 11 May 2006) | 1 line Don't mask a no memory error with a less meaningful one as discussed on python-checkins ........ r45964 | martin.v.loewis | 2006-05-11 15:28:43 +0200 (Thu, 11 May 2006) | 3 lines Change WindowsError to carry the Win32 error code in winerror, and the DOS error code in errno. Revert changes where WindowsError catch blocks unnecessarily special-case OSError. ........ r45965 | george.yoshida | 2006-05-11 17:53:27 +0200 (Thu, 11 May 2006) | 2 lines Grammar fix ........ r45967 | andrew.kuchling | 2006-05-11 18:32:24 +0200 (Thu, 11 May 2006) | 1 line typo fix ........ r45968 | tim.peters | 2006-05-11 18:37:42 +0200 (Thu, 11 May 2006) | 5 lines BaseThreadedTestCase.setup(): stop special-casing WindowsError. Rev 45964 fiddled with WindowsError, and broke test_bsddb3 on all the Windows buildbot slaves as a result. This should repair it. ........ r45969 | georg.brandl | 2006-05-11 21:57:09 +0200 (Thu, 11 May 2006) | 2 lines Typo fix. ........ r45970 | tim.peters | 2006-05-12 03:57:59 +0200 (Fri, 12 May 2006) | 5 lines SF patch #1473132: Improve docs for tp_clear and tp_traverse, by Collin Winter. Bugfix candidate (but I'm not going to bother). ........ r45974 | martin.v.loewis | 2006-05-12 14:27:28 +0200 (Fri, 12 May 2006) | 4 lines Dynamically allocate path name buffer for Unicode path name in listdir. Fixes #1431582. Stop overallocating MAX_PATH characters for ANSI path names. Stop assigning to errno. ........ r45975 | martin.v.loewis | 2006-05-12 15:57:36 +0200 (Fri, 12 May 2006) | 1 line Move icon files into DLLs dir. Fixes #1477968. ........ r45976 | george.yoshida | 2006-05-12 18:40:11 +0200 (Fri, 12 May 2006) | 2 lines At first there were 6 steps, but one was removed after that. ........ r45977 | martin.v.loewis | 2006-05-12 19:22:04 +0200 (Fri, 12 May 2006) | 1 line Fix alignment error on Itanium. ........ r45978 | george.yoshida | 2006-05-12 19:25:26 +0200 (Fri, 12 May 2006) | 3 lines Duplicated description about the illegal continue usage can be found in nearly the same place. They are same, so keep the original one and remove the later-added one. ........ r45980 | thomas.heller | 2006-05-12 20:16:03 +0200 (Fri, 12 May 2006) | 2 lines Add missing svn properties. ........ r45981 | thomas.heller | 2006-05-12 20:47:35 +0200 (Fri, 12 May 2006) | 1 line set svn properties ........ r45982 | thomas.heller | 2006-05-12 21:31:46 +0200 (Fri, 12 May 2006) | 1 line add svn:eol-style native svn:keywords Id ........ r45987 | gerhard.haering | 2006-05-13 01:49:49 +0200 (Sat, 13 May 2006) | 3 lines Integrated the rest of the pysqlite reference manual into the Python documentation. Ready to be reviewed and improved upon. ........ r45988 | george.yoshida | 2006-05-13 08:53:31 +0200 (Sat, 13 May 2006) | 2 lines Add \exception markup ........ r45990 | martin.v.loewis | 2006-05-13 15:34:04 +0200 (Sat, 13 May 2006) | 2 lines Revert 43315: Printing of %zd must be signed. ........ r45992 | tim.peters | 2006-05-14 01:28:20 +0200 (Sun, 14 May 2006) | 11 lines Teach PyString_FromFormat, PyErr_Format, and PyString_FromFormatV about "%u", "%lu" and "%zu" formats. Since PyString_FromFormat and PyErr_Format have exactly the same rules (both inherited from PyString_FromFormatV), it would be good if someone with more LaTeX Fu changed one of them to just point to the other. Their docs were way out of synch before this patch, and I just did a mass copy+paste to repair that. Not a backport candidate (this is a new feature). ........ r45993 | tim.peters | 2006-05-14 01:31:05 +0200 (Sun, 14 May 2006) | 2 lines Typo repair. ........ r45994 | tim.peters | 2006-05-14 01:33:19 +0200 (Sun, 14 May 2006) | 2 lines Remove lie in new comment. ........ r45995 | ronald.oussoren | 2006-05-14 21:56:34 +0200 (Sun, 14 May 2006) | 11 lines Rework the build system for osx applications: * Don't use xcodebuild for building PythonLauncher, but use a normal unix makefile. This makes it a lot easier to use the same build flags as for the rest of python (e.g. make a universal version of python launcher) * Convert the mac makefile-s to makefile.in-s and use configure to set makefile variables instead of forwarding them as command-line arguments * Add a C version of pythonw, that we you can use '#!/usr/local/bin/pythonw' * Build IDLE.app using bundlebuilder instead of BuildApplet, that will allow easier modification of the bundle contents later on. ........ r45996 | ronald.oussoren | 2006-05-14 22:35:41 +0200 (Sun, 14 May 2006) | 6 lines A first cut at replacing the icons on MacOS X. This replaces all icons by icons based on the new python.org logo. These are also the first icons that are "proper" OSX icons. These icons were created by Jacob Rus. ........ r45997 | ronald.oussoren | 2006-05-14 23:07:41 +0200 (Sun, 14 May 2006) | 3 lines I missed one small detail in my rewrite of the osx build files: the path to the Python.app template. ........ r45998 | martin.v.loewis | 2006-05-15 07:51:36 +0200 (Mon, 15 May 2006) | 2 lines Fix memory leak. ........ r45999 | neal.norwitz | 2006-05-15 08:48:14 +0200 (Mon, 15 May 2006) | 1 line Move items implemented after a2 into the new a3 section ........ r46000 | neal.norwitz | 2006-05-15 09:04:36 +0200 (Mon, 15 May 2006) | 5 lines - Bug #1487966: Fix SystemError with conditional expression in assignment Most of the test_syntax changes are just updating the numbers. ........ r46001 | neal.norwitz | 2006-05-15 09:17:23 +0200 (Mon, 15 May 2006) | 1 line Patch #1488312, Fix memory alignment problem on SPARC in unicode. Will backport ........ r46003 | martin.v.loewis | 2006-05-15 11:22:27 +0200 (Mon, 15 May 2006) | 3 lines Remove bogus DECREF of self. Change __str__() functions to METH_O. Change WindowsError__str__ to use PyTuple_Pack. ........ r46005 | georg.brandl | 2006-05-15 21:30:35 +0200 (Mon, 15 May 2006) | 3 lines [ 1488881 ] tarfile.py: support for file-objects and bz2 (cp. #1488634) ........ r46007 | tim.peters | 2006-05-15 22:44:10 +0200 (Mon, 15 May 2006) | 9 lines ReadDetectFileobjTest: repair Windows disasters by opening the file object in binary mode. The Windows buildbot slaves shouldn't swap themselves to death anymore. However, test_tarfile may still fail because of a temp directory left behind from a previous failing run. Windows buildbot owners may need to remove that directory by hand. ........ r46009 | tim.peters | 2006-05-15 23:32:25 +0200 (Mon, 15 May 2006) | 3 lines test_directory(): Remove the leftover temp directory that's making the Windows buildbots fail test_tarfile. ........ r46010 | martin.v.loewis | 2006-05-16 09:05:37 +0200 (Tue, 16 May 2006) | 4 lines - Test for sys/statvfs.h before including it, as statvfs is present on some OSX installation, but its header file is not. Will backport to 2.4 ........ r46012 | georg.brandl | 2006-05-16 09:38:27 +0200 (Tue, 16 May 2006) | 3 lines Patch #1435422: zlib's compress and decompress objects now have a copy() method. ........ r46015 | andrew.kuchling | 2006-05-16 18:11:54 +0200 (Tue, 16 May 2006) | 1 line Add item ........ r46016 | andrew.kuchling | 2006-05-16 18:27:31 +0200 (Tue, 16 May 2006) | 3 lines PEP 243 has been withdrawn, so don't refer to it any more. The PyPI upload material has been moved into the section on PEP314. ........ r46017 | george.yoshida | 2006-05-16 19:42:16 +0200 (Tue, 16 May 2006) | 2 lines Update for 'ImportWarning' ........ r46018 | george.yoshida | 2006-05-16 20:07:00 +0200 (Tue, 16 May 2006) | 4 lines Mention that Exception is now a subclass of BaseException. Remove a sentence that says that BaseException inherits from BaseException. (I guess this is just a copy & paste mistake.) ........ r46019 | george.yoshida | 2006-05-16 20:26:10 +0200 (Tue, 16 May 2006) | 2 lines Document ImportWarning ........ r46020 | tim.peters | 2006-05-17 01:22:20 +0200 (Wed, 17 May 2006) | 2 lines Whitespace normalization. ........ r46021 | tim.peters | 2006-05-17 01:24:08 +0200 (Wed, 17 May 2006) | 2 lines Text files missing the SVN eol-style property. ........ r46022 | tim.peters | 2006-05-17 03:30:11 +0200 (Wed, 17 May 2006) | 2 lines PyZlib_copy(), PyZlib_uncopy(): Repair leaks on the normal-case path. ........ r46023 | georg.brandl | 2006-05-17 16:06:07 +0200 (Wed, 17 May 2006) | 3 lines Remove misleading comment about type-class unification. ........ r46024 | georg.brandl | 2006-05-17 16:11:36 +0200 (Wed, 17 May 2006) | 3 lines Apply patch #1489784 from Michael Foord. ........ r46025 | georg.brandl | 2006-05-17 16:18:20 +0200 (Wed, 17 May 2006) | 3 lines Fix typo in os.utime docstring (patch #1490189) ........ r46026 | georg.brandl | 2006-05-17 16:26:50 +0200 (Wed, 17 May 2006) | 3 lines Patch #1490224: set time.altzone correctly on Cygwin. ........ r46027 | georg.brandl | 2006-05-17 16:45:06 +0200 (Wed, 17 May 2006) | 4 lines Add global debug flag to cookielib to avoid heavy dependency on the logging module. Resolves #1484758. ........ r46028 | georg.brandl | 2006-05-17 16:56:04 +0200 (Wed, 17 May 2006) | 3 lines Patch #1486962: Several bugs in the turtle Tk demo module were fixed and several features added, such as speed and geometry control. ........ r46029 | georg.brandl | 2006-05-17 17:17:00 +0200 (Wed, 17 May 2006) | 4 lines Delay-import some large modules to speed up urllib2 import. (fixes #1484793). ........ r46030 | georg.brandl | 2006-05-17 17:51:16 +0200 (Wed, 17 May 2006) | 3 lines Patch #1180296: improve locale string formatting functions ........ r46032 | tim.peters | 2006-05-18 04:06:40 +0200 (Thu, 18 May 2006) | 2 lines Whitespace normalization. ........ r46033 | georg.brandl | 2006-05-18 08:11:19 +0200 (Thu, 18 May 2006) | 3 lines Amendments to patch #1484695. ........ r46034 | georg.brandl | 2006-05-18 08:18:06 +0200 (Thu, 18 May 2006) | 3 lines Remove unused import. ........ r46035 | georg.brandl | 2006-05-18 08:33:27 +0200 (Thu, 18 May 2006) | 3 lines Fix test_locale for platforms without a default thousands separator. ........ r46036 | neal.norwitz | 2006-05-18 08:51:46 +0200 (Thu, 18 May 2006) | 1 line Little cleanup ........ r46037 | georg.brandl | 2006-05-18 09:01:27 +0200 (Thu, 18 May 2006) | 4 lines Bug #1462152: file() now checks more thoroughly for invalid mode strings and removes a possible "U" before passing the mode to the C library function. ........ r46038 | georg.brandl | 2006-05-18 09:20:05 +0200 (Thu, 18 May 2006) | 3 lines Bug #1490688: properly document %e, %f, %g format subtleties. ........ r46039 | vinay.sajip | 2006-05-18 09:28:58 +0200 (Thu, 18 May 2006) | 1 line Changed status from "beta" to "production"; since logging has been part of the stdlib since 2.3, it should be safe to make this assertion ;-) ........ r46040 | ronald.oussoren | 2006-05-18 11:04:15 +0200 (Thu, 18 May 2006) | 2 lines Fix some minor issues with the generated application bundles on MacOSX ........ r46041 | andrew.kuchling | 2006-05-19 02:03:55 +0200 (Fri, 19 May 2006) | 1 line Typo fix; add clarifying word ........ r46044 | neal.norwitz | 2006-05-19 08:31:23 +0200 (Fri, 19 May 2006) | 3 lines Fix #132 from Coverity, retval could have been derefed if a continue inside a try failed. ........ r46045 | neal.norwitz | 2006-05-19 08:43:50 +0200 (Fri, 19 May 2006) | 2 lines Fix #1474677, non-keyword argument following keyword. ........ r46046 | neal.norwitz | 2006-05-19 09:00:58 +0200 (Fri, 19 May 2006) | 4 lines Bug/Patch #1481770: Use .so extension for shared libraries on HP-UX for ia64. I suppose this could be backported if anyone cares. ........ r46047 | neal.norwitz | 2006-05-19 09:05:01 +0200 (Fri, 19 May 2006) | 7 lines Oops, I forgot to include this file in the last commit (46046): Bug/Patch #1481770: Use .so extension for shared libraries on HP-UX for ia64. I suppose this could be backported if anyone cares. ........ r46050 | ronald.oussoren | 2006-05-19 20:17:31 +0200 (Fri, 19 May 2006) | 6 lines * Change working directory to the users home directory, that makes the file open/save dialogs more useable. * Don't use argv emulator, its not needed for idle. ........ r46052 | tim.peters | 2006-05-19 21:16:34 +0200 (Fri, 19 May 2006) | 2 lines Whitespace normalization. ........ r46054 | ronald.oussoren | 2006-05-20 08:17:01 +0200 (Sat, 20 May 2006) | 9 lines Fix bug #1000914 (again). This patches a file that is generated by bgen, however the code is now the same as a current copy of bgen would generate. Without this patch most types in the Carbon.CF module are unusable. I haven't managed to coax bgen into generating a complete copy of _CFmodule.c yet :-(, hence the manual patching. ........ r46055 | george.yoshida | 2006-05-20 17:36:19 +0200 (Sat, 20 May 2006) | 3 lines - markup fix - add clarifying words ........ r46057 | george.yoshida | 2006-05-20 18:29:14 +0200 (Sat, 20 May 2006) | 3 lines - Add 'as' and 'with' as new keywords in 2.5. - Regenerate keyword lists with reswords.py. ........ r46058 | george.yoshida | 2006-05-20 20:07:26 +0200 (Sat, 20 May 2006) | 2 lines Apply patch #1492147 from Mike Foord. ........ r46059 | andrew.kuchling | 2006-05-20 21:25:16 +0200 (Sat, 20 May 2006) | 1 line Minor edits ........ r46061 | george.yoshida | 2006-05-21 06:22:59 +0200 (Sun, 21 May 2006) | 2 lines Fix the TeX compile error. ........ r46062 | george.yoshida | 2006-05-21 06:40:32 +0200 (Sun, 21 May 2006) | 2 lines Apply patch #1492255 from Mike Foord. ........ r46063 | martin.v.loewis | 2006-05-22 10:48:14 +0200 (Mon, 22 May 2006) | 1 line Patch 1490384: New Icons for the PC build. ........ r46064 | martin.v.loewis | 2006-05-22 11:15:18 +0200 (Mon, 22 May 2006) | 1 line Patch #1492356: Port to Windows CE (patch set 1). ........ r46065 | tim.peters | 2006-05-22 13:29:41 +0200 (Mon, 22 May 2006) | 4 lines Define SIZEOF_{DOUBLE,FLOAT} on Windows. Else Michael Hudson's nice gimmicks for IEEE special values (infinities, NaNs) don't work. ........ r46070 | bob.ippolito | 2006-05-22 16:31:24 +0200 (Mon, 22 May 2006) | 2 lines GzipFile.readline performance improvement (~30-40%), patch #1281707 ........ r46071 | bob.ippolito | 2006-05-22 17:22:46 +0200 (Mon, 22 May 2006) | 1 line Revert gzip readline performance patch #1281707 until a more generic performance improvement can be found ........ r46073 | fredrik.lundh | 2006-05-22 17:35:12 +0200 (Mon, 22 May 2006) | 4 lines docstring tweaks: count counts non-overlapping substrings, not total number of occurences ........ r46075 | bob.ippolito | 2006-05-22 17:59:12 +0200 (Mon, 22 May 2006) | 1 line Apply revised patch for GzipFile.readline performance #1281707 ........ r46076 | fredrik.lundh | 2006-05-22 18:29:30 +0200 (Mon, 22 May 2006) | 3 lines needforspeed: speed up unicode repeat, unicode string copy ........ r46079 | fredrik.lundh | 2006-05-22 19:12:58 +0200 (Mon, 22 May 2006) | 4 lines needforspeed: use memcpy for "long" strings; use a better algorithm for long repeats. ........ r46084 | tim.peters | 2006-05-22 21:17:04 +0200 (Mon, 22 May 2006) | 7 lines PyUnicode_Join(): Recent code changes introduced new compiler warnings on Windows (signed vs unsigned mismatch in comparisons). Cleaned that up by switching more locals to Py_ssize_t. Simplified overflow checking (it can _be_ simpler because while these things are declared as Py_ssize_t, then should in fact never be negative). ........ r46085 | tim.peters | 2006-05-23 07:47:16 +0200 (Tue, 23 May 2006) | 3 lines unicode_repeat(): Change type of local to Py_ssize_t, since that's what it should be. ........ r46094 | fredrik.lundh | 2006-05-23 12:10:57 +0200 (Tue, 23 May 2006) | 3 lines needforspeed: check first *and* last character before doing a full memcmp ........ r46095 | fredrik.lundh | 2006-05-23 12:12:21 +0200 (Tue, 23 May 2006) | 4 lines needforspeed: fixed unicode "in" operator to use same implementation approach as find/index ........ r46096 | richard.jones | 2006-05-23 12:37:38 +0200 (Tue, 23 May 2006) | 7 lines Merge from rjones-funccall branch. Applied patch zombie-frames-2.diff from sf patch 876206 with updates for Python 2.5 and also modified to retain the free_list to avoid the 67% slow-down in pybench recursion test. 5% speed up in function call pybench. ........ r46098 | ronald.oussoren | 2006-05-23 13:04:24 +0200 (Tue, 23 May 2006) | 2 lines Avoid creating a mess when installing a framework for the second time. ........ r46101 | georg.brandl | 2006-05-23 13:17:21 +0200 (Tue, 23 May 2006) | 3 lines PyErr_NewException now accepts a tuple of base classes as its "base" parameter. ........ r46103 | ronald.oussoren | 2006-05-23 13:47:16 +0200 (Tue, 23 May 2006) | 3 lines Disable linking extensions with -lpython2.5 for darwin. This should fix bug #1487105. ........ r46104 | ronald.oussoren | 2006-05-23 14:01:11 +0200 (Tue, 23 May 2006) | 6 lines Patch #1488098. This patchs makes it possible to create a universal build on OSX 10.4 and use the result to build extensions on 10.3. It also makes it possible to override the '-arch' and '-isysroot' compiler arguments for specific extensions. ........ r46108 | andrew.kuchling | 2006-05-23 14:44:36 +0200 (Tue, 23 May 2006) | 1 line Add some items; mention the sprint ........ r46109 | andrew.kuchling | 2006-05-23 14:47:01 +0200 (Tue, 23 May 2006) | 1 line Mention string improvements ........ r46110 | andrew.kuchling | 2006-05-23 14:49:35 +0200 (Tue, 23 May 2006) | 4 lines Use 'speed' instead of 'performance', because I agree with the argument at http://zestyping.livejournal.com/193260.html that 'erformance' really means something more general. ........ r46113 | ronald.oussoren | 2006-05-23 17:09:57 +0200 (Tue, 23 May 2006) | 2 lines An improved script for building the binary distribution on MacOSX. ........ r46128 | richard.jones | 2006-05-23 20:28:17 +0200 (Tue, 23 May 2006) | 3 lines Applied patch 1337051 by Neal Norwitz, saving 4 ints on frame objects. ........ r46129 | richard.jones | 2006-05-23 20:32:11 +0200 (Tue, 23 May 2006) | 1 line fix broken merge ........ r46130 | bob.ippolito | 2006-05-23 20:41:17 +0200 (Tue, 23 May 2006) | 1 line Update Misc/NEWS for gzip patch #1281707 ........ r46131 | bob.ippolito | 2006-05-23 20:43:47 +0200 (Tue, 23 May 2006) | 1 line Update Misc/NEWS for gzip patch #1281707 ........ r46132 | fredrik.lundh | 2006-05-23 20:44:25 +0200 (Tue, 23 May 2006) | 7 lines needforspeed: use append+reverse for rsplit, use "bloom filters" to speed up splitlines and strip with charsets; etc. rsplit is now as fast as split in all our tests (reverse takes no time at all), and splitlines() is nearly as fast as a plain split("\n") in our tests. and we're not done yet... ;-) ........ r46133 | tim.peters | 2006-05-23 20:45:30 +0200 (Tue, 23 May 2006) | 38 lines Bug #1334662 / patch #1335972: int(string, base) wrong answers. In rare cases of strings specifying true values near sys.maxint, and oddball bases (not decimal or a power of 2), int(string, base) could deliver insane answers. This repairs all such problems, and also speeds string->int significantly. On my box, here are % speedups for decimal strings of various lengths: length speedup ------ ------- 1 12.4% 2 15.7% 3 20.6% 4 28.1% 5 33.2% 6 37.5% 7 41.9% 8 46.3% 9 51.2% 10 19.5% 11 19.9% 12 23.9% 13 23.7% 14 23.3% 15 24.9% 16 25.3% 17 28.3% 18 27.9% 19 35.7% Note that the difference between 9 and 10 is the difference between short and long Python ints on a 32-bit box. The patch doesn't actually do anything to speed conversion to long: the speedup is due to detecting "unsigned long" overflow more quickly. This is a bugfix candidate, but it's a non-trivial patch and it would be painful to separate the "bug fix" from the "speed up" parts. ........ r46134 | bob.ippolito | 2006-05-23 20:46:41 +0200 (Tue, 23 May 2006) | 1 line Patch #1493701: performance enhancements for struct module. ........ r46136 | andrew.kuchling | 2006-05-23 21:00:45 +0200 (Tue, 23 May 2006) | 1 line Remove duplicate item ........ r46141 | bob.ippolito | 2006-05-23 21:09:51 +0200 (Tue, 23 May 2006) | 1 line revert #1493701 ........ r46142 | bob.ippolito | 2006-05-23 21:11:34 +0200 (Tue, 23 May 2006) | 1 line patch #1493701: performance enhancements for struct module ........ r46144 | bob.ippolito | 2006-05-23 21:12:41 +0200 (Tue, 23 May 2006) | 1 line patch #1493701: performance enhancements for struct module ........ r46148 | bob.ippolito | 2006-05-23 21:25:52 +0200 (Tue, 23 May 2006) | 1 line fix linking issue, warnings, in struct ........ r46149 | andrew.kuchling | 2006-05-23 21:29:38 +0200 (Tue, 23 May 2006) | 1 line Add two items ........ r46150 | bob.ippolito | 2006-05-23 21:31:23 +0200 (Tue, 23 May 2006) | 1 line forward declaration for PyStructType ........ r46151 | bob.ippolito | 2006-05-23 21:32:25 +0200 (Tue, 23 May 2006) | 1 line fix typo in _struct ........ r46152 | andrew.kuchling | 2006-05-23 21:32:35 +0200 (Tue, 23 May 2006) | 1 line Add item ........ r46153 | tim.peters | 2006-05-23 21:34:37 +0200 (Tue, 23 May 2006) | 3 lines Get the Windows build working again (recover from `struct` module changes). ........ r46155 | fredrik.lundh | 2006-05-23 21:47:35 +0200 (Tue, 23 May 2006) | 3 lines return 0 on misses, not -1. ........ r46156 | tim.peters | 2006-05-23 23:51:35 +0200 (Tue, 23 May 2006) | 4 lines test_struct grew weird behavior under regrtest.py -R, due to a module-level cache. Clearing the cache should make it stop showing up in refleak reports. ........ r46157 | tim.peters | 2006-05-23 23:54:23 +0200 (Tue, 23 May 2006) | 2 lines Whitespace normalization. ........ r46158 | tim.peters | 2006-05-23 23:55:53 +0200 (Tue, 23 May 2006) | 2 lines Add missing svn:eol-style property to text files. ........ r46161 | fredrik.lundh | 2006-05-24 12:20:36 +0200 (Wed, 24 May 2006) | 3 lines use Py_ssize_t for string indexes (thanks, neal!) ........ r46173 | fredrik.lundh | 2006-05-24 16:28:11 +0200 (Wed, 24 May 2006) | 14 lines needforspeed: use "fastsearch" for count and findstring helpers. this results in a 2.5x speedup on the stringbench count tests, and a 20x (!) speedup on the stringbench search/find/contains test, compared to 2.5a2. for more on the algorithm, see: http://effbot.org/zone/stringlib.htm if you get weird results, you can disable the new algoritm by undefining USE_FAST in Objects/unicodeobject.c. enjoy /F ........ r46182 | fredrik.lundh | 2006-05-24 17:11:01 +0200 (Wed, 24 May 2006) | 3 lines needforspeedindeed: use fastsearch also for __contains__ ........ r46184 | bob.ippolito | 2006-05-24 17:32:06 +0200 (Wed, 24 May 2006) | 1 line refactor unpack, add unpack_from ........ r46189 | fredrik.lundh | 2006-05-24 18:35:18 +0200 (Wed, 24 May 2006) | 4 lines needforspeed: refactored the replace code slightly; special-case constant-length changes; use fastsearch to locate the first match. ........ r46198 | andrew.dalke | 2006-05-24 20:55:37 +0200 (Wed, 24 May 2006) | 10 lines Added a slew of test for string replace, based various corner cases from the Need For Speed sprint coding. Includes commented out overflow tests which will be uncommented once the code is fixed. This test will break the 8-bit string tests because "".replace("", "A") == "" when it should == "A" We have a fix for it, which should be added tomorrow. ........ r46200 | tim.peters | 2006-05-24 22:27:18 +0200 (Wed, 24 May 2006) | 2 lines We can't leave the checked-in tests broken. ........ r46201 | tim.peters | 2006-05-24 22:29:44 +0200 (Wed, 24 May 2006) | 2 lines Whitespace normalization. ........ r46202 | tim.peters | 2006-05-24 23:00:45 +0200 (Wed, 24 May 2006) | 4 lines Disable the damn empty-string replace test -- it can't be make to pass now for unicode if it passes for str, or vice versa. ........ r46203 | tim.peters | 2006-05-24 23:10:40 +0200 (Wed, 24 May 2006) | 58 lines Heavily fiddled variant of patch #1442927: PyLong_FromString optimization. ``long(str, base)`` is now up to 6x faster for non-power-of-2 bases. The largest speedup is for inputs with about 1000 decimal digits. Conversion from non-power-of-2 bases remains quadratic-time in the number of input digits (it was and remains linear-time for bases 2, 4, 8, 16 and 32). Speedups at various lengths for decimal inputs, comparing 2.4.3 with current trunk. Note that it's actually a bit slower for 1-digit strings: len speedup ---- ------- 1 -4.5% 2 4.6% 3 8.3% 4 12.7% 5 16.9% 6 28.6% 7 35.5% 8 44.3% 9 46.6% 10 55.3% 11 65.7% 12 77.7% 13 73.4% 14 75.3% 15 85.2% 16 103.0% 17 95.1% 18 112.8% 19 117.9% 20 128.3% 30 174.5% 40 209.3% 50 236.3% 60 254.3% 70 262.9% 80 295.8% 90 297.3% 100 324.5% 200 374.6% 300 403.1% 400 391.1% 500 388.7% 600 440.6% 700 468.7% 800 498.0% 900 507.2% 1000 501.2% 2000 450.2% 3000 463.2% 4000 452.5% 5000 440.6% 6000 439.6% 7000 424.8% 8000 418.1% 9000 417.7% ........ r46204 | andrew.kuchling | 2006-05-25 02:23:03 +0200 (Thu, 25 May 2006) | 1 line Minor edits; add an item ........ r46205 | fred.drake | 2006-05-25 04:42:25 +0200 (Thu, 25 May 2006) | 3 lines fix broken links in PDF (SF patch #1281291, contributed by Rory Yorke) ........ r46208 | walter.doerwald | 2006-05-25 10:53:28 +0200 (Thu, 25 May 2006) | 2 lines Replace tab inside comment with space. ........ r46209 | thomas.wouters | 2006-05-25 13:25:51 +0200 (Thu, 25 May 2006) | 4 lines Fix #1488915, Multiple dots in relative import statement raise SyntaxError. ........ r46210 | thomas.wouters | 2006-05-25 13:26:25 +0200 (Thu, 25 May 2006) | 5 lines Update graminit.c for the fix for #1488915, Multiple dots in relative import statement raise SyntaxError, and add testcase. ........ r46211 | andrew.kuchling | 2006-05-25 14:27:59 +0200 (Thu, 25 May 2006) | 1 line Add entry; and fix a typo ........ r46214 | fredrik.lundh | 2006-05-25 17:22:03 +0200 (Thu, 25 May 2006) | 7 lines needforspeed: speed up upper and lower for 8-bit string objects. (the unicode versions of these are still 2x faster on windows, though...) based on work by Andrew Dalke, with tweaks by yours truly. ........ r46216 | fredrik.lundh | 2006-05-25 17:49:45 +0200 (Thu, 25 May 2006) | 5 lines needforspeed: make new upper/lower work properly for single-character strings too... (thanks to georg brandl for spotting the exact problem faster than anyone else) ........ r46217 | kristjan.jonsson | 2006-05-25 17:53:30 +0200 (Thu, 25 May 2006) | 1 line Added a new macro, Py_IS_FINITE(X). On windows there is an intrinsic for this and it is more efficient than to use !Py_IS_INFINITE(X) && !Py_IS_NAN(X). No change on other platforms ........ r46219 | fredrik.lundh | 2006-05-25 18:10:12 +0200 (Thu, 25 May 2006) | 4 lines needforspeed: _toupper/_tolower is a SUSv2 thing; fall back on ISO C versions if they're not defined. ........ r46220 | andrew.kuchling | 2006-05-25 18:23:15 +0200 (Thu, 25 May 2006) | 1 line Fix comment typos ........ r46221 | andrew.dalke | 2006-05-25 18:30:52 +0200 (Thu, 25 May 2006) | 2 lines Added tests for implementation error we came up with in the need for speed sprint. ........ r46222 | andrew.kuchling | 2006-05-25 18:34:54 +0200 (Thu, 25 May 2006) | 1 line Fix another typo ........ r46223 | kristjan.jonsson | 2006-05-25 18:39:27 +0200 (Thu, 25 May 2006) | 1 line Fix incorrect documentation for the Py_IS_FINITE(X) macro. ........ r46224 | fredrik.lundh | 2006-05-25 18:46:54 +0200 (Thu, 25 May 2006) | 3 lines needforspeed: check for overflow in replace (from Andrew Dalke) ........ r46226 | fredrik.lundh | 2006-05-25 19:08:14 +0200 (Thu, 25 May 2006) | 5 lines needforspeed: new replace implementation by Andrew Dalke. replace is now about 3x faster on my machine, for the replace tests from string- bench. ........ r46227 | tim.peters | 2006-05-25 19:34:03 +0200 (Thu, 25 May 2006) | 5 lines A new table to help string->integer conversion was added yesterday to both mystrtoul.c and longobject.c. Share the table instead. Also cut its size by 64 entries (they had been used for an inscrutable trick originally, but the code no longer tries to use that trick). ........ r46229 | andrew.dalke | 2006-05-25 19:53:00 +0200 (Thu, 25 May 2006) | 11 lines Fixed problem identified by Georg. The special-case in-place code for replace made a copy of the string using PyString_FromStringAndSize(s, n) and modify the copied string in-place. However, 1 (and 0) character strings are shared from a cache. This cause "A".replace("A", "a") to change the cached version of "A" -- used by everyone. Now may the copy with NULL as the string and do the memcpy manually. I've added regression tests to check if this happens in the future. Perhaps there should be a PyString_Copy for this case? ........ r46230 | fredrik.lundh | 2006-05-25 19:55:31 +0200 (Thu, 25 May 2006) | 4 lines needforspeed: use "fastsearch" for count. this results in a 3x speedup for the related stringbench tests. ........ r46231 | andrew.dalke | 2006-05-25 20:03:25 +0200 (Thu, 25 May 2006) | 4 lines Code had returned an ssize_t, upcast to long, then converted with PyInt_FromLong. Now using PyInt_FromSsize_t. ........ r46233 | andrew.kuchling | 2006-05-25 20:11:16 +0200 (Thu, 25 May 2006) | 1 line Comment typo ........ r46234 | andrew.dalke | 2006-05-25 20:18:39 +0200 (Thu, 25 May 2006) | 4 lines Added overflow test for adding two (very) large strings where the new string is over max Py_ssize_t. I have no way to test it on my box or any box I have access to. At least it doesn't break anything. ........ r46235 | bob.ippolito | 2006-05-25 20:20:23 +0200 (Thu, 25 May 2006) | 1 line Faster path for PyLong_FromLongLong, using PyLong_FromLong algorithm ........ r46238 | georg.brandl | 2006-05-25 20:44:09 +0200 (Thu, 25 May 2006) | 3 lines Guard the _active.remove() call to avoid errors when there is no _active list. ........ r46239 | fredrik.lundh | 2006-05-25 20:44:29 +0200 (Thu, 25 May 2006) | 4 lines needforspeed: use fastsearch also for find/index and contains. the related tests are now about 10x faster. ........ r46240 | bob.ippolito | 2006-05-25 20:44:50 +0200 (Thu, 25 May 2006) | 1 line Struct now unpacks to PY_LONG_LONG directly when possible, also include #ifdef'ed out code that will return int instead of long when in bounds (not active since it's an API and doc change) ........ r46241 | jack.diederich | 2006-05-25 20:47:15 +0200 (Thu, 25 May 2006) | 1 line * eliminate warning by reverting tmp_s type to 'const char*' ........ r46242 | bob.ippolito | 2006-05-25 21:03:19 +0200 (Thu, 25 May 2006) | 1 line Fix Cygwin compiler issue ........ r46243 | bob.ippolito | 2006-05-25 21:15:27 +0200 (Thu, 25 May 2006) | 1 line fix a struct regression where long would be returned for short unsigned integers ........ r46244 | georg.brandl | 2006-05-25 21:15:31 +0200 (Thu, 25 May 2006) | 4 lines Replace PyObject_CallFunction calls with only object args with PyObject_CallFunctionObjArgs, which is 30% faster. ........ r46245 | fredrik.lundh | 2006-05-25 21:19:05 +0200 (Thu, 25 May 2006) | 3 lines needforspeed: use insert+reverse instead of append ........ r46246 | bob.ippolito | 2006-05-25 21:33:38 +0200 (Thu, 25 May 2006) | 1 line Use LONG_MIN and LONG_MAX to check Python integer bounds instead of the incorrect INT_MIN and INT_MAX ........ r46248 | bob.ippolito | 2006-05-25 21:56:56 +0200 (Thu, 25 May 2006) | 1 line Use faster struct pack/unpack functions for the endian table that matches the host's ........ r46249 | bob.ippolito | 2006-05-25 21:59:56 +0200 (Thu, 25 May 2006) | 1 line enable darwin/x86 support for libffi and hence ctypes (doesn't yet support --enable-universalsdk) ........ r46252 | georg.brandl | 2006-05-25 22:28:10 +0200 (Thu, 25 May 2006) | 4 lines Someone seems to just have copy-pasted the docs of tp_compare to tp_richcompare ;) ........ r46253 | brett.cannon | 2006-05-25 22:44:08 +0200 (Thu, 25 May 2006) | 2 lines Swap out bare malloc()/free() use for PyMem_MALLOC()/PyMem_FREE() . ........ r46254 | bob.ippolito | 2006-05-25 22:52:38 +0200 (Thu, 25 May 2006) | 1 line squelch gcc4 darwin/x86 compiler warnings ........ r46255 | bob.ippolito | 2006-05-25 23:09:45 +0200 (Thu, 25 May 2006) | 1 line fix test_float regression and 64-bit size mismatch issue ........ r46256 | georg.brandl | 2006-05-25 23:11:56 +0200 (Thu, 25 May 2006) | 3 lines Add a x-ref to newer calling APIs. ........ r46257 | ronald.oussoren | 2006-05-25 23:30:54 +0200 (Thu, 25 May 2006) | 2 lines Fix minor typo in prep_cif.c ........ r46259 | brett.cannon | 2006-05-25 23:33:11 +0200 (Thu, 25 May 2006) | 4 lines Change test_values so that it compares the lowercasing of group names since getgrall() can return all lowercase names while getgrgid() returns proper casing. Discovered on Ubuntu 5.04 (custom). ........ r46261 | tim.peters | 2006-05-25 23:50:17 +0200 (Thu, 25 May 2006) | 7 lines Some Win64 pre-release in 2000 didn't support QueryPerformanceCounter(), but we believe Win64 does support it now. So use in time.clock(). It would be peachy if someone with a Win64 box tried this ;-) ........ r46262 | tim.peters | 2006-05-25 23:52:19 +0200 (Thu, 25 May 2006) | 2 lines Whitespace normalization. ........ r46263 | bob.ippolito | 2006-05-25 23:58:05 +0200 (Thu, 25 May 2006) | 1 line Add missing files from x86 darwin ctypes patch ........ r46264 | brett.cannon | 2006-05-26 00:00:14 +0200 (Fri, 26 May 2006) | 2 lines Move over to use of METH_O and METH_NOARGS. ........ r46265 | tim.peters | 2006-05-26 00:25:25 +0200 (Fri, 26 May 2006) | 3 lines Repair idiot typo, and complete the job of trying to use the Windows time.clock() implementation on Win64. ........ r46266 | tim.peters | 2006-05-26 00:28:46 +0200 (Fri, 26 May 2006) | 9 lines Patch #1494387: SVN longobject.c compiler warnings The SIGCHECK macro defined here has always been bizarre, but it apparently causes compiler warnings on "Sun Studio 11". I believe the warnings are bogus, but it doesn't hurt to make the macro definition saner. Bugfix candidate (but I'm not going to bother). ........ r46268 | fredrik.lundh | 2006-05-26 01:27:53 +0200 (Fri, 26 May 2006) | 8 lines needforspeed: partition for 8-bit strings. for some simple tests, this is on par with a corresponding find, and nearly twice as fast as split(sep, 1) full tests, a unicode version, and documentation will follow to- morrow. ........ r46271 | andrew.kuchling | 2006-05-26 03:46:22 +0200 (Fri, 26 May 2006) | 1 line Add Soc student ........ r46272 | ronald.oussoren | 2006-05-26 10:41:25 +0200 (Fri, 26 May 2006) | 3 lines Without this patch OSX users couldn't add new help sources because the code tried to update one item in a tuple. ........ r46273 | fredrik.lundh | 2006-05-26 10:54:28 +0200 (Fri, 26 May 2006) | 5 lines needforspeed: partition implementation, part two. feel free to improve the documentation and the docstrings. ........ r46274 | georg.brandl | 2006-05-26 11:05:54 +0200 (Fri, 26 May 2006) | 3 lines Clarify docs for str.partition(). ........ r46278 | fredrik.lundh | 2006-05-26 11:46:59 +0200 (Fri, 26 May 2006) | 5 lines needforspeed: use METH_O for argument handling, which made partition some ~15% faster for the current tests (which is noticable faster than a corre- sponding find call). thanks to neal-who-never-sleeps for the tip. ........ r46280 | fredrik.lundh | 2006-05-26 12:27:17 +0200 (Fri, 26 May 2006) | 5 lines needforspeed: use Py_ssize_t for the fastsearch counter and skip length (thanks, neal!). and yes, I've verified that this doesn't slow things down ;-) ........ r46285 | andrew.dalke | 2006-05-26 13:11:38 +0200 (Fri, 26 May 2006) | 2 lines Added a few more test cases for whitespace split. These strings have leading whitespace. ........ r46286 | jack.diederich | 2006-05-26 13:15:17 +0200 (Fri, 26 May 2006) | 1 line use Py_ssize_t in places that may need it ........ r46287 | andrew.dalke | 2006-05-26 13:15:22 +0200 (Fri, 26 May 2006) | 2 lines Added split whitespace checks for characters other than space. ........ r46288 | ronald.oussoren | 2006-05-26 13:17:55 +0200 (Fri, 26 May 2006) | 2 lines Fix buglet in postinstall script, it would generate an invalid .cshrc file. ........ r46290 | georg.brandl | 2006-05-26 13:26:11 +0200 (Fri, 26 May 2006) | 3 lines Add "partition" to UserString. ........ r46291 | fredrik.lundh | 2006-05-26 13:29:39 +0200 (Fri, 26 May 2006) | 5 lines needforspeed: added Py_LOCAL macro, based on the LOCAL macro used for SRE and others. applied Py_LOCAL to relevant portion of ceval, which gives a 1-2% speedup on my machine. ymmv. ........ r46292 | jack.diederich | 2006-05-26 13:37:20 +0200 (Fri, 26 May 2006) | 1 line when generating python code prefer to generate valid python code ........ r46293 | fredrik.lundh | 2006-05-26 13:38:15 +0200 (Fri, 26 May 2006) | 3 lines use Py_LOCAL also for string and unicode objects ........ r46294 | ronald.oussoren | 2006-05-26 13:38:39 +0200 (Fri, 26 May 2006) | 12 lines - Search the sqlite specific search directories after the normal include directories when looking for the version of sqlite to use. - On OSX: * Extract additional include and link directories from the CFLAGS and LDFLAGS, if the user has bothered to specify them we might as wel use them. * Add '-Wl,-search_paths_first' to the extra_link_args for readline and sqlite. This makes it possible to use a static library to override the system provided dynamic library. ........ r46295 | ronald.oussoren | 2006-05-26 13:43:26 +0200 (Fri, 26 May 2006) | 6 lines Integrate installing a framework in the 'make install' target. Until now users had to use 'make frameworkinstall' to install python when it is configured with '--enable-framework'. This tends to confuse users that don't hunt for readme files hidden in platform specific directories :-) ........ r46297 | fredrik.lundh | 2006-05-26 13:54:04 +0200 (Fri, 26 May 2006) | 4 lines needforspeed: added PY_LOCAL_AGGRESSIVE macro to enable "aggressive" LOCAL inlining; also added some missing whitespace ........ r46298 | andrew.kuchling | 2006-05-26 14:01:44 +0200 (Fri, 26 May 2006) | 1 line Typo fixes ........ r46299 | fredrik.lundh | 2006-05-26 14:01:49 +0200 (Fri, 26 May 2006) | 4 lines Py_LOCAL shouldn't be used for data; it works for some .NET 2003 compilers, but Trent's copy thinks that it's an anachronism... ........ r46300 | martin.blais | 2006-05-26 14:03:27 +0200 (Fri, 26 May 2006) | 12 lines Support for buffer protocol for socket and struct. * Added socket.recv_buf() and socket.recvfrom_buf() methods, that use the buffer protocol (send and sendto already did). * Added struct.pack_to(), that is the corresponding buffer compatible method to unpack_from(). * Fixed minor typos in arraymodule. ........ r46302 | ronald.oussoren | 2006-05-26 14:23:20 +0200 (Fri, 26 May 2006) | 6 lines - Remove previous version of the binary distribution script for OSX - Some small bugfixes for the IDLE.app wrapper - Tweaks to build-installer to ensure that python gets build in the right way, including sqlite3. - Updated readme files ........ r46305 | tim.peters | 2006-05-26 14:26:21 +0200 (Fri, 26 May 2006) | 2 lines Whitespace normalization. ........ r46307 | andrew.dalke | 2006-05-26 14:28:15 +0200 (Fri, 26 May 2006) | 7 lines I like tests. The new split functions use a preallocated list. Added tests which exceed the preallocation size, to exercise list appends/resizes. Also added more edge case tests. ........ r46308 | andrew.dalke | 2006-05-26 14:31:00 +0200 (Fri, 26 May 2006) | 2 lines Test cases for off-by-one errors in string split with multicharacter pattern. ........ r46309 | tim.peters | 2006-05-26 14:31:20 +0200 (Fri, 26 May 2006) | 2 lines Whitespace normalization. ........ r46313 | andrew.kuchling | 2006-05-26 14:39:48 +0200 (Fri, 26 May 2006) | 1 line Add str.partition() ........ r46314 | bob.ippolito | 2006-05-26 14:52:53 +0200 (Fri, 26 May 2006) | 1 line quick hack to fix busted binhex test ........ r46316 | andrew.dalke | 2006-05-26 15:05:55 +0200 (Fri, 26 May 2006) | 2 lines Added more rstrip tests, including for prealloc'ed arrays ........ r46320 | bob.ippolito | 2006-05-26 15:15:44 +0200 (Fri, 26 May 2006) | 1 line fix #1229380 No struct.pack exception for some out of range integers ........ r46325 | tim.peters | 2006-05-26 15:39:17 +0200 (Fri, 26 May 2006) | 2 lines Use open() to open files (was using file()). ........ r46327 | andrew.dalke | 2006-05-26 16:00:45 +0200 (Fri, 26 May 2006) | 37 lines Changes to string.split/rsplit on whitespace to preallocate space in the results list. Originally it allocated 0 items and used the list growth during append. Now it preallocates 12 items so the first few appends don't need list reallocs. ("Here are some words ."*2).split(None, 1) is 7% faster ("Here are some words ."*2).split() is is 15% faster (Your milage may vary, see dealership for details.) File parsing like this for line in f: count += len(line.split()) is also about 15% faster. There is a slowdown of about 3% for large strings because of the additional overhead of checking if the append is to a preallocated region of the list or not. This will be the rare case. It could be improved with special case code but we decided it was not useful enough. There is a cost of 12*sizeof(PyObject *) bytes per list. For the normal case of file parsing this is not a problem because of the lists have a short lifetime. We have not come up with cases where this is a problem in real life. I chose 12 because human text averages about 11 words per line in books, one of my data sets averages 6.2 words with a final peak at 11 words per line, and I work with a tab delimited data set with 8 tabs per line (or 9 words per line). 12 encompasses all of these. Also changed the last rstrip code to append then reverse, rather than doing insert(0). The strip() and rstrip() times are now comparable. ........ r46328 | tim.peters | 2006-05-26 16:02:05 +0200 (Fri, 26 May 2006) | 5 lines Explicitly close files. I'm trying to stop the frequent spurious test_tarfile failures on Windows buildbots, but it's hard to know how since the regrtest failure output is useless here, and it never fails when a buildbot slave runs test_tarfile the second time in verbose mode. ........ r46329 | andrew.kuchling | 2006-05-26 16:03:41 +0200 (Fri, 26 May 2006) | 1 line Add buffer support for struct, socket ........ r46330 | andrew.kuchling | 2006-05-26 16:04:19 +0200 (Fri, 26 May 2006) | 1 line Typo fix ........ r46331 | bob.ippolito | 2006-05-26 16:07:23 +0200 (Fri, 26 May 2006) | 1 line Fix distutils so that libffi will cross-compile between darwin/x86 and darwin/ppc ........ r46333 | bob.ippolito | 2006-05-26 16:23:21 +0200 (Fri, 26 May 2006) | 1 line Fix _struct typo that broke some 64-bit platforms ........ r46335 | bob.ippolito | 2006-05-26 16:29:35 +0200 (Fri, 26 May 2006) | 1 line Enable PY_USE_INT_WHEN_POSSIBLE in struct ........ r46343 | andrew.dalke | 2006-05-26 17:21:01 +0200 (Fri, 26 May 2006) | 2 lines Eeked out another 3% or so performance in split whitespace by cleaning up the algorithm. ........ r46352 | andrew.dalke | 2006-05-26 18:22:52 +0200 (Fri, 26 May 2006) | 3 lines Test for more edge strip cases; leading and trailing separator gets removed even with strip(..., 0) ........ r46354 | bob.ippolito | 2006-05-26 18:23:28 +0200 (Fri, 26 May 2006) | 1 line fix signed/unsigned mismatch in struct ........ r46355 | steve.holden | 2006-05-26 18:27:59 +0200 (Fri, 26 May 2006) | 5 lines Add -t option to allow easy test selection. Action verbose option correctly. Tweak operation counts. Add empty and new instances tests. Enable comparisons across different warp factors. Change version. ........ r46356 | fredrik.lundh | 2006-05-26 18:32:42 +0200 (Fri, 26 May 2006) | 3 lines needforspeed: use Py_LOCAL on a few more locals in stringobject.c ........ r46357 | thomas.heller | 2006-05-26 18:42:44 +0200 (Fri, 26 May 2006) | 4 lines For now, I gave up with automatic conversion of reST to Python-latex, so I'm writing this in latex now. Skeleton for the ctypes reference. ........ r46358 | tim.peters | 2006-05-26 18:49:28 +0200 (Fri, 26 May 2006) | 3 lines Repair Windows compiler warnings about mixing signed and unsigned integral types in comparisons. ........ r46359 | tim.peters | 2006-05-26 18:52:04 +0200 (Fri, 26 May 2006) | 2 lines Whitespace normalization. ........ r46360 | tim.peters | 2006-05-26 18:53:04 +0200 (Fri, 26 May 2006) | 2 lines Add missing svn:eol-style property to text files. ........ r46362 | fredrik.lundh | 2006-05-26 19:04:58 +0200 (Fri, 26 May 2006) | 3 lines needforspeed: stringlib refactoring (in progress) ........ r46363 | thomas.heller | 2006-05-26 19:18:33 +0200 (Fri, 26 May 2006) | 1 line Write some docs. ........ r46364 | fredrik.lundh | 2006-05-26 19:22:38 +0200 (Fri, 26 May 2006) | 3 lines needforspeed: stringlib refactoring (in progress) ........ r46366 | fredrik.lundh | 2006-05-26 19:26:39 +0200 (Fri, 26 May 2006) | 3 lines needforspeed: cleanup ........ r46367 | fredrik.lundh | 2006-05-26 19:31:41 +0200 (Fri, 26 May 2006) | 4 lines needforspeed: remove remaining USE_FAST macros; if fastsearch was broken, someone would have noticed by now ;-) ........ r46368 | steve.holden | 2006-05-26 19:41:32 +0200 (Fri, 26 May 2006) | 5 lines Use minimum calibration time rather than avergae to avoid the illusion of negative run times. Halt with an error if run times go below 10 ms, indicating that results will be unreliable. ........ r46370 | thomas.heller | 2006-05-26 19:47:40 +0200 (Fri, 26 May 2006) | 2 lines Reordered, and wrote more docs. ........ r46372 | georg.brandl | 2006-05-26 20:03:31 +0200 (Fri, 26 May 2006) | 9 lines Need for speed: Patch #921466 : sys.path_importer_cache is now used to cache valid and invalid file paths for the built-in import machinery which leads to fewer open calls on startup. Also fix issue with PEP 302 style import hooks which lead to more open() calls than necessary. ........ r46373 | fredrik.lundh | 2006-05-26 20:05:34 +0200 (Fri, 26 May 2006) | 3 lines removed unnecessary include ........ r46377 | fredrik.lundh | 2006-05-26 20:15:38 +0200 (Fri, 26 May 2006) | 3 lines needforspeed: added rpartition implementation ........ r46380 | fredrik.lundh | 2006-05-26 20:24:15 +0200 (Fri, 26 May 2006) | 5 lines needspeed: rpartition documentation, tests, and a bug fixes. feel free to add more tests and improve the documentation. ........ r46381 | steve.holden | 2006-05-26 20:26:21 +0200 (Fri, 26 May 2006) | 4 lines Revert tests to MAL's original round sizes to retiain comparability from long ago and far away. Stop calling this pybench 1.4 because it isn't. Remove the empty test, which was a bad idea. ........ r46387 | andrew.kuchling | 2006-05-26 20:41:18 +0200 (Fri, 26 May 2006) | 1 line Add rpartition() and path caching ........ r46388 | andrew.dalke | 2006-05-26 21:02:09 +0200 (Fri, 26 May 2006) | 10 lines substring split now uses /F's fast string matching algorithm. (If compiled without FAST search support, changed the pre-memcmp test to check the last character as well as the first. This gave a 25% speedup for my test case.) Rewrote the split algorithms so they stop when maxsplit gets to 0. Previously they did a string match first then checked if the maxsplit was reached. The new way prevents a needless string search. ........ r46391 | brett.cannon | 2006-05-26 21:04:47 +0200 (Fri, 26 May 2006) | 2 lines Change C spacing to 4 spaces by default to match PEP 7 for new C files. ........ r46392 | georg.brandl | 2006-05-26 21:04:47 +0200 (Fri, 26 May 2006) | 3 lines Exception isn't the root of all exception classes anymore. ........ r46397 | fredrik.lundh | 2006-05-26 21:23:21 +0200 (Fri, 26 May 2006) | 3 lines added rpartition method to UserString class ........ r46398 | fredrik.lundh | 2006-05-26 21:24:53 +0200 (Fri, 26 May 2006) | 4 lines needforspeed: stringlib refactoring, continued. added count and find helpers; updated unicodeobject to use stringlib_count ........ r46400 | fredrik.lundh | 2006-05-26 21:29:05 +0200 (Fri, 26 May 2006) | 4 lines needforspeed: stringlib refactoring: use stringlib/find for unicode find ........ r46403 | fredrik.lundh | 2006-05-26 21:33:03 +0200 (Fri, 26 May 2006) | 3 lines needforspeed: use a macro to fix slice indexes ........ r46404 | thomas.heller | 2006-05-26 21:43:45 +0200 (Fri, 26 May 2006) | 1 line Write more docs. ........ r46406 | fredrik.lundh | 2006-05-26 21:48:07 +0200 (Fri, 26 May 2006) | 3 lines needforspeed: stringlib refactoring: use stringlib/find for string find ........ r46407 | andrew.kuchling | 2006-05-26 21:51:10 +0200 (Fri, 26 May 2006) | 1 line Comment typo ........ r46409 | georg.brandl | 2006-05-26 22:04:44 +0200 (Fri, 26 May 2006) | 3 lines Replace Py_BuildValue("OO") by PyTuple_Pack. ........ r46411 | georg.brandl | 2006-05-26 22:14:47 +0200 (Fri, 26 May 2006) | 2 lines Patch #1492218: document None being a constant. ........ r46415 | georg.brandl | 2006-05-26 22:22:50 +0200 (Fri, 26 May 2006) | 3 lines Simplify calling. ........ r46416 | andrew.dalke | 2006-05-26 22:25:22 +0200 (Fri, 26 May 2006) | 4 lines Added limits to the replace code so it does not count all of the matching patterns in a string, only the number needed by the max limit. ........ r46417 | bob.ippolito | 2006-05-26 22:25:23 +0200 (Fri, 26 May 2006) | 1 line enable all of the struct tests, use ssize_t, fix some whitespace ........ r46418 | tim.peters | 2006-05-26 22:56:56 +0200 (Fri, 26 May 2006) | 2 lines Record Iceland sprint attendees. ........ r46421 | tim.peters | 2006-05-26 23:51:13 +0200 (Fri, 26 May 2006) | 2 lines Whitespace normalization. ........ r46422 | steve.holden | 2006-05-27 00:17:54 +0200 (Sat, 27 May 2006) | 2 lines Add Richard Tew to developers ........ r46423 | steve.holden | 2006-05-27 00:33:20 +0200 (Sat, 27 May 2006) | 2 lines Update help text and documentaition. ........ r46424 | steve.holden | 2006-05-27 00:39:27 +0200 (Sat, 27 May 2006) | 2 lines Blasted typos ... ........ r46425 | andrew.dalke | 2006-05-27 00:49:03 +0200 (Sat, 27 May 2006) | 2 lines Added description of why splitlines doesn't use the prealloc strategy ........ r46426 | tim.peters | 2006-05-27 01:14:37 +0200 (Sat, 27 May 2006) | 19 lines Patch 1145039. set_exc_info(), reset_exc_info(): By exploiting the likely (who knows?) invariant that when an exception's `type` is NULL, its `value` and `traceback` are also NULL, save some cycles in heavily-executed code. This is a "a kronar saved is a kronar earned" patch: the speedup isn't reliably measurable, but it obviously does reduce the operation count in the normal (no exception raised) path through PyEval_EvalFrameEx(). The tim-exc_sanity branch tries to push this harder, but is still blowing up (at least in part due to pre-existing subtle bugs that appear to have no other visible consequences!). Not a bugfix candidate. ........ r46429 | steve.holden | 2006-05-27 02:51:52 +0200 (Sat, 27 May 2006) | 2 lines Reinstate new-style object tests. ........ r46430 | neal.norwitz | 2006-05-27 07:18:57 +0200 (Sat, 27 May 2006) | 1 line Fix compiler warning (and whitespace) on Mac OS 10.4. (A lot of this code looked duplicated, I wonder if a utility function could help reduce the duplication here.) ........ r46431 | neal.norwitz | 2006-05-27 07:21:30 +0200 (Sat, 27 May 2006) | 4 lines Fix Coverity warnings. - Check the correct variable (str_obj, not str) for NULL - sep_len was already verified it wasn't 0 ........ r46432 | martin.v.loewis | 2006-05-27 10:36:52 +0200 (Sat, 27 May 2006) | 2 lines Patch 1494554: Update numeric properties to Unicode 4.1. ........ r46433 | martin.v.loewis | 2006-05-27 10:54:29 +0200 (Sat, 27 May 2006) | 2 lines Explain why 'consumed' is initialized. ........ r46436 | fredrik.lundh | 2006-05-27 12:05:10 +0200 (Sat, 27 May 2006) | 3 lines needforspeed: more stringlib refactoring ........ r46438 | fredrik.lundh | 2006-05-27 12:39:48 +0200 (Sat, 27 May 2006) | 5 lines needforspeed: backed out the Py_LOCAL-isation of ceval; the massive in- lining killed performance on certain Intel boxes, and the "aggressive" macro itself gives most of the benefits on others. ........ r46439 | andrew.dalke | 2006-05-27 13:04:36 +0200 (Sat, 27 May 2006) | 2 lines fixed typo ........ r46440 | martin.v.loewis | 2006-05-27 13:07:49 +0200 (Sat, 27 May 2006) | 2 lines Revert bogus change committed in 46432 to this file. ........ r46444 | andrew.kuchling | 2006-05-27 13:26:33 +0200 (Sat, 27 May 2006) | 1 line Add Py_LOCAL macros ........ r46450 | bob.ippolito | 2006-05-27 13:47:12 +0200 (Sat, 27 May 2006) | 1 line Remove the range checking and int usage #defines from _struct and strip out the now-dead code ........ r46454 | bob.ippolito | 2006-05-27 14:11:36 +0200 (Sat, 27 May 2006) | 1 line Fix up struct docstrings, add struct.pack_to function for symmetry ........ r46456 | richard.jones | 2006-05-27 14:29:24 +0200 (Sat, 27 May 2006) | 2 lines Conversion of exceptions over from faked-up classes to new-style C types. ........ r46457 | georg.brandl | 2006-05-27 14:30:25 +0200 (Sat, 27 May 2006) | 3 lines Add news item for new-style exception class branch merge. ........ r46458 | tim.peters | 2006-05-27 14:36:53 +0200 (Sat, 27 May 2006) | 3 lines More random thrashing trying to understand spurious Windows failures. Who's keeping a bz2 file open? ........ r46460 | andrew.kuchling | 2006-05-27 15:44:37 +0200 (Sat, 27 May 2006) | 1 line Mention new-style exceptions ........ r46461 | richard.jones | 2006-05-27 15:50:42 +0200 (Sat, 27 May 2006) | 1 line credit where credit is due ........ r46462 | georg.brandl | 2006-05-27 16:02:03 +0200 (Sat, 27 May 2006) | 3 lines Always close BZ2Proxy object. Remove unnecessary struct usage. ........ r46463 | tim.peters | 2006-05-27 16:13:13 +0200 (Sat, 27 May 2006) | 2 lines The cheery optimism of old age. ........ r46464 | andrew.dalke | 2006-05-27 16:16:40 +0200 (Sat, 27 May 2006) | 2 lines cleanup - removed trailing whitespace ........ r46465 | georg.brandl | 2006-05-27 16:41:55 +0200 (Sat, 27 May 2006) | 3 lines Remove spurious semicolons after macro invocations. ........ r46468 | fredrik.lundh | 2006-05-27 16:58:20 +0200 (Sat, 27 May 2006) | 4 lines needforspeed: replace improvements, changed to Py_LOCAL_INLINE where appropriate ........ r46469 | fredrik.lundh | 2006-05-27 17:20:22 +0200 (Sat, 27 May 2006) | 4 lines needforspeed: stringlib refactoring: changed find_obj to find_slice, to enable use from stringobject ........ r46470 | fredrik.lundh | 2006-05-27 17:26:19 +0200 (Sat, 27 May 2006) | 3 lines needforspeed: stringlib refactoring: use find_slice for stringobject ........ r46472 | kristjan.jonsson | 2006-05-27 17:41:31 +0200 (Sat, 27 May 2006) | 1 line Add a PCBuild8 build directory for building with Visual Studio .NET 2005. Contains a special project to perform profile guided optimizations on the pythoncore.dll, by instrumenting and running pybench.py ........ r46473 | jack.diederich | 2006-05-27 17:44:34 +0200 (Sat, 27 May 2006) | 3 lines needforspeed: use PyObject_MALLOC instead of system malloc for small allocations. Use PyMem_MALLOC for larger (1k+) chunks. 1%-2% speedup. ........ r46474 | bob.ippolito | 2006-05-27 17:53:49 +0200 (Sat, 27 May 2006) | 1 line fix struct regression on 64-bit platforms ........ r46475 | richard.jones | 2006-05-27 18:07:28 +0200 (Sat, 27 May 2006) | 1 line doc string additions and tweaks ........ r46477 | richard.jones | 2006-05-27 18:15:11 +0200 (Sat, 27 May 2006) | 1 line move semicolons ........ r46478 | george.yoshida | 2006-05-27 18:32:44 +0200 (Sat, 27 May 2006) | 2 lines minor markup nits ........ r46488 | george.yoshida | 2006-05-27 18:51:43 +0200 (Sat, 27 May 2006) | 3 lines End of Ch.3 is now about "with statement". Avoid obsolescence by directly referring to the section. ........ r46489 | george.yoshida | 2006-05-27 19:09:17 +0200 (Sat, 27 May 2006) | 2 lines fix typo ........
2006-05-27 16:21:47 -03:00
# should not format with a comma, but always with C locale
self.assertEqual('1.0', '%.1f' % 1.0)
2006-01-20 13:48:54 -04:00
def test_constructor(self):
# unicode(obj) tests (this maps to PyObject_Unicode() at C level)
self.assertEqual(
str('unicode remains unicode'),
'unicode remains unicode'
)
for text in ('ascii', '\xe9', '\u20ac', '\U0010FFFF'):
subclass = StrSubclass(text)
self.assertEqual(str(subclass), text)
self.assertEqual(len(subclass), len(text))
if text == 'ascii':
self.assertEqual(subclass.encode('ascii'), b'ascii')
self.assertEqual(subclass.encode('utf-8'), b'ascii')
self.assertEqual(
str('strings are converted to unicode'),
'strings are converted to unicode'
)
class StringCompat:
def __init__(self, x):
self.x = x
def __str__(self):
return self.x
self.assertEqual(
str(StringCompat('__str__ compatible objects are recognized')),
'__str__ compatible objects are recognized'
)
# unicode(obj) is compatible to str():
o = StringCompat('unicode(obj) is compatible to str()')
self.assertEqual(str(o), 'unicode(obj) is compatible to str()')
self.assertEqual(str(o), 'unicode(obj) is compatible to str()')
for obj in (123, 123.45, 123):
self.assertEqual(str(obj), str(str(obj)))
# unicode(obj, encoding, error) tests (this maps to
# PyUnicode_FromEncodedObject() at C level)
self.assertRaises(
TypeError,
str,
'decoding unicode is not supported',
'utf-8',
'strict'
)
self.assertEqual(
str(b'strings are decoded to unicode', 'utf-8', 'strict'),
'strings are decoded to unicode'
)
self.assertEqual(
str(
memoryview(b'character buffers are decoded to unicode'),
'utf-8',
'strict'
),
'character buffers are decoded to unicode'
)
self.assertRaises(TypeError, str, 42, 42, 42)
def test_constructor_keyword_args(self):
"""Pass various keyword argument combinations to the constructor."""
# The object argument can be passed as a keyword.
self.assertEqual(str(object='foo'), 'foo')
self.assertEqual(str(object=b'foo', encoding='utf-8'), 'foo')
# The errors argument without encoding triggers "decode" mode.
self.assertEqual(str(b'foo', errors='strict'), 'foo') # not "b'foo'"
self.assertEqual(str(object=b'foo', errors='strict'), 'foo')
def test_constructor_defaults(self):
"""Check the constructor argument defaults."""
# The object argument defaults to '' or b''.
self.assertEqual(str(), '')
self.assertEqual(str(errors='strict'), '')
utf8_cent = '¢'.encode('utf-8')
# The encoding argument defaults to utf-8.
self.assertEqual(str(utf8_cent, errors='strict'), '¢')
# The errors argument defaults to strict.
self.assertRaises(UnicodeDecodeError, str, utf8_cent, encoding='ascii')
def test_codecs_utf7(self):
utfTests = [
('A\u2262\u0391.', b'A+ImIDkQ.'), # RFC2152 example
('Hi Mom -\u263a-!', b'Hi Mom -+Jjo--!'), # RFC2152 example
('\u65E5\u672C\u8A9E', b'+ZeVnLIqe-'), # RFC2152 example
('Item 3 is \u00a31.', b'Item 3 is +AKM-1.'), # RFC2152 example
('+', b'+-'),
('+-', b'+--'),
('+?', b'+-?'),
(r'\?', b'+AFw?'),
('+?', b'+-?'),
(r'\\?', b'+AFwAXA?'),
(r'\\\?', b'+AFwAXABc?'),
(r'++--', b'+-+---'),
('\U000abcde', b'+2m/c3g-'), # surrogate pairs
('/', b'/'),
]
for (x, y) in utfTests:
self.assertEqual(x.encode('utf-7'), y)
# Unpaired surrogates are passed through
self.assertEqual('\uD801'.encode('utf-7'), b'+2AE-')
self.assertEqual('\uD801x'.encode('utf-7'), b'+2AE-x')
self.assertEqual('\uDC01'.encode('utf-7'), b'+3AE-')
self.assertEqual('\uDC01x'.encode('utf-7'), b'+3AE-x')
self.assertEqual(b'+2AE-'.decode('utf-7'), '\uD801')
self.assertEqual(b'+2AE-x'.decode('utf-7'), '\uD801x')
self.assertEqual(b'+3AE-'.decode('utf-7'), '\uDC01')
self.assertEqual(b'+3AE-x'.decode('utf-7'), '\uDC01x')
self.assertEqual('\uD801\U000abcde'.encode('utf-7'), b'+2AHab9ze-')
self.assertEqual(b'+2AHab9ze-'.decode('utf-7'), '\uD801\U000abcde')
# Issue #2242: crash on some Windows/MSVC versions
self.assertEqual(b'+\xc1'.decode('utf-7', 'ignore'), '')
# Direct encoded characters
set_d = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789'(),-./:?"
# Optional direct characters
set_o = '!"#$%&*;<=>@[]^_`{|}'
for c in set_d:
self.assertEqual(c.encode('utf7'), c.encode('ascii'))
self.assertEqual(c.encode('ascii').decode('utf7'), c)
for c in set_o:
self.assertEqual(c.encode('ascii').decode('utf7'), c)
with self.assertRaisesRegex(UnicodeDecodeError,
'ill-formed sequence'):
b'+@'.decode('utf-7')
def test_codecs_utf8(self):
self.assertEqual(''.encode('utf-8'), b'')
self.assertEqual('\u20ac'.encode('utf-8'), b'\xe2\x82\xac')
self.assertEqual('\U00010002'.encode('utf-8'), b'\xf0\x90\x80\x82')
self.assertEqual('\U00023456'.encode('utf-8'), b'\xf0\xa3\x91\x96')
self.assertEqual('\ud800'.encode('utf-8', 'surrogatepass'), b'\xed\xa0\x80')
self.assertEqual('\udc00'.encode('utf-8', 'surrogatepass'), b'\xed\xb0\x80')
self.assertEqual(('\U00010002'*10).encode('utf-8'),
b'\xf0\x90\x80\x82'*10)
self.assertEqual(
'\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f'
'\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00'
'\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c'
'\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067'
'\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das'
' Nunstuck git und'.encode('utf-8'),
b'\xe6\xad\xa3\xe7\xa2\xba\xe3\x81\xab\xe8\xa8\x80\xe3\x81'
b'\x86\xe3\x81\xa8\xe7\xbf\xbb\xe8\xa8\xb3\xe3\x81\xaf\xe3'
b'\x81\x95\xe3\x82\x8c\xe3\x81\xa6\xe3\x81\x84\xe3\x81\xbe'
b'\xe3\x81\x9b\xe3\x82\x93\xe3\x80\x82\xe4\xb8\x80\xe9\x83'
b'\xa8\xe3\x81\xaf\xe3\x83\x89\xe3\x82\xa4\xe3\x83\x84\xe8'
b'\xaa\x9e\xe3\x81\xa7\xe3\x81\x99\xe3\x81\x8c\xe3\x80\x81'
b'\xe3\x81\x82\xe3\x81\xa8\xe3\x81\xaf\xe3\x81\xa7\xe3\x81'
b'\x9f\xe3\x82\x89\xe3\x82\x81\xe3\x81\xa7\xe3\x81\x99\xe3'
b'\x80\x82\xe5\xae\x9f\xe9\x9a\x9b\xe3\x81\xab\xe3\x81\xaf'
b'\xe3\x80\x8cWenn ist das Nunstuck git und'
)
# UTF-8 specific decoding tests
self.assertEqual(str(b'\xf0\xa3\x91\x96', 'utf-8'), '\U00023456' )
self.assertEqual(str(b'\xf0\x90\x80\x82', 'utf-8'), '\U00010002' )
self.assertEqual(str(b'\xe2\x82\xac', 'utf-8'), '\u20ac' )
# Other possible utf-8 test cases:
# * strict decoding testing for all of the
# UTF8_ERROR cases in PyUnicode_DecodeUTF8
def test_utf8_decode_valid_sequences(self):
sequences = [
# single byte
(b'\x00', '\x00'), (b'a', 'a'), (b'\x7f', '\x7f'),
# 2 bytes
(b'\xc2\x80', '\x80'), (b'\xdf\xbf', '\u07ff'),
# 3 bytes
(b'\xe0\xa0\x80', '\u0800'), (b'\xed\x9f\xbf', '\ud7ff'),
(b'\xee\x80\x80', '\uE000'), (b'\xef\xbf\xbf', '\uffff'),
# 4 bytes
(b'\xF0\x90\x80\x80', '\U00010000'),
(b'\xf4\x8f\xbf\xbf', '\U0010FFFF')
]
for seq, res in sequences:
self.assertEqual(seq.decode('utf-8'), res)
def test_utf8_decode_invalid_sequences(self):
# continuation bytes in a sequence of 2, 3, or 4 bytes
continuation_bytes = [bytes([x]) for x in range(0x80, 0xC0)]
# start bytes of a 2-byte sequence equivalent to code points < 0x7F
invalid_2B_seq_start_bytes = [bytes([x]) for x in range(0xC0, 0xC2)]
# start bytes of a 4-byte sequence equivalent to code points > 0x10FFFF
invalid_4B_seq_start_bytes = [bytes([x]) for x in range(0xF5, 0xF8)]
invalid_start_bytes = (
continuation_bytes + invalid_2B_seq_start_bytes +
invalid_4B_seq_start_bytes + [bytes([x]) for x in range(0xF7, 0x100)]
)
for byte in invalid_start_bytes:
self.assertRaises(UnicodeDecodeError, byte.decode, 'utf-8')
for sb in invalid_2B_seq_start_bytes:
for cb in continuation_bytes:
self.assertRaises(UnicodeDecodeError, (sb+cb).decode, 'utf-8')
for sb in invalid_4B_seq_start_bytes:
for cb1 in continuation_bytes[:3]:
for cb3 in continuation_bytes[:3]:
self.assertRaises(UnicodeDecodeError,
(sb+cb1+b'\x80'+cb3).decode, 'utf-8')
for cb in [bytes([x]) for x in range(0x80, 0xA0)]:
self.assertRaises(UnicodeDecodeError,
(b'\xE0'+cb+b'\x80').decode, 'utf-8')
self.assertRaises(UnicodeDecodeError,
(b'\xE0'+cb+b'\xBF').decode, 'utf-8')
# surrogates
for cb in [bytes([x]) for x in range(0xA0, 0xC0)]:
self.assertRaises(UnicodeDecodeError,
(b'\xED'+cb+b'\x80').decode, 'utf-8')
self.assertRaises(UnicodeDecodeError,
(b'\xED'+cb+b'\xBF').decode, 'utf-8')
for cb in [bytes([x]) for x in range(0x80, 0x90)]:
self.assertRaises(UnicodeDecodeError,
(b'\xF0'+cb+b'\x80\x80').decode, 'utf-8')
self.assertRaises(UnicodeDecodeError,
(b'\xF0'+cb+b'\xBF\xBF').decode, 'utf-8')
for cb in [bytes([x]) for x in range(0x90, 0xC0)]:
self.assertRaises(UnicodeDecodeError,
(b'\xF4'+cb+b'\x80\x80').decode, 'utf-8')
self.assertRaises(UnicodeDecodeError,
(b'\xF4'+cb+b'\xBF\xBF').decode, 'utf-8')
def test_issue8271(self):
# Issue #8271: during the decoding of an invalid UTF-8 byte sequence,
# only the start byte and the continuation byte(s) are now considered
# invalid, instead of the number of bytes specified by the start byte.
# See https://www.unicode.org/versions/Unicode5.2.0/ch03.pdf (page 95,
# table 3-8, Row 2) for more information about the algorithm used.
FFFD = '\ufffd'
sequences = [
# invalid start bytes
(b'\x80', FFFD), # continuation byte
(b'\x80\x80', FFFD*2), # 2 continuation bytes
(b'\xc0', FFFD),
(b'\xc0\xc0', FFFD*2),
(b'\xc1', FFFD),
(b'\xc1\xc0', FFFD*2),
(b'\xc0\xc1', FFFD*2),
# with start byte of a 2-byte sequence
(b'\xc2', FFFD), # only the start byte
(b'\xc2\xc2', FFFD*2), # 2 start bytes
(b'\xc2\xc2\xc2', FFFD*3), # 3 start bytes
(b'\xc2\x41', FFFD+'A'), # invalid continuation byte
# with start byte of a 3-byte sequence
(b'\xe1', FFFD), # only the start byte
(b'\xe1\xe1', FFFD*2), # 2 start bytes
(b'\xe1\xe1\xe1', FFFD*3), # 3 start bytes
(b'\xe1\xe1\xe1\xe1', FFFD*4), # 4 start bytes
(b'\xe1\x80', FFFD), # only 1 continuation byte
(b'\xe1\x41', FFFD+'A'), # invalid continuation byte
(b'\xe1\x41\x80', FFFD+'A'+FFFD), # invalid cb followed by valid cb
(b'\xe1\x41\x41', FFFD+'AA'), # 2 invalid continuation bytes
(b'\xe1\x80\x41', FFFD+'A'), # only 1 valid continuation byte
(b'\xe1\x80\xe1\x41', FFFD*2+'A'), # 1 valid and the other invalid
(b'\xe1\x41\xe1\x80', FFFD+'A'+FFFD), # 1 invalid and the other valid
# with start byte of a 4-byte sequence
(b'\xf1', FFFD), # only the start byte
(b'\xf1\xf1', FFFD*2), # 2 start bytes
(b'\xf1\xf1\xf1', FFFD*3), # 3 start bytes
(b'\xf1\xf1\xf1\xf1', FFFD*4), # 4 start bytes
(b'\xf1\xf1\xf1\xf1\xf1', FFFD*5), # 5 start bytes
(b'\xf1\x80', FFFD), # only 1 continuation bytes
(b'\xf1\x80\x80', FFFD), # only 2 continuation bytes
(b'\xf1\x80\x41', FFFD+'A'), # 1 valid cb and 1 invalid
(b'\xf1\x80\x41\x41', FFFD+'AA'), # 1 valid cb and 1 invalid
(b'\xf1\x80\x80\x41', FFFD+'A'), # 2 valid cb and 1 invalid
(b'\xf1\x41\x80', FFFD+'A'+FFFD), # 1 invalid cv and 1 valid
(b'\xf1\x41\x80\x80', FFFD+'A'+FFFD*2), # 1 invalid cb and 2 invalid
(b'\xf1\x41\x80\x41', FFFD+'A'+FFFD+'A'), # 2 invalid cb and 1 invalid
(b'\xf1\x41\x41\x80', FFFD+'AA'+FFFD), # 1 valid cb and 1 invalid
(b'\xf1\x41\xf1\x80', FFFD+'A'+FFFD),
(b'\xf1\x41\x80\xf1', FFFD+'A'+FFFD*2),
(b'\xf1\xf1\x80\x41', FFFD*2+'A'),
(b'\xf1\x41\xf1\xf1', FFFD+'A'+FFFD*2),
# with invalid start byte of a 4-byte sequence (rfc2279)
(b'\xf5', FFFD), # only the start byte
(b'\xf5\xf5', FFFD*2), # 2 start bytes
(b'\xf5\x80', FFFD*2), # only 1 continuation byte
(b'\xf5\x80\x80', FFFD*3), # only 2 continuation byte
(b'\xf5\x80\x80\x80', FFFD*4), # 3 continuation bytes
(b'\xf5\x80\x41', FFFD*2+'A'), # 1 valid cb and 1 invalid
(b'\xf5\x80\x41\xf5', FFFD*2+'A'+FFFD),
(b'\xf5\x41\x80\x80\x41', FFFD+'A'+FFFD*2+'A'),
# with invalid start byte of a 5-byte sequence (rfc2279)
(b'\xf8', FFFD), # only the start byte
(b'\xf8\xf8', FFFD*2), # 2 start bytes
(b'\xf8\x80', FFFD*2), # only one continuation byte
(b'\xf8\x80\x41', FFFD*2 + 'A'), # 1 valid cb and 1 invalid
(b'\xf8\x80\x80\x80\x80', FFFD*5), # invalid 5 bytes seq with 5 bytes
# with invalid start byte of a 6-byte sequence (rfc2279)
(b'\xfc', FFFD), # only the start byte
(b'\xfc\xfc', FFFD*2), # 2 start bytes
(b'\xfc\x80\x80', FFFD*3), # only 2 continuation bytes
(b'\xfc\x80\x80\x80\x80\x80', FFFD*6), # 6 continuation bytes
# invalid start byte
(b'\xfe', FFFD),
(b'\xfe\x80\x80', FFFD*3),
# other sequences
(b'\xf1\x80\x41\x42\x43', '\ufffd\x41\x42\x43'),
(b'\xf1\x80\xff\x42\x43', '\ufffd\ufffd\x42\x43'),
(b'\xf1\x80\xc2\x81\x43', '\ufffd\x81\x43'),
(b'\x61\xF1\x80\x80\xE1\x80\xC2\x62\x80\x63\x80\xBF\x64',
'\x61\uFFFD\uFFFD\uFFFD\x62\uFFFD\x63\uFFFD\uFFFD\x64'),
]
for n, (seq, res) in enumerate(sequences):
self.assertRaises(UnicodeDecodeError, seq.decode, 'utf-8', 'strict')
self.assertEqual(seq.decode('utf-8', 'replace'), res)
self.assertEqual((seq+b'b').decode('utf-8', 'replace'), res+'b')
self.assertEqual(seq.decode('utf-8', 'ignore'),
res.replace('\uFFFD', ''))
def assertCorrectUTF8Decoding(self, seq, res, err):
"""
Check that an invalid UTF-8 sequence raises a UnicodeDecodeError when
'strict' is used, returns res when 'replace' is used, and that doesn't
return anything when 'ignore' is used.
"""
with self.assertRaises(UnicodeDecodeError) as cm:
seq.decode('utf-8')
exc = cm.exception
self.assertIn(err, str(exc))
self.assertEqual(seq.decode('utf-8', 'replace'), res)
self.assertEqual((b'aaaa' + seq + b'bbbb').decode('utf-8', 'replace'),
'aaaa' + res + 'bbbb')
res = res.replace('\ufffd', '')
self.assertEqual(seq.decode('utf-8', 'ignore'), res)
self.assertEqual((b'aaaa' + seq + b'bbbb').decode('utf-8', 'ignore'),
'aaaa' + res + 'bbbb')
def test_invalid_start_byte(self):
"""
Test that an 'invalid start byte' error is raised when the first byte
is not in the ASCII range or is not a valid start byte of a 2-, 3-, or
4-bytes sequence. The invalid start byte is replaced with a single
U+FFFD when errors='replace'.
E.g. <80> is a continuation byte and can appear only after a start byte.
"""
FFFD = '\ufffd'
for byte in b'\x80\xA0\x9F\xBF\xC0\xC1\xF5\xFF':
self.assertCorrectUTF8Decoding(bytes([byte]), '\ufffd',
'invalid start byte')
def test_unexpected_end_of_data(self):
"""
Test that an 'unexpected end of data' error is raised when the string
ends after a start byte of a 2-, 3-, or 4-bytes sequence without having
enough continuation bytes. The incomplete sequence is replaced with a
single U+FFFD when errors='replace'.
E.g. in the sequence <F3 80 80>, F3 is the start byte of a 4-bytes
sequence, but it's followed by only 2 valid continuation bytes and the
last continuation bytes is missing.
Note: the continuation bytes must be all valid, if one of them is
invalid another error will be raised.
"""
sequences = [
'C2', 'DF',
'E0 A0', 'E0 BF', 'E1 80', 'E1 BF', 'EC 80', 'EC BF',
'ED 80', 'ED 9F', 'EE 80', 'EE BF', 'EF 80', 'EF BF',
'F0 90', 'F0 BF', 'F0 90 80', 'F0 90 BF', 'F0 BF 80', 'F0 BF BF',
'F1 80', 'F1 BF', 'F1 80 80', 'F1 80 BF', 'F1 BF 80', 'F1 BF BF',
'F3 80', 'F3 BF', 'F3 80 80', 'F3 80 BF', 'F3 BF 80', 'F3 BF BF',
'F4 80', 'F4 8F', 'F4 80 80', 'F4 80 BF', 'F4 8F 80', 'F4 8F BF'
]
FFFD = '\ufffd'
for seq in sequences:
2016-12-21 06:59:28 -04:00
self.assertCorrectUTF8Decoding(bytes.fromhex(seq), '\ufffd',
'unexpected end of data')
def test_invalid_cb_for_2bytes_seq(self):
"""
Test that an 'invalid continuation byte' error is raised when the
continuation byte of a 2-bytes sequence is invalid. The start byte
is replaced by a single U+FFFD and the second byte is handled
separately when errors='replace'.
E.g. in the sequence <C2 41>, C2 is the start byte of a 2-bytes
sequence, but 41 is not a valid continuation byte because it's the
ASCII letter 'A'.
"""
FFFD = '\ufffd'
FFFDx2 = FFFD * 2
sequences = [
('C2 00', FFFD+'\x00'), ('C2 7F', FFFD+'\x7f'),
('C2 C0', FFFDx2), ('C2 FF', FFFDx2),
('DF 00', FFFD+'\x00'), ('DF 7F', FFFD+'\x7f'),
('DF C0', FFFDx2), ('DF FF', FFFDx2),
]
for seq, res in sequences:
2016-12-21 06:59:28 -04:00
self.assertCorrectUTF8Decoding(bytes.fromhex(seq), res,
'invalid continuation byte')
def test_invalid_cb_for_3bytes_seq(self):
"""
Test that an 'invalid continuation byte' error is raised when the
continuation byte(s) of a 3-bytes sequence are invalid. When
errors='replace', if the first continuation byte is valid, the first
two bytes (start byte + 1st cb) are replaced by a single U+FFFD and the
third byte is handled separately, otherwise only the start byte is
replaced with a U+FFFD and the other continuation bytes are handled
separately.
E.g. in the sequence <E1 80 41>, E1 is the start byte of a 3-bytes
sequence, 80 is a valid continuation byte, but 41 is not a valid cb
because it's the ASCII letter 'A'.
Note: when the start byte is E0 or ED, the valid ranges for the first
continuation byte are limited to A0..BF and 80..9F respectively.
Python 2 used to consider all the bytes in range 80..BF valid when the
start byte was ED. This is fixed in Python 3.
"""
FFFD = '\ufffd'
FFFDx2 = FFFD * 2
sequences = [
('E0 00', FFFD+'\x00'), ('E0 7F', FFFD+'\x7f'), ('E0 80', FFFDx2),
('E0 9F', FFFDx2), ('E0 C0', FFFDx2), ('E0 FF', FFFDx2),
('E0 A0 00', FFFD+'\x00'), ('E0 A0 7F', FFFD+'\x7f'),
('E0 A0 C0', FFFDx2), ('E0 A0 FF', FFFDx2),
('E0 BF 00', FFFD+'\x00'), ('E0 BF 7F', FFFD+'\x7f'),
('E0 BF C0', FFFDx2), ('E0 BF FF', FFFDx2), ('E1 00', FFFD+'\x00'),
('E1 7F', FFFD+'\x7f'), ('E1 C0', FFFDx2), ('E1 FF', FFFDx2),
('E1 80 00', FFFD+'\x00'), ('E1 80 7F', FFFD+'\x7f'),
('E1 80 C0', FFFDx2), ('E1 80 FF', FFFDx2),
('E1 BF 00', FFFD+'\x00'), ('E1 BF 7F', FFFD+'\x7f'),
('E1 BF C0', FFFDx2), ('E1 BF FF', FFFDx2), ('EC 00', FFFD+'\x00'),
('EC 7F', FFFD+'\x7f'), ('EC C0', FFFDx2), ('EC FF', FFFDx2),
('EC 80 00', FFFD+'\x00'), ('EC 80 7F', FFFD+'\x7f'),
('EC 80 C0', FFFDx2), ('EC 80 FF', FFFDx2),
('EC BF 00', FFFD+'\x00'), ('EC BF 7F', FFFD+'\x7f'),
('EC BF C0', FFFDx2), ('EC BF FF', FFFDx2), ('ED 00', FFFD+'\x00'),
('ED 7F', FFFD+'\x7f'),
('ED A0', FFFDx2), ('ED BF', FFFDx2), # see note ^
('ED C0', FFFDx2), ('ED FF', FFFDx2), ('ED 80 00', FFFD+'\x00'),
('ED 80 7F', FFFD+'\x7f'), ('ED 80 C0', FFFDx2),
('ED 80 FF', FFFDx2), ('ED 9F 00', FFFD+'\x00'),
('ED 9F 7F', FFFD+'\x7f'), ('ED 9F C0', FFFDx2),
('ED 9F FF', FFFDx2), ('EE 00', FFFD+'\x00'),
('EE 7F', FFFD+'\x7f'), ('EE C0', FFFDx2), ('EE FF', FFFDx2),
('EE 80 00', FFFD+'\x00'), ('EE 80 7F', FFFD+'\x7f'),
('EE 80 C0', FFFDx2), ('EE 80 FF', FFFDx2),
('EE BF 00', FFFD+'\x00'), ('EE BF 7F', FFFD+'\x7f'),
('EE BF C0', FFFDx2), ('EE BF FF', FFFDx2), ('EF 00', FFFD+'\x00'),
('EF 7F', FFFD+'\x7f'), ('EF C0', FFFDx2), ('EF FF', FFFDx2),
('EF 80 00', FFFD+'\x00'), ('EF 80 7F', FFFD+'\x7f'),
('EF 80 C0', FFFDx2), ('EF 80 FF', FFFDx2),
('EF BF 00', FFFD+'\x00'), ('EF BF 7F', FFFD+'\x7f'),
('EF BF C0', FFFDx2), ('EF BF FF', FFFDx2),
]
for seq, res in sequences:
2016-12-21 06:59:28 -04:00
self.assertCorrectUTF8Decoding(bytes.fromhex(seq), res,
'invalid continuation byte')
def test_invalid_cb_for_4bytes_seq(self):
"""
Test that an 'invalid continuation byte' error is raised when the
continuation byte(s) of a 4-bytes sequence are invalid. When
errors='replace',the start byte and all the following valid
continuation bytes are replaced with a single U+FFFD, and all the bytes
starting from the first invalid continuation bytes (included) are
handled separately.
E.g. in the sequence <E1 80 41>, E1 is the start byte of a 3-bytes
sequence, 80 is a valid continuation byte, but 41 is not a valid cb
because it's the ASCII letter 'A'.
Note: when the start byte is E0 or ED, the valid ranges for the first
continuation byte are limited to A0..BF and 80..9F respectively.
However, when the start byte is ED, Python 2 considers all the bytes
in range 80..BF valid. This is fixed in Python 3.
"""
FFFD = '\ufffd'
FFFDx2 = FFFD * 2
sequences = [
('F0 00', FFFD+'\x00'), ('F0 7F', FFFD+'\x7f'), ('F0 80', FFFDx2),
('F0 8F', FFFDx2), ('F0 C0', FFFDx2), ('F0 FF', FFFDx2),
('F0 90 00', FFFD+'\x00'), ('F0 90 7F', FFFD+'\x7f'),
('F0 90 C0', FFFDx2), ('F0 90 FF', FFFDx2),
('F0 BF 00', FFFD+'\x00'), ('F0 BF 7F', FFFD+'\x7f'),
('F0 BF C0', FFFDx2), ('F0 BF FF', FFFDx2),
('F0 90 80 00', FFFD+'\x00'), ('F0 90 80 7F', FFFD+'\x7f'),
('F0 90 80 C0', FFFDx2), ('F0 90 80 FF', FFFDx2),
('F0 90 BF 00', FFFD+'\x00'), ('F0 90 BF 7F', FFFD+'\x7f'),
('F0 90 BF C0', FFFDx2), ('F0 90 BF FF', FFFDx2),
('F0 BF 80 00', FFFD+'\x00'), ('F0 BF 80 7F', FFFD+'\x7f'),
('F0 BF 80 C0', FFFDx2), ('F0 BF 80 FF', FFFDx2),
('F0 BF BF 00', FFFD+'\x00'), ('F0 BF BF 7F', FFFD+'\x7f'),
('F0 BF BF C0', FFFDx2), ('F0 BF BF FF', FFFDx2),
('F1 00', FFFD+'\x00'), ('F1 7F', FFFD+'\x7f'), ('F1 C0', FFFDx2),
('F1 FF', FFFDx2), ('F1 80 00', FFFD+'\x00'),
('F1 80 7F', FFFD+'\x7f'), ('F1 80 C0', FFFDx2),
('F1 80 FF', FFFDx2), ('F1 BF 00', FFFD+'\x00'),
('F1 BF 7F', FFFD+'\x7f'), ('F1 BF C0', FFFDx2),
('F1 BF FF', FFFDx2), ('F1 80 80 00', FFFD+'\x00'),
('F1 80 80 7F', FFFD+'\x7f'), ('F1 80 80 C0', FFFDx2),
('F1 80 80 FF', FFFDx2), ('F1 80 BF 00', FFFD+'\x00'),
('F1 80 BF 7F', FFFD+'\x7f'), ('F1 80 BF C0', FFFDx2),
('F1 80 BF FF', FFFDx2), ('F1 BF 80 00', FFFD+'\x00'),
('F1 BF 80 7F', FFFD+'\x7f'), ('F1 BF 80 C0', FFFDx2),
('F1 BF 80 FF', FFFDx2), ('F1 BF BF 00', FFFD+'\x00'),
('F1 BF BF 7F', FFFD+'\x7f'), ('F1 BF BF C0', FFFDx2),
('F1 BF BF FF', FFFDx2), ('F3 00', FFFD+'\x00'),
('F3 7F', FFFD+'\x7f'), ('F3 C0', FFFDx2), ('F3 FF', FFFDx2),
('F3 80 00', FFFD+'\x00'), ('F3 80 7F', FFFD+'\x7f'),
('F3 80 C0', FFFDx2), ('F3 80 FF', FFFDx2),
('F3 BF 00', FFFD+'\x00'), ('F3 BF 7F', FFFD+'\x7f'),
('F3 BF C0', FFFDx2), ('F3 BF FF', FFFDx2),
('F3 80 80 00', FFFD+'\x00'), ('F3 80 80 7F', FFFD+'\x7f'),
('F3 80 80 C0', FFFDx2), ('F3 80 80 FF', FFFDx2),
('F3 80 BF 00', FFFD+'\x00'), ('F3 80 BF 7F', FFFD+'\x7f'),
('F3 80 BF C0', FFFDx2), ('F3 80 BF FF', FFFDx2),
('F3 BF 80 00', FFFD+'\x00'), ('F3 BF 80 7F', FFFD+'\x7f'),
('F3 BF 80 C0', FFFDx2), ('F3 BF 80 FF', FFFDx2),
('F3 BF BF 00', FFFD+'\x00'), ('F3 BF BF 7F', FFFD+'\x7f'),
('F3 BF BF C0', FFFDx2), ('F3 BF BF FF', FFFDx2),
('F4 00', FFFD+'\x00'), ('F4 7F', FFFD+'\x7f'), ('F4 90', FFFDx2),
('F4 BF', FFFDx2), ('F4 C0', FFFDx2), ('F4 FF', FFFDx2),
('F4 80 00', FFFD+'\x00'), ('F4 80 7F', FFFD+'\x7f'),
('F4 80 C0', FFFDx2), ('F4 80 FF', FFFDx2),
('F4 8F 00', FFFD+'\x00'), ('F4 8F 7F', FFFD+'\x7f'),
('F4 8F C0', FFFDx2), ('F4 8F FF', FFFDx2),
('F4 80 80 00', FFFD+'\x00'), ('F4 80 80 7F', FFFD+'\x7f'),
('F4 80 80 C0', FFFDx2), ('F4 80 80 FF', FFFDx2),
('F4 80 BF 00', FFFD+'\x00'), ('F4 80 BF 7F', FFFD+'\x7f'),
('F4 80 BF C0', FFFDx2), ('F4 80 BF FF', FFFDx2),
('F4 8F 80 00', FFFD+'\x00'), ('F4 8F 80 7F', FFFD+'\x7f'),
('F4 8F 80 C0', FFFDx2), ('F4 8F 80 FF', FFFDx2),
('F4 8F BF 00', FFFD+'\x00'), ('F4 8F BF 7F', FFFD+'\x7f'),
('F4 8F BF C0', FFFDx2), ('F4 8F BF FF', FFFDx2)
]
for seq, res in sequences:
2016-12-21 06:59:28 -04:00
self.assertCorrectUTF8Decoding(bytes.fromhex(seq), res,
'invalid continuation byte')
def test_codecs_idna(self):
# Test whether trailing dot is preserved
self.assertEqual("www.python.org.".encode("idna"), b"www.python.org.")
def test_codecs_errors(self):
# Error handling (encoding)
self.assertRaises(UnicodeError, 'Andr\202 x'.encode, 'ascii')
self.assertRaises(UnicodeError, 'Andr\202 x'.encode, 'ascii','strict')
self.assertEqual('Andr\202 x'.encode('ascii','ignore'), b"Andr x")
self.assertEqual('Andr\202 x'.encode('ascii','replace'), b"Andr? x")
self.assertEqual('Andr\202 x'.encode('ascii', 'replace'),
'Andr\202 x'.encode('ascii', errors='replace'))
self.assertEqual('Andr\202 x'.encode('ascii', 'ignore'),
'Andr\202 x'.encode(encoding='ascii', errors='ignore'))
# Error handling (decoding)
self.assertRaises(UnicodeError, str, b'Andr\202 x', 'ascii')
self.assertRaises(UnicodeError, str, b'Andr\202 x', 'ascii', 'strict')
self.assertEqual(str(b'Andr\202 x', 'ascii', 'ignore'), "Andr x")
self.assertEqual(str(b'Andr\202 x', 'ascii', 'replace'), 'Andr\uFFFD x')
self.assertEqual(str(b'\202 x', 'ascii', 'replace'), '\uFFFD x')
# Error handling (unknown character names)
self.assertEqual(b"\\N{foo}xx".decode("unicode-escape", "ignore"), "xx")
# Error handling (truncated escape sequence)
self.assertRaises(UnicodeError, b"\\".decode, "unicode-escape")
self.assertRaises(TypeError, b"hello".decode, "test.unicode1")
self.assertRaises(TypeError, str, b"hello", "test.unicode2")
self.assertRaises(TypeError, "hello".encode, "test.unicode1")
self.assertRaises(TypeError, "hello".encode, "test.unicode2")
# Error handling (wrong arguments)
self.assertRaises(TypeError, "hello".encode, 42, 42, 42)
# Error handling (lone surrogate in
# _PyUnicode_TransformDecimalAndSpaceToASCII())
self.assertRaises(ValueError, int, "\ud800")
self.assertRaises(ValueError, int, "\udf00")
self.assertRaises(ValueError, float, "\ud800")
self.assertRaises(ValueError, float, "\udf00")
self.assertRaises(ValueError, complex, "\ud800")
self.assertRaises(ValueError, complex, "\udf00")
def test_codecs(self):
# Encoding
self.assertEqual('hello'.encode('ascii'), b'hello')
self.assertEqual('hello'.encode('utf-7'), b'hello')
self.assertEqual('hello'.encode('utf-8'), b'hello')
self.assertEqual('hello'.encode('utf-8'), b'hello')
self.assertEqual('hello'.encode('utf-16-le'), b'h\000e\000l\000l\000o\000')
self.assertEqual('hello'.encode('utf-16-be'), b'\000h\000e\000l\000l\000o')
self.assertEqual('hello'.encode('latin-1'), b'hello')
# Default encoding is utf-8
self.assertEqual('\u2603'.encode(), b'\xe2\x98\x83')
# Roundtrip safety for BMP (just the first 1024 chars)
Merged revisions 55007-55179 via svnmerge from svn+ssh://pythondev@svn.python.org/python/branches/p3yk ........ r55077 | guido.van.rossum | 2007-05-02 11:54:37 -0700 (Wed, 02 May 2007) | 2 lines Use the new print syntax, at least. ........ r55142 | fred.drake | 2007-05-04 21:27:30 -0700 (Fri, 04 May 2007) | 1 line remove old cruftiness ........ r55143 | fred.drake | 2007-05-04 21:52:16 -0700 (Fri, 04 May 2007) | 1 line make this work with the new Python ........ r55162 | neal.norwitz | 2007-05-06 22:29:18 -0700 (Sun, 06 May 2007) | 1 line Get asdl code gen working with Python 2.3. Should continue to work with 3.0 ........ r55164 | neal.norwitz | 2007-05-07 00:00:38 -0700 (Mon, 07 May 2007) | 1 line Verify checkins to p3yk (sic) branch go to 3000 list. ........ r55166 | neal.norwitz | 2007-05-07 00:12:35 -0700 (Mon, 07 May 2007) | 1 line Fix this test so it runs again by importing warnings_test properly. ........ r55167 | neal.norwitz | 2007-05-07 01:03:22 -0700 (Mon, 07 May 2007) | 8 lines So long xrange. range() now supports values that are outside -sys.maxint to sys.maxint. floats raise a TypeError. This has been sitting for a long time. It probably has some problems and needs cleanup. Objects/rangeobject.c now uses 4-space indents since it is almost completely new. ........ r55171 | guido.van.rossum | 2007-05-07 10:21:26 -0700 (Mon, 07 May 2007) | 4 lines Fix two tests that were previously depending on significant spaces at the end of a line (and before that on Python 2.x print behavior that has no exact equivalent in 3.0). ........
2007-05-07 19:24:25 -03:00
for c in range(1024):
u = chr(c)
for encoding in ('utf-7', 'utf-8', 'utf-16', 'utf-16-le',
'utf-16-be', 'raw_unicode_escape',
'unicode_escape'):
self.assertEqual(str(u.encode(encoding),encoding), u)
# Roundtrip safety for BMP (just the first 256 chars)
Merged revisions 55007-55179 via svnmerge from svn+ssh://pythondev@svn.python.org/python/branches/p3yk ........ r55077 | guido.van.rossum | 2007-05-02 11:54:37 -0700 (Wed, 02 May 2007) | 2 lines Use the new print syntax, at least. ........ r55142 | fred.drake | 2007-05-04 21:27:30 -0700 (Fri, 04 May 2007) | 1 line remove old cruftiness ........ r55143 | fred.drake | 2007-05-04 21:52:16 -0700 (Fri, 04 May 2007) | 1 line make this work with the new Python ........ r55162 | neal.norwitz | 2007-05-06 22:29:18 -0700 (Sun, 06 May 2007) | 1 line Get asdl code gen working with Python 2.3. Should continue to work with 3.0 ........ r55164 | neal.norwitz | 2007-05-07 00:00:38 -0700 (Mon, 07 May 2007) | 1 line Verify checkins to p3yk (sic) branch go to 3000 list. ........ r55166 | neal.norwitz | 2007-05-07 00:12:35 -0700 (Mon, 07 May 2007) | 1 line Fix this test so it runs again by importing warnings_test properly. ........ r55167 | neal.norwitz | 2007-05-07 01:03:22 -0700 (Mon, 07 May 2007) | 8 lines So long xrange. range() now supports values that are outside -sys.maxint to sys.maxint. floats raise a TypeError. This has been sitting for a long time. It probably has some problems and needs cleanup. Objects/rangeobject.c now uses 4-space indents since it is almost completely new. ........ r55171 | guido.van.rossum | 2007-05-07 10:21:26 -0700 (Mon, 07 May 2007) | 4 lines Fix two tests that were previously depending on significant spaces at the end of a line (and before that on Python 2.x print behavior that has no exact equivalent in 3.0). ........
2007-05-07 19:24:25 -03:00
for c in range(256):
u = chr(c)
for encoding in ('latin-1',):
self.assertEqual(str(u.encode(encoding),encoding), u)
# Roundtrip safety for BMP (just the first 128 chars)
Merged revisions 55007-55179 via svnmerge from svn+ssh://pythondev@svn.python.org/python/branches/p3yk ........ r55077 | guido.van.rossum | 2007-05-02 11:54:37 -0700 (Wed, 02 May 2007) | 2 lines Use the new print syntax, at least. ........ r55142 | fred.drake | 2007-05-04 21:27:30 -0700 (Fri, 04 May 2007) | 1 line remove old cruftiness ........ r55143 | fred.drake | 2007-05-04 21:52:16 -0700 (Fri, 04 May 2007) | 1 line make this work with the new Python ........ r55162 | neal.norwitz | 2007-05-06 22:29:18 -0700 (Sun, 06 May 2007) | 1 line Get asdl code gen working with Python 2.3. Should continue to work with 3.0 ........ r55164 | neal.norwitz | 2007-05-07 00:00:38 -0700 (Mon, 07 May 2007) | 1 line Verify checkins to p3yk (sic) branch go to 3000 list. ........ r55166 | neal.norwitz | 2007-05-07 00:12:35 -0700 (Mon, 07 May 2007) | 1 line Fix this test so it runs again by importing warnings_test properly. ........ r55167 | neal.norwitz | 2007-05-07 01:03:22 -0700 (Mon, 07 May 2007) | 8 lines So long xrange. range() now supports values that are outside -sys.maxint to sys.maxint. floats raise a TypeError. This has been sitting for a long time. It probably has some problems and needs cleanup. Objects/rangeobject.c now uses 4-space indents since it is almost completely new. ........ r55171 | guido.van.rossum | 2007-05-07 10:21:26 -0700 (Mon, 07 May 2007) | 4 lines Fix two tests that were previously depending on significant spaces at the end of a line (and before that on Python 2.x print behavior that has no exact equivalent in 3.0). ........
2007-05-07 19:24:25 -03:00
for c in range(128):
u = chr(c)
for encoding in ('ascii',):
self.assertEqual(str(u.encode(encoding),encoding), u)
# Roundtrip safety for non-BMP (just a few chars)
with warnings.catch_warnings():
u = '\U00010001\U00020002\U00030003\U00040004\U00050005'
for encoding in ('utf-8', 'utf-16', 'utf-16-le', 'utf-16-be',
'raw_unicode_escape', 'unicode_escape'):
self.assertEqual(str(u.encode(encoding),encoding), u)
2011-11-11 08:35:44 -04:00
# UTF-8 must be roundtrip safe for all code points
# (except surrogates, which are forbidden).
u = ''.join(map(chr, list(range(0, 0xd800)) +
2011-11-11 11:00:46 -04:00
list(range(0xe000, 0x110000))))
for encoding in ('utf-8',):
self.assertEqual(str(u.encode(encoding),encoding), u)
def test_codecs_charmap(self):
# 0-127
Merged revisions 55007-55179 via svnmerge from svn+ssh://pythondev@svn.python.org/python/branches/p3yk ........ r55077 | guido.van.rossum | 2007-05-02 11:54:37 -0700 (Wed, 02 May 2007) | 2 lines Use the new print syntax, at least. ........ r55142 | fred.drake | 2007-05-04 21:27:30 -0700 (Fri, 04 May 2007) | 1 line remove old cruftiness ........ r55143 | fred.drake | 2007-05-04 21:52:16 -0700 (Fri, 04 May 2007) | 1 line make this work with the new Python ........ r55162 | neal.norwitz | 2007-05-06 22:29:18 -0700 (Sun, 06 May 2007) | 1 line Get asdl code gen working with Python 2.3. Should continue to work with 3.0 ........ r55164 | neal.norwitz | 2007-05-07 00:00:38 -0700 (Mon, 07 May 2007) | 1 line Verify checkins to p3yk (sic) branch go to 3000 list. ........ r55166 | neal.norwitz | 2007-05-07 00:12:35 -0700 (Mon, 07 May 2007) | 1 line Fix this test so it runs again by importing warnings_test properly. ........ r55167 | neal.norwitz | 2007-05-07 01:03:22 -0700 (Mon, 07 May 2007) | 8 lines So long xrange. range() now supports values that are outside -sys.maxint to sys.maxint. floats raise a TypeError. This has been sitting for a long time. It probably has some problems and needs cleanup. Objects/rangeobject.c now uses 4-space indents since it is almost completely new. ........ r55171 | guido.van.rossum | 2007-05-07 10:21:26 -0700 (Mon, 07 May 2007) | 4 lines Fix two tests that were previously depending on significant spaces at the end of a line (and before that on Python 2.x print behavior that has no exact equivalent in 3.0). ........
2007-05-07 19:24:25 -03:00
s = bytes(range(128))
for encoding in (
'cp037', 'cp1026', 'cp273',
'cp437', 'cp500', 'cp720', 'cp737', 'cp775', 'cp850',
'cp852', 'cp855', 'cp858', 'cp860', 'cp861', 'cp862',
'cp863', 'cp865', 'cp866', 'cp1125',
'iso8859_10', 'iso8859_13', 'iso8859_14', 'iso8859_15',
'iso8859_2', 'iso8859_3', 'iso8859_4', 'iso8859_5', 'iso8859_6',
'iso8859_7', 'iso8859_9',
'koi8_r', 'koi8_t', 'koi8_u', 'kz1048', 'latin_1',
'mac_cyrillic', 'mac_latin2',
'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255',
'cp1256', 'cp1257', 'cp1258',
'cp856', 'cp857', 'cp864', 'cp869', 'cp874',
'mac_greek', 'mac_iceland','mac_roman', 'mac_turkish',
'cp1006', 'iso8859_8',
### These have undefined mappings:
#'cp424',
### These fail the round-trip:
#'cp875'
):
self.assertEqual(str(s, encoding).encode(encoding), s)
# 128-255
Merged revisions 55007-55179 via svnmerge from svn+ssh://pythondev@svn.python.org/python/branches/p3yk ........ r55077 | guido.van.rossum | 2007-05-02 11:54:37 -0700 (Wed, 02 May 2007) | 2 lines Use the new print syntax, at least. ........ r55142 | fred.drake | 2007-05-04 21:27:30 -0700 (Fri, 04 May 2007) | 1 line remove old cruftiness ........ r55143 | fred.drake | 2007-05-04 21:52:16 -0700 (Fri, 04 May 2007) | 1 line make this work with the new Python ........ r55162 | neal.norwitz | 2007-05-06 22:29:18 -0700 (Sun, 06 May 2007) | 1 line Get asdl code gen working with Python 2.3. Should continue to work with 3.0 ........ r55164 | neal.norwitz | 2007-05-07 00:00:38 -0700 (Mon, 07 May 2007) | 1 line Verify checkins to p3yk (sic) branch go to 3000 list. ........ r55166 | neal.norwitz | 2007-05-07 00:12:35 -0700 (Mon, 07 May 2007) | 1 line Fix this test so it runs again by importing warnings_test properly. ........ r55167 | neal.norwitz | 2007-05-07 01:03:22 -0700 (Mon, 07 May 2007) | 8 lines So long xrange. range() now supports values that are outside -sys.maxint to sys.maxint. floats raise a TypeError. This has been sitting for a long time. It probably has some problems and needs cleanup. Objects/rangeobject.c now uses 4-space indents since it is almost completely new. ........ r55171 | guido.van.rossum | 2007-05-07 10:21:26 -0700 (Mon, 07 May 2007) | 4 lines Fix two tests that were previously depending on significant spaces at the end of a line (and before that on Python 2.x print behavior that has no exact equivalent in 3.0). ........
2007-05-07 19:24:25 -03:00
s = bytes(range(128, 256))
for encoding in (
'cp037', 'cp1026', 'cp273',
'cp437', 'cp500', 'cp720', 'cp737', 'cp775', 'cp850',
'cp852', 'cp855', 'cp858', 'cp860', 'cp861', 'cp862',
'cp863', 'cp865', 'cp866', 'cp1125',
'iso8859_10', 'iso8859_13', 'iso8859_14', 'iso8859_15',
'iso8859_2', 'iso8859_4', 'iso8859_5',
'iso8859_9', 'koi8_r', 'koi8_u', 'latin_1',
'mac_cyrillic', 'mac_latin2',
### These have undefined mappings:
#'cp1250', 'cp1251', 'cp1252', 'cp1253', 'cp1254', 'cp1255',
#'cp1256', 'cp1257', 'cp1258',
#'cp424', 'cp856', 'cp857', 'cp864', 'cp869', 'cp874',
#'iso8859_3', 'iso8859_6', 'iso8859_7', 'koi8_t', 'kz1048',
#'mac_greek', 'mac_iceland','mac_roman', 'mac_turkish',
### These fail the round-trip:
#'cp1006', 'cp875', 'iso8859_8',
):
self.assertEqual(str(s, encoding).encode(encoding), s)
def test_concatenation(self):
self.assertEqual(("abc" "def"), "abcdef")
self.assertEqual(("abc" "def"), "abcdef")
self.assertEqual(("abc" "def"), "abcdef")
self.assertEqual(("abc" "def" "ghi"), "abcdefghi")
self.assertEqual(("abc" "def" "ghi"), "abcdefghi")
def test_ucs4(self):
x = '\U00100000'
y = x.encode("raw-unicode-escape").decode("raw-unicode-escape")
self.assertEqual(x, y)
y = br'\U00100000'
x = y.decode("raw-unicode-escape").encode("raw-unicode-escape")
self.assertEqual(x, y)
y = br'\U00010000'
x = y.decode("raw-unicode-escape").encode("raw-unicode-escape")
self.assertEqual(x, y)
try:
br'\U11111111'.decode("raw-unicode-escape")
except UnicodeDecodeError as e:
self.assertEqual(e.start, 0)
self.assertEqual(e.end, 10)
else:
self.fail("Should have raised UnicodeDecodeError")
Merged revisions 61724-61725,61731-61735,61737,61739,61741,61743-61744,61753,61761,61765-61767,61769,61773,61776-61778,61780-61783,61788,61793,61796,61807,61813 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ................ r61724 | martin.v.loewis | 2008-03-22 01:01:12 +0100 (Sat, 22 Mar 2008) | 49 lines Merged revisions 61602-61723 via svnmerge from svn+ssh://pythondev@svn.python.org/sandbox/trunk/2to3/lib2to3 ........ r61626 | david.wolever | 2008-03-19 17:19:16 +0100 (Mi, 19 M?\195?\164r 2008) | 1 line Added fixer for implicit local imports. See #2414. ........ r61628 | david.wolever | 2008-03-19 17:57:43 +0100 (Mi, 19 M?\195?\164r 2008) | 1 line Added a class for tests which should not run if a particular import is found. ........ r61629 | collin.winter | 2008-03-19 17:58:19 +0100 (Mi, 19 M?\195?\164r 2008) | 1 line Two more relative import fixes in pgen2. ........ r61635 | david.wolever | 2008-03-19 20:16:03 +0100 (Mi, 19 M?\195?\164r 2008) | 1 line Fixed print fixer so it will do the Right Thing when it encounters __future__.print_function. 2to3 gets upset, though, so the tests have been commented out. ........ r61637 | david.wolever | 2008-03-19 21:37:17 +0100 (Mi, 19 M?\195?\164r 2008) | 3 lines Added a fixer for itertools imports (from itertools import imap, ifilterfalse --> from itertools import filterfalse) ........ r61645 | david.wolever | 2008-03-19 23:22:35 +0100 (Mi, 19 M?\195?\164r 2008) | 1 line SVN is happier when you add the files you create... -_-' ........ r61654 | david.wolever | 2008-03-20 01:09:56 +0100 (Do, 20 M?\195?\164r 2008) | 1 line Added an explicit sort order to fixers -- fixes problems like #2427 ........ r61664 | david.wolever | 2008-03-20 04:32:40 +0100 (Do, 20 M?\195?\164r 2008) | 3 lines Fixes #2428 -- comments are no longer eatten by __future__ fixer. ........ r61673 | david.wolever | 2008-03-20 17:22:40 +0100 (Do, 20 M?\195?\164r 2008) | 1 line Added 2to3 node pretty-printer ........ r61679 | david.wolever | 2008-03-20 20:50:42 +0100 (Do, 20 M?\195?\164r 2008) | 1 line Made node printing a little bit prettier ........ r61723 | martin.v.loewis | 2008-03-22 00:59:27 +0100 (Sa, 22 M?\195?\164r 2008) | 2 lines Fix whitespace. ........ ................ r61725 | martin.v.loewis | 2008-03-22 01:02:41 +0100 (Sat, 22 Mar 2008) | 2 lines Install lib2to3. ................ r61731 | facundo.batista | 2008-03-22 03:45:37 +0100 (Sat, 22 Mar 2008) | 4 lines Small fix that complicated the test actually when that test failed. ................ r61732 | alexandre.vassalotti | 2008-03-22 05:08:44 +0100 (Sat, 22 Mar 2008) | 2 lines Added warning for the removal of 'hotshot' in Py3k. ................ r61733 | georg.brandl | 2008-03-22 11:07:29 +0100 (Sat, 22 Mar 2008) | 4 lines #1918: document that weak references *to* an object are cleared before the object's __del__ is called, to ensure that the weak reference callback (if any) finds the object healthy. ................ r61734 | georg.brandl | 2008-03-22 11:56:23 +0100 (Sat, 22 Mar 2008) | 2 lines Activate the Sphinx doctest extension and convert howto/functional to use it. ................ r61735 | georg.brandl | 2008-03-22 11:58:38 +0100 (Sat, 22 Mar 2008) | 2 lines Allow giving source names on the cmdline. ................ r61737 | georg.brandl | 2008-03-22 12:00:48 +0100 (Sat, 22 Mar 2008) | 2 lines Fixup this HOWTO's doctest blocks so that they can be run with sphinx' doctest builder. ................ r61739 | georg.brandl | 2008-03-22 12:47:10 +0100 (Sat, 22 Mar 2008) | 2 lines Test decimal.rst doctests as far as possible with sphinx doctest. ................ r61741 | georg.brandl | 2008-03-22 13:04:26 +0100 (Sat, 22 Mar 2008) | 2 lines Make doctests in re docs usable with sphinx' doctest. ................ r61743 | georg.brandl | 2008-03-22 13:59:37 +0100 (Sat, 22 Mar 2008) | 2 lines Make more doctests in pprint docs testable. ................ r61744 | georg.brandl | 2008-03-22 14:07:06 +0100 (Sat, 22 Mar 2008) | 2 lines No need to specify explicit "doctest_block" anymore. ................ r61753 | georg.brandl | 2008-03-22 21:08:43 +0100 (Sat, 22 Mar 2008) | 2 lines Fix-up syntax problems. ................ r61761 | georg.brandl | 2008-03-22 22:06:20 +0100 (Sat, 22 Mar 2008) | 4 lines Make collections' doctests executable. (The <BLANKLINE>s will be stripped from presentation output.) ................ r61765 | georg.brandl | 2008-03-22 22:21:57 +0100 (Sat, 22 Mar 2008) | 2 lines Test doctests in datetime docs. ................ r61766 | georg.brandl | 2008-03-22 22:26:44 +0100 (Sat, 22 Mar 2008) | 2 lines Test doctests in operator docs. ................ r61767 | georg.brandl | 2008-03-22 22:38:33 +0100 (Sat, 22 Mar 2008) | 2 lines Enable doctests in functions.rst. Already found two errors :) ................ r61769 | georg.brandl | 2008-03-22 23:04:10 +0100 (Sat, 22 Mar 2008) | 3 lines Enable doctest running for several other documents. We have now over 640 doctests that are run with "make doctest". ................ r61773 | raymond.hettinger | 2008-03-23 01:55:46 +0100 (Sun, 23 Mar 2008) | 1 line Simplify demo code. ................ r61776 | neal.norwitz | 2008-03-23 04:43:33 +0100 (Sun, 23 Mar 2008) | 7 lines Try to make this test a little more robust and not fail with: timeout (10.0025) is more than 2 seconds more than expected (0.001) I'm assuming this problem is caused by DNS lookup. This change does a DNS lookup of the hostname before trying to connect, so the time is not included. ................ r61777 | neal.norwitz | 2008-03-23 05:08:30 +0100 (Sun, 23 Mar 2008) | 1 line Speed up the test by avoiding socket timeouts. ................ r61778 | neal.norwitz | 2008-03-23 05:43:09 +0100 (Sun, 23 Mar 2008) | 1 line Skip the epoll test if epoll() does not work ................ r61780 | neal.norwitz | 2008-03-23 06:47:20 +0100 (Sun, 23 Mar 2008) | 1 line Suppress failure (to avoid a flaky test) if we cannot connect to svn.python.org ................ r61781 | neal.norwitz | 2008-03-23 07:13:25 +0100 (Sun, 23 Mar 2008) | 4 lines Move itertools before future_builtins since the latter depends on the former. From a clean build importing future_builtins would fail since itertools wasn't built yet. ................ r61782 | neal.norwitz | 2008-03-23 07:16:04 +0100 (Sun, 23 Mar 2008) | 1 line Try to prevent the alarm going off early in tearDown ................ r61783 | neal.norwitz | 2008-03-23 07:19:57 +0100 (Sun, 23 Mar 2008) | 4 lines Remove compiler warnings (on Alpha at least) about using chars as array subscripts. Using chars are dangerous b/c they are signed on some platforms and unsigned on others. ................ r61788 | georg.brandl | 2008-03-23 09:05:30 +0100 (Sun, 23 Mar 2008) | 2 lines Make the doctests presentation-friendlier. ................ r61793 | amaury.forgeotdarc | 2008-03-23 10:55:29 +0100 (Sun, 23 Mar 2008) | 4 lines #1477: ur'\U0010FFFF' raised in narrow unicode builds. Corrected the raw-unicode-escape codec to use UTF-16 surrogates in this case, just like the unicode-escape codec. ................ r61796 | raymond.hettinger | 2008-03-23 14:32:32 +0100 (Sun, 23 Mar 2008) | 1 line Issue 1681432: Add triangular distribution the random module. ................ r61807 | raymond.hettinger | 2008-03-23 20:37:53 +0100 (Sun, 23 Mar 2008) | 4 lines Adopt Nick's suggestion for useful default arguments. Clean-up floating point issues by adding true division and float constants. ................ r61813 | gregory.p.smith | 2008-03-23 22:04:43 +0100 (Sun, 23 Mar 2008) | 6 lines Fix gzip to deal with CRC's being signed values in Python 2.x properly and to read 32bit values as unsigned to start with rather than applying signedness fixups allover the place afterwards. This hopefully fixes the test_tarfile failure on the alpha/tru64 buildbot. ................
2008-03-23 18:54:12 -03:00
def test_conversion(self):
# Make sure __str__() works properly
class ObjectToStr:
def __str__(self):
return "foo"
class StrSubclassToStr(str):
def __str__(self):
return "foo"
class StrSubclassToStrSubclass(str):
def __new__(cls, content=""):
return str.__new__(cls, 2*content)
def __str__(self):
return self
self.assertEqual(str(ObjectToStr()), "foo")
self.assertEqual(str(StrSubclassToStr("bar")), "foo")
s = str(StrSubclassToStrSubclass("foo"))
self.assertEqual(s, "foofoo")
self.assertIs(type(s), StrSubclassToStrSubclass)
s = StrSubclass(StrSubclassToStrSubclass("foo"))
self.assertEqual(s, "foofoo")
self.assertIs(type(s), StrSubclass)
def test_unicode_repr(self):
class s1:
def __repr__(self):
return '\\n'
self.assertEqual(repr(s1()), '\\n')
def test_printable_repr(self):
self.assertEqual(repr('\U00010000'), "'%c'" % (0x10000,)) # printable
self.assertEqual(repr('\U00014000'), "'\\U00014000'") # nonprintable
# This test only affects 32-bit platforms because expandtabs can only take
# an int as the max value, not a 64-bit C long. If expandtabs is changed
# to take a 64-bit long, this test should apply to all platforms.
@unittest.skipIf(sys.maxsize > (1 << 32) or struct.calcsize('P') != 4,
'only applies to 32-bit platforms')
Merged revisions 55817-55961 via svnmerge from svn+ssh://pythondev@svn.python.org/python/branches/p3yk ................ r55837 | guido.van.rossum | 2007-06-08 16:04:42 -0700 (Fri, 08 Jun 2007) | 2 lines PEP 3119 -- the abc module. ................ r55838 | guido.van.rossum | 2007-06-08 17:38:55 -0700 (Fri, 08 Jun 2007) | 2 lines Implement part of PEP 3119 -- One Trick Ponies. ................ r55847 | guido.van.rossum | 2007-06-09 08:28:06 -0700 (Sat, 09 Jun 2007) | 2 lines Different way to do one trick ponies, allowing registration (per PEP strawman). ................ r55849 | guido.van.rossum | 2007-06-09 18:06:38 -0700 (Sat, 09 Jun 2007) | 3 lines Make sure that the magic looking for __hash__ (etc.) doesn't apply to real subclasses of Hashable. ................ r55852 | guido.van.rossum | 2007-06-10 08:29:51 -0700 (Sun, 10 Jun 2007) | 2 lines Add some more examples, e.g. generators and dict views. ................ r55853 | guido.van.rossum | 2007-06-10 08:31:59 -0700 (Sun, 10 Jun 2007) | 2 lines keys() and items() *are* containers -- just values() isn't. ................ r55864 | georg.brandl | 2007-06-10 15:29:40 -0700 (Sun, 10 Jun 2007) | 2 lines PEP 3127: new octal literals, binary literals. ................ r55865 | georg.brandl | 2007-06-10 15:31:37 -0700 (Sun, 10 Jun 2007) | 2 lines Some octal literal fixes in Tools. ................ r55866 | georg.brandl | 2007-06-10 15:37:43 -0700 (Sun, 10 Jun 2007) | 2 lines Tokenizer changes for PEP 3127. ................ r55867 | georg.brandl | 2007-06-10 15:37:55 -0700 (Sun, 10 Jun 2007) | 2 lines Some docs for PEP 3127. ................ r55868 | georg.brandl | 2007-06-10 15:44:39 -0700 (Sun, 10 Jun 2007) | 2 lines Missed a place in intobject.c. Is that used anymore anyway? ................ r55871 | neal.norwitz | 2007-06-10 18:31:49 -0700 (Sun, 10 Jun 2007) | 182 lines Merged revisions 55729-55868 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r55731 | neal.norwitz | 2007-06-01 00:29:12 -0700 (Fri, 01 Jun 2007) | 7 lines SF 1668596/1720897: distutils now copies data files even if package_dir is empty. This needs to be backported. I'm too tired tonight. It would be great if someone backports this if the buildbots are ok with it. Otherwise, I will try to get to it tomorrow. ........ r55732 | georg.brandl | 2007-06-01 04:33:33 -0700 (Fri, 01 Jun 2007) | 2 lines Bug #1722484: remove docstrings again when running with -OO. ........ r55735 | georg.brandl | 2007-06-01 12:20:27 -0700 (Fri, 01 Jun 2007) | 2 lines Fix wrong issue number. ........ r55739 | brett.cannon | 2007-06-01 20:02:29 -0700 (Fri, 01 Jun 2007) | 3 lines Have configure raise an error when building on AtheOS. Code specific to AtheOS will be removed in Python 2.7. ........ r55746 | neal.norwitz | 2007-06-02 11:33:53 -0700 (Sat, 02 Jun 2007) | 1 line Update expected birthday of 2.6 ........ r55751 | neal.norwitz | 2007-06-03 13:32:50 -0700 (Sun, 03 Jun 2007) | 10 lines Backout the original 'fix' to 1721309 which had no effect. Different versions of Berkeley DB handle this differently. The comments and bug report should have the details. Memory is allocated in 4.4 (and presumably earlier), but not in 4.5. Thus 4.5 has the free error, but not earlier versions. Mostly update comments, plus make the free conditional. This fix was already applied to the 2.5 branch. ........ r55752 | brett.cannon | 2007-06-03 16:13:41 -0700 (Sun, 03 Jun 2007) | 6 lines Make _strptime.TimeRE().pattern() use ``\s+`` for matching whitespace instead of ``\s*``. This prevents patterns from "stealing" bits from other patterns in order to make a match work. Closes bug #1730389. Will be backported. ........ r55766 | hyeshik.chang | 2007-06-05 11:16:52 -0700 (Tue, 05 Jun 2007) | 4 lines Fix build on FreeBSD. Bluetooth HCI API in FreeBSD is quite different from Linux's. Just fix the build for now but the code doesn't support the complete capability of HCI on FreeBSD yet. ........ r55770 | hyeshik.chang | 2007-06-05 11:58:51 -0700 (Tue, 05 Jun 2007) | 4 lines Bug #1728403: Fix a bug that CJKCodecs StreamReader hangs when it reads a file that ends with incomplete sequence and sizehint argument for .read() is specified. ........ r55775 | hyeshik.chang | 2007-06-05 12:28:15 -0700 (Tue, 05 Jun 2007) | 2 lines Fix for Windows: close a temporary file before trying to delete it. ........ r55783 | guido.van.rossum | 2007-06-05 14:24:47 -0700 (Tue, 05 Jun 2007) | 2 lines Patch by Tim Delany (missing DECREF). SF #1731330. ........ r55785 | collin.winter | 2007-06-05 17:17:35 -0700 (Tue, 05 Jun 2007) | 3 lines Patch #1731049: make threading.py use a proper "raise" when checking internal state, rather than assert statements (which get stripped out by -O). ........ r55786 | facundo.batista | 2007-06-06 08:13:37 -0700 (Wed, 06 Jun 2007) | 4 lines FTP.ntransfercmd method now uses create_connection when passive, using the timeout received in connection time. ........ r55792 | facundo.batista | 2007-06-06 10:15:23 -0700 (Wed, 06 Jun 2007) | 7 lines Added an optional timeout parameter to function urllib2.urlopen, with tests in test_urllib2net.py (must have network resource enabled to execute them). Also modified test_urllib2.py because testing mock classes must take it into acount. Docs are also updated. ........ r55793 | thomas.heller | 2007-06-06 13:19:19 -0700 (Wed, 06 Jun 2007) | 1 line Build _ctypes and _ctypes_test in the ReleaseAMD64 configuration. ........ r55802 | georg.brandl | 2007-06-07 06:23:24 -0700 (Thu, 07 Jun 2007) | 3 lines Disallow function calls like foo(None=1). Backport from py3k rev. 55708 by Guido. ........ r55804 | georg.brandl | 2007-06-07 06:30:24 -0700 (Thu, 07 Jun 2007) | 2 lines Make reindent.py executable. ........ r55805 | georg.brandl | 2007-06-07 06:34:10 -0700 (Thu, 07 Jun 2007) | 2 lines Patch #1667860: Fix UnboundLocalError in urllib2. ........ r55821 | kristjan.jonsson | 2007-06-07 16:53:49 -0700 (Thu, 07 Jun 2007) | 1 line Fixing changes to getbuildinfo.c that broke linux builds ........ r55828 | thomas.heller | 2007-06-08 09:10:27 -0700 (Fri, 08 Jun 2007) | 1 line Make this test work with older Python releases where struct has no 't' format character. ........ r55829 | martin.v.loewis | 2007-06-08 10:29:20 -0700 (Fri, 08 Jun 2007) | 3 lines Bug #1733488: Fix compilation of bufferobject.c on AIX. Will backport to 2.5. ........ r55831 | thomas.heller | 2007-06-08 11:20:09 -0700 (Fri, 08 Jun 2007) | 2 lines [ 1715718 ] x64 clean compile patch for _ctypes, by Kristj?n Valur with small modifications. ........ r55832 | thomas.heller | 2007-06-08 12:01:06 -0700 (Fri, 08 Jun 2007) | 1 line Fix gcc warnings intruduced by passing Py_ssize_t to PyErr_Format calls. ........ r55833 | thomas.heller | 2007-06-08 12:08:31 -0700 (Fri, 08 Jun 2007) | 2 lines Fix wrong documentation, and correct the punktuation. Closes [1700455]. ........ r55834 | thomas.heller | 2007-06-08 12:14:23 -0700 (Fri, 08 Jun 2007) | 1 line Fix warnings by using proper function prototype. ........ r55839 | neal.norwitz | 2007-06-08 20:36:34 -0700 (Fri, 08 Jun 2007) | 7 lines Prevent expandtabs() on string and unicode objects from causing a segfault when a large width is passed on 32-bit platforms. Found by Google. It would be good for people to review this especially carefully and verify I don't have an off by one error and there is no other way to cause overflow. ........ r55841 | neal.norwitz | 2007-06-08 21:48:22 -0700 (Fri, 08 Jun 2007) | 1 line Use macro version of GET_SIZE to avoid Coverity warning (#150) about a possible error. ........ r55842 | martin.v.loewis | 2007-06-09 00:42:52 -0700 (Sat, 09 Jun 2007) | 3 lines Patch #1733960: Allow T_LONGLONG to accept ints. Will backport to 2.5. ........ r55843 | martin.v.loewis | 2007-06-09 00:58:05 -0700 (Sat, 09 Jun 2007) | 2 lines Fix Windows build. ........ r55845 | martin.v.loewis | 2007-06-09 03:10:26 -0700 (Sat, 09 Jun 2007) | 2 lines Provide LLONG_MAX for S390. ........ r55854 | thomas.heller | 2007-06-10 08:59:17 -0700 (Sun, 10 Jun 2007) | 4 lines First version of build scripts for Windows/AMD64 (no external components are built yet, and 'kill_python' is disabled). ........ r55855 | thomas.heller | 2007-06-10 10:55:51 -0700 (Sun, 10 Jun 2007) | 3 lines For now, disable the _bsddb, _sqlite3, _ssl, _testcapi, _tkinter modules in the ReleaseAMD64 configuration because they do not compile. ........ r55856 | thomas.heller | 2007-06-10 11:27:54 -0700 (Sun, 10 Jun 2007) | 1 line Need to set the environment variables, otherwise devenv.com is not found. ........ r55860 | thomas.heller | 2007-06-10 14:01:17 -0700 (Sun, 10 Jun 2007) | 1 line Revert commit 55855. ........ ................ r55880 | neal.norwitz | 2007-06-10 22:07:36 -0700 (Sun, 10 Jun 2007) | 5 lines Fix the refleak counter on test_collections. The ABC metaclass creates a registry which must be cleared on each run. Otherwise, there *seem* to be refleaks when there really aren't any. (The class is held within the registry even though it's no longer needed.) ................ r55884 | neal.norwitz | 2007-06-10 22:46:33 -0700 (Sun, 10 Jun 2007) | 1 line These tests have been removed, so they are no longer needed here ................ r55886 | georg.brandl | 2007-06-11 00:26:37 -0700 (Mon, 11 Jun 2007) | 3 lines Optimize access to True and False in the compiler (if True) and the peepholer (LOAD_NAME True). ................ r55905 | georg.brandl | 2007-06-11 10:02:26 -0700 (Mon, 11 Jun 2007) | 5 lines Remove __oct__ and __hex__ and use __index__ for converting non-ints before formatting in a base. Add a bin() builtin. ................ r55906 | georg.brandl | 2007-06-11 10:04:44 -0700 (Mon, 11 Jun 2007) | 2 lines int(x, 0) does not "guess". ................ r55907 | georg.brandl | 2007-06-11 10:05:47 -0700 (Mon, 11 Jun 2007) | 2 lines Add a comment to explain that nb_oct and nb_hex are nonfunctional. ................ r55908 | guido.van.rossum | 2007-06-11 10:49:18 -0700 (Mon, 11 Jun 2007) | 2 lines Get rid of unused imports and comment. ................ r55910 | guido.van.rossum | 2007-06-11 13:05:17 -0700 (Mon, 11 Jun 2007) | 2 lines _Abstract.__new__ now requires either no arguments or __init__ overridden. ................ r55911 | guido.van.rossum | 2007-06-11 13:07:49 -0700 (Mon, 11 Jun 2007) | 7 lines Move the collections ABCs to a separate file, _abcoll.py, in order to avoid needing to import _collections.so during the bootstrap (this will become apparent in the next submit of os.py). Add (plain and mutable) ABCs for Set, Mapping, Sequence. ................ r55912 | guido.van.rossum | 2007-06-11 13:09:31 -0700 (Mon, 11 Jun 2007) | 2 lines Rewrite the _Environ class to use the new collections ABCs. ................ r55913 | guido.van.rossum | 2007-06-11 13:59:45 -0700 (Mon, 11 Jun 2007) | 72 lines Merged revisions 55869-55912 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r55869 | neal.norwitz | 2007-06-10 17:42:11 -0700 (Sun, 10 Jun 2007) | 1 line Add Atul Varma for patch # 1667860 ........ r55870 | neal.norwitz | 2007-06-10 18:22:03 -0700 (Sun, 10 Jun 2007) | 1 line Ignore valgrind problems on Ubuntu from ld ........ r55872 | neal.norwitz | 2007-06-10 18:48:46 -0700 (Sun, 10 Jun 2007) | 2 lines Ignore config.status.lineno which seems new (new autoconf?) ........ r55873 | neal.norwitz | 2007-06-10 19:14:39 -0700 (Sun, 10 Jun 2007) | 1 line Prevent these tests from running on Win64 since they don\'t apply there either ........ r55874 | neal.norwitz | 2007-06-10 19:16:10 -0700 (Sun, 10 Jun 2007) | 5 lines Fix a bug when there was a newline in the string expandtabs was called on. This also catches another condition that can overflow. Will backport. ........ r55879 | neal.norwitz | 2007-06-10 21:52:37 -0700 (Sun, 10 Jun 2007) | 1 line Prevent hang if the port cannot be opened. ........ r55881 | neal.norwitz | 2007-06-10 22:28:45 -0700 (Sun, 10 Jun 2007) | 4 lines Add all of the distuils modules that don't seem to have explicit tests. :-( Move an import in mworkscompiler so that this module can be imported on any platform. Hopefully this works on all platforms. ........ r55882 | neal.norwitz | 2007-06-10 22:35:10 -0700 (Sun, 10 Jun 2007) | 4 lines SF #1734732, lower case the module names per PEP 8. Will backport. ........ r55885 | neal.norwitz | 2007-06-10 23:16:48 -0700 (Sun, 10 Jun 2007) | 4 lines Not sure why this only fails sometimes on Unix machines. Better to disable it and only import msvccompiler on Windows since that's the only place it can work anyways. ........ r55887 | neal.norwitz | 2007-06-11 00:29:43 -0700 (Mon, 11 Jun 2007) | 4 lines Bug #1734723: Fix repr.Repr() so it doesn't ignore the maxtuple attribute. Will backport ........ r55889 | neal.norwitz | 2007-06-11 00:36:24 -0700 (Mon, 11 Jun 2007) | 1 line Reflow long line ........ r55896 | thomas.heller | 2007-06-11 08:58:33 -0700 (Mon, 11 Jun 2007) | 3 lines Use "O&" in calls to PyArg_Parse when we need a 'void*' instead of "k" or "K" codes. ........ r55901 | facundo.batista | 2007-06-11 09:27:08 -0700 (Mon, 11 Jun 2007) | 5 lines Added versionchanged flag to all the methods which received a new optional timeout parameter, and a versionadded flag to the socket.create_connection function. ........ ................ r55914 | guido.van.rossum | 2007-06-11 14:19:50 -0700 (Mon, 11 Jun 2007) | 3 lines New super() implementation, for PEP 3135 (though the PEP is not yet updated to this design, and small tweaks may still be made later). ................ r55923 | guido.van.rossum | 2007-06-11 21:15:24 -0700 (Mon, 11 Jun 2007) | 4 lines I'm guessing this module broke when Neal ripped out the types module -- it used 'list' both as a local variable and as the built-in list type. Renamed the local variable since that was easier. ................ r55924 | guido.van.rossum | 2007-06-11 21:20:05 -0700 (Mon, 11 Jun 2007) | 5 lines Change all occurrences of super(<thisclass>, <firstarg>) to super(). Seems to have worked, all the tests still pass. Exception: test_descr and test_descrtut, which have tons of these and are there to test the various usages. ................ r55939 | collin.winter | 2007-06-12 13:57:33 -0700 (Tue, 12 Jun 2007) | 1 line Patch #1735485: remove StandardError from the exception hierarchy. ................ r55954 | neal.norwitz | 2007-06-12 21:56:32 -0700 (Tue, 12 Jun 2007) | 51 lines Merged revisions 55913-55950 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r55926 | marc-andre.lemburg | 2007-06-12 02:09:58 -0700 (Tue, 12 Jun 2007) | 3 lines Apply patch #1734945 to support TurboLinux as distribution. ........ r55927 | marc-andre.lemburg | 2007-06-12 02:26:49 -0700 (Tue, 12 Jun 2007) | 3 lines Add patch #1726668: Windows Vista support. ........ r55929 | thomas.heller | 2007-06-12 08:36:22 -0700 (Tue, 12 Jun 2007) | 1 line Checkout, but do not yet try to build, exernal sources. ........ r55930 | thomas.heller | 2007-06-12 09:08:27 -0700 (Tue, 12 Jun 2007) | 6 lines Add bufferoverflowU.lib to the libraries needed by _ssl (is this the right thing to do?). Set the /XP64 /RETAIL build enviroment in the makefile when building ReleaseAMD64. ........ r55931 | thomas.heller | 2007-06-12 09:23:19 -0700 (Tue, 12 Jun 2007) | 5 lines Revert this change, since it breaks the win32 build: Add bufferoverflowU.lib to the libraries needed by _ssl (is this the right thing to do?). ........ r55934 | thomas.heller | 2007-06-12 10:28:31 -0700 (Tue, 12 Jun 2007) | 3 lines Specify the bufferoverflowU.lib to the makefile on the command line (for ReleaseAMD64 builds). ........ r55937 | thomas.heller | 2007-06-12 12:02:59 -0700 (Tue, 12 Jun 2007) | 3 lines Add bufferoverflowU.lib to PCBuild\_bsddb.vcproj. Build sqlite3.dll and bsddb. ........ r55938 | thomas.heller | 2007-06-12 12:56:12 -0700 (Tue, 12 Jun 2007) | 2 lines Don't rebuild Berkeley DB if not needed (this was committed by accident). ........ r55948 | martin.v.loewis | 2007-06-12 20:42:19 -0700 (Tue, 12 Jun 2007) | 3 lines Provide PY_LLONG_MAX on all systems having long long. Will backport to 2.5. ........ ................ r55959 | guido.van.rossum | 2007-06-13 09:22:41 -0700 (Wed, 13 Jun 2007) | 2 lines Fix a compilation warning. ................
2007-06-13 15:07:49 -03:00
def test_expandtabs_overflows_gracefully(self):
self.assertRaises(OverflowError, 't\tt\t'.expandtabs, sys.maxsize)
@support.cpython_only
def test_expandtabs_optimization(self):
s = 'abc'
self.assertIs(s.expandtabs(), s)
def test_raiseMemError(self):
asciifields = "nnb"
compactfields = asciifields + "nP"
ascii_struct_size = support.calcobjsize(asciifields)
compact_struct_size = support.calcobjsize(compactfields)
2011-09-28 02:41:54 -03:00
for char in ('a', '\xe9', '\u20ac', '\U0010ffff'):
code = ord(char)
if code < 0x80:
2011-09-28 02:41:54 -03:00
char_size = 1 # sizeof(Py_UCS1)
struct_size = ascii_struct_size
elif code < 0x100:
char_size = 1 # sizeof(Py_UCS1)
struct_size = compact_struct_size
2011-09-28 02:41:54 -03:00
elif code < 0x10000:
char_size = 2 # sizeof(Py_UCS2)
struct_size = compact_struct_size
else:
char_size = 4 # sizeof(Py_UCS4)
struct_size = compact_struct_size
# Note: sys.maxsize is half of the actual max allocation because of
# the signedness of Py_ssize_t. Strings of maxlen-1 should in principle
# be allocatable, given enough memory.
maxlen = ((sys.maxsize - struct_size) // char_size)
2011-09-28 02:41:54 -03:00
alloc = lambda: char * maxlen
with self.subTest(
char=char,
struct_size=struct_size,
char_size=char_size
):
# self-check
self.assertEqual(
sys.getsizeof(char * 42),
struct_size + (char_size * (42 + 1))
)
self.assertRaises(MemoryError, alloc)
self.assertRaises(MemoryError, alloc)
def test_format_subclass(self):
class S(str):
def __str__(self):
return '__str__ overridden'
s = S('xxx')
self.assertEqual("%s" % s, '__str__ overridden')
self.assertEqual("{}".format(s), '__str__ overridden')
def test_subclass_add(self):
class S(str):
def __add__(self, o):
return "3"
self.assertEqual(S("4") + S("5"), "3")
class S(str):
def __iadd__(self, o):
return "3"
s = S("1")
s += "4"
self.assertEqual(s, "3")
def test_getnewargs(self):
text = 'abc'
args = text.__getnewargs__()
self.assertIsNot(args[0], text)
self.assertEqual(args[0], text)
self.assertEqual(len(args), 1)
@support.cpython_only
@support.requires_legacy_unicode_capi
@unittest.skipIf(_testcapi is None, 'need _testcapi module')
def test_resize(self):
for length in range(1, 100, 7):
# generate a fresh string (refcount=1)
text = 'a' * length + 'b'
# fill wstr internal field
with self.assertWarns(DeprecationWarning):
abc = _testcapi.getargs_u(text)
self.assertEqual(abc, text)
# resize text: wstr field must be cleared and then recomputed
text += 'c'
with self.assertWarns(DeprecationWarning):
abcdef = _testcapi.getargs_u(text)
self.assertNotEqual(abc, abcdef)
self.assertEqual(abcdef, text)
def test_compare(self):
# Issue #17615
N = 10
ascii = 'a' * N
ascii2 = 'z' * N
latin = '\x80' * N
latin2 = '\xff' * N
bmp = '\u0100' * N
bmp2 = '\uffff' * N
astral = '\U00100000' * N
astral2 = '\U0010ffff' * N
strings = (
ascii, ascii2,
latin, latin2,
bmp, bmp2,
astral, astral2)
for text1, text2 in itertools.combinations(strings, 2):
equal = (text1 is text2)
self.assertEqual(text1 == text2, equal)
self.assertEqual(text1 != text2, not equal)
if equal:
self.assertTrue(text1 <= text2)
self.assertTrue(text1 >= text2)
# text1 is text2: duplicate strings to skip the "str1 == str2"
# optimization in unicode_compare_eq() and really compare
# character per character
copy1 = duplicate_string(text1)
copy2 = duplicate_string(text2)
self.assertIsNot(copy1, copy2)
self.assertTrue(copy1 == copy2)
self.assertFalse(copy1 != copy2)
self.assertTrue(copy1 <= copy2)
self.assertTrue(copy2 >= copy2)
self.assertTrue(ascii < ascii2)
self.assertTrue(ascii < latin)
self.assertTrue(ascii < bmp)
self.assertTrue(ascii < astral)
self.assertFalse(ascii >= ascii2)
self.assertFalse(ascii >= latin)
self.assertFalse(ascii >= bmp)
self.assertFalse(ascii >= astral)
self.assertFalse(latin < ascii)
self.assertTrue(latin < latin2)
self.assertTrue(latin < bmp)
self.assertTrue(latin < astral)
self.assertTrue(latin >= ascii)
self.assertFalse(latin >= latin2)
self.assertFalse(latin >= bmp)
self.assertFalse(latin >= astral)
self.assertFalse(bmp < ascii)
self.assertFalse(bmp < latin)
self.assertTrue(bmp < bmp2)
self.assertTrue(bmp < astral)
self.assertTrue(bmp >= ascii)
self.assertTrue(bmp >= latin)
self.assertFalse(bmp >= bmp2)
self.assertFalse(bmp >= astral)
self.assertFalse(astral < ascii)
self.assertFalse(astral < latin)
self.assertFalse(astral < bmp2)
self.assertTrue(astral < astral2)
self.assertTrue(astral >= ascii)
self.assertTrue(astral >= latin)
self.assertTrue(astral >= bmp2)
self.assertFalse(astral >= astral2)
def test_free_after_iterating(self):
support.check_free_after_iterating(self, iter, str)
support.check_free_after_iterating(self, reversed, str)
def test_check_encoding_errors(self):
# bpo-37388: str(bytes) and str.decode() must check encoding and errors
# arguments in dev mode
encodings = ('ascii', 'utf8', 'latin1')
invalid = 'Boom, Shaka Laka, Boom!'
code = textwrap.dedent(f'''
import sys
encodings = {encodings!r}
for data in (b'', b'short string'):
try:
str(data, encoding={invalid!r})
except LookupError:
pass
else:
sys.exit(21)
try:
str(data, errors={invalid!r})
except LookupError:
pass
else:
sys.exit(22)
for encoding in encodings:
try:
str(data, encoding, errors={invalid!r})
except LookupError:
pass
else:
sys.exit(22)
for data in ('', 'short string'):
try:
data.encode(encoding={invalid!r})
except LookupError:
pass
else:
sys.exit(23)
try:
data.encode(errors={invalid!r})
except LookupError:
pass
else:
sys.exit(24)
for encoding in encodings:
try:
data.encode(encoding, errors={invalid!r})
except LookupError:
pass
else:
sys.exit(24)
sys.exit(10)
''')
proc = assert_python_failure('-X', 'dev', '-c', code)
self.assertEqual(proc.rc, 10, proc)
class StringModuleTest(unittest.TestCase):
def test_formatter_parser(self):
def parse(format):
return list(_string.formatter_parser(format))
formatter = parse("prefix {2!s}xxx{0:^+10.3f}{obj.attr!s} {z[0]!s:10}")
self.assertEqual(formatter, [
('prefix ', '2', '', 's'),
('xxx', '0', '^+10.3f', None),
('', 'obj.attr', '', 's'),
(' ', 'z[0]', '10', 's'),
])
formatter = parse("prefix {} suffix")
self.assertEqual(formatter, [
('prefix ', '', '', None),
(' suffix', None, None, None),
])
formatter = parse("str")
self.assertEqual(formatter, [
('str', None, None, None),
])
formatter = parse("")
self.assertEqual(formatter, [])
formatter = parse("{0}")
self.assertEqual(formatter, [
('', '0', '', None),
])
self.assertRaises(TypeError, _string.formatter_parser, 1)
def test_formatter_field_name_split(self):
def split(name):
items = list(_string.formatter_field_name_split(name))
items[1] = list(items[1])
return items
self.assertEqual(split("obj"), ["obj", []])
self.assertEqual(split("obj.arg"), ["obj", [(True, 'arg')]])
self.assertEqual(split("obj[key]"), ["obj", [(False, 'key')]])
self.assertEqual(split("obj.arg[key1][key2]"), [
"obj",
[(True, 'arg'),
(False, 'key1'),
(False, 'key2'),
]])
self.assertRaises(TypeError, _string.formatter_field_name_split, 1)
def test_str_subclass_attr(self):
name = StrSubclass("name")
name2 = StrSubclass("name2")
class Bag:
pass
o = Bag()
with self.assertRaises(AttributeError):
delattr(o, name)
setattr(o, name, 1)
self.assertEqual(o.name, 1)
o.name = 2
self.assertEqual(list(o.__dict__), [name])
with self.assertRaises(AttributeError):
delattr(o, name2)
with self.assertRaises(AttributeError):
del o.name2
setattr(o, name2, 3)
self.assertEqual(o.name2, 3)
o.name2 = 4
self.assertEqual(list(o.__dict__), [name, name2])
if __name__ == "__main__":
unittest.main()