Menu
▾
▴
[Jython-checkins] SF.net SVN: jython: [4892] branches/asm/Lib/test/string_tests.py
|
From: <pj...@us...> - 2008-07-11 20:10:35
|
Revision: 4892
http://jython.svn.sourceforge.net/jython/?rev=4892&view=rev
Author: pjenvey
Date: 2008-07-11 13:10:32 -0700 (Fri, 11 Jul 2008)
Log Message:
-----------
from:
http://svn.python.org/projects/python/branches/release25-maint/Lib/test/string_tests.py@55878
Modified Paths:
--------------
branches/asm/Lib/test/string_tests.py
Modified: branches/asm/Lib/test/string_tests.py
===================================================================
--- branches/asm/Lib/test/string_tests.py 2008-07-11 19:37:19 UTC (rev 4891)
+++ branches/asm/Lib/test/string_tests.py 2008-07-11 20:10:32 UTC (rev 4892)
@@ -2,7 +2,7 @@
Common tests shared by test_str, test_unicode, test_userstring and test_string.
"""
-import unittest, string, sys
+import unittest, string, sys, struct
from test import test_support
from UserList import UserList
@@ -80,6 +80,15 @@
args = self.fixtype(args)
getattr(object, methodname)(*args)
+ def test_hash(self):
+ # SF bug 1054139: += optimization was not invalidating cached hash value
+ a = self.type2test('DNSSEC')
+ b = self.type2test('')
+ for c in a:
+ b += c
+ hash(b)
+ self.assertEqual(hash(a), hash(b))
+
def test_capitalize(self):
self.checkequal(' hello ', ' hello ', 'capitalize')
self.checkequal('Hello ', 'Hello ','capitalize')
@@ -97,28 +106,97 @@
self.checkequal(3, 'aaa', 'count', 'a')
self.checkequal(0, 'aaa', 'count', 'b')
self.checkequal(0, 'aaa', 'count', 'b')
+ self.checkequal(2, 'aaa', 'count', 'a', 1)
+ self.checkequal(0, 'aaa', 'count', 'a', 10)
self.checkequal(1, 'aaa', 'count', 'a', -1)
self.checkequal(3, 'aaa', 'count', 'a', -10)
+ self.checkequal(1, 'aaa', 'count', 'a', 0, 1)
+ self.checkequal(3, 'aaa', 'count', 'a', 0, 10)
self.checkequal(2, 'aaa', 'count', 'a', 0, -1)
self.checkequal(0, 'aaa', 'count', 'a', 0, -10)
+ self.checkequal(3, 'aaa', 'count', '', 1)
+ self.checkequal(1, 'aaa', 'count', '', 3)
+ self.checkequal(0, 'aaa', 'count', '', 10)
+ self.checkequal(2, 'aaa', 'count', '', -1)
+ self.checkequal(4, 'aaa', 'count', '', -10)
self.checkraises(TypeError, 'hello', 'count')
self.checkraises(TypeError, 'hello', 'count', 42)
+ # For a variety of combinations,
+ # verify that str.count() matches an equivalent function
+ # replacing all occurrences and then differencing the string lengths
+ charset = ['', 'a', 'b']
+ digits = 7
+ base = len(charset)
+ teststrings = set()
+ for i in xrange(base ** digits):
+ entry = []
+ for j in xrange(digits):
+ i, m = divmod(i, base)
+ entry.append(charset[m])
+ teststrings.add(''.join(entry))
+ teststrings = list(teststrings)
+ for i in teststrings:
+ i = self.fixtype(i)
+ n = len(i)
+ for j in teststrings:
+ r1 = i.count(j)
+ if j:
+ r2, rem = divmod(n - len(i.replace(j, '')), len(j))
+ else:
+ r2, rem = len(i)+1, 0
+ if rem or r1 != r2:
+ self.assertEqual(rem, 0, '%s != 0 for %s' % (rem, i))
+ self.assertEqual(r1, r2, '%s != %s for %s' % (r1, r2, i))
+
def test_find(self):
self.checkequal(0, 'abcdefghiabc', 'find', 'abc')
self.checkequal(9, 'abcdefghiabc', 'find', 'abc', 1)
self.checkequal(-1, 'abcdefghiabc', 'find', 'def', 4)
+ self.checkequal(0, 'abc', 'find', '', 0)
+ self.checkequal(3, 'abc', 'find', '', 3)
+ self.checkequal(-1, 'abc', 'find', '', 4)
+
self.checkraises(TypeError, 'hello', 'find')
self.checkraises(TypeError, 'hello', 'find', 42)
+ # For a variety of combinations,
+ # verify that str.find() matches __contains__
+ # and that the found substring is really at that location
+ charset = ['', 'a', 'b', 'c']
+ digits = 5
+ base = len(charset)
+ teststrings = set()
+ for i in xrange(base ** digits):
+ entry = []
+ for j in xrange(digits):
+ i, m = divmod(i, base)
+ entry.append(charset[m])
+ teststrings.add(''.join(entry))
+ teststrings = list(teststrings)
+ for i in teststrings:
+ i = self.fixtype(i)
+ for j in teststrings:
+ loc = i.find(j)
+ r1 = (loc != -1)
+ r2 = j in i
+ if r1 != r2:
+ self.assertEqual(r1, r2)
+ if loc != -1:
+ self.assertEqual(i[loc:loc+len(j)], j)
+
def test_rfind(self):
self.checkequal(9, 'abcdefghiabc', 'rfind', 'abc')
self.checkequal(12, 'abcdefghiabc', 'rfind', '')
self.checkequal(0, 'abcdefghiabc', 'rfind', 'abcd')
self.checkequal(-1, 'abcdefghiabc', 'rfind', 'abcz')
+ self.checkequal(3, 'abc', 'rfind', '', 0)
+ self.checkequal(3, 'abc', 'rfind', '', 3)
+ self.checkequal(-1, 'abc', 'rfind', '', 4)
+
self.checkraises(TypeError, 'hello', 'rfind')
self.checkraises(TypeError, 'hello', 'rfind', 42)
@@ -169,26 +247,191 @@
self.checkequal('abc\rab def\ng hi', 'abc\rab\tdef\ng\thi', 'expandtabs')
self.checkequal('abc\rab def\ng hi', 'abc\rab\tdef\ng\thi', 'expandtabs', 8)
self.checkequal('abc\r\nab\r\ndef\ng\r\nhi', 'abc\r\nab\r\ndef\ng\r\nhi', 'expandtabs', 4)
+ self.checkequal(' a\n b', ' \ta\n\tb', 'expandtabs', 1)
self.checkraises(TypeError, 'hello', 'expandtabs', 42, 42)
+ # This test is only valid when sizeof(int) == sizeof(void*) == 4.
+ if sys.maxint < (1 << 32) and struct.calcsize('P') == 4:
+ self.checkraises(OverflowError,
+ '\ta\n\tb', 'expandtabs', sys.maxint)
def test_split(self):
self.checkequal(['this', 'is', 'the', 'split', 'function'],
'this is the split function', 'split')
- self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|')
- self.checkequal(['a', 'b', 'c|d'], 'a|b|c|d', 'split', '|', 2)
+
+ # by whitespace
+ self.checkequal(['a', 'b', 'c', 'd'], 'a b c d ', 'split')
self.checkequal(['a', 'b c d'], 'a b c d', 'split', None, 1)
self.checkequal(['a', 'b', 'c d'], 'a b c d', 'split', None, 2)
self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'split', None, 3)
self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'split', None, 4)
+ self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'split', None,
+ sys.maxint-1)
self.checkequal(['a b c d'], 'a b c d', 'split', None, 0)
+ self.checkequal(['a b c d'], ' a b c d', 'split', None, 0)
self.checkequal(['a', 'b', 'c d'], 'a b c d', 'split', None, 2)
- self.checkequal(['a', 'b', 'c', 'd'], 'a b c d ', 'split')
+
+ self.checkequal([], ' ', 'split')
+ self.checkequal(['a'], ' a ', 'split')
+ self.checkequal(['a', 'b'], ' a b ', 'split')
+ self.checkequal(['a', 'b '], ' a b ', 'split', None, 1)
+ self.checkequal(['a', 'b c '], ' a b c ', 'split', None, 1)
+ self.checkequal(['a', 'b', 'c '], ' a b c ', 'split', None, 2)
+ self.checkequal(['a', 'b'], '\n\ta \t\r b \v ', 'split')
+ aaa = ' a '*20
+ self.checkequal(['a']*20, aaa, 'split')
+ self.checkequal(['a'] + [aaa[4:]], aaa, 'split', None, 1)
+ self.checkequal(['a']*19 + ['a '], aaa, 'split', None, 19)
+
+ # by a char
+ self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|')
+ self.checkequal(['a|b|c|d'], 'a|b|c|d', 'split', '|', 0)
+ self.checkequal(['a', 'b|c|d'], 'a|b|c|d', 'split', '|', 1)
+ self.checkequal(['a', 'b', 'c|d'], 'a|b|c|d', 'split', '|', 2)
+ self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|', 3)
+ self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|', 4)
+ self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'split', '|',
+ sys.maxint-2)
+ self.checkequal(['a|b|c|d'], 'a|b|c|d', 'split', '|', 0)
+ self.checkequal(['a', '', 'b||c||d'], 'a||b||c||d', 'split', '|', 2)
+ self.checkequal(['endcase ', ''], 'endcase |', 'split', '|')
+ self.checkequal(['', ' startcase'], '| startcase', 'split', '|')
+ self.checkequal(['', 'bothcase', ''], '|bothcase|', 'split', '|')
+ self.checkequal(['a', '', 'b\x00c\x00d'], 'a\x00\x00b\x00c\x00d', 'split', '\x00', 2)
+
+ self.checkequal(['a']*20, ('a|'*20)[:-1], 'split', '|')
+ self.checkequal(['a']*15 +['a|a|a|a|a'],
+ ('a|'*20)[:-1], 'split', '|', 15)
+
+ # by string
self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//')
- #self.checkequal(['endcase ', ''], 'endcase test', 'split', 'test')
+ self.checkequal(['a', 'b//c//d'], 'a//b//c//d', 'split', '//', 1)
+ self.checkequal(['a', 'b', 'c//d'], 'a//b//c//d', 'split', '//', 2)
+ self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//', 3)
+ self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//', 4)
+ self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//',
+ sys.maxint-10)
+ self.checkequal(['a//b//c//d'], 'a//b//c//d', 'split', '//', 0)
+ self.checkequal(['a', '', 'b////c////d'], 'a////b////c////d', 'split', '//', 2)
+ self.checkequal(['endcase ', ''], 'endcase test', 'split', 'test')
+ self.checkequal(['', ' begincase'], 'test begincase', 'split', 'test')
+ self.checkequal(['', ' bothcase ', ''], 'test bothcase test',
+ 'split', 'test')
+ self.checkequal(['a', 'bc'], 'abbbc', 'split', 'bb')
+ self.checkequal(['', ''], 'aaa', 'split', 'aaa')
+ self.checkequal(['aaa'], 'aaa', 'split', 'aaa', 0)
+ self.checkequal(['ab', 'ab'], 'abbaab', 'split', 'ba')
+ self.checkequal(['aaaa'], 'aaaa', 'split', 'aab')
+ self.checkequal([''], '', 'split', 'aaa')
+ self.checkequal(['aa'], 'aa', 'split', 'aaa')
+ self.checkequal(['A', 'bobb'], 'Abbobbbobb', 'split', 'bbobb')
+ self.checkequal(['A', 'B', ''], 'AbbobbBbbobb', 'split', 'bbobb')
+ self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'split', 'BLAH')
+ self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'split', 'BLAH', 19)
+ self.checkequal(['a']*18 + ['aBLAHa'], ('aBLAH'*20)[:-4],
+ 'split', 'BLAH', 18)
+
+ # mixed use of str and unicode
+ self.checkequal([u'a', u'b', u'c d'], 'a b c d', 'split', u' ', 2)
+
+ # argument type
self.checkraises(TypeError, 'hello', 'split', 42, 42, 42)
+ # null case
+ self.checkraises(ValueError, 'hello', 'split', '')
+ self.checkraises(ValueError, 'hello', 'split', '', 0)
+
+ def test_rsplit(self):
+ self.checkequal(['this', 'is', 'the', 'rsplit', 'function'],
+ 'this is the rsplit function', 'rsplit')
+
+ # by whitespace
+ self.checkequal(['a', 'b', 'c', 'd'], 'a b c d ', 'rsplit')
+ self.checkequal(['a b c', 'd'], 'a b c d', 'rsplit', None, 1)
+ self.checkequal(['a b', 'c', 'd'], 'a b c d', 'rsplit', None, 2)
+ self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'rsplit', None, 3)
+ self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'rsplit', None, 4)
+ self.checkequal(['a', 'b', 'c', 'd'], 'a b c d', 'rsplit', None,
+ sys.maxint-20)
+ self.checkequal(['a b c d'], 'a b c d', 'rsplit', None, 0)
+ self.checkequal(['a b c d'], 'a b c d ', 'rsplit', None, 0)
+ self.checkequal(['a b', 'c', 'd'], 'a b c d', 'rsplit', None, 2)
+
+ self.checkequal([], ' ', 'rsplit')
+ self.checkequal(['a'], ' a ', 'rsplit')
+ self.checkequal(['a', 'b'], ' a b ', 'rsplit')
+ self.checkequal([' a', 'b'], ' a b ', 'rsplit', None, 1)
+ self.checkequal([' a b','c'], ' a b c ', 'rsplit',
+ None, 1)
+ self.checkequal([' a', 'b', 'c'], ' a b c ', 'rsplit',
+ None, 2)
+ self.checkequal(['a', 'b'], '\n\ta \t\r b \v ', 'rsplit', None, 88)
+ aaa = ' a '*20
+ self.checkequal(['a']*20, aaa, 'rsplit')
+ self.checkequal([aaa[:-4]] + ['a'], aaa, 'rsplit', None, 1)
+ self.checkequal([' a a'] + ['a']*18, aaa, 'rsplit', None, 18)
+
+
+ # by a char
+ self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|')
+ self.checkequal(['a|b|c', 'd'], 'a|b|c|d', 'rsplit', '|', 1)
+ self.checkequal(['a|b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 2)
+ self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 3)
+ self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 4)
+ self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|',
+ sys.maxint-100)
+ self.checkequal(['a|b|c|d'], 'a|b|c|d', 'rsplit', '|', 0)
+ self.checkequal(['a||b||c', '', 'd'], 'a||b||c||d', 'rsplit', '|', 2)
+ self.checkequal(['', ' begincase'], '| begincase', 'rsplit', '|')
+ self.checkequal(['endcase ', ''], 'endcase |', 'rsplit', '|')
+ self.checkequal(['', 'bothcase', ''], '|bothcase|', 'rsplit', '|')
+
+ self.checkequal(['a\x00\x00b', 'c', 'd'], 'a\x00\x00b\x00c\x00d', 'rsplit', '\x00', 2)
+
+ self.checkequal(['a']*20, ('a|'*20)[:-1], 'rsplit', '|')
+ self.checkequal(['a|a|a|a|a']+['a']*15,
+ ('a|'*20)[:-1], 'rsplit', '|', 15)
+
+ # by string
+ self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//')
+ self.checkequal(['a//b//c', 'd'], 'a//b//c//d', 'rsplit', '//', 1)
+ self.checkequal(['a//b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//', 2)
+ self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//', 3)
+ self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//', 4)
+ self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'rsplit', '//',
+ sys.maxint-5)
+ self.checkequal(['a//b//c//d'], 'a//b//c//d', 'rsplit', '//', 0)
+ self.checkequal(['a////b////c', '', 'd'], 'a////b////c////d', 'rsplit', '//', 2)
+ self.checkequal(['', ' begincase'], 'test begincase', 'rsplit', 'test')
+ self.checkequal(['endcase ', ''], 'endcase test', 'rsplit', 'test')
+ self.checkequal(['', ' bothcase ', ''], 'test bothcase test',
+ 'rsplit', 'test')
+ self.checkequal(['ab', 'c'], 'abbbc', 'rsplit', 'bb')
+ self.checkequal(['', ''], 'aaa', 'rsplit', 'aaa')
+ self.checkequal(['aaa'], 'aaa', 'rsplit', 'aaa', 0)
+ self.checkequal(['ab', 'ab'], 'abbaab', 'rsplit', 'ba')
+ self.checkequal(['aaaa'], 'aaaa', 'rsplit', 'aab')
+ self.checkequal([''], '', 'rsplit', 'aaa')
+ self.checkequal(['aa'], 'aa', 'rsplit', 'aaa')
+ self.checkequal(['bbob', 'A'], 'bbobbbobbA', 'rsplit', 'bbobb')
+ self.checkequal(['', 'B', 'A'], 'bbobbBbbobbA', 'rsplit', 'bbobb')
+
+ self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'rsplit', 'BLAH')
+ self.checkequal(['a']*20, ('aBLAH'*20)[:-4], 'rsplit', 'BLAH', 19)
+ self.checkequal(['aBLAHa'] + ['a']*18, ('aBLAH'*20)[:-4],
+ 'rsplit', 'BLAH', 18)
+
+ # mixed use of str and unicode
+ self.checkequal([u'a b', u'c', u'd'], 'a b c d', 'rsplit', u' ', 2)
+
+ # argument type
+ self.checkraises(TypeError, 'hello', 'rsplit', 42, 42, 42)
+
+ # null case
+ self.checkraises(ValueError, 'hello', 'rsplit', '')
+ self.checkraises(ValueError, 'hello', 'rsplit', '', 0)
+
def test_strip(self):
self.checkequal('hello', ' hello ', 'strip')
self.checkequal('hello ', ' hello ', 'lstrip')
@@ -227,7 +470,7 @@
self.checkequal('abc ', 'abc', 'ljust', 6)
self.checkequal('abc', 'abc', 'ljust', 3)
self.checkequal('abc', 'abc', 'ljust', 2)
-
+ self.checkequal('abc*******', 'abc', 'ljust', 10, '*')
self.checkraises(TypeError, 'abc', 'ljust')
def test_rjust(self):
@@ -235,7 +478,7 @@
self.checkequal(' abc', 'abc', 'rjust', 6)
self.checkequal('abc', 'abc', 'rjust', 3)
self.checkequal('abc', 'abc', 'rjust', 2)
-
+ self.checkequal('*******abc', 'abc', 'rjust', 10, '*')
self.checkraises(TypeError, 'abc', 'rjust')
def test_center(self):
@@ -243,7 +486,7 @@
self.checkequal(' abc ', 'abc', 'center', 6)
self.checkequal('abc', 'abc', 'center', 3)
self.checkequal('abc', 'abc', 'center', 2)
-
+ self.checkequal('***abc****', 'abc', 'center', 10, '*')
self.checkraises(TypeError, 'abc', 'center')
def test_swapcase(self):
@@ -252,6 +495,158 @@
self.checkraises(TypeError, 'hello', 'swapcase', 42)
def test_replace(self):
+ EQ = self.checkequal
+
+ # Operations on the empty string
+ EQ("", "", "replace", "", "")
+ EQ("A", "", "replace", "", "A")
+ EQ("", "", "replace", "A", "")
+ EQ("", "", "replace", "A", "A")
+ EQ("", "", "replace", "", "", 100)
+ EQ("", "", "replace", "", "", sys.maxint)
+
+ # interleave (from=="", 'to' gets inserted everywhere)
+ EQ("A", "A", "replace", "", "")
+ EQ("*A*", "A", "replace", "", "*")
+ EQ("*1A*1", "A", "replace", "", "*1")
+ EQ("*-#A*-#", "A", "replace", "", "*-#")
+ EQ("*-A*-A*-", "AA", "replace", "", "*-")
+ EQ("*-A*-A*-", "AA", "replace", "", "*-", -1)
+ EQ("*-A*-A*-", "AA", "replace", "", "*-", sys.maxint)
+ EQ("*-A*-A*-", "AA", "replace", "", "*-", 4)
+ EQ("*-A*-A*-", "AA", "replace", "", "*-", 3)
+ EQ("*-A*-A", "AA", "replace", "", "*-", 2)
+ EQ("*-AA", "AA", "replace", "", "*-", 1)
+ EQ("AA", "AA", "replace", "", "*-", 0)
+
+ # single character deletion (from=="A", to=="")
+ EQ("", "A", "replace", "A", "")
+ EQ("", "AAA", "replace", "A", "")
+ EQ("", "AAA", "replace", "A", "", -1)
+ EQ("", "AAA", "replace", "A", "", sys.maxint)
+ EQ("", "AAA", "replace", "A", "", 4)
+ EQ("", "AAA", "replace", "A", "", 3)
+ EQ("A", "AAA", "replace", "A", "", 2)
+ EQ("AA", "AAA", "replace", "A", "", 1)
+ EQ("AAA", "AAA", "replace", "A", "", 0)
+ EQ("", "AAAAAAAAAA", "replace", "A", "")
+ EQ("BCD", "ABACADA", "replace", "A", "")
+ EQ("BCD", "ABACADA", "replace", "A", "", -1)
+ EQ("BCD", "ABACADA", "replace", "A", "", sys.maxint)
+ EQ("BCD", "ABACADA", "replace", "A", "", 5)
+ EQ("BCD", "ABACADA", "replace", "A", "", 4)
+ EQ("BCDA", "ABACADA", "replace", "A", "", 3)
+ EQ("BCADA", "ABACADA", "replace", "A", "", 2)
+ EQ("BACADA", "ABACADA", "replace", "A", "", 1)
+ EQ("ABACADA", "ABACADA", "replace", "A", "", 0)
+ EQ("BCD", "ABCAD", "replace", "A", "")
+ EQ("BCD", "ABCADAA", "replace", "A", "")
+ EQ("BCD", "BCD", "replace", "A", "")
+ EQ("*************", "*************", "replace", "A", "")
+ EQ("^A^", "^"+"A"*1000+"^", "replace", "A", "", 999)
+
+ # substring deletion (from=="the", to=="")
+ EQ("", "the", "replace", "the", "")
+ EQ("ater", "theater", "replace", "the", "")
+ EQ("", "thethe", "replace", "the", "")
+ EQ("", "thethethethe", "replace", "the", "")
+ EQ("aaaa", "theatheatheathea", "replace", "the", "")
+ EQ("that", "that", "replace", "the", "")
+ EQ("thaet", "thaet", "replace", "the", "")
+ EQ("here and re", "here and there", "replace", "the", "")
+ EQ("here and re and re", "here and there and there",
+ "replace", "the", "", sys.maxint)
+ EQ("here and re and re", "here and there and there",
+ "replace", "the", "", -1)
+ EQ("here and re and re", "here and there and there",
+ "replace", "the", "", 3)
+ EQ("here and re and re", "here and there and there",
+ "replace", "the", "", 2)
+ EQ("here and re and there", "here and there and there",
+ "replace", "the", "", 1)
+ EQ("here and there and there", "here and there and there",
+ "replace", "the", "", 0)
+ EQ("here and re and re", "here and there and there", "replace", "the", "")
+
+ EQ("abc", "abc", "replace", "the", "")
+ EQ("abcdefg", "abcdefg", "replace", "the", "")
+
+ # substring deletion (from=="bob", to=="")
+ EQ("bob", "bbobob", "replace", "bob", "")
+ EQ("bobXbob", "bbobobXbbobob", "replace", "bob", "")
+ EQ("aaaaaaa", "aaaaaaabob", "replace", "bob", "")
+ EQ("aaaaaaa", "aaaaaaa", "replace", "bob", "")
+
+ # single character replace in place (len(from)==len(to)==1)
+ EQ("Who goes there?", "Who goes there?", "replace", "o", "o")
+ EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O")
+ EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", sys.maxint)
+ EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", -1)
+ EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", 3)
+ EQ("WhO gOes there?", "Who goes there?", "replace", "o", "O", 2)
+ EQ("WhO goes there?", "Who goes there?", "replace", "o", "O", 1)
+ EQ("Who goes there?", "Who goes there?", "replace", "o", "O", 0)
+
+ EQ("Who goes there?", "Who goes there?", "replace", "a", "q")
+ EQ("who goes there?", "Who goes there?", "replace", "W", "w")
+ EQ("wwho goes there?ww", "WWho goes there?WW", "replace", "W", "w")
+ EQ("Who goes there!", "Who goes there?", "replace", "?", "!")
+ EQ("Who goes there!!", "Who goes there??", "replace", "?", "!")
+
+ EQ("Who goes there?", "Who goes there?", "replace", ".", "!")
+
+ # substring replace in place (len(from)==len(to) > 1)
+ EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**")
+ EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", sys.maxint)
+ EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", -1)
+ EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", 4)
+ EQ("Th** ** a t**sue", "This is a tissue", "replace", "is", "**", 3)
+ EQ("Th** ** a tissue", "This is a tissue", "replace", "is", "**", 2)
+ EQ("Th** is a tissue", "This is a tissue", "replace", "is", "**", 1)
+ EQ("This is a tissue", "This is a tissue", "replace", "is", "**", 0)
+ EQ("cobob", "bobob", "replace", "bob", "cob")
+ EQ("cobobXcobocob", "bobobXbobobob", "replace", "bob", "cob")
+ EQ("bobob", "bobob", "replace", "bot", "bot")
+
+ # replace single character (len(from)==1, len(to)>1)
+ EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK")
+ EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK", -1)
+ EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK", sys.maxint)
+ EQ("ReyKKjaviKK", "Reykjavik", "replace", "k", "KK", 2)
+ EQ("ReyKKjavik", "Reykjavik", "replace", "k", "KK", 1)
+ EQ("Reykjavik", "Reykjavik", "replace", "k", "KK", 0)
+ EQ("A----B----C----", "A.B.C.", "replace", ".", "----")
+
+ EQ("Reykjavik", "Reykjavik", "replace", "q", "KK")
+
+ # replace substring (len(from)>1, len(to)!=len(from))
+ EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
+ "replace", "spam", "ham")
+ EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
+ "replace", "spam", "ham", sys.maxint)
+ EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
+ "replace", "spam", "ham", -1)
+ EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
+ "replace", "spam", "ham", 4)
+ EQ("ham, ham, eggs and ham", "spam, spam, eggs and spam",
+ "replace", "spam", "ham", 3)
+ EQ("ham, ham, eggs and spam", "spam, spam, eggs and spam",
+ "replace", "spam", "ham", 2)
+ EQ("ham, spam, eggs and spam", "spam, spam, eggs and spam",
+ "replace", "spam", "ham", 1)
+ EQ("spam, spam, eggs and spam", "spam, spam, eggs and spam",
+ "replace", "spam", "ham", 0)
+
+ EQ("bobob", "bobobob", "replace", "bobob", "bob")
+ EQ("bobobXbobob", "bobobobXbobobob", "replace", "bobob", "bob")
+ EQ("BOBOBOB", "BOBOBOB", "replace", "bob", "bobby")
+
+ ba = buffer('a')
+ bb = buffer('b')
+ EQ("bbc", "abc", "replace", ba, bb)
+ EQ("aac", "abc", "replace", bb, ba)
+
+ #
self.checkequal('one@two!three!', 'one!two!three!', 'replace', '!', '@', 1)
self.checkequal('onetwothree', 'one!two!three!', 'replace', '!', '')
self.checkequal('one@two@three!', 'one!two!three!', 'replace', '!', '@', 2)
@@ -279,6 +674,15 @@
self.checkraises(TypeError, 'hello', 'replace', 42, 'h')
self.checkraises(TypeError, 'hello', 'replace', 'h', 42)
+ def test_replace_overflow(self):
+ # Check for overflow checking on 32 bit machines
+ if sys.maxint != 2147483647 or struct.calcsize("P") > 4:
+ return
+ A2_16 = "A" * (2**16)
+ self.checkraises(OverflowError, A2_16, "replace", "", A2_16)
+ self.checkraises(OverflowError, A2_16, "replace", "A", A2_16)
+ self.checkraises(OverflowError, A2_16, "replace", "AA", A2_16+A2_16)
+
def test_zfill(self):
self.checkequal('123', '123', 'zfill', 2)
self.checkequal('123', '123', 'zfill', 3)
@@ -425,6 +829,21 @@
self.checkraises(TypeError, 'hello', 'startswith')
self.checkraises(TypeError, 'hello', 'startswith', 42)
+ # test tuple arguments
+ self.checkequal(True, 'hello', 'startswith', ('he', 'ha'))
+ self.checkequal(False, 'hello', 'startswith', ('lo', 'llo'))
+ self.checkequal(True, 'hello', 'startswith', ('hellox', 'hello'))
+ self.checkequal(False, 'hello', 'startswith', ())
+ self.checkequal(True, 'helloworld', 'startswith', ('hellowo',
+ 'rld', 'lowo'), 3)
+ self.checkequal(False, 'helloworld', 'startswith', ('hellowo', 'ello',
+ 'rld'), 3)
+ self.checkequal(True, 'hello', 'startswith', ('lo', 'he'), 0, -1)
+ self.checkequal(False, 'hello', 'startswith', ('he', 'hel'), 0, 1)
+ self.checkequal(True, 'hello', 'startswith', ('he', 'hel'), 0, 2)
+
+ self.checkraises(TypeError, 'hello', 'startswith', (42,))
+
def test_endswith(self):
self.checkequal(True, 'hello', 'endswith', 'lo')
self.checkequal(False, 'hello', 'endswith', 'he')
@@ -459,6 +878,21 @@
self.checkraises(TypeError, 'hello', 'endswith')
self.checkraises(TypeError, 'hello', 'endswith', 42)
+ # test tuple arguments
+ self.checkequal(False, 'hello', 'endswith', ('he', 'ha'))
+ self.checkequal(True, 'hello', 'endswith', ('lo', 'llo'))
+ self.checkequal(True, 'hello', 'endswith', ('hellox', 'hello'))
+ self.checkequal(False, 'hello', 'endswith', ())
+ self.checkequal(True, 'helloworld', 'endswith', ('hellowo',
+ 'rld', 'lowo'), 3)
+ self.checkequal(False, 'helloworld', 'endswith', ('hellowo', 'ello',
+ 'rld'), 3, -1)
+ self.checkequal(True, 'hello', 'endswith', ('hell', 'ell'), 0, -1)
+ self.checkequal(False, 'hello', 'endswith', ('he', 'hel'), 0, 1)
+ self.checkequal(True, 'hello', 'endswith', ('he', 'hell'), 0, 4)
+
+ self.checkraises(TypeError, 'hello', 'endswith', (42,))
+
def test___contains__(self):
self.checkequal(True, '', '__contains__', '') # vereq('' in '', True)
self.checkequal(True, 'abc', '__contains__', '') # vereq('' in 'abc', True)
@@ -478,7 +912,7 @@
self.checkequal(u'abc', 'abc', '__getitem__', slice(0, 1000))
self.checkequal(u'a', 'abc', '__getitem__', slice(0, 1))
self.checkequal(u'', 'abc', '__getitem__', slice(0, 0))
- # FIXME What about negative indizes? This is handled differently by [] and __getitem__(slice)
+ # FIXME What about negative indices? This is handled differently by [] and __getitem__(slice)
self.checkraises(TypeError, 'abc', '__getitem__', 'def')
@@ -502,13 +936,10 @@
self.checkequal('abc', 'abc', '__mul__', 1)
self.checkequal('abcabcabc', 'abc', '__mul__', 3)
self.checkraises(TypeError, 'abc', '__mul__')
- # CPython specific; pypy tests via the operator module instead
- if not test_support.is_jython:
- self.checkraises(TypeError, 'abc', '__mul__', '')
- else:
- import operator
- self.checkraises(TypeError, operator, '__mul__', 'abc', '')
- self.checkraises(OverflowError, 10000*'abc', '__mul__', 2000000000)
+ self.checkraises(TypeError, 'abc', '__mul__', '')
+ # XXX: on a 64-bit system, this doesn't raise an overflow error,
+ # but either raises a MemoryError, or succeeds (if you have 54TiB)
+ #self.checkraises(OverflowError, 10000*'abc', '__mul__', 2000000000)
def test_join(self):
# join now works with any sequence type
@@ -517,6 +948,8 @@
# test.test_string.StringTest.test_join)
self.checkequal('a b c d', ' ', 'join', ['a', 'b', 'c', 'd'])
self.checkequal('abcd', '', 'join', ('a', 'b', 'c', 'd'))
+ self.checkequal('bd', '', 'join', ('', 'b', '', 'd'))
+ self.checkequal('ac', '', 'join', ('a', '', 'c', ''))
self.checkequal('w x y z', ' ', 'join', Sequence())
self.checkequal('abc', 'a', 'join', ('abc',))
self.checkequal('z', 'a', 'join', UserList(['z']))
@@ -538,6 +971,15 @@
self.checkraises(TypeError, ' ', 'join')
self.checkraises(TypeError, ' ', 'join', 7)
self.checkraises(TypeError, ' ', 'join', Sequence([7, 'hello', 123L]))
+ try:
+ def f():
+ yield 4 + ""
+ self.fixtype(' ').join(f())
+ except TypeError, e:
+ if '+' not in str(e):
+ self.fail('join() ate exception message')
+ else:
+ self.fail('exception not raised')
def test_formatting(self):
self.checkequal('+hello+', '+%s+', '__mod__', 'hello')
@@ -585,12 +1027,32 @@
# unicodeobject.c uses a 120 byte buffer and switches from
# 'f' formatting to 'g' at precision 50, so we expect
# OverflowErrors for the ranges x < 50 and prec >= 67.
- if not test_support.is_jython and x < 50 and prec >= 67:
+ if x < 50 and prec >= 67:
self.checkraises(OverflowError, format, "__mod__", value)
else:
self.checkcall(format, "__mod__", value)
+ def test_inplace_rewrites(self):
+ # Check that strings don't copy and modify cached single-character strings
+ self.checkequal('a', 'A', 'lower')
+ self.checkequal(True, 'A', 'isupper')
+ self.checkequal('A', 'a', 'upper')
+ self.checkequal(True, 'a', 'islower')
+
+ self.checkequal('a', 'A', 'replace', 'A', 'a')
+ self.checkequal(True, 'A', 'isupper')
+
+ self.checkequal('A', 'a', 'capitalize')
+ self.checkequal(True, 'a', 'islower')
+
+ self.checkequal('A', 'a', 'swapcase')
+ self.checkequal(True, 'a', 'islower')
+
+ self.checkequal('A', 'a', 'title')
+ self.checkequal(True, 'a', 'islower')
+
def test_partition(self):
+
self.checkequal(('this is the par', 'ti', 'tion method'),
'this is the partition method', 'partition', 'ti')
@@ -605,6 +1067,7 @@
self.checkraises(TypeError, S, 'partition', None)
def test_rpartition(self):
+
self.checkequal(('this is the rparti', 'ti', 'on method'),
'this is the rpartition method', 'rpartition', 'ti')
@@ -616,8 +1079,9 @@
self.checkequal(('http://www.python.', 'org', ''), S, 'rpartition', 'org')
self.checkraises(ValueError, S, 'rpartition', '')
- self.checkraises(TypeError, S, 'rpartition', None)
+ self.checkraises(TypeError, S, 'rpartition', None)
+
class MixinStrStringUserStringTest:
# Additional tests for 8bit strings, i.e. str, UserString and
# the string module
@@ -645,23 +1109,70 @@
# Additional tests that only work with
# 8bit compatible object, i.e. str and UserString
- def test_encoding_decoding(self):
- codecs = [('rot13', 'uryyb jbeyq'),
- ('base64', 'aGVsbG8gd29ybGQ=\n'),
- ('hex', '68656c6c6f20776f726c64'),
- ('uu', 'begin 666 <data>\n+:&5L;&\\@=V]R;&0 \n \nend\n')]
- for encoding, data in codecs:
- self.checkequal(data, 'hello world', 'encode', encoding)
- self.checkequal('hello world', data, 'decode', encoding)
- # zlib is optional, so we make the test optional too...
- try:
- import zlib
- except ImportError:
+ if test_support.have_unicode:
+ def test_encoding_decoding(self):
+ codecs = [('rot13', 'uryyb jbeyq'),
+ ('base64', 'aGVsbG8gd29ybGQ=\n'),
+ ('hex', '68656c6c6f20776f726c64'),
+ ('uu', 'begin 666 <data>\n+:&5L;&\\@=V]R;&0 \n \nend\n')]
+ for encoding, data in codecs:
+ self.checkequal(data, 'hello world', 'encode', encoding)
+ self.checkequal('hello world', data, 'decode', encoding)
+ # zlib is optional, so we make the test optional too...
+ try:
+ import zlib
+ except ImportError:
+ pass
+ else:
+ data = 'x\x9c\xcbH\xcd\xc9\xc9W(\xcf/\xcaI\x01\x00\x1a\x0b\x04]'
+ self.checkequal(data, 'hello world', 'encode', 'zlib')
+ self.checkequal('hello world', data, 'decode', 'zlib')
+
+ self.checkraises(TypeError, 'xyz', 'decode', 42)
+ self.checkraises(TypeError, 'xyz', 'encode', 42)
+
+
+class MixinStrUnicodeTest:
+ # Additional tests that only work with str and unicode.
+
+ def test_bug1001011(self):
+ # Make sure join returns a NEW object for single item sequences
+ # involving a subclass.
+ # Make sure that it is of the appropriate type.
+ # Check the optimisation still occurs for standard objects.
+ t = self.type2test
+ class subclass(t):
pass
+ s1 = subclass("abcd")
+ s2 = t().join([s1])
+ self.assert_(s1 is not s2)
+ self.assert_(type(s2) is t)
+
+ s1 = t("abcd")
+ s2 = t().join([s1])
+ self.assert_(s1 is s2)
+
+ # Should also test mixed-type join.
+ if t is unicode:
+ s1 = subclass("abcd")
+ s2 = "".join([s1])
+ self.assert_(s1 is not s2)
+ self.assert_(type(s2) is t)
+
+ s1 = t("abcd")
+ s2 = "".join([s1])
+ self.assert_(s1 is s2)
+
+ elif t is str:
+ s1 = subclass("abcd")
+ s2 = u"".join([s1])
+ self.assert_(s1 is not s2)
+ self.assert_(type(s2) is unicode) # promotes!
+
+ s1 = t("abcd")
+ s2 = u"".join([s1])
+ self.assert_(s1 is not s2)
+ self.assert_(type(s2) is unicode) # promotes!
+
else:
- data = 'x\x9c\xcbH\xcd\xc9\xc9W(\xcf/\xcaI\x01\x00\x1a\x0b\x04]'
- self.checkequal(data, 'hello world', 'encode', 'zlib')
- self.checkequal('hello world', data, 'decode', 'zlib')
-
- self.checkraises(TypeError, 'xyz', 'decode', 42)
- self.checkraises(TypeError, 'xyz', 'encode', 42)
+ self.fail("unexpected type for MixinStrUnicodeTest %r" % t)
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
