Kaydet (Commit) cfff15d2 authored tarafından Martin Panter's avatar Martin Panter

Issue #26712: Merge string_tests cleanup from 3.5

......@@ -368,6 +368,8 @@ class BaseTest:
sys.maxsize-2)
self.checkequal(['a|b|c|d'], 'a|b|c|d', 'split', '|', 0)
self.checkequal(['a', '', 'b||c||d'], 'a||b||c||d', 'split', '|', 2)
self.checkequal(['abcd'], 'abcd', 'split', '|')
self.checkequal([''], '', 'split', '|')
self.checkequal(['endcase ', ''], 'endcase |', 'split', '|')
self.checkequal(['', ' startcase'], '| startcase', 'split', '|')
self.checkequal(['', 'bothcase', ''], '|bothcase|', 'split', '|')
......@@ -435,6 +437,8 @@ class BaseTest:
sys.maxsize-100)
self.checkequal(['a|b|c|d'], 'a|b|c|d', 'rsplit', '|', 0)
self.checkequal(['a||b||c', '', 'd'], 'a||b||c||d', 'rsplit', '|', 2)
self.checkequal(['abcd'], 'abcd', 'rsplit', '|')
self.checkequal([''], '', 'rsplit', '|')
self.checkequal(['', ' begincase'], '| begincase', 'rsplit', '|')
self.checkequal(['endcase ', ''], 'endcase |', 'rsplit', '|')
self.checkequal(['', 'bothcase', ''], '|bothcase|', 'rsplit', '|')
......@@ -641,14 +645,6 @@ class BaseTest:
EQ("bobobXbobob", "bobobobXbobobob", "replace", "bobob", "bob")
EQ("BOBOBOB", "BOBOBOB", "replace", "bob", "bobby")
# XXX Commented out. Is there any reason to support buffer objects
# as arguments for str.replace()? GvR
## ba = bytearray('a')
## bb = bytearray('b')
## EQ("bbc", "abc", "replace", ba, bb)
## EQ("aac", "abc", "replace", bb, ba)
#
self.checkequal('one@two!three!', 'one!two!three!', 'replace', '!', '@', 1)
self.checkequal('onetwothree', 'one!two!three!', 'replace', '!', '')
self.checkequal('one@two@three!', 'one!two!three!', 'replace', '!', '@', 2)
......@@ -714,16 +710,21 @@ class BaseTest:
self.checkequal(['a'], ' a ', 'split')
self.checkequal(['a', 'b'], ' a b ', 'split')
self.checkequal(['a', 'b '], ' a b ', 'split', None, 1)
self.checkequal(['a b c '], ' a b c ', 'split', None, 0)
self.checkequal(['a', 'b c '], ' a b c ', 'split', None, 1)
self.checkequal(['a', 'b', 'c '], ' a b c ', 'split', None, 2)
self.checkequal(['a', 'b', 'c'], ' a b c ', 'split', None, 3)
self.checkequal(['a', 'b'], '\n\ta \t\r b \v ', 'split')
aaa = ' a '*20
self.checkequal(['a']*20, aaa, 'split')
self.checkequal(['a'] + [aaa[4:]], aaa, 'split', None, 1)
self.checkequal(['a']*19 + ['a '], aaa, 'split', None, 19)
# mixed use of str and unicode
self.checkequal(['a', 'b', 'c d'], 'a b c d', 'split', ' ', 2)
for b in ('arf\tbarf', 'arf\nbarf', 'arf\rbarf',
'arf\fbarf', 'arf\vbarf'):
self.checkequal(['arf', 'barf'], b, 'split')
self.checkequal(['arf', 'barf'], b, 'split', None)
self.checkequal(['arf', 'barf'], b, 'split', None, 2)
def test_additional_rsplit(self):
self.checkequal(['this', 'is', 'the', 'rsplit', 'function'],
......@@ -745,36 +746,53 @@ class BaseTest:
self.checkequal(['a'], ' a ', 'rsplit')
self.checkequal(['a', 'b'], ' a b ', 'rsplit')
self.checkequal([' a', 'b'], ' a b ', 'rsplit', None, 1)
self.checkequal([' a b c'], ' a b c ', 'rsplit',
None, 0)
self.checkequal([' a b','c'], ' a b c ', 'rsplit',
None, 1)
self.checkequal([' a', 'b', 'c'], ' a b c ', 'rsplit',
None, 2)
self.checkequal(['a', 'b', 'c'], ' a b c ', 'rsplit',
None, 3)
self.checkequal(['a', 'b'], '\n\ta \t\r b \v ', 'rsplit', None, 88)
aaa = ' a '*20
self.checkequal(['a']*20, aaa, 'rsplit')
self.checkequal([aaa[:-4]] + ['a'], aaa, 'rsplit', None, 1)
self.checkequal([' a a'] + ['a']*18, aaa, 'rsplit', None, 18)
# mixed use of str and unicode
self.checkequal(['a b', 'c', 'd'], 'a b c d', 'rsplit', ' ', 2)
for b in ('arf\tbarf', 'arf\nbarf', 'arf\rbarf',
'arf\fbarf', 'arf\vbarf'):
self.checkequal(['arf', 'barf'], b, 'rsplit')
self.checkequal(['arf', 'barf'], b, 'rsplit', None)
self.checkequal(['arf', 'barf'], b, 'rsplit', None, 2)
def test_strip(self):
def test_strip_whitespace(self):
self.checkequal('hello', ' hello ', 'strip')
self.checkequal('hello ', ' hello ', 'lstrip')
self.checkequal(' hello', ' hello ', 'rstrip')
self.checkequal('hello', 'hello', 'strip')
b = ' \t\n\r\f\vabc \t\n\r\f\v'
self.checkequal('abc', b, 'strip')
self.checkequal('abc \t\n\r\f\v', b, 'lstrip')
self.checkequal(' \t\n\r\f\vabc', b, 'rstrip')
# strip/lstrip/rstrip with None arg
self.checkequal('hello', ' hello ', 'strip', None)
self.checkequal('hello ', ' hello ', 'lstrip', None)
self.checkequal(' hello', ' hello ', 'rstrip', None)
self.checkequal('hello', 'hello', 'strip', None)
def test_strip(self):
# strip/lstrip/rstrip with str arg
self.checkequal('hello', 'xyzzyhelloxyzzy', 'strip', 'xyz')
self.checkequal('helloxyzzy', 'xyzzyhelloxyzzy', 'lstrip', 'xyz')
self.checkequal('xyzzyhello', 'xyzzyhelloxyzzy', 'rstrip', 'xyz')
self.checkequal('hello', 'hello', 'strip', 'xyz')
self.checkequal('', 'mississippi', 'strip', 'mississippi')
# only trim the start and end; does not strip internal characters
self.checkequal('mississipp', 'mississippi', 'strip', 'i')
self.checkraises(TypeError, 'hello', 'strip', 42, 42)
self.checkraises(TypeError, 'hello', 'lstrip', 42, 42)
......@@ -1363,28 +1381,3 @@ class MixinStrUnicodeTest:
s1 = t("abcd")
s2 = t().join([s1])
self.assertIs(s1, s2)
# Should also test mixed-type join.
if t is str:
s1 = subclass("abcd")
s2 = "".join([s1])
self.assertIsNot(s1, s2)
self.assertIs(type(s2), t)
s1 = t("abcd")
s2 = "".join([s1])
self.assertIs(s1, s2)
## elif t is str8:
## s1 = subclass("abcd")
## s2 = "".join([s1])
## self.assertIsNot(s1, s2)
## self.assertIs(type(s2), str) # promotes!
## s1 = t("abcd")
## s2 = "".join([s1])
## self.assertIsNot(s1, s2)
## self.assertIs(type(s2), str) # promotes!
else:
self.fail("unexpected type for MixinStrUnicodeTest %r" % t)
......@@ -509,68 +509,16 @@ class BaseBytesTest:
self.assertEqual(b.replace(b'i', b'a'), b'massassappa')
self.assertEqual(b.replace(b'ss', b'x'), b'mixixippi')
def test_split(self):
b = self.type2test(b'mississippi')
self.assertEqual(b.split(b'i'), [b'm', b'ss', b'ss', b'pp', b''])
self.assertEqual(b.split(b'ss'), [b'mi', b'i', b'ippi'])
self.assertEqual(b.split(b'w'), [b])
# with keyword args
b = self.type2test(b'a|b|c|d')
self.assertEqual(b.split(sep=b'|'), [b'a', b'b', b'c', b'd'])
self.assertEqual(b.split(b'|', maxsplit=1), [b'a', b'b|c|d'])
self.assertEqual(b.split(sep=b'|', maxsplit=1), [b'a', b'b|c|d'])
self.assertEqual(b.split(maxsplit=1, sep=b'|'), [b'a', b'b|c|d'])
b = self.type2test(b'a b c d')
self.assertEqual(b.split(maxsplit=1), [b'a', b'b c d'])
def test_split_whitespace(self):
for b in (b' arf barf ', b'arf\tbarf', b'arf\nbarf', b'arf\rbarf',
b'arf\fbarf', b'arf\vbarf'):
b = self.type2test(b)
self.assertEqual(b.split(), [b'arf', b'barf'])
self.assertEqual(b.split(None), [b'arf', b'barf'])
self.assertEqual(b.split(None, 2), [b'arf', b'barf'])
for b in (b'a\x1Cb', b'a\x1Db', b'a\x1Eb', b'a\x1Fb'):
b = self.type2test(b)
self.assertEqual(b.split(), [b])
self.assertEqual(self.type2test(b' a bb c ').split(None, 0), [b'a bb c '])
self.assertEqual(self.type2test(b' a bb c ').split(None, 1), [b'a', b'bb c '])
self.assertEqual(self.type2test(b' a bb c ').split(None, 2), [b'a', b'bb', b'c '])
self.assertEqual(self.type2test(b' a bb c ').split(None, 3), [b'a', b'bb', b'c'])
def test_split_string_error(self):
self.assertRaises(TypeError, self.type2test(b'a b').split, ' ')
def test_split_unicodewhitespace(self):
for b in (b'a\x1Cb', b'a\x1Db', b'a\x1Eb', b'a\x1Fb'):
b = self.type2test(b)
self.assertEqual(b.split(), [b])
b = self.type2test(b"\x09\x0A\x0B\x0C\x0D\x1C\x1D\x1E\x1F")
self.assertEqual(b.split(), [b'\x1c\x1d\x1e\x1f'])
def test_rsplit(self):
b = self.type2test(b'mississippi')
self.assertEqual(b.rsplit(b'i'), [b'm', b'ss', b'ss', b'pp', b''])
self.assertEqual(b.rsplit(b'ss'), [b'mi', b'i', b'ippi'])
self.assertEqual(b.rsplit(b'w'), [b])
# with keyword args
b = self.type2test(b'a|b|c|d')
self.assertEqual(b.rsplit(sep=b'|'), [b'a', b'b', b'c', b'd'])
self.assertEqual(b.rsplit(b'|', maxsplit=1), [b'a|b|c', b'd'])
self.assertEqual(b.rsplit(sep=b'|', maxsplit=1), [b'a|b|c', b'd'])
self.assertEqual(b.rsplit(maxsplit=1, sep=b'|'), [b'a|b|c', b'd'])
b = self.type2test(b'a b c d')
self.assertEqual(b.rsplit(maxsplit=1), [b'a b c', b'd'])
def test_rsplit_whitespace(self):
for b in (b' arf barf ', b'arf\tbarf', b'arf\nbarf', b'arf\rbarf',
b'arf\fbarf', b'arf\vbarf'):
b = self.type2test(b)
self.assertEqual(b.rsplit(), [b'arf', b'barf'])
self.assertEqual(b.rsplit(None), [b'arf', b'barf'])
self.assertEqual(b.rsplit(None, 2), [b'arf', b'barf'])
self.assertEqual(self.type2test(b' a bb c ').rsplit(None, 0), [b' a bb c'])
self.assertEqual(self.type2test(b' a bb c ').rsplit(None, 1), [b' a bb', b'c'])
self.assertEqual(self.type2test(b' a bb c ').rsplit(None, 2), [b' a', b'bb', b'c'])
self.assertEqual(self.type2test(b' a bb c ').rsplit(None, 3), [b'a', b'bb', b'c'])
def test_rsplit_string_error(self):
self.assertRaises(TypeError, self.type2test(b'a b').rsplit, ' ')
......@@ -615,37 +563,6 @@ class BaseBytesTest:
it = pickle.loads(d)
self.assertEqual(list(it), data[1:])
def test_strip(self):
b = self.type2test(b'mississippi')
self.assertEqual(b.strip(b'i'), b'mississipp')
self.assertEqual(b.strip(b'm'), b'ississippi')
self.assertEqual(b.strip(b'pi'), b'mississ')
self.assertEqual(b.strip(b'im'), b'ssissipp')
self.assertEqual(b.strip(b'pim'), b'ssiss')
self.assertEqual(b.strip(b), b'')
def test_lstrip(self):
b = self.type2test(b'mississippi')
self.assertEqual(b.lstrip(b'i'), b'mississippi')
self.assertEqual(b.lstrip(b'm'), b'ississippi')
self.assertEqual(b.lstrip(b'pi'), b'mississippi')
self.assertEqual(b.lstrip(b'im'), b'ssissippi')
self.assertEqual(b.lstrip(b'pim'), b'ssissippi')
def test_rstrip(self):
b = self.type2test(b'mississippi')
self.assertEqual(b.rstrip(b'i'), b'mississipp')
self.assertEqual(b.rstrip(b'm'), b'mississippi')
self.assertEqual(b.rstrip(b'pi'), b'mississ')
self.assertEqual(b.rstrip(b'im'), b'mississipp')
self.assertEqual(b.rstrip(b'pim'), b'mississ')
def test_strip_whitespace(self):
b = self.type2test(b' \t\n\r\f\vabc \t\n\r\f\v')
self.assertEqual(b.strip(), b'abc')
self.assertEqual(b.lstrip(), b'abc \t\n\r\f\v')
self.assertEqual(b.rstrip(), b' \t\n\r\f\vabc')
def test_strip_bytearray(self):
self.assertEqual(self.type2test(b'abc').strip(memoryview(b'ac')), b'b')
self.assertEqual(self.type2test(b'abc').lstrip(memoryview(b'ac')), b'bc')
......@@ -1565,7 +1482,7 @@ class AssortedBytesTest(unittest.TestCase):
# XXX More string methods? (Those that don't use character properties)
# There are tests in string_tests.py that are more
# comprehensive for things like split, partition, etc.
# comprehensive for things like partition, etc.
# Unfortunately they are all bundled with tests that
# are not appropriate for bytes
......
......@@ -380,10 +380,6 @@ class UnicodeTest(string_tests.CommonTest,
def test_split(self):
string_tests.CommonTest.test_split(self)
# Mixed arguments
self.checkequalnofix(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//')
self.checkequalnofix(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//')
self.checkequalnofix(['endcase ', ''], 'endcase test', 'split', 'test')
# test mixed kinds
for left, right in ('ba', '\u0101\u0100', '\U00010301\U00010300'):
left *= 9
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment