# HG changeset patch # Parent 633bb190fb76be9c24345ccce6ad65ee7d28696b Issue #26712: Unify (r)split(), (l/r)strip() tests into string_tests This eliminates a few redundant test cases. diff -r 633bb190fb76 Lib/test/string_tests.py --- a/Lib/test/string_tests.py Fri Apr 08 08:48:20 2016 +0300 +++ b/Lib/test/string_tests.py Sat Apr 09 02:16:50 2016 +0000 @@ -368,6 +368,8 @@ 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 @@ 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', '|') @@ -714,16 +718,21 @@ 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 +754,53 @@ 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) diff -r 633bb190fb76 Lib/test/test_bytes.py --- a/Lib/test/test_bytes.py Fri Apr 08 08:48:20 2016 +0300 +++ b/Lib/test/test_bytes.py Sat Apr 09 02:16:50 2016 +0000 @@ -509,68 +509,16 @@ 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 @@ 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 @@ # 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 diff -r 633bb190fb76 Lib/test/test_unicode.py --- a/Lib/test/test_unicode.py Fri Apr 08 08:48:20 2016 +0300 +++ b/Lib/test/test_unicode.py Sat Apr 09 02:16:50 2016 +0000 @@ -380,10 +380,6 @@ 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