diff options
| author | Hye-Shik Chang <hyeshik@gmail.com> | 2004-01-05 00:29:51 (GMT) |
|---|---|---|
| committer | Hye-Shik Chang <hyeshik@gmail.com> | 2004-01-05 00:29:51 (GMT) |
| commit | 75c00efcc79d8207242685ddbd499d5af892bfd1 (patch) | |
| tree | 4b91c2c7ef9158f1959dec8fb7b6f73e18505330 /Lib/test | |
| parent | cb2117a83cf09dcccb7882f8b8210f74b8206ae0 (diff) | |
| download | cpython-75c00efcc79d8207242685ddbd499d5af892bfd1.zip cpython-75c00efcc79d8207242685ddbd499d5af892bfd1.tar.gz cpython-75c00efcc79d8207242685ddbd499d5af892bfd1.tar.bz2 | |
[SF #866875] Add a specialized routine for one character
separaters on str.split() and str.rsplit().
Diffstat (limited to 'Lib/test')
| -rw-r--r-- | Lib/test/string_tests.py | 69 |
1 files changed, 55 insertions, 14 deletions
diff --git a/Lib/test/string_tests.py b/Lib/test/string_tests.py index eafc89a..860c1f2 100644 --- a/Lib/test/string_tests.py +++ b/Lib/test/string_tests.py @@ -175,41 +175,82 @@ class CommonTest(unittest.TestCase): 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, 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') + + # 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', '|', 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', '|', 0) + self.checkequal(['a', '', 'b||c||d'], 'a||b||c||d', 'split', '|', 2) + self.checkequal(['endcase ', ''], 'endcase |', 'split', '|') + self.checkequal(['a', '', 'b\x00c\x00d'], 'a\x00\x00b\x00c\x00d', 'split', '\x00', 2) + + # by string self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//') + self.checkequal(['a', 'b//c//d'], 'a//b//c//d', 'split', '//', 1) + self.checkequal(['a', 'b', 'c//d'], 'a//b//c//d', 'split', '//', 2) + self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//', 3) + self.checkequal(['a', 'b', 'c', 'd'], 'a//b//c//d', 'split', '//', 4) + self.checkequal(['a//b//c//d'], 'a//b//c//d', 'split', '//', 0) + self.checkequal(['a', '', 'b////c////d'], 'a////b////c////d', 'split', '//', 2) self.checkequal(['endcase ', ''], 'endcase test', 'split', 'test') + # 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) def test_rsplit(self): self.checkequal(['this', 'is', 'the', 'rsplit', 'function'], 'this is the rsplit function', 'rsplit') - self.checkequal(['a', 'b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|') - self.checkequal(['a|b', 'c', 'd'], 'a|b|c|d', 'rsplit', '|', 2) + + # 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, 0) - 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', ', ', 0) self.checkequal(['a b', 'c', 'd'], 'a b c d', 'rsplit', None, 2) - self.checkequal(['a\x00b', 'c'], 'a\x00b\x00c', 'rsplit', '\x00', 1) - self.checkequal(['', ''], 'abcd', 'rsplit', 'abcd') + + # 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', '|', 0) + self.checkequal(['a||b||c', '', 'd'], 'a||b||c||d', 'rsplit', '|', 2) + self.checkequal(['', ' begincase'], '| begincase', 'rsplit', '|') + self.checkequal(['a\x00\x00b', 'c', 'd'], 'a\x00\x00b\x00c\x00d', 'rsplit', '\x00', 2) + + # 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', '//', 0) + self.checkequal(['a////b////c', '', 'd'], 'a////b////c////d', 'rsplit', '//', 2) + self.checkequal(['', ' begincase'], 'test begincase', 'rsplit', 'test') + + # mixed use of str and unicode self.checkequal([u'a b', u'c', u'd'], 'a b c d', 'rsplit', u' ', 2) - self.checkequal(['', ' endcase'], '| endcase', 'rsplit', '|') - self.checkequal(['', ' endcase'], 'test endcase', 'rsplit', 'test') + + # argument type + self.checkraises(TypeError, 'hello', 'rsplit', 42, 42, 42) def test_strip(self): self.checkequal('hello', ' hello ', 'strip') |