diff options
Diffstat (limited to 'Lib/test/test_re.py')
| -rw-r--r-- | Lib/test/test_re.py | 54 |
1 files changed, 38 insertions, 16 deletions
diff --git a/Lib/test/test_re.py b/Lib/test/test_re.py index 0fb47a8..4f7e162 100644 --- a/Lib/test/test_re.py +++ b/Lib/test/test_re.py @@ -84,7 +84,7 @@ class ReTests(unittest.TestCase): self.assertEqual(re.sub("(?i)b+", "x", "bbbb BBBB"), 'x x') self.assertEqual(re.sub(r'\d+', self.bump_num, '08.2 -2 23x99y'), '9.3 -3 24x100y') - self.assertEqual(re.sub(r'\d+', self.bump_num, '08.2 -2 23x99y', 3), + self.assertEqual(re.sub(r'\d+', self.bump_num, '08.2 -2 23x99y', count=3), '9.3 -3 23x99y') self.assertEqual(re.sub('.', lambda m: r"\n", 'x'), '\\n') @@ -155,8 +155,8 @@ class ReTests(unittest.TestCase): self.assertEqual(re.sub('x', r'\09', 'x'), '\0' + '9') self.assertEqual(re.sub('x', r'\0a', 'x'), '\0' + 'a') - self.assertEqual(re.sub('x', r'\400', 'x'), '\0') - self.assertEqual(re.sub('x', r'\777', 'x'), '\377') + self.assertRaises(re.error, re.sub, 'x', r'\400', 'x') + self.assertRaises(re.error, re.sub, 'x', r'\777', 'x') self.assertRaises(re.error, re.sub, 'x', r'\1', 'x') self.assertRaises(re.error, re.sub, 'x', r'\8', 'x') @@ -180,7 +180,7 @@ class ReTests(unittest.TestCase): def test_qualified_re_sub(self): self.assertEqual(re.sub('a', 'b', 'aaaaa'), 'bbbbb') - self.assertEqual(re.sub('a', 'b', 'aaaaa', 1), 'baaaa') + self.assertEqual(re.sub('a', 'b', 'aaaaa', count=1), 'baaaa') def test_bug_114660(self): self.assertEqual(re.sub(r'(\S)\s+(\S)', r'\1 \2', 'hello there'), @@ -194,6 +194,7 @@ class ReTests(unittest.TestCase): def test_symbolic_groups(self): re.compile('(?P<a>x)(?P=a)(?(a)y)') re.compile('(?P<a1>x)(?P=a1)(?(a1)y)') + re.compile('(?P<a1>x)\1(?(1)y)') self.assertRaises(re.error, re.compile, '(?P<a>)(?P<a>)') self.assertRaises(re.error, re.compile, '(?Px)') self.assertRaises(re.error, re.compile, '(?P=)') @@ -213,6 +214,10 @@ class ReTests(unittest.TestCase): re.compile('(?P<ยต>x)(?P=ยต)(?(ยต)y)') re.compile('(?P<๐๐ซ๐ฆ๐ ๐ฌ๐ก๐ข>x)(?P=๐๐ซ๐ฆ๐ ๐ฌ๐ก๐ข)(?(๐๐ซ๐ฆ๐ ๐ฌ๐ก๐ข)y)') self.assertRaises(re.error, re.compile, '(?P<ยฉ>x)') + # Support > 100 groups. + pat = '|'.join('x(?P<a%d>%x)y' % (i, i) for i in range(1, 200 + 1)) + pat = '(?:%s)(?(200)z|t)' % pat + self.assertEqual(re.match(pat, 'xc8yz').span(), (0, 5)) def test_symbolic_refs(self): self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<a', 'xx') @@ -221,21 +226,26 @@ class ReTests(unittest.TestCase): self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<a a>', 'xx') self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<>', 'xx') self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<1a1>', 'xx') + self.assertRaises(re.error, re.sub, '(?P<a>x)', r'\g<2>', 'xx') + self.assertRaises(re.error, re.sub, '(?P<a>x)', r'\2', 'xx') self.assertRaises(IndexError, re.sub, '(?P<a>x)', '\g<ab>', 'xx') - self.assertRaises(re.error, re.sub, '(?P<a>x)|(?P<b>y)', '\g<b>', 'xx') - self.assertRaises(re.error, re.sub, '(?P<a>x)|(?P<b>y)', '\\2', 'xx') + self.assertEqual(re.sub('(?P<a>x)|(?P<b>y)', r'\g<b>', 'xx'), '') + self.assertEqual(re.sub('(?P<a>x)|(?P<b>y)', r'\2', 'xx'), '') self.assertRaises(re.error, re.sub, '(?P<a>x)', '\g<-1>', 'xx') # New valid/invalid identifiers in Python 3 self.assertEqual(re.sub('(?P<ยต>x)', r'\g<ยต>', 'xx'), 'xx') self.assertEqual(re.sub('(?P<๐๐ซ๐ฆ๐ ๐ฌ๐ก๐ข>x)', r'\g<๐๐ซ๐ฆ๐ ๐ฌ๐ก๐ข>', 'xx'), 'xx') self.assertRaises(re.error, re.sub, '(?P<a>x)', r'\g<ยฉ>', 'xx') + # Support > 100 groups. + pat = '|'.join('x(?P<a%d>%x)y' % (i, i) for i in range(1, 200 + 1)) + self.assertEqual(re.sub(pat, '\g<200>', 'xc8yzxc8y'), 'c8zc8') def test_re_subn(self): self.assertEqual(re.subn("(?i)b+", "x", "bbbb BBBB"), ('x x', 2)) self.assertEqual(re.subn("b+", "x", "bbbb BBBB"), ('x BBBB', 1)) self.assertEqual(re.subn("b+", "x", "xyz"), ('xyz', 0)) self.assertEqual(re.subn("b*", "x", "xyz"), ('xxxyxzx', 4)) - self.assertEqual(re.subn("b*", "x", "xyz", 2), ('xxxyz', 2)) + self.assertEqual(re.subn("b*", "x", "xyz", count=2), ('xxxyz', 2)) def test_re_split(self): for string in ":a:b::c", S(":a:b::c"): @@ -273,11 +283,11 @@ class ReTests(unittest.TestCase): ['', 'a', '', '', 'c']) def test_qualified_re_split(self): - self.assertEqual(re.split(":", ":a:b::c", 2), ['', 'a', 'b::c']) - self.assertEqual(re.split(':', 'a:b:c:d', 2), ['a', 'b', 'c:d']) - self.assertEqual(re.split("(:)", ":a:b::c", 2), + self.assertEqual(re.split(":", ":a:b::c", maxsplit=2), ['', 'a', 'b::c']) + self.assertEqual(re.split(':', 'a:b:c:d', maxsplit=2), ['a', 'b', 'c:d']) + self.assertEqual(re.split("(:)", ":a:b::c", maxsplit=2), ['', ':', 'a', ':', 'b::c']) - self.assertEqual(re.split("(:*)", ":a:b::c", 2), + self.assertEqual(re.split("(:*)", ":a:b::c", maxsplit=2), ['', ':', 'a', ':', 'b::c']) def test_re_findall(self): @@ -405,6 +415,10 @@ class ReTests(unittest.TestCase): self.assertIsNone(p.match('abd')) self.assertIsNone(p.match('ac')) + # Support > 100 groups. + pat = '|'.join('x(?P<a%d>%x)y' % (i, i) for i in range(1, 200 + 1)) + pat = '(?:%s)(?(200)z)' % pat + self.assertEqual(re.match(pat, 'xc8yz').span(), (0, 5)) def test_re_groupref(self): self.assertEqual(re.match(r'^(\|)?([^()]+)\1$', '|a|').groups(), @@ -428,6 +442,10 @@ class ReTests(unittest.TestCase): "first second") .expand(r"\2 \1 \g<second> \g<first>"), "second first second first") + self.assertEqual(re.match("(?P<first>first)|(?P<second>second)", + "first") + .expand(r"\2 \g<second>"), + " ") def test_repeat_minmax(self): self.assertIsNone(re.match("^(\w){1}$", "abc")) @@ -756,7 +774,7 @@ class ReTests(unittest.TestCase): self.assertTrue(re.match(r"\08", "\0008")) self.assertTrue(re.match(r"\01", "\001")) self.assertTrue(re.match(r"\018", "\0018")) - self.assertTrue(re.match(r"\567", chr(0o167))) + self.assertRaises(re.error, re.match, r"\567", "") self.assertRaises(re.error, re.match, r"\911", "") self.assertRaises(re.error, re.match, r"\x1", "") self.assertRaises(re.error, re.match, r"\x1z", "") @@ -784,12 +802,13 @@ class ReTests(unittest.TestCase): self.assertTrue(re.match(r"[\U%08x]" % i, chr(i))) self.assertTrue(re.match(r"[\U%08x0]" % i, chr(i)+"0")) self.assertTrue(re.match(r"[\U%08xz]" % i, chr(i)+"z")) - self.assertTrue(re.match(r"[\U0001d49c-\U0001d4b5]", "\U0001d49e")) + self.assertRaises(re.error, re.match, r"[\567]", "") self.assertRaises(re.error, re.match, r"[\911]", "") self.assertRaises(re.error, re.match, r"[\x1z]", "") self.assertRaises(re.error, re.match, r"[\u123z]", "") self.assertRaises(re.error, re.match, r"[\U0001234z]", "") self.assertRaises(re.error, re.match, r"[\U00110000]", "") + self.assertTrue(re.match(r"[\U0001d49c-\U0001d4b5]", "\U0001d49e")) def test_sre_byte_literals(self): for i in [0, 8, 16, 32, 64, 127, 128, 255]: @@ -805,7 +824,7 @@ class ReTests(unittest.TestCase): self.assertTrue(re.match(br"\08", b"\0008")) self.assertTrue(re.match(br"\01", b"\001")) self.assertTrue(re.match(br"\018", b"\0018")) - self.assertTrue(re.match(br"\567", bytes([0o167]))) + self.assertRaises(re.error, re.match, br"\567", b"") self.assertRaises(re.error, re.match, br"\911", b"") self.assertRaises(re.error, re.match, br"\x1", b"") self.assertRaises(re.error, re.match, br"\x1z", b"") @@ -822,6 +841,7 @@ class ReTests(unittest.TestCase): self.assertTrue(re.match((r"[\x%02xz]" % i).encode(), bytes([i]))) self.assertTrue(re.match(br"[\u]", b'u')) self.assertTrue(re.match(br"[\U]", b'U')) + self.assertRaises(re.error, re.match, br"[\567]", b"") self.assertRaises(re.error, re.match, br"[\911]", b"") self.assertRaises(re.error, re.match, br"[\x1z]", b"") @@ -1124,8 +1144,10 @@ class ReTests(unittest.TestCase): # a RuntimeError is raised instead of OverflowError. long_overflow = 2**128 self.assertRaises(TypeError, re.finditer, "a", {}) - self.assertRaises(OverflowError, _sre.compile, "abc", 0, [long_overflow]) - self.assertRaises(TypeError, _sre.compile, {}, 0, []) + with self.assertRaises(OverflowError): + _sre.compile("abc", 0, [long_overflow], 0, [], []) + with self.assertRaises(TypeError): + _sre.compile({}, 0, [], 0, [], []) def test_search_dot_unicode(self): self.assertTrue(re.search("123.*-", '123abc-')) |