bpo-32308: Replace empty matches adjacent to a previous non-empty match in re.sub(). (#4846)

This commit is contained in:
Serhiy Storchaka 2018-01-04 11:06:13 +02:00 committed by GitHub
parent 0cc99c8cd7
commit fbb490fd2f
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 35 additions and 25 deletions

View file

@ -213,11 +213,6 @@ class ReTests(unittest.TestCase):
self.assertEqual(re.sub(r'(\S)\s+(\S)', r'\1 \2', 'hello there'),
'hello there')
def test_bug_462270(self):
# Test for empty sub() behaviour, see SF bug #462270
self.assertEqual(re.sub('x*', '-', 'abxd'), '-a-b-d-')
self.assertEqual(re.sub('x+', '-', 'abxd'), 'ab-d')
def test_symbolic_groups(self):
re.compile(r'(?P<a>x)(?P=a)(?(a)y)')
re.compile(r'(?P<a1>x)(?P=a1)(?(a1)y)')
@ -331,10 +326,10 @@ class ReTests(unittest.TestCase):
['', 'a', '', '', 'c'])
for sep, expected in [
(':*', ['', 'a', 'b', 'c', '']),
('(?::*)', ['', 'a', 'b', 'c', '']),
('(:*)', ['', ':', 'a', ':', 'b', '::', 'c', '', '']),
('(:)*', ['', ':', 'a', ':', 'b', ':', 'c', None, '']),
(':*', ['', '', 'a', '', 'b', '', 'c', '']),
('(?::*)', ['', '', 'a', '', 'b', '', 'c', '']),
('(:*)', ['', ':', '', '', 'a', ':', '', '', 'b', '::', '', '', 'c', '', '']),
('(:)*', ['', ':', '', None, 'a', ':', '', None, 'b', ':', '', None, 'c', None, '']),
]:
with self.subTest(sep=sep):
self.assertTypedEqual(re.split(sep, ':a:b::c'), expected)
@ -357,7 +352,7 @@ class ReTests(unittest.TestCase):
self.assertEqual(re.split("(:+)", ":a:b::c", maxsplit=2),
['', ':', 'a', ':', 'b::c'])
self.assertEqual(re.split("(:*)", ":a:b::c", maxsplit=2),
['', ':', 'a', ':', 'b::c'])
['', ':', '', '', 'a:b::c'])
def test_re_findall(self):
self.assertEqual(re.findall(":+", "abc"), [])
@ -1753,13 +1748,13 @@ class ReTests(unittest.TestCase):
def test_zerowidth(self):
# Issues 852532, 1647489, 3262, 25054.
self.assertEqual(re.split(r"\b", "a::bc"), ['', 'a', '::', 'bc', ''])
self.assertEqual(re.split(r"\b|:+", "a::bc"), ['', 'a', '', 'bc', ''])
self.assertEqual(re.split(r"(?<!\w)(?=\w)|:+", "a::bc"), ['', 'a', 'bc'])
self.assertEqual(re.split(r"\b|:+", "a::bc"), ['', 'a', '', '', 'bc', ''])
self.assertEqual(re.split(r"(?<!\w)(?=\w)|:+", "a::bc"), ['', 'a', '', 'bc'])
self.assertEqual(re.split(r"(?<=\w)(?!\w)|:+", "a::bc"), ['a', '', 'bc', ''])
self.assertEqual(re.sub(r"\b", "-", "a::bc"), '-a-::-bc-')
self.assertEqual(re.sub(r"\b|:+", "-", "a::bc"), '-a--bc-')
self.assertEqual(re.sub(r"(\b|:+)", r"[\1]", "a::bc"), '[]a[][::]bc[]')
self.assertEqual(re.sub(r"\b|:+", "-", "a::bc"), '-a---bc-')
self.assertEqual(re.sub(r"(\b|:+)", r"[\1]", "a::bc"), '[]a[][::][]bc[]')
self.assertEqual(re.findall(r"\b|:+", "a::bc"), ['', '', '::', '', ''])
self.assertEqual(re.findall(r"\b|\w+", "a::bc"),