summaryrefslogtreecommitdiffstats
path: root/Lib
diff options
context:
space:
mode:
authorSerhiy Storchaka <storchaka@gmail.com>2013-11-23 21:20:30 (GMT)
committerSerhiy Storchaka <storchaka@gmail.com>2013-11-23 21:20:30 (GMT)
commit32eddc1bbc47479a3639b9191ffc82a52903c5f4 (patch)
tree8ce67ed6f7d6db96277f4e6d07457f2b159fb362 /Lib
parent3ed82c55a85665a33b821064c1911b4aa09301d9 (diff)
downloadcpython-32eddc1bbc47479a3639b9191ffc82a52903c5f4.zip
cpython-32eddc1bbc47479a3639b9191ffc82a52903c5f4.tar.gz
cpython-32eddc1bbc47479a3639b9191ffc82a52903c5f4.tar.bz2
Issue #16203: Add re.fullmatch() function and regex.fullmatch() method,
which anchor the pattern at both ends of the string to match. Original patch by Matthew Barnett.
Diffstat (limited to 'Lib')
-rw-r--r--Lib/re.py28
-rw-r--r--Lib/test/test_re.py30
2 files changed, 47 insertions, 11 deletions
diff --git a/Lib/re.py b/Lib/re.py
index b41aab0..77f5e3f 100644
--- a/Lib/re.py
+++ b/Lib/re.py
@@ -85,16 +85,17 @@ resulting RE will match the second character.
\\ Matches a literal backslash.
This module exports the following functions:
- match Match a regular expression pattern to the beginning of a string.
- search Search a string for the presence of a pattern.
- sub Substitute occurrences of a pattern found in a string.
- subn Same as sub, but also return the number of substitutions made.
- split Split a string by the occurrences of a pattern.
- findall Find all occurrences of a pattern in a string.
- finditer Return an iterator yielding a match object for each match.
- compile Compile a pattern into a RegexObject.
- purge Clear the regular expression cache.
- escape Backslash all non-alphanumerics in a string.
+ match Match a regular expression pattern to the beginning of a string.
+ fullmatch Match a regular expression pattern to all of a string.
+ search Search a string for the presence of a pattern.
+ sub Substitute occurrences of a pattern found in a string.
+ subn Same as sub, but also return the number of substitutions made.
+ split Split a string by the occurrences of a pattern.
+ findall Find all occurrences of a pattern in a string.
+ finditer Return an iterator yielding a match object for each match.
+ compile Compile a pattern into a RegexObject.
+ purge Clear the regular expression cache.
+ escape Backslash all non-alphanumerics in a string.
Some of the functions in this module takes flags as optional parameters:
A ASCII For string patterns, make \w, \W, \b, \B, \d, \D
@@ -123,7 +124,7 @@ import sre_compile
import sre_parse
# public symbols
-__all__ = [ "match", "search", "sub", "subn", "split", "findall",
+__all__ = [ "match", "fullmatch", "search", "sub", "subn", "split", "findall",
"compile", "purge", "template", "escape", "A", "I", "L", "M", "S", "X",
"U", "ASCII", "IGNORECASE", "LOCALE", "MULTILINE", "DOTALL", "VERBOSE",
"UNICODE", "error" ]
@@ -154,6 +155,11 @@ def match(pattern, string, flags=0):
a match object, or None if no match was found."""
return _compile(pattern, flags).match(string)
+def fullmatch(pattern, string, flags=0):
+ """Try to apply the pattern to all of the string, returning
+ a match object, or None if no match was found."""
+ return _compile(pattern, flags).fullmatch(string)
+
def search(pattern, string, flags=0):
"""Scan through string looking for a match to the pattern, returning
a match object, or None if no match was found."""
diff --git a/Lib/test/test_re.py b/Lib/test/test_re.py
index 1ef68b8..a4e11c6 100644
--- a/Lib/test/test_re.py
+++ b/Lib/test/test_re.py
@@ -349,6 +349,36 @@ class ReTests(unittest.TestCase):
(None, 'b', None))
self.assertEqual(pat.match('ac').group(1, 'b2', 3), ('a', None, 'c'))
+ def test_re_fullmatch(self):
+ # Issue 16203: Proposal: add re.fullmatch() method.
+ self.assertEqual(re.fullmatch(r"a", "a").span(), (0, 1))
+ for string in "ab", S("ab"):
+ self.assertEqual(re.fullmatch(r"a|ab", string).span(), (0, 2))
+ for string in b"ab", B(b"ab"), bytearray(b"ab"), memoryview(b"ab"):
+ self.assertEqual(re.fullmatch(br"a|ab", string).span(), (0, 2))
+ for a, b in "\xe0\xdf", "\u0430\u0431", "\U0001d49c\U0001d49e":
+ r = r"%s|%s" % (a, a + b)
+ self.assertEqual(re.fullmatch(r, a + b).span(), (0, 2))
+ self.assertEqual(re.fullmatch(r".*?$", "abc").span(), (0, 3))
+ self.assertEqual(re.fullmatch(r".*?", "abc").span(), (0, 3))
+ self.assertEqual(re.fullmatch(r"a.*?b", "ab").span(), (0, 2))
+ self.assertEqual(re.fullmatch(r"a.*?b", "abb").span(), (0, 3))
+ self.assertEqual(re.fullmatch(r"a.*?b", "axxb").span(), (0, 4))
+ self.assertIsNone(re.fullmatch(r"a+", "ab"))
+ self.assertIsNone(re.fullmatch(r"abc$", "abc\n"))
+ self.assertIsNone(re.fullmatch(r"abc\Z", "abc\n"))
+ self.assertIsNone(re.fullmatch(r"(?m)abc$", "abc\n"))
+ self.assertEqual(re.fullmatch(r"ab(?=c)cd", "abcd").span(), (0, 4))
+ self.assertEqual(re.fullmatch(r"ab(?<=b)cd", "abcd").span(), (0, 4))
+ self.assertEqual(re.fullmatch(r"(?=a|ab)ab", "ab").span(), (0, 2))
+
+ self.assertEqual(
+ re.compile(r"bc").fullmatch("abcd", pos=1, endpos=3).span(), (1, 3))
+ self.assertEqual(
+ re.compile(r".*?$").fullmatch("abcd", pos=1, endpos=3).span(), (1, 3))
+ self.assertEqual(
+ re.compile(r".*?").fullmatch("abcd", pos=1, endpos=3).span(), (1, 3))
+
def test_re_groupref_exists(self):
self.assertEqual(re.match('^(\()?([^()]+)(?(1)\))$', '(a)').groups(),
('(', 'a'))