From: Ezio Melotti Date: Fri, 11 Jan 2013 06:32:01 +0000 (+0200) Subject: #13899: \A, \Z, and \B now correctly match the A, Z, and B literals when used inside... X-Git-Tag: v2.7.4rc1~164^2~97 X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=5c4e32b131af335d82e467ba95d6b30a414020e8;p=python #13899: \A, \Z, and \B now correctly match the A, Z, and B literals when used inside character classes (e.g. [A]). Patch by Matthew Barnett. --- diff --git a/Lib/sre_parse.py b/Lib/sre_parse.py index 7149dca491..8b98b1ac2e 100644 --- a/Lib/sre_parse.py +++ b/Lib/sre_parse.py @@ -228,7 +228,7 @@ def _class_escape(source, escape): if code: return code code = CATEGORIES.get(escape) - if code: + if code and code[0] == IN: return code try: c = escape[1:2] diff --git a/Lib/test/test_re.py b/Lib/test/test_re.py index 70702e6348..dee5efee8e 100644 --- a/Lib/test/test_re.py +++ b/Lib/test/test_re.py @@ -821,6 +821,12 @@ class ReTests(unittest.TestCase): # Test behaviour when not given a string or pattern as parameter self.assertRaises(TypeError, re.compile, 0) + def test_bug_13899(self): + # Issue #13899: re pattern r"[\A]" should work like "A" but matches + # nothing. Ditto B and Z. + self.assertEqual(re.findall(r'[\A\B\b\C\Z]', 'AB\bCZ'), + ['A', 'B', '\b', 'C', 'Z']) + @precisionbigmemtest(size=_2G, memuse=1) def test_large_search(self, size): # Issue #10182: indices were 32-bit-truncated. diff --git a/Misc/ACKS b/Misc/ACKS index 41c684f09a..c185689227 100644 --- a/Misc/ACKS +++ b/Misc/ACKS @@ -58,6 +58,7 @@ Chris Barker Anton Barkovsky Nick Barnes Quentin Barnes +Matthew Barnett Richard Barran Cesar Eduardo Barros Des Barry diff --git a/Misc/NEWS b/Misc/NEWS index 469ca8b2fa..1f4e282d2c 100644 --- a/Misc/NEWS +++ b/Misc/NEWS @@ -186,6 +186,9 @@ Core and Builtins Library ------- +- Issue #13899: \A, \Z, and \B now correctly match the A, Z, and B literals + when used inside character classes (e.g. '[\A]'). Patch by Matthew Barnett. + - Issue #15109: Fix regression in sqlite3's iterdump method where it would die with an encoding error if the database contained string values containing non-ASCII. (Regression was introduced by fix for 9750).