summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorSerhiy Storchaka <storchaka@gmail.com>2013-10-24 19:02:42 (GMT)
committerSerhiy Storchaka <storchaka@gmail.com>2013-10-24 19:02:42 (GMT)
commit22fb0dec30af4168c81744782a8bcc2453ac8055 (patch)
tree0daf6e478012eda3a71a9c44f6d5f7e6ad70a920
parent2147857db3f0ac3ff0200e52c930ed5ef43c2bfd (diff)
downloadcpython-22fb0dec30af4168c81744782a8bcc2453ac8055.zip
cpython-22fb0dec30af4168c81744782a8bcc2453ac8055.tar.gz
cpython-22fb0dec30af4168c81744782a8bcc2453ac8055.tar.bz2
Issue #19327: Fixed the working of regular expressions with too big charset.
-rw-r--r--Lib/sre_compile.py2
-rw-r--r--Lib/test/test_re.py2
-rw-r--r--Misc/NEWS2
3 files changed, 5 insertions, 1 deletions
diff --git a/Lib/sre_compile.py b/Lib/sre_compile.py
index 97c1663..bd40705 100644
--- a/Lib/sre_compile.py
+++ b/Lib/sre_compile.py
@@ -343,7 +343,7 @@ def _optimize_unicode(charset, fixup):
else:
code = 'I'
# Convert block indices to byte array of 256 bytes
- mapping = array.array('b', mapping).tostring()
+ mapping = array.array('B', mapping).tostring()
# Convert byte array to word array
mapping = array.array(code, mapping)
assert mapping.itemsize == _sre.CODESIZE
diff --git a/Lib/test/test_re.py b/Lib/test/test_re.py
index 8b277cf..d879bac 100644
--- a/Lib/test/test_re.py
+++ b/Lib/test/test_re.py
@@ -427,6 +427,8 @@ class ReTests(unittest.TestCase):
u"\u2222").group(1), u"\u2222")
self.assertEqual(re.match(u"([\u2222\u2223])",
u"\u2222", re.UNICODE).group(1), u"\u2222")
+ r = u'[%s]' % u''.join(map(unichr, range(256, 2**16, 255)))
+ self.assertEqual(re.match(r, u"\uff01", re.UNICODE).group(), u"\uff01")
def test_big_codesize(self):
# Issue #1160
diff --git a/Misc/NEWS b/Misc/NEWS
index 4e8dab8..5dc2870 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -40,6 +40,8 @@ Core and Builtins
Library
-------
+- Issue #19327: Fixed the working of regular expressions with too big charset.
+
- Issue #19350: Increasing the test coverage of macurl2path. Patch by Colin
Williams.