diff options
| author | Serhiy Storchaka <storchaka@gmail.com> | 2013-10-24 19:02:58 (GMT) |
|---|---|---|
| committer | Serhiy Storchaka <storchaka@gmail.com> | 2013-10-24 19:02:58 (GMT) |
| commit | be80fc9a843e3c51d1030d3eab52d6287e5aef3a (patch) | |
| tree | eb5b7b5fd1dcf66a70a7cc566772d7ad581dbeb9 /Lib | |
| parent | b82a3dc2409e68dbd20d1991ba2e9d1c490c67a3 (diff) | |
| download | cpython-be80fc9a843e3c51d1030d3eab52d6287e5aef3a.zip cpython-be80fc9a843e3c51d1030d3eab52d6287e5aef3a.tar.gz cpython-be80fc9a843e3c51d1030d3eab52d6287e5aef3a.tar.bz2 | |
Issue #19327: Fixed the working of regular expressions with too big charset.
Diffstat (limited to 'Lib')
| -rw-r--r-- | Lib/sre_compile.py | 2 | ||||
| -rw-r--r-- | Lib/test/test_re.py | 3 |
2 files changed, 4 insertions, 1 deletions
diff --git a/Lib/sre_compile.py b/Lib/sre_compile.py index b6b377f..a80c74d 100644 --- a/Lib/sre_compile.py +++ b/Lib/sre_compile.py @@ -345,7 +345,7 @@ def _optimize_unicode(charset, fixup): else: code = 'I' # Convert block indices to byte array of 256 bytes - mapping = array.array('b', mapping).tobytes() + mapping = array.array('B', mapping).tobytes() # 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 2104437..f093812 100644 --- a/Lib/test/test_re.py +++ b/Lib/test/test_re.py @@ -428,6 +428,9 @@ class ReTests(unittest.TestCase): "\u2222").group(1), "\u2222") self.assertEqual(re.match("([\u2222\u2223])", "\u2222", re.UNICODE).group(1), "\u2222") + r = '[%s]' % ''.join(map(chr, range(256, 2**16, 255))) + self.assertEqual(re.match(r, + "\uff01", re.UNICODE).group(), "\uff01") def test_big_codesize(self): # Issue #1160 |