STINNER Victor added the comment:
Ok, it's a bug in the function resize a compact Unicode string,
resize_compact(): wstr field is not updated to the new size.
Attached patch should fix it. The bug was introduced by me in Python 3.3.
I don't think that it's possible to resize wstr buffer instead of
freeing it: it will not be refilled by PyUnicode_AsUnicodeAndSize() if
wstr is not NULL. An alternative is to create a new string (instead of
using realloc) if wstr is not NULL.
2013/2/7 Florent Xicluna <rep...@bugs.python.org>:
>
> Changes by Florent Xicluna <florent.xicl...@gmail.com>:
>
>
> ----------
> components: -Windows
>
> _______________________________________
> Python tracker <rep...@bugs.python.org>
> <http://bugs.python.org/issue17137>
> _______________________________________
----------
keywords: +patch
Added file: http://bugs.python.org/file28987/pep393.patch
_______________________________________
Python tracker <rep...@bugs.python.org>
<http://bugs.python.org/issue17137>
_______________________________________
diff -r b8a6bc70fc08 Lib/test/test_unicode.py
--- a/Lib/test/test_unicode.py Thu Feb 07 17:05:32 2013 +0200
+++ b/Lib/test/test_unicode.py Thu Feb 07 17:15:48 2013 +0100
@@ -7,6 +7,7 @@ Written by Marc-Andre Lemburg (mal@lembu
"""#"
import _string
import codecs
+import random
import struct
import sys
import unittest
@@ -2191,6 +2192,20 @@ class UnicodeTest(string_tests.CommonTes
self.assertEqual(args[0], text)
self.assertEqual(len(args), 1)
+ def test_resize(self):
+ for length in range(1, 100, 7):
+ # generate a fresh string (refcount=1)
+ text = 'a' * length + 'b'
+
+ # fill wstr internal field
+ abc = text.encode('unicode_internal')
+ self.assertEqual(abc.decode('unicode_internal'), text)
+
+ text += 'c'
+ abcdef = text.encode('unicode_internal')
+ self.assertNotEqual(abc, abcdef)
+ self.assertEqual(abcdef.decode('unicode_internal'), text)
+
class StringModuleTest(unittest.TestCase):
def test_formatter_parser(self):
diff -r b8a6bc70fc08 Objects/unicodeobject.c
--- a/Objects/unicodeobject.c Thu Feb 07 17:05:32 2013 +0200
+++ b/Objects/unicodeobject.c Thu Feb 07 17:15:48 2013 +0100
@@ -717,6 +717,10 @@ resize_compact(PyObject *unicode, Py_ssi
if (!PyUnicode_IS_ASCII(unicode))
_PyUnicode_WSTR_LENGTH(unicode) = length;
}
+ else if (_PyUnicode_HAS_WSTR_MEMORY(unicode)) {
+ PyObject_DEL(_PyUnicode_WSTR(unicode));
+ _PyUnicode_WSTR(unicode) = NULL;
+ }
#ifdef Py_DEBUG
unicode_fill_invalid(unicode, old_length);
#endif
_______________________________________________
Python-bugs-list mailing list
Unsubscribe:
http://mail.python.org/mailman/options/python-bugs-list/archive%40mail-archive.com
