From e9741f3ed8487da1d7c8ac8b0c04d3f09802fb1a Mon Sep 17 00:00:00 2001 From: Georg Brandl Date: Thu, 17 Sep 2009 11:28:09 +0000 Subject: [PATCH] Issue #6922: Fix an infinite loop when trying to decode an invalid UTF-32 stream with a non-raising error handler like "replace" or "ignore". --- Lib/test/test_codecs.py | 12 ++++++++++++ Misc/NEWS | 3 +++ Objects/unicodeobject.c | 2 +- 3 files changed, 16 insertions(+), 1 deletion(-) diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py index 06cab1c7efa..18933112a6e 100644 --- a/Lib/test/test_codecs.py +++ b/Lib/test/test_codecs.py @@ -305,6 +305,12 @@ class UTF32Test(ReadTest): ] ) + def test_handlers(self): + self.assertEqual((u'\ufffd', 1), + codecs.utf_32_decode('\x01', 'replace', True)) + self.assertEqual((u'', 1), + codecs.utf_32_decode('\x01', 'ignore', True)) + def test_errors(self): self.assertRaises(UnicodeDecodeError, codecs.utf_32_decode, "\xff", "strict", True) @@ -422,6 +428,12 @@ class UTF16Test(ReadTest): ] ) + def test_handlers(self): + self.assertEqual((u'\ufffd', 1), + codecs.utf_16_decode('\x01', 'replace', True)) + self.assertEqual((u'', 1), + codecs.utf_16_decode('\x01', 'ignore', True)) + def test_errors(self): self.assertRaises(UnicodeDecodeError, codecs.utf_16_decode, "\xff", "strict", True) diff --git a/Misc/NEWS b/Misc/NEWS index 77969570475..dc37a37dd2e 100644 --- a/Misc/NEWS +++ b/Misc/NEWS @@ -12,6 +12,9 @@ What's New in Python 2.7 alpha 1 Core and Builtins ----------------- +- Issue #6922: Fix an infinite loop when trying to decode an invalid + UTF-32 stream with a non-raising error handler like "replace" or "ignore". + - Issue #6713: Improve performance of integer -> string conversions. - Issue #1590864: Fix potential deadlock when mixing threads and fork(). diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c index c4b490295f3..61645101171 100644 --- a/Objects/unicodeobject.c +++ b/Objects/unicodeobject.c @@ -2321,7 +2321,7 @@ PyUnicode_DecodeUTF32Stateful(const char *s, if (unicode_decode_call_errorhandler( errors, &errorHandler, "utf32", errmsg, - starts, size, &startinpos, &endinpos, &exc, &s, + starts, size, &startinpos, &endinpos, &exc, (const char **)&q, &unicode, &outpos, &p)) goto onError; }