From 070de9bd4137b78b1a74e287fea475ac7aa39bf6 Mon Sep 17 00:00:00 2001
From: Ben Pfaff <blp@nicira.com>
Date: Fri, 1 Jul 2011 10:11:30 -0700
Subject: [PATCH] python: Make invalid UTF-8 sequence messages consistent
across Python versions.
Given the invalid input <C0 22>, some versions of Python report <C0> as the
invalid sequence and other versions report <C0 22> as the invalid sequence.
Similarly, given input <ED 80 7F>, some report <ED 80> and others report
<ED 80 7F> as the invalid sequence. This caused spurious test failures for
the test "no invalid UTF-8 sequences in strings - Python", so this commit
makes the messages consistent by dropping the extra trailing byte from the
message.
I first noticed the longer sequences <C0 22> and <ED 80 7F> on Ubuntu
10.04 with python version 2.6.5-0ubuntu1, but undoubtedly it exists
elsewhere also.
---
python/ovs/json.py | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/python/ovs/json.py b/python/ovs/json.py
index f8b02d180..67470fcbc 100644
--- a/python/ovs/json.py
+++ b/python/ovs/json.py
@@ -113,7 +113,8 @@ def from_string(s):
try:
s = unicode(s, 'utf-8')
except UnicodeDecodeError, e:
- seq = ' '.join(["0x%2x" % ord(c) for c in e.object[e.start:e.end]])
+ seq = ' '.join(["0x%2x" % ord(c)
+ for c in e.object[e.start:e.end] if ord(c) >= 0x80])
return ("not a valid UTF-8 string: invalid UTF-8 sequence %s" % seq)
p = Parser(check_trailer=True)
p.feed(s)
--
2.47.0