[Reproducible-commits] [debbindiff] 01/01: Decode msgunfmt output using actual PO charset

[Jérémy Bobbio]

This is an automated email from the git hooks/post-receive script.

lunar pushed a commit to branch master
in repository debbindiff.

commit 112bd5e8a611d92bb5c2d8ee4ee8ae3412eb5051
Author: Jérémy Bobbio <lunar at debian.org>
Date:   Sun Mar 29 14:46:53 2015 +0200

    Decode msgunfmt output using actual PO charset
---
 debbindiff/comparators/gettext.py | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/debbindiff/comparators/gettext.py b/debbindiff/comparators/gettext.py
index 26a20e5..5e803eb 100644
--- a/debbindiff/comparators/gettext.py
+++ b/debbindiff/comparators/gettext.py
@@ -17,15 +17,24 @@
 # You should have received a copy of the GNU General Public License
 # along with debbindiff.  If not, see <http://www.gnu.org/licenses/>.
 
+import re
 import subprocess
 from debbindiff import tool_required
 from debbindiff.comparators.utils import binary_fallback
 from debbindiff.difference import Difference
+from debbindiff import logger
 
 
 @tool_required('msgunfmt')
 def msgunfmt(path):
-    return subprocess.check_output(['msgunfmt', path], shell=False).decode('utf-8')
+    output = subprocess.check_output(['msgunfmt', path], shell=False)
+    found = re.search(r'^"Content-Type: [^;]+; charset=([^\\]+)\\n"$', output, re.MULTILINE)
+    if found:
+        encoding = found.group(1)
+    else:
+        logger.debug('unable to determine PO encoding, falling back to utf-8')
+        encoding = 'utf-8'
+    return output.decode(encoding)
 
 
 @binary_fallback

-- 
Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/reproducible/debbindiff.git