diff options
| author | ayleph <ayleph@thisshitistemp.com> | 2015-12-04 02:02:02 -0500 |
|---|---|---|
| committer | Christopher Allan Webber <cwebber@dustycloud.org> | 2015-12-10 11:11:42 -0600 |
| commit | e2b44bd7a7478792be47c98086f5c91d0da283e2 (patch) | |
| tree | e6c78c30c2dc61349874e03e36ed10c116996f99 | |
| parent | fd07dd6da996eca21e82263e55889d28393ba75e (diff) | |
| download | mediagoblin-e2b44bd7a7478792be47c98086f5c91d0da283e2.tar.lz mediagoblin-e2b44bd7a7478792be47c98086f5c91d0da283e2.tar.xz mediagoblin-e2b44bd7a7478792be47c98086f5c91d0da283e2.zip | |
Fix issue 983 PDF UnicodeDecodeError
Parse PDF lines as unicode to prevent UnicodeDecodeError when a
non-ASCII character is encountered.
| -rw-r--r-- | mediagoblin/media_types/pdf/processing.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/mediagoblin/media_types/pdf/processing.py b/mediagoblin/media_types/pdf/processing.py index f6d10a5f..ac4bab6d 100644 --- a/mediagoblin/media_types/pdf/processing.py +++ b/mediagoblin/media_types/pdf/processing.py @@ -207,7 +207,7 @@ def pdf_info(original): _log.debug('pdfinfo could not read the pdf file.') raise BadMediaFail() - lines = [l.decode() for l in lines] + lines = [l.decode('utf-8', 'replace') for l in lines] info_dict = dict([[part.strip() for part in l.strip().split(':', 1)] for l in lines if ':' in l]) |