do not fail indexing invalid utf8

2014-04-06 21:37:32 +02:00 · 2014-04-06 21:37:32 +02:00 · 440980b16a
parent 25438a598a
commit 440980b16a
1 changed files with 2 additions and 1 deletions
--- a/src/pfwbged/basecontent/indexers.py
+++ b/src/pfwbged/basecontent/indexers.py
@ -40,7 +40,8 @@ def document_dynamic_searchable_text_indexer(obj):
                datastream = transforms.convertTo(
                    'text/plain', child.file.data, mimetype=child.file.contentType,
                    filename=child.file.filename)
-                indexed_elements.append(unicode(datastream.getData(), 'utf-8'))
+                indexed_elements.append(unicode(datastream.getData(), 'utf-8',
+                    'ignore'))
            except (ConflictError, KeyboardInterrupt):
                raise