You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ni...@apache.org on 2015/06/02 13:00:22 UTC
svn commit: r1683076 -
/tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml
Author: nick
Date: Tue Jun 2 11:00:22 2015
New Revision: 1683076
URL: http://svn.apache.org/r1683076
Log:
Try to make the low-priority padded PDF magic match more specific, as it looks to have incorrectly triggered on a few of the govdocs text files
Modified:
tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml
Modified: tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml
URL: http://svn.apache.org/viewvc/tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml?rev=1683076&r1=1683075&r2=1683076&view=diff
==============================================================================
--- tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml (original)
+++ tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml Tue Jun 2 11:00:22 2015
@@ -489,7 +489,8 @@
<magic priority="20">
<!-- Low priority match for %PDF near the start of the file -->
<!-- Can trigger false positives, so set the priority rather low here -->
- <match value="%PDF-" type="string" offset="1:512"/>
+ <match value="%PDF-1." type="string" offset="1:512"/>
+ <match value="%PDF-2." type="string" offset="1:512"/>
</magic>
<glob pattern="*.pdf"/>
</mime-type>