You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@jackrabbit.apache.org by ju...@apache.org on 2009/04/08 06:11:15 UTC
svn commit: r762821 - /jackrabbit/trunk/jackrabbit-core/src/main/resources/org/apache/jackrabbit/core/repository.xml

Author: jukka
Date: Tue Apr  7 15:34:17 2009
New Revision: 762821

URL: http://svn.apache.org/viewvc?rev=762821&view=rev
Log:
JCR-1878: Use Apache Tika for text extraction

The default textFilterClasses settings is now very powerful, so no need to have explicit configuration in the default repository.xml.

Modified:
    jackrabbit/trunk/jackrabbit-core/src/main/resources/org/apache/jackrabbit/core/repository.xml

Modified: jackrabbit/trunk/jackrabbit-core/src/main/resources/org/apache/jackrabbit/core/repository.xml
URL: http://svn.apache.org/viewvc/jackrabbit/trunk/jackrabbit-core/src/main/resources/org/apache/jackrabbit/core/repository.xml?rev=762821&r1=762820&r2=762821&view=diff
==============================================================================
--- jackrabbit/trunk/jackrabbit-core/src/main/resources/org/apache/jackrabbit/core/repository.xml (original)
+++ jackrabbit/trunk/jackrabbit-core/src/main/resources/org/apache/jackrabbit/core/repository.xml Tue Apr  7 15:34:17 2009
@@ -98,7 +98,6 @@
         -->
         <SearchIndex class="org.apache.jackrabbit.core.query.lucene.SearchIndex">
             <param name="path" value="${wsp.home}/index"/>
-            <param name="textFilterClasses" value="org.apache.jackrabbit.extractor.PlainTextExtractor,org.apache.jackrabbit.extractor.MsWordTextExtractor,org.apache.jackrabbit.extractor.MsExcelTextExtractor,org.apache.jackrabbit.extractor.MsPowerPointTextExtractor,org.apache.jackrabbit.extractor.PdfTextExtractor,org.apache.jackrabbit.extractor.OpenOfficeTextExtractor,org.apache.jackrabbit.extractor.RTFTextExtractor,org.apache.jackrabbit.extractor.HTMLTextExtractor,org.apache.jackrabbit.extractor.XMLTextExtractor"/>
             <param name="extractorPoolSize" value="2"/>
             <param name="supportHighlighting" value="true"/>
         </SearchIndex>
@@ -134,7 +133,6 @@
     -->
     <SearchIndex class="org.apache.jackrabbit.core.query.lucene.SearchIndex">
         <param name="path" value="${rep.home}/repository/index"/>
-        <param name="textFilterClasses" value="org.apache.jackrabbit.extractor.PlainTextExtractor,org.apache.jackrabbit.extractor.MsWordTextExtractor,org.apache.jackrabbit.extractor.MsExcelTextExtractor,org.apache.jackrabbit.extractor.MsPowerPointTextExtractor,org.apache.jackrabbit.extractor.PdfTextExtractor,org.apache.jackrabbit.extractor.OpenOfficeTextExtractor,org.apache.jackrabbit.extractor.RTFTextExtractor,org.apache.jackrabbit.extractor.HTMLTextExtractor,org.apache.jackrabbit.extractor.XMLTextExtractor"/>
         <param name="extractorPoolSize" value="2"/>
         <param name="supportHighlighting" value="true"/>
     </SearchIndex>