You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by ko...@apache.org on 2010/06/03 12:51:46 UTC
svn commit: r950950 -
/lucene/dev/trunk/solr/example/example-DIH/solr/rss/conf/schema.xml
Author: koji
Date: Thu Jun 3 10:51:46 2010
New Revision: 950950
URL: http://svn.apache.org/viewvc?rev=950950&view=rev
Log:
use HTMLStripCharFilterFactory instead of HTMLStripStandardTokenizerFactory in example-DIH schema
Modified:
lucene/dev/trunk/solr/example/example-DIH/solr/rss/conf/schema.xml
Modified: lucene/dev/trunk/solr/example/example-DIH/solr/rss/conf/schema.xml
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/solr/example/example-DIH/solr/rss/conf/schema.xml?rev=950950&r1=950949&r2=950950&view=diff
==============================================================================
--- lucene/dev/trunk/solr/example/example-DIH/solr/rss/conf/schema.xml (original)
+++ lucene/dev/trunk/solr/example/example-DIH/solr/rss/conf/schema.xml Thu Jun 3 10:51:46 2010
@@ -239,7 +239,8 @@
<fieldtype name="html" stored="true" indexed="true" class="solr.TextField">
<analyzer type="index">
- <tokenizer class="solr.HTMLStripStandardTokenizerFactory"/>
+ <charFilter class="solr.HTMLStripCharFilterFactory"/>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
@@ -251,7 +252,8 @@
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
<analyzer type="query">
- <tokenizer class="solr.HTMLStripStandardTokenizerFactory"/>
+ <charFilter class="solr.HTMLStripCharFilterFactory"/>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>