<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN"
"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head><meta http-equiv="content-type" content="text/html; charset=utf-8" /><style type="text/css"><!--
#msg dl { border: 1px #006 solid; background: #369; padding: 6px; color: #fff; }
#msg dt { float: left; width: 6em; font-weight: bold; }
#msg dt:after { content:':';}
#msg dl, #msg dt, #msg ul, #msg li, #header, #footer { font-family: verdana,arial,helvetica,sans-serif; font-size: 10pt; }
#msg dl a { font-weight: bold}
#msg dl a:link { color:#fc3; }
#msg dl a:active { color:#ff0; }
#msg dl a:visited { color:#cc6; }
h3 { font-family: verdana,arial,helvetica,sans-serif; font-size: 10pt; font-weight: bold; }
#msg pre, #msg p { overflow: auto; background: #ffc; border: 1px #fc0 solid; padding: 6px; }
#msg ul { overflow: auto; }
#header, #footer { color: #fff; background: #636; border: 1px #300 solid; padding: 6px; }
#patch { width: 100%; }
#patch h4 {font-family: verdana,arial,helvetica,sans-serif;font-size:10pt;padding:8px;background:#369;color:#fff;margin:0;}
#patch .propset h4, #patch .binary h4 {margin:0;}
#patch pre {padding:0;line-height:1.2em;margin:0;}
#patch .diff {width:100%;background:#eee;padding: 0 0 10px 0;overflow:auto;}
#patch .propset .diff, #patch .binary .diff {padding:10px 0;}
#patch span {display:block;padding:0 10px;}
#patch .modfile, #patch .addfile, #patch .delfile, #patch .propset, #patch .binary, #patch .copfile {border:1px solid #ccc;margin:10px 0;}
#patch ins {background:#dfd;text-decoration:none;display:block;padding:0 10px;}
#patch del {background:#fdd;text-decoration:none;display:block;padding:0 10px;}
#patch .lines, .info {color:#888;background:#fff;}
--></style>
<title>[617] trunk/solr/conf/schema.xml:
Changes to schema to strip HTML tags from fields before indexing,
and to change how accent stripping is handled</title>
</head>
<body>
<div id="msg">
<dl>
<dt>Revision</dt> <dd>617</dd>
<dt>Author</dt> <dd>haschart</dd>
<dt>Date</dt> <dd>2008-07-03 13:43:12 -0400 (Thu, 03 Jul 2008)</dd>
</dl>
<h3>Log Message</h3>
<pre>Changes to schema to strip HTML tags from fields before indexing, and to change how accent stripping is handled</pre>
<h3>Modified Paths</h3>
<ul>
<li><a href="#trunksolrconfschemaxml">trunk/solr/conf/schema.xml</a></li>
</ul>
</div>
<div id="patch">
<h3>Diff</h3>
<a id="trunksolrconfschemaxml"></a>
<div class="modfile"><h4>Modified: trunk/solr/conf/schema.xml (616 => 617)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/solr/conf/schema.xml 2008-07-03 16:32:26 UTC (rev 616)
+++ trunk/solr/conf/schema.xml 2008-07-03 17:43:12 UTC (rev 617)
</span><span class="lines">@@ -50,9 +50,8 @@
</span><span class="cx">
</span><span class="cx"> <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
</span><span class="cx"> <analyzer type="index">
</span><del>- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="schema.UnicodeNormalizationFilterFactory"/>
- <filter class="solr.ISOLatin1AccentFilterFactory"/>
</del><ins>+ <tokenizer class="solr.HTMLStripWhitespaceTokenizerFactory"/>
+ <filter class="schema.UnicodeNormalizationFilterFactory" version="icu4j" composed="false" remove_diacritics="true" remove_modifiers="true" fold="true"/>
</ins><span class="cx"> <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
</span><span class="cx"> <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
</span><span class="cx"> <filter class="solr.LowerCaseFilterFactory"/>
</span><span class="lines">@@ -61,8 +60,7 @@
</span><span class="cx"> </analyzer>
</span><span class="cx"> <analyzer type="query">
</span><span class="cx"> <tokenizer class="solr.WhitespaceTokenizerFactory"/>
</span><del>- <filter class="schema.UnicodeNormalizationFilterFactory"/>
- <filter class="solr.ISOLatin1AccentFilterFactory"/>
</del><ins>+ <filter class="schema.UnicodeNormalizationFilterFactory" version="icu4j" composed="false" remove_diacritics="true" remove_modifiers="true" fold="true"/>
</ins><span class="cx"> <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
</span><span class="cx"> <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
</span><span class="cx"> <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
</span><span class="lines">@@ -100,12 +98,14 @@
</span><span class="cx"> <fieldType name="spellText" class="solr.TextField" positionIncrementGap="100">
</span><span class="cx"> <analyzer type="index">
</span><span class="cx"> <tokenizer class="solr.StandardTokenizerFactory"/>
</span><ins>+ <filter class="schema.UnicodeNormalizationFilterFactory" version="icu4j" composed="false" remove_diacritics="true" remove_modifiers="true" fold="true"/>
</ins><span class="cx"> <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
</span><span class="cx"> <filter class="solr.StandardFilterFactory"/>
</span><span class="cx"> <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</span><span class="cx"> </analyzer>
</span><span class="cx"> <analyzer type="query">
</span><span class="cx"> <tokenizer class="solr.StandardTokenizerFactory"/>
</span><ins>+ <filter class="schema.UnicodeNormalizationFilterFactory" version="icu4j" composed="false" remove_diacritics="true" remove_modifiers="true" fold="true"/>
</ins><span class="cx"> <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
</span><span class="cx"> <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
</span><span class="cx"> <filter class="solr.StandardFilterFactory"/>
</span></span></pre>
</div>
</div>
</body>
</html>