From 4a8e4d246a96e063a068ffda5c0a649c29c963a0 Mon Sep 17 00:00:00 2001
From: Yonik Seeley <yonik@apache.org>
Date: Sun, 15 May 2011 16:20:28 +0000
Subject: [PATCH] example: first attempt at *_nwd, non-whitespace-delimited
 field type

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1103444 13f79535-47bb-0310-9956-ffa450edef68
---
 solr/example/solr/conf/schema.xml | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/solr/example/solr/conf/schema.xml b/solr/example/solr/conf/schema.xml
index 7b23135365a..7e4a51b7ff3 100755
--- a/solr/example/solr/conf/schema.xml
+++ b/solr/example/solr/conf/schema.xml
@@ -274,6 +274,16 @@
       </analyzer>
     </fieldType>
 
+    <!-- A general unstemmed text field that is better for non whitespace delimited languanges (nwd) due to autoGeneratePhraseQueries=false -->
+    <fieldType name="text_nwd" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false"> >
+      <analyzer>
+        <tokenizer class="solr.StandardTokenizerFactory"/>
+        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
+        <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
+
 
     <!-- A general unstemmed text field that indexes tokens normally and also
          reversed (via ReversedWildcardFilterFactory), to enable more efficient 
@@ -523,6 +533,8 @@
    <dynamicField name="*_td" type="tdouble" indexed="true"  stored="true"/>
    <dynamicField name="*_tdt" type="tdate"  indexed="true"  stored="true"/>
 
+   <dynamicField name="*_nwd" type="text_nwd" indexed="true"  stored="true"/>
+
    <dynamicField name="*_pi"  type="pint"    indexed="true"  stored="true"/>
 
    <dynamicField name="ignored_*" type="ignored" multiValued="true"/>