litvinovg/vitro
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

NIHVIVO-2459 Tokenized, stemmed autocomplete search

Browse source
This commit is contained in:
ryounes 2011-06-28 19:18:03 +00:00
parent 2bf3e20cd8
commit 997b3ef2cd
4 changed files with 64 additions and 39 deletions
Download patch file Download diff file Expand all files Collapse all files

31
solr/exampleSolr/conf/schema.xml
View file

@ -479,6 +479,35 @@
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
</analyzer>
</fieldtype>
<!-- Commenting this fieldtype out for now because we have no use case for
a tokenized, unstemmed autocomplete field. Identical to edgengram_stemmed but without
the stemming.
<fieldtype name="edgengram_unstemmed" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<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="1" />
<filter class="solr.LowerCaseFilterFactory" />
<filter class="solr.EdgeNGramFilterFactory" minGramSize="1" maxGramSize="25" side="front"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<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="1" />
<filter class="solr.LowerCaseFilterFactory" />
</analyzer>
</fieldtype>
-->
</types>
@ -529,7 +558,7 @@
<!-- Autocomplete search fields -->
<field name="acNameUntokenized" type="edgengram_untokenized" indexed="true" stored="false" multiValued="true" />
<!-- <field name="acNameTokenized" type="edgengram_tokenized" indexed="true" stored="false" multiValued="true" /> -->
<!-- <field name="acNameUnstemmed" type="edgengram_unstemmed" indexed="true" stored="false" multiValued="true" /> -->
<field name="acNameStemmed" type="edgengram_stemmed" indexed="true" stored="false" multiValued="true" />
<field name="indexedTime" type="long" indexed="true" stored="true"/>