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

NIHVIVO-2459 Solr field definitions for autocomplete

Browse source
This commit is contained in:
ryounes 2011-05-16 19:16:47 +00:00
parent eac9e5dca1
commit ad98e7723c
7 changed files with 56 additions and 29 deletions
Download patch file Download diff file Expand all files Collapse all files

26
solr/exampleSolr/conf/schema.xml
View file

@ -224,7 +224,7 @@
words="stopwords.txt"
enablePositionIncrements="true"
/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
</analyzer>
@ -242,6 +242,20 @@
</analyzer>
</fieldType>
<!-- Like text, but without synonyms and stemming. Good for autocomplete matching of proper names, where we want to remove
stop words but not stem. -->
<fieldType name="textUnstemmed" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<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>
<!-- Less flexible matching, but less false matches. Probably not ideal for product names,
but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
@ -423,8 +437,6 @@
<!-- **************************** Vitro Fields *************************** -->
<field name="DocId" type="string" indexed="true" stored="true" required="true" />
<field name="type" type="string" indexed="true" stored="true" omitNorms="true" multiValued="true"/>
@ -434,10 +446,10 @@
<field name="PROHIBITED_FROM_TEXT_RESULTS" type="string" indexed="true" stored="false" multiValued="false"/>
<field name="URI" type="string" indexed="true" stored="true" multiValued="false" omitNorms="true"/>
<field name="nameRaw" type="string" indexed="true" stored="true" multiValued="true"/>
<!-- RY Not sure if we need to store nameLowercase -->
<field name="nameLowercase" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="nameUnstemmed" type="text" indexed="true" stored="false" multiValued="true"/>
<field name="nameStemmed" type="text" indexed="true" stored="false" multiValued="true"/>
<!-- RY Not sure if we need to store nameLowercase. Is it ever displayed? -->
<field name="nameLowercase" type="lowercase" indexed="true" stored="true" multiValued="true"/>
<field name="acNameUnstemmed" type="textUnstemmed" indexed="true" stored="false" multiValued="true"/>
<field name="acNameStemmed" type="text" indexed="true" stored="false" multiValued="true"/>
<field name="indexedTime" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="ALLTEXT" type="text" indexed="true" stored="false" multiValued="true"/>
<field name="ALLTEXTUNSTEMMED" type="textgen" indexed="true" stored="false" multiValued="true"/>