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

Fixing bug for search terms like McCluskey NIHVIVO-3701

Browse source
This commit is contained in:
briancaruso 2012-06-14 15:51:38 +00:00
parent f7e7bd9998
commit 65ac740cff
2 changed files with 23 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

22
solr/homeDirectoryTemplate/conf/schema.xml
View file

@ -46,16 +46,22 @@
</analyzer>
</fieldType>
<!-- This field intentionally lacks solr.WordDelimiterFilterFactory because of issue NIHVIVO-3332 -->
<fieldType name="text_unstemmed" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.ASCIIFoldingFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
<!-- This field intentionally sets solr.WordDelimiterFilterFactory splitOnCaseChange to 0/false because of issue NIHVIVO-3332 -->
<filter class="solr.WordDelimiterFilterFactory"
generateWordParts="1" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" />
<filter class="solr.ASCIIFoldingFilterFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<!-- Like text, but without synonyms. Good for autocomplete matching of book/grant titles, etc.,
where we want to remove stop words and stem. -->
<fieldType name="text_stemmed" class="solr.TextField" positionIncrementGap="100">
@ -63,7 +69,9 @@
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true"
words="stopwords-name.txt" enablePositionIncrements="true" />
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1" />
<filter class="solr.WordDelimiterFilterFactory"
generateWordParts="1" generateNumberParts="1" catenateWords="0"
catenateNumbers="0" catenateAll="0" splitOnCaseChange="1" />
<filter class="solr.ASCIIFoldingFilterFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
@ -190,8 +198,11 @@
<field name="URI" type="string" indexed="true" stored="true" multiValued="false" omitNorms="true"/>
<field name="nameRaw" type="string" indexed="false" stored="true" 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"/>
<!-- nameText added for NIHVIVO-3701 -->
<field name="nameText" type="text" indexed="true" stored="false" multiValued="true"/>
<field name="nameLowercase" type="lowercase" indexed="true" stored="false" multiValued="true"/>
<!-- A sortable version of nameLowercase -->
<field name="nameLowercaseSingleValued" type="lowercase" indexed="true" stored="false" multiValued="false" omitNorms="true" />
<field name="nameUnstemmed" type="text_unstemmed" indexed="true" stored="false" multiValued="true"/>
@ -237,6 +248,7 @@
<copyField source="nameRaw" dest="acNameUntokenized" />
<copyField source="nameRaw" dest="acNameStemmed" />
<copyField source="nameRaw" dest="nameLowercaseSingleValued" />
<copyField source="nameRaw" dest="nameText" />
<!-- **************************** End Vitro Fields *************************** -->

3
solr/homeDirectoryTemplate/conf/solrconfig.xml
View file

@ -708,7 +708,8 @@
-->
<lst name="defaults">
<str name="defType">edismax</str>
<str name="qf">ALLTEXT ALLTEXTUNSTEMMED nameUnstemmed nameStemmed nameLowercase</str>
<!-- nameText added for NIHVIVO-3701 -->
<str name="qf">ALLTEXT ALLTEXTUNSTEMMED nameText^2.0 nameUnstemmed^2.0 nameStemmed^2.0 nameLowercase</str>
<str name="echoParams">explicit</str>
<str name="qs">2</str>
<int name="rows">10</int>