NIHVIVO-2459 Define edgeNGram field for autocomplete on people names. NIHVIVO-2437 Refactoring in search controllers to remove outdated references to Lucene.

solr/exampleSolr/conf/schema.xml

@@ -258,16 +258,36 @@
 
     <!-- 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>
+    <fieldType name="text_unstemmed" class="solr.TextField" positionIncrementGap="100">
+      <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.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>
+      <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>
     
@@ -443,7 +463,19 @@
     See http://wiki.apache.org/solr/SpatialSearch
    -->
     <fieldtype name="geohash" class="solr.GeoHashField"/>   
- 
+
+    <fieldtype name="edgengram_untokenized" class="solr.TextField">
+      <analyzer type="index">
+        <tokenizer class="solr.KeywordTokenizerFactory"/>       
+        <filter class="solr.LowerCaseFilterFactory" />
+        <filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="25" side="front"/>
+      </analyzer>
+      <analyzer type="query">
+        <tokenizer class="solr.KeywordTokenizerFactory"/>       
+        <filter class="solr.LowerCaseFilterFactory" />
+      </analyzer>      
+    </fieldtype>
+    
  </types>
 
 
@@ -489,8 +521,14 @@
 <field name="nameLowercase" type="lowercase" indexed="true" stored="true" multiValued="true"/>
 <!-- A sortable version of nameLowercase -->
 <field name="nameLowercaseSingleValued" type="lowercase" indexed="true" stored="false" multiValued="false" /> 
-<field name="nameUnstemmed" type="textUnstemmed" indexed="true" stored="false" multiValued="true"/>
-<field name="nameStemmed" type="text" indexed="true" stored="false" multiValued="true"/>
+<field name="nameUnstemmed" type="text_unstemmed" indexed="true" stored="false" multiValued="true"/>
+<field name="nameStemmed" type="text" indexed="true" stored="false" multiValued="true"/>  
+<!-- Untokenized autocomplete on name (suitable for person names) -->
+<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="acNameStemmed" type="edgengram_stemmed" indexed="true" stored="false" multiValued="true" />
+-->
 
 <field name="indexedTime" type="string" indexed="true" stored="true" multiValued="true"/>
 <field name="NAME_PHONETIC" type ="phonetic" indexed="true" stored="false" multiValued="true"/>

solr/exampleSolr/conf/solrconfig.xml

@@ -709,7 +709,7 @@
      <lst name="defaults">
        <str name="defType">edismax</str>
        <str name="qf">nameRaw nameLowercase ALLTEXT ALLTEXTUNSTEMMED ALLTEXT_PHONETIC NAME_PHONETIC nameUnstemmed nameStemmed targetInfo</str>
-       <str name="pf">targetInfo nameStemmed nameUnstemmed</str>
+       <str name="pf">targetInfo</str>
        <str name="echoParams">explicit</str>
        <str name="ps">2</str>
        <str name="qs">2</str>