Cleanup for exactish

Author: billdueber

exampledocs/exactish.json

@@ -10,5 +10,9 @@
   {
     "id": "3",
     "title": "Meet the Monkees"
+  },
+  {
+    "id": "4",
+    "title": "Corportate boy bands through the ages"
   }
 ]

ruby/exactish_query.rb

@@ -4,21 +4,21 @@
   'defType' => 'dismax',
   'q' => 'the monkees',
   'qf' => 'title',
-  'pf' => 'title'
+  'pf' => 'title^2'
   },
   {
   'fl' => 'score, *',
   'defType' => 'dismax',
   'q' => 'the monkees',
   'qf' => 'title',
-  'pf' => 'title_exact^10 title'
+  'pf' => 'title_exact^10 title^2'
   },
   {
   'fl' => 'score, *',
   'defType' => 'dismax',
   'q' => 'the monkees',
   'qf' => 'title',
-  'pf' => 'title_exact^10 title_l^3 title'
+  'pf' => 'title_exact^10 title_l^3 title^2'
   }
 
 ]

solr/conf/schema.xml

@@ -103,7 +103,6 @@
            - Synonyms can be put in syn.txt (see sample synonyms.txt file in solr example)
            - Word delimiter splits on CaseChange and numbers (e.g., code4lib).
            - The CJK stuff produces bigrams for those languages
-           - Remove Duplicates does what it says on the tin.
     -->
     <fieldtype name="text" class="solr.TextField" positionIncrementGap="1000">
       <analyzer>
@@ -113,8 +112,6 @@
           <!-- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/> -->
           <filter class="solr.CJKWidthFilterFactory"/>
           <filter class="solr.CJKBigramFilterFactory"/> 
-          <filter class="solr.TrimFilterFactory"/>       
-          <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldtype>
 
@@ -124,32 +121,25 @@
 
     <fieldtype name="text_lr" class="solr.TextField" positionIncrementGap="1000">
       <analyzer>
+        <charFilter class="solr.PatternReplaceCharFilterFactory"
+          pattern="^(.*)$" replacement="AAAA $1 ZZZZ" />       
         <tokenizer class="solr.ICUTokenizerFactory"/>
-          <charFilter class="solr.PatternReplaceCharFilterFactory"
-            pattern="^(.*)$" replacement="AAAA $1 ZZZZ" />       
           <filter class="solr.ICUFoldingFilterFactory"/>
           <filter class="solr.SynonymFilterFactory" synonyms="syn.txt" ignoreCase="true" expand="false"/>
           <filter class="solr.CJKWidthFilterFactory"/>
           <filter class="solr.CJKBigramFilterFactory"/> 
-          <filter class="solr.TrimFilterFactory"/>
-          <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldtype>
 
     <fieldtype name="text_l" class="solr.TextField" positionIncrementGap="1000">
       <analyzer>
+        <charFilter class="solr.PatternReplaceCharFilterFactory"
+          pattern="^(.*)$" replacement="AAAA $1" />       
         <tokenizer class="solr.ICUTokenizerFactory"/>
           <filter class="solr.ICUFoldingFilterFactory"/>
           <filter class="solr.SynonymFilterFactory" synonyms="syn.txt" ignoreCase="true" expand="false"/>
           <filter class="solr.CJKWidthFilterFactory"/>
           <filter class="solr.CJKBigramFilterFactory"/> 
-          <filter class="solr.TrimFilterFactory"/>
-          <filter class="solr.PatternReplaceFilterFactory"
-                    pattern="\p{Z}+" replacement=" "
-          />
-          <charFilter class="solr.PatternReplaceCharFilterFactory"
-            pattern="^(.*)$" replacement="AAAA $1" />       
-          <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
       </analyzer>
     </fieldtype>