Umich experimental text types for solr

solr_text_types.xml

    <!-- 
      #########################
        TEXT FIELD TYPES
      ######################### 

      In all cases, we want to perform NFKC unicode normalization,
      case folding, and ASCII-folding (i.e., removal of accents so
      ü => u).                                   
      
      ICUFoldingFilterFactory will give us *all* of those things.

      For queries only, we also do synonym expansion

    -->
      
      <!-- text : the basic text type -->
      
      <fieldtype name="text" class="solr.TextField" positionIncrementGap="1000">
        <analyzer type="index">
          <charFilter class="solr.PatternReplaceCharFilterFactory"
            pattern="&amp;" replacement=" and " />
          <tokenizer class="solr.ICUTokenizerFactory"/>
            <filter class="solr.ICUFoldingFilterFactory"/>
            <filter class="solr.SynonymFilterFactory"
                    synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
            <filter class="solr.CJKWidthFilterFactory"/>
            <filter class="solr.CJKBigramFilterFactory" han="true" hiragana="true" 
                    katakana="true" hangul="true" outputUnigrams="true" />        
        </analyzer>
        <analyzer type="query">
          <charFilter class="solr.PatternReplaceCharFilterFactory"
            pattern="&amp;" replacement=" and " />
          <tokenizer class="solr.ICUTokenizerFactory"/>
            <filter class="solr.ICUFoldingFilterFactory"/>
            <filter class="solr.SynonymFilterFactory"
                    synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
            <filter class="solr.CJKWidthFilterFactory"/>
            <filter class="solr.CJKBigramFilterFactory" han="true" hiragana="true" 
                    katakana="true" hangul="true" outputUnigrams="true" />        
        </analyzer>
      </fieldtype> 
      
      
      
            <!-- text_l: text type anchored only on the left,,
           for "starts with" matches. This is the same as text_lr
           but with only the leading anchor
      -->
      

      <fieldtype name="text_l" class="solr.TextField" positionIncrementGap="1000">
        <analyzer type="index">
          <charFilter class="solr.PatternReplaceCharFilterFactory"
            pattern="&amp;" replacement=" and " />
          <charFilter class="solr.PatternReplaceCharFilterFactory"
                pattern="^(.*)$" replacement="AAAA$1" />  
          <tokenizer class="solr.ICUTokenizerFactory"/>
            <filter class="solr.ICUFoldingFilterFactory"/>
            <filter class="solr.SynonymFilterFactory"
                    synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
            <filter class="solr.CJKWidthFilterFactory"/>
            <filter class="solr.CJKBigramFilterFactory" han="true" hiragana="true" 
               katakana="true" hangul="true" outputUnigrams="true" />        
           </analyzer>
        <analyzer type="query">
          <charFilter class="solr.PatternReplaceCharFilterFactory"
            pattern="&amp;" replacement=" and " />
          <charFilter class="solr.PatternReplaceCharFilterFactory"
                pattern="^(.*)$" replacement="AAAA$1" />  
          <tokenizer class="solr.ICUTokenizerFactory"/>
            <filter class="solr.ICUFoldingFilterFactory"/>
            <filter class="solr.SynonymFilterFactory"
                    synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
            <filter class="solr.CJKWidthFilterFactory"/>
            <filter class="solr.CJKBigramFilterFactory" han="true" hiragana="true" 
       katakana="true" hangul="true" outputUnigrams="true" />
        </analyzer>
      </fieldtype>