SOLR Query

managed-schema field definition

    <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
    <field name="_version_" type="long" indexed="true" stored="true"/>
    <field name="_root_" type="string" indexed="true" stored="false"/>
    <field name="_text_" type="text_autophrase" indexed="true" stored="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
    <field name="content" type="text_autophrase" indexed="true" stored="true" multiValued="true" termVectors="true" termPositions="true" termOffsets="true"/>
    <field name="entity_name" type="text_autophrase" indexed="true" stored="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
    <field name="entity_type" type="text_general" indexed="true" stored="true" multiValued="false" termVectors="true" termPositions="true" termOffsets="true"/>
    <field name="entity_date" type="tdate" indexed="true" stored="true" multiValued="false"/>
    <field name="entity_sort" type="int" indexed="true" stored="true" multiValued="false"/>
    <field name="entity_author" type="text_general" indexed="true" stored="true" multiValued="false"/>
    <field name="content_exact" type="text_autophrase_exact" indexed="true" stored="false" multiValued="true"/>
    <field name="entity_name_exact" type="text_autophrase_exact" indexed="true" stored="false" multiValued="false"/>
    <copyField source="*" dest="_text_"/>
    <copyField source="entity_name" dest="entity_name_exact"/>
    <copyField source="content" dest="content_exact"/>

managed-schema field type definition

    <fieldType name="text_autophrase" class="solr.TextField" positionIncrementGap="100">
      <analyzer type="index">
        <tokenizer class="solr.WhitespaceTokenizerFactory" />
        <filter class="solr.LowerCaseFilterFactory" />
        <filter class="org.apache.lucene.analysis.autophrase.AutoPhrasingTokenFilterFactory" phrases="autophrases.txt" includeTokens="true" replaceWhitespaceWith="_" /> 
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true" />
        <filter class="solr.NGramFilterFactory" minGramSize="3" maxGramSize="6"/>
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.WhitespaceTokenizerFactory" />
        <filter class="solr.LowerCaseFilterFactory" />
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
      </analyzer>
    </fieldType>

    <fieldType name="text_autophrase_exact" class="solr.TextField" positionIncrementGap="100">
      <analyzer type="index">
        <tokenizer class="solr.WhitespaceTokenizerFactory" />
        <filter class="solr.LowerCaseFilterFactory" />
        <filter class="org.apache.lucene.analysis.autophrase.AutoPhrasingTokenFilterFactory" phrases="autophrases.txt" includeTokens="true" replaceWhitespaceWith="_" /> 
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
        <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true" />
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.WhitespaceTokenizerFactory" />
        <filter class="solr.LowerCaseFilterFactory" />
        <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
      </analyzer>
    </fieldType>

Query

		var SEARCH_URL_PREFIX = "http://localhost:8983/solr/rms_core_dev/autophrase?q="
		var URL = SEARCH_URL_PREFIX + searchTerm + 
		"&q.op=AND
		 &wt=json
		 &defType=dismax
		 &qf=entity_name_exact^10000.0 content_exact^5000.0 entity_name^1000.0 content^500 entity_author
		 &pf=entity_name_exact entity_name content content_exact
		 &bq=(entity_type:company^10000 OR entity_type:insight^7500)
		 &rows=100
		 &fl=*,score
		 &hl=true
		 &hl.useFastVectorHighlighter=true
		 &hl.q=" + searchTerm + "
		 &hl.fl=entity_name content
		 &hl.bs.maxScan=15
		 &hl.snippets=1000
		 &hl.fragsize=50000
		 

My general objective is:

• Support both partial and exact matches (have supported this using ngram for partial, and _exact fields for exact matches
• Weight exact matches as higher than partial matches
• Weight matches in the entity_name (and entity_name_exact) field higher than in the content (and content_exact) field
• Weight matches that have an entity type of company as the highest, weight matches that have an entity_type of insight as second highest.

A few questions:

• My max score is 1.7ish. I'm concerned that my boosting may not be working as I expect if I'm applying boosts (exponents) to a decimal number.
• Are there any suggestions on how to debug highlighter results?