Ken's schema.xml

schema.xml

<?xml version="1.0" encoding="UTF-8" ?>

<schema name="gios-stuff" version="0.1">

  <fields>
    <!-- Should id be string? -->
    <field name="id" type="string" indexed="true" stored="true" required="true"/>

    <field name="title" type="textgen" indexed="true" stored="true"/>

    <!-- textgen tokenizes at whilespace, will catenate words and split on case change when indexed and queried. 
          So a query for "Augustus DeMorgan" and "Augustus De-Morgan" will both be a match for Augustus De Morgan
    -->
    <field name="author" type="textgen" indexed="true" stored="true"/>
    <field name="author_last_name" type="textgen" indexed="true" stored="true"/>
    <field name="author_first_name" type="textgen" indexed="true" stored="true"/>

    <field name="organization" type="textgen" indexed="true" stored="true"/>

    <field name="publish_date" type="TrieDateField" indexed="true" stored="true"/>

    <field name="body" type="document_body" indexed="true" stored="true"/>
    <!-- document body should use a special type of class solr.TextField so analyzers can be used -->

    <field name="collector" type="textgen" indexed="true" stored="false" multiValued="true"/>
    <!-- collection of all fields; not stored -->
  </fields>

  <!-- may simplify some queries to combine fields into one -->
  <copyField source="title"           dest="collector"/>
  <copyField source="author"          dest="collector"/>
  <copyField source="body"            dest="collector"/>
  <copyField source="organization"    dest="collector"/>

  <!-- custom type for document body -->
  <fieldType name="document_body" class="solr.TextField">
    <analyzer type="index">
      <!-- sample; Tokenization and filtering can happen during indexing
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      <filter class="solr.KeepWordFilterFactory" words="keepwords.txt"/>
      <filter class="solr.SynonymFilterFactory" synonyms="syns.txt"/>
      -->
    </analyzer>
    <analyzer type="query">
      <!-- sample; Tokenization and filtering can happen during querying
      <tokenizer class="solr.StandardTokenizerFactory"/>
      <filter class="solr.LowerCaseFilterFactory"/>
      -->
    </analyzer>
  </fieldType>
</schema>