schema.xml

<?xml version="1.0" ?>

<schema name="documents" version="1.1">

    <!--
        Fields
    -->

    <field name="id" type="string" indexed="true" stored="true" multiValued="false" />
    <field name="parent_id" type="string" indexed="true" stored="true" multiValued="false" />



    <!-- Document level (parent) Fields -->
    <field name="title" type="text" indexed="true" stored="true" multiValued="false" />
    <field name="path" type="string" indexed="false" stored="true" multiValued="false" />
    <field name="content_type" type="string" indexed="true" stored="true" multiValued="false" />

    <field name="file_binary_base64" type="binary" indexed="false" stored="true" multiValued="false" />
    <field name="file_binary_base64_str" type="string" indexed="false" stored="true" multiValued="false" />

    <!-- Page Level (child) Fields -->
    <field name="content" type="text" indexed="true" stored="true" multiValued="false" />
    <field name="content_ocr" type="ocr" indexed="true" stored="true" multiValued="false" termPayloads="true" termOffsets="true" termPositions="true" termVectors="true" />
    <field name="content_extracted" type="text" indexed="true" stored="true" multiValued="false" />

    <field name="page_number" type="int" indexed="true"  stored="true"  multiValued="false" />
    <field name="page_dimension" type="string" indexed="false" stored="true" multiValued="true" />


    <!--
        Copy fields
    -->

    <!--
        Internal schema configuration settings
    -->
    <!-- Specifically _root_ is used by Parent/Child indexing -->

    <field name="_root_" type="string" indexed="true" stored="false" docValues="false" />

    <!-- SOLR-12519 enforces either use _nest_path_ or parentFilter but not both
    <fieldType name="_nest_path_" class="solr.NestPathField" />
    <field name="_nest_path_" type="_nest_path_"/>
    -->

    <!-- Used by Solr for optimistic concurrency -->
    <field name="_version_" type="long" indexed="true" stored="true"/>

    <dynamicField name="ignored_*" type="ignored" multiValued="true"/>

    <dynamicField name="attr_*" type="text" indexed="true" stored="true" multiValued="true"/>

    <!-- field to use to determine and enforce document uniqueness. -->
    <uniqueKey>id</uniqueKey>


    <!--
        Field Types
    -->

    <!-- since fields of this type are by default not stored or indexed,
     any data added to them will be ignored outright.  -->
    <fieldType name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />

    <!-- OCR Payloads -->
    <fieldType name="ocr" stored="false" indexed="true" class="solr.TextField">
      <analyzer>
        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
        <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="com.o19s.payloads.Base64Encoder" />
        <!-- The payload buffer works around WDF removing payloads from tokens by copying and replacing later in the chain -->
        <filter class="com.o19s.payloads.filter.PayloadBufferFilterFactory" />
        <filter class="solr.LowerCaseFilterFactory" />
        <filter class="solr.WordDelimiterFilterFactory" />
        <filter class="solr.KStemFilterFactory" />
        <filter class="com.o19s.payloads.filter.PayloadBufferFilterFactory" />
      </analyzer>
    </fieldType>

    <!-- Simple text analysis -->
    <fieldType name="text" class="solr.TextField" positionIncrementGap="100">
      <analyzer type="index">
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.KStemFilterFactory" />
      </analyzer>
      <analyzer type="query">
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.KStemFilterFactory" />
      </analyzer>
    </fieldType>

    <!-- Simple types -->
    <fieldtype name="string" class="solr.StrField"      sortMissingLast="true" omitNorms="true"/>
    <fieldType name="long"   class="solr.TrieLongField" precisionStep="0" positionIncrementGap="0"/>
    <fieldType name="int"    class="solr.TrieIntField"  precisionStep="8" positionIncrementGap="0"/>
    <fieldType name="date"   class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
    <fieldtype name="binary" class="solr.BinaryField"   />

</schema>