Mapping the NPR API schema to a solr index using the Data Import Handler URLDataSource

data-config.xml

<dataConfig>
        <dataSource name="nprapi" type="URLDataSource" encoding="UTF-8" connectionTimeout="5000" readTimeout="10000"/>
        <document>
                <entity name="nprapi"
                        pk="id"
                        url="http://api.npr.org/query?numResults=20&amp;fields=all&amp;output=nprml&amp;apiKey=[redacted]&amp;startNum=${dataimporter.request.startNum}"
                        processor="XPathEntityProcessor"
                        forEach="/nprml/list/story"
                        transformer="DateFormatTransformer">

                        <field column="id"        xpath="/nprml/list/story/@id" />
                        <field column="link"         xpath="/nprml/list/story/link[@type='html']" />
                        <field column="api"         xpath="/nprml/list/story/link[@type='api']" />
                        <field column="title"        xpath="/nprml/list/story/title" />
                        <field column="description"  xpath="/nprml/list/story/teaser" />
                        <field column="author"      xpath="/nprml/list/story/byline/name" />
                        <field column="organization"      xpath="/nprml/list/story/organization/name" />
                        <field column="subject" xpath="/nprml/list/story/priorityKeywords" />
                        <field column="keywords" xpath="/nprml/list/story/keywords" />
                        <field column="category" xpath="/nprml/list/story/parent[@type='topic']/title" />
                        <field column="category_primary" xpath="/nprml/list/story/parent[@type='primaryTopic']/title" />
                        <field column="related" xpath="/nprml/list/story/relatedLink/link[@type='api']" />
                        <field column="show" xpath="/nprml/list/story/show/program" />
                        <field column="show_slug" xpath="/nprml/list/story/show/program/@code" />

                        <field column="extent" xpath="/nprml/list/story/audio/duration" />
                        <field column="media" xpath="/nprml/list/story/audio/format/mp3" />
                        <field column="thumbnail" xpath="/nprml/list/story/thumbnail/large" />

                        <field column="last_modified" xpath="/nprml/list/story/storyDate" dateTimeFormat="EEE, dd MMM yyyy HH:mm:ss Z" />
                        <field column="transcript" xpath="/nprml/list/story/text/paragraph" />
                </entity>
        </document>
</dataConfig>

schema.xml

<fields>
   <field name="id" type="string" indexed="true" stored="true" required="true" />
   <field name="link" type="string" indexed="true" stored="true"  />
   <field name="api" type="string" indexed="true" stored="true"  />
   <field name="title" type="text" indexed="true" stored="true" required="true" />
   <field name="description" type="text" indexed="true" stored="true"/>
   <field name="last_modified" type="date" indexed="true" stored="true"/>
   <field name="subject" type="string" indexed="true" stored="true"  multiValued="true"/>
   <field name="keywords" type="string" indexed="true" stored="true" multiValued="true"/>
   <field name="category" type="string" indexed="true" stored="true" multiValued="true"/>
   <field name="category_primary" type="string" indexed="true" stored="true" multiValued="true"/>
   <field name="author" type="string" indexed="true" stored="true"/>

   <field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
   <field name="links" type="string" indexed="true" stored="true" multiValued="true"/>
   <field name="related" type="string" indexed="true" stored="true" multiValued="true"/>

   <field name="comments" type="text" indexed="true" stored="true"/>

   <field name="show" type="string" indexed="true" stored="true" />
   <field name="show_slug" type="string" indexed="true" stored="true" />

   <field name="organization" type="string" indexed="true" stored="true" />
   <field name="media" type="string" indexed="true" stored="true" />
   <field name="extent" type="int" indexed="true" stored="true" />

   <field name="transcript" type="text" indexed="true" stored="true" multiValued="true"/>

   <!-- catchall field, containing all other searchable text fields (implemented
        via copyField further on in this schema  -->
   <field name="text" type="text" indexed="true" stored="true" multiValued="true"/>

   <!-- catchall text field that indexes tokens both normally and in reverse for efficient
        leading wildcard queries. -->
   <field name="text_rev" type="text_rev" indexed="true" stored="false" multiValued="true"/>

   <field name="payloads" type="payloads" indexed="true" stored="true"/>

   <!-- Uncommenting the following will create a "timestamp" field using
        a default value of "NOW" to indicate when each document was indexed.
     -->
   <field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
</fields>

<!-- [...] -->

   <copyField source="show" dest="show_t"/>
   <copyField source="subject" dest="keywords"/>
   <copyField source="author" dest="author_t"/>

   <copyField source="payloads" dest="text"/>
   <copyField source="transcript" dest="text" />
   <copyField source="text" dest="text_rev" />