Skip to content

Instantly share code, notes, and snippets.

@AlJohri
Last active August 29, 2015 13:56
Show Gist options
  • Save AlJohri/9154945 to your computer and use it in GitHub Desktop.
Save AlJohri/9154945 to your computer and use it in GitHub Desktop.
<fields>
<field name="slug" type="string" indexed="true" stored="true" required="true" />
<field name="congress" type="string" indexed="true" stored="true" required="true" />
<field name="session" type="string" indexed="true" stored="true" required="true" />
<field name="bill" type="string" indexed="true" stored="true" required="false" multiValued="true" />
<field name="year" type="string" indexed="true" stored="true" required="true" />
<field name="month" type="string" indexed="true" stored="true" required="true" />
<field name="day" type="string" indexed="true" stored="true" required="true" />
<field name="year_month" type="string" indexed="true" stored="true" required="true" />
<field name="id" type="string" indexed="true" stored="true" required="true" />
<field name="page_id" type="string" indexed="true" stored="true" required="true" />
<field name="crdoc" type="string" indexed="true" stored="true" required="true" />
<field name="volume" type="int" indexed="true" stored="true" required="true" />
<field name="number" type="int" indexed="true" stored="true" required="true" />
<field name="date" type="date" indexed="true" stored="true" required="true" />
<field name="chamber" type="string" indexed="true" stored="false" required="true" />
<field name="pages" type="string" indexed="true" stored="true" required="true" />
<field name="document_title" type="CRtext" indexed="true" stored="true" required="false" />
<field name="rollcall" type="CRtext" indexed="true" stored="true" required="false" />
<!-- speaker info -->
<field name="speaker_raw" type="string" indexed="false" stored="true" required="true" />
<field name="speaker_state" type="string" indexed="true" stored="true" required="false" />
<field name="speaker_party" type="string" indexed="true" stored="true" required="false" />
<field name="speaker_bioguide" type="string" indexed="true" stored="true" required="false" />
<field name="speaker_firstname" type="string" indexed="true" stored="true" required="false" />
<field name="speaker_middlename" type="string" indexed="true" stored="true" required="false" />
<field name="speaker_lastname" type="string" indexed="true" stored="true" required="false" />
<field name="speaker_title" type="string" indexed="true" stored="true" required="false" />
<field name="speaker_district" type="string" indexed="true" stored="true" required="false" />
<!-- the dummy field has the same value in every document, and is used
to anchor searches when we want to facet on "all" since wildcard
searches for * are not allowed in solr -->
<field name="dummy" type="CRtext" indexed="true" stored="false" required="false" multiValued="true"/>
<!-- multivalued fields -->
<field name="title" type="CRtext" indexed="true" stored="true" required="false" multiValued="true" />
<field name="speaking" type="CRtext" indexed="true" stored="true" required="false" multiValued="true"/>
<field name="quote" type="CRtext" indexed="true" stored="true" required="false" multiValued="true"/>
<field name="longquote" type="CRtext" indexed="true" stored="true" required="false" multiValued="true"/>
<!-- this is a destination for the copy field which stores the speaker
first name, last name and bioguide ID to enable simpler searching
speaker field has to be multi valued even though there is only one speaker per
document because it is a copy field for multiple fields in the
document -->
<field name="speaker" type="CRtext_multivalued" indexed="true" stored="false" required="false" multiValued="true"/>
<!-- text is a copy field for both the speaking and quote fields. it is
indexed as normal with stop words removed and case normalized-->
<field name="text" type="CRtext" indexed="true" stored="false" required="false" multiValued="true"/>
<!-- ngrams is a field for ngrams to be indexed. ngrams is configurable but
the field is defined to index up to n=5. -->
<field name="unigrams" type="unigrams" indexed="true" stored="false" required="false" multiValued="true"/>
<field name="unigrams_stemmed" type="unigrams_stemmed" indexed="true" stored="false" required="false" multiValued="true"/>
<field name="bigrams" type="bigrams" indexed="true" stored="false" required="false" multiValued="true"/>
<field name="trigrams" type="trigrams" indexed="true" stored="false" required="false" multiValued="true"/>
<field name="quadgrams" type="quadgrams" indexed="true" stored="false" required="false" multiValued="true"/>
<field name="pentagrams" type="pentagrams" indexed="true" stored="false" required="false" multiValued="true"/>
<!--
to be implemented...
<field name="vote" type="" indexed="true" stored="true" required="false" multiValued="true"/>
<field name="time" type="" indexed="true" stored="true" required="false" multiValued="true"/>
-->
<!-- A timestamp field with a default value of "NOW" to indicate when
each document was indexed. -->
<field name="ingestdate" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
<field name="_version_" type="long" indexed="true" stored="true"/>
</fields>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment