Solr Places Schema

schema.xml

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

<!-- 
	This is the schema for places (to be used for autocomplete)
	Here are some more reference links:
		https://github.com/wikimedia/mediawiki-extensions-WikibaseSolr/blob/master/schema.solr4.xml
-->

<schema name="places.solr.schema" version="1.5">
	<types>
		<!-- Plain text -->
		<fieldType name="string" class="solr.StrField" sortMissingLast="true" positionIncrementGap="100" />
		<fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="100" />
		<fieldType name="long" class="solr.TrieFloatField" precisionStep="0" positionIncrementGap="0" />
		<fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" positionIncrementGap="0" />

		<!-- States and countries have a lot of synonyms and act a little different -->
		<fieldtype name="text_edge" class="solr.TextField" positionIncrementGap="100">
			<!-- Analyzer to use when indexing a field of this type -->
			<analyzer type="index">
				<tokenizer class="solr.KeywordTokenizerFactory"/>
				<filter class="solr.LowerCaseFilterFactory"/>
				<filter class="solr.EdgeNGramFilterFactory" minGramSize="3" maxGramSize="25" />
			</analyzer>

			<!-- Analyzer to use when matching against field of this type -->
			<analyzer type="query">
				<tokenizer class="solr.KeywordTokenizerFactory" />
				<filter class="solr.LowerCaseFilterFactory" />
			</analyzer>
		</fieldtype>

		<!-- Text, like paragraphs and posts -->
		<fieldtype name="text" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false" omitTermFreqAndPositions="false" omitPositions="false">
			<!-- Analyzer to use when indexing a field of this type -->
			<analyzer type="index">
				<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
				<tokenizer class="solr.WhitespaceTokenizerFactory"/>
				<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt" enablePositionIncrements="true"/>
				<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
				<filter class="solr.LowerCaseFilterFactory"/>
				<filter class="solr.EnglishPossessiveFilterFactory"/>
				<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
				<filter class="solr.PorterStemFilterFactory"/>
				<filter class="solr.PhoneticFilterFactory" encoder="DoubleMetaphone" inject="true"/>
				<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
			</analyzer>
			<analyzer type="query">
				<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
				<tokenizer class="solr.StandardTokenizerFactory"/>
				<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
				<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt" enablePositionIncrements="true"/>
				<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
				<filter class="solr.LowerCaseFilterFactory"/>
				<filter class="solr.EnglishPossessiveFilterFactory"/>
				<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
				<filter class="solr.PorterStemFilterFactory"/>
				<filter class="solr.PhoneticFilterFactory" encoder="DoubleMetaphone" inject="true"/>
				<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
			</analyzer>
		</fieldtype>

		<!-- 
			Only available in Solr 4
			@link http://wiki.apache.org/solr/SpatialSearch
		 -->
		<fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
	</types>

	<fields>
		<!-- The document version (only used for Solr) -->
		<field name="_version_" type="long" indexed="true" stored="true" multiValued="false" />
		<field name="doc_id" type="int" indexed="true" stored="true" required="true" multiValued="false" />

		<!-- Location -->
			<!-- facility.PointLocation -->
			<field name="location" type="location" indexed="true" stored="true" required="false" multiValued="false" />
			<dynamicField name="*_coordinate" type="double" indexed="true" stored="false"/>
			<!-- facility.PostalCode -->
			<field name="postal_code" type="string" indexed="true" stored="true" required="false" multiValued="false" />
			<!-- town.TownId -->
			<field name="town_id" type="int" indexed="true" stored="true" required="false" multiValued="false" />
			<!-- town.ItemName -->
			<field name="town" type="text_edge" indexed="true" stored="true" required="false" multiValued="false" omitTermFreqAndPositions="true" />
			<!-- state.StateId -->
			<field name="state_id" type="int" indexed="true" stored="true" required="false" multiValued="false" />
			<!-- state.ItemName -->
			<field name="state" type="text_edge" indexed="true" stored="true" required="false" multiValued="false" omitNorms="true" omitTermFreqAndPositions="true" />
			<!-- state.StateCode -->
			<field name="state_code" type="string" indexed="true" stored="true" required="false" multiValued="false" />
			<!-- country.CountryId -->
			<field name="country_id" type="int" indexed="true" stored="true" required="false" multiValued="false" />
			<!-- country.ItemName -->
			<field name="country" type="text_edge" indexed="true" stored="true" required="false" multiValued="false" omitTermFreqAndPositions="true" />
			<!-- country.StateeCode -->
			<field name="country_code" type="string" indexed="true" stored="true" required="false" multiValued="false" />
		<!-- End Location -->

		<!-- Catch All -->
			<!-- Contains all of the text fields -->
			<field name="catchall" type="text" indexed="true" stored="true" required="false" multiValued="true" />
		<!-- End Catch All -->
	</fields>

	<uniqueKey>doc_id</uniqueKey>

	<!-- Catch all of the fields in to one for searching -->
	<copyField source="*" dest="catchall" />

	<solrQueryParser defaultOperator="OR" />
</schema>