Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- <?xml version="1.0" encoding="UTF-8"?>
- <!-- Solr managed schema - automatically generated - DO NOT EDIT -->
- <schema name="nutch" version="1.5">
- <uniqueKey>id</uniqueKey>
- <defaultSearchField>text</defaultSearchField>
- <solrQueryParser defaultOperator="OR"/>
- <fieldType name="binary" class="solr.BinaryField"/>
- <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
- <fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
- <fieldType name="date" class="solr.TrieDateField" omitNorms="true" positionIncrementGap="0" precisionStep="0"/>
- <fieldType name="double" class="solr.TrieDoubleField" omitNorms="true" positionIncrementGap="0" precisionStep="0"/>
- <fieldType name="float" class="solr.TrieFloatField" omitNorms="true" positionIncrementGap="0" precisionStep="0"/>
- <fieldType name="ignored" class="solr.StrField" indexed="false" stored="false" multiValued="true"/>
- <fieldType name="int" class="solr.TrieIntField" omitNorms="true" positionIncrementGap="0" precisionStep="0"/>
- <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
- <fieldType name="long" class="solr.TrieLongField" omitNorms="true" positionIncrementGap="0" precisionStep="0"/>
- <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.KeywordTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
- <fieldType name="payloads" class="solr.TextField" indexed="true" stored="false">
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
- </analyzer>
- </fieldType>
- <fieldType name="phonetic" class="solr.TextField" indexed="true" stored="false">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
- </analyzer>
- </fieldType>
- <fieldType name="string" class="solr.StrField" omitNorms="true" sortMissingLast="true"/>
- <fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true"/>
- <fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" positionIncrementGap="0" precisionStep="6"/>
- <fieldType name="tdates" class="solr.TrieDateField" positionIncrementGap="0" multiValued="true" precisionStep="6"/>
- <fieldType name="tdouble" class="solr.TrieDoubleField" omitNorms="true" positionIncrementGap="0" precisionStep="8"/>
- <fieldType name="tdoubles" class="solr.TrieDoubleField" positionIncrementGap="0" multiValued="true" precisionStep="8"/>
- <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishPossessiveFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
- <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EnglishPossessiveFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_en_splitting" class="solr.TextField" autoGeneratePhraseQueries="true" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
- <filter class="solr.WordDelimiterFilterFactory" catenateNumbers="1" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="1"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
- <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
- <filter class="solr.WordDelimiterFilterFactory" catenateNumbers="0" generateNumberParts="1" splitOnCaseChange="1" generateWordParts="1" catenateAll="0" catenateWords="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.PorterStemFilterFactory"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_en_splitting_tight" class="solr.TextField" autoGeneratePhraseQueries="true" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" expand="false" ignoreCase="true" synonyms="synonyms.txt"/>
- <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
- <filter class="solr.WordDelimiterFilterFactory" catenateNumbers="1" generateNumberParts="0" generateWordParts="0" catenateAll="0" catenateWords="1"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.EnglishMinimalStemFilterFactory"/>
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
- <filter class="solr.SynonymFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.ReversedWildcardFilterFactory" maxPosQuestion="2" maxFractionAsterisk="0.33" maxPosAsterisk="3" withOriginal="true"/>
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" expand="true" ignoreCase="true" synonyms="synonyms.txt"/>
- <filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
- <fieldType name="text_path" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.PathHierarchyTokenizerFactory"/>
- </analyzer>
- </fieldType>
- <fieldType name="tfloat" class="solr.TrieFloatField" omitNorms="true" positionIncrementGap="0" precisionStep="8"/>
- <fieldType name="tint" class="solr.TrieIntField" omitNorms="true" positionIncrementGap="0" precisionStep="8"/>
- <fieldType name="tlong" class="solr.TrieLongField" omitNorms="true" positionIncrementGap="0" precisionStep="8"/>
- <fieldType name="tlongs" class="solr.TrieLongField" positionIncrementGap="0" multiValued="true" precisionStep="8"/>
- <fieldType name="url" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateNumberParts="1" generateWordParts="1"/>
- </analyzer>
- </fieldType>
- <field name="_version_" type="long" indexed="true" stored="true"/>
- <field name="accRadius" type="int" indexed="true" stored="true"/>
- <field name="anchor" type="text_general" multiValued="true" indexed="true" stored="true"/>
- <field name="author" type="string" indexed="true" stored="true"/>
- <field name="autonSystemNum" type="int" indexed="true" stored="true"/>
- <field name="autonSystemOrg" type="string" indexed="true" stored="true"/>
- <field name="binaryContent" type="binary" indexed="false" stored="true"/>
- <field name="boost" type="float" indexed="false" stored="true"/>
- <field name="cache" type="string" indexed="false" stored="true"/>
- <field name="cc" type="string" multiValued="true" indexed="true" stored="true"/>
- <field name="cityConfidence" type="int" indexed="true" stored="true"/>
- <field name="cityGeoNameId" type="int" indexed="true" stored="true"/>
- <field name="cityName" type="string" indexed="true" stored="true"/>
- <field name="connType" type="string" indexed="true" stored="true"/>
- <field name="content" type="text_en" indexed="true" stored="true"/>
- <field name="contentLength" type="string" indexed="false" stored="true"/>
- <field name="contentName" type="string" indexed="true" stored="true"/>
- <field name="continentCode" type="string" indexed="true" stored="true"/>
- <field name="continentGeoNameId" type="int" indexed="true" stored="true"/>
- <field name="countryConfidence" type="int" indexed="true" stored="true"/>
- <field name="countryGeoNameId" type="int" indexed="true" stored="true"/>
- <field name="countryIsoCode" type="string" indexed="true" stored="true"/>
- <field name="countryName" type="string" indexed="true" stored="true"/>
- <field name="countryType" type="string" indexed="true" stored="true"/>
- <field name="date" type="tdate" indexed="true" stored="true"/>
- <field name="digest" type="string" indexed="false" stored="true"/>
- <field name="domain" type="string" indexed="true" stored="true"/>
- <field name="feed" type="string" indexed="true" stored="true"/>
- <field name="host" type="url" indexed="true" stored="false"/>
- <field name="id" type="string" indexed="true" required="true" stored="true"/>
- <field name="ip" type="string" indexed="true" stored="true"/>
- <field name="isAnonProxy" type="boolean" indexed="true" stored="true"/>
- <field name="isSatelitteProv" type="boolean" indexed="true" stored="true"/>
- <field name="isp" type="string" indexed="true" stored="true"/>
- <field name="lang" type="string" indexed="true" stored="true"/>
- <field name="lastModified" type="date" indexed="true" stored="true"/>
- <field name="latLon" type="string" indexed="true" stored="true"/>
- <field name="location" type="location" indexed="true" stored="true"/>
- <field name="meta_description" type="strings"/>
- <field name="meta_keywords" type="strings"/>
- <field name="metroCode" type="int" indexed="true" stored="true"/>
- <field name="org" type="string" indexed="true" stored="true"/>
- <field name="postalCode" type="string" indexed="true" stored="true"/>
- <field name="postalConfidence" type="int" indexed="true" stored="true"/>
- <field name="publishedDate" type="date" indexed="true" stored="true"/>
- <field name="segment" type="string" indexed="false" stored="true"/>
- <field name="subDivConfidence" type="int" indexed="true" stored="true"/>
- <field name="subDivGeoNameId" type="int" indexed="true" stored="true"/>
- <field name="subDivIsoCode" type="string" indexed="true" stored="true"/>
- <field name="subDivName" type="string" indexed="true" stored="true"/>
- <field name="subcollection" type="string" multiValued="true" indexed="true" stored="true"/>
- <field name="tag" type="string" multiValued="true" indexed="true" stored="true"/>
- <field name="text" type="text_general" multiValued="true" indexed="true" stored="false"/>
- <field name="timeZone" type="string" indexed="true" stored="true"/>
- <field name="title" type="text_en" indexed="true" stored="true"/>
- <field name="tld" type="string" indexed="false" stored="false"/>
- <field name="tstamp" type="date" indexed="false" stored="true"/>
- <field name="type" type="string" multiValued="true" indexed="true" stored="true"/>
- <field name="updatedDate" type="date" indexed="true" stored="true"/>
- <field name="url" type="url" indexed="true" stored="true"/>
- <field name="userType" type="string" indexed="true" stored="true"/>
- <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false"/>
- <copyField source="anchor" dest="text"/>
- <copyField source="author" dest="text"/>
- <copyField source="content" dest="text"/>
- <copyField source="latLon" dest="location"/>
- <copyField source="title" dest="text"/>
- <copyField source="url" dest="text"/>
- </schema>
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement