solr.Items.conf.schema.xml Maven / Gradle / Ivy
The newest version!
<?xml version="1.0" encoding="utf-8"?>
<schema name="example" version="1.5">
<fields>
<field name="id" type="string" indexed="true" stored="true" required="true"
multiValued="false" />
<!-- SocialSensor fields -->
<field name="streamId" type="string" indexed="true" stored="true" multiValued="false" />
<field name="source" type="string" indexed="true" stored="true" multiValued="false" />
<field name="title" type="text_en" indexed="true" stored="true" multiValued="false" />
<field name="description" type="text_en" indexed="true" stored="true" multiValued="false" />
<field name="tags" type="string" indexed="true" stored="true" multiValued="true" />
<field name="categories" type="string" indexed="true" stored="true" multiValued="true" />
<field name="author" type="string" indexed="true" stored="true" multiValued="false" />
<field name="links" type="string" indexed="false" stored="true" multiValued="true" />
<field name="popularity" type="string" indexed="false" stored="true" multiValued="true" />
<field name="mediaLinks" type="string" indexed="false" stored="true" multiValued="true" />
<field name="publicationTime" type="long" indexed="true" stored="true" multiValued="false" />
<field name="operation" type="string" indexed="true" stored="true" multiValued="false" />
<field name="comments" type="text_en" indexed="true" stored="true" multiValued="false" />
<field name="latitude" type="double" indexed="true" stored="true" multiValued="false" />
<field name="longitude" type="double" indexed="true" stored="true" multiValued="false" />
<field name="location" type="string" indexed="true" stored="true" multiValued="false" />
<field name="text" type="text_en" indexed="true" stored="true" multiValued="true" />
<field name="mediaIds" type="string" indexed="true" stored="true" multiValued="true" />
<field name="dyscoId" type="string" indexed="true" stored="true" multiValued="false" />
<!-- new fields: 27.3.2013 -->
<field name="sentiment" type="int" indexed="true" stored="true" multiValued="false" />
<field name="retweetsCount" type="long" indexed="true" stored="true" multiValued="false" />
<field name="alethiometerScore" type="int" indexed="true" stored="true"
multiValued="false" />
<field name="alethiometerUserScore" type="int" indexed="true" stored="true"
multiValued="false" />
<field name="authorFullName" type="string" indexed="true" stored="true"
multiValued="false" />
<field name="userRole" type="string" indexed="true" stored="true" multiValued="false" />
<field name="followersCount" type="int" indexed="true" stored="true" multiValued="false" />
<field name="friendsCount" type="int" indexed="true" stored="true" multiValued="false" />
<field name="avatarImageSmall" type="string" indexed="true" stored="true"
multiValued="false" />
<field name="avatarImage" type="string" indexed="true" stored="true" multiValued="false" />
<field name="authorScreenName" type="string" indexed="true" stored="true"
multiValued="false" />
<field name="people" type="string" indexed="true" stored="true" multiValued="true" />
<field name="original" type="boolean" indexed="true" stored="true" multiValued="false" />
<field name="validityScore" type="int" indexed="true" stored="true" multiValued="false" />
<field name="validityVotes" type="string" indexed="true" stored="true" multiValued="false" />
<field name="positiveVotes" type="int" indexed="true" stored="true" multiValued="false" />
<field name="negativeVotes" type="int" indexed="true" stored="true" multiValued="false" />
<field name="_version_" type="long" indexed="true" stored="true" />
<!-- newshound list id -->
<field name="lists" type="string" indexed="true" stored="true" multiValued="true" />
<!-- popularity fields -->
<field name="popularityShares" type="long" indexed="true" stored="true" multiValued="false" />
<field name="popularityLikes" type="long" indexed="true" stored="true" multiValued="false" />
<field name="popularityComments" type="long" indexed="true" stored="true" multiValued="false" />
<dynamicField name="attr_*" type="text_general" indexed="true" stored="true"
multiValued="true" />
<dynamicField name="random_*" type="random" />
</fields>
<!-- Field to use to determine and enforce document uniqueness.
Unless this field is marked with required="false", it will be a required field
-->
<uniqueKey>id</uniqueKey>
<copyField source="title" dest="text" />
<types>
<!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
<fieldType name="string" class="solr.StrField" sortMissingLast="true" />
<!-- boolean type: "true" or "false" -->
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" />
<!--
Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
-->
<fieldType name="int" class="solr.TrieIntField" precisionStep="0" positionIncrementGap="0" />
<fieldType name="float" class="solr.TrieFloatField" precisionStep="0"
positionIncrementGap="0" />
<fieldType name="long" class="solr.TrieLongField" precisionStep="0"
positionIncrementGap="0" />
<fieldType name="double" class="solr.TrieDoubleField" precisionStep="0"
positionIncrementGap="0" />
<fieldType name="tint" class="solr.TrieIntField" precisionStep="8"
positionIncrementGap="0" />
<fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8"
positionIncrementGap="0" />
<fieldType name="tlong" class="solr.TrieLongField" precisionStep="8"
positionIncrementGap="0" />
<fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8"
positionIncrementGap="0" />
<fieldType name="date" class="solr.TrieDateField" precisionStep="0"
positionIncrementGap="0" />
<fieldType name="tdate" class="solr.TrieDateField" precisionStep="6"
positionIncrementGap="0" />
<fieldtype name="binary" class="solr.BinaryField" />
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
<!-- A text field that only splits on whitespace for exact matching of words -->
<fieldType name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory" />
</analyzer>
</fieldType>
<!-- A general text field that has reasonable, generic
cross-language defaults: it tokenizes with StandardTokenizer,
removes stop words from case-insensitive "stopwords.txt"
(empty by default), and down cases. At query time only, it
also applies synonyms. -->
<fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory" />
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"
enablePositionIncrements="true" />
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<filter class="solr.LowerCaseFilterFactory" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory" />
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"
enablePositionIncrements="true" />
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true"
expand="true" />
<filter class="solr.LowerCaseFilterFactory" />
</analyzer>
</fieldType>
<!-- A text field with defaults appropriate for English: it
tokenizes with StandardTokenizer, removes English stop words
(lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
finally applies Porter's stemming. The query time analyzer
also applies synonyms from synonyms.txt. -->
<fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory" />
<!-- in this example, we will only use synonyms at query time
<filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
-->
<!-- Case insensitive stop word removal.
add enablePositionIncrements=true in both the index and query
analyzers to leave a 'gap' for more accurate phrase queries.
-->
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"
enablePositionIncrements="true" />
<filter class="solr.LowerCaseFilterFactory" />
<filter class="solr.EnglishPossessiveFilterFactory" />
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt" />
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter class="solr.EnglishMinimalStemFilterFactory"/>
-->
<filter class="solr.PorterStemFilterFactory" />
</analyzer>
<analyzer type="query">
<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.LowerCaseFilterFactory" />
<filter class="solr.EnglishPossessiveFilterFactory" />
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt" />
<!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
<filter class="solr.EnglishMinimalStemFilterFactory"/>
-->
<filter class="solr.PorterStemFilterFactory" />
</analyzer>
</fieldType>
<fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100"
autoGeneratePhraseQueries="true">
<analyzer type="index">
<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.KeywordMarkerFilterFactory" protected="protwords.txt" />
<filter class="solr.PorterStemFilterFactory" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory" />
<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="0" catenateNumbers="0" catenateAll="0"
splitOnCaseChange="1" />
<filter class="solr.LowerCaseFilterFactory" />
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt" />
<filter class="solr.PorterStemFilterFactory" />
</analyzer>
</fieldType>
</types>
</schema>
© 2015 - 2025 Weber Informatics LLC | Privacy Policy