280 lines
15 KiB
XML
280 lines
15 KiB
XML
<?xml version="1.0" encoding="UTF-8" ?>
|
|
<schema name="example" version="1.3">
|
|
|
|
<types>
|
|
<!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
|
|
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
|
|
|
|
<!-- boolean type: "true" or "false" -->
|
|
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
|
|
|
|
<!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
|
|
<fieldtype name="binary" class="solr.BinaryField"/>
|
|
|
|
<fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
|
|
<fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
|
|
<fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
|
|
<fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
|
|
|
|
<fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/>
|
|
<!-- A Trie based date field for faster date range queries and date faceting. -->
|
|
<fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
|
|
|
|
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
|
|
|
|
<fieldType name="text" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<filter class="solr.ASCIIFoldingFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
|
|
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1"
|
|
catenateWords="1" catenateNumbers="1" catenateAll="0"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<filter class="solr.ASCIIFoldingFilterFactory"/>
|
|
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
|
|
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1"
|
|
catenateWords="0" catenateNumbers="0" catenateAll="0"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
|
|
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
|
|
<fieldType name="text_unstemmed" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
|
|
|
<!-- This field intentionally sets solr.WordDelimiterFilterFactory splitOnCaseChange to 0/false because of issue NIHVIVO-3332 -->
|
|
<filter class="solr.WordDelimiterFilterFactory"
|
|
generateWordParts="1" generateNumberParts="1" catenateWords="0"
|
|
catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" />
|
|
<filter class="solr.ASCIIFoldingFilterFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
|
|
<!-- Like text, but without synonyms. Good for autocomplete matching of book/grant titles, etc.,
|
|
where we want to remove stop words and stem. -->
|
|
<fieldType name="text_stemmed" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true"
|
|
words="stopwords-name.txt" enablePositionIncrements="true" />
|
|
<filter class="solr.WordDelimiterFilterFactory"
|
|
generateWordParts="1" generateNumberParts="1" catenateWords="0"
|
|
catenateNumbers="0" catenateAll="0" splitOnCaseChange="1" />
|
|
<filter class="solr.ASCIIFoldingFilterFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
|
|
<!-- A general unstemmed text field - good if one does not know the language of the field -->
|
|
<fieldType name="textgen" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
|
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="0"/>
|
|
<filter class="solr.ASCIIFoldingFilterFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</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="stopwords.txt" enablePositionIncrements="true" />
|
|
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0"/>
|
|
<filter class="solr.ASCIIFoldingFilterFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
|
|
<fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.PhoneticFilterFactory" encoder="Metaphone" inject="false"/>
|
|
</analyzer>
|
|
</fieldtype>
|
|
|
|
<!-- lowercases the entire field value, keeping it as a single token. -->
|
|
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="true" />
|
|
<filter class="solr.ASCIIFoldingFilterFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory" />
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- since fields of this type are by default not stored or indexed,
|
|
any data added to them will be ignored outright. -->
|
|
<fieldtype name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
|
|
|
|
<fieldtype name="edgengram_untokenized" class="solr.TextField">
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory" />
|
|
<filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="25" side="front"/>
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory" />
|
|
</analyzer>
|
|
</fieldtype>
|
|
|
|
<fieldtype name="edgengram_stemmed" class="solr.TextField">
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true"
|
|
words="stopwords-name.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.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
|
|
<filter class="solr.EdgeNGramFilterFactory" minGramSize="1" maxGramSize="25" side="front"/>
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true"
|
|
words="stopwords-name.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.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
|
|
</analyzer>
|
|
</fieldtype>
|
|
|
|
</types>
|
|
|
|
|
|
<fields>
|
|
<!-- Valid attributes for fields:
|
|
name: mandatory - the name for the field
|
|
type: mandatory - the name of a previously defined type from the
|
|
<types> section
|
|
indexed: true if this field should be indexed (searchable or sortable)
|
|
stored: true if this field should be retrievable
|
|
multiValued: true if this field may contain multiple values per document
|
|
omitNorms: (expert) set to true to omit the norms associated with
|
|
this field (this disables length normalization and index-time
|
|
boosting for the field, and saves some memory). Only full-text
|
|
fields or fields that need an index-time boost need norms.
|
|
termVectors: [false] set to true to store the term vector for a
|
|
given field.
|
|
When using MoreLikeThis, fields used for similarity should be
|
|
stored for best performance.
|
|
termPositions: Store position information with the term vector.
|
|
This will increase storage costs.
|
|
termOffsets: Store offset information with the term vector. This
|
|
will increase storage costs.
|
|
default: a value that should be used if no value is specified
|
|
when adding a document.
|
|
-->
|
|
|
|
<!-- **************************** Vitro Fields *************************** -->
|
|
|
|
<field name="DocId" type="string" indexed="true" stored="true" required="true" omitNorms="true"/>
|
|
|
|
<field name="type" type="string" indexed="true" stored="true" omitNorms="true" multiValued="true"/>
|
|
|
|
<field name="classLocalName" type="text" indexed="true" stored="true" multiValued="true"/>
|
|
|
|
<field name="classgroup" type="string" indexed="true" stored="true" multiValued="true"/>
|
|
|
|
<field name="mostSpecificTypeURIs" type="string" indexed="true" stored="true" omitNorms="true" multiValued="true"/>
|
|
|
|
<field name="PROHIBITED_FROM_TEXT_RESULTS" type="string" indexed="true" stored="false" omitNorms="true" multiValued="true"/>
|
|
<field name="URI" type="string" indexed="true" stored="true" multiValued="false" omitNorms="true"/>
|
|
|
|
<field name="nameRaw" type="string" indexed="false" stored="true" multiValued="true"/>
|
|
|
|
<!-- nameText added for NIHVIVO-3701 -->
|
|
<field name="nameText" type="text" indexed="true" stored="false" multiValued="true"/>
|
|
|
|
<field name="nameLowercase" type="lowercase" indexed="true" stored="false" multiValued="true"/>
|
|
<!-- A sortable version of nameLowercase -->
|
|
<field name="nameLowercaseSingleValued" type="lowercase" indexed="true" stored="false" multiValued="false" omitNorms="true" />
|
|
<field name="nameUnstemmed" type="text_unstemmed" indexed="true" stored="false" multiValued="true"/>
|
|
<field name="nameStemmed" type="text_stemmed" indexed="true" stored="false" multiValued="true"/>
|
|
|
|
<!-- Autocomplete search fields -->
|
|
<field name="acNameUntokenized" type="edgengram_untokenized" indexed="true" stored="false" multiValued="true" />
|
|
<field name="acNameStemmed" type="edgengram_stemmed" indexed="true" stored="false" multiValued="true" />
|
|
|
|
<field name="indexedTime" type="long" indexed="true" stored="true"/>
|
|
<field name="NAME_PHONETIC" type ="phonetic" indexed="true" stored="false" multiValued="true"/>
|
|
|
|
<field name="ALLTEXT" type="text" indexed="true" stored="true" multiValued="true"/>
|
|
<field name="ALLTEXTUNSTEMMED" type="textgen" indexed="true" stored="false" multiValued="true"/>
|
|
|
|
<field name="THUMBNAIL" type="string" indexed="true" stored="true"/>
|
|
|
|
<field name="BETA" type="float" indexed="true" stored="true" multiValued="false"/>
|
|
|
|
<!-- field for storing locations of thumbnails -->
|
|
<field name="THUMBNAIL_URL" type="string" indexed="false" stored="true"/>
|
|
|
|
<!-- field for source institution's url -->
|
|
<field name="siteURL" type="string" indexed="true" stored="true"/>
|
|
|
|
<!-- field for source institution's name -->
|
|
<field name="siteName" type="string" indexed="true" stored="true"/>
|
|
|
|
<!-- field for preferred title -->
|
|
<field name="PREFERRED_TITLE" type="string" indexed="true" stored="true"/>
|
|
|
|
<!-- Copy nameRaw into several other fields -->
|
|
<copyField source="nameRaw" dest="nameStemmed" />
|
|
<copyField source="nameRaw" dest="nameUnstemmed" />
|
|
<copyField source="nameRaw" dest="nameLowercase" />
|
|
<copyField source="nameRaw" dest="NAME_PHONETIC" />
|
|
<copyField source="nameRaw" dest="acNameUntokenized" />
|
|
<copyField source="nameRaw" dest="acNameStemmed" />
|
|
<copyField source="nameRaw" dest="nameText" />
|
|
<!-- nameLowercaseSingleValued is not copied from nameRaw becasue nameRaw might have multiple values -->
|
|
|
|
<!-- field for hash signature, used for comparing to versions from external caches -->
|
|
<field name="etag" type="string" stored="true" indexed="false" multiValued="false" />
|
|
|
|
|
|
|
|
<!-- **************************** End Vitro Fields *************************** -->
|
|
<!-- **************************** Dynamic Fields *************************** -->
|
|
<dynamicField name="*_string" type="string" indexed="true" stored="true" multiValued="true"/>
|
|
<!-- **************************** End Dynamic Fields *************************** -->
|
|
|
|
|
|
<field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
|
|
</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>DocId</uniqueKey>
|
|
|
|
<!-- field for the QueryParser to use when an explicit fieldname is absent -->
|
|
<!-- This is now set in solrconfig.xml -->
|
|
<!-- <defaultSearchField>ALLTEXT</defaultSearchField> -->
|
|
|
|
<!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
|
|
<solrQueryParser defaultOperator="AND"/>
|
|
|
|
<!-- Similarity is the scoring routine for each document vs. a query.
|
|
A custom similarity may be specified here, but the default is fine
|
|
for most applications. -->
|
|
<similarity class="org.apache.lucene.search.DefaultSimilarity"/>
|
|
|
|
</schema>
|