<?xml version="1.0" ?>
<!--
THE OFFICIAL DataONE Index Solr Schema definition file.
This schema is copied into the dataone-cn-index buildout for deployment on cn nodes.
The Solr schema file. This file should be named "schema.xml" and
should be in the conf directory under the solr home
(i.e. ./solr/conf/schema.xml by default)
or located where the classloader for the Solr webapp can find it.
For more information, on how to customize this file, please see...
http://wiki.apache.org/solr/SchemaXml
-->
<schema name="dataone" version="1.1">
<types>
<!-- field type definitions. The "name" attribute is
just a label to be used by field definitions. The "class"
attribute and any other attributes determine the real
behavior of the fieldtype. -->
<!-- The StringField 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"/>
<!-- The optional sortMissingLast and sortMissingFirst attributes are
currently supported on types that are sorted internally as a strings.
- If sortMissingLast="true" then a sort on this field will cause documents
without the field to come after documents with the field,
regardless of the requested sort order (asc or desc).
- If sortMissingFirst="true" then a sort on this field will cause documents
without the field to come before documents with the field,
regardless of the requested sort order.
- If sortMissingLast="false" and sortMissingFirst="false" (the default),
then default lucene sorting will be used which places docs without the field
first in an ascending sort and last in a descending sort.
-->
<!-- numeric field types that store and index the text
value verbatim (and hence don't support range queries since the
lexicographic ordering isn't equal to the numeric ordering) -->
<fieldtype name="integer" class="solr.IntField"/>
<fieldtype name="long" class="solr.LongField"/>
<fieldtype name="float" class="solr.FloatField"/>
<fieldtype name="double" class="solr.DoubleField"/>
<!-- Numeric field types that manipulate the value into
a string value that isn't human readable in it's internal form,
but with a lexicographic ordering the same as the numeric ordering
so that range queries correctly work. -->
<fieldtype name="sint" class="solr.SortableIntField" sortMissingLast="true"/>
<fieldtype name="slong" class="solr.SortableLongField" sortMissingLast="true"/>
<fieldtype name="sfloat" class="solr.SortableFloatField" sortMissingLast="true"/>
<fieldtype name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true"/>
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
is a more restricted form of the canonical representation of dateTime
http://www.w3.org/TR/xmlschema-2/#dateTime
The trailing "Z" designates UTC time and is mandatory.
Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
All other components are mandatory. -->
<fieldtype name="date" class="solr.DateField" sortMissingLast="true"/>
<!-- solr.TextField allows the specification of custom text analyzers
specified as a tokenizer and a list of token filters. Different
analyzers may be specified for indexing and querying.
The optional positionIncrementGap puts space between multiple fields of
this type on the same document, with the purpose of preventing false phrase
matching across fields.
For more info on customizing your analyzer chain, please see...
http://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters
-->
<!-- Standard analyzer commonly used by Lucene developers
-->
<!-- Standard analyzer commonly used by Lucene developers -->
<!--
<fieldtype name="text_lu" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StandardFilterFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory"/>
<filter class="solr.EnglishPorterFilterFactory"/>
</analyzer>
</fieldtype>
-->
<!-- One could also specify an existing Analyzer implementation in Java
via the class attribute on the analyzer element:
<fieldtype name="text_lu" class="solr.TextField">
<analyzer class="org.apache.lucene.analysis.snowball.SnowballAnalyzer"/>
</fieldType>
-->
<!-- A text field that only splits on whitespace for more exact matching -->
<fieldtype name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldtype>
<fieldtype name="text" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.WordDelimiterFilterFactory"
generateWordParts="1"
catenateWords="1"
generateNumberParts="1"
splitOnNumerics="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" />
<filter class="solr.PorterStemFilterFactory" />
<filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.WordDelimiterFilterFactory"
generateWordParts="1"
catenateWords="0"
generateNumberParts="1"
splitOnNumerics="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory"/>
<filter class="solr.PorterStemFilterFactory" />
</analyzer>
</fieldtype>
<fieldtype name="text_no_token" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory"/>
</analyzer>
</fieldtype>
<!--
<fieldtype name="text_all" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
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.StopFilterFactory" ignoreCase="true"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1"
catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
</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"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1"
catenateWords="0" catenateNumbers="0" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
</analyzer>
</fieldtype>
-->
<!-- Less flexible matching, but less false matches. Probably not ideal for product names
but may be good for SKUs. Can insert dashes in the wrong place and still match. -->
<fieldtype name="textTight" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0"
catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
</analyzer>
</fieldtype>
<fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.TrimFilterFactory"/>
<filter class="solr.PatternReplaceFilterFactory" pattern="([^a-z])" replacement="" replace="all"/>
</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)
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)
-->
<field name="id" type="string" indexed="true" stored="true" multiValued="false"/>
<field name="seriesId" type="string" indexed="true" stored="true" multiValued="false" />
<field name="fileName" type="string" indexed="true" stored="true" multiValued="false" />
<field name="mediaType" type="string" indexed="true" stored="true" multiValued="false" />
<field name="mediaTypeProperty" type="string" indexed="true" stored="true" multiValued="true" />
<field name="formatId" type="string" indexed="true" stored="true" multiValued="false"/>
<field name="formatType" type="string" indexed="true" stored="true" multiValued="false"/>
<field name="size" type="slong" indexed="true" stored="true" multiValued="false"/>
<field name="checksum" type="string" indexed="true" stored="true" multiValued="false"/>
<field name="archived" type="boolean" indexed="true" stored="true" multiValued="false"/>
<field name="checksumAlgorithm" type="string" indexed="true" stored="true"/>
<field name="dateUploaded" type="date" indexed="true" stored="true" multiValued="false"/>
<field name="dateModified" type="date" indexed="true" stored="true" multiValued="false"/>
<field name="submitter" type="string" indexed="true" stored="true" multiValued="false"/>
<field name="rightsHolder" type="string" indexed="true" stored="true" multiValued="false"/>
<field name="authoritativeMN" type="string" indexed="true" stored="true" multiValued="false"/>
<field name="replicationAllowed" type="boolean" indexed="true" stored="true" multiValued="false"/>
<field name="numberReplicas" type="integer" indexed="true" stored="true" multiValued="false"/>
<field name="preferredReplicationMN" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="blockedReplicationMN" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="replicaMN" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="replicationStatus" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="replicaVerifiedDate" type="date" indexed="true" stored="true" multiValued="true"/>
<field name="datasource" type="string" indexed="true" stored="true" multiValued="false"/>
<field name="obsoletes" type="string" indexed="true" stored="true" multiValued="false"/>
<field name="obsoletedBy" type="string" indexed="true" stored="true" multiValued="false"/>
<!-- Object relationships -->
<field name="resourceMap" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="documents" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="isDocumentedBy" type="string" indexed="true" stored="true" multiValued="true"/>
<!--Permissions-->
<field name="readPermission" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="writePermission" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="changePermission" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="isPublic" type="boolean" indexed="true" stored="true" />
<!-- Science metadata properties -->
<field name="author" type="string" multiValued="false" indexed="true" stored="true" />
<field name="authorSurName" type="string" multiValued="false" indexed="true" stored="true" />
<field name="authorGivenName" type="string" multiValued="false" indexed="true" stored="true" />
<field name="authorSurNameSort" type="alphaOnlySort" multiValued="false" indexed="true" stored="true" />
<field name="authorGivenNameSort" type="alphaOnlySort" multiValued="false" indexed="true" stored="true" />
<field name="authorLastName" type="string" multiValued="true" indexed="true" stored="true" />
<field name="abstract" type="text" multiValued="false" indexed="true" stored="true" />
<field name="keywords" type="string" multiValued="true" indexed="true" stored="true" />
<field name="keyConcept" type="string" multiValued="true" indexed="true" stored="true" />
<field name="southBoundCoord" type="sfloat" multiValued="false" indexed="true" stored="true"/>
<field name="northBoundCoord" type="sfloat" multiValued="false" indexed="true" stored="true"/>
<field name="westBoundCoord" type="sfloat" multiValued="false" indexed="true" stored="true"/>
<field name="eastBoundCoord" type="sfloat" multiValued="false" indexed="true" stored="true"/>
<field name="namedLocation" type="string" multiValued="true" indexed="true" stored="true" />
<field name="beginDate" type="date" multiValued="false" indexed="true" stored="true" />
<field name="endDate" type="date" multiValued="false" indexed="true" stored="true" />
<field name="title" type="text" multiValued="false" indexed="true" stored="true" />
<field name="scientificName" type="string" multiValued="true" indexed="true" stored="true" />
<field name="relatedOrganizations" type="string" multiValued="true" indexed="true" stored="true" />
<field name="datePublished" type="date" multiValued="false" indexed="true" stored="true" />
<field name="pubDate" type="date" multiValued="false" indexed="true" stored="true"/>
<field name="investigator" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="investigatorText" type="text" indexed="true" stored="false" multiValued="true"/>
<field name="ogcUrl" type="text" indexed="false" stored="true"/>
<field name="sku" type="textTight" indexed="true" stored="true"/>
<field name="identifier" type="textTight" indexed="true" stored="true"/>
<field name="LTERSite" type="string" indexed="true" stored="true"/>
<field name="origin" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="originText" type="text" indexed="true" stored="false" multiValued="true"/>
<field name="titlestr" type="string" indexed="true" stored="false"/>
<field name="geoform" type="string" indexed="true" stored="true"/>
<field name="presentationCat" type="string" indexed="true" stored="true"/>
<field name="purpose" type="text" indexed="true" stored="true"/>
<field name="updateDate" type="date" indexed="true" stored="true"/>
<field name="edition" type="text" indexed="true" stored="true"/>
<field name="dataUrl" type="string" indexed="false" stored="true"/>
<field name="originator" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="originatorText" type="text" indexed="true" stored="false" multiValued="true"/>
<field name="family" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="species" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="genus" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="kingdom" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="phylum" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="order" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="class" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="attributeName" type="string" indexed="true" stored="true" multiValued="true" />
<field name="attributeLabel" type="string" indexed="true" stored="true" multiValued="true" />
<field name="attributeDescription" type="text" indexed="true" stored="true" multiValued="true" />
<field name="attributeUnit" type="string" indexed="true" stored="true" multiValued="true" />
<field name="attribute" type="text" indexed="true" stored="true" multiValued="true" />
<field name="webUrl" type="string" indexed="false" stored="true" multiValued="true"/>
<field name="contactOrganization" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="contactOrganizationText" type="text" indexed="true" stored="false" multiValued="true"/>
<field name="keywordsText" type="text" indexed="true" stored="false" multiValued="true"/>
<field name="placeKey" type="text" indexed="true" stored="true" multiValued="true"/>
<field name="noBoundingBox" type="string" indexed="true" stored="true"/>
<field name="isSpatial" type="string" indexed="true" stored="true"/>
<field name="decade" type="string" indexed="true" stored="true"/>
<field name="gcmdKeyword" type="text" indexed="true" stored="true" multiValued="true"/>
<!-- these are ornl daac fields, may not be populated for nbii, but are required to be here for indexing purpose-->
<field name="project" type="string" indexed="true" stored="true"/>
<field name="projectText" type="text" indexed="true" stored="false"/>
<field name="site" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="siteText" type="text" indexed="true" stored="false" multiValued="true"/>
<field name="parameter" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="parameterText" type="text" indexed="true" stored="false" multiValued="true"/>
<field name="sensor" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="sensorText" type="text" indexed="true" stored="false" multiValued="true"/>
<field name="source" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="sourceText" type="text" indexed="true" stored="false" multiValued="true"/>
<field name="term" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="termText" type="text" indexed="true" stored="false" multiValued="true"/>
<field name="topic" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="topicText" type="text" indexed="true" stored="false" multiValued="true"/>
<field name="fileID" type="string" indexed="true" stored="true"/>
<field name="text" type="text" indexed="true" stored="true" multiValued="false" />
<field name="geohash_1" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="geohash_2" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="geohash_3" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="geohash_4" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="geohash_5" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="geohash_6" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="geohash_7" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="geohash_8" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="geohash_9" type="string" indexed="true" stored="true" multiValued="true"/>
<!-- Provenance-based fields -->
<field name="prov_wasDerivedFrom" type="string" indexed="true" stored="true" multiValued="true" />
<field name="prov_wasGeneratedBy" type="string" indexed="true" stored="true" multiValued="true" />
<field name="prov_wasInformedBy" type="string" indexed="true" stored="true" multiValued="true" />
<field name="prov_used" type="string" indexed="true" stored="true" multiValued="true" />
<field name="prov_generated" type="string" indexed="true" stored="true" multiValued="true" />
<field name="prov_generatedByProgram" type="string" indexed="true" stored="true" multiValued="true" />
<field name="prov_generatedByExecution" type="string" indexed="true" stored="true" multiValued="true" />
<field name="prov_generatedByUser" type="string" indexed="true" stored="true" multiValued="true" />
<field name="prov_usedByProgram" type="string" indexed="true" stored="true" multiValued="true" />
<field name="prov_usedByExecution" type="string" indexed="true" stored="true" multiValued="true" />
<field name="prov_usedByUser" type="string" indexed="true" stored="true" multiValued="true" />
<field name="prov_wasExecutedByExecution" type="string" indexed="true" stored="true" multiValued="true" />
<field name="prov_wasExecutedByUser" type="string" indexed="true" stored="true" multiValued="true" />
<field name="prov_hasSources" type="string" indexed="true" stored="true" multiValued="true" />
<field name="prov_hasDerivations" type="string" indexed="true" stored="true" multiValued="true" />
<field name="prov_instanceOfClass" type="string" indexed="true" stored="true" multiValued="true" />
<!-- semantic fields -->
<field name="sem_annotation" type="string" indexed="true" stored="true" multiValued="true" />
<field name="sem_annotated_by" type="string" indexed="true" stored="true" multiValued="true" />
<field name="sem_annotates" type="string" indexed="true" stored="true" multiValued="true" />
<field name="sem_comment" type="string" indexed="true" stored="true" multiValued="true" />
<!-- member node service fields -->
<field name="isService" type="boolean" indexed="true" stored="true" multiValued="false" default="false" />
<field name="serviceCoupling" type="string" indexed="true" stored="true" multiValued="false" default="false" />
<field name="serviceTitle" type="text" indexed="true" stored="true" multiValued="false" />
<field name="serviceDescription" type="text" indexed="true" stored="true" multiValued="false" />
<field name="serviceType" type="string" indexed="true" stored="true" multiValued="true" />
<field name="serviceEndpoint" type="string" indexed="true" stored="true" multiValued="true" />
<field name="serviceInput" type="string" indexed="true" stored="true" multiValued="true" />
<field name="serviceOutput" type="string" indexed="true" stored="true" multiValued="true" />
<!-- ======================================================================= -->
<!-- Dynamic field definitions. If a field name is not found, dynamicFields
will be used if the name matches any of the patterns.
RESTRICTION: the glob-like pattern in the name attribute must have
a "*" only at the start or the end.
EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
Longer patterns will be matched first. if equal size patterns
both match, the first appearing in the schema will be used. -->
<dynamicField name="*_i" type="sint" indexed="true" stored="true"/>
<dynamicField name="*_s" type="string" indexed="true" stored="true"/>
<dynamicField name="*_l" type="slong" indexed="true" stored="true"/>
<dynamicField name="*_t" type="text" indexed="true" stored="true"/>
<dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
<dynamicField name="*_f" type="sfloat" indexed="true" stored="true"/>
<dynamicField name="*_d" type="sdouble" indexed="true" stored="true"/>
<dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
<!-- allow multivalued dynamic fields as well -->
<dynamicField name="*_im" type="sint" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_sm" type="string" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_lm" type="slong" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_tm" type="text" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_bm" type="boolean" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_fm" type="sfloat" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_dm" type="sdouble" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_dtm" type="date" indexed="true" stored="true" multiValued="true"/>
</fields>
<!-- ======================================================================= -->
<!-- field to use to determine and enforce document uniqueness. -->
<uniqueKey>id</uniqueKey>
<!-- field for the QueryParser to use when an explicit fieldname is absent -->
<defaultSearchField>text</defaultSearchField>
<!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
<solrQueryParser defaultOperator="AND"/>
<!-- ======================================================================= -->
<!-- copyField commands copy one field to another at the time a document
is added to the index. It's used either to index the same field different
ways, or to add multiple fields to the same field for easier/faster searching. -->
<copyField source="id" dest="sku"/>
<copyField source="id" dest="identifier"/>
<copyField source="title" dest="titlestr"/>
<copyField source="origin" dest="originText"/>
<copyField source="origin" dest="originatorText"/>
<copyField source="project" dest="projectText"/>
<copyField source="site" dest="siteText"/>
<copyField source="parameter" dest="parameterText"/>
<copyField source="sensor" dest="sensorText"/>
<copyField source="source" dest="sourceText"/>
<copyField source="term" dest="termText"/>
<copyField source="topic" dest="topicText"/>
<copyField source="investigator" dest="investigatorText"/>
<copyField source="keywords" dest="keywordsText"/>
<copyField source="pubDate" dest="datePublished"/>
<copyField source="dateUploaded" dest="updateDate"/>
<copyField source="contactOrganization" dest="contactOrganizationText"/>
<!-- 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>