eulfedora/indexdata/sample-solr-schema.xml
<?xml version="1.0" encoding="UTF-8" ?>
<!--
Licensed to the Apache Software Foundation (ASF) under one or more
contributor license agreements. See the NOTICE file distributed with
this work for additional information regarding copyright ownership.
The ASF licenses this file to You under the Apache License, Version 2.0
(the "License"); you may not use this file except in compliance with
the License. You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
-->
<!--
This is an example Solr schema for use with eulfedora indexdata,
(adapted from a Solr example schema). It includes field
configurations for all the fields that are made available by the
default DigitalObject index_data method. This may be a useful initial
Solr Schema for projects using eulfedora and indexdata.
-->
<!--
This is 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.
This example schema is the recommended starting point for users.
It should be kept correct and concise, usable out-of-the-box.
For more information, on how to customize this file, please see
http://wiki.apache.org/solr/SchemaXml
-->
<schema name="example" version="1.1">
<!-- attribute "name" is the name of this schema and is only used
for display purposes. Applications should change this to
reflect the nature of the search collection. version="1.1" is
Solr's version number for the schema syntax and semantics. It
should not normally be changed by applications. 1.0:
multiValued attribute did not exist, all fields are multiValued
by nature 1.1: multiValued attribute introduced, false by
default -->
<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.
Class names starting with "solr" refer to java classes in the
org.apache.solr.analysis package.
-->
<!-- The StrField type is not analyzed, but indexed/stored verbatim.
- StrField and TextField support an optional compressThreshold which
limits compression (if enabled in the derived fields) to values which
exceed a certain size (in characters).
-->
<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"/>
<!-- The optional sortMissingLast and sortMissingFirst attributes are
currently supported on types that are sorted internally as 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" omitNorms="true"/>
<fieldType name="long" class="solr.LongField" omitNorms="true"/>
<fieldType name="float" class="solr.FloatField" omitNorms="true"/>
<fieldType name="double" class="solr.DoubleField" omitNorms="true"/>
<!-- Numeric field types that manipulate the value into
a string value that isn't human-readable in its internal form,
but with a lexicographic ordering the same as the numeric ordering,
so that range queries work correctly. -->
<fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="slong" class="solr.SortableLongField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="sfloat" class="solr.SortableFloatField" sortMissingLast="true" omitNorms="true"/>
<fieldType name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true" omitNorms="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.
Expressions can also be used to denote calculations that should be
performed relative to "NOW" to determine the value, ie...
NOW/HOUR
... Round to the start of the current hour
NOW-1DAY
... Exactly 1 day prior to now
NOW/DAY+6MONTHS+3DAYS
... 6 months and 3 days in the future from the start of
the current day
Consult the DateField javadocs for more information.
-->
<fieldType name="date" class="solr.DateField" sortMissingLast="true" omitNorms="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
-->
<!-- One can also specify an existing Analyzer class that has a
default constructor via the class attribute on the analyzer element
<fieldType name="text_greek" class="solr.TextField">
<analyzer class="org.apache.lucene.analysis.el.GreekAnalyzer"/>
</fieldType>
-->
<!-- 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 text field that uses WordDelimiterFilter to enable splitting and matching of
words on case-change, alpha numeric boundaries, and non-alphanumeric chars,
so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi".
Synonyms and stopwords are customized by external files, and stemming is enabled.
Duplicate tokens at the same position (which may result from Stemmed Synonyms or
WordDelim parts) are removed.
-->
<fieldType name="text" 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" words="stopwords.txt"/>
<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"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</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"/>
<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"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</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" words="stopwords.txt"/>
<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"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldType>
<!-- This is an example of using the KeywordTokenizer along
With various TokenFilterFactories to produce a sortable field
that does not include some properties of the source text
-->
<fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true">
<analyzer>
<!-- KeywordTokenizer does no actual tokenizing, so the entire
input string is preserved as a single token
-->
<tokenizer class="solr.KeywordTokenizerFactory"/>
<!-- The LowerCase TokenFilter does what you expect, which can be
when you want your sorting to be case insensitive
-->
<filter class="solr.LowerCaseFilterFactory" />
<!-- The TrimFilter removes any leading or trailing whitespace -->
<filter class="solr.TrimFilterFactory" />
<!-- The PatternReplaceFilter gives you the flexibility to use
Java Regular expression to replace any sequence of characters
matching a pattern with an arbitrary replacement string,
which may include back refrences to portions of the orriginal
string matched by the pattern.
See the Java Regular Expression documentation for more
infomation on pattern and replacement string syntax.
http://java.sun.com/j2se/1.5.0/docs/api/java/util/regex/package-summary.html
-->
<filter class="solr.PatternReplaceFilterFactory"
pattern="([^a-z])" replacement="" replace="all"
/>
</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" class="solr.StrField" />
</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
compressed: [false] if this field should be stored using gzip compression
(this will only apply if the field type is compressable; among
the standard field types, only TextField and StrField are)
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.
-->
<field name="pid" type="string" indexed="true" stored="true" required="true" />
<!-- standard fedora fields that should apply to all objects -->
<field name="content_model" type="string" indexed="true" stored="true" multiValued="true"/>
<!-- treat dates as string or date ? -->
<field name="label" type="string" indexed="true" stored="false"/>
<field name="created" type="date" indexed="true" stored="true"/>
<field name="last_modified" type="date" indexed="true" stored="true" />
<field name="owner" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="state" type="string" indexed="true" stored="false"/>
<field name="dsids" type="string" indexed="true" stored="true" multiValued="true"/>
<!-- explicitly define string-variants of date fields for wildcard searching -->
<field name="created_s" type="string" indexed="true" stored="true"/>
<field name="last_modified_s" type="string" indexed="true" stored="false" />
<!-- Dublin Core fields -->
<field name="title" type="text" indexed="true" stored="true"/>
<field name="contributor" type="text" indexed="true" stored="true" multiValued="true"/>
<field name="coverage" type="text" indexed="true" stored="true" multiValued="true"/>
<field name="creator" type="text" indexed="true" stored="true" multiValued="true"/>
<field name="date" type="text" indexed="true" stored="true" multiValued="true"/>
<field name="description" type="text" indexed="true" stored="true" multiValued="true"/>
<field name="format" type="text" indexed="true" stored="true" multiValued="true"/>
<field name="identifier" type="text" indexed="true" stored="true" multiValued="true"/>
<field name="language" type="text" indexed="true" stored="true" multiValued="true"/>
<field name="publisher" type="text" indexed="true" stored="true" multiValued="true"/>
<field name="relation" type="text" indexed="true" stored="true" multiValued="true"/>
<field name="rights" type="text" indexed="true" stored="true" multiValued="true"/>
<field name="source" type="text" indexed="true" stored="true" multiValued="true"/>
<field name="subject" type="text" indexed="true" stored="true" multiValued="true"/>
<field name="type" type="text" indexed="true" stored="true" multiValued="true"/>
<!-- Fedora Relations -->
<field name="isPartOf" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="hasPart" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="isConstituentOf" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="hasConstituent" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="isMemberOf" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="hasMember" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="isSubsetOf" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="hasSubset" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="isMemberOfCollection" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="hasCollectionMember" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="isDerivationOf" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="isDependentOf" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="hasDependent" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="isDescriptionOf" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="isMetadataFor" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="HasMetadata" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="isAnnotationOf" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="HasAnnotation" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="hasEquivalent" type="string" indexed="true" stored="true" multiValued="true"/>
<!-- catchall field, containing all other searchable text fields (implemented
via copyField further on in this schema -->
<field name="text" type="text" indexed="true" stored="false" multiValued="true"/>
<!-- non-tokenized versions of terms to for sorting and/or facets -->
<field name="title_exact" type="string" indexed="true" stored="false"/>
<field name="subject_facet" type="string" indexed="true" stored="false" multiValued="true"/>
<!-- Here, default is used to create a "timestamp" field indicating
When each document was indexed.
-->
<field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
<!-- 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"/>
<!-- uncomment the following to ignore any fields that don't already match an existing
field name or dynamic field, rather than reporting them as an error.
alternately, change the type="ignored" to some other type e.g. "text" if you want
unknown fields indexed and/or stored by default -->
<!--dynamicField name="*" type="ignored" /-->
</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>pid</uniqueKey>
<!-- field for the QueryParser to use when an explicit fieldname is absent -->
<defaultSearchField>text</defaultSearchField>
<!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
<solrQueryParser defaultOperator="OR"/>
<!-- 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 differently,
or to add multiple fields to the same field for easier/faster searching. -->
<copyField source="title" dest="title_exact"/>
<!-- copy text fields into string fields for faceting -->
<copyField source="subject" dest="subject_facet"/>
<!-- fields that should be included in the default search -->
<!-- top-level object properties: label, pid, owner -->
<copyField source="pid" dest="text"/>
<copyField source="label" dest="text"/>
<copyField source="owner" dest="text"/>
<!-- copy datetime fields to string variants for wildcard searching -->
<copyField source="created" dest="created_s"/>
<copyField source="last_modified" dest="last_modified_s"/>
<!-- all DC fields -->
<copyField source="title" dest="text"/>
<copyField source="contributor" dest="text"/>
<copyField source="creator" dest="text"/>
<copyField source="coverage" dest="text"/>
<copyField source="date" dest="text"/>
<copyField source="description" dest="text"/>
<copyField source="format" dest="text"/>
<copyField source="identifier" dest="text"/>
<copyField source="language" dest="text"/>
<copyField source="publisher" dest="text"/>
<copyField source="relation" dest="text"/>
<copyField source="rights" dest="text"/>
<copyField source="source" dest="text"/>
<copyField source="subject" dest="text"/>
<copyField source="type" dest="text"/>
<!-- 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>