Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- <?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.
- -->
- <!DOCTYPE schema [
- <!ENTITY extrafields SYSTEM "schema_extra_fields.xml">
- <!ENTITY extratypes SYSTEM "schema_extra_types.xml">
- <!ENTITY legacyfields SYSTEM "schema_legacy_fields.xml">
- <!ENTITY legacytypes SYSTEM "schema_legacy_types.xml">
- ]>
- <!--
- 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
- PERFORMANCE NOTE: this schema includes many optional features and should not
- be used for benchmarking. To improve performance one could
- - set stored="false" for all fields possible (esp large fields) when you
- only need to search on the field but don't need to return the original
- value.
- - set indexed="false" if you don't need to search on the field, but only
- return the field as a result of searching on other indexed fields.
- - remove all unneeded copyField statements
- - for best index size and searching performance, set "index" to false
- for all general text fields, use copyField to copy them to the
- catchall "text" field, and use that for searching.
- - For maximum indexing performance, use the ConcurrentUpdateSolrServer
- java client.
- - Remember to run the JVM in server mode, and use a higher logging level
- that avoids logging every request
- -->
- <schema name="drupal-5.5-solr-6.x" version="1.6">
- <!-- attribute "name" is the name of this schema and is only used for display purposes.
- version="x.y" 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
- 1.2: omitTermFreqAndPositions attribute introduced, true by default
- except for text fields.
- 1.3: removed optional field compress feature
- 1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
- behavior when a single string produces multiple tokens. Defaults
- to off for version >= 1.4
- 1.5: omitNorms defaults to true for primitive field types
- (int, float, boolean, string...)
- 1.6: useDocValuesAsStored defaults to true.
- -->
- <!-- Valid attributes for fields:
- name: mandatory - the name for the field
- type: mandatory - the name of a field type from the
- <types> fieldType section
- indexed: true if this field should be indexed (searchable or sortable)
- stored: true if this field should be retrievable
- docValues: true if this field should have doc values. Doc values are
- useful for faceting, grouping, sorting and function queries. Although not
- required, doc values will make the index faster to load, more
- NRT-friendly and more memory-efficient. They however come with some
- limitations: they are currently only supported by StrField, UUIDField
- and all Trie*Fields, and depending on the field type, they might
- require the field to be single-valued, be required or have a default
- value (check the documentation of the field type you're interested in
- for more information)
- 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.
- Norms are omitted for primitive (non-analyzed) types by default.
- 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.
- required: The field is required. It will throw an error if the
- value does not exist
- default: a value that should be used if no value is specified
- when adding a document.
- -->
- <!-- field names should consist of alphanumeric or underscore characters only and
- not start with a digit. This is not currently strictly enforced,
- but other field names will not have first class support from all components
- and back compatibility is not guaranteed. Names with both leading and
- trailing underscores (e.g. _version_) are reserved.
- -->
- <!-- If you remove this field, you must _also_ disable the update log in solrconfig.xml
- or Solr won't start. _version_ and update log are required for SolrCloud
- -->
- <field name="_version_" type="long" indexed="true" stored="true"/>
- <!-- points to the root document of a block of nested documents. Required for nested
- document support, may be removed otherwise
- -->
- <field name="_root_" type="string" indexed="true" stored="false"/>
- <!-- Only remove the "id" field if you have a very good reason to. While not strictly
- required, it is highly recommended. A <uniqueKey> is present in almost all Solr
- installations. See the <uniqueKey> declaration below where <uniqueKey> is set to "id".
- -->
- <!-- The document id is usually derived from a site-spcific key (hash) and the
- entity type and ID like:
- Search Api 7.x:
- The format used is $document->id = $index_id . '-' . $item_id
- Search Api 8.x:
- The format used is $document->id = $site_hash . '-' . $index_id . '-' . $item_id
- Apache Solr Search Integration 7.x:
- The format used is $document->id = $site_hash . '/' . $entity_type . '/' . $entity->id;
- -->
- <field name="id" type="string" indexed="true" stored="true" required="true" />
- <!-- Search Api specific fields -->
- <!-- index_id is the machine name of the search index this entry belongs to. -->
- <field name="index_id" type="string" indexed="true" stored="true" />
- <!-- Here, default is used to create a "timestamp" field indicating
- when each document was indexed.-->
- <field name="timestamp" type="tdate" indexed="true" stored="true" default="NOW" multiValued="false"/>
- <!-- This field is used to build the spellchecker index -->
- <field name="spell" type="textSpell" indexed="true" stored="true" multiValued="true"/>
- <field name="site" type="string" indexed="true" stored="true"/>
- <field name="hash" type="string" indexed="true" stored="true"/>
- <!--TF custom-->
- <field name="url" type="string" indexed="true" stored="true"/>
- <field name="title" type="text" indexed="true" stored="true" termVectors="true" omitNorms="true"/>
- <field name="price" type="tfloat" indexed="true" stored="true"/>
- <field name="sort_title" type="sortString" indexed="true" stored="false"/>
- <field name="body" type="text" indexed="true" stored="true" termVectors="true"/>
- <field name="keywords" type="text" indexed="true" stored="true" multiValued="true"/>
- <field name="author" type="int" indexed="true" stored="true"/>
- <field name="author_name" type="string" indexed="true" stored="true"/>
- <field name="cnvnode" type="int" indexed="true" stored="true"/>
- <field name="bifthumb" type="string" indexed="true" stored="true"/>
- <field name="bif" type="text" indexed="false" stored="true"/>
- <field name="bifcount" type="int" stored="true"/>
- <field name="type" type="string" indexed="true" stored="true" multiValued="true"/>
- <field name="print_options" type="int" indexed="true" stored="true"/>
- <field name="apptype" type="int" indexed="true" stored="true"/>
- <field name="filename" type="string" indexed="true" stored="true"/>
- <field name="uid" type="int" indexed="true" stored="true"/>
- <field name="name" type="text" indexed="true" stored="true" termVectors="true"/>
- <field name="sname" type="string" indexed="true" stored="false"/>
- <field name="sort_name" type="sortString" indexed="true" stored="false"/>
- <field name="nid" type="int" indexed="true" stored="true"/>
- <field name="width" type="int" indexed="false" stored="true"/>
- <field name="height" type="int" indexed="false" stored="true"/>
- <field name="size" type="int" indexed="true" stored="true" termVectors="true"/>
- <field name="tnid" type="int" indexed="true" stored="true"/>
- <field name="tid" type="int" indexed="true" stored="true" multiValued="true"/>
- <field name="vid" type="int" indexed="true" stored="true" multiValued="true"/>
- <field name="sizes" type="text" indexed="false" stored="true"/>
- <field name="sizenid" type="int" indexed="true" stored="true" multiValued="true"/>
- <field name="frameimage" type="string" indexed="true" stored="true" multiValued="true"/>
- <field name="frametype" type="string" indexed="true" stored="true" multiValued="true"/>
- <field name="taxonomy_names" type="text" indexed="true" stored="false" multiValued="true" omitNorms="true"/>
- <copyField source="title" dest="sort_title"/>
- <copyField source="name" dest="sname"/>
- <copyField source="name" dest="sort_name"/>
- <copyField source="ts_vid_*" dest="taxonomy_names"/>
- <field name="tags_h1" type="text" indexed="true" stored="false" omitNorms="true"/>
- <field name="tags_h2_h3" type="text" indexed="true" stored="false" omitNorms="true"/>
- <field name="tags_h4_h5_h6" type="text" indexed="true" stored="false" omitNorms="true"/>
- <field name="tags_a" type="text" indexed="true" stored="false" omitNorms="true"/>
- <field name="tags_inline" type="text" indexed="true" stored="false" omitNorms="true"/>
- <copyField source="title" dest="spell"/>
- <copyField source="body" dest="spell"/>
- <dynamicField name="sis_*" type="tint" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="sim_*" type="tint" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="sort_ss_*" type="sortString" indexed="true" stored="false"/>
- <copyField source="ss_*" dest="sort_ss_*"/>
- <dynamicField name="nodeaccess*" type="int" indexed="true" stored="false" multiValued="true"/>
- <field name="stitle" type="string" indexed="true" stored="true"/>
- <field name="title_sort" type="sortString" indexed="true" stored="false"/>
- <field name="name_sort" type="sortString" indexed="true" stored="false"/>
- <fieldType name="textTight" class="solr.TextField" positionIncrementGap="100" />
- <solrQueryParser defaultOperator="AND"/>
- <!--TF custom end-->
- <!-- 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="ts_*" dest="spell"/>
- <copyField source="tm_*" dest="spell"/>
- <copyField source="ts_*" dest="terms_ts_*"/>
- <copyField source="tm_*" dest="terms_tm_*"/>
- <!-- 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. -->
- <!-- For 2 and 3 letter prefix dynamic fields, the 1st letter indicates the data type and
- the last letter is 's' for single valued, 'm' for multi-valued -->
- <!-- We use long for integer since 64 bit ints are now common in PHP. -->
- <dynamicField name="is_*" type="long" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="im_*" type="long" indexed="true" stored="true" multiValued="true"/>
- <!-- List of floats can be saved in a regular float field -->
- <dynamicField name="fs_*" type="float" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="fm_*" type="float" indexed="true" stored="true" multiValued="true"/>
- <!-- List of doubles can be saved in a regular double field -->
- <dynamicField name="ps_*" type="double" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="pm_*" type="double" indexed="true" stored="true" multiValued="true"/>
- <!-- List of booleans can be saved in a regular boolean field -->
- <dynamicField name="bm_*" type="boolean" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="bs_*" type="boolean" indexed="true" stored="true" multiValued="false"/>
- <!-- Regular text (without processing) can be stored in a string field-->
- <dynamicField name="ss_*" type="string" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="sm_*" type="string" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="ses_*" type="edge_n2_kw_string" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="sem_*" type="edge_n2_kw_string" indexed="true" stored="true" multiValued="true"/>
- <!-- Normal text fields are for full text - the relevance of a match depends on the length of the text -->
- <dynamicField name="ts_*" type="text" indexed="true" stored="true" multiValued="false" termVectors="true"/>
- <dynamicField name="tm_*" type="text" indexed="true" stored="true" multiValued="true" termVectors="true"/>
- <!-- Unstemmed text fields for full text - the relevance of a match depends on the length of the text -->
- <dynamicField name="tus_*" type="text_und" indexed="true" stored="true" multiValued="false" termVectors="true"/>
- <dynamicField name="tum_*" type="text_und" indexed="true" stored="true" multiValued="true" termVectors="true"/>
- <!-- These text fields omit norms - useful for extracted text like taxonomy_names -->
- <dynamicField name="tos_*" type="text" indexed="true" stored="true" multiValued="false" termVectors="true" omitNorms="true"/>
- <dynamicField name="tom_*" type="text" indexed="true" stored="true" multiValued="true" termVectors="true" omitNorms="true"/>
- <!-- Special-purpose text fields -->
- <dynamicField name="tes_*" type="edge_n2_kw_text" indexed="true" stored="true" multiValued="false" omitTermFreqAndPositions="true" />
- <dynamicField name="tem_*" type="edge_n2_kw_text" indexed="true" stored="true" multiValued="true" omitTermFreqAndPositions="true" />
- <dynamicField name="tws_*" type="text_ws" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="twm_*" type="text_ws" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="terms_ts_*" type="textSpell" indexed="true" stored="true" multiValued="false" termVectors="true"/>
- <dynamicField name="terms_tm_*" type="textSpell" indexed="true" stored="true" multiValued="true" termVectors="true"/>
- <!-- trie dates are preferred, so give them the 2 letter prefix -->
- <dynamicField name="ds_*" type="tdate" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="dm_*" type="tdate" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="its_*" type="tlong" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="itm_*" type="tlong" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="fts_*" type="tfloat" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="ftm_*" type="tfloat" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="pts_*" type="tdouble" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="ptm_*" type="tdouble" indexed="true" stored="true" multiValued="true"/>
- <!-- Binary fields can be populated using base64 encoded data. Useful e.g. for embedding
- a small image in a search result using the data URI scheme -->
- <dynamicField name="xs_*" type="binary" indexed="false" stored="true" multiValued="false"/>
- <dynamicField name="xm_*" type="binary" indexed="false" stored="true" multiValued="true"/>
- <!-- In rare cases a date rather than tdate is needed for sortMissingLast -->
- <dynamicField name="dds_*" type="date" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="ddm_*" type="date" indexed="true" stored="true" multiValued="true"/>
- <!-- In case a 32 bit int is really needed, we provide these fields. 'h' is mnemonic for 'half word', i.e. 32 bit on 64 arch -->
- <dynamicField name="hs_*" type="int" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="hm_*" type="int" indexed="true" stored="true" multiValued="true"/>
- <dynamicField name="hts_*" type="tint" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="htm_*" type="tint" indexed="true" stored="true" multiValued="true"/>
- <!-- Unindexed string fields that can be used to store values that won't be searchable -->
- <dynamicField name="zs_*" type="string" indexed="false" stored="true" multiValued="false"/>
- <dynamicField name="zm_*" type="string" indexed="false" stored="true" multiValued="true"/>
- <!-- Fields for location searches.
- http://wiki.apache.org/solr/SpatialSearch#geodist_-_The_distance_function -->
- <dynamicField name="points_*" type="point" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="pointm_*" type="point" indexed="true" stored="true" multiValued="true"/>
- <!--<dynamicField name="locs_*" type="location" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="locm_*" type="location" indexed="true" stored="true" multiValued="true"/>-->
- <!--<dynamicField name="geos_*" type="geohash" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="geom_*" type="geohash" indexed="true" stored="true" multiValued="true"/>-->
- <dynamicField name="bboxs_*" type="bbox" indexed="true" stored="true" multiValued="false" />
- <dynamicField name="bboxm_*" type="bbox" indexed="true" stored="true" multiValued="true" />
- <dynamicField name="rpts_*" type="location_rpt" indexed="true" stored="true" multiValued="false" />
- <dynamicField name="rptm_*" type="location_rpt" indexed="true" stored="true" multiValued="true" />
- <!-- Special fields for Solr 5 functionality. -->
- <dynamicField name="phons_*" type="phonetic" indexed="true" stored="true" multiValued="false" />
- <dynamicField name="phonm_*" type="phonetic" indexed="true" stored="true" multiValued="true" />
- <!-- External file fields -->
- <dynamicField name="eff_*" type="file"/>
- <!-- Sortable version of the dynamic string field -->
- <dynamicField name="sort_*" type="sortString" indexed="true" stored="false"/>
- <!-- A random sort field -->
- <dynamicField name="random_*" type="random" indexed="true" stored="true"/>
- <!-- This field is used to store access information (e.g. node access grants), as opposed to field data -->
- <dynamicField name="access_*" type="int" indexed="true" stored="false" multiValued="true"/>
- <!-- The following causes solr 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" multiValued="true" />
- <!-- 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 a
- standard package such as org.apache.solr.analysis
- -->
- <!-- The StrField type is not analyzed, but indexed/stored verbatim.
- It supports doc values but in that case the field needs to be
- single-valued and either required or have a default value.
- -->
- <fieldType name="string" class="solr.StrField"/>
- <!-- boolean type: "true" or "false" -->
- <fieldType name="boolean" class="solr.BoolField"/>
- <!-- sortMissingLast and sortMissingFirst attributes are optional attributes are
- currently supported on types that are sorted internally as strings
- and on numeric types.
- This includes "string","boolean", and, as of 3.5 (and 4.x),
- int, float, long, date, double, including the "Trie" variants.
- - 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.
- -->
- <!--
- Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
- These fields support doc values, but they require the field to be
- single-valued and either be required or have a default value.
- -->
- <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"/>
- <!--
- Numeric field types that index each value at various levels of precision
- to accelerate range queries when the number of values between the range
- endpoints is large. See the javadoc for NumericRangeQuery for internal
- implementation details.
- Smaller precisionStep values (specified in bits) will lead to more tokens
- indexed per value, slightly larger index size, and faster range queries.
- A precisionStep of 0 disables indexing at different precision levels.
- -->
- <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"/>
- <!--
- The ExternalFileField type gets values from an external file instead of the
- index. This is useful for data such as rankings that might change frequently
- and require different update frequencies than the documents they are
- associated with.
- -->
- <fieldType name="file" keyField="id" defVal="1" stored="false" indexed="false" class="solr.ExternalFileField" valType="float"/>
- <!-- 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 TrieDateField javadocs for more information.
- Note: For faster range queries, consider the tdate type
- -->
- <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0" omitNorms="true"/>
- <!-- A Trie based date field for faster date range queries and date faceting. -->
- <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
- <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
- <fieldType name="binary" class="solr.BinaryField"/>
- <!-- The "RandomSortField" is not used to store or search any
- data. You can declare fields of this type it in your schema
- to generate pseudo-random orderings of your docs for sorting
- or function purposes. The ordering is generated based on the field
- name and the version of the index. As long as the index version
- remains unchanged, and the same field name is reused,
- the ordering of the docs will be consistent.
- If you want different psuedo-random orderings of documents,
- for the same version of the index, use a dynamicField and
- change the field name in the request.
- -->
- <fieldType name="random" class="solr.RandomSortField" indexed="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.
- Example:
- <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" omitNorms="true" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </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">
- <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
- <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"/>
- -->
- <!-- Case insensitive stop word removal. -->
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="stopwords.txt"
- />
- <!--<filter class="solr.WordDelimiterFilterFactory"
- protected="protwords.txt"
- generateWordParts="1"
- generateNumberParts="1"
- catenateWords="1"
- catenateNumbers="1"
- catenateAll="0"
- splitOnCaseChange="0"
- preserveOriginal="1"/>-->
- <filter class="solr.LengthFilterFactory" min="2" max="100" />
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- <analyzer type="query">
- <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
- <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"
- protected="protwords.txt"
- generateWordParts="1"
- generateNumberParts="1"
- catenateWords="0"
- catenateNumbers="0"
- catenateAll="0"
- splitOnCaseChange="0"
- preserveOriginal="1"/>-->
- <filter class="solr.LengthFilterFactory" min="2" max="100" />
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- <analyzer type="multiterm">
- <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
- <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"
- protected="protwords.txt"
- generateWordParts="1"
- generateNumberParts="1"
- catenateWords="0"
- catenateNumbers="0"
- catenateAll="0"
- splitOnCaseChange="1"
- preserveOriginal="1"/>-->
- <filter class="solr.LengthFilterFactory" min="2" max="100" />
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.SnowballPorterFilterFactory" language="English" protected="protwords.txt"/>
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- </analyzer>
- </fieldType>
- <!-- An unstemmed text field - good if one does not know the language of the field -->
- <fieldType name="text_und" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
- <!--<filter class="solr.WordDelimiterFilterFactory"
- protected="protwords.txt"
- generateWordParts="1"
- generateNumberParts="1"
- catenateWords="1"
- catenateNumbers="1"
- catenateAll="0"
- splitOnCaseChange="0"/>-->
- <filter class="solr.LengthFilterFactory" min="2" max="100" />
- <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"
- />
- <!--<filter class="solr.WordDelimiterFilterFactory"
- protected="protwords.txt"
- generateWordParts="1"
- generateNumberParts="1"
- catenateWords="0"
- catenateNumbers="0"
- catenateAll="0"
- splitOnCaseChange="0"/>-->
- <filter class="solr.LengthFilterFactory" min="2" max="100" />
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- <analyzer type="multiterm">
- <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"
- protected="protwords.txt"
- generateWordParts="1"
- generateNumberParts="1"
- catenateWords="0"
- catenateNumbers="0"
- catenateAll="0"
- splitOnCaseChange="0"/>-->
- <filter class="solr.LengthFilterFactory" min="2" max="100" />
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
- <fieldType name="edge_n2_kw_text" class="solr.TextField" positionIncrementGap="100">
- <analyzer type="index">
- <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <!-- Case insensitive stop word removal. -->
- <filter class="solr.StopFilterFactory"
- ignoreCase="true"
- words="stopwords.txt"
- />
- <!--<filter class="solr.WordDelimiterFilterFactory"
- protected="protwords.txt"
- generateWordParts="1"
- generateNumberParts="1"
- catenateWords="1"
- catenateNumbers="1"
- catenateAll="0"
- splitOnCaseChange="0"
- preserveOriginal="1"/>-->
- <filter class="solr.LengthFilterFactory" min="2" max="100" />
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
- <filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="25" />
- </analyzer>
- <analyzer type="query">
- <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
- <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.LengthFilterFactory" min="2" max="100" />
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- <analyzer type="multiterm">
- <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
- <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.LengthFilterFactory" min="2" max="100" />
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
- <!-- Edge N gram type - for example for matching against queries with results
- KeywordTokenizer leaves input string intact as a single term.
- see: http://www.lucidimagination.com/blog/2009/09/08/auto-suggest-from-popular-queries-using-edgengrams/
- -->
- <fieldType name="edge_n2_kw_string" class="solr.TextField" omitNorms="true" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.KeywordTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="25" />
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.KeywordTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldType>
- <!-- Setup simple analysis for spell checking -->
- <fieldType name="textSpell" class="solr.TextField" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory" />
- <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/>
- <filter class="solr.LengthFilterFactory" min="4" max="20" />
- <filter class="solr.LowerCaseFilterFactory" />
- <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" 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 references to portions of the original
- string matched by the pattern.
- See the Java Regular Expression documentation for more
- information on pattern and replacement string syntax.
- http://docs.oracle.com/javase/8/docs/api/java/util/regex/package-summary.html
- -->
- <filter class="solr.PatternReplaceFilterFactory"
- pattern="([^a-z])" replacement="" replace="all"
- />
- </analyzer>
- </fieldType>
- <!-- The Solr 6.x example file replaced the sortString type by alphaOnlySort
- above. This one is not suitable for search_api_id which consists of
- characters, numbers and punctuation, for example
- 'entity:entity_test_mulrev_changed/2:en'.
- -->
- <fieldType name="sortString" class="solr.TextField" 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="(^\p{Punct}+)" replacement="" replace="all"
- />
- -->
- </analyzer>
- </fieldType>
- <fieldType name="phonetic" stored="false" indexed="true" class="solr.TextField" >
- <analyzer>
- <tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
- </analyzer>
- </fieldType>
- <fieldType name="payloads" stored="false" indexed="true" class="solr.TextField" >
- <analyzer>
- <tokenizer class="solr.WhitespaceTokenizerFactory"/>
- <!--
- The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
- a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
- Attributes of the DelimitedPayloadTokenFilterFactory :
- "delimiter" - a one character delimiter. Default is | (pipe)
- "encoder" - how to encode the following value into a playload
- float -> org.apache.lucene.analysis.payloads.FloatEncoder,
- integer -> o.a.l.a.p.IntegerEncoder
- identity -> o.a.l.a.p.IdentityEncoder
- Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
- -->
- <filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
- </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.LowerCaseFilterFactory" />
- </analyzer>
- </fieldType>
- <!--
- Example of using PathHierarchyTokenizerFactory at index time, so
- queries for paths match documents at that path, or in descendent paths
- -->
- <fieldType name="descendent_path" class="solr.TextField">
- <analyzer type="index">
- <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.KeywordTokenizerFactory" />
- </analyzer>
- </fieldType>
- <!--
- Example of using PathHierarchyTokenizerFactory at query time, so
- queries for paths match documents at that path, or in ancestor paths
- -->
- <fieldType name="ancestor_path" class="solr.TextField">
- <analyzer type="index">
- <tokenizer class="solr.KeywordTokenizerFactory" />
- </analyzer>
- <analyzer type="query">
- <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
- </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" />
- <!-- This point type indexes the coordinates as separate fields (subFields)
- If subFieldType is defined, it references a type, and a dynamic field
- definition is created matching *___<typename>. Alternately, if
- subFieldSuffix is defined, that is used to create the subFields.
- Example: if subFieldType="double", then the coordinates would be
- indexed in fields myloc_0___double,myloc_1___double.
- Example: if subFieldSuffix="_d" then the coordinates would be indexed
- in fields myloc_0_d,myloc_1_d
- The subFields are an implementation detail of the fieldType, and end
- users normally should not need to know about them.
- -->
- <!-- In Drupal we only use prefixes for dynmaic fields. Tht might change in
- the future but for now we keep this pattern.
- -->
- <fieldType name="point" class="solr.PointType" dimension="2" subFieldType="tdouble"/>
- <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
- <!--<fieldType name="location" class="solr.LatLonType" subFieldType="tdouble"/>-->
- <!-- An alternative geospatial field type new to Solr 4. It supports multiValued and polygon shapes.
- For more information about this and other Spatial fields new to Solr 4, see:
- http://wiki.apache.org/solr/SolrAdaptersForLuceneSpatial4
- -->
- <fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
- geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
- <!-- A Geohash is a compact representation of a latitude longitude pair in a single field.
- See http://wiki.apache.org/solr/SpatialSearch
- -->
- <!--<fieldtype name="geohash" class="solr.GeoHashField"/>-->
- <!-- Spatial rectangle (bounding box) field. It supports most spatial predicates, and has
- special relevancy modes: score=overlapRatio|area|area2D (local-param to the query). DocValues is recommended for
- relevancy. -->
- <fieldType name="bbox" class="solr.BBoxField"
- geo="true" distanceUnits="kilometers" numberType="_bbox_coord" />
- <fieldType name="_bbox_coord" class="solr.TrieDoubleField" precisionStep="8" docValues="true" stored="false"/>
- <!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
- Parameters:
- defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
- precisionStep: Specifies the precisionStep for the TrieLong field used for the amount
- providerClass: Lets you plug in other exchange provider backend:
- solr.FileExchangeRateProvider is the default and takes one parameter:
- currencyConfig: name of an xml file holding exchange rates
- solr.OpenExchangeRatesOrgProvider uses rates from openexchangerates.org:
- ratesFileLocation: URL or path to rates JSON file (default latest.json on the web)
- refreshInterval: Number of minutes between each rates fetch (default: 1440, min: 60)
- -->
- <!-- <fieldType name="currency" class="solr.CurrencyField" precisionStep="8" defaultCurrency="USD" currencyConfig="currency.xml" /> -->
- <!-- Following is a dynamic way to include other fields, added by other contrib modules -->
- &extrafields;
- <!--
- Enable the following only if you need backwards compatibility with
- Drupal 6 or Drupal 7 versions of search_api or apachesolr,
- e.g. if you are running a multi-site search that mixes
- Drupal 8 and earlier versions.
- -->
- <!--
- &legacyfields;
- -->
- <!-- Following is a dynamic way to include other types, added by other contrib modules -->
- &extratypes;
- <!--
- Enable the following only if you need backwards compatibility with
- Drupal 6 or Drupal 7 versions of search_api or apachesolr,
- e.g. if you are running a multi-site search that mixes
- Drupal 8 and earlier versions.
- -->
- <!--
- &legacytypes;
- -->
- <!-- 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>
- <defaultSearchField>keywords</defaultSearchField>
- <!-- Similarity is the scoring routine for each document vs. a query.
- A custom Similarity or SimilarityFactory may be specified here, but
- the default is fine for most applications.
- For more info: http://wiki.apache.org/solr/SchemaXml#Similarity
- -->
- <!--
- <similarity class="com.example.solr.CustomSimilarityFactory">
- <str name="paramkey">param value</str>
- </similarity>
- -->
- </schema>
Add Comment
Please, Sign In to add comment