You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by us...@apache.org on 2014/02/22 21:02:21 UTC
svn commit: r1570898 [4/21] - in /lucene/dev/trunk/solr: ./
contrib/map-reduce/ contrib/map-reduce/src/test-files/
contrib/map-reduce/src/test-files/solr/
contrib/map-reduce/src/test-files/test-documents/
contrib/map-reduce/src/test-files/test-morphlin...
Modified: lucene/dev/trunk/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/schema.xml
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/schema.xml?rev=1570898&r1=1570897&r2=1570898&view=diff
==============================================================================
--- lucene/dev/trunk/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/schema.xml (original)
+++ lucene/dev/trunk/solr/contrib/morphlines-core/src/test-files/solr/collection1/conf/schema.xml Sat Feb 22 20:02:13 2014
@@ -1,4 +1,4 @@
-<?xml version="1.0" ?>
+<?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
@@ -16,697 +16,932 @@
limitations under the License.
-->
-<!-- The Solr schema file. This file should be named "schema.xml" and
- should be located where the classloader for the Solr webapp can find it.
+<!--
+ 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 StreamingUpdateSolrServer
+ java client.
+ - Remember to run the JVM in server mode, and use a higher logging level
+ that avoids logging every request
+-->
+
+<schema name="example" version="1.5">
+ <!-- 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...)
+ -->
+
+ <fields>
+ <!-- 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
+ 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.
+ -->
+
+ <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
+ <field name="user_friends_count" type="tint" indexed="true" stored="true" />
+ <field name="user_location" type="lowercase" indexed="true" stored="true" />
+ <field name="user_description" type="text_en" indexed="true" stored="false"/>
+ <field name="user_statuses_count" type="tint" indexed="true" stored="true" />
+ <field name="user_followers_count" type="tint" indexed="true" stored="true"/>
+ <field name="user_name" type="text_en" indexed="true" stored="true" />
+ <field name="user_screen_name" type="text_en" indexed="true" stored="true" />
+ <field name="created_at" type="tdate" indexed="true" stored="true" />
+ <field name="text" type="text_en" indexed="true" stored="true" multiValued="true" />
+ <field name="retweet_count" type="tint" indexed="true" stored="true" />
+ <field name="retweeted" type="boolean" indexed="true" stored="false" />
+ <field name="in_reply_to_user_id" type="long" indexed="true" stored="true" />
+ <field name="source" type="lowercase" indexed="true" stored="true" />
+ <field name="in_reply_to_status_id" type="long" indexed="true" stored="true" multiValued="true"/>
+ <field name="media_url_https" type="string" indexed="false" stored="true" />
+ <field name="expanded_url" type="string" indexed="false" stored="true" />
+
+ <!-- file metadata -->
+ <field name="file_download_url" type="string" indexed="false" stored="true" />
+ <field name="file_upload_url" type="string" indexed="false" stored="true" />
+ <field name="file_scheme" type="string" indexed="true" stored="true" />
+ <field name="file_host" type="string" indexed="true" stored="true" />
+ <field name="file_port" type="int" indexed="true" stored="true" />
+ <field name="file_path" type="string" indexed="true" stored="true" />
+ <field name="file_name" type="string" indexed="true" stored="true" />
+ <field name="file_length" type="tlong" indexed="true" stored="true" />
+ <field name="file_last_modified" type="tlong" indexed="true" stored="true" />
+ <field name="file_owner" type="string" indexed="true" stored="true" />
+ <field name="file_group" type="string" indexed="true" stored="true" />
+ <field name="file_permissions_user" type="string" indexed="true" stored="true" />
+ <field name="file_permissions_group" type="string" indexed="true" stored="true" />
+ <field name="file_permissions_other" type="string" indexed="true" stored="true" />
+ <field name="file_permissions_stickybit" type="boolean" indexed="true" stored="true" />
+
+ <!-- tika metadata -->
+ <field name="content_type" type="lowercase" indexed="true" stored="true" />
+
+ <field name="_version_" type="long" indexed="true" stored="true"/>
+ <dynamicField name="ignored_*" 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>id</uniqueKey>
- This schema is used for testing, and as such has everything and the
- kitchen sink thrown in. See example/solr/conf/schema.xml for a
- more concise example.
+ <!-- DEPRECATED: The defaultSearchField is consulted by various query parsers when
+ parsing a query string that isn't explicit about the field. Machine (non-user)
+ generated queries are best made explicit, or they can use the "df" request parameter
+ which takes precedence over this.
+ Note: Un-commenting defaultSearchField will be insufficient if your request handler
+ in solrconfig.xml defines "df", which takes precedence. That would need to be removed.
+ <defaultSearchField>text</defaultSearchField> -->
+
+ <!-- DEPRECATED: The defaultOperator (AND|OR) is consulted by various query parsers
+ when parsing a query string to determine if a clause of the query should be marked as
+ required or optional, assuming the clause isn't already marked by some operator.
+ The default is OR, which is generally assumed so it is not a good idea to change it
+ globally here. The "q.op" request parameter takes precedence over this.
+ <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. -->
-<schema name="test" version="1.0">
+
<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 a
+ standard package such as org.apache.solr.analysis
+ -->
+
+ <!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
+ <fieldType name="string" class="solr.StrField" sortMissingLast="true" />
+
+ <!-- boolean type: "true" or "false" -->
+ <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
- <!-- field type definitions... note that the "name" attribute is
- just a label to be used by field definitions. The "class"
- attribute and any other attributes determine the real type and
- behavior of the fieldtype.
+ <!-- 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.
+ -->
+ <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 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.
+
+ Note: For faster range queries, consider the tdate type
-->
+ <fieldType name="date" class="solr.TrieDateField" precisionStep="0" positionIncrementGap="0"/>
+
+ <!-- A Trie based date field for faster date range queries and date faceting. -->
+ <fieldType name="tdate" class="solr.TrieDateField" precisionStep="6" positionIncrementGap="0"/>
- <!-- numeric field types that store and index the text
- value verbatim (and hence don't sort correctly or support range queries.)
- These are provided more for backward compatability, allowing one
- to create a schema that matches an existing lucene index.
+
+ <!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
+ <fieldtype name="binary" class="solr.BinaryField"/>
+
+ <!--
+ Note:
+ These should only be used for compatibility with existing indexes (created with lucene or older Solr versions).
+ Use Trie based fields instead. As of Solr 3.5 and 4.x, Trie based fields support sortMissingFirst/Last
+
+ Plain numeric field types that store and index the text
+ value verbatim (and hence don't correctly support range queries, since the
+ lexicographic ordering isn't equal to the numeric ordering)
-->
<fieldType name="pint" class="solr.IntField"/>
<fieldType name="plong" class="solr.LongField"/>
- <fieldtype name="pfloat" class="solr.FloatField"/>
+ <fieldType name="pfloat" class="solr.FloatField"/>
<fieldType name="pdouble" class="solr.DoubleField"/>
+ <fieldType name="pdate" class="solr.DateField" sortMissingLast="true"/>
- <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="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
- <fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
-
- <!-- numeric field types that manipulate the value into
- a string value that isn't human readable in it's internal form,
- but sorts correctly and supports range queries.
-
- 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.
- 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.
- -->
- <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"/>
-
- <!-- bcd versions of sortable numeric type may provide smaller
- storage space and support very large numbers.
- -->
- <fieldtype name="bcdint" class="solr.BCDIntField" sortMissingLast="true"/>
- <fieldtype name="bcdlong" class="solr.BCDLongField" sortMissingLast="true"/>
- <fieldtype name="bcdstr" class="solr.BCDStrField" sortMissingLast="true"/>
-
- <!-- Field type demonstrating an Analyzer failure -->
- <fieldtype name="failtype1" class="solr.TextField">
- <analyzer type="index">
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- </analyzer>
- </fieldtype>
+ <!-- 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>
+ -->
- <!-- Demonstrating ignoreCaseChange -->
- <fieldtype name="wdf_nocase" class="solr.TextField">
+ <!-- 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.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
- </fieldtype>
+ </fieldType>
- <fieldtype name="wdf_preserve" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="0" preserveOriginal="1"/>
- <filter class="solr.LowerCaseFilterFactory"/>
+ <!-- A general text field that has reasonable, generic
+ cross-language defaults: it tokenizes with StandardTokenizer,
+ removes stop words from case-insensitive "stopwords.txt"
+ (empty by default), and down cases. At query time only, it
+ also applies synonyms. -->
+ <fieldType name="text_general" class="solr.TextField" positionIncrementGap="100">
+ <analyzer type="index">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ -->
+ <filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
- </fieldtype>
-
-
- <!-- HighlitText optimizes storage for (long) columns which will be highlit -->
- <fieldtype name="highlittext" class="solr.TextField" compressThreshold="345" />
-
- <fieldtype name="boolean" class="solr.BoolField" sortMissingLast="true"/>
- <fieldtype name="string" class="solr.StrField" sortMissingLast="true"/>
-
- <!-- format for date is 1995-12-31T23:59:59.999Z and only the fractional
- seconds part (.999) is optional.
- -->
- <fieldtype name="date" class="solr.TrieDateField" precisionStep="0"/>
- <fieldtype name="tdate" class="solr.TrieDateField" precisionStep="6"/>
- <fieldtype name="pdate" class="solr.DateField" sortMissingLast="true"/>
-
+ <analyzer type="query">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ </analyzer>
+ </fieldType>
- <!-- solr.TextField allows the specification of custom
- text analyzers specified as a tokenizer and a list
- of token filters.
- -->
- <fieldtype name="text" class="solr.TextField">
- <analyzer>
+ <!-- A text field with defaults appropriate for English: it
+ tokenizes with StandardTokenizer, removes English stop words
+ (lang/stopwords_en.txt), down cases, protects words from protwords.txt, and
+ finally applies Porter's stemming. The query time analyzer
+ also applies synonyms from synonyms.txt. -->
+ <fieldType name="text_en" class="solr.TextField" positionIncrementGap="100">
+ <analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.StandardFilterFactory"/>
+ <!-- in this example, we will only use synonyms at query time
+ <filter class="solr.SynonymFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
+ -->
+ <!-- Case insensitive stop word removal.
+ add enablePositionIncrements=true in both the index and query
+ analyzers to leave a 'gap' for more accurate phrase queries.
+ -->
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+
+ />
<filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory"/>
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ -->
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
- </fieldtype>
+ <analyzer type="query">
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+
+ />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.EnglishPossessiveFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <!-- Optionally you may want to use this less aggressive stemmer instead of PorterStemFilterFactory:
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ -->
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
+ <!-- A text field with defaults appropriate for English, plus
+ aggressive word-splitting and autophrase features enabled.
+ This field is just like text_en, except it adds
+ WordDelimiterFilter to enable splitting and matching of
+ words on case-change, alpha numeric boundaries, and
+ non-alphanumeric chars. This means certain compound word
+ cases will work, for example query "wi fi" will match
+ document "WiFi" or "wi-fi".
+ -->
+ <fieldType name="text_en_splitting" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+ <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"/>
+ -->
+ <!-- Case insensitive stop word removal.
+ add enablePositionIncrements=true in both the index and query
+ analyzers to leave a 'gap' for more accurate phrase queries.
+ -->
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+
+ />
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ <analyzer type="query">
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory"
+ ignoreCase="true"
+ words="lang/stopwords_en.txt"
+
+ />
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.PorterStemFilterFactory"/>
+ </analyzer>
+ </fieldType>
- <fieldtype name="nametext" class="solr.TextField">
- <analyzer class="org.apache.lucene.analysis.core.WhitespaceAnalyzer"/>
- </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="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
+ <analyzer>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
+ <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
+ <filter class="solr.EnglishMinimalStemFilterFactory"/>
+ <!-- this filter can remove any duplicate tokens that appear at the same position - sometimes
+ possible with WordDelimiterFilter in conjuncton with stemming. -->
+ <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
+ </analyzer>
+ </fieldType>
- <fieldtype name="teststop" class="solr.TextField">
+ <!-- Just like text_general except it reverses the characters of
+ each token, to enable more efficient leading wildcard queries. -->
+ <fieldType name="text_general_rev" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
- <tokenizer class="solr.LowerCaseTokenizerFactory"/>
- <filter class="solr.StandardFilterFactory"/>
- <filter class="solr.StopFilterFactory" words="stopwords.txt"/>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.ReversedWildcardFilterFactory" withOriginal="true"
+ maxPosAsterisk="3" maxPosQuestion="2" maxFractionAsterisk="0.33"/>
</analyzer>
<analyzer type="query">
- <tokenizer class="solr.LowerCaseTokenizerFactory"/>
- <filter class="solr.StandardFilterFactory"/>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
+ <filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
- </fieldtype>
+ </fieldType>
- <!-- fieldtypes in this section isolate tokenizers and tokenfilters for testing -->
- <fieldtype name="lowertok" class="solr.TextField">
- <analyzer><tokenizer class="solr.LowerCaseTokenizerFactory"/></analyzer>
- </fieldtype>
- <fieldtype name="keywordtok" class="solr.TextField">
- <analyzer><tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/></analyzer>
- </fieldtype>
- <fieldtype name="standardtok" class="solr.TextField">
- <analyzer><tokenizer class="solr.StandardTokenizerFactory"/></analyzer>
- </fieldtype>
- <fieldtype name="lettertok" class="solr.TextField">
- <analyzer><tokenizer class="solr.LetterTokenizerFactory"/></analyzer>
- </fieldtype>
- <fieldtype name="whitetok" class="solr.TextField">
- <analyzer><tokenizer class="solr.MockTokenizerFactory"/></analyzer>
- </fieldtype>
- <fieldtype name="HTMLstandardtok" class="solr.TextField">
+ <!-- charFilter + WhitespaceTokenizer -->
+ <!--
+ <fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
<analyzer>
- <charFilter class="solr.HTMLStripCharFilterFactory"/>
- <tokenizer class="solr.StandardTokenizerFactory"/>
+ <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
+ <tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
- </fieldtype>
- <fieldtype name="HTMLwhitetok" class="solr.TextField">
+ </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>
- <charFilter class="solr.HTMLStripCharFilterFactory"/>
- <tokenizer class="solr.MockTokenizerFactory"/>
+ <!-- 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://java.sun.com/j2se/1.6.0/docs/api/java/util/regex/package-summary.html
+ -->
+ <filter class="solr.PatternReplaceFilterFactory"
+ pattern="([^a-z])" replacement="" replace="all"
+ />
</analyzer>
- </fieldtype>
- <fieldtype name="standardtokfilt" class="solr.TextField">
+ </fieldType>
+
+ <!--
+ <fieldtype name="phonetic" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
- <filter class="solr.StandardFilterFactory"/>
+ <filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
</analyzer>
</fieldtype>
- <fieldtype name="standardfilt" class="solr.TextField">
+ -->
+
+ <fieldtype name="payloads" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.StandardFilterFactory"/>
+ <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>
- <fieldtype name="lowerfilt" class="solr.TextField">
+
+ <!-- lowercases the entire field value, keeping it as a single token. -->
+ <fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
<analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
+ <tokenizer class="solr.KeywordTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory" />
</analyzer>
- </fieldtype>
- <fieldtype name="lowerpunctfilt" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" expand="true"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="1" splitOnCaseChange="1"/>
- <filter class="solr.LowerCaseFilterFactory"/>
+ </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>
- </fieldtype>
- <fieldtype name="patternreplacefilt" class="solr.TextField">
+ <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.MockTokenizerFactory" pattern="keyword"/>
- <filter class="solr.PatternReplaceFilterFactory"
- pattern="([^a-zA-Z])" replacement="_" replace="all"
- />
+ <tokenizer class="solr.KeywordTokenizerFactory" />
</analyzer>
<analyzer type="query">
- <tokenizer class="solr.MockTokenizerFactory" pattern="keyword"/>
+ <tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
</analyzer>
- </fieldtype>
- <fieldtype name="patterntok" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.PatternTokenizerFactory" pattern=","/>
+ </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.
+ -->
+ <fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
+
+ <!-- A specialized field for geospatial search. If indexed, this fieldType must not be multivalued. -->
+ <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
+
+ <!--
+ 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"/>
+
+ <!-- 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 exhange 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" />
+
+
+
+ <!-- some examples for different languages (generally ordered by ISO code) -->
+
+ <!-- Arabic -->
+ <fieldType name="text_ar" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- for any non-arabic -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ar.txt"/>
+ <!-- normalizes ﻯ to ﻱ, etc -->
+ <filter class="solr.ArabicNormalizationFilterFactory"/>
+ <filter class="solr.ArabicStemFilterFactory"/>
</analyzer>
- </fieldtype>
- <fieldtype name="porterfilt" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.PorterStemFilterFactory"/>
+ </fieldType>
+
+ <!-- Bulgarian -->
+ <fieldType name="text_bg" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_bg.txt"/>
+ <filter class="solr.BulgarianStemFilterFactory"/>
</analyzer>
- </fieldtype>
- <!-- fieldtype name="snowballfilt" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.SnowballPorterFilterFactory"/>
+ </fieldType>
+
+ <!-- Catalan -->
+ <fieldType name="text_ca" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ca.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ca.txt"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Catalan"/>
</analyzer>
- </fieldtype -->
- <fieldtype name="engporterfilt" class="solr.TextField">
+ </fieldType>
+
+ <!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
+ <fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
<analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.PorterStemFilterFactory"/>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- normalize width before bigram, as e.g. half-width dakuten combine -->
+ <filter class="solr.CJKWidthFilterFactory"/>
+ <!-- for any non-CJK -->
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.CJKBigramFilterFactory"/>
</analyzer>
- </fieldtype>
- <fieldtype name="custengporterfilt" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.KeywordMarkerFilterFactory" protected="protwords.txt"/>
- <filter class="solr.PorterStemFilterFactory"/>
+ </fieldType>
+
+ <!-- Czech -->
+ <fieldType name="text_cz" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_cz.txt"/>
+ <filter class="solr.CzechStemFilterFactory"/>
</analyzer>
- </fieldtype>
- <fieldtype name="stopfilt" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" ignoreCase="true"/>
+ </fieldType>
+
+ <!-- Danish -->
+ <fieldType name="text_da" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_da.txt" format="snowball"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Danish"/>
</analyzer>
- </fieldtype>
- <fieldtype name="custstopfilt" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.StopFilterFactory" words="stopwords.txt"/>
+ </fieldType>
+
+ <!-- German -->
+ <fieldType name="text_de" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_de.txt" format="snowball"/>
+ <filter class="solr.GermanNormalizationFilterFactory"/>
+ <filter class="solr.GermanLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.GermanMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="German2"/> -->
</analyzer>
- </fieldtype>
- <fieldtype name="lengthfilt" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.LengthFilterFactory" min="2" max="5"/>
+ </fieldType>
+
+ <!-- Greek -->
+ <fieldType name="text_el" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- greek specific lowercase for sigma -->
+ <filter class="solr.GreekLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_el.txt"/>
+ <filter class="solr.GreekStemFilterFactory"/>
</analyzer>
- </fieldtype>
- <fieldType name="charfilthtmlmap" class="solr.TextField">
+ </fieldType>
+
+ <!-- Spanish -->
+ <fieldType name="text_es" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_es.txt" format="snowball"/>
+ <filter class="solr.SpanishLightStemFilterFactory"/>
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Spanish"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Basque -->
+ <fieldType name="text_eu" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_eu.txt"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Basque"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Persian -->
+ <fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
<analyzer>
- <charFilter class="solr.HTMLStripCharFilterFactory"/>
- <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
- <tokenizer class="solr.MockTokenizerFactory"/>
+ <!-- for ZWNJ -->
+ <charFilter class="solr.PersianCharFilterFactory"/>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.ArabicNormalizationFilterFactory"/>
+ <filter class="solr.PersianNormalizationFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fa.txt"/>
</analyzer>
</fieldType>
-
- <fieldtype name="subword" class="solr.TextField" multiValued="true" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory"/>
- <filter class="solr.PorterStemFilterFactory"/>
+
+ <!-- Finnish -->
+ <fieldType name="text_fi" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fi.txt" format="snowball"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Finnish"/>
+ <!-- less aggressive: <filter class="solr.FinnishLightStemFilterFactory"/> -->
</analyzer>
- <analyzer type="query">
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.StopFilterFactory"/>
- <filter class="solr.PorterStemFilterFactory"/>
+ </fieldType>
+
+ <!-- French -->
+ <fieldType name="text_fr" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_fr.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_fr.txt" format="snowball"/>
+ <filter class="solr.FrenchLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.FrenchMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="French"/> -->
</analyzer>
- </fieldtype>
-
- <fieldtype name="numericsubword" class="solr.TextField" multiValued="true" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1" generateNumberParts="0" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
- <filter class="solr.StopFilterFactory"/>
- <filter class="solr.PorterStemFilterFactory"/>
+ </fieldType>
+
+ <!-- Irish -->
+ <fieldType name="text_ga" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes d', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_ga.txt"/>
+ <!-- removes n-, etc. position increments is intentionally false! -->
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/hyphenations_ga.txt"/>
+ <filter class="solr.IrishLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ga.txt"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Irish"/>
</analyzer>
- <analyzer type="query">
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.StopFilterFactory"/>
- <filter class="solr.PorterStemFilterFactory"/>
+ </fieldType>
+
+ <!-- Galician -->
+ <fieldType name="text_gl" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_gl.txt"/>
+ <filter class="solr.GalicianStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.GalicianMinimalStemFilterFactory"/> -->
</analyzer>
- </fieldtype>
-
- <fieldtype name="protectedsubword" class="solr.TextField" multiValued="true" positionIncrementGap="100">
- <analyzer type="index">
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" protected="protwords.txt" splitOnNumerics="0" splitOnCaseChange="0" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
+ </fieldType>
+
+ <!-- Hindi -->
+ <fieldType name="text_hi" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <!-- normalizes unicode representation -->
+ <filter class="solr.IndicNormalizationFilterFactory"/>
+ <!-- normalizes variation in spelling -->
+ <filter class="solr.HindiNormalizationFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hi.txt"/>
+ <filter class="solr.HindiStemFilterFactory"/>
</analyzer>
- <analyzer type="query">
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
+ </fieldType>
+
+ <!-- Hungarian -->
+ <fieldType name="text_hu" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hu.txt" format="snowball"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Hungarian"/>
+ <!-- less aggressive: <filter class="solr.HungarianLightStemFilterFactory"/> -->
</analyzer>
- </fieldtype>
-
-
- <!-- more flexible in matching skus, but more chance of a false match -->
- <fieldtype name="skutype1" class="solr.TextField">
- <analyzer type="index">
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
+ </fieldType>
+
+ <!-- Armenian -->
+ <fieldType name="text_hy" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_hy.txt"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Armenian"/>
</analyzer>
- <analyzer type="query">
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
+ </fieldType>
+
+ <!-- Indonesian -->
+ <fieldType name="text_id" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_id.txt"/>
+ <!-- for a less aggressive approach (only inflectional suffixes), set stemDerivational to false -->
+ <filter class="solr.IndonesianStemFilterFactory" stemDerivational="true"/>
</analyzer>
- </fieldtype>
-
- <!-- less flexible in matching skus, but less chance of a false match -->
- <fieldtype name="skutype2" class="solr.TextField">
- <analyzer type="index">
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
+ </fieldType>
+
+ <!-- Italian -->
+ <fieldType name="text_it" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <!-- removes l', etc -->
+ <filter class="solr.ElisionFilterFactory" ignoreCase="true" articles="lang/contractions_it.txt"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt" format="snowball"/>
+ <filter class="solr.ItalianLightStemFilterFactory"/>
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Italian"/> -->
</analyzer>
- <analyzer type="query">
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
- <filter class="solr.LowerCaseFilterFactory"/>
+ </fieldType>
+
+ <!-- Latvian -->
+ <fieldType name="text_lv" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_lv.txt"/>
+ <filter class="solr.LatvianStemFilterFactory"/>
</analyzer>
- </fieldtype>
-
- <!-- less flexible in matching skus, but less chance of a false match -->
- <fieldtype name="syn" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory" synonyms="old_synonyms.txt"/>
+ </fieldType>
+
+ <!-- Dutch -->
+ <fieldType name="text_nl" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_nl.txt" format="snowball"/>
+ <filter class="solr.StemmerOverrideFilterFactory" dictionary="lang/stemdict_nl.txt" ignoreCase="false"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Dutch"/>
</analyzer>
- </fieldtype>
-
- <!-- Demonstrates How RemoveDuplicatesTokenFilter makes stemmed
- synonyms "better"
- -->
- <fieldtype name="dedup" class="solr.TextField">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.SynonymFilterFactory"
- synonyms="old_synonyms.txt" expand="true" />
- <filter class="solr.PorterStemFilterFactory"/>
- <filter class="solr.RemoveDuplicatesTokenFilterFactory" />
+ </fieldType>
+
+ <!-- Norwegian -->
+ <fieldType name="text_no" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_no.txt" format="snowball"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Norwegian"/>
+ <!-- less aggressive: <filter class="solr.NorwegianLightStemFilterFactory"/> -->
+ <!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory"/> -->
</analyzer>
- </fieldtype>
-
- <fieldtype name="unstored" class="solr.StrField" indexed="true" stored="false"/>
-
-
- <fieldtype name="textgap" class="solr.TextField" multiValued="true" positionIncrementGap="100">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- <filter class="solr.LowerCaseFilterFactory"/>
+ </fieldType>
+
+ <!-- Portuguese -->
+ <fieldType name="text_pt" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_pt.txt" format="snowball"/>
+ <filter class="solr.PortugueseLightStemFilterFactory"/>
+ <!-- less aggressive: <filter class="solr.PortugueseMinimalStemFilterFactory"/> -->
+ <!-- more aggressive: <filter class="solr.SnowballPorterFilterFactory" language="Portuguese"/> -->
+ <!-- most aggressive: <filter class="solr.PortugueseStemFilterFactory"/> -->
</analyzer>
- </fieldtype>
-
- <fieldType name="uuid" class="solr.UUIDField" />
-
- <!-- Try out some point types -->
- <fieldType name="xy" class="solr.PointType" dimension="2" subFieldType="double"/>
- <fieldType name="x" class="solr.PointType" dimension="1" subFieldType="double"/>
- <fieldType name="tenD" class="solr.PointType" dimension="10" subFieldType="double"/>
- <!-- Use the sub field suffix -->
- <fieldType name="xyd" class="solr.PointType" dimension="2" subFieldSuffix="_d1"/>
- <fieldtype name="geohash" class="solr.GeoHashField"/>
-
-
- <fieldType name="latLon" class="solr.LatLonType" subFieldType="double"/>
+ </fieldType>
+
+ <!-- Romanian -->
+ <fieldType name="text_ro" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ro.txt"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Romanian"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Russian -->
+ <fieldType name="text_ru" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ru.txt" format="snowball"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Russian"/>
+ <!-- less aggressive: <filter class="solr.RussianLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Swedish -->
+ <fieldType name="text_sv" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_sv.txt" format="snowball"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Swedish"/>
+ <!-- less aggressive: <filter class="solr.SwedishLightStemFilterFactory"/> -->
+ </analyzer>
+ </fieldType>
+
+ <!-- Thai -->
+ <fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.LowerCaseFilterFactory"/>
+ <filter class="solr.ThaiWordFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt"/>
+ </analyzer>
+ </fieldType>
+
+ <!-- Turkish -->
+ <fieldType name="text_tr" class="solr.TextField" positionIncrementGap="100">
+ <analyzer>
+ <tokenizer class="solr.StandardTokenizerFactory"/>
+ <filter class="solr.TurkishLowerCaseFilterFactory"/>
+ <filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt"/>
+ <filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
+ </analyzer>
+ </fieldType>
- <!-- Currency type -->
- <fieldType name="currency" class="solr.CurrencyField" currencyConfig="currency.xml" multiValued="false" />
- <fieldType name="mock_currency" class="solr.CurrencyField" providerClass="solr.MockExchangeRateProvider" foo="bar" multiValued="false" />
- <fieldType name="oer_currency"
- class="solr.CurrencyField"
- multiValued="false"
- providerClass="solr.OpenExchangeRatesOrgProvider"
- ratesFileLocation="open-exchange-rates.json" />
-
- <!-- omitPositions example -->
- <fieldType name="nopositions" class="solr.TextField" omitPositions="true">
- <analyzer>
- <tokenizer class="solr.MockTokenizerFactory"/>
- </analyzer>
- </fieldType>
+ </types>
- <fieldType name="location" class="solr.LatLonType" subFieldSuffix="_coordinate"/>
-
- <!--
- Example of using PathHierarchyTokenizerFactory at index time, so
- queries for paths match documents at that path, or in descendent paths
- -->
- <fieldType name="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>
-
-</types>
-
-
- <fields>
- <field name="id" type="int" indexed="true" stored="true" multiValued="false" required="false"/>
- <field name="_root_" type="int" indexed="true" stored="true" multiValued="false" required="false"/>
-
- <field name="signatureField" type="string" indexed="true" stored="false"/>
- <field name="uuid" type="uuid" stored="true" />
- <field name="name" type="nametext" indexed="true" stored="true"/>
- <field name="text" type="text" indexed="true" stored="false"/>
- <field name="subject" type="text" indexed="true" stored="true"/>
- <field name="title" type="nametext" indexed="true" stored="true"/>
- <field name="weight" type="float" indexed="true" stored="true" multiValued="false"/>
- <field name="bday" type="date" indexed="true" stored="true" multiValued="false"/>
-
- <field name="title_stemmed" type="text" indexed="true" stored="false"/>
- <field name="title_lettertok" type="lettertok" indexed="true" stored="false"/>
-
- <field name="syn" type="syn" indexed="true" stored="true"/>
-
- <!-- to test property inheritance and overriding -->
- <field name="shouldbeunstored" type="unstored" />
- <field name="shouldbestored" type="unstored" stored="true"/>
- <field name="shouldbeunindexed" type="unstored" indexed="false" stored="true"/>
-
- <!-- Test points -->
- <!-- Test points -->
- <field name="home" type="xy" indexed="true" stored="true" multiValued="false"/>
- <field name="x" type="x" indexed="true" stored="true" multiValued="false"/>
- <field name="homed" type="xyd" indexed="true" stored="true" multiValued="false"/>
- <field name="home_ns" type="xy" indexed="true" stored="false" multiValued="false"/>
- <field name="work" type="xy" indexed="true" stored="true" multiValued="false"/>
-
- <field name="home_ll" type="latLon" indexed="true" stored="true" multiValued="false"/>
- <field name="work_ll" type="latLon" indexed="true" stored="true" multiValued="false"/>
-
- <field name="home_gh" type="geohash" indexed="true" stored="true" multiValued="false"/>
-
-
- <field name="point10" type="tenD" indexed="true" stored="true" multiValued="false"/>
-
- <!-- Test currency -->
- <field name="amount" type="currency" indexed="true" stored="true" multiValued="false"/>
- <field name="mock_amount" type="mock_currency" indexed="true" stored="true"/>
- <field name="oer_amount" type="oer_currency" indexed="true" stored="true"/>
-
- <!-- test different combinations of indexed and stored -->
- <field name="bind" type="boolean" indexed="true" stored="false"/>
- <field name="bsto" type="boolean" indexed="false" stored="true"/>
- <field name="bindsto" type="boolean" indexed="true" stored="true"/>
- <field name="isto" type="int" indexed="false" stored="true"/>
- <field name="iind" type="int" indexed="true" stored="false"/>
- <field name="ssto" type="string" indexed="false" stored="true"/>
- <field name="sind" type="string" indexed="true" stored="false"/>
- <field name="sindsto" type="string" indexed="true" stored="true"/>
-
- <!-- test combinations of term vector settings -->
- <field name="test_basictv" type="text" termVectors="true"/>
- <field name="test_notv" type="text" termVectors="false"/>
- <field name="test_postv" type="text" termVectors="true" termPositions="true"/>
- <field name="test_offtv" type="text" termVectors="true" termOffsets="true"/>
- <field name="test_posofftv" type="text" termVectors="true"
- termPositions="true" termOffsets="true"/>
-
- <!-- test valid combinations of indexed settings,
- see also BadIndexSchemaTest -->
- <!-- indexed=false should not prevent omit___=true -->
- <field name="pint_i_norm" type="pint" omitNorms="true"
- indexed="false" />
- <field name="pint_i_tf" type="pint" omitTermFreqAndPositions="true"
- indexed="false" />
- <field name="pint_i_pos" type="pint" omitPositions="true"
- indexed="false" />
- <field name="pint_i_all" type="pint"
- indexed="false"
- omitNorms="true"
- omitTermFreqAndPositions="true"
- omitPositions="true" />
- <!-- omitTermFreqAndPositions=false and omitPositions=true are ok -->
- <field name="pint_tf_pos" type="pint" indexed="true"
- omitTermFreqAndPositions="false" omitPositions="true" />
-
- <!-- test highlit field settings -->
- <field name="test_hlt" type="highlittext" indexed="true"/>
- <field name="test_hlt_off" type="highlittext" indexed="true"/>
-
- <!-- fields to test individual tokenizers and tokenfilters -->
- <field name="teststop" type="teststop" indexed="true" stored="true"/>
- <field name="lowertok" type="lowertok" indexed="true" stored="true"/>
- <field name="keywordtok" type="keywordtok" indexed="true" stored="true"/>
- <field name="standardtok" type="standardtok" indexed="true" stored="true"/>
- <field name="HTMLstandardtok" type="HTMLstandardtok" indexed="true" stored="true"/>
- <field name="lettertok" type="lettertok" indexed="true" stored="true"/>
- <field name="whitetok" type="whitetok" indexed="true" stored="true"/>
- <field name="HTMLwhitetok" type="HTMLwhitetok" indexed="true" stored="true"/>
- <field name="standardtokfilt" type="standardtokfilt" indexed="true" stored="true"/>
- <field name="standardfilt" type="standardfilt" indexed="true" stored="true"/>
- <field name="lowerfilt" type="lowerfilt" indexed="true" stored="true"/>
- <field name="lowerfilt1" type="lowerfilt" indexed="true" stored="true"/>
- <field name="lowerfilt1and2" type="lowerfilt" indexed="true" stored="true"/>
- <field name="patterntok" type="patterntok" indexed="true" stored="true"/>
- <field name="patternreplacefilt" type="patternreplacefilt" indexed="true" stored="true"/>
- <field name="porterfilt" type="porterfilt" indexed="true" stored="true"/>
- <field name="engporterfilt" type="engporterfilt" indexed="true" stored="true"/>
- <field name="custengporterfilt" type="custengporterfilt" indexed="true" stored="true"/>
- <field name="stopfilt" type="stopfilt" indexed="true" stored="true"/>
- <field name="custstopfilt" type="custstopfilt" indexed="true" stored="true"/>
- <field name="lengthfilt" type="lengthfilt" indexed="true" stored="true"/>
- <field name="dedup" type="dedup" indexed="true" stored="true"/>
- <field name="wdf_nocase" type="wdf_nocase" indexed="true" stored="true"/>
- <field name="wdf_preserve" type="wdf_preserve" indexed="true" stored="true"/>
-
- <field name="numberpartfail" type="failtype1" indexed="true" stored="true"/>
-
- <field name="nullfirst" type="string" indexed="true" stored="true" sortMissingFirst="true" multiValued="false"/>
-
-
- <field name="cat" type="string" indexed="true" stored="true" multiValued="true"/>
- <field name="price" type="float" indexed="true" stored="true"/>
- <field name="inStock" type="boolean" indexed="true" stored="true" />
-
- <field name="subword" type="subword" indexed="true" stored="true"/>
- <field name="subword_offsets" type="subword" indexed="true" stored="true" termVectors="true" termOffsets="true"/>
- <field name="numericsubword" type="numericsubword" indexed="true" stored="true"/>
- <field name="protectedsubword" type="protectedsubword" indexed="true" stored="true"/>
-
- <field name="sku1" type="skutype1" indexed="true" stored="true"/>
- <field name="sku2" type="skutype2" indexed="true" stored="true"/>
-
- <field name="textgap" type="textgap" indexed="true" stored="true"/>
-
- <field name="timestamp" type="date" indexed="true" stored="true" docValues="true" default="NOW" multiValued="false"/>
- <field name="multiDefault" type="string" indexed="true" stored="true" default="muLti-Default" multiValued="true"/>
- <field name="intDefault" type="int" indexed="true" stored="true" default="42" multiValued="false"/>
-
- <field name="nopositionstext" type="nopositions" indexed="true" stored="true"/>
-
- <field name="tlong" type="tlong" indexed="true" stored="true" />
-
- <field name="_version_" type="long" indexed="true" stored="true" multiValued="false"/>
-
- <field name="title_stringNoNorms" type="string" omitNorms="true" indexed="true" stored="true"/>
-
- <field name="store" type="location" indexed="true" stored="true" omitNorms="false"/>
-
- <field name="lower" type="lowertok" indexed="false" stored="true" multiValued="true" />
- <field name="_route_" type="string" indexed="true" stored="true" 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="int" indexed="true" stored="true"/>
- <dynamicField name="*_i1" type="int" indexed="true" stored="true" multiValued="false"/>
-
- <dynamicField name="*_s" type="string" indexed="true" stored="true"/>
- <dynamicField name="*_s1" type="string" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="*_l" type="long" indexed="true" stored="true"/>
- <dynamicField name="*_l1" type="long" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="*_t" type="text" indexed="true" stored="true"/>
- <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
- <dynamicField name="*_b1" type="boolean" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="*_f" type="float" indexed="true" stored="true"/>
- <dynamicField name="*_f1" type="float" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="*_d" type="double" indexed="true" stored="true"/>
- <dynamicField name="*_d1" type="double" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
- <dynamicField name="*_dt1" type="date" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="*_bcd" type="bcdstr" indexed="true" stored="true"/>
-
-
- <!-- some trie-coded dynamic fields for faster range queries -->
- <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/>
- <dynamicField name="*_ti1" type="tint" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/>
- <dynamicField name="*_tl1" type="tlong" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/>
- <dynamicField name="*_tf1" type="tfloat" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/>
- <dynamicField name="*_td1" type="tdouble" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="*_tds" type="tdouble" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/>
- <dynamicField name="*_tdt1" type="tdate" indexed="true" stored="true" multiValued="false"/>
-
- <dynamicField name="*_si" type="sint" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="*_sl" type="slong" indexed="true" stored="true"/>
- <dynamicField name="*_sf" type="sfloat" indexed="true" stored="true"/>
- <dynamicField name="*_sf1" type="sfloat" indexed="true" stored="true" multiValued="false"/>
- <dynamicField name="*_sd" type="sdouble" indexed="true" stored="true"/>
- <dynamicField name="*_sd1" type="sdouble" indexed="true" stored="true" multiValued="false"/>
-
- <dynamicField name="*_pi" type="pint" indexed="true" stored="true"/>
- <dynamicField name="*_pf" type="pfloat" indexed="true" stored="true"/>
- <dynamicField name="*_pl" type="plong" indexed="true" stored="true"/>
- <dynamicField name="*_pd" type="pdouble" indexed="true" stored="true"/>
- <dynamicField name="*_pdt" type="pdate" indexed="true" stored="true"/>
-
-
- <dynamicField name="*_sI" type="string" indexed="true" stored="false"/>
- <dynamicField name="*_sS" type="string" indexed="false" stored="true"/>
- <dynamicField name="t_*" type="text" indexed="true" stored="true"/>
- <dynamicField name="tv_*" type="text" indexed="true" stored="true"
- termVectors="true" termPositions="true" termOffsets="true"/>
- <dynamicField name="tv_mv_*" type="text" indexed="true" stored="true" multiValued="true"
- termVectors="true" termPositions="true" termOffsets="true"/>
- <dynamicField name="tv_no_off_*" type="text" indexed="true" stored="true"
- termVectors="true" termPositions="true"/>
-
- <dynamicField name="*_p" type="xyd" indexed="true" stored="true" multiValued="false"/>
-
- <!-- special fields for dynamic copyField test -->
- <dynamicField name="dynamic_*" type="string" indexed="true" stored="true"/>
- <dynamicField name="*_dynamic" type="string" indexed="true" stored="true"/>
-
- <!-- for testing to ensure that longer patterns are matched first -->
- <dynamicField name="*aa" type="string" indexed="true" stored="true"/>
- <dynamicField name="*aaa" type="pint" indexed="false" stored="true"/>
-
- <!-- ignored becuase not stored or indexed -->
- <dynamicField name="*_ignored" type="text" indexed="false" stored="false"/>
-
- <dynamicField name="*_mfacet" type="string" indexed="true" stored="false" multiValued="true" />
-
- <!-- Type used to index the lat and lon components for the "location" FieldType -->
- <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" omitNorms="true" />
-
- <dynamicField name="*_path" type="path" indexed="true" stored="true" omitNorms="true" multiValued="true" />
- <dynamicField name="*_ancestor" type="ancestor_path" indexed="true" stored="true" omitNorms="true" multiValued="true" />
-
- </fields>
-
- <defaultSearchField>text</defaultSearchField>
- <uniqueKey>id</uniqueKey>
+ <!-- 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>
+ -->
- <!-- 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="title" dest="title_stemmed"/>
- <copyField source="title" dest="title_lettertok"/>
- <copyField source="title" dest="title_stringNoNorms"/>
-
- <copyField source="title" dest="text"/>
- <copyField source="subject" dest="text"/>
-
- <copyField source="lowerfilt1" dest="lowerfilt1and2"/>
- <copyField source="lowerfilt" dest="lowerfilt1and2"/>
-
- <copyField source="*_t" dest="text"/>
-
- <copyField source="id" dest="range_facet_si"/>
- <copyField source="id" dest="range_facet_l"/>
- <copyField source="id" dest="range_facet_sl"/>
- <copyField source="range_facet_f" dest="range_facet_sf"/>
- <copyField source="range_facet_f" dest="range_facet_d"/>
- <copyField source="range_facet_f" dest="range_facet_sd"/>
-
- <copyField source="bday" dest="bday_pdt"/>
- <copyField source="a_tdt" dest="a_pdt"/>
-
- <!-- dynamic destination -->
- <copyField source="*_dynamic" dest="dynamic_*"/>
- <copyField source="*_path" dest="*_ancestor"/>
-
- <!-- example of a custom similarity -->
- <similarity class="solr.CustomSimilarityFactory">
- <str name="echo">I am your default sim</str>
- </similarity>
</schema>