schema_sample1.xml

<field name="title" type="watson_text_ja" indexed="true" stored="true" required="false" multiValued="true" />

<field name="body" type="watson_text_ja" indexed="true" stored="true" required="false" multiValued="true" />

<!-- make a copy field using normal OOB solr text_en -->

<field name="text" type="text_ja" indexed="true" stored="false" required="false" multiValued="true" />

<!-- make a copy field using watson_text_ja -->

<field name="watson_text" type="watson_text_ja" indexed="true" stored="false" required="false" multiValued="true" />

<copyField source="title" dest="text"/>

<copyField source="body" dest="text"/>

<copyField source="title" dest="watson_text"/>

<copyField source="body" dest="watson_text"/>

<fieldType name="text_ja" indexed="true" class="solr.TextField" positionIncrementGap="100">

<analyzer type="index">

<tokenizer class="solr.JapaneseTokenizerFactory"/>

<filter class="solr.JapaneseBaseFormFilterFactory"/>

<filter class="solr.CJKWidthFilterFactory"/>

<filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>

<filter class="solr.LowerCaseFilterFactory"/>

</analyzer>

<analyzer type="query">

<tokenizer class="solr.JapaneseTokenizerFactory"/>

<filter class="solr.JapaneseBaseFormFilterFactory"/>

<filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt"/>

<filter class="solr.CJKWidthFilterFactory"/>

<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt"/>

<filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>

<filter class="solr.LowerCaseFilterFactory"/>

</analyzer>

</fieldType>

<?xml version="1.0" encoding="UTF-8" ?><!-- Licensed to the Apache Software Foundation (ASF) under one or more contributor license agreements. See the NOTICE file distributed with this work for additional information regarding copyright ownership. The ASF licenses this file to You under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License.--><!-- This is the Solr schema file. This file should be named "schema.xml" and should be in the conf directory under the solr home (i.e. ./solr/conf/schema.xml by default) or located where the classloader for the Solr webapp can find it. This example schema is the recommended starting point for users. It should be kept correct and concise, usable out-of-the-box. For more information, on how to customize this file, please see http://wiki.apache.org/solr/SchemaXml--><schema name="example" version="1.5"> <!-- 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...) --> <!-- 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". Do NOT change the type and apply index-time analysis to the <uniqueKey> as it will likely make routing in SolrCloud and document replacement in general fail. Limited _query_ time analysis is possible as long as the indexing process is guaranteed to index the term in a compatible way. Any analysis applied to the <uniqueKey> should _not_ produce multiple tokens --> <field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" /> <field name="title" type="watson_text_ja" indexed="true" stored="true" required="false" multiValued="true" /> <field name="body" type="watson_text_ja" indexed="true" stored="true" required="false" multiValued="true" /> <!-- make a copy field using normal OOB solr text_en --> <field name="text" type="text_ja" indexed="true" stored="false" required="false" multiValued="true" /> <!-- make a copy field using watson_text_ja --> <field name="watson_text" type="watson_text_ja" indexed="true" stored="false" required="false" multiValued="true" /> <copyField source="title" dest="text"/> <copyField source="body" dest="text"/> <copyField source="title" dest="watson_text"/> <copyField source="body" dest="watson_text"/> <!-- Dynamic field definitions allow using convention over configuration for fields via the specification of patterns to match field names. EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i) RESTRICTION: the glob-like pattern in the name attribute must have a "*" only at the start or the end. --> <dynamicField name="*_i" type="int" indexed="true" stored="true"/> <dynamicField name="*_is" type="int" indexed="true" stored="true" multiValued="true"/> <dynamicField name="*_s" type="string" indexed="true" stored="true" /> <dynamicField name="*_ss" type="string" indexed="true" stored="true" multiValued="true"/> <dynamicField name="*_l" type="long" indexed="true" stored="true"/> <dynamicField name="*_ls" type="long" indexed="true" stored="true" multiValued="true"/> <dynamicField name="*_t" type="text_general" indexed="true" stored="true"/> <dynamicField name="*_txt" type="text_general" indexed="true" stored="true" multiValued="true"/> <dynamicField name="*_en" type="text_en" indexed="true" stored="true" multiValued="true"/> <!-- just in case someone builds an *_en automatically. --> <dynamicField name="*_ja" type="text_ja" indexed="true" stored="true" multiValued="true"/> <dynamicField name="*_b" type="boolean" indexed="true" stored="true"/> <dynamicField name="*_bs" type="boolean" indexed="true" stored="true" multiValued="true"/> <dynamicField name="*_f" type="float" indexed="true" stored="true"/> <dynamicField name="*_fs" type="float" indexed="true" stored="true" multiValued="true"/> <dynamicField name="*_d" type="double" indexed="true" stored="true"/> <dynamicField name="*_ds" type="double" indexed="true" stored="true" multiValued="true"/> <!-- Type used to index the lat and lon components for the "location" FieldType --> <dynamicField name="*_coordinate" type="tdouble" indexed="true" stored="false" /> <dynamicField name="*_dt" type="date" indexed="true" stored="true"/> <dynamicField name="*_dts" type="date" indexed="true" stored="true" multiValued="true"/> <dynamicField name="*_p" type="location" indexed="true" stored="true"/> <!-- some trie-coded dynamic fields for faster range queries --> <dynamicField name="*_ti" type="tint" indexed="true" stored="true"/> <dynamicField name="*_tl" type="tlong" indexed="true" stored="true"/> <dynamicField name="*_tf" type="tfloat" indexed="true" stored="true"/> <dynamicField name="*_td" type="tdouble" indexed="true" stored="true"/> <dynamicField name="*_tdt" type="tdate" indexed="true" stored="true"/> <dynamicField name="*_c" type="currency" indexed="true" stored="true"/> <dynamicField name="ignored_*" type="ignored" multiValued="true"/> <dynamicField name="attr_*" type="text_general" indexed="true" stored="true" multiValued="true"/> <dynamicField name="random_*" type="random" /> <!-- uncomment the following to ignore any fields that don't already match an existing field name or dynamic field, rather than reporting them as an error. alternately, change the type="ignored" to some other type e.g. "text" if you want unknown fields indexed and/or stored by default --> <!--dynamicField name="*" type="ignored" multiValued="true" /--> <!-- 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> <!-- copyField commands copy one field to another at the time a document is added to the index. It's used either to index the same field differently, or to add multiple fields to the same field for easier/faster searching. --> <!-- <copyField source="title" dest="text"/> <copyField source="body" dest="text"/> --> <!-- 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 --> <fieldType name="watson_text_ja" indexed="true" stored="true" class="com.ibm.watson.hector.plugins.fieldtype.WatsonTextField"> <analyzer type="index"> <tokenizer class="solr.JapaneseTokenizerFactory"/> <filter class="solr.JapaneseBaseFormFilterFactory"/> <filter class="solr.CJKWidthFilterFactory"/> <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/> <filter class="solr.LowerCaseFilterFactory"/> </analyzer> <analyzer type="query"> <tokenizer class="solr.JapaneseTokenizerFactory"/> <filter class="solr.JapaneseBaseFormFilterFactory"/> <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt"/> <filter class="solr.CJKWidthFilterFactory"/> <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt"/> <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/> <filter class="solr.LowerCaseFilterFactory"/> </analyzer> </fieldType> <!-- 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" sortMissingLast="true" /> <!-- boolean type: "true" or "false" --> <fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/> <!-- 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 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"/> <!-- 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" positionIncrementGap="100"> <analyzer> <tokenizer class="solr.WhitespaceTokenizerFactory"/> </analyzer> </fieldType> <!-- 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> <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> <fieldType name="text_ja" indexed="true" class="solr.TextField" positionIncrementGap="100"> <analyzer type="index"> <tokenizer class="solr.JapaneseTokenizerFactory"/> <filter class="solr.JapaneseBaseFormFilterFactory"/> <filter class="solr.CJKWidthFilterFactory"/> <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/> <filter class="solr.LowerCaseFilterFactory"/> </analyzer> <analyzer type="query"> <tokenizer class="solr.JapaneseTokenizerFactory"/> <filter class="solr.JapaneseBaseFormFilterFactory"/> <filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt"/> <filter class="solr.CJKWidthFilterFactory"/> <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt"/> <filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/> <filter class="solr.LowerCaseFilterFactory"/> </analyzer> </fieldType> <!-- 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"/> <!-- 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="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> <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. --> <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> <!-- 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> <!-- 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.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.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> <!-- This is an example of using the KeywordTokenizer along With various TokenFilterFactories to produce a sortable field that does not include some properties of the source text --> <fieldType name="alphaOnlySort" class="solr.TextField" sortMissingLast="true" omitNorms="true"> <analyzer> <!-- KeywordTokenizer does no actual tokenizing, so the entire input string is preserved as a single token --> <tokenizer class="solr.KeywordTokenizerFactory"/> <!-- The LowerCase TokenFilter does what you expect, which can be when you want your sorting to be case insensitive --> <filter class="solr.LowerCaseFilterFactory" /> <!-- The TrimFilter removes any leading or trailing whitespace --> <filter class="solr.TrimFilterFactory" /> <!-- The PatternReplaceFilter gives you the flexibility to use Java Regular expression to replace any sequence of characters matching a pattern with an arbitrary replacement string, which may include back 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/7/docs/api/java/util/regex/package-summary.html --> <filter class="solr.PatternReplaceFilterFactory" pattern="([^a-z])" replacement="" replace="all" /> </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> <!-- 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"/> <!-- 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" /> <!-- 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" /> <similarity class="org.apache.lucene.search.similarities.LMDirichletSimilarity"/> </schema>