forked from D-Net/dnet-hadoop
1004 lines
53 KiB
XML
1004 lines
53 KiB
XML
<?xml version="1.0" encoding="UTF-8" ?>
|
|
<!--
|
|
Licensed to the Apache Software Foundation (ASF) under one or more
|
|
contributor license agreements. See the NOTICE file distributed with
|
|
this work for additional information regarding copyright ownership.
|
|
The ASF licenses this file to You under the Apache License, Version 2.0
|
|
(the "License"); you may not use this file except in compliance with
|
|
the License. You may obtain a copy of the License at
|
|
|
|
http://www.apache.org/licenses/LICENSE-2.0
|
|
|
|
Unless required by applicable law or agreed to in writing, software
|
|
distributed under the License is distributed on an "AS IS" BASIS,
|
|
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
See the License for the specific language governing permissions and
|
|
limitations under the License.
|
|
-->
|
|
|
|
<!--
|
|
|
|
This 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://lucene.apache.org/solr/guide/documents-fields-and-schema-design.html
|
|
|
|
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.
|
|
-->
|
|
|
|
<schema name="testConfig" version="1.6">
|
|
<!-- attribute "name" is the name of this schema and is only used for display purposes.
|
|
version="x.y" is Solr's version number for the schema syntax and
|
|
semantics. It should not normally be changed by applications.
|
|
|
|
1.0: multiValued attribute did not exist, all fields are multiValued
|
|
by nature
|
|
1.1: multiValued attribute introduced, false by default
|
|
1.2: omitTermFreqAndPositions attribute introduced, true by default
|
|
except for text fields.
|
|
1.3: removed optional field compress feature
|
|
1.4: autoGeneratePhraseQueries attribute introduced to drive QueryParser
|
|
behavior when a single string produces multiple tokens. Defaults
|
|
to off for version >= 1.4
|
|
1.5: omitNorms defaults to true for primitive field types
|
|
(int, float, boolean, string...)
|
|
1.6: useDocValuesAsStored defaults to true.
|
|
-->
|
|
|
|
<!-- Valid attributes for fields:
|
|
name: mandatory - the name for the field
|
|
type: mandatory - the name of a field type from the
|
|
fieldTypes 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 is
|
|
recommended (required, if you are using *Point fields) for faceting,
|
|
grouping, sorting and function queries. Doc Values will make the index
|
|
faster to load, more NRT-friendly and more memory-efficient.
|
|
They are currently only supported by StrField, UUIDField, all
|
|
*PointFields, 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.
|
|
-->
|
|
|
|
<!-- In this _default configset, only four fields are pre-declared:
|
|
id, _version_, and _text_ and _root_. All other fields will be type guessed and added via the
|
|
"add-unknown-fields-to-the-schema" update request processor chain declared in solrconfig.xml.
|
|
|
|
Note that many dynamic fields are also defined - you can use them to specify a
|
|
field's type via field naming conventions - see below.
|
|
|
|
WARNING: The _text_ catch-all field will significantly increase your index size.
|
|
If you don't need it, consider removing it and the corresponding copyField directive.
|
|
-->
|
|
|
|
<field name="id" type="string" indexed="true" stored="true" required="true" multiValued="false" />
|
|
<!-- docValues are enabled by default for long type so we don't need to index the version field -->
|
|
<field name="_version_" type="plong" indexed="false" stored="false"/>
|
|
<field name="_root_" type="string" indexed="true" stored="false" docValues="false" />
|
|
<field name="_text_" type="text_general" indexed="true" stored="false" multiValued="true"/>
|
|
|
|
<!-- This can be enabled, in case the client does not know what fields may be searched. It isn't enabled by default
|
|
because it's very expensive to index everything twice. -->
|
|
<!-- <copyField source="*" dest="_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="pint" indexed="true" stored="true"/>
|
|
<dynamicField name="*_is" type="pints" indexed="true" stored="true"/>
|
|
<dynamicField name="*_s" type="string" indexed="true" stored="true" />
|
|
<dynamicField name="*_ss" type="strings" indexed="true" stored="true"/>
|
|
<dynamicField name="*_l" type="plong" indexed="true" stored="true"/>
|
|
<dynamicField name="*_ls" type="plongs" indexed="true" stored="true"/>
|
|
<dynamicField name="*_t" type="text_general" indexed="true" stored="true" multiValued="false"/>
|
|
<dynamicField name="*_txt" type="text_general" indexed="true" stored="true"/>
|
|
<dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
|
|
<dynamicField name="*_bs" type="booleans" indexed="true" stored="true"/>
|
|
<dynamicField name="*_f" type="pfloat" indexed="true" stored="true"/>
|
|
<dynamicField name="*_fs" type="pfloats" indexed="true" stored="true"/>
|
|
<dynamicField name="*_d" type="pdouble" indexed="true" stored="true"/>
|
|
<dynamicField name="*_ds" type="pdoubles" indexed="true" stored="true"/>
|
|
<dynamicField name="random_*" type="random"/>
|
|
|
|
<!-- Type used for data-driven schema, to add a string copy for each text field -->
|
|
<dynamicField name="*_str" type="strings" stored="false" docValues="true" indexed="false" useDocValuesAsStored="false"/>
|
|
|
|
<dynamicField name="*_dt" type="pdate" indexed="true" stored="true"/>
|
|
<dynamicField name="*_dts" type="pdate" indexed="true" stored="true" multiValued="true"/>
|
|
<dynamicField name="*_p" type="location" indexed="true" stored="true"/>
|
|
<dynamicField name="*_srpt" type="location_rpt" indexed="true" stored="true"/>
|
|
|
|
<!-- payloaded dynamic fields -->
|
|
<dynamicField name="*_dpf" type="delimited_payloads_float" indexed="true" stored="true"/>
|
|
<dynamicField name="*_dpi" type="delimited_payloads_int" indexed="true" stored="true"/>
|
|
<dynamicField name="*_dps" type="delimited_payloads_string" indexed="true" stored="true"/>
|
|
|
|
<dynamicField name="attr_*" type="text_general" indexed="true" stored="true" 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="sourceFieldName" dest="destinationFieldName"/>
|
|
-->
|
|
|
|
<!-- 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
|
|
-->
|
|
|
|
<!-- 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", "pint", "pfloat", "plong", "pdate", "pdouble".
|
|
- 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.
|
|
-->
|
|
|
|
<!-- The StrField type is not analyzed, but indexed/stored verbatim. -->
|
|
<fieldType name="string" class="solr.StrField" sortMissingLast="true" docValues="true" />
|
|
<fieldType name="strings" class="solr.StrField" sortMissingLast="true" multiValued="true" docValues="true" />
|
|
|
|
<!-- boolean type: "true" or "false" -->
|
|
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true"/>
|
|
<fieldType name="booleans" class="solr.BoolField" sortMissingLast="true" multiValued="true"/>
|
|
|
|
<!--
|
|
Numeric field types that index values using KD-trees.
|
|
Point fields don't support FieldCache, so they must have docValues="true" if needed for sorting, faceting, functions, etc.
|
|
-->
|
|
<fieldType name="pint" class="solr.IntPointField" docValues="true"/>
|
|
<fieldType name="pfloat" class="solr.FloatPointField" docValues="true"/>
|
|
<fieldType name="plong" class="solr.LongPointField" docValues="true"/>
|
|
<fieldType name="pdouble" class="solr.DoublePointField" docValues="true"/>
|
|
|
|
<fieldType name="pints" class="solr.IntPointField" docValues="true" multiValued="true"/>
|
|
<fieldType name="pfloats" class="solr.FloatPointField" docValues="true" multiValued="true"/>
|
|
<fieldType name="plongs" class="solr.LongPointField" docValues="true" multiValued="true"/>
|
|
<fieldType name="pdoubles" class="solr.DoublePointField" docValues="true" multiValued="true"/>
|
|
<fieldType name="random" class="solr.RandomSortField" indexed="true"/>
|
|
|
|
|
|
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
|
|
is a more restricted form of the canonical representation of dateTime
|
|
http://www.w3.org/TR/xmlschema-2/#dateTime
|
|
The trailing "Z" designates UTC time and is mandatory.
|
|
Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
|
|
All other components are mandatory.
|
|
|
|
Expressions can also be used to denote calculations that should be
|
|
performed relative to "NOW" to determine the value, ie...
|
|
|
|
NOW/HOUR
|
|
... Round to the start of the current hour
|
|
NOW-1DAY
|
|
... Exactly 1 day prior to now
|
|
NOW/DAY+6MONTHS+3DAYS
|
|
... 6 months and 3 days in the future from the start of
|
|
the current day
|
|
|
|
-->
|
|
<!-- KD-tree versions of date fields -->
|
|
<fieldType name="pdate" class="solr.DatePointField" docValues="true"/>
|
|
<fieldType name="pdates" class="solr.DatePointField" docValues="true" multiValued="true"/>
|
|
|
|
<!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
|
|
<fieldType name="binary" class="solr.BinaryField"/>
|
|
|
|
<!-- 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://lucene.apache.org/solr/guide/understanding-analyzers-tokenizers-and-filters.html#understanding-analyzers-tokenizers-and-filters
|
|
-->
|
|
|
|
<!-- 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 -->
|
|
<dynamicField name="*_ws" type="text_ws" indexed="true" stored="true"/>
|
|
<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" multiValued="true">
|
|
<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.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
|
<filter class="solr.FlattenGraphFilterFactory"/>
|
|
-->
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
|
|
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
|
|
<!-- SortableTextField generaly functions exactly like TextField,
|
|
except that it supports, and by default uses, docValues for sorting (or faceting)
|
|
on the first 1024 characters of the original field values (which is configurable).
|
|
|
|
This makes it a bit more useful then TextField in many situations, but the trade-off
|
|
is that it takes up more space on disk; which is why it's not used in place of TextField
|
|
for every fieldType in this _default schema.
|
|
-->
|
|
<dynamicField name="*_t_sort" type="text_gen_sort" indexed="true" stored="true" multiValued="false"/>
|
|
<dynamicField name="*_txt_sort" type="text_gen_sort" indexed="true" stored="true"/>
|
|
<fieldType name="text_gen_sort" class="solr.SortableTextField" positionIncrementGap="100" multiValued="true">
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
|
|
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
|
<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. -->
|
|
<dynamicField name="*_txt_en" type="text_en" indexed="true" stored="true"/>
|
|
<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.SynonymGraphFilterFactory" synonyms="index_synonyms.txt" ignoreCase="true" expand="false"/>
|
|
<filter class="solr.FlattenGraphFilterFactory"/>
|
|
-->
|
|
<!-- 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.SynonymGraphFilterFactory" 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
|
|
WordDelimiterGraphFilter 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".
|
|
-->
|
|
<dynamicField name="*_txt_en_split" type="text_en_splitting" indexed="true" stored="true"/>
|
|
<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.SynonymGraphFilterFactory" 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.WordDelimiterGraphFilterFactory" 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"/>
|
|
<filter class="solr.FlattenGraphFilterFactory" />
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
|
<filter class="solr.StopFilterFactory"
|
|
ignoreCase="true"
|
|
words="lang/stopwords_en.txt"
|
|
/>
|
|
<filter class="solr.WordDelimiterGraphFilterFactory" 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. -->
|
|
<dynamicField name="*_txt_en_split_tight" type="text_en_splitting_tight" indexed="true" stored="true"/>
|
|
<fieldType name="text_en_splitting_tight" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="true">
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
|
|
<filter class="solr.WordDelimiterGraphFilterFactory" 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 WordDelimiterGraphFilter in conjuncton with stemming. -->
|
|
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
|
|
<filter class="solr.FlattenGraphFilterFactory" />
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_en.txt"/>
|
|
<filter class="solr.WordDelimiterGraphFilterFactory" 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 WordDelimiterGraphFilter 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.
|
|
-->
|
|
<dynamicField name="*_txt_rev" type="text_general_rev" indexed="true" stored="true"/>
|
|
<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.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<dynamicField name="*_phon_en" type="phonetic_en" indexed="true" stored="true"/>
|
|
<fieldType name="phonetic_en" stored="false" indexed="true" class="solr.TextField" >
|
|
<analyzer>
|
|
<tokenizer class="solr.StandardTokenizerFactory"/>
|
|
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- lowercases the entire field value, keeping it as a single token. -->
|
|
<dynamicField name="*_s_lower" type="lowercase" indexed="true" stored="true"/>
|
|
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.KeywordTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory" />
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!--
|
|
Example of using PathHierarchyTokenizerFactory at index time, so
|
|
queries for paths match documents at that path, or in descendent paths
|
|
-->
|
|
<dynamicField name="*_descendent_path" type="descendent_path" indexed="true" stored="true"/>
|
|
<fieldType name="descendent_path" class="solr.TextField">
|
|
<analyzer type="index">
|
|
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
|
|
</analyzer>
|
|
<analyzer type="query">
|
|
<tokenizer class="solr.KeywordTokenizerFactory" />
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!--
|
|
Example of using PathHierarchyTokenizerFactory at query time, so
|
|
queries for paths match documents at that path, or in ancestor paths
|
|
-->
|
|
<dynamicField name="*_ancestor_path" type="ancestor_path" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<!-- 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.
|
|
-->
|
|
<dynamicField name="*_point" type="point" indexed="true" stored="true"/>
|
|
<fieldType name="point" class="solr.PointType" dimension="2" subFieldSuffix="_d"/>
|
|
|
|
<!-- A specialized field for geospatial search filters and distance sorting. -->
|
|
<fieldType name="location" class="solr.LatLonPointSpatialField" docValues="true"/>
|
|
|
|
<!-- A geospatial field type that supports multiValued and polygon shapes.
|
|
For more information about this and other spatial fields see:
|
|
http://lucene.apache.org/solr/guide/spatial-search.html
|
|
-->
|
|
<fieldType name="location_rpt" class="solr.SpatialRecursivePrefixTreeFieldType"
|
|
geo="true" distErrPct="0.025" maxDistErr="0.001" distanceUnits="kilometers" />
|
|
|
|
<!-- Payloaded field types -->
|
|
<fieldType name="delimited_payloads_float" stored="false" indexed="true" class="solr.TextField">
|
|
<analyzer>
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="delimited_payloads_int" stored="false" indexed="true" class="solr.TextField">
|
|
<analyzer>
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="integer"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
<fieldType name="delimited_payloads_string" stored="false" indexed="true" class="solr.TextField">
|
|
<analyzer>
|
|
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
|
|
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="identity"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- some examples for different languages (generally ordered by ISO code) -->
|
|
|
|
<!-- Arabic -->
|
|
<dynamicField name="*_txt_ar" type="text_ar" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<!-- Bulgarian -->
|
|
<dynamicField name="*_txt_bg" type="text_bg" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<!-- Catalan -->
|
|
<dynamicField name="*_txt_ca" type="text_ca" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<!-- CJK bigram (see text_ja for a Japanese configuration using morphological analysis) -->
|
|
<dynamicField name="*_txt_cjk" type="text_cjk" indexed="true" stored="true"/>
|
|
<fieldType name="text_cjk" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<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>
|
|
|
|
<!-- Czech -->
|
|
<dynamicField name="*_txt_cz" type="text_cz" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<!-- Danish -->
|
|
<dynamicField name="*_txt_da" type="text_da" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<!-- German -->
|
|
<dynamicField name="*_txt_de" type="text_de" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<!-- Greek -->
|
|
<dynamicField name="*_txt_el" type="text_el" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<!-- Spanish -->
|
|
<dynamicField name="*_txt_es" type="text_es" indexed="true" stored="true"/>
|
|
<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 -->
|
|
<dynamicField name="*_txt_eu" type="text_eu" indexed="true" stored="true"/>
|
|
<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 -->
|
|
<dynamicField name="*_txt_fa" type="text_fa" indexed="true" stored="true"/>
|
|
<fieldType name="text_fa" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<!-- 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>
|
|
|
|
<!-- Finnish -->
|
|
<dynamicField name="*_txt_fi" type="text_fi" indexed="true" stored="true"/>
|
|
<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>
|
|
</fieldType>
|
|
|
|
<!-- French -->
|
|
<dynamicField name="*_txt_fr" type="text_fr" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<!-- Irish -->
|
|
<dynamicField name="*_txt_ga" type="text_ga" indexed="true" stored="true"/>
|
|
<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>
|
|
</fieldType>
|
|
|
|
<!-- Galician -->
|
|
<dynamicField name="*_txt_gl" type="text_gl" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<!-- Hindi -->
|
|
<dynamicField name="*_txt_hi" type="text_hi" indexed="true" stored="true"/>
|
|
<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>
|
|
</fieldType>
|
|
|
|
<!-- Hungarian -->
|
|
<dynamicField name="*_txt_hu" type="text_hu" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<!-- Armenian -->
|
|
<dynamicField name="*_txt_hy" type="text_hy" indexed="true" stored="true"/>
|
|
<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>
|
|
</fieldType>
|
|
|
|
<!-- Indonesian -->
|
|
<dynamicField name="*_txt_id" type="text_id" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<!-- Italian -->
|
|
<dynamicField name="*_txt_it" type="text_it" indexed="true" stored="true"/>
|
|
<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>
|
|
</fieldType>
|
|
|
|
<!-- Japanese using morphological analysis (see text_cjk for a configuration using bigramming)
|
|
|
|
NOTE: If you want to optimize search for precision, use default operator AND in your request
|
|
handler config (q.op) Use OR if you would like to optimize for recall (default).
|
|
-->
|
|
<dynamicField name="*_txt_ja" type="text_ja" indexed="true" stored="true"/>
|
|
<fieldType name="text_ja" class="solr.TextField" positionIncrementGap="100" autoGeneratePhraseQueries="false">
|
|
<analyzer>
|
|
<!-- Kuromoji Japanese morphological analyzer/tokenizer (JapaneseTokenizer)
|
|
|
|
Kuromoji has a search mode (default) that does segmentation useful for search. A heuristic
|
|
is used to segment compounds into its parts and the compound itself is kept as synonym.
|
|
|
|
Valid values for attribute mode are:
|
|
normal: regular segmentation
|
|
search: segmentation useful for search with synonyms compounds (default)
|
|
extended: same as search mode, but unigrams unknown words (experimental)
|
|
|
|
For some applications it might be good to use search mode for indexing and normal mode for
|
|
queries to reduce recall and prevent parts of compounds from being matched and highlighted.
|
|
Use <analyzer type="index"> and <analyzer type="query"> for this and mode normal in query.
|
|
|
|
Kuromoji also has a convenient user dictionary feature that allows overriding the statistical
|
|
model with your own entries for segmentation, part-of-speech tags and readings without a need
|
|
to specify weights. Notice that user dictionaries have not been subject to extensive testing.
|
|
|
|
User dictionary attributes are:
|
|
userDictionary: user dictionary filename
|
|
userDictionaryEncoding: user dictionary encoding (default is UTF-8)
|
|
|
|
See lang/userdict_ja.txt for a sample user dictionary file.
|
|
|
|
Punctuation characters are discarded by default. Use discardPunctuation="false" to keep them.
|
|
-->
|
|
<tokenizer class="solr.JapaneseTokenizerFactory" mode="search"/>
|
|
<!--<tokenizer class="solr.JapaneseTokenizerFactory" mode="search" userDictionary="lang/userdict_ja.txt"/>-->
|
|
<!-- Reduces inflected verbs and adjectives to their base/dictionary forms (辞書形) -->
|
|
<filter class="solr.JapaneseBaseFormFilterFactory"/>
|
|
<!-- Removes tokens with certain part-of-speech tags -->
|
|
<filter class="solr.JapanesePartOfSpeechStopFilterFactory" tags="lang/stoptags_ja.txt" />
|
|
<!-- Normalizes full-width romaji to half-width and half-width kana to full-width (Unicode NFKC subset) -->
|
|
<filter class="solr.CJKWidthFilterFactory"/>
|
|
<!-- Removes common tokens typically not useful for search, but have a negative effect on ranking -->
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ja.txt" />
|
|
<!-- Normalizes common katakana spelling variations by removing any last long sound character (U+30FC) -->
|
|
<filter class="solr.JapaneseKatakanaStemFilterFactory" minimumLength="4"/>
|
|
<!-- Lower-cases romaji characters -->
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Korean morphological analysis -->
|
|
<dynamicField name="*_txt_ko" type="text_ko" indexed="true" stored="true"/>
|
|
<fieldType name="text_ko" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<!-- Nori Korean morphological analyzer/tokenizer (KoreanTokenizer)
|
|
The Korean (nori) analyzer integrates Lucene nori analysis module into Solr.
|
|
It uses the mecab-ko-dic dictionary to perform morphological analysis of Korean texts.
|
|
|
|
This dictionary was built with MeCab, it defines a format for the features adapted
|
|
for the Korean language.
|
|
|
|
Nori also has a convenient user dictionary feature that allows overriding the statistical
|
|
model with your own entries for segmentation, part-of-speech tags and readings without a need
|
|
to specify weights. Notice that user dictionaries have not been subject to extensive testing.
|
|
|
|
The tokenizer supports multiple schema attributes:
|
|
* userDictionary: User dictionary path.
|
|
* userDictionaryEncoding: User dictionary encoding.
|
|
* decompoundMode: Decompound mode. Either 'none', 'discard', 'mixed'. Default is 'discard'.
|
|
* outputUnknownUnigrams: If true outputs unigrams for unknown words.
|
|
-->
|
|
<tokenizer class="solr.KoreanTokenizerFactory" decompoundMode="discard" outputUnknownUnigrams="false"/>
|
|
<!-- Removes some part of speech stuff like EOMI (Pos.E), you can add a parameter 'tags',
|
|
listing the tags to remove. By default it removes:
|
|
E, IC, J, MAG, MAJ, MM, SP, SSC, SSO, SC, SE, XPN, XSA, XSN, XSV, UNA, NA, VSV
|
|
This is basically an equivalent to stemming.
|
|
-->
|
|
<filter class="solr.KoreanPartOfSpeechStopFilterFactory" />
|
|
<!-- Replaces term text with the Hangul transcription of Hanja characters, if applicable: -->
|
|
<filter class="solr.KoreanReadingFormFilterFactory" />
|
|
<filter class="solr.LowerCaseFilterFactory" />
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Latvian -->
|
|
<dynamicField name="*_txt_lv" type="text_lv" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<!-- Dutch -->
|
|
<dynamicField name="*_txt_nl" type="text_nl" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<!-- Norwegian -->
|
|
<dynamicField name="*_txt_no" type="text_no" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<!-- Portuguese -->
|
|
<dynamicField name="*_txt_pt" type="text_pt" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<!-- Romanian -->
|
|
<dynamicField name="*_txt_ro" type="text_ro" indexed="true" stored="true"/>
|
|
<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 -->
|
|
<dynamicField name="*_txt_ru" type="text_ru" indexed="true" stored="true"/>
|
|
<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 -->
|
|
<dynamicField name="*_txt_sv" type="text_sv" indexed="true" stored="true"/>
|
|
<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 -->
|
|
<dynamicField name="*_txt_th" type="text_th" indexed="true" stored="true"/>
|
|
<fieldType name="text_th" class="solr.TextField" positionIncrementGap="100">
|
|
<analyzer>
|
|
<tokenizer class="solr.ThaiTokenizerFactory"/>
|
|
<filter class="solr.LowerCaseFilterFactory"/>
|
|
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_th.txt" />
|
|
</analyzer>
|
|
</fieldType>
|
|
|
|
<!-- Turkish -->
|
|
<dynamicField name="*_txt_tr" type="text_tr" indexed="true" stored="true"/>
|
|
<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>
|
|
|
|
<!-- 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://lucene.apache.org/solr/guide/other-schema-elements.html#OtherSchemaElements-Similarity
|
|
-->
|
|
<!--
|
|
<similarity class="com.example.solr.CustomSimilarityFactory">
|
|
<str name="paramkey">param value</str>
|
|
</similarity>
|
|
-->
|
|
|
|
</schema>
|