solr 加分词
目录结构
/usr/local/docker/solr# tree.├── docker-compose.yml├── ikanalyzer│ ├── Dockerfile│ ├── dynamicdic.txt│ ├── ext.dic│ ├── ik-analyzer-8.3.0.jar // 资源自己下载│ ├── IKAnalyzer.cfg.xml│ ├── ik-analyzer-solr5-5.x.jar // 资源自己下载│ ├── ik.conf│ ├── managed-schema│ ├── solr-analyzer-ik-5.1.0.jar // 资源自己下载│ └── stopword.dic└── solrdata
文件：docker-compose.yml
version: '3.1'services:solr:#image: solr:8.5build: ikanalyzerrestart: 'no'container_name: solrports:- 8983:8983volumes:- ./solrdata:/var/solr/data
文件：Dockerfile
FROM solr:8.5
MAINTAINER airvip <sdqhwzb@163.com>
# 安装中文分词
WORKDIR /opt/solr/server/solr-webapp/webapp/WEB-INF/lib
ADD ik-analyzer-8.3.0.jar .
WORKDIR /opt/solr/server/solr-webapp/webapp/WEB-INF
ADD IKAnalyzer.cfg.xml .
ADD ext.dic .
ADD stopword.dic .
ADD ik.conf .
ADD dynamicdic.txt .
WORKDIR /opt/solr
文件：dynamicdic.txt
文件：ext.dic
阿尔维奇
帅哥哥啊
文件：IKAnalyzer.cfg.xml
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE properties SYSTEM "http://java.sun.com/dtd/properties.dtd">
<properties>
<comment>IK Analyzer 扩展配置</comment>
<!-- 配置是否加载默认词典 -->
<entry key="use_main_dict">true</entry>
<!-- 配置自己的扩展字典，多个用分号分隔 -->
<entry key="ext_dict">ext.dic;</entry>
<!-- 配置自己的扩展停止词字典，多个用分号分隔 -->
<entry key="ext_stopwords">stopword.dic;</entry>
</properties>
文件：ik.conf
Wed Aug 01 11:21:30 CST 2018
files=dynamicdic.txt
lastupdate=0
文件：managed-schema
<?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
PERFORMANCE NOTE: this schema includes many optional features and should not
be used for benchmarking. To improve performance one could
- set stored="false" for all fields possible (esp large fields) when you
only need to search on the field but don't need to return the original
value.
- set indexed="false" if you don't need to search on the field, but only
return the field as a result of searching on other indexed fields.
- remove all unneeded copyField statements
- for best index size and searching performance, set "index" to false
for all general text fields, use copyField to copy them to the
catchall "text" field, and use that for searching.
- For maximum indexing performance, use the ConcurrentUpdateSolrServer
java client.
- Remember to run the JVM in server mode, and use a higher logging level
that avoids logging every request
-->
<schema name="example" 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
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 (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 however come with some limitations: 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.
termPayloads: Store payload 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
-->
<!-- doc values are enabled by default for primitive types such as long so we don't index the version field -->
<field name="_version_" type="plong" indexed="false" stored="false"/>
<!-- 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" docValues="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="pre" type="preanalyzed" indexed="true" stored="true"/>
<field name="sku" type="text_en_splitting_tight" indexed="true" stored="true" omitNorms="true"/>
<field name="name" type="text_general" indexed="true" stored="true"/>
<field name="manu" type="text_general" indexed="true" stored="true" omitNorms="true"/>
<field name="cat" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="features" type="text_general" indexed="true" stored="true" multiValued="true"/>
<field name="includes" type="text_general" indexed="true" stored="true" termVectors="true" termPositions="true" termOffsets="true" />
<field name="weight" type="pfloat" indexed="true" stored="true"/>
<field name="price" type="pfloat" indexed="true" stored="true"/>
<field name="popularity" type="pint" indexed="true" stored="true" />
<field name="inStock" type="boolean" indexed="true" stored="true" />
<field name="store" type="location" indexed="true" stored="true"/>
<!-- Common metadata fields, named specifically to match up with
SolrCell metadata when parsing rich documents such as Word, PDF.
Some fields are multiValued only because Tika currently may return
multiple values for them. Some metadata is parsed from the documents,
but there are some which come from the client context:
"content_type": From the HTTP headers of incoming stream
"resourcename": From SolrCell request param resource.name
-->
<field name="title" type="text_general" indexed="true" stored="true" multiValued="true"/>
<field name="subject" type="text_general" indexed="true" stored="true"/>
<field name="description" type="text_general" indexed="true" stored="true"/>
<field name="comments" type="text_general" indexed="true" stored="true"/>
<field name="author" type="text_general" indexed="true" stored="true"/>
<field name="keywords" type="text_general" indexed="true" stored="true"/>
<field name="category" type="text_general" indexed="true" stored="true"/>
<field name="resourcename" type="text_general" indexed="true" stored="true"/>
<field name="url" type="text_general" indexed="true" stored="true"/>
<field name="content_type" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="last_modified" type="pdate" indexed="true" stored="true"/>
<field name="links" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="_src_" type="string" indexed="false" stored="true"/>
<!-- Main body of document extracted by SolrCell.
NOTE: This field is not indexed by default, since it is also copied to "text"
using copyField below. This is to save space. Use this field for returning and
highlighting document content. Use the "text" field to search the content. -->
<field name="content" type="text_general" indexed="false" stored="true" multiValued="true"/>
<!-- catchall field, containing all other searchable text fields (implemented
via copyField further on in this schema -->
<field name="text" type="text_general" indexed="true" stored="false" multiValued="true"/>
<!-- catchall text field that indexes tokens both normally and in reverse for efficient
leading wildcard queries. -->
<field name="text_rev" type="text_general_rev" indexed="true" stored="false" multiValued="true"/>
<!-- non-tokenized version of manufacturer to make it easier to sort or group
results by manufacturer. copied from "manu" via copyField -->
<field name="manu_exact" type="string" indexed="true" stored="false" docValues="false" />
<field name="payloads" type="payloads" indexed="true" stored="true"/>
<!-- 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="pint" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_s" type="string" indexed="true" stored="true" />
<dynamicField name="*_s_ns" type="string" indexed="true" stored="false" />
<dynamicField name="*_ss" type="string" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_l" type="plong" indexed="true" stored="true"/>
<dynamicField name="*_l_ns" type="plong" indexed="true" stored="false"/>
<dynamicField name="*_ls" type="plong" 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"/>
<dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
<dynamicField name="*_bs" type="boolean" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_f" type="pfloat" indexed="true" stored="true"/>
<dynamicField name="*_fs" type="pfloat" indexed="true" stored="true" multiValued="true"/>
<dynamicField name="*_d" type="pdouble" indexed="true" stored="true"/>
<dynamicField name="*_ds" type="pdouble" indexed="true" stored="true" multiValued="true"/>
<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="*_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="cat" dest="text"/>
<copyField source="name" dest="text"/>
<copyField source="manu" dest="text"/>
<copyField source="features" dest="text"/>
<copyField source="includes" dest="text"/>
<copyField source="manu" dest="manu_exact"/>
<!-- Copy the price into a currency enabled field (default USD) -->
<copyField source="price" dest="price_c"/>
<!-- Text fields from SolrCell to search by default in our catch-all field -->
<copyField source="title" dest="text"/>
<copyField source="author" dest="text"/>
<copyField source="description" dest="text"/>
<copyField source="keywords" dest="text"/>
<copyField source="content" dest="text"/>
<copyField source="content_type" dest="text"/>
<copyField source="resourcename" dest="text"/>
<copyField source="url" dest="text"/>
<!-- Create a string version of author for faceting -->
<copyField source="author" dest="author_s"/>
<!-- Above, multiple source fields are copied to the [text] field.
Another way to map multiple source fields to the same
destination field is to use the dynamic field syntax.
copyField also supports a maxChars to copy setting. -->
<!-- <copyField source="*_t" dest="text" maxChars="3000"/> -->
<!-- copy name to alphaNameSort, a field designed for sorting by name -->
<!-- <copyField source="name" dest="alphaNameSort"/> -->
<!-- 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"/>
<!-- 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.
-->
<!--
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"/>
<!-- 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 DatePointField javadocs for more information.
-->
<!-- 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"/>
<!-- 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 text type for English text where stopwords and synonyms are managed using the REST API -->
<fieldType name="managed_en" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.ManagedStopFilterFactory" managed="english" />
<filter class="solr.ManagedSynonymGraphFilterFactory" managed="english" />
<filter class="solr.FlattenGraphFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.ManagedStopFilterFactory" managed="english" />
<filter class="solr.ManagedSynonymGraphFilterFactory" managed="english" />
</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.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>
<!-- 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.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".
-->
<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. -->
<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. -->
<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>
<!-- charFilter + WhitespaceTokenizer -->
<!--
<fieldType name="text_char_norm" class="solr.TextField" positionIncrementGap="100" >
<analyzer>
<charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</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/8/docs/api/java/util/regex/package-summary.html
-->
<filter class="solr.PatternReplaceFilterFactory"
pattern="([^a-z])" replacement="" replace="all"
/>
</analyzer>
</fieldType>
<fieldType name="phonetic" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.DoubleMetaphoneFilterFactory" inject="false"/>
</analyzer>
</fieldType>
<fieldType name="payloads" stored="false" indexed="true" class="solr.TextField" >
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<!--
The DelimitedPayloadTokenFilter can put payloads on tokens... for example,
a token of "foo|1.4" would be indexed as "foo" with a payload of 1.4f
Attributes of the DelimitedPayloadTokenFilterFactory :
"delimiter" - a one character delimiter. Default is | (pipe)
"encoder" - how to encode the following value into a playload
float -> org.apache.lucene.analysis.payloads.FloatEncoder,
integer -> o.a.l.a.p.IntegerEncoder
identity -> o.a.l.a.p.IdentityEncoder
Fully Qualified class name implementing PayloadEncoder, Encoder must have a no arg constructor.
-->
<filter class="solr.DelimitedPayloadTokenFilterFactory" encoder="float"/>
</analyzer>
</fieldType>
<!-- lowercases the entire field value, keeping it as a single token. -->
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory" />
</analyzer>
</fieldType>
<!--
Example of using PathHierarchyTokenizerFactory at index time, so
queries for paths match documents at that path, or in descendent paths
-->
<fieldType name="descendent_path" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.KeywordTokenizerFactory" />
</analyzer>
</fieldType>
<!--
Example of using PathHierarchyTokenizerFactory at query time, so
queries for paths match documents at that path, or in ancestor paths
-->
<fieldType name="ancestor_path" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.KeywordTokenizerFactory" />
</analyzer>
<analyzer type="query">
<tokenizer class="solr.PathHierarchyTokenizerFactory" delimiter="/" />
</analyzer>
</fieldType>
<!-- since fields of this type are by default not stored or indexed,
any data added to them will be ignored outright. -->
<fieldType name="ignored" stored="false" indexed="false" multiValued="true" class="solr.StrField" />
<!-- This point type indexes the coordinates as separate fields (subFields)
If subFieldType is defined, it references a type, and a dynamic field
definition is created matching *___<typename>. Alternately, if
subFieldSuffix is defined, that is used to create the subFields.
Example: if subFieldType="double", then the coordinates would be
indexed in fields myloc_0___double,myloc_1___double.
Example: if subFieldSuffix="_d" then the coordinates would be indexed
in fields myloc_0_d,myloc_1_d
The subFields are an implementation detail of the fieldType, and end
users normally should not need to know about them.
-->
<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"/>
<!-- 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="pdouble" />
<!-- Money/currency field type. See http://wiki.apache.org/solr/MoneyFieldType
Parameters:
amountLongSuffix: Required. Refers to a dynamic field for the raw amount sub-field.
The dynamic field must have a field type that extends LongValueFieldType.
Note: If you expect to use Atomic Updates, this dynamic field may not be stored.
codeStrSuffix: Required. Refers to a dynamic field for the currency code sub-field.
The dynamic field must have a field type that extends StrField.
Note: If you expect to use Atomic Updates, this dynamic field may not be stored.
defaultCurrency: Specifies the default currency if none specified. Defaults to "USD"
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.CurrencyFieldType" amountLongSuffix="_l_ns" codeStrSuffix="_s_ns"
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>
<!-- 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>
<!-- 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>
<!-- 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.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>
<!-- Kurdish -->
<fieldType name="text_ckb" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.SoraniNormalizationFilterFactory"/>
<!-- for any latin text -->
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_ckb.txt"/>
<filter class="solr.SoraniStemFilterFactory"/>
</analyzer>
</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>
<!-- 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>
<!-- 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>
<!-- 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>
<!-- 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>
<!-- 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 -->
<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 -->
<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 -->
<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 -->
<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 -->
<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 -->
<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 -->
<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 -->
<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 -->
<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).
-->
<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.
See http://wiki.apache.org/solr/JapaneseLanguageSupport for more on Japanese language support.
-->
<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>
<!-- 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>
<!-- 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>
<!-- 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" variant="nb"/> -->
<!-- singular/plural: <filter class="solr.NorwegianMinimalStemFilterFactory" variant="nb"/> -->
<!-- The "light" and "minimal" stemmers support variants: nb=Bokmål, nn=Nynorsk, no=Both -->
</analyzer>
</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>
<!-- 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.ThaiTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<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.ApostropheFilterFactory"/>
<filter class="solr.TurkishLowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="false" words="lang/stopwords_tr.txt" />
<filter class="solr.SnowballPorterFilterFactory" language="Turkish"/>
</analyzer>
</fieldType>
<!-- Pre-analyzed field type, allows inserting arbitrary token streams and stored values. -->
<fieldType name="preanalyzed" class="solr.PreAnalyzedField">
<!-- PreAnalyzedField's builtin index analyzer just decodes the pre-analyzed token stream. -->
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</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://wiki.apache.org/solr/SchemaXml#Similarity
-->
<!--
<similarity class="com.example.solr.CustomSimilarityFactory">
<str name="paramkey">param value</str>
</similarity>
-->
<!-- ik分词器 -->
<fieldType name="text_ik" class="solr.TextField">
<analyzer type="index">
<tokenizer class="org.wltea.analyzer.lucene.IKTokenizerFactory" useSmart="false" conf="ik.conf"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="org.wltea.analyzer.lucene.IKTokenizerFactory" useSmart="true" conf="ik.conf"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
</schema>
文件：stopword.dic
,
?
、
。
“
”
《
》
！
，
：
；
？
人民
末##末
啊
阿
哎
哎呀
哎哟
唉
俺
俺们
按
按照
吧
吧哒
把
罢了
被
本
本着
比
比方
比如
鄙人
彼
彼此
边
别
别的
别说
并
并且
不比
不成
不单
不但
不独
不管
不光
不过
不仅
不拘
不论
不怕
不然
不如
不特
不惟
不问
不只
朝
朝着
趁
趁着
乘
冲
除
除此之外
除非
除了
此
此间
此外
从
从而
打
待
但
但是
当
当着
到
得
的
的话
等
等等
地
第
叮咚
对
对于
多
多少
而
而况
而且
而是
而外
而言
而已
尔后
反过来
反过来说
反之
非但
非徒
否则
嘎
嘎登
该
赶
个
各
各个
各位
各种
各自
给
根据
跟
故
故此
固然
关于
管
归
果然
果真
过
哈
哈哈
呵
和
何
何处
何况
何时
嘿
哼
哼唷
呼哧
乎
哗
还是
还有
换句话说
换言之
或
或是
或者
极了
及
及其
及至
即
即便
即或
即令
即若
即使
几
几时
己
既
既然
既是
继而
加之
假如
假若
假使
鉴于
将
较
较之
叫
接着
结果
借
紧接着
进而
尽
尽管
经
经过
就
就是
就是说
据
具体地说
具体说来
开始
开外
靠
咳
可
可见
可是
可以
况且
啦
来
来着
离
例如
哩
连
连同
两者
了
临
另
另外
另一方面
论
嘛
吗
慢说
漫说
冒
么
每
每当
们
莫若
某
某个
某些
拿
哪
哪边
哪儿
哪个
哪里
哪年
哪怕
哪天
哪些
哪样
那
那边
那儿
那个
那会儿
那里
那么
那么些
那么样
那时
那些
那样
乃
乃至
呢
能
你
你们
您
宁
宁可
宁肯
宁愿
哦
呕
啪达
旁人
呸
凭
凭借
其
其次
其二
其他
其它
其一
其余
其中
起
起见
岂但
恰恰相反
前后
前者
且
然而
然后
然则
让
人家
任
任何
任凭
如
如此
如果
如何
如其
如若
如上所述
若
若非
若是
啥
上下
尚且
设若
设使
甚而
甚么
甚至
省得
时候
什么
什么样
使得
是
是的
首先
谁
谁知
顺
顺着
似的
虽
虽然
虽说
虽则
随
随着
所
所以
他
他们
他人
它
它们
她
她们
倘
倘或
倘然
倘若
倘使
腾
替
通过
同
同时
哇
万一
往
望
为
为何
为了
为什么
为着
喂
嗡嗡
我
我们
呜
呜呼
乌乎
无论
无宁
毋宁
嘻
吓
相对而言
像
向
向着
嘘
呀
焉
沿
沿着
要
要不
要不然
要不是
要么
要是
也
也罢
也好
一
一般
一旦
一方面
一来
一切
一样
一则
依
依照
矣
以
以便
以及
以免
以至
以至于
以致
抑或
因
因此
因而
因为
哟
用
由
由此可见
由于
有
有的
有关
有些
又
于
于是
于是乎
与
与此同时
与否
与其
越是
云云
哉
再说
再者
在
在下
咱
咱们
则
怎
怎么
怎么办
怎么样
怎样
咋
照
照着
者
这
这边
这儿
这个
这会儿
这就是说
这里
这么
这么点儿
这么些
这么样
这时
这些
这样
正如
吱
之
之类
之所以
之一
只是
只限
只要
只有
至
至于
诸位
着
着呢
自
自从
自个儿
自各儿
自己
自家
自身
综上所述
总的来看
总的来说
总的说来
总而言之
总之
纵
纵令
纵然
纵使
遵照
作为
兮
呃
呗
咚
咦
喏
啐
喔唷
嗬
嗯
嗳
~
!
.
:
"
'
(
)
*
A
白
社会主义
--
..
>>
[
]
<
>
/
\
|
-
_
+
=
&
^
%
#
@
`
;
$
（
）
——
—
￥
·
...
‘
’
〉
〈
…
0
1
2
3
4
5
6
7
8
9
０
１
２
３
４
５
６
７
８
９
二
三
四
五
六
七
八
九
零
＞
＜
＠
＃
＄
％
︿
＆
＊
＋
～
｜
［
］
｛
｝
啊哈
啊呀
啊哟
挨次
挨个
挨家挨户
挨门挨户
挨门逐户
挨着
按理
按期
按时
按说
暗地里
暗中
暗自
昂然
八成
白白
半
梆
保管
保险
饱
背地里
背靠背
倍感
倍加
本人
本身
甭
比起
比如说
比照
毕竟
必
必定
必将
必须
便
别人
并非
并肩
并没
并没有
并排
并无
勃然
不
不必
不常
不大
不但...而且
不得
不得不
不得了
不得已
不迭
不定
不对
不妨
不管怎样
不会
不仅...而且
不仅仅
不仅仅是
不经意
不可开交
不可抗拒
不力
不了
不料
不满
不免
不能不
不起
不巧
不然的话
不日
不少
不胜
不时
不是
不同
不能
不要
不外
不外乎
不下
不限
不消
不已
不亦乐乎
不由得
不再
不择手段
不怎么
不曾
不知不觉
不止
不止一次
不至于
才
才能
策略地
差不多
差一点
常
常常
常言道
常言说
常言说得好
长此下去
长话短说
长期以来
长线
敞开儿
彻夜
陈年
趁便
趁机
趁热
趁势
趁早
成年
成年累月
成心
乘机
乘胜
乘势
乘隙
乘虚
诚然
迟早
充分
充其极
充其量
抽冷子
臭
初
出
出来
出去
除此
除此而外
除此以外
除开
除去
除却
除外
处处
川流不息
传
传说
传闻
串行
纯
纯粹
此后
此中
次第
匆匆
从不
从此
从此以后
从古到今
从古至今
从今以后
从宽
从来
从轻
从速
从头
从未
从无到有
从小
从新
从严
从优
从早到晚
从中
从重
凑巧
粗
存心
达旦
打从
打开天窗说亮话
大
大不了
大大
大抵
大都
大多
大凡
大概
大家
大举
大略
大面儿上
大事
大体
大体上
大约
大张旗鼓
大致
呆呆地
带
殆
待到
单
单纯
单单
但愿
弹指之间
当场
当儿
当即
当口儿
当然
当庭
当头
当下
当真
当中
倒不如
倒不如说
倒是
到处
到底
到了儿
到目前为止
到头
到头来
得起
得天独厚
的确
等到
叮当
顶多
定
动不动
动辄
陡然
都
独
独自
断然
顿时
多次
多多
多多少少
多多益善
多亏
多年来
多年前
而后
而论
而又
尔等
二话不说
二话没说
反倒
反倒是
反而
反手
反之亦然
反之则
方
方才
方能
放量
非常
非得
分期
分期分批
分头
奋勇
愤然
风雨无阻
逢
弗
甫
嘎嘎
该当
概
赶快
赶早不赶晚
敢
敢情
敢于
刚
刚才
刚好
刚巧
高低
格外
隔日
隔夜
个人
各式
更
更加
更进一步
更为
公然
共
共总
够瞧的
姑且
古来
故而
故意
固
怪
怪不得
惯常
光
光是
归根到底
归根结底
过于
毫不
毫无
毫无保留地
毫无例外
好在
何必
何尝
何妨
何苦
何乐而不为
何须
何止
很
很多
很少
轰然
后来
呼啦
忽地
忽然
互
互相
哗啦
话说
还
恍然
会
豁然
活
伙同
或多或少
或许
基本
基本上
基于
极
极大
极度
极端
极力
极其
极为
急匆匆
即将
即刻
即是说
几度
几番
几乎
几经
既...又
继之
加上
加以
间或
简而言之
简言之
简直
见
将才
将近
将要
交口
较比
较为
接连不断
接下来
皆可
截然
截至
藉以
借此
借以
届时
仅
仅仅
谨
进来
进去
近
近几年来
近来
近年来
尽管如此
尽可能
尽快
尽量
尽然
尽如人意
尽心竭力
尽心尽力
尽早
精光
经常
竟
竟然
究竟
就此
就地
就算
居然
局外
举凡
据称
据此
据实
据说
据我所知
据悉
具体来说
决不
决非
绝
绝不
绝顶
绝对
绝非
均
喀
看
看来
看起来
看上去
看样子
可好
可能
恐怕
快
快要
来不及
来得及
来讲
来看
拦腰
牢牢
老
老大
老老实实
老是
累次
累年
理当
理该
理应
历
立
立地
立刻
立马
立时
联袂
连连
连日
连日来
连声
连袂
临到
另方面
另行
另一个
路经
屡
屡次
屡次三番
屡屡
缕缕
率尔
率然
略
略加
略微
略为
论说
马上
蛮
满
没
没有
每逢
每每
每时每刻
猛然
猛然间
莫
莫不
莫非
莫如
默默地
默然
呐
那末
奈
难道
难得
难怪
难说
内
年复一年
凝神
偶而
偶尔
怕
砰
碰巧
譬如
偏偏
乒
平素
颇
迫于
扑通
其后
其实
奇
齐
起初
起来
起首
起头
起先
岂
岂非
岂止
迄
恰逢
恰好
恰恰
恰巧
恰如
恰似
千
千万
千万千万
切
切不可
切莫
切切
切勿
窃
亲口
亲身
亲手
亲眼
亲自
顷
顷刻
顷刻间
顷刻之间
请勿
穷年累月
取道
去
权时
全都
全力
全年
全然
全身心
然
人人
仍
仍旧
仍然
日复一日
日见
日渐
日益
日臻
如常
如此等等
如次
如今
如期
如前所述
如上
如下
汝
三番两次
三番五次
三天两头
瑟瑟
沙沙
上
上来
上去
solr
目录结构
/usr/local/docker/solrOnly# tree
.
└── docker-compose.yml
文件：docker-compose.yml
version: '3.1'
services:
solr:
image: solr:8.5
restart: 'no'
container_name: solrOnly
ports:
- 8983:8983
若有收获，就点个赞吧
0 人点赞
