22

✏️ Editing: solr-config-9.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.
-->

<config>
  <!-- In all configuration below, a prefix of "solr." for class names
       is an alias that causes solr to search appropriate packages,
       including org.apache.solr.(search|update|request|core|analysis)

You may also specify a fully qualified Java classname if you
       have your own custom plugins.
    -->

<luceneMatchVersion>9.8</luceneMatchVersion>

<!-- <lib/> directives can be used to instruct Solr to load any Jars
       identified and use them to resolve any "plugins" specified in
       your solrconfig.xml or schema.xml (ie: Analyzers, Request
       Handlers, etc...).

All directories and paths are resolved relative to the
       instanceDir.

Please note that <lib/> directives are processed in the order
       that they appear in your solrconfig.xml file, and are "stacked"
       on top of each other when building a ClassLoader - so if you have
       plugin jars with dependencies on other jars, the "lower level"
       dependency jars should be loaded first.

If a "./lib" directory exists in your instanceDir, all files
       found in it are included as if you had used the following
       syntax...

<!-- A 'dir' option by itself adds any files found in the directory
       to the classpath, this is useful for including all jars in a
       directory.

When a 'regex' is specified in addition to a 'dir', only the
       files in that directory which completely match the regex
       (anchored on both ends) will be included.

If a 'dir' option (with or without a regex) is used and nothing
       is found that matches, a warning will be logged.

The example below can be used to load a Solr Module along
       with their external dependencies.
    -->

<lib dir="${solr.install.dir:../../../..}/modules/analysis-extras/lib" regex="icu4j-.*\.jar"/>
    <lib dir="${solr.install.dir:../../../..}/modules/analysis-extras/lib" regex="lucene-analysis-icu-.*\.jar"/>

<!-- Data Directory

Used to specify an alternate directory to hold all index data
       other than the default ./data under the Solr home.  If
       replication is in use, this should match the replication
       configuration.
    -->
  <dataDir>${solr.data.dir:}</dataDir>

<!-- The DirectoryFactory to use for indexes.

solr.StandardDirectoryFactory is filesystem
       based and tries to pick the best implementation for the current
       JVM and platform.  solr.NRTCachingDirectoryFactory, the default,
       wraps solr.StandardDirectoryFactory and caches small files in memory
       for better NRT performance.

One can force a particular implementation via solr.MMapDirectoryFactory
       or solr.NIOFSDirectoryFactory.

solr.RAMDirectoryFactory is memory based and not persistent.
    -->
  <directoryFactory name="DirectoryFactory"
                    class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>

<codecFactory class="solr.SchemaCodecFactory"/>

<!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
       Index Config - These settings control low-level behavior of indexing
       Most example settings here show the default value, but are commented
       out, to more easily see where customizations have been made.

Note: This replaces <indexDefaults> and <mainIndex> from older versions
       ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
  <indexConfig>

<!-- LockFactory

This option specifies which Lucene LockFactory implementation
         to use.

single = SingleInstanceLockFactory - suggested for a
                  read-only index or when there is no possibility of
                  another process trying to modify the index.
         native = NativeFSLockFactory - uses OS native file locking.
                  Do not use when multiple solr webapps in the same
                  JVM are attempting to share a single index.
         simple = SimpleFSLockFactory  - uses a plain file for locking

Defaults: 'native' is default for Solr3.6 and later, otherwise
                   'simple' is the default

More details on the nuances of each LockFactory...
         https://cwiki.apache.org/confluence/display/lucene/AvailableLockFactories
    -->
    <lockType>${solr.lock.type:native}</lockType>

<!-- Commit Deletion Policy
         Custom deletion policies can be specified here. The class must
         implement org.apache.lucene.index.IndexDeletionPolicy.

The default Solr IndexDeletionPolicy implementation supports
         deleting index commit points on number of commits, age of
         commit point and optimized status.

The latest commit point should always be preserved regardless
         of the criteria.
    -->

<!-- Lucene Infostream

To aid in advanced debugging, Lucene provides an "InfoStream"
         of detailed information when indexing.

Setting The value to true will instruct the underlying Lucene
         IndexWriter to write its debugging info the specified file
      -->
    
  </indexConfig>

<updateHandler class="solr.DirectUpdateHandler2">

<updateLog>
      <str name="dir">${solr.ulog.dir:}</str>
      <int name="numVersionBuckets">${solr.ulog.numVersionBuckets:65536}</int>
    </updateLog>

<!-- AutoCommit

Perform a hard commit automatically under certain conditions.
         Instead of enabling autoCommit, consider using "commitWithin"
         when adding documents.

https://solr.apache.org/guide/solr/latest/indexing-guide/indexing-with-update-handlers.html

maxDocs - Maximum number of documents to add since the last
                   commit before automatically triggering a new commit.

maxTime - Maximum amount of time in ms that is allowed to pass
                   since a document was added before automatically
                   triggering a new commit.
         openSearcher - if false, the commit causes recent index changes
           to be flushed to stable storage, but does not cause a new
           searcher to be opened to make those changes visible.

If the updateLog is enabled, then it's highly recommended to
         have some sort of hard autoCommit to limit the log size.
      -->
    <autoCommit>
      <maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
      <openSearcher>false</openSearcher>
    </autoCommit>

<autoSoftCommit>
      <maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
    </autoSoftCommit>

<!-- Update Related Event Listeners

Various IndexWriter related events can trigger Listeners to
         take actions.

postCommit - fired after every commit or optimize command
         postOptimize - fired after every optimize command
      -->

</updateHandler>

<!-- IndexReaderFactory

Use the following format to specify a custom IndexReaderFactory,
       which allows for alternate IndexReader implementations.

** Experimental Feature **

Please note - Using a custom IndexReaderFactory may prevent
       certain other features from working. The API to
       IndexReaderFactory may change without warning or may even be
       removed from future releases if the problems cannot be
       resolved.

** Features that may not work with custom IndexReaderFactory **

The ReplicationHandler assumes a disk-resident index. Using a
       custom IndexReader implementation may cause incompatibility
       with ReplicationHandler and may cause replication to not work
       correctly. See SOLR-1366 for details.

-->

<query>

<!-- Maximum number of clauses allowed when parsing a boolean query string.

This limit only impacts boolean queries specified by a user as part of a query string,
         and provides per-collection controls on how complex user specified boolean queries can
         be.  Query strings that specify more clauses than this will result in an error.

If this per-collection limit is greater than the global `maxBooleanClauses` limit
         specified in `solr.xml`, it will have no effect, as that setting also limits the size
         of user specified boolean queries.
      -->
    <maxBooleanClauses>${solr.max.booleanClauses:1024}</maxBooleanClauses>

<!-- Filter Cache

Cache used by SolrIndexSearcher for filters (DocSets),
         unordered sets of *all* documents that match a query.  When a
         new searcher is opened, its caches may be prepopulated or
         "autowarmed" using data from caches in the old searcher.
         autowarmCount is the number of items to prepopulate. For
         CaffeineCache, the autowarmed items will be the most recently
         accessed items.

Parameters:
           class - the SolrCache implementation (CaffeineCache by default)
           size - the maximum number of entries in the cache
           initialSize - the initial capacity (number of entries) of
               the cache.  (see java.util.HashMap)
           autowarmCount - the number of entries to prepopulate from
               an old cache.
           maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
                      to occupy. Note that when this option is specified, the size
                      and initialSize parameters are ignored.
      -->
    <filterCache size="512"
                 initialSize="512"
                 autowarmCount="0"/>

<!-- Query Result Cache

Caches results of searches - ordered lists of document ids
         (DocList) based on a query, a sort, and the range of documents requested.
         Additional supported parameter by CaffeineCache:
            maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
                       to occupy
      -->
    <queryResultCache size="512"
                      initialSize="512"
                      autowarmCount="128"/>

<!-- Document Cache

Caches Lucene Document objects (the stored fields for each
         document).  Since Lucene internal document ids are transient,
         this cache will not be autowarmed.
      -->
    <documentCache size="512"
                   initialSize="512"
                   autowarmCount="0"/>

<cache name="perSegFilter"
           class="solr.CaffeineCache"
           size="4096"
           initialSize="1024"
           autowarmCount="1024"
           regenerator="solr.NoOpRegenerator" />

<!-- Field Value Cache

Cache used to hold field values that are quickly accessible
         by document id.  The fieldValueCache is created by default
         even if not configured here.
      -->

<!-- Custom Cache

Example of a generic cache.  These caches may be accessed by
         name through SolrIndexSearcher.getCache(),cacheLookup(), and
         cacheInsert().  The purpose is to enable easy caching of
         user/application level data.  The regenerator argument should
         be specified as an implementation of solr.CacheRegenerator
         if autowarming is desired.
      -->

<!-- Lazy Field Loading

If true, stored fields that are not requested will be loaded
         lazily.  This can result in a significant speed improvement
         if the usual case is to not load all stored fields,
         especially if the skipped fields are large compressed text
         fields.
    -->
    <enableLazyFieldLoading>true</enableLazyFieldLoading>

<!-- Use Filter For Sorted Query

A possible optimization that attempts to use a filter to
         satisfy a search.  If the requested sort does not include
         score, then the filterCache will be checked for a filter
         matching the query. If found, the filter will be used as the
         source of document ids, and then the sort will be applied to
         that.

For most situations, this will not be useful unless you
         frequently get the same search repeatedly with different sort
         options, and none of them ever use "score"
      -->

<!-- Result Window Size

An optimization for use with the queryResultCache.  When a search
         is requested, a superset of the requested number of document ids
         are collected.  For example, if a search for a particular query
         requests matching documents 10 through 19, and queryWindowSize is 50,
         then documents 0 through 49 will be collected and cached.  Any further
         requests in that range can be satisfied via the cache.
      -->
    <queryResultWindowSize>20</queryResultWindowSize>

<queryResultMaxDocsCached>200</queryResultMaxDocsCached>

<!-- Use Filter For Sorted Query

A possible optimization that attempts to use a filter to
   satisfy a search.  If the requested sort does not include
   score, then the filterCache will be checked for a filter
   matching the query. If found, the filter will be used as the
   source of document ids, and then the sort will be applied to
   that.

For most situations, this will not be useful unless you
   frequently get the same search repeatedly with different sort
   options, and none of them ever use "score"
-->

<!-- Query Related Event Listeners

Various IndexSearcher related events can trigger Listeners to
         take actions.

newSearcher - fired whenever a new searcher is being prepared
         and there is a current searcher handling requests (aka
         registered).  It can be used to prime certain caches to
         prevent long request times for certain requests.

firstSearcher - fired whenever a new searcher is being
         prepared but there is no current registered searcher to handle
         requests or to gain autowarming data from.

-->
    
    <listener event="newSearcher" class="solr.QuerySenderListener">
      <arr name="queries">
        
      </arr>
    </listener>
    <listener event="firstSearcher" class="solr.QuerySenderListener">
      <arr name="queries">
        
      </arr>
    </listener>

<!-- Use Cold Searcher

If a search request comes in and there is no current
         registered searcher, then immediately register the still
         warming searcher and use it.  If "false" then all requests
         will block until the first searcher is done warming.
      -->
    <useColdSearcher>false</useColdSearcher>

</query>

<!-- Request Dispatcher

This section contains instructions for how the SolrDispatchFilter
       should behave when processing requests for this SolrCore.

-->
  <requestDispatcher>
    <!-- Request Parsing

These settings indicate how Solr Requests may be parsed, and
         what restrictions may be placed on the ContentStreams from
         those requests

multipartUploadLimitInKB - specifies the max size (in KiB) of
         Multipart File Uploads that Solr will allow in a Request.

formdataUploadLimitInKB - specifies the max size (in KiB) of
         form data (application/x-www-form-urlencoded) sent via
         POST. You can use POST to pass request parameters not
         fitting into the URL.

addHttpRequestToContext - if set to true, it will instruct
         the requestParsers to include the original HttpServletRequest
         object in the context map of the SolrQueryRequest under the
         key "httpRequest". It will not be used by any of the existing
         Solr components, but may be useful when developing custom
         plugins.

<!-- HTTP Caching

Set HTTP caching related parameters (for proxy caches and clients).

The options below instruct Solr not to output any HTTP Caching
         related headers
      -->
    <httpCaching never304="true" />
    <!-- If you include a <cacheControl> directive, it will be used to
         generate a Cache-Control header (as well as an Expires header
         if the value contains "max-age=")

By default, no Cache-Control header is generated.

You can use the <cacheControl> option even if you have set
         never304="true"
      -->
    
    <!-- To enable Solr to respond with automatically generated HTTP
         Caching headers, and to response to Cache Validation requests
         correctly, set the value of never304="false"

This will cause Solr to generate Last-Modified and ETag
         headers based on the properties of the Index.

The following options can also be specified to affect the
         values of these headers...

lastModFrom - the default value is "openTime" which means the
         Last-Modified value (and validation against If-Modified-Since
         requests) will all be relative to when the current Searcher
         was opened.  You can change it to lastModFrom="dirLastMod" if
         you want the value to exactly correspond to when the physical
         index was last modified.

etagSeed="..." is an option you can change to force the ETag
         header (and validation against If-None-Match requests) to be
         different even if the index has not changed (ie: when making
         significant changes to your config file)

(lastModifiedFrom and etagSeed are both ignored if you use
         the never304="true" option)
      -->
    
  </requestDispatcher>

<!-- Request Handlers

https://solr.apache.org/guide/solr/latest/configuration-guide/requesthandlers-searchcomponents.html

Incoming queries will be dispatched to a specific handler by name based on the path specified in the request.

All handlers (Search Handlers, Update Request Handlers, and other specialized types) can have default parameters (defaults, appends and invariants).

Search Handlers can also (append, prepend or even replace) default or defined Search Components.

Update Request Handlers can leverage Update Request Processors to pre-process documents after they are loaded
       and before they are indexed/stored.

Not all Request Handlers are defined in the solrconfig.xml, many are implicit.
    -->

<requestHandler name="/select" class="solr.SearchHandler">
    <lst name="defaults">
      <str name="echoParams">explicit</str>
      <int name="rows">10</int>
    </lst>
  </requestHandler>

<requestHandler name="/query" class="solr.SearchHandler">
    <lst name="defaults">
      <str name="echoParams">explicit</str>
      <str name="wt">json</str>
      <str name="indent">true</str>
    </lst>
  </requestHandler>

<initParams path="/update/**,/query,/select,/spell">
    <lst name="defaults">
      <str name="df">_text_</str>
    </lst>
  </initParams>

<!-- Response Writers

https://solr.apache.org/guide/solr/latest/query-guide/response-writers.html

Request responses will be written using the writer specified by
       the 'wt' request parameter matching the name of a registered
       writer.

The "default" writer is the default and will be used if 'wt' is
       not specified in the request.
    -->
  
     <queryResponseWriter name="xml"
                          default="true"
	     class="solr.XMLResponseWriter" />

<!-- Query Parsers

https://solr.apache.org/guide/solr/latest/query-guide/query-syntax-and-parsers.html

Multiple QParserPlugins can be registered by name, and then
       used in either the "defType" param for the QueryComponent (used
       by SearchHandler) or in LocalParams
    -->

<!-- Function Parsers

https://solr.apache.org/guide/solr/latest/query-guide/function-queries.html

Multiple ValueSourceParsers can be registered by name, and then
       used as function names when using the "func" QParser.
    -->

<!--
     Could be something like:
     <transformer name="db" class="com.mycompany.LoadFromDatabaseTransformer" >
       <int name="connection">jdbc://....</int>
     </transformer>

To add a constant value to all docs, use:
     <transformer name="mytrans2" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
       <int name="value">5</int>
     </transformer>

If you want the user to still be able to change it with _value:something_ use this:
     <transformer name="mytrans3" class="org.apache.solr.response.transform.ValueAugmenterFactory" >
       <double name="defaultValue">5</double>
     </transformer>

If you are using the QueryElevationComponent, you may wish to mark documents that get boosted.  The
      EditorialMarkerFactory will do exactly that:
     <transformer name="qecBooster" class="org.apache.solr.response.transform.EditorialMarkerFactory" />
    -->
</config>

MR SKB