812 lines
32 KiB
XML
812 lines
32 KiB
XML
<?xml version="1.0" encoding="UTF-8" ?>
|
|
|
|
<!DOCTYPE config [
|
|
<!ENTITY extra SYSTEM "solrconfig_extra.xml">
|
|
<!ENTITY index SYSTEM "solrconfig_index.xml">
|
|
<!ENTITY query SYSTEM "solrconfig_query.xml">
|
|
<!ENTITY requestdispatcher SYSTEM "solrconfig_requestdispatcher.xml">
|
|
]>
|
|
|
|
<!--
|
|
For more details about configurations options that may appear in
|
|
this file, see http://wiki.apache.org/solr/SolrConfigXml.
|
|
-->
|
|
<config name="drupal-4.2.1-solr-8.x-0" >
|
|
<!-- 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.
|
|
-->
|
|
|
|
<!-- Set this to 'false' if you want solr to continue working after
|
|
it has encountered an severe configuration error. In a
|
|
production environment, you may want solr to keep working even
|
|
if one handler is mis-configured.
|
|
|
|
You may also set this to false using by setting the system
|
|
property:
|
|
|
|
-Dsolr.abortOnConfigurationError=false
|
|
-->
|
|
<abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>
|
|
|
|
<!-- Controls what version of Lucene various components of Solr
|
|
adhere to. Generally, you want to use the latest version to
|
|
get all bug fixes and improvements. It is highly recommended
|
|
that you fully re-index after changing this setting as it can
|
|
affect both how text is indexed and queried.
|
|
-->
|
|
<luceneMatchVersion>${solr.luceneMatchVersion:LUCENE_80}</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...
|
|
|
|
<lib dir="./lib" />
|
|
-->
|
|
|
|
<!-- 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 examples below can be used to load some solr-contribs along
|
|
with their external dependencies.
|
|
-->
|
|
<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-dataimporthandler-.*\.jar" />
|
|
|
|
<lib dir="${solr.install.dir:../../../..}/contrib/extraction/lib" regex=".*\.jar" />
|
|
<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-cell-\d.*\.jar" />
|
|
|
|
<lib dir="${solr.install.dir:../../../..}/contrib/langid/lib/" regex=".*\.jar" />
|
|
<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-langid-\d.*\.jar" />
|
|
|
|
<lib dir="${solr.install.dir:../../../..}/contrib/analysis-extras/lib" regex=".*\.jar" />
|
|
<lib dir="${solr.install.dir:../../../..}/contrib/analysis-extras/lucene-libs" regex=".*\.jar" />
|
|
<lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-analysis-extras-\d.*\.jar" />
|
|
|
|
<!-- an exact 'path' can be used instead of a 'dir' to specify a
|
|
specific jar file. This will cause a serious error to be logged
|
|
if it can't be loaded.
|
|
-->
|
|
<!--
|
|
<lib path="../a-jar-that-does-not-exist.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>${solr.data.dir:}</dataDir>
|
|
|
|
|
|
<!-- The DirectoryFactory to use for indexes.
|
|
|
|
solr.StandardDirectoryFactory is filesystem
|
|
based and tries to pick the best implementation for the current
|
|
JVM and platform. solr.NRTCachingDirectoryFactory, the default,
|
|
wraps solr.StandardDirectoryFactory and caches small files in memory
|
|
for better NRT performance.
|
|
|
|
One can force a particular implementation via solr.MMapDirectoryFactory,
|
|
solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
|
|
|
|
solr.RAMDirectoryFactory is memory based and not persistent.
|
|
-->
|
|
<directoryFactory name="DirectoryFactory"
|
|
class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}">
|
|
|
|
|
|
<!-- These will be used if you are using the solr.HdfsDirectoryFactory,
|
|
otherwise they will be ignored. If you don't plan on using hdfs,
|
|
you can safely remove this section. -->
|
|
<!-- The root directory that collection data should be written to. -->
|
|
<str name="solr.hdfs.home">${solr.hdfs.home:}</str>
|
|
<!-- The hadoop configuration files to use for the hdfs client. -->
|
|
<str name="solr.hdfs.confdir">${solr.hdfs.confdir:}</str>
|
|
<!-- Enable/Disable the hdfs cache. -->
|
|
<str name="solr.hdfs.blockcache.enabled">${solr.hdfs.blockcache.enabled:true}</str>
|
|
<!-- Enable/Disable using one global cache for all SolrCores.
|
|
The settings used will be from the first HdfsDirectoryFactory created. -->
|
|
<str name="solr.hdfs.blockcache.global">${solr.hdfs.blockcache.global:true}</str>
|
|
|
|
</directoryFactory>
|
|
|
|
<!-- The CodecFactory for defining the format of the inverted index.
|
|
The default implementation is SchemaCodecFactory, which is the official Lucene
|
|
index format, but hooks into the schema to provide per-field customization of
|
|
the postings lists and per-document values in the fieldType element
|
|
(postingsFormat/docValuesFormat). Note that most of the alternative implementations
|
|
are experimental, so if you choose to customize the index format, it's a good
|
|
idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)
|
|
before upgrading to a newer version to avoid unnecessary reindexing.
|
|
-->
|
|
<codecFactory class="solr.SchemaCodecFactory"/>
|
|
|
|
<!-- To enable dynamic schema REST APIs, remove the following <schemaFactory>.
|
|
-->
|
|
<schemaFactory class="ClassicIndexSchemaFactory"/>
|
|
|
|
<!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
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>
|
|
<!-- maxFieldLength was removed in 4.0. To get similar behavior, include a
|
|
LimitTokenCountFilterFactory in your fieldType definition. E.g.
|
|
<filter class="solr.LimitTokenCountFilterFactory" maxTokenCount="10000"/>
|
|
-->
|
|
<!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
|
|
<!-- <writeLockTimeout>1000</writeLockTimeout> -->
|
|
|
|
<!-- Expert: Enabling compound file will use less files for the index,
|
|
using fewer file descriptors on the expense of performance decrease.
|
|
Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
|
|
<!-- <useCompoundFile>false</useCompoundFile> -->
|
|
|
|
<!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
|
|
indexing for buffering added documents and deletions before they are
|
|
flushed to the Directory.
|
|
maxBufferedDocs sets a limit on the number of documents buffered
|
|
before flushing.
|
|
If both ramBufferSizeMB and maxBufferedDocs is set, then
|
|
Lucene will flush based on whichever limit is hit first.
|
|
The default is 100 MB. -->
|
|
<!-- <ramBufferSizeMB>100</ramBufferSizeMB> -->
|
|
<!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
|
|
|
|
<!-- Expert: Merge Policy
|
|
The Merge Policy in Lucene controls how merging of segments is done.
|
|
The default since Solr/Lucene 3.3 is TieredMergePolicy.
|
|
The default since Lucene 2.3 was the LogByteSizeMergePolicy,
|
|
Even older versions of Lucene used LogDocMergePolicy.
|
|
-->
|
|
<!--
|
|
<mergePolicyFactory class="solr.TieredMergePolicyFactory">
|
|
<int name="maxMergeAtOnce">10</int>
|
|
<int name="segmentsPerTier">10</int>
|
|
</mergePolicyFactory>
|
|
-->
|
|
|
|
<!-- Expert: Merge Scheduler
|
|
The Merge Scheduler in Lucene controls how merges are
|
|
performed. The ConcurrentMergeScheduler (Lucene 2.3 default)
|
|
can perform merges in the background using separate threads.
|
|
The SerialMergeScheduler (Lucene 2.2 default) does not.
|
|
-->
|
|
<!--
|
|
<mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
|
|
-->
|
|
|
|
<!-- 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...
|
|
http://wiki.apache.org/lucene-java/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.
|
|
-->
|
|
<!--
|
|
<deletionPolicy class="solr.SolrDeletionPolicy">
|
|
-->
|
|
<!-- The number of commit points to be kept -->
|
|
<!-- <str name="maxCommitsToKeep">1</str> -->
|
|
<!-- The number of optimized commit points to be kept -->
|
|
<!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
|
|
<!--
|
|
Delete all commit points once they have reached the given age.
|
|
Supports DateMathParser syntax e.g.
|
|
-->
|
|
<!--
|
|
<str name="maxCommitAge">30MINUTES</str>
|
|
<str name="maxCommitAge">1DAY</str>
|
|
-->
|
|
<!--
|
|
</deletionPolicy>
|
|
-->
|
|
|
|
<!-- 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 info stream to solr's log. By default,
|
|
this is enabled here, and controlled through log4j2.xml
|
|
-->
|
|
<infoStream>true</infoStream>
|
|
|
|
<!-- Let the config generator easily inject additional stuff. -->
|
|
&index;
|
|
|
|
</indexConfig>
|
|
|
|
<!-- The default high-performance update handler -->
|
|
<updateHandler class="solr.DirectUpdateHandler2">
|
|
|
|
<!-- Enables a transaction log, used for real-time get, durability, and
|
|
and solr cloud replica recovery. The log can grow as big as
|
|
uncommitted changes to the index, so use of a hard autoCommit
|
|
is recommended (see below).
|
|
"dir" - the target directory for transaction logs, defaults to the
|
|
solr data directory. -->
|
|
<updateLog>
|
|
<str name="dir">${solr.ulog.dir:}</str>
|
|
</updateLog>
|
|
|
|
<!-- AutoCommit
|
|
|
|
Perform a hard commit automatically under certain conditions.
|
|
Instead of enabling autoCommit, consider using "commitWithin"
|
|
when adding documents.
|
|
|
|
http://wiki.apache.org/solr/UpdateXmlMessages
|
|
|
|
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>
|
|
<maxDocs>${solr.autoCommit.MaxDocs:-1}</maxDocs>
|
|
<maxTime>${solr.autoCommit.MaxTime:15000}</maxTime>
|
|
<openSearcher>false</openSearcher>
|
|
</autoCommit>
|
|
|
|
<!-- softAutoCommit is like autoCommit except it causes a
|
|
'soft' commit which only ensures that changes are visible
|
|
but does not ensure that data is synced to disk. This is
|
|
faster and more near-realtime friendly than a hard commit.
|
|
-->
|
|
|
|
<autoSoftCommit>
|
|
<maxDocs>${solr.autoSoftCommit.MaxDocs:-1}</maxDocs>
|
|
<maxTime>${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
|
|
-->
|
|
<!-- The RunExecutableListener executes an external command from a
|
|
hook such as postCommit or postOptimize.
|
|
|
|
exe - the name of the executable to run
|
|
dir - dir to use as the current working directory. (default=".")
|
|
wait - the calling thread waits until the executable returns.
|
|
(default="true")
|
|
args - the arguments to pass to the program. (default is none)
|
|
env - environment variables to set. (default is none)
|
|
-->
|
|
<!-- This example shows how RunExecutableListener could be used
|
|
with the script based replication...
|
|
http://wiki.apache.org/solr/CollectionDistribution
|
|
-->
|
|
<!--
|
|
<listener event="postCommit" class="solr.RunExecutableListener">
|
|
<str name="exe">solr/bin/snapshooter</str>
|
|
<str name="dir">.</str>
|
|
<bool name="wait">true</bool>
|
|
<arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
|
|
<arr name="env"> <str>MYVAR=val1</str> </arr>
|
|
</listener>
|
|
-->
|
|
|
|
</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.
|
|
|
|
-->
|
|
<!--
|
|
<indexReaderFactory name="IndexReaderFactory" class="package.class">
|
|
<str name="someArg">Some Value</str>
|
|
</indexReaderFactory >
|
|
-->
|
|
|
|
<!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
Query section - these settings control query time things like caches
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
|
|
<query>
|
|
<!-- Let the config generator easily inject additional stuff. -->
|
|
&query;
|
|
|
|
<!-- 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.
|
|
|
|
|
|
-->
|
|
<!-- QuerySenderListener takes an array of NamedList and executes a
|
|
local query request for each NamedList in sequence.
|
|
-->
|
|
<listener event="newSearcher" class="solr.QuerySenderListener">
|
|
<arr name="queries">
|
|
<!--
|
|
<lst><str name="q">solr</str><str name="sort">price asc</str></lst>
|
|
<lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
|
|
-->
|
|
</arr>
|
|
</listener>
|
|
<listener event="firstSearcher" class="solr.QuerySenderListener">
|
|
<arr name="queries">
|
|
<lst>
|
|
<str name="q">static firstSearcher warming in solrconfig.xml</str>
|
|
</lst>
|
|
</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
|
|
|
|
enableRemoteStreaming - enables use of the stream.file
|
|
and stream.url parameters for specifying remote streams.
|
|
|
|
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.
|
|
|
|
*** WARNING ***
|
|
Before enabling remote streaming, you should make sure your
|
|
system has authentication enabled.
|
|
|
|
<requestParsers enableRemoteStreaming="false"
|
|
multipartUploadLimitInKB="-1"
|
|
formdataUploadLimitInKB="-1"
|
|
addHttpRequestToContext="false"/>
|
|
-->
|
|
<!-- Let the config generator easily inject additional stuff. -->
|
|
&requestdispatcher;
|
|
|
|
</requestDispatcher>
|
|
|
|
<!-- Search Components
|
|
|
|
Search components are registered to SolrCore and used by
|
|
instances of SearchHandler (which can access them by name)
|
|
|
|
By default, the following components are available:
|
|
|
|
<searchComponent name="query" class="solr.QueryComponent" />
|
|
<searchComponent name="facet" class="solr.FacetComponent" />
|
|
<searchComponent name="mlt" class="solr.MoreLikeThisComponent" />
|
|
<searchComponent name="highlight" class="solr.HighlightComponent" />
|
|
<searchComponent name="stats" class="solr.StatsComponent" />
|
|
<searchComponent name="debug" class="solr.DebugComponent" />
|
|
|
|
Default configuration in a requestHandler would look like:
|
|
|
|
<arr name="components">
|
|
<str>query</str>
|
|
<str>facet</str>
|
|
<str>mlt</str>
|
|
<str>highlight</str>
|
|
<str>stats</str>
|
|
<str>debug</str>
|
|
</arr>
|
|
|
|
If you register a searchComponent to one of the standard names,
|
|
that will be used instead of the default.
|
|
|
|
To insert components before or after the 'standard' components, use:
|
|
|
|
<arr name="first-components">
|
|
<str>myFirstComponentName</str>
|
|
</arr>
|
|
|
|
<arr name="last-components">
|
|
<str>myLastComponentName</str>
|
|
</arr>
|
|
|
|
NOTE: The component registered with the name "debug" will
|
|
always be executed after the "last-components"
|
|
|
|
-->
|
|
|
|
<!-- Following is a dynamic way to include other components or any customized solrconfig.xml stuff, added by other contrib modules -->
|
|
&extra;
|
|
|
|
<!-- Highlighting Component
|
|
|
|
http://wiki.apache.org/solr/HighlightingParameters
|
|
-->
|
|
<searchComponent class="solr.HighlightComponent" name="highlight">
|
|
<highlighting>
|
|
<!-- Configure the standard fragmenter -->
|
|
<!-- This could most likely be commented out in the "default" case -->
|
|
<fragmenter name="gap"
|
|
default="true"
|
|
class="solr.highlight.GapFragmenter">
|
|
<lst name="defaults">
|
|
<int name="hl.fragsize">100</int>
|
|
</lst>
|
|
</fragmenter>
|
|
|
|
<!-- A regular-expression-based fragmenter
|
|
(for sentence extraction)
|
|
-->
|
|
<fragmenter name="regex"
|
|
class="solr.highlight.RegexFragmenter">
|
|
<lst name="defaults">
|
|
<!-- slightly smaller fragsizes work better because of slop -->
|
|
<int name="hl.fragsize">70</int>
|
|
<!-- allow 50% slop on fragment sizes -->
|
|
<float name="hl.regex.slop">0.5</float>
|
|
<!-- a basic sentence pattern -->
|
|
<str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str>
|
|
</lst>
|
|
</fragmenter>
|
|
|
|
<!-- Configure the standard formatter -->
|
|
<formatter name="html"
|
|
default="true"
|
|
class="solr.highlight.HtmlFormatter">
|
|
<lst name="defaults">
|
|
<str name="hl.simple.pre"><![CDATA[<em>]]></str>
|
|
<str name="hl.simple.post"><![CDATA[</em>]]></str>
|
|
</lst>
|
|
</formatter>
|
|
|
|
<!-- Configure the standard encoder -->
|
|
<encoder name="html"
|
|
class="solr.highlight.HtmlEncoder" />
|
|
|
|
<!-- Configure the standard fragListBuilder -->
|
|
<fragListBuilder name="simple"
|
|
class="solr.highlight.SimpleFragListBuilder"/>
|
|
|
|
<!-- Configure the single fragListBuilder -->
|
|
<fragListBuilder name="single"
|
|
class="solr.highlight.SingleFragListBuilder"/>
|
|
|
|
<!-- Configure the weighted fragListBuilder -->
|
|
<fragListBuilder name="weighted"
|
|
default="true"
|
|
class="solr.highlight.WeightedFragListBuilder"/>
|
|
|
|
<!-- default tag FragmentsBuilder -->
|
|
<fragmentsBuilder name="default"
|
|
default="true"
|
|
class="solr.highlight.ScoreOrderFragmentsBuilder">
|
|
<!--
|
|
<lst name="defaults">
|
|
<str name="hl.multiValuedSeparatorChar">/</str>
|
|
</lst>
|
|
-->
|
|
</fragmentsBuilder>
|
|
|
|
<!-- multi-colored tag FragmentsBuilder -->
|
|
<fragmentsBuilder name="colored"
|
|
class="solr.highlight.ScoreOrderFragmentsBuilder">
|
|
<lst name="defaults">
|
|
<str name="hl.tag.pre"><![CDATA[
|
|
<b style="background:yellow">,<b style="background:lawgreen">,
|
|
<b style="background:aquamarine">,<b style="background:magenta">,
|
|
<b style="background:palegreen">,<b style="background:coral">,
|
|
<b style="background:wheat">,<b style="background:khaki">,
|
|
<b style="background:lime">,<b style="background:deepskyblue">]]></str>
|
|
<str name="hl.tag.post"><![CDATA[</b>]]></str>
|
|
</lst>
|
|
</fragmentsBuilder>
|
|
|
|
<boundaryScanner name="default"
|
|
default="true"
|
|
class="solr.highlight.SimpleBoundaryScanner">
|
|
<lst name="defaults">
|
|
<str name="hl.bs.maxScan">10</str>
|
|
<str name="hl.bs.chars">.,!? 	 </str>
|
|
</lst>
|
|
</boundaryScanner>
|
|
|
|
<boundaryScanner name="breakIterator"
|
|
class="solr.highlight.BreakIteratorBoundaryScanner">
|
|
<lst name="defaults">
|
|
<!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
|
|
<str name="hl.bs.type">WORD</str>
|
|
<!-- language and country are used when constructing Locale object. -->
|
|
<!-- And the Locale object will be used when getting instance of BreakIterator -->
|
|
<str name="hl.bs.language">en</str>
|
|
<str name="hl.bs.country">US</str>
|
|
</lst>
|
|
</boundaryScanner>
|
|
</highlighting>
|
|
</searchComponent>
|
|
|
|
<!-- Update Processors
|
|
|
|
Chains of Update Processor Factories for dealing with Update
|
|
Requests can be declared, and then used by name in Update
|
|
Request Processors
|
|
|
|
http://wiki.apache.org/solr/UpdateRequestProcessor
|
|
|
|
-->
|
|
<!-- Deduplication
|
|
|
|
An example dedup update processor that creates the "id" field
|
|
on the fly based on the hash code of some other fields. This
|
|
example has overwriteDupes set to false since we are using the
|
|
id field as the signatureField and Solr will maintain
|
|
uniqueness based on that anyway.
|
|
|
|
-->
|
|
<!--
|
|
<updateRequestProcessorChain name="dedupe">
|
|
<processor class="solr.processor.SignatureUpdateProcessorFactory">
|
|
<bool name="enabled">true</bool>
|
|
<str name="signatureField">id</str>
|
|
<bool name="overwriteDupes">false</bool>
|
|
<str name="fields">name,features,cat</str>
|
|
<str name="signatureClass">solr.processor.Lookup3Signature</str>
|
|
</processor>
|
|
<processor class="solr.LogUpdateProcessorFactory" />
|
|
<processor class="solr.RunUpdateProcessorFactory" />
|
|
</updateRequestProcessorChain>
|
|
-->
|
|
|
|
<!-- Language identification
|
|
|
|
This example update chain identifies the language of the incoming
|
|
documents using the langid contrib. The detected language is
|
|
written to field language_s. No field name mapping is done.
|
|
The fields used for detection are text, title, subject and description,
|
|
making this example suitable for detecting languages form full-text
|
|
rich documents injected via ExtractingRequestHandler.
|
|
See more about langId at http://wiki.apache.org/solr/LanguageDetection
|
|
-->
|
|
<!--
|
|
<updateRequestProcessorChain name="langid">
|
|
<processor class="org.apache.solr.update.processor.TikaLanguageIdentifierUpdateProcessorFactory">
|
|
<str name="langid.fl">text,title,subject,description</str>
|
|
<str name="langid.langField">language_s</str>
|
|
<str name="langid.fallback">en</str>
|
|
</processor>
|
|
<processor class="solr.LogUpdateProcessorFactory" />
|
|
<processor class="solr.RunUpdateProcessorFactory" />
|
|
</updateRequestProcessorChain>
|
|
-->
|
|
|
|
<!-- Script update processor
|
|
|
|
This example hooks in an update processor implemented using JavaScript.
|
|
|
|
See more about the script update processor at http://wiki.apache.org/solr/ScriptUpdateProcessor
|
|
-->
|
|
<!--
|
|
<updateRequestProcessorChain name="script">
|
|
<processor class="solr.StatelessScriptUpdateProcessorFactory">
|
|
<str name="script">update-script.js</str>
|
|
<lst name="params">
|
|
<str name="config_param">example config parameter</str>
|
|
</lst>
|
|
</processor>
|
|
<processor class="solr.RunUpdateProcessorFactory" />
|
|
</updateRequestProcessorChain>
|
|
-->
|
|
|
|
<!-- Response Writers
|
|
|
|
http://wiki.apache.org/solr/QueryResponseWriter
|
|
|
|
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.
|
|
-->
|
|
<!-- The following response writers are implicitly configured unless
|
|
overridden...
|
|
-->
|
|
<!--
|
|
<queryResponseWriter name="xml"
|
|
default="true"
|
|
class="solr.XMLResponseWriter" />
|
|
<queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
|
|
<queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
|
|
<queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
|
|
<queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
|
|
<queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
|
|
<queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
|
|
<queryResponseWriter name="schema.xml" class="solr.SchemaXmlResponseWriter"/>
|
|
-->
|
|
|
|
<queryResponseWriter name="json" class="solr.JSONResponseWriter">
|
|
</queryResponseWriter>
|
|
|
|
<!--
|
|
Custom response writers can be declared as needed...
|
|
-->
|
|
<!-- The solr.velocity.enabled flag is used by Solr's test cases so that this response writer is not
|
|
loaded (causing an error if contrib/velocity has not been built fully) -->
|
|
<!--
|
|
<queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" startup="lazy">
|
|
<str name="template.base.dir">${velocity.template.base.dir:}</str>
|
|
</queryResponseWriter>
|
|
-->
|
|
|
|
<!-- XSLT response writer transforms the XML output by any xslt file found
|
|
in Solr's conf/xslt directory. Changes to xslt files are checked for
|
|
every xsltCacheLifetimeSeconds.
|
|
-->
|
|
<queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
|
|
<int name="xsltCacheLifetimeSeconds">5</int>
|
|
</queryResponseWriter>
|
|
|
|
<!-- Query Parsers
|
|
|
|
https://lucene.apache.org/solr/guide/query-syntax-and-parsing.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
|
|
-->
|
|
<!-- example of registering a query parser -->
|
|
<!--
|
|
<queryParser name="myparser" class="com.mycompany.MyQParserPlugin"/>
|
|
-->
|
|
|
|
<!-- Function Parsers
|
|
|
|
http://wiki.apache.org/solr/FunctionQuery
|
|
|
|
Multiple ValueSourceParsers can be registered by name, and then
|
|
used as function names when using the "func" QParser.
|
|
-->
|
|
<!-- example of registering a custom function parser -->
|
|
<!--
|
|
<valueSourceParser name="myfunc"
|
|
class="com.mycompany.MyValueSourceParser" />
|
|
-->
|
|
|
|
|
|
<!-- Document Transformers
|
|
http://wiki.apache.org/solr/DocTransformers
|
|
-->
|
|
<!--
|
|
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>
|