You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@ranger.apache.org by ma...@apache.org on 2020/08/16 19:17:56 UTC
[ranger] 03/04: RANGER-2937 : Refresh Ranger's Solr configs
This is an automated email from the ASF dual-hosted git repository.
madhan pushed a commit to branch ranger-2.1
in repository https://gitbox.apache.org/repos/asf/ranger.git
commit 801e9b0f1b965c55156bbd08c945f3e9fe338df0
Author: Dhaval B. Shah <dh...@gmail.com>
AuthorDate: Thu Aug 13 13:37:00 2020 +0530
RANGER-2937 : Refresh Ranger's Solr configs
Signed-off-by: Mehul Parikh <me...@apache.org>
(cherry picked from commit 4706b1093da13eae77697ea5efce7b2fae357781)
---
.../solr_for_audit_setup/conf/solrconfig.xml | 1301 +++++---------------
1 file changed, 286 insertions(+), 1015 deletions(-)
diff --git a/security-admin/contrib/solr_for_audit_setup/conf/solrconfig.xml b/security-admin/contrib/solr_for_audit_setup/conf/solrconfig.xml
index 9791a1f..51b58e4 100644
--- a/security-admin/contrib/solr_for_audit_setup/conf/solrconfig.xml
+++ b/security-admin/contrib/solr_for_audit_setup/conf/solrconfig.xml
@@ -6,9 +6,7 @@
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.
@@ -16,15 +14,14 @@
limitations under the License.
-->
-<!--
+<!--
For more details about configurations options that may appear in
- this file, see http://wiki.apache.org/solr/SolrConfigXml.
+ this file, see http://wiki.apache.org/solr/SolrConfigXml.
-->
<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.
-->
@@ -35,67 +32,49 @@
that you fully re-index after changing this setting as it can
affect both how text is indexed and queried.
-->
- <luceneMatchVersion>5.2.0</luceneMatchVersion>
+ <luceneMatchVersion>8.4.1</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"
+ 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
+ <!-- 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
+ The example below can be used to load a solr-contrib 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:../../../..}/dist/" regex="solr-ltr-\d.*\.jar" /> -->
- <lib dir="${solr.install.dir:../../../..}/contrib/clustering/lib/" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-clustering-\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="${solr.install.dir:../../../..}/contrib/velocity/lib" regex=".*\.jar" />
- <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-velocity-\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
+ <!-- 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" />
+ <lib path="../a-jar-that-does-not-exist.jar" />
-->
- <!-- Data Directory
+ <lib dir="${solr.install.dir:../../../..}/dist/" regex="solr-dataimporthandler-.*\.jar" />
+ <!-- Data Directory
Used to specify an alternate directory to hold all index data
other than the default ./data under the Solr home. If
replication is in use, this should match the replication
@@ -105,19 +84,16 @@
<!-- The DirectoryFactory to use for indexes.
-
solr.StandardDirectoryFactory is filesystem
based and tries to pick the best implementation for the current
JVM and platform. solr.NRTCachingDirectoryFactory, the default,
wraps solr.StandardDirectoryFactory and caches small files in memory
for better NRT performance.
-
One can force a particular implementation via solr.MMapDirectoryFactory,
solr.NIOFSDirectoryFactory, or solr.SimpleFSDirectoryFactory.
-
- solr.RAMDirectoryFactory is memory based, not
- persistent, and doesn't work with replication.
+ solr.RAMDirectoryFactory is memory based and not persistent.
-->
+
<directoryFactory name="DirectoryFactory"
class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}">
@@ -145,55 +121,28 @@
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.
+ A "compressionMode" string element can be added to <codecFactory> to choose
+ between the existing compression modes in the default codec: "BEST_SPEED" (default)
+ or "BEST_COMPRESSION".
-->
<codecFactory class="solr.SchemaCodecFactory"/>
- <!-- To enable dynamic schema REST APIs, use the following for <schemaFactory>: -->
-
- <schemaFactory class="ManagedIndexSchemaFactory">
- <bool name="mutable">true</bool>
- <str name="managedSchemaResourceName">managed-schema</str>
- </schemaFactory>
-<!--
- When ManagedIndexSchemaFactory is specified, Solr will load the schema from
- the resource named in 'managedSchemaResourceName', rather than from schema.xml.
- Note that the managed schema resource CANNOT be named schema.xml. If the managed
- schema does not exist, Solr will create it after reading schema.xml, then rename
- 'schema.xml' to 'schema.xml.bak'.
-
- Do NOT hand edit the managed schema - external modifications will be ignored and
- overwritten as a result of schema modification REST API calls.
-
- When ManagedIndexSchemaFactory is specified with mutable = true, schema
- modification REST API calls will be allowed; otherwise, error responses will be
- sent back for these requests.
-
- <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.
+ <!-- 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> -->
- <!-- The maximum number of simultaneous threads that may be
- indexing documents at once in IndexWriter; if more than this
- many threads arrive they will wait for others to finish.
- Default in Solr/Lucene is 8. -->
- <!-- <maxIndexingThreads>8</maxIndexingThreads> -->
-
- <!-- Expert: Enabling compound file will use less files for the index,
- using fewer file descriptors on the expense of performance decrease.
+ <!-- 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> -->
@@ -203,34 +152,31 @@
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> -->
+ Lucene will flush based on whichever limit is hit first. -->
+ <ramBufferSizeMB>128</ramBufferSizeMB>
<!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
- <!-- Expert: Merge Policy
+ <!-- Expert: ramPerThreadHardLimitMB sets the maximum amount of RAM that can be consumed
+ per thread before they are flushed. When limit is exceeded, this triggers a forced
+ flush even if ramBufferSizeMB has not been exceeded.
+ This is a safety limit to prevent Lucene's DocumentsWriterPerThread from address space
+ exhaustion due to its internal 32 bit signed integer based memory addressing.
+ The specified value should be greater than 0 and less than 2048MB. When not specified,
+ Solr uses Lucene's default value 1945. -->
+ <!-- <ramPerThreadHardLimitMB>1945</ramPerThreadHardLimitMB> -->
+
+ <!-- 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.
-->
<!--
- <mergePolicy class="org.apache.lucene.index.TieredMergePolicy">
+ <mergePolicyFactory class="org.apache.solr.index.TieredMergePolicyFactory">
<int name="maxMergeAtOnce">10</int>
<int name="segmentsPerTier">10</int>
- </mergePolicy>
- -->
-
- <!-- Merge Factor
- The merge factor controls how many segments will get merged at a time.
- For TieredMergePolicy, mergeFactor is a convenience parameter which
- will set both MaxMergeAtOnce and SegmentsPerTier at once.
- For LogByteSizeMergePolicy, mergeFactor decides how many new segments
- will be allowed before they are merged into one.
- Default is 10 for both merge policies.
- -->
- <!--
- <mergeFactor>10</mergeFactor>
+ <double name="noCFSRatio">0.1</double>
+ </mergePolicyFactory>
-->
<!-- Expert: Merge Scheduler
@@ -239,15 +185,13 @@
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
-
+ <!-- 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.
@@ -255,83 +199,61 @@
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>
- <!-- Unlock On Startup
-
- If true, unlock any held write or commit locks on startup.
- This defeats the locking mechanism that allows multiple
- processes to safely access a lucene index, and should be used
- with care. Default is "false".
-
- This is not needed if lock type is 'single'
- -->
- <!--
- <unlockOnStartup>false</unlockOnStartup>
- -->
-
<!-- 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>
+ <!-- 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 log4j.properties.
+ Setting The value to true will instruct the underlying Lucene
+ IndexWriter to write its debugging info the specified file
-->
- <infoStream>true</infoStream>
+ <!-- <infoStream file="INFOSTREAM.txt">false</infoStream> -->
</indexConfig>
<!-- JMX
-
This example enables JMX if and only if an existing MBeanServer
is found, use this if you want to configure JMX through JVM
parameters. Remove this to disable exposing Solr configuration
and statistics to JMX.
-
For more details see http://wiki.apache.org/solr/SolrJmx
-->
<jmx />
<!-- If you want to connect to a particular server, specify the
- agentId
+ agentId
-->
<!-- <jmx agentId="myAgent" /> -->
<!-- If you want to start a new MBeanServer, specify the serviceUrl -->
@@ -346,36 +268,40 @@
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. -->
+ solr data directory.
+ "numVersionBuckets" - sets the number of buckets used to keep
+ track of max version values when checking for re-ordered
+ updates; increase this value to reduce the cost of
+ synchronizing access to version buckets during high-volume
+ indexing, this requires 8 bytes (long) * numVersionBuckets
+ of heap space per Solr core.
+ -->
<updateLog>
<str name="dir">${solr.ulog.dir:}</str>
+ <int name="tlogDfsReplication">${solr.ulog.tlogDfsReplication:3}</int>
+ <int name="numVersionBuckets">${solr.ulog.numVersionBuckets:65536}</int>
</updateLog>
-
- <!-- AutoCommit
+ <!-- AutoCommit
Perform a hard commit automatically under certain conditions.
Instead of enabling autoCommit, consider using "commitWithin"
- when adding documents.
-
+ 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.
+ 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>${solr.autoCommit.maxTime:15000}</maxTime>
- <openSearcher>false</openSearcher>
- </autoCommit>
+ <autoCommit>
+ <maxTime>${solr.autoCommit.maxTime:60000}</maxTime>
+ <openSearcher>false</openSearcher>
+ </autoCommit>
<!-- softAutoCommit is like autoCommit except it causes a
'soft' commit which only ensures that changes are visible
@@ -383,24 +309,21 @@
faster and more near-realtime friendly than a hard commit.
-->
- <autoSoftCommit>
- <maxTime>${solr.autoSoftCommit.maxTime:5000}</maxTime>
- </autoSoftCommit>
+ <autoSoftCommit>
+ <maxTime>${solr.autoSoftCommit.maxTime:15000}</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.
+ 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)
@@ -420,28 +343,21 @@
-->
</updateHandler>
-
- <!-- IndexReaderFactory
+ <!-- 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">
@@ -453,28 +369,23 @@
Query section - these settings control query time things like caches
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
<query>
- <!-- Max Boolean Clauses
-
- Maximum number of clauses in each BooleanQuery, an exception
- is thrown if exceeded.
- ** WARNING **
+ <!-- Maximum number of clauses allowed when parsing a boolean query string.
- This option actually modifies a global Lucene property that
- will affect all SolrCores. If multiple solrconfig.xml files
- disagree on this property, the value at any given moment will
- be based on the last SolrCore to be initialized.
+ 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 then this will result in an error.
+ If this per-collection limit is greater then 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>1024</maxBooleanClauses>
-
+ <maxBooleanClauses>${solr.max.booleanClauses:1024}</maxBooleanClauses>
<!-- Solr Internal Query Caches
-
There are two implementations of cache available for Solr,
LRUCache, based on a synchronized LinkedHashMap, and
- FastLRUCache, based on a ConcurrentHashMap.
-
+ FastLRUCache, based on a ConcurrentHashMap.
FastLRUCache has faster gets and slower puts in single
threaded operation and thus is generally faster than LRUCache
when the hit ratio of the cache is high (> 75%), and may be
@@ -482,7 +393,6 @@
-->
<!-- 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
@@ -490,7 +400,6 @@
autowarmCount is the number of items to prepopulate. For
LRUCache, the autowarmed items will be the most recently
accessed items.
-
Parameters:
class - the SolrCache implementation LRUCache or
(LRUCache or FastLRUCache)
@@ -498,45 +407,47 @@
initialSize - the initial capacity (number of entries) of
the cache. (see java.util.HashMap)
autowarmCount - the number of entries to prepopulate from
- and old cache.
+ and 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 class="solr.FastLRUCache"
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.
+ (DocList) based on a query, a sort, and the range of documents requested.
+ Additional supported parameter by LRUCache:
+ maxRamMB - the maximum amount of RAM (in MB) that this cache is allowed
+ to occupy
-->
<queryResultCache class="solr.LRUCache"
- size="512"
- initialSize="512"
- autowarmCount="0"/>
-
- <!-- Document Cache
+ size="512"
+ initialSize="512"
+ autowarmCount="0"/>
+ <!-- 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.
+ this cache will not be autowarmed.
-->
<documentCache class="solr.LRUCache"
size="512"
initialSize="512"
autowarmCount="0"/>
-
- <!-- custom cache currently used by block join -->
+
+ <!-- custom cache currently used by block join -->
<cache name="perSegFilter"
- class="solr.search.LRUCache"
- size="10"
- initialSize="0"
- autowarmCount="10"
- regenerator="solr.NoOpRegenerator" />
+ class="solr.search.LRUCache"
+ size="10"
+ initialSize="0"
+ autowarmCount="10"
+ 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.
@@ -549,13 +460,12 @@
-->
<!-- 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.
+ be specified as an implementation of solr.CacheRegenerator
+ if autowarming is desired.
-->
<!--
<cache name="myUserCache"
@@ -569,7 +479,6 @@
<!-- 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,
@@ -578,57 +487,49 @@
-->
<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"
- -->
- <!--
- <useFilterForSortedQuery>true</useFilterForSortedQuery>
- -->
-
- <!-- 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>
-
- <!-- Maximum number of documents to cache for any entry in the
- queryResultCache.
- -->
- <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
-
- <!-- Query Related Event Listeners
-
- Various IndexSearcher related events can trigger Listeners to
- take actions.
+ <!-- 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"
+ -->
+ <!--
+ <useFilterForSortedQuery>true</useFilterForSortedQuery>
+ -->
- 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.
+ <!-- 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>
- 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.
+ <!-- Maximum number of documents to cache for any entry in the
+ queryResultCache.
+ -->
+ <queryResultMaxDocsCached>200</queryResultMaxDocsCached>
-
- -->
+ <!-- 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.
+ local query request for each NamedList in sequence.
-->
<listener event="newSearcher" class="solr.QuerySenderListener">
<arr name="queries">
@@ -640,94 +541,67 @@
</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>true</useColdSearcher>
+ <useColdSearcher>false</useColdSearcher>
- <!-- Max Warming Searchers
-
- Maximum number of searchers that may be warming in the
- background concurrently. An error is returned if this limit
- is exceeded.
-
- Recommend values of 1-2 for read-only slaves, higher for
- masters w/o cache warming.
+ <!-- Slow Query Request Logging
+ Any queries that take longer than the specified threshold
+ will be logged as "slow" queries.
+ To disable slow request logging for this Solr config,
+ set the value to -1
-->
- <maxWarmingSearchers>2</maxWarmingSearchers>
+ <slowQueryThresholdMillis>5000</slowQueryThresholdMillis>
</query>
<!-- Request Dispatcher
-
This section contains instructions for how the SolrDispatchFilter
should behave when processing requests for this SolrCore.
-
- handleSelect is a legacy option that affects the behavior of requests
- such as /select?qt=XXX
-
- handleSelect="true" will cause the SolrDispatchFilter to process
- the request and dispatch the query to a handler specified by the
- "qt" param, assuming "/select" isn't already registered.
-
- handleSelect="false" will cause the SolrDispatchFilter to
- ignore "/select" requests, resulting in a 404 unless a handler
- is explicitly registered with the name "/select"
-
- handleSelect="true" is not recommended for new users, but is the default
- for backwards compatibility
-->
- <requestDispatcher handleSelect="false" >
+ <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
+ 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
+ Solr components, but may be useful when developing custom
plugins.
-
*** WARNING ***
- The settings below authorize Solr to fetch remote files, You
- should make sure your system has some authentication before
- using enableRemoteStreaming="true"
-
- -->
- <requestParsers enableRemoteStreaming="true"
+ Before enabling remote streaming, you should make sure your
+ system has authentication enabled.
+ -->
+ <requestParsers enableRemoteStreaming="true"
multipartUploadLimitInKB="2048000"
formdataUploadLimitInKB="2048"
- addHttpRequestToContext="false"/>
+ addHttpRequestToContext="true"/>
<!-- 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
-->
@@ -735,80 +609,52 @@
<!-- 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"
-->
<!--
<httpCaching never304="true" >
- <cacheControl>max-age=30, public</cacheControl>
+ <cacheControl>max-age=30, public</cacheControl>
</httpCaching>
-->
<!-- 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)
-->
<!--
<httpCaching lastModifiedFrom="openTime"
etagSeed="Solr">
- <cacheControl>max-age=30, public</cacheControl>
+ <cacheControl>max-age=30, public</cacheControl>
</httpCaching>
-->
</requestDispatcher>
- <!-- Request Handlers
-
+ <!-- Request Handlers
http://wiki.apache.org/solr/SolrRequestHandler
-
Incoming queries will be dispatched to a specific handler by name
based on the path specified in the request.
-
- Legacy behavior: If the request path uses "/select" but no Request
- Handler has that name, and if handleSelect="true" has been specified in
- the requestDispatcher, then the Request Handler is dispatched based on
- the qt parameter. Handlers without a leading '/' are accessed this way
- like so: http://host/app/[core/]select?qt=name If no qt is
- given, then the requestHandler that declares default="true" will be
- used or the one named "standard".
-
If a Request Handler is declared with startup="lazy", then it will
not be initialized until the first request that uses it.
-
-->
-
- <requestHandler name="/dataimport" class="solr.DataImportHandler">
- <lst name="defaults">
- <str name="config">solr-data-config.xml</str>
- </lst>
- </requestHandler>
-
<!-- SearchHandler
-
http://wiki.apache.org/solr/SearchHandler
-
For processing Search Queries, the primary Request Handler
provided with Solr is "SearchHandler" It delegates to a sequent
of SearchComponents (see below) and supports distributed
@@ -818,11 +664,16 @@
<!-- default values for query parameters can be specified, these
will be overridden by parameters in the request
-->
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <int name="rows">10</int>
- <str name="df">text</str>
- </lst>
+ <lst name="defaults">
+ <str name="echoParams">explicit</str>
+ <int name="rows">10</int>
+ <!-- Default search field
+ <str name="df">text</str>
+ -->
+ <!-- Change from JSON to XML format (the default prior to Solr 7.0)
+ <str name="wt">xml</str>
+ -->
+ </lst>
<!-- In addition to defaults, "appends" params can be specified
to identify values which should be appended to the list of
multi-val params from the query (or the existing "defaults").
@@ -831,7 +682,6 @@
any query time fq params the user may specify, as a mechanism for
partitioning the index, independent of any user selected filtering
that may also be desired (perhaps as a result of faceted searching).
-
NOTE: there is *absolutely* nothing a client can do to prevent these
"appends" values from being used, so don't use this mechanism
unless you are sure you always want it.
@@ -845,14 +695,12 @@
the options available to Solr clients. Any params values
specified here are used regardless of what values may be specified
in either the query, the "defaults", or the "appends" params.
-
In this example, the facet.field and facet.query params would
be fixed, limiting the facets clients can use. Faceting is
not turned on by default - but if the client does specify
facet=true in the request, these are the only facets they
will be able to see counts for; regardless of what other
facet.field or facet.query params they may specify.
-
NOTE: there is *absolutely* nothing a client can do to prevent these
"invariants" values from being used, so don't use this mechanism
unless you are sure you always want it.
@@ -875,297 +723,34 @@
<str>nameOfCustomComponent2</str>
</arr>
-->
- </requestHandler>
+ </requestHandler>
<!-- A request handler that returns indented JSON by default -->
<requestHandler name="/query" class="solr.SearchHandler">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <str name="wt">json</str>
- <str name="indent">true</str>
- <str name="df">text</str>
- </lst>
- </requestHandler>
-
-
- <!-- realtime get handler, guaranteed to return the latest stored fields of
- any document, without the need to commit or open a new searcher. The
- current implementation relies on the updateLog feature being enabled.
-
- ** WARNING **
- Do NOT disable the realtime get handler at /get if you are using
- SolrCloud otherwise any leader election will cause a full sync in ALL
- replicas for the shard in question. Similarly, a replica recovery will
- also always fetch the complete index from the leader because a partial
- sync will not be possible in the absence of this handler.
- -->
- <requestHandler name="/get" class="solr.RealTimeGetHandler">
- <lst name="defaults">
- <str name="omitHeader">true</str>
- <str name="wt">json</str>
- <str name="indent">true</str>
- </lst>
- </requestHandler>
-
-
- <!-- A Robust Example
-
- This example SearchHandler declaration shows off usage of the
- SearchHandler with many defaults declared
-
- Note that multiple instances of the same Request Handler
- (SearchHandler) can be registered multiple times with different
- names (and different init parameters)
- -->
- <requestHandler name="/browse" class="solr.SearchHandler">
<lst name="defaults">
<str name="echoParams">explicit</str>
-
- <!-- VelocityResponseWriter settings -->
- <str name="wt">velocity</str>
- <str name="v.template">browse</str>
- <str name="v.layout">layout</str>
-
- <!-- Query settings -->
- <str name="defType">edismax</str>
- <str name="q.alt">*:*</str>
- <str name="rows">10</str>
- <str name="fl">*,score</str>
-
- <!-- Faceting defaults -->
- <str name="facet">on</str>
- <str name="facet.mincount">1</str>
+ <str name="wt">json</str>
+ <str name="indent">true</str>
</lst>
</requestHandler>
-
- <initParams path="/update/**,/query,/select,/tvrh,/elevate,/spell,/browse">
+ <initParams path="/update/**,/query,/select,/spell">
<lst name="defaults">
- <str name="df">text</str>
- <str name="update.chain">add-unknown-fields-to-the-schema</str>
+ <str name="df">_text_</str>
</lst>
</initParams>
- <!-- Update Request Handler.
-
- http://wiki.apache.org/solr/UpdateXmlMessages
-
- The canonical Request Handler for Modifying the Index through
- commands specified using XML, JSON, CSV, or JAVABIN
-
- Note: Since solr1.1 requestHandlers requires a valid content
- type header if posted in the body. For example, curl now
- requires: -H 'Content-type:text/xml; charset=utf-8'
-
- To override the request content type and force a specific
- Content-type, use the request parameter:
- ?update.contentType=text/csv
-
- This handler will pick a response format to match the input
- if the 'wt' parameter is not explicit
- -->
- <requestHandler name="/update" class="solr.UpdateRequestHandler">
- <!-- See below for information on defining
- updateRequestProcessorChains that can be used by name
- on each Update Request
- -->
- <!--
- <lst name="defaults">
- <str name="update.chain">dedupe</str>
- </lst>
- -->
- </requestHandler>
-
- <!-- Solr Cell Update Request Handler
-
- http://wiki.apache.org/solr/ExtractingRequestHandler
-
- -->
- <requestHandler name="/update/extract"
- startup="lazy"
- class="solr.extraction.ExtractingRequestHandler" >
- <lst name="defaults">
- <str name="lowernames">true</str>
- <str name="uprefix">ignored_</str>
-
- <!-- capture link hrefs but ignore div attributes -->
- <str name="captureAttr">true</str>
- <str name="fmap.a">links</str>
- <str name="fmap.div">ignored_</str>
- </lst>
- </requestHandler>
-
-
- <!-- Field Analysis Request Handler
-
- RequestHandler that provides much the same functionality as
- analysis.jsp. Provides the ability to specify multiple field
- types and field names in the same request and outputs
- index-time and query-time analysis for each of them.
-
- Request parameters are:
- analysis.fieldname - field name whose analyzers are to be used
-
- analysis.fieldtype - field type whose analyzers are to be used
- analysis.fieldvalue - text for index-time analysis
- q (or analysis.q) - text for query time analysis
- analysis.showmatch (true|false) - When set to true and when
- query analysis is performed, the produced tokens of the
- field value analysis will be marked as "matched" for every
- token that is produces by the query analysis
- -->
- <requestHandler name="/analysis/field"
- startup="lazy"
- class="solr.FieldAnalysisRequestHandler" />
-
-
- <!-- Document Analysis Handler
-
- http://wiki.apache.org/solr/AnalysisRequestHandler
-
- An analysis handler that provides a breakdown of the analysis
- process of provided documents. This handler expects a (single)
- content stream with the following format:
-
- <docs>
- <doc>
- <field name="id">1</field>
- <field name="name">The Name</field>
- <field name="text">The Text Value</field>
- </doc>
- <doc>...</doc>
- <doc>...</doc>
- ...
- </docs>
-
- Note: Each document must contain a field which serves as the
- unique key. This key is used in the returned response to associate
- an analysis breakdown to the analyzed document.
-
- Like the FieldAnalysisRequestHandler, this handler also supports
- query analysis by sending either an "analysis.query" or "q"
- request parameter that holds the query text to be analyzed. It
- also supports the "analysis.showmatch" parameter which when set to
- true, all field tokens that match the query tokens will be marked
- as a "match".
- -->
- <requestHandler name="/analysis/document"
- class="solr.DocumentAnalysisRequestHandler"
- startup="lazy" />
-
- <!-- This single handler is equivalent to the following... -->
- <!--
- <requestHandler name="/admin/luke" class="solr.admin.LukeRequestHandler" />
- <requestHandler name="/admin/system" class="solr.admin.SystemInfoHandler" />
- <requestHandler name="/admin/plugins" class="solr.admin.PluginInfoHandler" />
- <requestHandler name="/admin/threads" class="solr.admin.ThreadDumpHandler" />
- <requestHandler name="/admin/properties" class="solr.admin.PropertiesRequestHandler" />
- <requestHandler name="/admin/file" class="solr.admin.ShowFileRequestHandler" >
- -->
- <!-- If you wish to hide files under ${solr.home}/conf, explicitly
- register the ShowFileRequestHandler using the definition below.
- NOTE: The glob pattern ('*') is the only pattern supported at present, *.xml will
- not exclude all files ending in '.xml'. Use it to exclude _all_ updates
- -->
- <!--
- <requestHandler name="/admin/file"
- class="solr.admin.ShowFileRequestHandler" >
- <lst name="invariants">
- <str name="hidden">synonyms.txt</str>
- <str name="hidden">anotherfile.txt</str>
- <str name="hidden">*</str>
- </lst>
- </requestHandler>
- -->
-
- <!--
- Enabling this request handler (which is NOT a default part of the admin handler) will allow the Solr UI to edit
- all the config files. This is intended for secure/development use ONLY! Leaving available and publically
- accessible is a security vulnerability and should be done with extreme caution!
- -->
- <!--
- <requestHandler name="/admin/fileedit" class="solr.admin.EditFileRequestHandler" >
- <lst name="invariants">
- <str name="hidden">synonyms.txt</str>
- <str name="hidden">anotherfile.txt</str>
- </lst>
- </requestHandler>
- -->
- <!-- ping/healthcheck -->
- <requestHandler name="/admin/ping" class="solr.PingRequestHandler">
- <lst name="invariants">
- <str name="q">solrpingquery</str>
- </lst>
- <lst name="defaults">
- <str name="echoParams">all</str>
- </lst>
- <!-- An optional feature of the PingRequestHandler is to configure the
- handler with a "healthcheckFile" which can be used to enable/disable
- the PingRequestHandler.
- relative paths are resolved against the data dir
- -->
- <!-- <str name="healthcheckFile">server-enabled.txt</str> -->
- </requestHandler>
-
- <!-- Echo the request contents back to the client -->
- <requestHandler name="/debug/dump" class="solr.DumpRequestHandler" >
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <str name="echoHandler">true</str>
- </lst>
- </requestHandler>
-
- <!-- Solr Replication
-
- The SolrReplicationHandler supports replicating indexes from a
- "master" used for indexing and "slaves" used for queries.
-
- http://wiki.apache.org/solr/SolrReplication
-
- It is also necessary for SolrCloud to function (in Cloud mode, the
- replication handler is used to bulk transfer segments when nodes
- are added or need to recover).
-
- https://wiki.apache.org/solr/SolrCloud/
- -->
- <requestHandler name="/replication" class="solr.ReplicationHandler" >
- <!--
- To enable simple master/slave replication, uncomment one of the
- sections below, depending on whether this solr instance should be
- the "master" or a "slave". If this instance is a "slave" you will
- also need to fill in the masterUrl to point to a real machine.
- -->
- <!--
- <lst name="master">
- <str name="replicateAfter">commit</str>
- <str name="replicateAfter">startup</str>
- <str name="confFiles">schema.xml,stopwords.txt</str>
- </lst>
- -->
- <!--
- <lst name="slave">
- <str name="masterUrl">http://your-master-hostname:8983/solr</str>
- <str name="pollInterval">00:00:60</str>
- </lst>
- -->
- </requestHandler>
-
<!-- Search Components
-
- Search components are registered to SolrCore and used by
+ 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>
@@ -1174,32 +759,24 @@
<str>stats</str>
<str>debug</str>
</arr>
-
- If you register a searchComponent to one of the standard names,
+ 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"
-
+ always be executed after the "last-components"
-->
-
- <!-- Spell Check
-
- The spell check component can return a list of alternative spelling
- suggestions.
- http://wiki.apache.org/solr/SpellCheckComponent
- -->
+ <!-- Spell Check
+ The spell check component can return a list of alternative spelling
+ suggestions.
+ http://wiki.apache.org/solr/SpellCheckComponent
+ -->
<searchComponent name="spellcheck" class="solr.SpellCheckComponent">
<str name="queryAnalyzerFieldType">text_general</str>
@@ -1211,7 +788,7 @@
<!-- a spellchecker built from a field of the main index -->
<lst name="spellchecker">
<str name="name">default</str>
- <str name="field">text</str>
+ <str name="field">_text_</str>
<str name="classname">solr.DirectSolrSpellChecker</str>
<!-- the spellcheck distance measure used, the default is the internal levenshtein -->
<str name="distanceMeasure">internal</str>
@@ -1228,242 +805,57 @@
<!-- maximum threshold of documents a query term can appear to be considered for correction -->
<float name="maxQueryFrequency">0.01</float>
<!-- uncomment this to require suggestions to occur in 1% of the documents
- <float name="thresholdTokenFrequency">.01</float>
+ <float name="thresholdTokenFrequency">.01</float>
-->
</lst>
-
+
<!-- a spellchecker that can break or combine words. See "/spell" handler below for usage -->
+ <!--
<lst name="spellchecker">
<str name="name">wordbreak</str>
- <str name="classname">solr.WordBreakSolrSpellChecker</str>
+ <str name="classname">solr.WordBreakSolrSpellChecker</str>
<str name="field">name</str>
<str name="combineWords">true</str>
<str name="breakWords">true</str>
<int name="maxChanges">10</int>
</lst>
-
- <!-- a spellchecker that uses a different distance measure -->
- <!--
- <lst name="spellchecker">
- <str name="name">jarowinkler</str>
- <str name="field">spell</str>
- <str name="classname">solr.DirectSolrSpellChecker</str>
- <str name="distanceMeasure">
- org.apache.lucene.search.spell.JaroWinklerDistance
- </str>
- </lst>
- -->
-
- <!-- a spellchecker that use an alternate comparator
-
- comparatorClass be one of:
- 1. score (default)
- 2. freq (Frequency first, then score)
- 3. A fully qualified class name
- -->
- <!--
- <lst name="spellchecker">
- <str name="name">freq</str>
- <str name="field">lowerfilt</str>
- <str name="classname">solr.DirectSolrSpellChecker</str>
- <str name="comparatorClass">freq</str>
- -->
-
- <!-- A spellchecker that reads the list of words from a file -->
- <!--
- <lst name="spellchecker">
- <str name="classname">solr.FileBasedSpellChecker</str>
- <str name="name">file</str>
- <str name="sourceLocation">spellings.txt</str>
- <str name="characterEncoding">UTF-8</str>
- <str name="spellcheckIndexDir">spellcheckerFile</str>
- </lst>
- -->
+ -->
</searchComponent>
-
- <!-- A request handler for demonstrating the spellcheck component.
+ <!-- A request handler for demonstrating the spellcheck component.
NOTE: This is purely as an example. The whole purpose of the
SpellCheckComponent is to hook it into the request handler that
handles your normal user queries so that a separate request is
not needed to get suggestions.
-
IN OTHER WORDS, THERE IS REALLY GOOD CHANCE THE SETUP BELOW IS
NOT WHAT YOU WANT FOR YOUR PRODUCTION SYSTEM!
-
See http://wiki.apache.org/solr/SpellCheckComponent for details
on the request parameters.
-->
<requestHandler name="/spell" class="solr.SearchHandler" startup="lazy">
<lst name="defaults">
- <str name="df">text</str>
<!-- Solr will use suggestions from both the 'default' spellchecker
and from the 'wordbreak' spellchecker and combine them.
collations (re-written queries) can include a combination of
corrections from both spellcheckers -->
<str name="spellcheck.dictionary">default</str>
- <str name="spellcheck.dictionary">wordbreak</str>
<str name="spellcheck">on</str>
- <str name="spellcheck.extendedResults">true</str>
+ <str name="spellcheck.extendedResults">true</str>
<str name="spellcheck.count">10</str>
<str name="spellcheck.alternativeTermCount">5</str>
- <str name="spellcheck.maxResultsForSuggest">5</str>
+ <str name="spellcheck.maxResultsForSuggest">5</str>
<str name="spellcheck.collate">true</str>
- <str name="spellcheck.collateExtendedResults">true</str>
+ <str name="spellcheck.collateExtendedResults">true</str>
<str name="spellcheck.maxCollationTries">10</str>
- <str name="spellcheck.maxCollations">5</str>
+ <str name="spellcheck.maxCollations">5</str>
</lst>
<arr name="last-components">
<str>spellcheck</str>
</arr>
</requestHandler>
- <searchComponent name="suggest" class="solr.SuggestComponent">
- <lst name="suggester">
- <str name="name">mySuggester</str>
- <str name="lookupImpl">FuzzyLookupFactory</str> <!-- org.apache.solr.spelling.suggest.fst -->
- <str name="dictionaryImpl">DocumentDictionaryFactory</str> <!-- org.apache.solr.spelling.suggest.HighFrequencyDictionaryFactory -->
- <str name="field">cat</str>
- <str name="weightField">price</str>
- <str name="suggestAnalyzerFieldType">string</str>
- </lst>
- </searchComponent>
-
- <requestHandler name="/suggest" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <str name="suggest">true</str>
- <str name="suggest.count">10</str>
- </lst>
- <arr name="components">
- <str>suggest</str>
- </arr>
- </requestHandler>
- <!-- Term Vector Component
-
- http://wiki.apache.org/solr/TermVectorComponent
- -->
- <searchComponent name="tvComponent" class="solr.TermVectorComponent"/>
-
- <!-- A request handler for demonstrating the term vector component
-
- This is purely as an example.
-
- In reality you will likely want to add the component to your
- already specified request handlers.
- -->
- <requestHandler name="/tvrh" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <str name="df">text</str>
- <bool name="tv">true</bool>
- </lst>
- <arr name="last-components">
- <str>tvComponent</str>
- </arr>
- </requestHandler>
-
- <!-- Clustering Component
-
- You'll need to set the solr.clustering.enabled system property
- when running solr to run with clustering enabled:
-
- java -Dsolr.clustering.enabled=true -jar start.jar
-
- http://wiki.apache.org/solr/ClusteringComponent
- http://carrot2.github.io/solr-integration-strategies/
- -->
- <searchComponent name="clustering"
- enable="${solr.clustering.enabled:false}"
- class="solr.clustering.ClusteringComponent" >
- <lst name="engine">
- <str name="name">lingo</str>
-
- <!-- Class name of a clustering algorithm compatible with the Carrot2 framework.
-
- Currently available open source algorithms are:
- * org.carrot2.clustering.lingo.LingoClusteringAlgorithm
- * org.carrot2.clustering.stc.STCClusteringAlgorithm
- * org.carrot2.clustering.kmeans.BisectingKMeansClusteringAlgorithm
-
- See http://project.carrot2.org/algorithms.html for more information.
-
- A commercial algorithm Lingo3G (needs to be installed separately) is defined as:
- * com.carrotsearch.lingo3g.Lingo3GClusteringAlgorithm
- -->
- <str name="carrot.algorithm">org.carrot2.clustering.lingo.LingoClusteringAlgorithm</str>
-
- <!-- Override location of the clustering algorithm's resources
- (attribute definitions and lexical resources).
-
- A directory from which to load algorithm-specific stop words,
- stop labels and attribute definition XMLs.
-
- For an overview of Carrot2 lexical resources, see:
- http://download.carrot2.org/head/manual/#chapter.lexical-resources
-
- For an overview of Lingo3G lexical resources, see:
- http://download.carrotsearch.com/lingo3g/manual/#chapter.lexical-resources
- -->
- <str name="carrot.resourcesDir">clustering/carrot2</str>
- </lst>
-
- <!-- An example definition for the STC clustering algorithm. -->
- <lst name="engine">
- <str name="name">stc</str>
- <str name="carrot.algorithm">org.carrot2.clustering.stc.STCClusteringAlgorithm</str>
- </lst>
-
- <!-- An example definition for the bisecting kmeans clustering algorithm. -->
- <lst name="engine">
- <str name="name">kmeans</str>
- <str name="carrot.algorithm">org.carrot2.clustering.kmeans.BisectingKMeansClusteringAlgorithm</str>
- </lst>
- </searchComponent>
-
- <!-- A request handler for demonstrating the clustering component
-
- This is purely as an example.
-
- In reality you will likely want to add the component to your
- already specified request handlers.
- -->
- <requestHandler name="/clustering"
- startup="lazy"
- enable="${solr.clustering.enabled:false}"
- class="solr.SearchHandler">
- <lst name="defaults">
- <bool name="clustering">true</bool>
- <bool name="clustering.results">true</bool>
- <!-- Field name with the logical "title" of a each document (optional) -->
- <str name="carrot.title">name</str>
- <!-- Field name with the logical "URL" of a each document (optional) -->
- <str name="carrot.url">id</str>
- <!-- Field name with the logical "content" of a each document (optional) -->
- <str name="carrot.snippet">features</str>
- <!-- Apply highlighter to the title/ content and use this for clustering. -->
- <bool name="carrot.produceSummary">true</bool>
- <!-- the maximum number of labels per cluster -->
- <!--<int name="carrot.numDescriptions">5</int>-->
- <!-- produce sub clusters -->
- <bool name="carrot.outputSubClusters">false</bool>
-
- <!-- Configure the remaining request handler parameters. -->
- <str name="defType">edismax</str>
- <str name="qf">
- text^0.5 features^1.0 name^1.2 sku^1.5 id^10.0 manu^1.1 cat^1.4
- </str>
- <str name="q.alt">*:*</str>
- <str name="rows">10</str>
- <str name="fl">*,score</str>
- </lst>
- <arr name="last-components">
- <str>clustering</str>
- </arr>
- </requestHandler>
-
<!-- Terms Component
-
http://wiki.apache.org/solr/TermsComponent
-
A component to return terms and document frequency of those
terms
-->
@@ -1471,50 +863,23 @@
<!-- A request handler for demonstrating the terms component -->
<requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
+ <lst name="defaults">
<bool name="terms">true</bool>
<bool name="distrib">false</bool>
- </lst>
+ </lst>
<arr name="components">
<str>terms</str>
</arr>
</requestHandler>
-
- <!-- Query Elevation Component
-
- http://wiki.apache.org/solr/QueryElevationComponent
-
- a search component that enables you to configure the top
- results for a given query regardless of the normal lucene
- scoring.
- -->
- <searchComponent name="elevator" class="solr.QueryElevationComponent" >
- <!-- pick a fieldType to analyze queries -->
- <str name="queryFieldType">string</str>
- <str name="config-file">elevate.xml</str>
- </searchComponent>
-
- <!-- A request handler for demonstrating the elevator component -->
- <requestHandler name="/elevate" class="solr.SearchHandler" startup="lazy">
- <lst name="defaults">
- <str name="echoParams">explicit</str>
- <str name="df">text</str>
- </lst>
- <arr name="last-components">
- <str>elevator</str>
- </arr>
- </requestHandler>
-
<!-- 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"
+ <fragmenter name="gap"
default="true"
class="solr.highlight.GapFragmenter">
<lst name="defaults">
@@ -1522,10 +887,10 @@
</lst>
</fragmenter>
- <!-- A regular-expression-based fragmenter
- (for sentence extraction)
+ <!-- A regular-expression-based fragmenter
+ (for sentence extraction)
-->
- <fragmenter name="regex"
+ <fragmenter name="regex"
class="solr.highlight.RegexFragmenter">
<lst name="defaults">
<!-- slightly smaller fragsizes work better because of slop -->
@@ -1538,7 +903,7 @@
</fragmenter>
<!-- Configure the standard formatter -->
- <formatter name="html"
+ <formatter name="html"
default="true"
class="solr.highlight.HtmlFormatter">
<lst name="defaults">
@@ -1548,27 +913,27 @@
</formatter>
<!-- Configure the standard encoder -->
- <encoder name="html"
+ <encoder name="html"
class="solr.highlight.HtmlEncoder" />
<!-- Configure the standard fragListBuilder -->
- <fragListBuilder name="simple"
+ <fragListBuilder name="simple"
class="solr.highlight.SimpleFragListBuilder"/>
-
+
<!-- Configure the single fragListBuilder -->
- <fragListBuilder name="single"
+ <fragListBuilder name="single"
class="solr.highlight.SingleFragListBuilder"/>
-
+
<!-- Configure the weighted fragListBuilder -->
- <fragListBuilder name="weighted"
+ <fragListBuilder name="weighted"
default="true"
class="solr.highlight.WeightedFragListBuilder"/>
-
+
<!-- default tag FragmentsBuilder -->
- <fragmentsBuilder name="default"
+ <fragmentsBuilder name="default"
default="true"
class="solr.highlight.ScoreOrderFragmentsBuilder">
- <!--
+ <!--
<lst name="defaults">
<str name="hl.multiValuedSeparatorChar">/</str>
</lst>
@@ -1576,7 +941,7 @@
</fragmentsBuilder>
<!-- multi-colored tag FragmentsBuilder -->
- <fragmentsBuilder name="colored"
+ <fragmentsBuilder name="colored"
class="solr.highlight.ScoreOrderFragmentsBuilder">
<lst name="defaults">
<str name="hl.tag.pre"><![CDATA[
@@ -1588,8 +953,8 @@
<str name="hl.tag.post"><![CDATA[</b>]]></str>
</lst>
</fragmentsBuilder>
-
- <boundaryScanner name="default"
+
+ <boundaryScanner name="default"
default="true"
class="solr.highlight.SimpleBoundaryScanner">
<lst name="defaults">
@@ -1597,8 +962,8 @@
<str name="hl.bs.chars">.,!? 	 </str>
</lst>
</boundaryScanner>
-
- <boundaryScanner name="breakIterator"
+
+ <boundaryScanner name="breakIterator"
class="solr.highlight.BreakIteratorBoundaryScanner">
<lst name="defaults">
<!-- type should be one of CHARACTER, WORD(default), LINE and SENTENCE -->
@@ -1613,100 +978,78 @@
</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
+ -->
- -->
-
- <!-- Add unknown fields to the schema
-
- An example field type guessing update processor that will
+ <!-- Add unknown fields to the schema
+ Field type guessing update processors that will
attempt to parse string-typed field values as Booleans, Longs,
Doubles, or Dates, and then add schema fields with the guessed
- field types.
-
- This requires that the schema is both managed and mutable, by
+ field types. Text content will be indexed as "text_general" as
+ well as a copy to a plain string version in *_str.
+ These require that the schema is both managed and mutable, by
declaring schemaFactory as ManagedIndexSchemaFactory, with
- mutable specified as true.
-
+ mutable specified as true.
See http://wiki.apache.org/solr/GuessingFieldTypes
-->
- <updateRequestProcessorChain name="add-unknown-fields-to-the-schema">
- <processor class="solr.DefaultValueUpdateProcessorFactory">
- <str name="fieldName">_ttl_</str>
- <str name="value">+90DAYS</str>
- </processor>
- <processor class="solr.processor.DocExpirationUpdateProcessorFactory">
- <int name="autoDeletePeriodSeconds">86400</int>
- <str name="ttlFieldName">_ttl_</str>
- <str name="expirationFieldName">_expire_at_</str>
- </processor>
- <processor class="solr.FirstFieldValueUpdateProcessorFactory">
- <str name="fieldName">_expire_at_</str>
- </processor>
-
- <processor class="solr.RemoveBlankFieldUpdateProcessorFactory"/>
- <processor class="solr.ParseBooleanFieldUpdateProcessorFactory"/>
- <processor class="solr.ParseLongFieldUpdateProcessorFactory"/>
- <processor class="solr.ParseDoubleFieldUpdateProcessorFactory"/>
- <processor class="solr.ParseDateFieldUpdateProcessorFactory">
- <arr name="format">
- <str>yyyy-MM-dd'T'HH:mm:ss.SSSZ</str>
- <str>yyyy-MM-dd'T'HH:mm:ss,SSSZ</str>
- <str>yyyy-MM-dd'T'HH:mm:ss.SSS</str>
- <str>yyyy-MM-dd'T'HH:mm:ss,SSS</str>
- <str>yyyy-MM-dd'T'HH:mm:ssZ</str>
- <str>yyyy-MM-dd'T'HH:mm:ss</str>
- <str>yyyy-MM-dd'T'HH:mmZ</str>
- <str>yyyy-MM-dd'T'HH:mm</str>
- <str>yyyy-MM-dd HH:mm:ss.SSSZ</str>
- <str>yyyy-MM-dd HH:mm:ss,SSSZ</str>
- <str>yyyy-MM-dd HH:mm:ss.SSS</str>
- <str>yyyy-MM-dd HH:mm:ss,SSS</str>
- <str>yyyy-MM-dd HH:mm:ssZ</str>
- <str>yyyy-MM-dd HH:mm:ss</str>
- <str>yyyy-MM-dd HH:mmZ</str>
- <str>yyyy-MM-dd HH:mm</str>
- <str>yyyy-MM-dd</str>
- </arr>
- </processor>
- <processor class="solr.AddSchemaFieldsUpdateProcessorFactory">
- <str name="defaultFieldType">key_lower_case</str>
- <lst name="typeMapping">
- <str name="valueClass">java.lang.Boolean</str>
- <str name="fieldType">boolean</str>
- </lst>
- <lst name="typeMapping">
- <str name="valueClass">java.util.Date</str>
- <str name="fieldType">tdate</str>
- </lst>
- <lst name="typeMapping">
- <str name="valueClass">java.lang.Long</str>
- <str name="valueClass">java.lang.Integer</str>
- <str name="fieldType">tlong</str>
- </lst>
- <lst name="typeMapping">
- <str name="valueClass">java.lang.Number</str>
- <str name="fieldType">tdouble</str>
- </lst>
- </processor>
+ <updateProcessor class="solr.UUIDUpdateProcessorFactory" name="uuid"/>
+ <updateProcessor class="solr.RemoveBlankFieldUpdateProcessorFactory" name="remove-blank"/>
+ <updateProcessor class="solr.FieldNameMutatingUpdateProcessorFactory" name="field-name-mutating">
+ <str name="pattern">[^\w-\.]</str>
+ <str name="replacement">_</str>
+ </updateProcessor>
+ <updateProcessor class="solr.ParseBooleanFieldUpdateProcessorFactory" name="parse-boolean"/>
+ <updateProcessor class="solr.ParseLongFieldUpdateProcessorFactory" name="parse-long"/>
+ <updateProcessor class="solr.ParseDoubleFieldUpdateProcessorFactory" name="parse-double"/>
+ <updateProcessor class="solr.ParseDateFieldUpdateProcessorFactory" name="parse-date">
+ <arr name="format">
+ <str>yyyy-MM-dd['T'[HH:mm[:ss[.SSS]][z</str>
+ <str>yyyy-MM-dd['T'[HH:mm[:ss[,SSS]][z</str>
+ <str>yyyy-MM-dd HH:mm[:ss[.SSS]][z</str>
+ <str>yyyy-MM-dd HH:mm[:ss[,SSS]][z</str>
+ <str>[EEE, ]dd MMM yyyy HH:mm[:ss] z</str>
+ <str>EEEE, dd-MMM-yy HH:mm:ss z</str>
+ <str>EEE MMM ppd HH:mm:ss [z ]yyyy</str>
+ </arr>
+ </updateProcessor>
+ <updateProcessor class="solr.AddSchemaFieldsUpdateProcessorFactory" name="add-schema-fields">
+ <str name="defaultFieldType">key_lower_case</str>
+ <lst name="typeMapping">
+ <str name="valueClass">java.lang.Boolean</str>
+ <str name="fieldType">boolean</str>
+ </lst>
+ <lst name="typeMapping">
+ <str name="valueClass">java.util.Date</str>
+ <str name="fieldType">tdate</str>
+ </lst>
+ <lst name="typeMapping">
+ <str name="valueClass">java.lang.Long</str>
+ <str name="valueClass">java.lang.Integer</str>
+ <str name="fieldType">tlong</str>
+ </lst>
+ <lst name="typeMapping">
+ <str name="valueClass">java.lang.Number</str>
+ <str name="fieldType">tdouble</str>
+ </lst>
+ </updateProcessor>
+
+ <!-- The update.autoCreateFields property can be turned to false to disable schemaless mode -->
+ <updateRequestProcessorChain name="add-unknown-fields-to-the-schema" default="${update.autoCreateFields:true}"
+ processor="uuid,remove-blank,field-name-mutating,parse-boolean,parse-long,parse-double,parse-date,add-schema-fields">
<processor class="solr.LogUpdateProcessorFactory"/>
+ <processor class="solr.DistributedUpdateProcessorFactory"/>
<processor class="solr.RunUpdateProcessorFactory"/>
</updateRequestProcessorChain>
-
<!-- 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.
-
+ uniqueness based on that anyway.
-->
<!--
<updateRequestProcessorChain name="dedupe">
@@ -1721,55 +1064,12 @@
<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.
-->
@@ -1777,7 +1077,7 @@
overridden...
-->
<!--
- <queryResponseWriter name="xml"
+ <queryResponseWriter name="xml"
default="true"
class="solr.XMLResponseWriter" />
<queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
@@ -1790,32 +1090,15 @@
-->
<queryResponseWriter name="json" class="solr.JSONResponseWriter">
- <!-- For the purposes of the tutorial, JSON responses are written as
- plain text so that they are easy to read in *any* browser.
- If you expect a MIME type of "application/json" just remove this override.
- -->
- <str name="content-type">text/plain; charset=UTF-8</str>
- </queryResponseWriter>
-
- <!--
- Custom response writers can be declared as needed...
- -->
- <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.
+ <!-- For the purposes of the tutorial, JSON responses are written as
+ plain text so that they are easy to read in *any* browser.
+ If you expect a MIME type of "application/json" just remove this override.
-->
- <queryResponseWriter name="xslt" class="solr.XSLTResponseWriter">
- <int name="xsltCacheLifetimeSeconds">5</int>
+ <str name="content-type">text/plain; charset=UTF-8</str>
</queryResponseWriter>
<!-- Query Parsers
-
- http://wiki.apache.org/solr/SolrQuerySyntax
-
+ 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
@@ -1826,19 +1109,17 @@
-->
<!-- 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"
+ <valueSourceParser name="myfunc"
class="com.mycompany.MyValueSourceParser" />
-->
-
-
+
+
<!-- Document Transformers
http://wiki.apache.org/solr/DocTransformers
-->
@@ -1847,26 +1128,16 @@
<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" />
-->
-
-
- <!-- Legacy config for the admin interface -->
- <admin>
- <defaultQuery>*:*</defaultQuery>
- </admin>
-
</config>