mirror of https://github.com/apache/lucene.git
250 lines
9.8 KiB
XML
Executable File
250 lines
9.8 KiB
XML
Executable File
<?xml version="1.0" ?>
|
|
|
|
<config>
|
|
|
|
<!-- 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</dataDir>
|
|
-->
|
|
|
|
<indexDefaults>
|
|
<!-- Values here affect all index writers and act as a default unless overridden. -->
|
|
<useCompoundFile>false</useCompoundFile>
|
|
<mergeFactor>10</mergeFactor>
|
|
<maxBufferedDocs>1000</maxBufferedDocs>
|
|
<maxMergeDocs>2147483647</maxMergeDocs>
|
|
<maxFieldLength>10000</maxFieldLength>
|
|
<writeLockTimeout>1000</writeLockTimeout>
|
|
<commitLockTimeout>10000</commitLockTimeout>
|
|
</indexDefaults>
|
|
|
|
<mainIndex>
|
|
<!-- options specific to the main on-disk lucene index -->
|
|
<useCompoundFile>false</useCompoundFile>
|
|
<mergeFactor>10</mergeFactor>
|
|
<maxBufferedDocs>1000</maxBufferedDocs>
|
|
<maxMergeDocs>2147483647</maxMergeDocs>
|
|
<maxFieldLength>10000</maxFieldLength>
|
|
|
|
<!-- 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. -->
|
|
<unlockOnStartup>false</unlockOnStartup>
|
|
</mainIndex>
|
|
|
|
<!-- the default high-performance update handler -->
|
|
<updateHandler class="solr.DirectUpdateHandler2">
|
|
|
|
<!-- The RunExecutableListener executes an external command.
|
|
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=nothing
|
|
env - environment variables to set. default=nothing
|
|
-->
|
|
<!-- A postCommit event is fired after every commit or optimize command
|
|
<listener event="postCommit" class="solr.RunExecutableListener">
|
|
<str name="exe">snapshooter</str>
|
|
<str name="dir">solr/bin</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>
|
|
-->
|
|
<!-- A postOptimize event is fired only after every optimize command, useful
|
|
in conjunction with index distribution to only distribute optimized indicies
|
|
<listener event="postOptimize" class="solr.RunExecutableListener">
|
|
<str name="exe">snapshooter</str>
|
|
<str name="dir">solr/bin</str>
|
|
<bool name="wait">true</bool>
|
|
</listener>
|
|
-->
|
|
|
|
</updateHandler>
|
|
|
|
|
|
<query>
|
|
<!-- Maximum number of clauses in a boolean query... can affect
|
|
range or prefix queries that expand to big boolean
|
|
queries. An exception is thrown if exceeded. -->
|
|
<maxBooleanClauses>1024</maxBooleanClauses>
|
|
|
|
|
|
<!-- Cache used by SolrIndexSearcher for filters (DocSets),
|
|
unordered sets of *all* documents that match a query.
|
|
When a new searcher is opened, its caches may be prepopulated
|
|
or "autowarmed" using data from caches in the old searcher.
|
|
autowarmCount is the number of items to prepopulate. For LRUCache,
|
|
the autowarmed items will be the most recently accessed items. -->
|
|
<filterCache
|
|
class="solr.LRUCache"
|
|
size="512"
|
|
initialSize="512"
|
|
autowarmCount="256"/>
|
|
|
|
<!-- queryResultCache caches results of searches - ordered lists of
|
|
document ids (DocList) based on a query, a sort, and the range
|
|
of documents requested. -->
|
|
<queryResultCache
|
|
class="solr.LRUCache"
|
|
size="512"
|
|
initialSize="512"
|
|
autowarmCount="256"/>
|
|
|
|
<!-- documentCache caches Lucene Document objects (the stored fields for each document).
|
|
Since Lucene internal document ids are transient, this cache will not be autowarmed. -->
|
|
<documentCache
|
|
class="solr.LRUCache"
|
|
size="512"
|
|
initialSize="512"
|
|
autowarmCount="0"/>
|
|
|
|
<!-- 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.search.CacheRegenerator if autowarming is desired. -->
|
|
<!--
|
|
<cache name="myUserCache"
|
|
class="solr.LRUCache"
|
|
size="4096"
|
|
initialSize="1024"
|
|
autowarmCount="1024"
|
|
regenerator="org.mycompany.mypackage.MyRegenerator"
|
|
/>
|
|
-->
|
|
|
|
<!-- An 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. -->
|
|
<useFilterForSortedQuery>true</useFilterForSortedQuery>
|
|
|
|
<!-- 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 50 will be collected and cached. Any further
|
|
requests in that range can be satisfied via the cache. -->
|
|
<queryResultWindowSize>10</queryResultWindowSize>
|
|
|
|
<!-- This entry enables an int hash representation for filters (DocSets)
|
|
when the number of items in the set is less than maxSize. For smaller
|
|
sets, this representation is more memory efficient, more efficient to
|
|
iterate over, and faster to take intersections. -->
|
|
<HashDocSet maxSize="3000" loadFactor="0.75"/>
|
|
|
|
|
|
<!-- boolToFilterOptimizer converts boolean clauses with zero boost
|
|
into cached filters if the number of docs selected by the clause exceeds
|
|
the threshold (represented as a fraction of the total index) -->
|
|
<boolTofilterOptimizer enabled="true" cacheSize="32" threshold=".05"/>
|
|
|
|
|
|
<!-- a newSearcher event is fired whenever a new searcher is being prepared
|
|
and there is a current searcher handling requests (aka registered). -->
|
|
<!-- 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="start">0</str> <str name="rows">10</str> </lst>
|
|
<lst> <str name="q">rocks</str> <str name="start">0</str> <str name="rows">10</str> </lst>
|
|
</arr>
|
|
</listener>
|
|
-->
|
|
|
|
<!-- a firstSearcher event is fired whenever a new searcher is being
|
|
prepared but there is no current registered searcher to handle
|
|
requests or to gain autowarming data from. -->
|
|
<!--
|
|
<listener event="firstSearcher" class="solr.QuerySenderListener">
|
|
<arr name="queries">
|
|
<lst> <str name="q">fast_warm</str> <str name="start">0</str> <str name="rows">10</str> </lst>
|
|
</arr>
|
|
</listener>
|
|
-->
|
|
|
|
</query>
|
|
|
|
|
|
<!-- requestHandler plugins... incoming queries will be dispatched to the
|
|
correct handler based on the qt (query type) param matching the
|
|
name of registered handlers.
|
|
The "standard" request handler is the default and will be used if qt
|
|
is not specified in the request.
|
|
-->
|
|
<requestHandler name="standard" class="solr.StandardRequestHandler" />
|
|
|
|
<!-- DisMaxRequestHandler is an example of a request handler that
|
|
supports optional parameters which are passed to
|
|
its init() method.
|
|
-->
|
|
<requestHandler name="dismax" class="solr.DisMaxRequestHandler" >
|
|
<float name="tie">0.01</float>
|
|
<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="pf">
|
|
text^0.2 features^1.1 name^1.5 manu^1.4 manu_exact^1.9
|
|
</str>
|
|
<str name="bf">
|
|
ord(poplarity)^0.5 recip(rord(price),1,1000,1000)^0.3
|
|
</str>
|
|
<str name="fl">
|
|
id,name,price,score
|
|
</str>
|
|
<str name="mm">
|
|
2<-1 5<-2 6<90%
|
|
</str>
|
|
<int name="ps">100</int>
|
|
</requestHandler>
|
|
<!-- Note how you can register the same handler multiple times with
|
|
different names (and different init parameters)
|
|
-->
|
|
<requestHandler name="instock" class="solr.DisMaxRequestHandler" >
|
|
<str name="fq">
|
|
inStock:true
|
|
</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="mm">
|
|
2<-1 5<-2 6<90%
|
|
</str>
|
|
</requestHandler>
|
|
|
|
<!-- queryResponseWriter plugins... query responses will be written using the
|
|
writer specified by the 'wt' request parameter matching the name of a registered
|
|
writer.
|
|
The "standard" writer is the default and will be used if 'wt' is not specified
|
|
in the request. XMLResponseWriter will be used if nothing is specified here.
|
|
The json, python, and ruby writers are also available by default.
|
|
|
|
<queryResponseWriter name="standard" class="org.apache.solr.request.XMLResponseWriter"/>
|
|
<queryResponseWriter name="json" class="org.apache.solr.request.JSONResponseWriter"/>
|
|
<queryResponseWriter name="python" class="org.apache.solr.request.PythonResponseWriter"/>
|
|
<queryResponseWriter name="ruby" class="org.apache.solr.request.RubyResponseWriter"/>
|
|
|
|
<queryResponseWriter name="custom" class="com.example.MyResponseWriter"/>
|
|
-->
|
|
|
|
|
|
|
|
<!-- config for the admin interface -->
|
|
<admin>
|
|
<defaultQuery>solr</defaultQuery>
|
|
<gettableFiles>solrconfig.xml schema.xml admin-extra.html</gettableFiles>
|
|
<pingQuery>q=id:0&start=0&rows=0</pingQuery>
|
|
|
|
<!-- configure a healthcheck file for servers behind a loadbalancer
|
|
<healthcheck type="file">server-enabled</healthcheck>
|
|
-->
|
|
</admin>
|
|
|
|
</config>
|