Skip to content

Instantly share code, notes, and snippets.

@tschellenbach

tschellenbach/solr_config.xml

Created May 16, 2011 11:13
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save tschellenbach/974251 to your computer and use it in GitHub Desktop.
Save tschellenbach/974251 to your computer and use it in GitHub Desktop.
Download ZIP
solr schema tag search
Raw
solr_config.xml
<?xml version="1.0" encoding="UTF-8" ?>
<config>
<abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>
<luceneMatchVersion>LUCENE_31</luceneMatchVersion>
<lib dir="../../contrib/extraction/lib" />
<lib dir="../../dist/" regex="apache-solr-cell-\d.*\.jar" />
<lib dir="../../dist/" regex="apache-solr-clustering-\d.*\.jar" />
<lib dir="../../dist/" regex="apache-solr-dataimporthandler-\d.*\.jar" />
<lib dir="../../contrib/clustering/lib/" />
<dataDir>${solr.data.dir:}</dataDir>
<directoryFactory name="DirectoryFactory"
class="${solr.directoryFactory:solr.StandardDirectoryFactory}"/>
<indexDefaults>
<useCompoundFile>false</useCompoundFile>
<mergeFactor>2</mergeFactor>
<ramBufferSizeMB>128</ramBufferSizeMB>
<maxFieldLength>10000</maxFieldLength>
<writeLockTimeout>1000</writeLockTimeout>
<commitLockTimeout>10000</commitLockTimeout>
<lockType>native</lockType>
</indexDefaults>
<mainIndex>
<useCompoundFile>false</useCompoundFile>
<ramBufferSizeMB>128</ramBufferSizeMB>
<mergeFactor>2</mergeFactor>
<unlockOnStartup>false</unlockOnStartup>
<reopenReaders>true</reopenReaders>
<deletionPolicy class="solr.SolrDeletionPolicy">
<str name="maxCommitsToKeep">1</str>
<str name="maxOptimizedCommitsToKeep">0</str>
</deletionPolicy>
<infoStream file="INFOSTREAM.txt">false</infoStream>
</mainIndex>
<!-- 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
-->
<!-- <jmx agentId="myAgent" /> -->
<!-- If you want to start a new MBeanServer, specify the serviceUrl -->
<!-- <jmx serviceUrl="service:jmx:rmi:///jndi/rmi://localhost:9999/solr"/>
-->
<!-- The default high-performance update handler -->
<updateHandler class="solr.DirectUpdateHandler2">
<autoCommit>
<maxTime>300</maxTime>
</autoCommit>
<!-- Update Related Event Listeners
Various IndexWriter realted 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>
<query>
<maxBooleanClauses>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 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
faster under other scenarios on multi-cpu systems.
-->
<!-- Filter Cache
Cache used by SolrIndexSearcher for filters (DocSets),
unordered sets of *all* documents that match a query. When a
new searcher is opened, its caches may be prepopulated or
"autowarmed" using data from caches in the old searcher.
autowarmCount is the number of items to prepopulate. For
LRUCache, the autowarmed items will be the most recently
accessed items.
Parameters:
class - the SolrCache implementation LRUCache or
(LRUCache or FastLRUCache)
size - the maximum number of entries in the cache
initialSize - the initial capacity (number of entries) of
the cache. (see java.util.HashMap)
autowarmCount - the number of entries to prepopulate from
and old cache.
-->
<filterCache class="solr.FastLRUCache"
size="262144"
initialSize="65536"
autowarmCount="16384"/>
<!-- 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.
-->
<queryResultCache class="solr.LRUCache"
size="1048576"
initialSize="262144"
autowarmCount="65536"/>
<!-- Document Cache
Caches Lucene Document objects (the stored fields for each
document). Since Lucene internal document ids are transient,
this cache will not be autowarmed.
-->
<documentCache class="solr.LRUCache"
size="65536"
initialSize="32768"
autowarmCount="16384"/>
<!-- 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.
-->
<!--
<fieldValueCache class="solr.FastLRUCache"
size="512"
autowarmCount="128"
showItems="32" />
-->
<!-- 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.
-->
<!--
<cache name="myUserCache"
class="solr.LRUCache"
size="4096"
initialSize="1024"
autowarmCount="1024"
regenerator="com.mycompany.MyRegenerator"
/>
-->
<!-- Lazy Field Loading
If true, stored fields that are not requested will be loaded
lazily. This can result in a significant speed improvement
if the usual case is to not load all stored fields,
especially if the skipped fields are large compressed text
fields.
-->
<enableLazyFieldLoading>true</enableLazyFieldLoading>
<!-- Use Filter For Sorted Query
A possible optimization that attempts to use a filter to
satisfy a search. If the requested sort does not include
score, then the filterCache will be checked for a filter
matching the query. If found, the filter will be used as the
source of document ids, and then the sort will be applied to
that.
For most situations, this will not be useful unless you
frequently get the same search repeatedly with differnet 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>
<listener event="newSearcher" class="solr.QuerySenderListener">
<arr name="queries">
<lst>
<str name="q">*:*</str>
<str name="sort">recent_popularity desc</str>
</lst>
<lst>
<str name="q">*:*</str>
<str name="sort">popularity desc</str>
</lst>
<lst>
<str name="q">*:*</str>
<str name="sort">id desc</str>
</lst>
</arr>
</listener>
<listener event="firstSearcher" class="solr.QuerySenderListener">
<arr name="queries">
<lst>
<str name="q">*:*</str>
<str name="sort">recent_popularity desc</str>
</lst>
<lst>
<str name="q">*:*</str>
<str name="sort">popularity desc</str>
</lst>
<lst>
<str name="q">*:*</str>
<str name="sort">id desc</str>
</lst>
</arr>
</listener>
<useColdSearcher>true</useColdSearcher>
<maxWarmingSearchers>5</maxWarmingSearchers>
</query>
<requestDispatcher handleSelect="true" >
<requestParsers enableRemoteStreaming="true"
multipartUploadLimitInKB="2048000" />
<httpCaching never304="true" />
</requestDispatcher>
<requestHandler name="/dataimport" class="org.apache.solr.handler.dataimport.DataImportHandler">
<lst name="defaults">
<str name="config">data_config.xml</str>
</lst>
</requestHandler>
<requestHandler name="/dataimport_local" class="org.apache.solr.handler.dataimport.DataImportHandler">
<lst name="defaults">
<str name="config">data_config_local.xml</str>
</lst>
</requestHandler>
<requestHandler name="search" class="solr.SearchHandler" default="true">
<lst name="defaults">
<str name="echoParams">explicit</str>
<int name="rows">10</int>
</lst>
<arr name="components">
<str>query</str>
<str>facet</str>
<str>stats</str>
<str>debug</str>
</arr>
</requestHandler>
<requestHandler name="/update"
class="solr.XmlUpdateRequestHandler">
<!-- See below for information on defining
updateRequestProcessorChains that can be used by name
on each Update Request
-->
<!--
<lst name="defaults">
<str name="update.processor">dedupe</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 docuemnts. 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 assoicate
ananalysis breakdown to the analyzed document.
Like the FieldAnalysisRequestHandler, this handler also supports
query analysis by sending either an "analysis.query" or "q"
request paraemter that holds the query text to be analyized. 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" />
<!-- Admin Handlers
Admin Handlers - This will register all the standard admin
RequestHandlers.
-->
<requestHandler name="/admin/"
class="solr.admin.AdminHandlers" />
<!-- This single handler is equivilent 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:
-->
<!--
<requestHandler name="/admin/file"
class="solr.admin.ShowFileRequestHandler" >
<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="defaults">
<str name="qt">search</str>
<str name="q">solrpingquery</str>
<str name="echoParams">all</str>
</lst>
</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 "salves" used for queries.
http://wiki.apache.org/solr/SolrReplication
In the example below, remove the <lst name="master"> section if
this is just a slave and remove the <lst name="slave"> section
if this is just a master.
-->
<!--
<requestHandler name="/replication" class="solr.ReplicationHandler" >
<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://localhost:8983/solr/replication</str>
<str name="pollInterval">00:00:60</str>
</lst>
</requestHandler>
-->
<!-- 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 avaliable:
<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"
-->
<!-- Terms Component
http://wiki.apache.org/solr/TermsComponent
A component to return terms and document frequency of those
terms
-->
<searchComponent name="terms" class="solr.TermsComponent"/>
<!-- A request handler for demonstrating the terms component -->
<requestHandler name="/terms" class="solr.SearchHandler" startup="lazy">
<lst name="defaults">
<bool name="terms">true</bool>
</lst>
<arr name="components">
<str>terms</str>
</arr>
</requestHandler>
<!-- 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>
-->
<!-- 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="velocity" class="solr.VelocityResponseWriter"/>
<queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
-->
<!--
Custom response writers can be declared as needed...
-->
<!--
<queryResponseWriter name="custom" class="com.example.MyResponseWriter"/>
-->
<!-- 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
http://wiki.apache.org/solr/SolrQuerySyntax
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" />
-->
<admin>
<defaultQuery>*:*</defaultQuery>
</admin>
</config>
Raw
solr_schema.xml
<?xml version="1.0" encoding="UTF-8" ?>
<schema name="fashiolista_tags" version="0.1">
<types>
<fieldType name="sint" class="solr.SortableIntField" sortMissingLast="true" omitNorms="true" multiValued="false" />
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true" multiValued="false"/>
</types>
<fields>
<field name="id" type="sint" indexed="true" stored="true" required="true" />
<field name="tag" type="string" indexed="true" stored="true" multiValued="true"/>
<field name="popularity" type="sint" indexed="true" stored="true" required="true" />
<field name="recent_popularity" type="sint" indexed="true" stored="true" required="true" />
</fields>
<uniqueKey>id</uniqueKey>
<defaultSearchField>tag</defaultSearchField>
<solrQueryParser defaultOperator="AND"/>
</schema>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment