solr配置，
<dataConfig>
<!-- Create a dynamic attribute specific transformer -->
<script><![CDATA[
/*
* Note: all objects must be checked for null!!! As even the "What id"
* queries seem to be sent through this method, there will be calls to
* this with all fields other than "id" containting "null".
*/
function createPremiumProfile(row) {
return row;
}
function categoryTransformer(row) {
//if this is called we know we got a record
//so mark this as true
var category = row.get('category');
if (category == null) {
row.put('enabled', false);
} else {
row.put('enabled', true);
}
return row;
}
function userTransformer(row) {
var platformId = row.get('platform_id');
if (platformId == 14) {
row.put('platform_enabled', false);
} else {
row.put('platform_enabled', true);
}
return row;
}
]]></script>
<document name="profiles">
<!-- x
Query logic ():
1. Import all active objects (full import, "query")
2. Later only do updates:
2.1 Update the index: deltaQuery (to get the ids for changed ads) and deltaImportQuery
2.2 Remove those posts which have changed its state due to the delta import: postImportDeleteQuery + deletedPkQuery
-->
<entity name="premium_user_profile" pk="id" dataSource="datasource"
transformer="script:createPremiumProfile"
query="select * from premium_user_profile"
deltaQuery="select id from premium_user_profile where LAST_MODIFIED_ON > date_sub('${dataimporter.last_index_time}', INTERVAL 90 SECOND)"
deltaImportQuery="select * from premium_user_profile where id ='${dataimporter.delta.id}'"
preImportDeleteQuery="(*:* NOT platform_enabled:true) OR (*:* NOT enabled:true)"
postImportDeleteQuery="(*:* NOT platform_enabled:true) OR (*:* NOT enabled:true)"
>
<field column="id" name="id" />
<field column="LAST_MODIFIED_ON" name="modified_on" />
<entity name ="premium_user_category"
dataSource="datasource"
transformer="script:categoryTransformer"
query="select category from premium_user_category where user_id='${premium_user_profile.user_id}'">
</entity>
<entity name ="user"
dataSource="datasource"
transformer="script:userTransformer"
query="select platform_id from user where id='${premium_user_profile.user_id}'">
</entity>
</entity>
</document>
</dataConfig>schema.xml
<?xml version="1.0" encoding="UTF-8" ?>
<schema name="kijijiit_public_premium_user" version="1.5">
<types>
<!-- field type definitions. The "name" attribute is
just a label to be used by field definitions. The "class"
attribute and any other attributes determine the real
behavior of the fieldType.
Class names starting with "solr" refer to java classes in the
org.apache.solr.analysis package.
-->
<!-- The StrField type is not analyzed, but indexed/stored verbatim.
- StrField and TextField support an optional compressThreshold which
limits compression (if enabled in the derived fields) to values which
exceed a certain size (in characters).
-->
<fieldType name="string" class="solr.StrField" sortMissingLast="true" omitNorms="true"/>
<!-- boolean type: "true" or "false" -->
<fieldType name="boolean" class="solr.BoolField" sortMissingLast="true" omitNorms="true"/>
<!--Binary data type. The data should be sent/retrieved in as Base64 encoded Strings -->
<fieldtype name="binary" class="solr.BinaryField"/>
<!-- The optional sortMissingLast and sortMissingFirst attributes are
currently supported on types that are sorted internally as strings.
This includes "string","boolean","sint","slong","sfloat","sdouble","pdate"
- If sortMissingLast="true", then a sort on this field will cause documents
without the field to come after documents with the field,
regardless of the requested sort order (asc or desc).
- If sortMissingFirst="true", then a sort on this field will cause documents
without the field to come before documents with the field,
regardless of the requested sort order.
- If sortMissingLast="false" and sortMissingFirst="false" (the default),
then default lucene sorting will be used which places docs without the
field first in an ascending sort and last in a descending sort.
-->
<!--
Default numeric field types. For faster range queries, consider the tint/tfloat/tlong/tdouble types.
-->
<fieldType name="int" class="solr.TrieIntField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="float" class="solr.TrieFloatField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="long" class="solr.TrieLongField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="double" class="solr.TrieDoubleField" precisionStep="0" omitNorms="true" positionIncrementGap="0"/>
<!--
Numeric field types that index each value at various levels of precision
to accelerate range queries when the number of values between the range
endpoints is large. See the javadoc for NumericRangeQuery for internal
implementation details.
Smaller precisionStep values (specified in bits) will lead to more tokens
indexed per value, slightly larger index size, and faster range queries.
A precisionStep of 0 disables indexing at different precision levels.
-->
<fieldType name="tint" class="solr.TrieIntField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="tfloat" class="solr.TrieFloatField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="tlong" class="solr.TrieLongField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
<fieldType name="tdouble" class="solr.TrieDoubleField" precisionStep="8" omitNorms="true" positionIncrementGap="0"/>
<!-- The format for this date field is of the form 1995-12-31T23:59:59Z, and
is a more restricted form of the canonical representation of dateTime
http://www.w3.org/TR/xmlschema-2/#dateTime
The trailing "Z" designates UTC time and is mandatory.
Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
All other components are mandatory.
Expressions can also be used to denote calculations that should be
performed relative to "NOW" to determine the value, ie...
NOW/HOUR
... Round to the start of the current hour
NOW-1DAY
... Exactly 1 day prior to now
NOW/DAY+6MONTHS+3DAYS
... 6 months and 3 days in the future from the start of
the current day
Consult the DateField javadocs for more information.
Note: For faster range queries, consider the tdate type
-->
<fieldType name="date" class="solr.TrieDateField" omitNorms="true" precisionStep="0" positionIncrementGap="0"/>
<!-- A Trie based date field for faster date range queries and date faceting. -->
<fieldType name="tdate" class="solr.TrieDateField" omitNorms="true" precisionStep="6" positionIncrementGap="0"/>
<!-- A text field for italian language -->
<fieldType name="text_italian" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<!--tokenizer class="solr.HTMLStripWhitespaceTokenizerFactory"/ --><!-- Remove HTML/XML and tokenize on whitespace -->
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<charFilter class="solr.HTMLStripCharFilterFactory"/>
<filter class="solr.TrimFilterFactory"/>
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true" enablePositionIncrements="true"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
<filter class="solr.WordDelimiterFilterFactory" catenateWords="1"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ItalianLightStemFilterFactory" />
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
<filter class="solr.ASCIIFoldingFilterFactory"/> <!-- filters diacritics -->
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.TrimFilterFactory"/>
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true" enablePositionIncrements="true"/>
<filter class="solr.WordDelimiterFilterFactory" />
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ItalianLightStemFilterFactory" />
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
<filter class="solr.ASCIIFoldingFilterFactory"/> <!-- filters diacritics -->
</analyzer>
</fieldType>
<!-- Field type for suggestions. this one should not be stemmed!!!! -->
<fieldType name="text_suggestions" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.PatternTokenizerFactory" pattern="[\p{Punct}\p{Space}]+" />
<filter class="solr.TrimFilterFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory" words="stopwords.txt" ignoreCase="true" enablePositionIncrements="true"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.PatternTokenizerFactory" pattern="[\p{Punct}\p{Space}]+" />
<filter class="solr.TrimFilterFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<!-- lowercases the entire field value, keeping it as a single token. -->
<!--
<fieldType name="lowercase" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory" />
</analyzer>
</fieldType>
-->
<!-- // -->
<!-- some handy shorcut types ! -->
<!-- // -->
<fieldType name="random" class="solr.RandomSortField" indexed="true" />
<!-- since fields of this type are by default not stored or indexed, any data added to them will be ignored outright. -->
<fieldtype name="ignored" stored="false" indexed="false" multiValued="false" class="solr.StrField" />
<fieldtype name="string_indexed_and_stored" stored="true" indexed="true" class="solr.StrField"/>
<!-- unindexed string that is just stored -->
<fieldtype name="string_stored_only" stored="true" indexed="false" class="solr.StrField"/>
<!-- e.g. location_path like "0,117,5111" - TODO: does that needs to be stored ??? -->
<fieldtype name="text_comma_seperated" stored="true" indexed="true" class="solr.TextField">
<analyzer>
<tokenizer class="solr.PatternTokenizerFactory" pattern="\s*,\s*"/>
</analyzer>
</fieldtype>
</types>
<fields>
<!-- Fields comes from premium_user_reply -->
<field name="id" type="long" indexed="true" stored="true" required="true" multiValued="false"/>
<field name="user_id" type="long" indexed="true" stored="true" required="true" multiValued="false"/>
<field name="business_name" type="string" indexed="false" stored="true" required="false" multiValued="false"/>
<field name="business_description" type="string" indexed="false" stored="true" required="false" multiValued="false"/>
<field name="phone_number" type="string" indexed="false" stored="true" required="false" multiValued="false"/>
<field name="url" type="string" indexed="false" stored="true" required="false" multiValued="false"/>
<field name="area_id" type="long" indexed="false" stored="true" required="true" multiValued="false"/>
<field name="address" type="string" indexed="false" stored="true" required="false" multiValued="false"/>
<field name="hourly_rate" type="long" indexed="false" stored="true" required="false" multiValued="false"/>
<field name="lat" type="float" indexed="false" stored="true" required="false" multiValued="false"/>
<field name="lng" type="float" indexed="false" stored="true" required="false" multiValued="false"/>
<field name="img_hash" type="string" indexed="false" stored="true" required="false" multiValued="false"/>
<field name="status" type="int" indexed="false" stored="true" required="true" multiValued="false"/>
<field name="creation_date" type="tdate" indexed="true" stored="true" required="true" multiValued="false"/>
<field name="modified_on" type="tdate" indexed="true" stored="true" required="true" multiValued="false"/>
<field name="category" type="long" indexed="true" stored="true" required="false" multiValued="true"/>
<field name="platform_id" type="long" indexed="true" stored="true" required="false" multiValued="true"/>
<field name="enabled" required="false" type="boolean" indexed="true" stored="true" multiValued="false" />
<field name="platform_enabled" required="false" type="boolean" indexed="true" stored="true" multiValued="false" />
<field name="last_post_activated" type="tdate" indexed="true" stored="true" required="true" multiValued="false"/>
<field name="txt" required="false" type="text_italian" indexed="true" stored="false" multiValued="true" />
<!-- Here, default is used to create a "timestamp" field indicating when each document was indexed. -->
<field name="timestamp" type="date" indexed="true" stored="true" default="NOW" multiValued="false"/>
</fields>
<!-- Field to use to determine and enforce document uniqueness.
Unless this field is marked with required="false", it will be a required field
-->
<uniqueKey>id</uniqueKey>
<!-- field for the QueryParser to use when an explicit fieldname is absent -->
<defaultSearchField>txt</defaultSearchField>
<!-- SolrQueryParser configuration: defaultOperator="AND|OR" -->
<solrQueryParser defaultOperator="AND"/>
<copyField source="business_name" dest="txt"/>
<copyField source="business_description" dest="txt"/>
</schema>
solrconfig.xml
<?xml version="1.0" encoding="UTF-8" ?>
<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.
-->
<!-- Set this to 'false' if you want solr to continue working after
it has encountered an severe configuration error. In a
production environment, you may want solr to keep working even
if one handler is mis-configured.
You may also set this to false using by setting the system
property:
-Dsolr.abortOnConfigurationError=false
-->
<abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>
<!-- Controls what version of Lucene various components of Solr
adhere to. Generally, you want to use the latest version to
get all bug fixes and improvements. It is highly recommended
that you fully re-index after changing this setting as it can
affect both how text is indexed and queried.
-->
<luceneMatchVersion>4.10</luceneMatchVersion>
<dataDir>${solr.core.dataDir}</dataDir>
<!-- The DirectoryFactory to use for indexes.
solr.StandardDirectoryFactory, the default, is filesystem
based and tries to pick the best implementation for the current
JVM and platform. 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.
-->
<directoryFactory name="DirectoryFactory"
class="${solr.directoryFactory:solr.StandardDirectoryFactory}"/>
<!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
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: As of Solr 3.6, the <indexDefaults> and <mainIndex> sections
are deprecated and not shown in the example config. They will
still work, but will go away for good in 4.0
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -->
<indexConfig>
<!-- maxFieldLength specifies max number of *tokens* indexed per field. Default: 10000 -->
<!-- <maxFieldLength>10000</maxFieldLength> -->
<!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
<!-- <writeLockTimeout>1000</writeLockTimeout> -->
<!-- Expert: Enabling compound file will use less files for the index,
using fewer file descriptors on the expense of performance decrease.
Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
<useCompoundFile>false</useCompoundFile>
<!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
indexing for buffering added documents and deletions before they are
flushed to the Directory.
maxBufferedDocs sets a limit on the number of documents buffered
before flushing.
If both ramBufferSizeMB and maxBufferedDocs is set, then
Lucene will flush based on whichever limit is hit first. -->
<ramBufferSizeMB>64</ramBufferSizeMB>
<!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
<!-- Expert: Merge Policy
The Merge Policy in Lucene controls how merging of segments is done.
The default since Solr/Lucene 3.3 is TieredMergePolicy.
The default since Lucene 2.3 was the LogByteSizeMergePolicy,
Even older versions of Lucene used LogDocMergePolicy.
-->
<!--
<mergePolicy class="org.apache.lucene.index.TieredMergePolicy">
<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>
-->
<!-- Expert: Merge Scheduler
The Merge Scheduler in Lucene controls how merges are
performed. The ConcurrentMergeScheduler (Lucene 2.3 default)
can perform merges in the background using separate threads.
The SerialMergeScheduler (Lucene 2.2 default) does not.
-->
<!--
<mergeScheduler class="org.apache.lucene.index.ConcurrentMergeScheduler"/>
-->
<!-- LockFactory
This option specifies which Lucene LockFactory implementation
to use.
single = SingleInstanceLockFactory - suggested for a
read-only index or when there is no possibility of
another process trying to modify the index.
native = NativeFSLockFactory - uses OS native file locking.
Do not use when multiple solr webapps in the same
JVM are attempting to share a single index.
simple = SimpleFSLockFactory - uses a plain file for locking
Defaults: 'native' is default for Solr3.6 and later, otherwise
'simple' is the default
More details on the nuances of each LockFactory...
http://wiki.apache.org/lucene-java/AvailableLockFactories
-->
<!-- <lockType>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 'none' or 'single'
-->
<!--
<unlockOnStartup>false</unlockOnStartup>
-->
<!-- Expert: Controls how often Lucene loads terms into memory
Default is 128 and is likely good for most everyone.
-->
<!-- <termIndexInterval>128</termIndexInterval> -->
<!-- If true, IndexReaders will be reopened (often more efficient)
instead of closed and then opened. Default: true
-->
<!--
<reopenReaders>true</reopenReaders>
-->
<!-- Commit Deletion Policy
Custom deletion policies can be specified here. The class must
implement org.apache.lucene.index.IndexDeletionPolicy.
http://lucene.apache.org/java/3_5_0/api/core/org/apache/lucene/index/IndexDeletionPolicy.html
The default Solr IndexDeletionPolicy implementation supports
deleting index commit points on number of commits, age of
commit point and optimized status.
The latest commit point should always be preserved regardless
of the criteria.
-->
<!--
<deletionPolicy class="solr.SolrDeletionPolicy">
-->
<!-- The number of commit points to be kept -->
<!-- <str name="maxCommitsToKeep">1</str> -->
<!-- The number of optimized commit points to be kept -->
<!-- <str name="maxOptimizedCommitsToKeep">0</str> -->
<!--
Delete all commit points once they have reached the given age.
Supports DateMathParser syntax e.g.
-->
<!--
<str name="maxCommitAge">30MINUTES</str>
<str name="maxCommitAge">1DAY</str>
-->
<!--
</deletionPolicy>
-->
<!-- Lucene Infostream
To aid in advanced debugging, Lucene provides an "InfoStream"
of detailed information when indexing.
Setting The value to true will instruct the underlying Lucene
IndexWriter to write its debugging info the specified file
-->
<!-- <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
-->
<!-- <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
Perform a <commit/> automatically under certain conditions.
Instead of enabling autoCommit, consider using "commitWithin"
when adding documents.
http://wiki.apache.org/solr/UpdateXmlMessages
maxDocs - Maximum number of documents to add since the last
commit before automatically triggering a new commit.
maxTime - Maximum amount of time that is allowed to pass
since a document was added before automaticly
triggering a new commit.
-->
<!--
<autoCommit>
<maxDocs>10000</maxDocs>
<maxTime>1000</maxTime>
</autoCommit>
-->
<!-- Update Related Event Listeners
Various IndexWriter related events can trigger Listeners to
take actions.
postCommit - fired after every commit or optimize command
postOptimize - fired after every optimize command
-->
<!-- The RunExecutableListener executes an external command from a
hook such as postCommit or postOptimize.
exe - the name of the executable to run
dir - dir to use as the current working directory. (default=".")
wait - the calling thread waits until the executable returns.
(default="true")
args - the arguments to pass to the program. (default is none)
env - environment variables to set. (default is none)
-->
<!-- This example shows how RunExecutableListener could be used
with the script based replication...
http://wiki.apache.org/solr/CollectionDistribution
-->
<!--
<listener event="postCommit" class="solr.RunExecutableListener">
<str name="exe">solr/bin/snapshooter</str>
<str name="dir">.</str>
<bool name="wait">true</bool>
<arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
<arr name="env"> <str>MYVAR=val1</str> </arr>
</listener>
-->
</updateHandler>
<!-- IndexReaderFactory
Use the following format to specify a custom IndexReaderFactory,
which allows for alternate IndexReader implementations.
** Experimental Feature **
Please note - Using a custom IndexReaderFactory may prevent
certain other features from working. The API to
IndexReaderFactory may change without warning or may even be
removed from future releases if the problems cannot be
resolved.
** Features that may not work with custom IndexReaderFactory **
The ReplicationHandler assumes a disk-resident index. Using a
custom IndexReader implementation may cause incompatibility
with ReplicationHandler and may cause replication to not work
correctly. See SOLR-1366 for details.
-->
<!--
<indexReaderFactory name="IndexReaderFactory" class="package.class">
<str name="someArg">Some Value</str>
</indexReaderFactory >
-->
<!-- By explicitly declaring the Factory, the termIndexDivisor can
be specified.
-->
<!--
<indexReaderFactory name="IndexReaderFactory"
class="solr.StandardIndexReaderFactory">
<int name="setTermIndexDivisor">12</int>
</indexReaderFactory >
-->
<!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
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 **
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.
-->
<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="5000"
initialSize="4000"
autowarmCount="2000"/>
<!-- 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="4096"
initialSize="2048"
autowarmCount="2048"/>
<!-- 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="20000"
initialSize="10000"
autowarmCount="0"/>
<!-- 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="5"
autowarmCount="0"
showItems="1" />
<!-- 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 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>50</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.
newSearcher - fired whenever a new searcher is being prepared
and there is a current searcher handling requests (aka
registered). It can be used to prime certain caches to
prevent long request times for certain requests.
firstSearcher - fired whenever a new searcher is being
prepared but there is no current registered searcher to handle
requests or to gain autowarming data from.
-->
<!-- QuerySenderListener takes an array of NamedList and executes a
local query request for each NamedList in sequence.
-->
<listener event="newSearcher" class="solr.QuerySenderListener">
<arr name="queries">
<!--
<lst><str name="q">solr</str><str name="sort">price asc</str></lst>
<lst><str name="q">rocks</str><str name="sort">weight asc</str></lst>
-->
</arr>
</listener>
<listener event="firstSearcher" class="solr.QuerySenderListener">
<arr name="queries">
<!--
<lst>
<str name="q">static firstSearcher warming in solrconfig.xml</str>
</lst>
-->
</arr>
</listener>
<!-- Use Cold Searcher
If a search request comes in and there is no current
registered searcher, then immediately register the still
warming searcher and use it. If "false" then all requests
will block until the first searcher is done warming.
-->
<useColdSearcher>false</useColdSearcher>
<!-- 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.
-->
<maxWarmingSearchers>2</maxWarmingSearchers>
</query>
<!-- Request Dispatcher
This section contains instructions for how the SolrDispatchFilter
should behave when processing requests for this SolrCore.
If you wish to regain use of /select?qt=... style request handler
dispatching, then first add handleSelect="true" to
<requestDispatcher>. Then change the name of the request handler
named "/select" to something else without a leading "/", such as
simply "select" and add default="true" to it.
-->
<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.
SearchRequestHandler won't fetch it, but some others do.
multipartUploadLimitInKB - specifies the max size of
Multipart File Uploads that Solr will allow in a Request.
*** 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"
multipartUploadLimitInKB="2048000" />
<!-- HTTP Caching
Set HTTP caching related parameters (for proxy caches and clients).
The options below instruct Solr not to output any HTTP Caching
related headers
<httpCaching never304="true" /> -->
<!-- If you include a <cacheControl> directive, it will be used to
generate a Cache-Control header (as well as an Expires header
if the value contains "max-age=")
By default, no Cache-Control header is generated.
You can use the <cacheControl> option even if you have set
never304="true"
-->
<!--
<httpCaching never304="true" >
<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>
</httpCaching>
</requestDispatcher>
<!-- Request Handlers
http://wiki.apache.org/solr/SolrRequestHandler
Incoming queries will be dispatched to the correct handler
based on the matching request path piece.
If a Request Handler is declared with startup="lazy", then it will
not be initialized until the first request that uses it.
-->
<!-- 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
queries across multiple shards
-->
<requestHandler name="/select" class="solr.SearchHandler">
<!-- 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">txt</str>
<str name="q.op">OR</str>
<str name="defType">edismax</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").
-->
<!-- In this example, the param "fq=instock:true" would be appended to
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.
-->
<!--
<lst name="appends">
<str name="fq">inStock:true</str>
</lst>
-->
<!-- "invariants" are a way of letting the Solr maintainer lock down
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.
-->
<!--
<lst name="invariants">
<str name="facet.field">cat</str>
<str name="facet.field">manu_exact</str>
<str name="facet.query">price:[* TO 500]</str>
<str name="facet.query">price:[500 TO *]</str>
</lst>
-->
<!-- If the default list of SearchComponents is not desired, that
list can either be overridden completely, or components can be
prepended or appended to the default list. (see below)
-->
<!--
<arr name="components">
<str>nameOfCustomComponent1</str>
<str>nameOfCustomComponent2</str>
</arr>
-->
</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 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" />
<!-- Admin Handlers
Admin Handlers - This will register all the standard admin
RequestHandlers.
-->
<requestHandler name="/admin/"
class="solr.admin.AdminHandlers" />
<!-- 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 ${solr.home}/conf, explicitly
register the ShowFileRequestHandler using:
-->
<!--
<requestHandler name="/admin/file"
class="solr.admin.ShowFileRequestHandler" >
<lst name="invariants">
<str name="hidden">synonyms.txt</str>
<str name="hidden">anotherfile.txt</str>
</lst>
</requestHandler>
-->
<!-- ping/healthcheck -->
<requestHandler name="/admin/ping" class="solr.PingRequestHandler">
<lst name="invariants">
<str name="q">solrpingquery</str>
</lst>
<lst name="defaults">
<str name="echoParams">all</str>
</lst>
</requestHandler>
<!-- Echo the request contents back to the client -->
<requestHandler name="/debug/dump" class="solr.DumpRequestHandler" >
<lst name="defaults">
<str name="echoParams">explicit</str>
<str name="echoHandler">true</str>
</lst>
</requestHandler>
<requestHandler name="/dataimport" class="org.apache.solr.handler.dataimport.DataImportHandler" enable="${solr.master.enabled:false}">
<lst name="defaults">
<str name="config">./data-config.xml</str>
<lst name="datasource">
<str name="driver">com.mysql.jdbc.Driver</str>
<str name="url">jdbc:mysql://${solr.db.host:mysqldb}/ean_9?zeroDateTimeBehavior=convertToNull</str>
<str name="user">${solr.db.user:mysqluser}</str>
<str name="password">${solr.db.password:mysqlpass}</str>
<!-- Disable batch size by using -1 param, means stream. This avoids out of mem problem, but is a litle slower. -->
<str name="batchSize">-1</str>
<str name="readOnly">true</str>
<str name="autoCommit">false</str>
</lst>
</lst>
</requestHandler>
<requestHandler name="/replication" class="solr.ReplicationHandler">
<lst name="master">
<str name="enable">${solr.master.enabled}</str>
<!--Replicate on 'optimize' -->
<str name="replicateAfter">optimize</str>
<str name="replicateAfter">startup</str>
<str name="replicateAfter">commit</str>
</lst>
<lst name="slave">
<str name="enable">${solr.slave.enabled:false}</str>
<!--fully qualified url for the replication handler of master . -->
<str name="masterUrl">http://${solr.master.host}:${solr.master.port}/solr/${solr.core.name}/replication</str>
<!--Interval in which the slave should poll master .Format is HH:mm:ss .
If this is absent slave does not poll automatically.
But a snappull can be triggered from the admin or the http API -->
<str name="pollInterval">00:00:10</str>
</lst>
</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>
-->
<!--
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>
-->
<!-- Response Writers
http://wiki.apache.org/solr/QueryResponseWriter
Request responses will be written using the writer specified by
the 'wt' request parameter matching the name of a registered
writer.
The "default" writer is the default and will be used if 'wt' is
not specified in the request.
-->
<!-- The following response writers are implicitly configured unless
overridden...
-->
<!--
<queryResponseWriter name="xml"
default="true"
class="solr.XMLResponseWriter" />
<queryResponseWriter name="json" class="solr.JSONResponseWriter"/>
<queryResponseWriter name="python" class="solr.PythonResponseWriter"/>
<queryResponseWriter name="ruby" class="solr.RubyResponseWriter"/>
<queryResponseWriter name="php" class="solr.PHPResponseWriter"/>
<queryResponseWriter name="phps" class="solr.PHPSerializedResponseWriter"/>
<queryResponseWriter name="csv" class="solr.CSVResponseWriter"/>
-->
<!--
Custom response writers can be declared as needed...
-->
<queryResponseWriter name="velocity" class="solr.VelocityResponseWriter" startup="lazy"/>
<!-- 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" />
-->
<!-- Legacy config for the admin interface -->
<admin>
<defaultQuery>*:*</defaultQuery>
<!-- configure a healthcheck file for servers behind a
loadbalancer
-->
<!--
<healthcheck type="file">server-enabled</healthcheck>
-->
</admin>
</config>
本站文章为和通数据库网友分享或者投稿，欢迎任何形式的转载，但请务必注明出处.
同时文章内容如有侵犯了您的权益，请联系QQ：970679559，我们会在尽快处理。