|
|
|
|
@ -14,12 +14,12 @@
|
|
|
|
|
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
|
|
|
See the License for the specific language governing permissions and
|
|
|
|
|
limitations under the License.
|
|
|
|
|
-->
|
|
|
|
|
-->
|
|
|
|
|
|
|
|
|
|
<!--
|
|
|
|
|
For more details about configurations options that may appear in
|
|
|
|
|
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,
|
|
|
|
|
@ -115,10 +115,59 @@
|
|
|
|
|
solr.RAMDirectoryFactory is memory based, not
|
|
|
|
|
persistent, and doesn't work with replication.
|
|
|
|
|
-->
|
|
|
|
|
<directoryFactory name="DirectoryFactory" class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}"/>
|
|
|
|
|
<!-- <directoryFactory name="DirectoryFactory" class="${solr.directoryFactory:solr.MMapDirectoryFactory}"/> -->
|
|
|
|
|
<!-- using MMapDirectoryFactory as solution for ClosedChannelException given in https://issues.apache.org/jira/browse/SOLR-2247
|
|
|
|
|
this feature is now switched on in the startYACY.sh file using a -D option -->
|
|
|
|
|
<directoryFactory name="DirectoryFactory"
|
|
|
|
|
class="${solr.directoryFactory:solr.NRTCachingDirectoryFactory}">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<!-- These will be used if you are using the solr.HdfsDirectoryFactory,
|
|
|
|
|
otherwise they will be ignored. If you don't plan on using hdfs,
|
|
|
|
|
you can safely remove this section. -->
|
|
|
|
|
<!-- The root directory that collection data should be written to. -->
|
|
|
|
|
<str name="solr.hdfs.home">${solr.hdfs.home:}</str>
|
|
|
|
|
<!-- The hadoop configuration files to use for the hdfs client. -->
|
|
|
|
|
<str name="solr.hdfs.confdir">${solr.hdfs.confdir:}</str>
|
|
|
|
|
<!-- Enable/Disable the hdfs cache. -->
|
|
|
|
|
<str name="solr.hdfs.blockcache.enabled">${solr.hdfs.blockcache.enabled:true}</str>
|
|
|
|
|
|
|
|
|
|
</directoryFactory>
|
|
|
|
|
|
|
|
|
|
<!-- The CodecFactory for defining the format of the inverted index.
|
|
|
|
|
The default implementation is SchemaCodecFactory, which is the official Lucene
|
|
|
|
|
index format, but hooks into the schema to provide per-field customization of
|
|
|
|
|
the postings lists and per-document values in the fieldType element
|
|
|
|
|
(postingsFormat/docValuesFormat). Note that most of the alternative implementations
|
|
|
|
|
are experimental, so if you choose to customize the index format, its a good
|
|
|
|
|
idea to convert back to the official format e.g. via IndexWriter.addIndexes(IndexReader)
|
|
|
|
|
before upgrading to a newer version to avoid unnecessary reindexing.
|
|
|
|
|
-->
|
|
|
|
|
<codecFactory class="solr.SchemaCodecFactory"/>
|
|
|
|
|
|
|
|
|
|
<!-- To enable dynamic schema REST APIs, 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
|
|
|
|
|
he 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"/>
|
|
|
|
|
|
|
|
|
|
<!-- using MMapDirectoryFactory as solution for ClosedChannelException
|
|
|
|
|
given in https://issues.apache.org/jira/browse/SOLR-2247
|
|
|
|
|
this feature is now switched on in the startYACY.sh file using a -D option
|
|
|
|
|
-->
|
|
|
|
|
|
|
|
|
|
<!-- ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
|
Index Config - These settings control low-level behavior of indexing
|
|
|
|
|
@ -135,10 +184,16 @@
|
|
|
|
|
<!-- Maximum time to wait for a write lock (ms) for an IndexWriter. Default: 1000 -->
|
|
|
|
|
<writeLockTimeout>20000</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.
|
|
|
|
|
Default in Lucene is "true". Default in Solr is "false" (since 3.6) -->
|
|
|
|
|
<!-- <useCompoundFile>true</useCompoundFile> -->
|
|
|
|
|
<useCompoundFile>true</useCompoundFile>
|
|
|
|
|
|
|
|
|
|
<!-- ramBufferSizeMB sets the amount of RAM that may be used by Lucene
|
|
|
|
|
indexing for buffering added documents and deletions before they are
|
|
|
|
|
@ -146,9 +201,10 @@
|
|
|
|
|
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>32</ramBufferSizeMB> -->
|
|
|
|
|
<!-- <maxBufferedDocs>1000</maxBufferedDocs> -->
|
|
|
|
|
Lucene will flush based on whichever limit is hit first.
|
|
|
|
|
The default is 100 MB. -->
|
|
|
|
|
<ramBufferSizeMB>32</ramBufferSizeMB>
|
|
|
|
|
<maxBufferedDocs>100</maxBufferedDocs>
|
|
|
|
|
|
|
|
|
|
<!-- Expert: Merge Policy
|
|
|
|
|
The Merge Policy in Lucene controls how merging of segments is done.
|
|
|
|
|
@ -171,7 +227,9 @@
|
|
|
|
|
will be allowed before they are merged into one.
|
|
|
|
|
Default is 10 for both merge policies.
|
|
|
|
|
-->
|
|
|
|
|
<mergeFactor>5</mergeFactor>
|
|
|
|
|
<!--
|
|
|
|
|
<mergeFactor>10</mergeFactor>
|
|
|
|
|
-->
|
|
|
|
|
|
|
|
|
|
<!-- Expert: Merge Scheduler
|
|
|
|
|
The Merge Scheduler in Lucene controls how merges are
|
|
|
|
|
@ -202,7 +260,7 @@
|
|
|
|
|
More details on the nuances of each LockFactory...
|
|
|
|
|
http://wiki.apache.org/lucene-java/AvailableLockFactories
|
|
|
|
|
-->
|
|
|
|
|
<!-- <lockType>native</lockType> -->
|
|
|
|
|
<lockType>${solr.lock.type:native}</lockType>
|
|
|
|
|
|
|
|
|
|
<!-- Unlock On Startup
|
|
|
|
|
|
|
|
|
|
@ -211,7 +269,7 @@
|
|
|
|
|
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'
|
|
|
|
|
This is not needed if lock type is 'single'
|
|
|
|
|
-->
|
|
|
|
|
<!--
|
|
|
|
|
<unlockOnStartup>false</unlockOnStartup>
|
|
|
|
|
@ -222,20 +280,19 @@
|
|
|
|
|
-->
|
|
|
|
|
<!-- <termIndexInterval>128</termIndexInterval> -->
|
|
|
|
|
|
|
|
|
|
<!-- If true, IndexReaders will be reopened (often more efficient)
|
|
|
|
|
instead of closed and then opened. Default: true
|
|
|
|
|
<!-- If true, IndexReaders will be opened/reopened from the IndexWriter
|
|
|
|
|
instead of from the Directory. Hosts in a master/slave setup
|
|
|
|
|
should have this set to false while those in a SolrCloud
|
|
|
|
|
cluster need to be set to true. Default: true
|
|
|
|
|
-->
|
|
|
|
|
<!--
|
|
|
|
|
<reopenReaders>true</reopenReaders>
|
|
|
|
|
<nrtMode>true</nrtMode>
|
|
|
|
|
-->
|
|
|
|
|
|
|
|
|
|
<!-- 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.
|
|
|
|
|
@ -267,10 +324,11 @@
|
|
|
|
|
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
|
|
|
|
|
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.
|
|
|
|
|
-->
|
|
|
|
|
<!-- <infoStream file="INFOSTREAM.txt">false</infoStream> -->
|
|
|
|
|
<infoStream>true</infoStream>
|
|
|
|
|
</indexConfig>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
@ -295,6 +353,16 @@
|
|
|
|
|
<!-- The default high-performance update handler -->
|
|
|
|
|
<updateHandler class="solr.DirectUpdateHandler2">
|
|
|
|
|
|
|
|
|
|
<!-- Enables a transaction log, used for real-time get, durability, and
|
|
|
|
|
and solr cloud replica recovery. The log can grow as big as
|
|
|
|
|
uncommitted changes to the index, so use of a hard autoCommit
|
|
|
|
|
is recommended (see below).
|
|
|
|
|
"dir" - the target directory for transaction logs, defaults to the
|
|
|
|
|
solr data directory. -->
|
|
|
|
|
<updateLog>
|
|
|
|
|
<str name="dir">${solr.ulog.dir:}</str>
|
|
|
|
|
</updateLog>
|
|
|
|
|
|
|
|
|
|
<!-- AutoCommit
|
|
|
|
|
|
|
|
|
|
Perform a hard commit automatically under certain conditions.
|
|
|
|
|
@ -307,15 +375,18 @@
|
|
|
|
|
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 automaticly
|
|
|
|
|
since a document was added before automatically
|
|
|
|
|
triggering a new commit.
|
|
|
|
|
openSearcher - if false, the commit causes recent index changes
|
|
|
|
|
to be flushed to stable storage, but does not cause a new
|
|
|
|
|
searcher to be opened to make those changes visible.
|
|
|
|
|
|
|
|
|
|
If the updateLog is enabled, then it's highly recommended to
|
|
|
|
|
have some sort of hard autoCommit to limit the log size.
|
|
|
|
|
-->
|
|
|
|
|
<autoCommit>
|
|
|
|
|
<maxTime>180000</maxTime>
|
|
|
|
|
<openSearcher>false</openSearcher>
|
|
|
|
|
<maxTime>${solr.autoCommit.maxTime:15000}</maxTime>
|
|
|
|
|
<openSearcher>true</openSearcher>
|
|
|
|
|
</autoCommit>
|
|
|
|
|
|
|
|
|
|
<!-- softAutoCommit is like autoCommit except it causes a
|
|
|
|
|
@ -323,11 +394,10 @@
|
|
|
|
|
but does not ensure that data is synced to disk. This is
|
|
|
|
|
faster and more near-realtime friendly than a hard commit.
|
|
|
|
|
-->
|
|
|
|
|
<!--
|
|
|
|
|
|
|
|
|
|
<autoSoftCommit>
|
|
|
|
|
<maxTime>3000</maxTime>
|
|
|
|
|
<maxTime>${solr.autoSoftCommit.maxTime:-1}</maxTime>
|
|
|
|
|
</autoSoftCommit>
|
|
|
|
|
-->
|
|
|
|
|
|
|
|
|
|
<!-- Update Related Event Listeners
|
|
|
|
|
|
|
|
|
|
@ -361,15 +431,6 @@
|
|
|
|
|
</listener>
|
|
|
|
|
-->
|
|
|
|
|
|
|
|
|
|
<!-- Enables a transaction log, currently used for real-time get.
|
|
|
|
|
"dir" - the target directory for transaction logs, defaults to the
|
|
|
|
|
solr data directory. -->
|
|
|
|
|
<!--
|
|
|
|
|
<updateLog>
|
|
|
|
|
<str name="dir">${solr.data.dir:}</str>
|
|
|
|
|
</updateLog>
|
|
|
|
|
-->
|
|
|
|
|
|
|
|
|
|
</updateHandler>
|
|
|
|
|
|
|
|
|
|
<!-- IndexReaderFactory
|
|
|
|
|
@ -461,21 +522,19 @@
|
|
|
|
|
and old cache.
|
|
|
|
|
-->
|
|
|
|
|
<filterCache class="solr.FastLRUCache"
|
|
|
|
|
size="64"
|
|
|
|
|
initialSize="64"
|
|
|
|
|
autowarmCount="0"
|
|
|
|
|
cleanupThread="true"/>
|
|
|
|
|
size="100"
|
|
|
|
|
initialSize="100"
|
|
|
|
|
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.
|
|
|
|
|
-->
|
|
|
|
|
<queryResultCache class="solr.FastLRUCache"
|
|
|
|
|
size="64"
|
|
|
|
|
initialSize="64"
|
|
|
|
|
autowarmCount="0"
|
|
|
|
|
cleanupThread="true"/>
|
|
|
|
|
<queryResultCache class="solr.LRUCache"
|
|
|
|
|
size="100"
|
|
|
|
|
initialSize="100"
|
|
|
|
|
autowarmCount="0"/>
|
|
|
|
|
|
|
|
|
|
<!-- Document Cache
|
|
|
|
|
|
|
|
|
|
@ -483,11 +542,18 @@
|
|
|
|
|
document). Since Lucene internal document ids are transient,
|
|
|
|
|
this cache will not be autowarmed.
|
|
|
|
|
-->
|
|
|
|
|
<documentCache class="solr.FastLRUCache"
|
|
|
|
|
<documentCache class="solr.LRUCache"
|
|
|
|
|
size="64"
|
|
|
|
|
initialSize="64"
|
|
|
|
|
autowarmCount="0"
|
|
|
|
|
cleanupThread="true"/>
|
|
|
|
|
autowarmCount="0"/>
|
|
|
|
|
|
|
|
|
|
<!-- custom cache currently used by block join -->
|
|
|
|
|
<cache name="perSegFilter"
|
|
|
|
|
class="solr.search.LRUCache"
|
|
|
|
|
size="10"
|
|
|
|
|
initialSize="0"
|
|
|
|
|
autowarmCount="10"
|
|
|
|
|
regenerator="solr.NoOpRegenerator" />
|
|
|
|
|
|
|
|
|
|
<!-- Field Value Cache
|
|
|
|
|
|
|
|
|
|
@ -498,8 +564,7 @@
|
|
|
|
|
<fieldValueCache class="solr.FastLRUCache"
|
|
|
|
|
size="64"
|
|
|
|
|
autowarmCount="0"
|
|
|
|
|
showItems="32"
|
|
|
|
|
cleanupThread="true"/>
|
|
|
|
|
showItems="32" />
|
|
|
|
|
|
|
|
|
|
<!-- Custom Cache
|
|
|
|
|
|
|
|
|
|
@ -512,16 +577,14 @@
|
|
|
|
|
-->
|
|
|
|
|
<!--
|
|
|
|
|
<cache name="myUserCache"
|
|
|
|
|
class="solr.FastLRUCache"
|
|
|
|
|
size="64"
|
|
|
|
|
initialSize="64"
|
|
|
|
|
autowarmCount="0"
|
|
|
|
|
class="solr.LRUCache"
|
|
|
|
|
size="4096"
|
|
|
|
|
initialSize="1024"
|
|
|
|
|
autowarmCount="1024"
|
|
|
|
|
regenerator="com.mycompany.MyRegenerator"
|
|
|
|
|
cleanupThread="true"
|
|
|
|
|
/>
|
|
|
|
|
-->
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<!-- Lazy Field Loading
|
|
|
|
|
|
|
|
|
|
If true, stored fields that are not requested will be loaded
|
|
|
|
|
@ -558,12 +621,12 @@
|
|
|
|
|
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>
|
|
|
|
|
<queryResultWindowSize>1</queryResultWindowSize>
|
|
|
|
|
|
|
|
|
|
<!-- Maximum number of documents to cache for any entry in the
|
|
|
|
|
queryResultCache.
|
|
|
|
|
-->
|
|
|
|
|
<queryResultMaxDocsCached>200</queryResultMaxDocsCached>
|
|
|
|
|
<queryResultMaxDocsCached>100</queryResultMaxDocsCached>
|
|
|
|
|
|
|
|
|
|
<!-- Query Related Event Listeners
|
|
|
|
|
|
|
|
|
|
|
Michael Peter Christen
11 years ago