SOLR-1167: Add XInclude support

git-svn-id: https://svn.apache.org/repos/asf/lucene/solr/trunk@820652 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Grant Ingersoll 2009-10-01 13:32:22 +00:00
parent 14504d1a58
commit 8997d47156
7 changed files with 540 additions and 4 deletions

View File

@ -339,6 +339,8 @@ New Features
83. SOLR-1292: Add FieldCache introspection to stats.jsp and JMX Monitoring via
a new SolrFieldCacheMBean. (hossman)
84. SOLR-1167: Solr Config now supports XInclude for XML engines that can support it. (Bryan Talbot via gsingers)
Optimizations
----------------------
1. SOLR-374: Use IndexReader.reopen to save resources by re-using parts of the

View File

@ -167,8 +167,14 @@ public class DataImporter {
void loadDataConfig(String configFile) {
try {
DocumentBuilder builder = DocumentBuilderFactory.newInstance()
.newDocumentBuilder();
DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
try {
dbf.setXIncludeAware(true);
dbf.setNamespaceAware(true);
} catch( UnsupportedOperationException e ) {
LOG.warn( "XML parser doesn't support XInclude option" );
}
DocumentBuilder builder = dbf.newDocumentBuilder();
Document document = builder.parse(new InputSource(new StringReader(
configFile)));

View File

@ -15,7 +15,13 @@
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.
Specifically, the Solr Config can support XInclude, which may make it easier to manage
the configuration. See https://issues.apache.org/jira/browse/SOLR-1167
-->
<config>
<!-- Set this to 'false' if you want solr to continue working after it has
encountered an severe configuration error. In a production environment,

View File

@ -100,8 +100,14 @@ public class Config {
if (lis == null) {
lis = loader.openConfig(name);
}
javax.xml.parsers.DocumentBuilder builder = DocumentBuilderFactory.newInstance().newDocumentBuilder();
doc = builder.parse(lis);
javax.xml.parsers.DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
try {
dbf.setXIncludeAware(true);
dbf.setNamespaceAware(true);
} catch(UnsupportedOperationException e) {
log.warn(name + " XML parser doesn't support XInclude option");
}
doc = dbf.newDocumentBuilder().parse(lis);
DOMUtil.substituteProperties(doc, loader.getCoreProperties());
} catch (ParserConfigurationException e) {

View File

@ -0,0 +1,52 @@
package org.apache.solr.core;
import org.apache.solr.util.AbstractSolrTestCase;
import org.apache.solr.request.SolrRequestHandler;
import javax.xml.parsers.DocumentBuilderFactory;
/**
*
*
**/
public class TestXIncludeConfig extends AbstractSolrTestCase {
protected boolean supports;
public String getSchemaFile() {
return "schema.xml";
}
//public String getSolrConfigFile() { return "solrconfig.xml"; }
public String getSolrConfigFile() {
return "solrconfig-xinclude.xml";
}
@Override
public void setUp() throws Exception {
supports = true;
javax.xml.parsers.DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
try {
//see whether it even makes sense to run this test
dbf.setXIncludeAware(true);
dbf.setNamespaceAware(true);
super.setUp();
} catch (UnsupportedOperationException e) {
supports = false;
}
}
public void testXInclude() throws Exception {
//Figure out whether this JVM supports XInclude anyway, if it doesn't then don't run this test????
// TODO: figure out a better way to handle this.
if (supports == true){
SolrCore core = h.getCore();
SolrRequestHandler solrRequestHandler = core.getRequestHandler("dismaxOldStyleDefaults");
assertNotNull("Solr Req Handler is null", solrRequestHandler);
} else {
System.out.println("Didn't run testXInclude, because this XML DocumentBuilderFactory doesn't support it");
}
}
}

View File

@ -0,0 +1,22 @@
<requestHandler name="dismaxOldStyleDefaults"
class="solr.DisMaxRequestHandler" >
<!-- for historic reasons, DisMaxRequestHandler will use all of
it's init params as "defaults" if there is no "defaults" list
specified
-->
<float name="tie">0.01</float>
<str name="qf">
text^0.5 features_t^1.0 subject^1.4 title_stemmed^2.0
</str>
<str name="pf">
text^0.2 features_t^1.1 subject^1.4 title_stemmed^2.0 title^1.5
</str>
<str name="bf">
ord(weight)^0.5 recip(rord(iind),1,1000,1000)^0.3
</str>
<str name="mm">
3&lt;-1 5&lt;-2 6&lt;90%
</str>
<int name="ps">100</int>
</requestHandler>

View File

@ -0,0 +1,442 @@
<?xml version="1.0" ?>
<!--
Licensed to the Apache Software Foundation (ASF) under one or more
contributor license agreements. See the NOTICE file distributed with
this work for additional information regarding copyright ownership.
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.
See the License for the specific language governing permissions and
limitations under the License.
-->
<!-- $Id: solrconfig.xml 382610 2006-03-03 01:43:03Z yonik $
$Source$
$Name$
-->
<config>
<jmx />
<!-- Used to specify an alternate directory to hold all index data.
It defaults to "index" if not present, and should probably
not be changed if replication is in use. -->
<dataDir>${solr.data.dir:./solr/data}</dataDir>
<indexDefaults>
<!-- Values here affect all index writers and act as a default
unless overridden. -->
<!-- Values here affect all index writers and act as a default unless overridden. -->
<useCompoundFile>false</useCompoundFile>
<mergeFactor>10</mergeFactor>
<!-- If both ramBufferSizeMB and maxBufferedDocs is set, then Lucene will flush based on whichever limit is hit first.
-->
<!--<maxBufferedDocs>1000</maxBufferedDocs>-->
<!-- Tell Lucene when to flush documents to disk.
Giving Lucene more memory for indexing means faster indexing at the cost of more RAM
If both ramBufferSizeMB and maxBufferedDocs is set, then Lucene will flush based on whichever limit is hit first.
-->
<ramBufferSizeMB>32</ramBufferSizeMB>
<maxMergeDocs>2147483647</maxMergeDocs>
<maxFieldLength>10000</maxFieldLength>
<writeLockTimeout>1000</writeLockTimeout>
<commitLockTimeout>10000</commitLockTimeout>
<!--
Expert: Turn on Lucene's auto commit capability.
NOTE: Despite the name, this value does not have any relation to Solr's autoCommit functionality
-->
<luceneAutoCommit>false</luceneAutoCommit>
<!--
Expert:
The Merge Policy in Lucene controls how merging is handled by Lucene. The default in 2.3 is the LogByteSizeMergePolicy, previous
versions used LogDocMergePolicy.
LogByteSizeMergePolicy chooses segments to merge based on their size. The Lucene 2.2 default, LogDocMergePolicy chose when
to merge based on number of documents
Other implementations of MergePolicy must have a no-argument constructor
-->
<mergePolicy class="org.apache.lucene.index.LogByteSizeMergePolicy"/>
<!--
Expert:
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"/>
<!-- these are global... can't currently override per index -->
<writeLockTimeout>1000</writeLockTimeout>
<commitLockTimeout>10000</commitLockTimeout>
<!-- Controls how often Lucene loads terms into memory -->
<termIndexInterval>256</termIndexInterval>
<lockType>single</lockType>
</indexDefaults>
<mainIndex>
<!-- lucene options specific to the main on-disk lucene index -->
<useCompoundFile>false</useCompoundFile>
<mergeFactor>10</mergeFactor>
<!-- for better multi-segment testing, we are using slower
indexing properties of maxBufferedDocs=10 and LogDocMergePolicy.
-->
<maxBufferedDocs>10</maxBufferedDocs>
<termIndexInterval>256</termIndexInterval>
<maxMergeDocs>2147483647</maxMergeDocs>
<maxFieldLength>10000</maxFieldLength>
<mergePolicy class="org.apache.lucene.index.LogDocMergePolicy"/>
<unlockOnStartup>true</unlockOnStartup>
</mainIndex>
<updateHandler class="solr.DirectUpdateHandler2">
<!-- autocommit pending docs if certain criteria are met
<autoCommit>
<maxDocs>10000</maxDocs>
<maxTime>3600000</maxTime>
</autoCommit>
-->
<!-- represents a lower bound on the frequency that commits may
occur (in seconds). NOTE: not yet implemented
<commitIntervalLowerBound>0</commitIntervalLowerBound>
-->
<!-- 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
<listener event="postCommit" class="solr.RunExecutableListener">
<str name="exe">/var/opt/resin3/__PORT__/scripts/solr/snapshooter</str>
<str name="dir">/var/opt/resin3/__PORT__</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 name="IndexReaderFactory" class="org.apache.solr.core.StandardIndexReaderFactory">
<int name="termInfosIndexDivisor">12</int>
</indexReaderFactory >
<query>
<!-- Maximum number of clauses in a boolean query... can affect
range or wildcard queries that expand to big boolean
queries. An exception is thrown if exceeded.
-->
<maxBooleanClauses>1024</maxBooleanClauses>
<!-- Cache specification for Filters or DocSets - unordered set of *all* documents
that match a particular query.
-->
<filterCache
class="solr.search.FastLRUCache"
size="512"
initialSize="512"
autowarmCount="256"/>
<queryResultCache
class="solr.search.LRUCache"
size="512"
initialSize="512"
autowarmCount="1024"/>
<documentCache
class="solr.search.LRUCache"
size="512"
initialSize="512"
autowarmCount="0"/>
<!-- If true, stored fields that are not requested will be loaded lazily.
-->
<enableLazyFieldLoading>true</enableLazyFieldLoading>
<!--
<cache name="myUserCache"
class="solr.search.LRUCache"
size="4096"
initialSize="1024"
autowarmCount="1024"
regenerator="MyRegenerator"
/>
-->
<!--
<useFilterForSortedQuery>true</useFilterForSortedQuery>
-->
<queryResultWindowSize>10</queryResultWindowSize>
<!-- set maxSize artificially low to exercise both types of sets -->
<HashDocSet maxSize="3" 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="false" 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 prewarming 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>
<!-- An alternate set representation that uses an integer hash to store filters (sets of docids).
If the set cardinality <= maxSize elements, then HashDocSet will be used instead of the bitset
based HashBitset. -->
<!-- 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">
<bool name="httpCaching">true</bool>
</requestHandler>
<xi:include href="solr/conf/solrconfig-reqHandler.incl" xmlns:xi="http://www.w3.org/2001/XInclude"/>
<requestHandler name="dismax" class="solr.DisMaxRequestHandler" >
<lst name="defaults">
<str name="q.alt">*:*</str>
<float name="tie">0.01</float>
<str name="qf">
text^0.5 features_t^1.0 subject^1.4 title_stemmed^2.0
</str>
<str name="pf">
text^0.2 features_t^1.1 subject^1.4 title_stemmed^2.0 title^1.5
</str>
<str name="bf">
ord(weight)^0.5 recip(rord(iind),1,1000,1000)^0.3
</str>
<str name="mm">
3&lt;-1 5&lt;-2 6&lt;90%
</str>
<int name="ps">100</int>
</lst>
</requestHandler>
<requestHandler name="old" class="solr.tst.OldRequestHandler" >
<int name="myparam">1000</int>
<float name="ratio">1.4142135</float>
<arr name="myarr"><int>1</int><int>2</int></arr>
<str>foo</str>
</requestHandler>
<requestHandler name="oldagain" class="solr.tst.OldRequestHandler" >
<lst name="lst1"> <str name="op">sqrt</str> <int name="val">2</int> </lst>
<lst name="lst2"> <str name="op">log</str> <float name="val">10</float> </lst>
</requestHandler>
<requestHandler name="test" class="solr.tst.TestRequestHandler" />
<!-- test query parameter defaults -->
<requestHandler name="defaults" class="solr.StandardRequestHandler">
<lst name="defaults">
<int name="rows">4</int>
<bool name="hl">true</bool>
<str name="hl.fl">text,name,subject,title,whitetok</str>
</lst>
</requestHandler>
<!-- test query parameter defaults -->
<requestHandler name="lazy" class="solr.StandardRequestHandler" startup="lazy">
<lst name="defaults">
<int name="rows">4</int>
<bool name="hl">true</bool>
<str name="hl.fl">text,name,subject,title,whitetok</str>
</lst>
</requestHandler>
<requestHandler name="/update" class="solr.XmlUpdateRequestHandler" />
<requestHandler name="/update/csv" class="solr.CSVRequestHandler" startup="lazy">
<bool name="httpCaching">false</bool>
</requestHandler>
<!-- test elevation -->
<searchComponent name="elevate" class="org.apache.solr.handler.component.QueryElevationComponent" >
<str name="queryFieldType">string</str>
<str name="config-file">elevate.xml</str>
</searchComponent>
<requestHandler name="/elevate" class="org.apache.solr.handler.component.SearchHandler">
<lst name="defaults">
<str name="echoParams">explicit</str>
</lst>
<arr name="last-components">
<str>elevate</str>
</arr>
</requestHandler>
<searchComponent name="spellcheck" class="org.apache.solr.handler.component.SpellCheckComponent">
<str name="queryAnalyzerFieldType">lowerfilt</str>
<lst name="spellchecker">
<str name="name">default</str>
<str name="field">lowerfilt</str>
<str name="spellcheckIndexDir">spellchecker1</str>
<str name="buildOnCommit">true</str>
</lst>
<!-- Example of using different distance measure -->
<lst name="spellchecker">
<str name="name">jarowinkler</str>
<str name="field">lowerfilt</str>
<!-- Use a different Distance Measure -->
<str name="distanceMeasure">org.apache.lucene.search.spell.JaroWinklerDistance</str>
<str name="spellcheckIndexDir">spellchecker2</str>
</lst>
<lst name="spellchecker">
<str name="classname">solr.FileBasedSpellChecker</str>
<str name="name">external</str>
<str name="sourceLocation">spellings.txt</str>
<str name="characterEncoding">UTF-8</str>
<str name="spellcheckIndexDir">spellchecker3</str>
</lst>
</searchComponent>
<searchComponent name="termsComp" class="org.apache.solr.handler.component.TermsComponent"/>
<requestHandler name="/terms" class="org.apache.solr.handler.component.SearchHandler">
<arr name="components">
<str>termsComp</str>
</arr>
</requestHandler>
<!--
The SpellingQueryConverter to convert raw (CommonParams.Q) queries into tokens. Uses a simple regular expression
to strip off field markup, boosts, ranges, etc. but it is not guaranteed to match an exact parse from the query parser.
-->
<queryConverter name="queryConverter" class="org.apache.solr.spelling.SpellingQueryConverter"/>
<requestHandler name="spellCheckCompRH" class="org.apache.solr.handler.component.SearchHandler">
<lst name="defaults">
<!-- omp = Only More Popular -->
<str name="spellcheck.onlyMorePopular">false</str>
<!-- exr = Extended Results -->
<str name="spellcheck.extendedResults">false</str>
<!-- The number of suggestions to return -->
<str name="spellcheck.count">1</str>
</lst>
<arr name="last-components">
<str>spellcheck</str>
</arr>
</requestHandler>
<searchComponent name="tvComponent" class="org.apache.solr.handler.component.TermVectorComponent"/>
<requestHandler name="tvrh" class="org.apache.solr.handler.component.SearchHandler">
<lst name="defaults">
</lst>
<arr name="last-components">
<str>tvComponent</str>
</arr>
</requestHandler>
<highlighting>
<!-- Configure the standard fragmenter -->
<fragmenter name="gap" class="org.apache.solr.highlight.GapFragmenter" default="true">
<lst name="defaults">
<int name="hl.fragsize">100</int>
</lst>
</fragmenter>
<fragmenter name="regex" class="org.apache.solr.highlight.RegexFragmenter">
<lst name="defaults">
<int name="hl.fragsize">70</int>
</lst>
</fragmenter>
<!-- Configure the standard formatter -->
<formatter name="html" class="org.apache.solr.highlight.HtmlFormatter" default="true">
<lst name="defaults">
<str name="hl.simple.pre"><![CDATA[<em>]]></str>
<str name="hl.simple.post"><![CDATA[</em>]]></str>
</lst>
</formatter>
</highlighting>
<!-- enable streaming for testing... -->
<requestDispatcher handleSelect="true" >
<requestParsers enableRemoteStreaming="true" multipartUploadLimitInKB="2048" />
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" never304="false">
<cacheControl>max-age=30, public</cacheControl>
</httpCaching>
</requestDispatcher>
<admin>
<defaultQuery>solr</defaultQuery>
<gettableFiles>solrconfig.xml scheam.xml admin-extra.html</gettableFiles>
</admin>
<!-- test getting system property -->
<propTest attr1="${solr.test.sys.prop1}-$${literal}"
attr2="${non.existent.sys.prop:default-from-config}">prefix-${solr.test.sys.prop2}-suffix</propTest>
<queryParser name="foo" class="FooQParserPlugin"/>
<updateRequestProcessorChain name="dedupe">
<processor class="org.apache.solr.update.processor.SignatureUpdateProcessorFactory">
<bool name="enabled">false</bool>
<bool name="overwriteDupes">true</bool>
<str name="fields">v_t,t_field</str>
<str name="signatureClass">org.apache.solr.update.processor.TextProfileSignature</str>
</processor>
<processor class="solr.RunUpdateProcessorFactory" />
</updateRequestProcessorChain>
</config>