Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

adding neccessary SolrConfig hooks so TestHarness and unit tests can specify arbitrary solrconfig.xml files, modified unit tests to demonstrate this -- per SOLR-3 and SOLR-8 

git-svn-id: https://svn.apache.org/repos/asf/incubator/solr/trunk@395148 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Chris M. Hostetter 2006-04-19 06:00:20 +00:00
parent 99a3a71234
commit c2338fca20
15 changed files with 749 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
build.xml
View File

@ -164,7 +164,7 @@
haltonfailure="no"
errorProperty="tests.failed"
failureProperty="tests.failed"
dir="src/apps/SolrTest"
dir="src/test/test-files/"
>
<syspropertyset>
<propertyref prefix="solr" />

53
src/java/org/apache/solr/core/SolrConfig.java
View File

@ -16,27 +16,64 @@
package org.apache.solr.core;
import org.xml.sax.SAXException;
import javax.xml.parsers.ParserConfigurationException;
import java.io.IOException;
import java.io.InputStream;
/**
* Provides a static refrence to a Config object modeling the main
* configuration data for a a Solr instance -- typically found in
* "solrconfig.xml".
*
* @author yonik
* @version $Id$
*/
public class SolrConfig {
public static final String DEFAULT_CONF_FILE = "solrconfig.xml";
/**
* Singleton containing all configuration.
*/
public static Config config;
static {
RuntimeException e=null;
String file="solrconfig.xml";
/**
* (Re)loads the static configation information from the specified file.
*
* <p>
* This method is called implicitly on ClassLoad, but it may be
* called explicitly to change the Configuration used for the purpose
* of testing - in which case it should be called prior to initializing
* a SolrCore.
* </p>
*
* <p>
* This method should <b>only</b> be called for testing purposes.
* Because it modifies a singleton, it is not suitable for running
* multi-threaded tests.
* </p>
*
* @param file file name to load
* @see Config#openResource
*/
public static synchronized void initConfig(String file)
throws ParserConfigurationException, IOException, SAXException {
InputStream is = Config.openResource(file);
config=new Config(file, is, "/config/");
is.close();
Config.log.info("Loaded SolrConfig: " + file);
}
static {
try {
config=new Config(file, is, "/config/");
is.close();
initConfig(DEFAULT_CONF_FILE);
} catch (Exception ee) {
throw new RuntimeException("Error in solrconfig.xml", ee);
throw new RuntimeException("Error in " + DEFAULT_CONF_FILE, ee);
}
Config.log.info("Loaded Config solrconfig.xml");
}
}

14
src/java/org/apache/solr/util/AbstractSolrTestCase.java
View File

@ -45,10 +45,16 @@ public abstract class AbstractSolrTestCase extends TestCase {
protected TestHarness.LocalRequestFactory lrf;
/**
* Subclasses must define this method to return the path of the
* Subclasses must define this method to return the name of the
* schema.xml they wish to use.
*/
public abstract String getSchemaPath();
public abstract String getSchemaFile();
/**
* Subclasses must define this method to return the name of the
* solrconfig.xml they wish to use.
*/
public abstract String getSolrConfigFile();
/**
* The directory used to story the index managed by the TestHarness h
@ -72,7 +78,9 @@ public abstract class AbstractSolrTestCase extends TestCase {
+ getClass().getName() + "-" + getName() + "-"
+ System.currentTimeMillis());
dataDir.mkdirs();
h = new TestHarness(dataDir.getAbsolutePath(), getSchemaPath());
h = new TestHarness(dataDir.getAbsolutePath(),
getSolrConfigFile(),
getSchemaFile());
lrf = h.getRequestFactory
("standard",0,20,"version","2.0");

25
src/java/org/apache/solr/util/TestHarness.java
View File

@ -17,6 +17,7 @@
package org.apache.solr.util;
import org.apache.solr.schema.IndexSchema;
import org.apache.solr.core.SolrConfig;
import org.apache.solr.core.SolrCore;
import org.apache.solr.request.*;
@ -55,12 +56,34 @@ public class TestHarness {
private DocumentBuilder builder;
/**
* Assumes "solrconfig.xml" is the config file to use, and
* "schema.xml" is the schema path to use.
*
* @param dataDirectory path for index data, will not be cleaned up
*/
public TestHarness(String dataDirectory) {
this(dataDirectory, "schema.xml");
}
/**
* Assumes "solrconfig.xml" is the config file to use.
*
* @param dataDirectory path for index data, will not be cleaned up
* @param schemaFile path of schema file
*/
public TestHarness(String dataDirectory, String schemaFile) {
core = new SolrCore(dataDirectory, new IndexSchema(schemaFile));
this(dataDirectory, "solrconfig.xml", schemaFile);
}
/**
* @param dataDirectory path for index data, will not be cleaned up
* @param confFile solrconfig filename
* @param schemaFile schema filename
*/
public TestHarness(String dataDirectory,
String confFile,
String schemaFile) {
try {
SolrConfig.initConfig(confFile);
core = new SolrCore(dataDirectory, new IndexSchema(schemaFile));
builder = DocumentBuilderFactory.newInstance().newDocumentBuilder();
} catch (Exception e) {
throw new RuntimeException(e);

3
src/test/org/apache/solr/BasicFunctionalityTest.java
View File

@ -25,7 +25,8 @@ import org.apache.solr.util.*;
*/
public class BasicFunctionalityTest extends AbstractSolrTestCase {
public String getSchemaPath() { return "solr/conf/schema.xml"; }
public String getSchemaFile() { return "schema.xml"; }
public String getSolrConfigFile() { return "solrconfig.xml"; }
public void setUp() throws Exception {
// if you override setUp or tearDown, you better call

3
src/test/org/apache/solr/ConvertedLegacyTest.java
View File

@ -30,7 +30,8 @@ import java.io.IOException;
*/
public class ConvertedLegacyTest extends AbstractSolrTestCase {
public String getSchemaPath() { return "solr/conf/schema.xml"; }
public String getSchemaFile() { return "schema.xml"; }
public String getSolrConfigFile() { return "solrconfig.xml"; }
public void testABunchOfConvertedStuff() {
// these may be reused by things that need a special query

28
src/test/org/apache/solr/SampleTest.java
View File

@ -29,9 +29,24 @@ import java.io.IOException;
public class SampleTest extends AbstractSolrTestCase {
/**
* All subclasses of AbstractSolrTestCase must define this method
* All subclasses of AbstractSolrTestCase must define this method.
*
* <p>
* Note that different tests can use different schemas by refering
* to any crazy path they want (as long as it works).
* </p>
*/
public String getSchemaPath() { return "solr/conf/schema.xml"; }
public String getSchemaFile() { return "solr/crazy-path-to-schema.xml"; }
/**
* All subclasses of AbstractSolrTestCase must define this method
*
* <p>
* Note that different tests can use different configs by refering
* to any crazy path they want (as long as it works).
* </p>
*/
public String getSolrConfigFile() { return "solr/crazy-path-to-config.xml"; }
/**
* Demonstration of some of the simple ways to use the base class
@ -71,7 +86,7 @@ public class SampleTest extends AbstractSolrTestCase {
doc("id", "4059",
"subject", "Who Me Again?") + "</add>");
// or really make the xml yourself
/* or really make the xml yourself */
assertU("<add><doc><field name=\"id\">4055</field>"
+"<field name=\"subject\">Hoss the Hoss man Hostetter</field>"
+"</doc></add>");
@ -87,9 +102,12 @@ public class SampleTest extends AbstractSolrTestCase {
,"//int[@name='id'][.='4055']"
);
/* make your own LocalRequestFactory to build a request */
/* make your own LocalRequestFactory to build a request
*
* Note: the qt proves we are using our custom config...
*/
TestHarness.LocalRequestFactory l = h.getRequestFactory
("standard",100,200,"version","2.1");
("crazy_custom_qt",100,200,"version","2.1");
assertQ("how did i find Mack Daddy? ",
l.makeRequest( "Mack Daddy" )
,"//result[@numFound=0]"

4
src/test/test-files/README Normal file
View File

@ -0,0 +1,4 @@
This directory is where any non-transient, non-java files needed
for the execution of tests should live.
It is used as the CWD when running JUnit tests.

5
src/test/test-files/solr/conf/protwords.txt Normal file
View File

@ -0,0 +1,5 @@
#use a protected word file to avoid stemming two
#unrelated words to the same base word.
#to test, we will use words that would normally obviously be stemmed.
cats
ridding

346
src/test/test-files/solr/conf/schema.xml Normal file
View File

@ -0,0 +1,346 @@
<?xml version="1.0" ?>
<!-- The Solr schema file. This file should be named "schema.xml" and
should be located where the classloader for the Solr webapp can find it.
$Id: schema.xml 382610 2006-03-03 01:43:03Z yonik $
$Source: /cvs/main/searching/solr-configs/test/WEB-INF/classes/schema.xml,v $
$Name: $
-->
<schema name="test" version="1.0">
<types>
<!-- field type definitions... note that the "name" attribute is
just a label to be used by field definitions. The "class"
attribute and any other attributes determine the real type and
behavior of the fieldtype.
-->
<!-- numeric field types that store and index the text
value verbatim (and hence don't sort correctly or support range queries.)
These are provided more for backward compatability, allowing one
to create a schema that matches an existing lucene index.
-->
<fieldtype name="integer" class="solr.IntField"/>
<fieldtype name="long" class="solr.LongField"/>
<fieldtype name="float" class="solr.FloatField"/>
<fieldtype name="double" class="solr.DoubleField"/>
<!-- numeric field types that manipulate the value into
a string value that isn't human readable in it's internal form,
but sorts correctly and supports range queries.
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.
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.
-->
<fieldtype name="sint" class="solr.SortableIntField" sortMissingLast="true"/>
<fieldtype name="slong" class="solr.SortableLongField" sortMissingLast="true"/>
<fieldtype name="sfloat" class="solr.SortableFloatField" sortMissingLast="true"/>
<fieldtype name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true"/>
<!-- bcd versions of sortable numeric type may provide smaller
storage space and support very large numbers.
-->
<fieldtype name="bcdint" class="solr.BCDIntField" sortMissingLast="true"/>
<fieldtype name="bcdlong" class="solr.BCDLongField" sortMissingLast="true"/>
<fieldtype name="bcdstr" class="solr.BCDStrField" sortMissingLast="true"/>
<fieldtype name="boolean" class="solr.BoolField" sortMissingLast="true"/>
<fieldtype name="string" class="solr.StrField" sortMissingLast="true"/>
<!-- format for date is 1995-12-31T23:59:59.999Z and only the fractional
seconds part (.999) is optional.
-->
<fieldtype name="date" class="solr.DateField" sortMissingLast="true"/>
<!-- solr.TextField allows the specification of custom
text analyzers specified as a tokenizer and a list
of token filters.
-->
<fieldtype name="text" class="solr.TextField">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StandardFilterFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory"/>
<!-- lucene PorterStemFilterFactory deprecated
<filter class="solr.PorterStemFilterFactory"/>
-->
<filter class="solr.EnglishPorterFilterFactory"/>
</analyzer>
</fieldtype>
<fieldtype name="nametext" class="solr.TextField">
<analyzer class="org.apache.lucene.analysis.WhitespaceAnalyzer"/>
</fieldtype>
<fieldtype name="teststop" class="solr.TextField">
<analyzer>
<tokenizer class="solr.LowerCaseTokenizerFactory"/>
<filter class="solr.StandardFilterFactory"/>
<filter class="solr.StopFilterFactory" words="stopwords.txt"/>
</analyzer>
</fieldtype>
<!-- fieldtypes in this section isolate tokenizers and tokenfilters for testing -->
<fieldtype name="lowertok" class="solr.TextField">
<analyzer><tokenizer class="solr.LowerCaseTokenizerFactory"/></analyzer>
</fieldtype>
<fieldtype name="standardtok" class="solr.TextField">
<analyzer><tokenizer class="solr.StandardTokenizerFactory"/></analyzer>
</fieldtype>
<fieldtype name="lettertok" class="solr.TextField">
<analyzer><tokenizer class="solr.LetterTokenizerFactory"/></analyzer>
</fieldtype>
<fieldtype name="whitetok" class="solr.TextField">
<analyzer><tokenizer class="solr.WhitespaceTokenizerFactory"/></analyzer>
</fieldtype>
<fieldtype name="HTMLstandardtok" class="solr.TextField">
<analyzer><tokenizer class="solr.HTMLStripStandardTokenizerFactory"/></analyzer>
</fieldtype>
<fieldtype name="HTMLwhitetok" class="solr.TextField">
<analyzer><tokenizer class="solr.HTMLStripWhitespaceTokenizerFactory"/></analyzer>
</fieldtype>
<fieldtype name="standardtokfilt" class="solr.TextField">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StandardFilterFactory"/>
</analyzer>
</fieldtype>
<fieldtype name="standardfilt" class="solr.TextField">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StandardFilterFactory"/>
</analyzer>
</fieldtype>
<fieldtype name="lowerfilt" class="solr.TextField">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldtype>
<fieldtype name="porterfilt" class="solr.TextField">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.PorterStemFilterFactory"/>
</analyzer>
</fieldtype>
<!-- fieldtype name="snowballfilt" class="solr.TextField">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SnowballPorterFilterFactory"/>
</analyzer>
</fieldtype -->
<fieldtype name="engporterfilt" class="solr.TextField">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.EnglishPorterFilterFactory"/>
</analyzer>
</fieldtype>
<fieldtype name="custengporterfilt" class="solr.TextField">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
</analyzer>
</fieldtype>
<fieldtype name="stopfilt" class="solr.TextField">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true"/>
</analyzer>
</fieldtype>
<fieldtype name="custstopfilt" class="solr.TextField">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" words="stopwords.txt"/>
</analyzer>
</fieldtype>
<fieldtype name="lengthfilt" class="solr.TextField">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.LengthFilterFactory" min="2" max="5"/>
</analyzer>
</fieldtype>
<fieldtype name="subword" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory"/>
<filter class="solr.EnglishPorterFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory"/>
<filter class="solr.EnglishPorterFilterFactory"/>
</analyzer>
</fieldtype>
<!-- more flexible in matching skus, but more chance of a false match -->
<fieldtype name="skutype1" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldtype>
<!-- less flexible in matching skus, but less chance of a false match -->
<fieldtype name="skutype2" class="solr.TextField">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldtype>
<!-- less flexible in matching skus, but less chance of a false match -->
<fieldtype name="syn" class="solr.TextField">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter name="syn" class="solr.SynonymFilterFactory" synonyms="synonyms.txt"/>
</analyzer>
</fieldtype>
<fieldtype name="unstored" class="solr.StrField" indexed="true" stored="false"/>
<fieldtype name="textgap" class="solr.TextField" multiValued="true" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldtype>
</types>
<fields>
<field name="id" type="integer" indexed="true" stored="true"/>
<field name="name" type="nametext" indexed="true" stored="true"/>
<field name="text" type="text" indexed="true" stored="false"/>
<field name="subject" type="text" indexed="true" stored="true"/>
<field name="title" type="nametext" indexed="true" stored="true"/>
<field name="weight" type="float" indexed="true" stored="true"/>
<field name="bday" type="date" indexed="true" stored="true"/>
<field name="title_stemmed" type="text" indexed="true" stored="false"/>
<field name="title_lettertok" type="lettertok" indexed="true" stored="false"/>
<field name="syn" type="syn" indexed="true" stored="true"/>
<!-- to test property inheritance and overriding -->
<field name="shouldbeunstored" type="unstored" />
<field name="shouldbestored" type="unstored" stored="true"/>
<field name="shouldbeunindexed" type="unstored" indexed="false" stored="true"/>
<!-- test different combinations of indexed and stored -->
<field name="bind" type="boolean" indexed="true" stored="false"/>
<field name="bsto" type="boolean" indexed="false" stored="true"/>
<field name="bindsto" type="boolean" indexed="true" stored="true"/>
<field name="isto" type="integer" indexed="false" stored="true"/>
<field name="iind" type="integer" indexed="true" stored="false"/>
<field name="ssto" type="string" indexed="false" stored="true"/>
<field name="sind" type="string" indexed="true" stored="false"/>
<field name="sindsto" type="string" indexed="true" stored="true"/>
<!-- fields to test individual tokenizers and tokenfilters -->
<field name="teststop" type="teststop" indexed="true" stored="true"/>
<field name="lowertok" type="lowertok" indexed="true" stored="true"/>
<field name="standardtok" type="standardtok" indexed="true" stored="true"/>
<field name="HTMLstandardtok" type="HTMLstandardtok" indexed="true" stored="true"/>
<field name="lettertok" type="lettertok" indexed="true" stored="true"/>
<field name="whitetok" type="whitetok" indexed="true" stored="true"/>
<field name="HTMLwhitetok" type="HTMLwhitetok" indexed="true" stored="true"/>
<field name="standardtokfilt" type="standardtokfilt" indexed="true" stored="true"/>
<field name="standardfilt" type="standardfilt" indexed="true" stored="true"/>
<field name="lowerfilt" type="lowerfilt" indexed="true" stored="true"/>
<field name="porterfilt" type="porterfilt" indexed="true" stored="true"/>
<field name="engporterfilt" type="engporterfilt" indexed="true" stored="true"/>
<field name="custengporterfilt" type="custengporterfilt" indexed="true" stored="true"/>
<field name="stopfilt" type="stopfilt" indexed="true" stored="true"/>
<field name="custstopfilt" type="custstopfilt" indexed="true" stored="true"/>
<field name="lengthfilt" type="lengthfilt" indexed="true" stored="true"/>
<field name="subword" type="subword" indexed="true" stored="true"/>
<field name="sku1" type="skutype1" indexed="true" stored="true"/>
<field name="sku2" type="skutype2" indexed="true" stored="true"/>
<field name="textgap" type="textgap" indexed="true" stored="true"/>
<!-- Dynamic field definitions. If a field name is not found, dynamicFields
will be used if the name matches any of the patterns.
RESTRICTION: the glob-like pattern in the name attribute must have
a "*" only at the start or the end.
EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
Longer patterns will be matched first. if equal size patterns
both match, the first appearing in the schema will be used.
-->
<dynamicField name="*_i" type="sint" indexed="true" stored="true"/>
<dynamicField name="*_s" type="string" indexed="true" stored="true"/>
<dynamicField name="*_l" type="slong" indexed="true" stored="true"/>
<dynamicField name="*_t" type="text" indexed="true" stored="true"/>
<dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
<dynamicField name="*_f" type="sfloat" indexed="true" stored="true"/>
<dynamicField name="*_d" type="sdouble" indexed="true" stored="true"/>
<dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
<dynamicField name="*_bcd" type="bcdstr" indexed="true" stored="true"/>
<dynamicField name="*_sI" type="string" indexed="true" stored="false"/>
<dynamicField name="*_sS" type="string" indexed="false" stored="true"/>
<dynamicField name="t_*" type="text" indexed="true" stored="true"/>
<!-- for testing to ensure that longer patterns are matched first -->
<dynamicField name="*aa" type="string" indexed="true" stored="true"/>
<dynamicField name="*aaa" type="integer" indexed="false" stored="true"/>
</fields>
<defaultSearchField>text</defaultSearchField>
<uniqueKey>id</uniqueKey>
<!-- copyField commands copy one field to another at the time a document
is added to the index. It's used either to index the same field different
ways, or to add multiple fields to the same field for easier/faster searching.
-->
<copyField source="title" dest="title_stemmed"/>
<copyField source="title" dest="title_lettertok"/>
<copyField source="title" dest="text"/>
<copyField source="subject" dest="text"/>
<!-- Similarity is the scoring routine for each document vs a query.
A custom similarity may be specified here, but the default is fine
for most applications.
-->
<!-- <similarity class="org.apache.lucene.search.DefaultSimilarity"/> -->
</schema>

191
src/test/test-files/solr/conf/solrconfig.xml Normal file
View File

@ -0,0 +1,191 @@
<?xml version="1.0" ?>
<!-- $Id: solrconfig.xml 382610 2006-03-03 01:43:03Z yonik $
$Source$
$Name$
-->
<config>
<!-- 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. -->
<!--
<indexDir>index</indexDir>
-->
<indexDefaults>
<!-- Values here affect all index writers and act as a default
unless overridden. -->
<useCompoundFile>false</useCompoundFile>
<mergeFactor>10</mergeFactor>
<maxBufferedDocs>1000</maxBufferedDocs>
<maxMergeDocs>2147483647</maxMergeDocs>
<maxFieldLength>10000</maxFieldLength>
<!-- these are global... can't currently override per index -->
<writeLockTimeout>1000</writeLockTimeout>
<commitLockTimeout>10000</commitLockTimeout>
</indexDefaults>
<mainIndex>
<!-- lucene options specific to the main on-disk lucene index -->
<useCompoundFile>false</useCompoundFile>
<mergeFactor>10</mergeFactor>
<maxBufferedDocs>1000</maxBufferedDocs>
<maxMergeDocs>2147483647</maxMergeDocs>
<maxFieldLength>10000</maxFieldLength>
<unlockOnStartup>true</unlockOnStartup>
</mainIndex>
<updateHandler class="solr.DirectUpdateHandler2">
<!-- autocommit pending docs if certain criteria are met -->
<autocommit> <!-- NOTE: autocommit not implemented yet -->
<maxDocs>10000</maxDocs>
<maxSec>3600</maxSec>
</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>
<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.LRUCache"
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"/>
<!--
<cache name="myUserCache"
class="solr.search.LRUCache"
size="4096"
initialSize="1024"
autowarmCount="1024"
regenerator="MyRegenerator"
/>
-->
<useFilterForSortedQuery>true</useFilterForSortedQuery>
<queryResultWindowSize>10</queryResultWindowSize>
<HashDocSet maxSize="3000" loadFactor="0.75"/>
<!-- boolToFilterOptimizer converts boolean clauses with zero boost
into cached filters if the number of docs selected by the clause exceeds
the threshold (represented as a fraction of the total index)
-->
<boolTofilterOptimizer enabled="true" cacheSize="32" threshold=".05"/>
<!-- a newSearcher event is fired whenever a new searcher is being prepared
and there is a current searcher handling requests (aka registered). -->
<!-- QuerySenderListener takes an array of NamedList and executes a
local query request for each NamedList in sequence. -->
<!--
<listener event="newSearcher" class="solr.QuerySenderListener">
<arr name="queries">
<lst> <str name="q">solr</str> <str name="start">0</str> <str name="rows">10</str> </lst>
<lst> <str name="q">rocks</str> <str name="start">0</str> <str name="rows">10</str> </lst>
</arr>
</listener>
-->
<!-- a firstSearcher event is fired whenever a new searcher is being
prepared but there is no current registered searcher to handle
requests or to gain 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" />
<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" />
<admin>
<defaultQuery>solr</defaultQuery>
<gettableFiles>solrconfig.xml scheam.xml</gettableFiles>
</admin>
</config>

2
src/test/test-files/solr/conf/stopwords.txt Normal file
View File

@ -0,0 +1,2 @@
stopworda
stopwordb

6
src/test/test-files/solr/conf/synonyms.txt Normal file
View File

@ -0,0 +1,6 @@
a => aa
b => b1 b2
c => c1,c2
a\=>a => b\=>b
a\,a => b\,b
foo,bar,baz

53
src/test/test-files/solr/crazy-path-to-config.xml Normal file
View File

@ -0,0 +1,53 @@
<?xml version="1.0" ?>
<!--
Striped down solrconfig used by SampleTest to demonstrate picking any
config filename you want.
$Id: solrconfig.xml 382610 2006-03-03 01:43:03Z yonik $
$Source$
-->
<config>
<indexDefaults>
<useCompoundFile>false</useCompoundFile>
<mergeFactor>10</mergeFactor>
<maxBufferedDocs>1000</maxBufferedDocs>
<maxMergeDocs>2147483647</maxMergeDocs>
<maxFieldLength>10000</maxFieldLength>
<writeLockTimeout>1000</writeLockTimeout>
<commitLockTimeout>10000</commitLockTimeout>
</indexDefaults>
<mainIndex>
<useCompoundFile>false</useCompoundFile>
<mergeFactor>10</mergeFactor>
<maxBufferedDocs>1000</maxBufferedDocs>
<maxMergeDocs>2147483647</maxMergeDocs>
<maxFieldLength>10000</maxFieldLength>
<unlockOnStartup>true</unlockOnStartup>
</mainIndex>
<updateHandler class="solr.DirectUpdateHandler2">
<commitIntervalLowerBound>0</commitIntervalLowerBound>
</updateHandler>
<query>
<maxBooleanClauses>1024</maxBooleanClauses>
<useFilterForSortedQuery>true</useFilterForSortedQuery>
<queryResultWindowSize>10</queryResultWindowSize>
<HashDocSet maxSize="3000" loadFactor="0.75"/>
<boolTofilterOptimizer enabled="true" cacheSize="32" threshold=".05"/>
</query>
<requestHandler name="standard" class="solr.StandardRequestHandler" />
<requestHandler name="crazy_custom_qt" class="solr.StandardRequestHandler" />
<admin>
<defaultQuery>solr</defaultQuery>
<gettableFiles>solrconfig.xml scheam.xml</gettableFiles>
</admin>
</config>

32
src/test/test-files/solr/crazy-path-to-schema.xml Normal file
View File

@ -0,0 +1,32 @@
<?xml version="1.0" ?>
<!--
Striped down schema used by SampleTest to demonstrate picking any
schema filename you want.
$Id: schema.xml 382610 2006-03-03 01:43:03Z yonik $
$Source: /cvs/main/searching/solr-configs/test/WEB-INF/classes/schema.xml,v $
-->
<schema name="test" version="1.0">
<types>
<fieldtype name="sint" class="solr.SortableIntField" />
<fieldtype name="text" class="solr.TextField">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StandardFilterFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory"/>
<filter class="solr.EnglishPorterFilterFactory"/>
</analyzer>
</fieldtype>
</types>
<fields>
<field name="id" type="sint" indexed="true" stored="true"/>
<field name="subject" type="text" indexed="true" stored="true"/>
</fields>
<defaultSearchField>subject</defaultSearchField>
<uniqueKey>id</uniqueKey>
</schema>