mirror of https://github.com/apache/lucene.git
SOLR-1674: speed up analysis tests (thanks Robert Muir!)
git-svn-id: https://svn.apache.org/repos/asf/lucene/solr/trunk@921427 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
parent
ca50eef4ca
commit
ebc4ce0b14
|
@ -1,42 +0,0 @@
|
|||
/**
|
||||
* 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.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
import org.apache.solr.core.SolrConfig;
|
||||
import org.apache.solr.util.AbstractSolrTestCase;
|
||||
import org.apache.solr.util.TestHarness;
|
||||
import junit.framework.TestCase;
|
||||
|
||||
/**
|
||||
*
|
||||
*/
|
||||
abstract public class AnalysisTestCase extends AbstractSolrTestCase {
|
||||
protected SolrConfig solrConfig;
|
||||
/** Creates a new instance of AnalysisTestCase */
|
||||
public AnalysisTestCase() {
|
||||
}
|
||||
|
||||
public String getSolrConfigFile() { return "solrconfig.xml"; }
|
||||
public String getSchemaFile() { return "schema.xml"; }
|
||||
|
||||
public void setUp() throws Exception {
|
||||
// if you override setUp or tearDown, you better call
|
||||
// the super classes version
|
||||
super.setUp();
|
||||
solrConfig = TestHarness.createConfig(getSolrConfigFile());
|
||||
}
|
||||
}
|
|
@ -20,6 +20,8 @@ package org.apache.solr.analysis;
|
|||
import java.io.IOException;
|
||||
import java.io.StringReader;
|
||||
|
||||
import junit.framework.TestCase;
|
||||
|
||||
import org.apache.lucene.analysis.Analyzer;
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
|
||||
|
@ -30,7 +32,7 @@ import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
|
|||
/**
|
||||
* General token testing helper functions
|
||||
*/
|
||||
public abstract class BaseTokenTestCase extends AnalysisTestCase
|
||||
public abstract class BaseTokenTestCase extends TestCase
|
||||
{
|
||||
// some helpers to test Analyzers and TokenStreams:
|
||||
// these are taken from Lucene's BaseTokenStreamTestCase
|
||||
|
|
|
@ -20,8 +20,8 @@ package org.apache.solr.analysis;
|
|||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.Tokenizer;
|
||||
import org.apache.lucene.analysis.WhitespaceTokenizer;
|
||||
import org.apache.solr.util.AbstractSolrTestCase;
|
||||
import org.apache.solr.common.ResourceLoader;
|
||||
import org.apache.solr.core.SolrResourceLoader;
|
||||
|
||||
import java.io.StringReader;
|
||||
import java.util.Set;
|
||||
|
@ -34,16 +34,9 @@ import java.util.HashMap;
|
|||
* so this won't break if stop filter test files change
|
||||
**/
|
||||
public class CommonGramsFilterFactoryTest extends BaseTokenTestCase {
|
||||
public String getSchemaFile() {
|
||||
return "schema-stop-keep.xml";
|
||||
}
|
||||
|
||||
public String getSolrConfigFile() {
|
||||
return "solrconfig.xml";
|
||||
}
|
||||
|
||||
public void testInform() throws Exception {
|
||||
ResourceLoader loader = solrConfig.getResourceLoader();
|
||||
ResourceLoader loader = new SolrResourceLoader(null, null);
|
||||
assertTrue("loader is null and it shouldn't be", loader != null);
|
||||
CommonGramsFilterFactory factory = new CommonGramsFilterFactory();
|
||||
Map<String, String> args = new HashMap<String, String>();
|
||||
|
@ -75,7 +68,7 @@ public class CommonGramsFilterFactoryTest extends BaseTokenTestCase {
|
|||
* If no words are provided, then a set of english default stopwords is used.
|
||||
*/
|
||||
public void testDefaults() throws Exception {
|
||||
ResourceLoader loader = solrConfig.getResourceLoader();
|
||||
ResourceLoader loader = new SolrResourceLoader(null, null);
|
||||
assertTrue("loader is null and it shouldn't be", loader != null);
|
||||
CommonGramsFilterFactory factory = new CommonGramsFilterFactory();
|
||||
Map<String, String> args = new HashMap<String, String>();
|
||||
|
|
|
@ -20,6 +20,7 @@ import org.apache.lucene.analysis.TokenStream;
|
|||
import org.apache.lucene.analysis.Tokenizer;
|
||||
import org.apache.lucene.analysis.WhitespaceTokenizer;
|
||||
import org.apache.solr.common.ResourceLoader;
|
||||
import org.apache.solr.core.SolrResourceLoader;
|
||||
|
||||
import java.io.StringReader;
|
||||
import java.util.Set;
|
||||
|
@ -32,16 +33,9 @@ import java.util.HashMap;
|
|||
* so this won't break if stop filter test files change
|
||||
**/
|
||||
public class CommonGramsQueryFilterFactoryTest extends BaseTokenTestCase {
|
||||
public String getSchemaFile() {
|
||||
return "schema-stop-keep.xml";
|
||||
}
|
||||
|
||||
public String getSolrConfigFile() {
|
||||
return "solrconfig.xml";
|
||||
}
|
||||
|
||||
public void testInform() throws Exception {
|
||||
ResourceLoader loader = solrConfig.getResourceLoader();
|
||||
ResourceLoader loader = new SolrResourceLoader(null, null);
|
||||
assertTrue("loader is null and it shouldn't be", loader != null);
|
||||
CommonGramsQueryFilterFactory factory = new CommonGramsQueryFilterFactory();
|
||||
Map<String, String> args = new HashMap<String, String>();
|
||||
|
@ -73,7 +67,7 @@ public class CommonGramsQueryFilterFactoryTest extends BaseTokenTestCase {
|
|||
* If no words are provided, then a set of english default stopwords is used.
|
||||
*/
|
||||
public void testDefaults() throws Exception {
|
||||
ResourceLoader loader = solrConfig.getResourceLoader();
|
||||
ResourceLoader loader = new SolrResourceLoader(null, null);
|
||||
assertTrue("loader is null and it shouldn't be", loader != null);
|
||||
CommonGramsQueryFilterFactory factory = new CommonGramsQueryFilterFactory();
|
||||
Map<String, String> args = new HashMap<String, String>();
|
||||
|
|
|
@ -21,6 +21,7 @@ import org.apache.lucene.analysis.Tokenizer;
|
|||
import org.apache.lucene.analysis.WhitespaceTokenizer;
|
||||
import org.apache.solr.common.ResourceLoader;
|
||||
import org.apache.solr.common.util.StrUtils;
|
||||
import org.apache.solr.core.SolrResourceLoader;
|
||||
import org.tartarus.snowball.ext.EnglishStemmer;
|
||||
|
||||
import java.io.IOException;
|
||||
|
@ -114,7 +115,7 @@ public class SnowballPorterFilterFactoryTest extends BaseTokenTestCase {
|
|||
*/
|
||||
public void testProtected() throws Exception {
|
||||
SnowballPorterFilterFactory factory = new SnowballPorterFilterFactory();
|
||||
ResourceLoader loader = solrConfig.getResourceLoader();
|
||||
ResourceLoader loader = new SolrResourceLoader(null, null);
|
||||
Map<String,String> args = new HashMap<String,String>();
|
||||
args.put("protected", "protwords.txt");
|
||||
args.put("language", "English");
|
||||
|
|
|
@ -23,36 +23,23 @@ import java.util.Map;
|
|||
|
||||
import junit.framework.TestCase;
|
||||
|
||||
import org.apache.lucene.analysis.Token;
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.WhitespaceTokenizer;
|
||||
import org.apache.lucene.analysis.tokenattributes.PayloadAttribute;
|
||||
import org.apache.lucene.analysis.payloads.FloatEncoder;
|
||||
import org.apache.lucene.analysis.payloads.DelimitedPayloadTokenFilter;
|
||||
import org.apache.lucene.analysis.payloads.FloatEncoder;
|
||||
import org.apache.lucene.analysis.payloads.PayloadHelper;
|
||||
import org.apache.lucene.util.Attribute;
|
||||
import org.apache.solr.core.SolrCore;
|
||||
import org.apache.solr.core.SolrResourceLoader;
|
||||
import org.apache.lucene.analysis.tokenattributes.PayloadAttribute;
|
||||
import org.apache.solr.common.ResourceLoader;
|
||||
import org.apache.solr.util.AbstractSolrTestCase;
|
||||
import org.apache.solr.core.SolrResourceLoader;
|
||||
|
||||
public class TestDelimitedPayloadTokenFilterFactory extends AbstractSolrTestCase{
|
||||
|
||||
|
||||
public String getSchemaFile() {
|
||||
return "schema.xml";
|
||||
}
|
||||
|
||||
public String getSolrConfigFile() {
|
||||
return "solrconfig.xml";
|
||||
}
|
||||
public class TestDelimitedPayloadTokenFilterFactory extends TestCase {
|
||||
|
||||
public void testEncoder() throws Exception {
|
||||
Map<String,String> args = new HashMap<String, String>();
|
||||
args.put(DelimitedPayloadTokenFilterFactory.ENCODER_ATTR, "float");
|
||||
DelimitedPayloadTokenFilterFactory factory = new DelimitedPayloadTokenFilterFactory();
|
||||
factory.init(args);
|
||||
ResourceLoader loader = h.getCore().getResourceLoader();
|
||||
ResourceLoader loader = new SolrResourceLoader(null, null);
|
||||
factory.inform(loader);
|
||||
|
||||
TokenStream input = new WhitespaceTokenizer(new StringReader("the|0.1 quick|0.1 red|0.1"));
|
||||
|
@ -74,7 +61,7 @@ public class TestDelimitedPayloadTokenFilterFactory extends AbstractSolrTestCase
|
|||
args.put(DelimitedPayloadTokenFilterFactory.DELIMITER_ATTR, "*");
|
||||
DelimitedPayloadTokenFilterFactory factory = new DelimitedPayloadTokenFilterFactory();
|
||||
factory.init(args);
|
||||
ResourceLoader loader = h.getCore().getResourceLoader();
|
||||
ResourceLoader loader = new SolrResourceLoader(null, null);
|
||||
factory.inform(loader);
|
||||
|
||||
TokenStream input = new WhitespaceTokenizer(new StringReader("the*0.1 quick*0.1 red*0.1"));
|
||||
|
|
|
@ -26,6 +26,7 @@ import org.apache.lucene.analysis.TokenStream;
|
|||
import org.apache.lucene.analysis.Tokenizer;
|
||||
import org.apache.lucene.analysis.WhitespaceTokenizer;
|
||||
import org.apache.solr.common.ResourceLoader;
|
||||
import org.apache.solr.core.SolrResourceLoader;
|
||||
|
||||
/**
|
||||
* Simple tests to ensure the Dictionary compound filter factory is working.
|
||||
|
@ -38,7 +39,7 @@ public class TestDictionaryCompoundWordTokenFilterFactory extends BaseTokenTestC
|
|||
Reader reader = new StringReader("I like to play softball");
|
||||
Tokenizer tokenizer = new WhitespaceTokenizer(reader);
|
||||
DictionaryCompoundWordTokenFilterFactory factory = new DictionaryCompoundWordTokenFilterFactory();
|
||||
ResourceLoader loader = solrConfig.getResourceLoader();
|
||||
ResourceLoader loader = new SolrResourceLoader(null, null);
|
||||
Map<String,String> args = new HashMap<String,String>();
|
||||
args.put("dictionary", "compoundDictionary.txt");
|
||||
factory.init(args);
|
||||
|
|
|
@ -26,6 +26,7 @@ import org.apache.lucene.analysis.TokenStream;
|
|||
import org.apache.lucene.analysis.Tokenizer;
|
||||
import org.apache.lucene.analysis.WhitespaceTokenizer;
|
||||
import org.apache.solr.common.ResourceLoader;
|
||||
import org.apache.solr.core.SolrResourceLoader;
|
||||
|
||||
/**
|
||||
* Simple tests to ensure the French elision filter factory is working.
|
||||
|
@ -38,7 +39,7 @@ public class TestElisionFilterFactory extends BaseTokenTestCase {
|
|||
Reader reader = new StringReader("l'avion");
|
||||
Tokenizer tokenizer = new WhitespaceTokenizer(reader);
|
||||
ElisionFilterFactory factory = new ElisionFilterFactory();
|
||||
ResourceLoader loader = solrConfig.getResourceLoader();
|
||||
ResourceLoader loader = new SolrResourceLoader(null, null);
|
||||
Map<String,String> args = new HashMap<String,String>();
|
||||
args.put("articles", "frenchArticles.txt");
|
||||
factory.init(args);
|
||||
|
|
|
@ -16,29 +16,24 @@ package org.apache.solr.analysis;
|
|||
* limitations under the License.
|
||||
*/
|
||||
|
||||
import org.apache.solr.util.AbstractSolrTestCase;
|
||||
import org.apache.solr.common.ResourceLoader;
|
||||
import org.apache.solr.core.SolrResourceLoader;
|
||||
|
||||
import java.util.Set;
|
||||
import java.util.Map;
|
||||
import java.util.HashMap;
|
||||
|
||||
import junit.framework.TestCase;
|
||||
|
||||
|
||||
/**
|
||||
*
|
||||
*
|
||||
**/
|
||||
public class TestKeepFilterFactory extends AbstractSolrTestCase{
|
||||
public String getSchemaFile() {
|
||||
return "schema-stop-keep.xml";
|
||||
}
|
||||
|
||||
public String getSolrConfigFile() {
|
||||
return "solrconfig.xml";
|
||||
}
|
||||
public class TestKeepFilterFactory extends TestCase{
|
||||
|
||||
public void testInform() throws Exception {
|
||||
ResourceLoader loader = solrConfig.getResourceLoader();
|
||||
ResourceLoader loader = new SolrResourceLoader(null, null);
|
||||
assertTrue("loader is null and it shouldn't be", loader != null);
|
||||
KeepWordFilterFactory factory = new KeepWordFilterFactory();
|
||||
Map<String, String> args = new HashMap<String, String>();
|
||||
|
|
|
@ -25,6 +25,8 @@ import java.util.Set;
|
|||
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.WhitespaceTokenizer;
|
||||
import org.apache.solr.common.ResourceLoader;
|
||||
import org.apache.solr.core.SolrResourceLoader;
|
||||
|
||||
|
||||
/**
|
||||
|
@ -40,13 +42,13 @@ public class TestKeepWordFilter extends BaseTokenTestCase {
|
|||
|
||||
String input = "aaa BBB ccc ddd EEE";
|
||||
Map<String,String> args = new HashMap<String, String>();
|
||||
|
||||
ResourceLoader loader = new SolrResourceLoader(null, null);
|
||||
|
||||
// Test Stopwords
|
||||
KeepWordFilterFactory factory = new KeepWordFilterFactory();
|
||||
args.put( "ignoreCase", "true" );
|
||||
factory.init( args );
|
||||
factory.inform( solrConfig.getResourceLoader() );
|
||||
factory.inform( loader );
|
||||
factory.setWords( words );
|
||||
assertTrue(factory.isIgnoreCase());
|
||||
TokenStream stream = factory.create(new WhitespaceTokenizer(new StringReader(input)));
|
||||
|
@ -56,7 +58,7 @@ public class TestKeepWordFilter extends BaseTokenTestCase {
|
|||
factory = new KeepWordFilterFactory();
|
||||
args = new HashMap<String, String>();
|
||||
factory.init( args );
|
||||
factory.inform( solrConfig.getResourceLoader() );
|
||||
factory.inform( loader );
|
||||
factory.setIgnoreCase(true);
|
||||
factory.setWords( words );
|
||||
assertTrue(factory.isIgnoreCase());
|
||||
|
@ -67,7 +69,7 @@ public class TestKeepWordFilter extends BaseTokenTestCase {
|
|||
args = new HashMap<String, String>();
|
||||
args.put( "ignoreCase", "false" );
|
||||
factory.init( args );
|
||||
factory.inform( solrConfig.getResourceLoader() );
|
||||
factory.inform( loader );
|
||||
assertFalse(factory.isIgnoreCase());
|
||||
stream = factory.create(new WhitespaceTokenizer(new StringReader(input)));
|
||||
assertTokenStreamContents(stream, new String[] { "aaa" });
|
||||
|
|
|
@ -30,8 +30,11 @@ import org.apache.lucene.queryParser.ParseException;
|
|||
import org.apache.lucene.search.Query;
|
||||
import org.apache.solr.schema.IndexSchema;
|
||||
import org.apache.solr.search.SolrQueryParser;
|
||||
import org.apache.solr.util.AbstractSolrTestCase;
|
||||
|
||||
public class TestReversedWildcardFilterFactory extends BaseTokenTestCase {
|
||||
import static org.apache.solr.analysis.BaseTokenTestCase.*;
|
||||
|
||||
public class TestReversedWildcardFilterFactory extends AbstractSolrTestCase {
|
||||
Map<String,String> args = new HashMap<String, String>();
|
||||
ReversedWildcardFilterFactory factory = new ReversedWildcardFilterFactory();
|
||||
IndexSchema schema;
|
||||
|
|
|
@ -17,29 +17,24 @@ package org.apache.solr.analysis;
|
|||
*/
|
||||
|
||||
|
||||
import org.apache.solr.util.AbstractSolrTestCase;
|
||||
import org.apache.solr.common.ResourceLoader;
|
||||
import org.apache.solr.core.SolrResourceLoader;
|
||||
|
||||
import java.util.Set;
|
||||
import java.util.Map;
|
||||
import java.util.HashMap;
|
||||
|
||||
import junit.framework.TestCase;
|
||||
|
||||
|
||||
/**
|
||||
*
|
||||
*
|
||||
**/
|
||||
public class TestStopFilterFactory extends AbstractSolrTestCase{
|
||||
public String getSchemaFile() {
|
||||
return "schema-stop-keep.xml";
|
||||
}
|
||||
|
||||
public String getSolrConfigFile() {
|
||||
return "solrconfig.xml";
|
||||
}
|
||||
public class TestStopFilterFactory extends TestCase {
|
||||
|
||||
public void testInform() throws Exception {
|
||||
ResourceLoader loader = solrConfig.getResourceLoader();
|
||||
ResourceLoader loader = new SolrResourceLoader(null, null);
|
||||
assertTrue("loader is null and it shouldn't be", loader != null);
|
||||
StopFilterFactory factory = new StopFilterFactory();
|
||||
Map<String, String> args = new HashMap<String, String>();
|
||||
|
|
|
@ -22,9 +22,11 @@ import java.util.HashMap;
|
|||
import java.util.List;
|
||||
import java.util.Map;
|
||||
|
||||
import junit.framework.TestCase;
|
||||
|
||||
import org.apache.lucene.analysis.Token;
|
||||
|
||||
public class TestSynonymMap extends AnalysisTestCase {
|
||||
public class TestSynonymMap extends TestCase {
|
||||
|
||||
public void testInvalidMappingRules() throws Exception {
|
||||
SynonymMap synMap = new SynonymMap( true );
|
||||
|
|
|
@ -27,21 +27,25 @@ import org.apache.lucene.analysis.WhitespaceTokenizer;
|
|||
import org.apache.lucene.analysis.miscellaneous.SingleTokenTokenStream;
|
||||
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
|
||||
import org.apache.lucene.analysis.tokenattributes.TermAttribute;
|
||||
import org.apache.solr.util.AbstractSolrTestCase;
|
||||
|
||||
import static org.apache.solr.analysis.BaseTokenTestCase.*;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.io.Reader;
|
||||
import java.io.StringReader;
|
||||
import java.util.Arrays;
|
||||
import java.util.HashMap;
|
||||
import java.util.HashSet;
|
||||
import java.util.Map;
|
||||
|
||||
/**
|
||||
* New WordDelimiterFilter tests... most of the tests are in ConvertedLegacyTest
|
||||
*/
|
||||
public class TestWordDelimiterFilter extends BaseTokenTestCase {
|
||||
public class TestWordDelimiterFilter extends AbstractSolrTestCase {
|
||||
public String getSchemaFile() { return "solr/conf/schema.xml"; }
|
||||
public String getSolrConfigFile() { return "solr/conf/solrconfig.xml"; }
|
||||
|
||||
|
||||
public void posTst(String v1, String v2, String s1, String s2) {
|
||||
assertU(adoc("id", "42",
|
||||
"subword", v1,
|
||||
|
|
Loading…
Reference in New Issue