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

LUCENE-4044: get all lucene tests passing 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/branches/lucene2510@1364891 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Robert Muir 2012-07-24 05:11:20 +00:00
parent 5cc38490d0
commit e7ff3048ce
7 changed files with 67 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/StringMockResourceLoader.java Normal file
View File

@ -0,0 +1,53 @@
package org.apache.lucene.analysis.ja;
/*
* 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.
*/
import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.Arrays;
import java.util.List;
import org.apache.lucene.analysis.util.ResourceLoader;
/** Fake resource loader for tests: works if you want to fake reading a single file */
class StringMockResourceLoader implements ResourceLoader {
String text;
public StringMockResourceLoader(String text) {
this.text = text;
}
public List<String> getLines(String resource) throws IOException {
return Arrays.asList(text.split("\n"));
}
// TODO: do this subpackages thing... wtf is that?
public <T> T newInstance(String cname, Class<T> expectedType, String... subpackages) {
try {
Class<? extends T> clazz = Class.forName(cname).asSubclass(expectedType);
return clazz.newInstance();
} catch (Exception e) {
throw new RuntimeException(e);
}
}
public InputStream openResource(String resource) throws IOException {
return new ByteArrayInputStream(text.getBytes("UTF-8"));
}
}

3
lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/TestJapaneseBaseFormFilterFactory.java
View File

@ -24,7 +24,6 @@ import java.util.Map;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.TokenStream;
import org.apache.solr.core.SolrResourceLoader;
/**
* Simple tests for {@link JapaneseBaseFormFilterFactory}
@ -35,7 +34,7 @@ public class TestJapaneseBaseFormFilterFactory extends BaseTokenStreamTestCase {
tokenizerFactory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
Map<String, String> args = Collections.emptyMap();
tokenizerFactory.init(args);
tokenizerFactory.inform(new SolrResourceLoader(null, null));
tokenizerFactory.inform(new StringMockResourceLoader(""));
TokenStream ts = tokenizerFactory.create(new StringReader("それはまだ実験段階にあります"));
JapaneseBaseFormFilterFactory factory = new JapaneseBaseFormFilterFactory();
ts = factory.create(ts);

9
lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/TestJapaneseIterationMarkCharFilterFactory.java
View File

@ -21,7 +21,6 @@ import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.CharFilter;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.solr.core.SolrResourceLoader;
import java.io.IOException;
import java.io.StringReader;
@ -30,7 +29,7 @@ import java.util.HashMap;
import java.util.Map;
/**
* Simple tests for {@link org.apache.solr.analysis.JapaneseIterationMarkCharFilterFactory}
* Simple tests for {@link JapaneseIterationMarkCharFilterFactory}
*/
public class TestJapaneseIterationMarkCharFilterFactory extends BaseTokenStreamTestCase {
@ -46,7 +45,7 @@ public class TestJapaneseIterationMarkCharFilterFactory extends BaseTokenStreamT
JapaneseTokenizerFactory tokenizerFactory = new JapaneseTokenizerFactory();
Map<String, String> tokenizerArgs = Collections.emptyMap();
tokenizerFactory.init(tokenizerArgs);
tokenizerFactory.inform(new SolrResourceLoader(null, null));
tokenizerFactory.inform(new StringMockResourceLoader(""));
JapaneseIterationMarkCharFilterFactory filterFactory = new JapaneseIterationMarkCharFilterFactory();
Map<String, String> filterArgs = Collections.emptyMap();
@ -63,7 +62,7 @@ public class TestJapaneseIterationMarkCharFilterFactory extends BaseTokenStreamT
JapaneseTokenizerFactory tokenizerFactory = new JapaneseTokenizerFactory();
Map<String, String> tokenizerArgs = Collections.emptyMap();
tokenizerFactory.init(tokenizerArgs);
tokenizerFactory.inform(new SolrResourceLoader(null, null));
tokenizerFactory.inform(new StringMockResourceLoader(""));
JapaneseIterationMarkCharFilterFactory filterFactory = new JapaneseIterationMarkCharFilterFactory();
Map<String, String> filterArgs = new HashMap<String, String>();
@ -82,7 +81,7 @@ public class TestJapaneseIterationMarkCharFilterFactory extends BaseTokenStreamT
JapaneseTokenizerFactory tokenizerFactory = new JapaneseTokenizerFactory();
Map<String, String> tokenizerArgs = Collections.emptyMap();
tokenizerFactory.init(tokenizerArgs);
tokenizerFactory.inform(new SolrResourceLoader(null, null));
tokenizerFactory.inform(new StringMockResourceLoader(""));
JapaneseIterationMarkCharFilterFactory filterFactory = new JapaneseIterationMarkCharFilterFactory();
Map<String, String> filterArgs = new HashMap<String, String>();

3
lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/TestJapaneseKatakanaStemFilterFactory.java
View File

@ -19,7 +19,6 @@ package org.apache.lucene.analysis.ja;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.TokenStream;
import org.apache.solr.core.SolrResourceLoader;
import java.io.IOException;
import java.io.StringReader;
@ -34,7 +33,7 @@ public class TestJapaneseKatakanaStemFilterFactory extends BaseTokenStreamTestCa
JapaneseTokenizerFactory tokenizerFactory = new JapaneseTokenizerFactory();
Map<String, String> tokenizerArgs = Collections.emptyMap();
tokenizerFactory.init(tokenizerArgs);
tokenizerFactory.inform(new SolrResourceLoader(null, null));
tokenizerFactory.inform(new StringMockResourceLoader(""));
TokenStream tokenStream = tokenizerFactory.create(
new StringReader("明後日パーティーに行く予定がある。図書館で資料をコピーしました。")
);

5
lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/TestJapanesePartOfSpeechStopFilterFactory.java
View File

@ -25,7 +25,6 @@ import java.util.Map;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.TokenStream;
import org.apache.solr.core.SolrResourceLoader;
/**
* Simple tests for {@link JapanesePartOfSpeechStopFilterFactory}
@ -40,14 +39,14 @@ public class TestJapanesePartOfSpeechStopFilterFactory extends BaseTokenStreamTe
tokenizerFactory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
Map<String, String> tokenizerArgs = Collections.emptyMap();
tokenizerFactory.init(tokenizerArgs);
tokenizerFactory.inform(new SolrResourceLoader(null, null));
tokenizerFactory.inform(new StringMockResourceLoader(""));
TokenStream ts = tokenizerFactory.create(new StringReader("私は制限スピードを超える。"));
JapanesePartOfSpeechStopFilterFactory factory = new JapanesePartOfSpeechStopFilterFactory();
Map<String,String> args = new HashMap<String,String>();
args.put("tags", "stoptags.txt");
factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
factory.init(args);
factory.inform(new StringMockSolrResourceLoader(tags));
factory.inform(new StringMockResourceLoader(tags));
ts = factory.create(ts);
assertTokenStreamContents(ts,
new String[] { "私", "は", "制限", "スピード", "を" }

3
lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/TestJapaneseReadingFormFilterFactory.java
View File

@ -19,7 +19,6 @@ package org.apache.lucene.analysis.ja;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.TokenStream;
import org.apache.solr.core.SolrResourceLoader;
import java.io.IOException;
import java.io.StringReader;
@ -34,7 +33,7 @@ public class TestJapaneseReadingFormFilterFactory extends BaseTokenStreamTestCas
JapaneseTokenizerFactory tokenizerFactory = new JapaneseTokenizerFactory();
Map<String, String> args = Collections.emptyMap();
tokenizerFactory.init(args);
tokenizerFactory.inform(new SolrResourceLoader(null, null));
tokenizerFactory.inform(new StringMockResourceLoader(""));
TokenStream tokenStream = tokenizerFactory.create(new StringReader("先ほどベルリンから来ました。"));
JapaneseReadingFormFilterFactory filterFactory = new JapaneseReadingFormFilterFactory();
assertTokenStreamContents(filterFactory.create(tokenStream),

11
lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/TestJapaneseTokenizerFactory.java
View File

@ -25,7 +25,6 @@ import java.util.Map;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.TokenStream;
import org.apache.solr.core.SolrResourceLoader;
/**
* Simple tests for {@link JapaneseTokenizerFactory}
@ -36,7 +35,7 @@ public class TestJapaneseTokenizerFactory extends BaseTokenStreamTestCase {
factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
Map<String, String> args = Collections.emptyMap();
factory.init(args);
factory.inform(new SolrResourceLoader(null, null));
factory.inform(new StringMockResourceLoader(""));
TokenStream ts = factory.create(new StringReader("これは本ではない"));
assertTokenStreamContents(ts,
new String[] { "これ", "は", "本", "で", "は", "ない" },
@ -53,7 +52,7 @@ public class TestJapaneseTokenizerFactory extends BaseTokenStreamTestCase {
factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
Map<String, String> args = Collections.emptyMap();
factory.init(args);
factory.inform(new SolrResourceLoader(null, null));
factory.inform(new StringMockResourceLoader(""));
TokenStream ts = factory.create(new StringReader("シニアソフトウェアエンジニア"));
assertTokenStreamContents(ts,
new String[] { "シニア", "シニアソフトウェアエンジニア", "ソフトウェア", "エンジニア" }
@ -68,7 +67,7 @@ public class TestJapaneseTokenizerFactory extends BaseTokenStreamTestCase {
Map<String,String> args = new HashMap<String,String>();
args.put("mode", "normal");
factory.init(args);
factory.inform(new SolrResourceLoader(null, null));
factory.inform(new StringMockResourceLoader(""));
TokenStream ts = factory.create(new StringReader("シニアソフトウェアエンジニア"));
assertTokenStreamContents(ts,
new String[] { "シニアソフトウェアエンジニア" }
@ -89,7 +88,7 @@ public class TestJapaneseTokenizerFactory extends BaseTokenStreamTestCase {
Map<String,String> args = new HashMap<String,String>();
args.put("userDictionary", "userdict.txt");
factory.init(args);
factory.inform(new StringMockSolrResourceLoader(userDict));
factory.inform(new StringMockResourceLoader(userDict));
TokenStream ts = factory.create(new StringReader("関西国際空港に行った"));
assertTokenStreamContents(ts,
new String[] { "関西", "国際", "空港", "に", "行っ", "た" }
@ -104,7 +103,7 @@ public class TestJapaneseTokenizerFactory extends BaseTokenStreamTestCase {
Map<String,String> args = new HashMap<String,String>();
args.put("discardPunctuation", "false");
factory.init(args);
factory.inform(new SolrResourceLoader(null, null));
factory.inform(new StringMockResourceLoader(""));
TokenStream ts = factory.create(
new StringReader("今ノルウェーにいますが、来週の頭日本に戻ります。楽しみにしています！お寿司が食べたいな。。。")
);