honeymoose
/
OpenSearch
mirror of https://github.com/honeymoose/OpenSearch.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

add russian letter tokenizer

This commit is contained in:
kimchy 2010-08-24 23:11:22 +03:00
parent 49b4659322
commit d0f5bc3403
3 changed files with 48 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
modules/elasticsearch/src/main/java/org/elasticsearch/index/analysis/AbstractTokenizerFactory.java
View File

@ -25,7 +25,7 @@ import org.elasticsearch.index.Index;
import org.elasticsearch.index.settings.IndexSettings;
/**
* @author kimchy (Shay Banon)
* @author kimchy (shay.banon)
*/
public abstract class AbstractTokenizerFactory extends AbstractIndexComponent implements TokenizerFactory {

4
modules/elasticsearch/src/main/java/org/elasticsearch/index/analysis/AnalysisModule.java
View File

@ -305,6 +305,8 @@ public class AnalysisModule extends AbstractModule {
tokenizersBindings.processTokenizer("letter", LetterTokenizerFactory.class);
tokenizersBindings.processTokenizer("lowercase", LowerCaseTokenizerFactory.class);
tokenizersBindings.processTokenizer("whitespace", WhitespaceTokenizerFactory.class);
tokenizersBindings.processTokenizer("russian_letter", RussianLetterTokenizerFactory.class);
tokenizersBindings.processTokenizer("russianLetter", RussianLetterTokenizerFactory.class);
}
@Override public void processAnalyzers(AnalyzersBindings analyzersBindings) {
@ -347,7 +349,7 @@ public class AnalysisModule extends AbstractModule {
analyzersBindings.processAnalyzer("arabic", ArabicAnalyzerProvider.class);
analyzersBindings.processAnalyzer("brazilian", BrazilianAnalyzerProvider.class);
analyzersBindings.processAnalyzer("chinese", ChineseAnalyzerProvider.class);
analyzersBindings.processAnalyzer("cjk", ChineseAnalyzerProvider.class);
analyzersBindings.processAnalyzer("cjk", CjkAnalyzerProvider.class);
analyzersBindings.processAnalyzer("czech", CzechAnalyzerProvider.class);
analyzersBindings.processAnalyzer("dutch", DutchAnalyzerProvider.class);
analyzersBindings.processAnalyzer("french", FrenchAnalyzerProvider.class);

44
modules/elasticsearch/src/main/java/org/elasticsearch/index/analysis/RussianLetterTokenizerFactory.java Normal file
View File

@ -0,0 +1,44 @@
/*
* Licensed to Elastic Search and Shay Banon under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. Elastic Search 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.elasticsearch.index.analysis;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.ru.RussianLetterTokenizer;
import org.elasticsearch.common.inject.Inject;
import org.elasticsearch.common.inject.assistedinject.Assisted;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.index.Index;
import org.elasticsearch.index.settings.IndexSettings;
import java.io.Reader;
/**
* @author kimchy (shay.banon)
*/
public class RussianLetterTokenizerFactory extends AbstractTokenizerFactory {
@Inject public RussianLetterTokenizerFactory(Index index, @IndexSettings Settings indexSettings, @Assisted String name, @Assisted Settings settings) {
super(index, indexSettings, name);
}
@Override public Tokenizer create(Reader reader) {
return new RussianLetterTokenizer(reader);
}
}