third_codes/elasticsearch-analysis-ik
1
0
Fork 0
Code Issues 1 Pull Requests Packages Projects Releases Wiki Activity

add ik tokenizers and remove some useless class[IkAnalyzer].

Browse Source
This commit is contained in:
piaolingxue 2013-06-17 11:45:39 +08:00
parent fb1aa9b9ad
commit 963fac4771
3 changed files with 35 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
src/main/java/org/elasticsearch/index/analysis/IkAnalysisBinderProcessor.java
View File

@ -12,4 +12,11 @@ public class IkAnalysisBinderProcessor extends AnalysisModule.AnalysisBinderProc
analyzersBindings.processAnalyzer("ik", IkAnalyzerProvider.class); analyzersBindings.processAnalyzer("ik", IkAnalyzerProvider.class);
super.processAnalyzers(analyzersBindings); super.processAnalyzers(analyzersBindings);
} }
@Override
public void processTokenizers(TokenizersBindings tokenizersBindings) {
tokenizersBindings.processTokenizer("ik", IkTokenizerFactory.class);
super.processTokenizers(tokenizersBindings);
}
} }

33
src/main/java/org/elasticsearch/index/analysis/IkAnalyzer.java
View File

@ -1,33 +0,0 @@
package org.elasticsearch.index.analysis;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.wltea.analyzer.lucene.IKTokenizer;
//import org.wltea.lucene.IKTokenizer;
import java.io.Reader;
public class IkAnalyzer extends Analyzer {
// private boolean isMaxWordLength = false;
// @Override public TokenStream tokenStream(String fieldName, Reader reader) {
// return new IKTokenizer(reader,true);
// }
public IkAnalyzer() {
super();
}
@Override
protected TokenStreamComponents createComponents(String s, Reader reader) {
// new TokenStreamComponents
Tokenizer tokenizer = new IKTokenizer(reader, true);
return new TokenStreamComponents(tokenizer, null); //To change body of implemented methods use File | Settings | File Templates.
}
// public boolean isMaxWordLength() {
// return isMaxWordLength;
// }
}

28
src/main/java/org/elasticsearch/index/analysis/IkTokenizerFactory.java Normal file
View File

@ -0,0 +1,28 @@
package org.elasticsearch.index.analysis;
import java.io.Reader;
import org.apache.lucene.analysis.Tokenizer;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.index.Index;
import org.wltea.analyzer.dic.Dictionary;
import org.wltea.analyzer.lucene.IKTokenizer;
public class IkTokenizerFactory extends AbstractTokenizerFactory {
private boolean useSmart = false;
public IkTokenizerFactory(Index index, Settings indexSettings, String name, Settings settings) {
super(index, indexSettings, name, settings);
Dictionary.getInstance().Init(indexSettings);
if (settings.get("use_smart", "true").equals("true")) {
useSmart = true;
}
}
@Override
public Tokenizer create(Reader reader) {
return new IKTokenizer(reader, useSmart);
}
}