IK Analyzer 3.0中国語分詞器のリリース

Lucene全文検索に最適化されたクエリーアナライザIKQueryParser(著者らの吐血推奨);曖昧解析アルゴリズムを用いてクエリーキーワードの検索配列の組合せを最適化することで,Lucene検索のヒット率を極めて高めることができる.

/**
 * IK Analyzer Demo
 * @param args
 */
import java.io.IOException;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.LockObtainFailedException;
import org.apache.lucene.store.RAMDirectory;
//  IKAnalyzer3.0  
import org.wltea.analyzer.lucene.IKAnalyzer;
import org.wltea.analyzer.lucene.IKQueryParser;
import org.wltea.analyzer.lucene.IKSimilarity;

/**
 * @author linly
 *
 */
public class IKAnalyzerDemo {
	
	public static void main(String[] args){
		//Lucene Document   
		String fieldName = "text";
		 //    
		String text = "IK Analyzer                        。                   。";
		
		//   IKAnalyzer   
		Analyzer analyzer = new IKAnalyzer();
	 
		
		Directory directory = null;
		IndexWriter iwriter = null;
		IndexSearcher isearcher = null;
		try {
			//        
			directory = new RAMDirectory();	 
			iwriter = new IndexWriter(directory, analyzer, true , IndexWriter.MaxFieldLength.LIMITED);
			Document doc = new Document();
			doc.add(new Field(fieldName, text, Field.Store.YES, Field.Index.ANALYZED));
			iwriter.addDocument(doc);
			iwriter.close();
			
		    //         
			isearcher = new IndexSearcher(directory);			
			//       IKSimilarity      
			isearcher.setSimilarity(new IKSimilarity());
			
			String keyword = "       ";
			
			//  IKQueryParser       Query  
			Query query = IKQueryParser.parse(fieldName, keyword);
			
			//        5   
			TopDocs topDocs = isearcher.search(query , 5);
			System.out.println("  ：" + topDocs.totalHits);
			//    
			ScoreDoc[] scoreDocs = topDocs.scoreDocs;
			for (int i = 0; i < topDocs.totalHits; i++){
				Document targetDoc = isearcher.doc(scoreDocs[i].doc);
				System.out.println("  ：" + targetDoc.toString());
			}			
			
		} catch (CorruptIndexException e) {
			e.printStackTrace();
		} catch (LockObtainFailedException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		} finally{
			if(isearcher != null){
				try {
					isearcher.close();
				} catch (IOException e) {
					e.printStackTrace();
				}
			}
			if(directory != null){
				try {
					directory.close();
				} catch (IOException e) {
					e.printStackTrace();
				}
			}
		}
	}
}

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE properties SYSTEM "http://java.sun.com/dtd/properties.dtd">  
<properties>  
	<comment>IK Analyzer     </comment>
	<!--                -->
	<entry key="ext_dict">/mydict.dic ; /mypack/mydict2.dic ; /com/mycompany/dic/mydict3.dic ;</entry> 
</properties>