Lucene中文分词

package com.fxr.test2;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;

import net.paoding.analysis.analyzer.PaodingAnalyzer;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

public class TestFileIndex {

	/**
	 * ??????ж????????????
	 * @throws IOException
	 */
	public static void main(String[] args) throws IOException {
		String dataDir = "f:/lucenedata";
		String indexDir = "f:/ChinesLuceneIndex";
		File [] files = new File(dataDir).listFiles();
		System.out.println(files.length);
		Analyzer analyzer = new PaodingAnalyzer();
		Directory directory = FSDirectory.getDirectory(indexDir);
		IndexWriter indexWriter = new IndexWriter(directory,analyzer,true,IndexWriter.MaxFieldLength.LIMITED);
		for(int i=0;i<files.length;i++){
			StringBuffer strBuffer = new StringBuffer();
			String line = "";
			FileInputStream is = new FileInputStream(files[i].getCanonicalFile());
			BufferedReader reader = new BufferedReader(new InputStreamReader(is));
			System.out.println(files[i].getName());
			line = reader.readLine();
			while(line != null){
				strBuffer.append(line);
				strBuffer.append("\n");
				line = reader.readLine();
			}
			Document document = new Document();
			document.add(new Field("fileName",files[i].getName(),Field.Store.YES,Field.Index.ANALYZED));
			document.add(new Field("contents",strBuffer.toString(),Field.Store.YES,Field.Index.ANALYZED));
			indexWriter.addDocument(document);
			is.close();
			reader.close();
			System.out.println(strBuffer.toString());

		}
		indexWriter.close();
		directory.close();

	}

}

package com.fxr.test2;

import java.io.IOException;

import org.apache.lucene.document.Document;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

public class TestFileSearch {

	/**
	 * @param args
	 * @throws IOException
	 */
	public static void main(String[] args) throws IOException {
		String indexDir = "f:/ChinesLuceneIndex";
		Directory directory = FSDirectory.getDirectory(indexDir);
		IndexSearcher indexSearcher = new IndexSearcher(directory);
		ScoreDoc [] hits = null;
		Term term = new Term("contents","中国");
		TermQuery query = new TermQuery(term);
		TopDocs topDocs = indexSearcher.search(query, 100);
		hits = topDocs.scoreDocs;
		for(int i=0;i<hits.length;i++){
			Document doc = indexSearcher.doc(hits[i].doc);
			 System.out.print(hits[i].score+" ");
				System.out.println(doc.get("fileName")+" ");
				System.out.println(doc.get("contents")+" ");

		}

		indexSearcher.close();
		directory.close();

	}

}

package com.fxr.test2;

import java.io.IOException;

import net.paoding.analysis.analyzer.PaodingAnalyzer;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

public class TestIndex {

	/**
	 * 中文分词的效果
	 * @throws IOException
	 */
	public static void main(String[] args) throws IOException {
		String [] ids = {"1","2","3","4"};
		String [] names = {"张三","李逵","zhangsan","zhangsun"};
		String [] addresses = {"居住在北京","居住在南京","北京海淀","nanning"};
		String [] birthdays = {"19820720","19840203","19770409","19830130"};
		Analyzer analyzer = new PaodingAnalyzer();
		String indexDir = "f:/ChinesLuceneIndex";
		Directory directory = FSDirectory.getDirectory(indexDir);
		//true表示创建或者覆盖当前的索引，FALSE表示当前的索引进行追加
		IndexWriter indexWriter = new IndexWriter(directory,analyzer,true,IndexWriter.MaxFieldLength.LIMITED);
		for(int i=0;i<ids.length;i++){
			Document document = new Document();
			document.add(new Field("id",ids[i],Field.Store.YES,Field.Index.ANALYZED));
			document.add(new Field("name",names[i],Field.Store.YES,Field.Index.ANALYZED));
			document.add(new Field("address",addresses[i],Field.Store.YES,Field.Index.ANALYZED));
			document.add(new Field("birthday",birthdays[i],Field.Store.YES,Field.Index.ANALYZED));
			indexWriter.addDocument(document);
		}
		indexWriter.optimize();
		indexWriter.close();
		System.out.println("ok!");

	}

}
============================================
package com.fxr.test2;

import java.io.IOException;

import net.paoding.analysis.analyzer.PaodingAnalyzer;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocCollector;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

public class TestQueryParser {

	/**
	 * @param args
	 * @throws IOException
	 * @throws ParseException
	 */
	public static void main(String[] args) throws IOException, ParseException {
		String indexDir = "f:/ChinesLuceneIndex";
		Analyzer analyzer = new PaodingAnalyzer();
		Directory directory = FSDirectory.getDirectory(indexDir);
		IndexSearcher indexSearcher = new IndexSearcher(directory);
		ScoreDoc [] hits = null;
		QueryParser parser = new QueryParser("address",analyzer);
		Query query = parser.parse("(海淀 OR 居住)AND北京");
		TopDocCollector topdoc = new TopDocCollector(100);
		indexSearcher.search(query,topdoc);
		hits = topdoc.topDocs().scoreDocs;
		for(int i=0;i<hits.length;i++){
			Document doc=indexSearcher.doc(hits[i].doc);
		    System.out.print(hits[i].score+" ");
			System.out.print(doc.get("id")+" ");
			System.out.print(doc.get("name")+" ");
			System.out.print(doc.get("address")+" ");
			System.out.println(doc.get("birthday")+" ");
		}
		indexSearcher.close();
		directory.close();

	}

}
==========================================
package com.fxr.test2;

import java.io.IOException;

import org.apache.lucene.document.Document;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.PrefixQuery;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.WildcardQuery;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

public class TestSearch {

	/**
	 * @param args
	 * @throws IOException
	 */
	public static void main(String[] args) throws IOException {
		String indexDir = "f:/ChinesLuceneIndex";
		Directory dir = FSDirectory.getDirectory(indexDir);
		IndexSearcher indexSearcher = new IndexSearcher(dir);
		ScoreDoc [] hits = null;
		Term term = new Term("address","*海*");
		//TermQuery termQuery = new TermQuery(term);
		//PrefixQuery prefixQuery = new PrefixQuery(term);
		WildcardQuery wildcardQuery = new WildcardQuery(term);
		TopDocs topDocs = indexSearcher.search(wildcardQuery, 100);
		hits = topDocs.scoreDocs;
		for(int i=0;i<hits.length;i++){
			Document doc = indexSearcher.doc(hits[i].doc);
			System.out.print(hits[i].score);
			System.out.print(doc.get("id")+" ");
			System.out.print(doc.get("name")+" ");
			System.out.print(doc.get("address")+" ");
			System.out.println(doc.get("birthday")+" ");
		}
		indexSearcher.close();
		dir.close();

	}

}