一个简单的lucene例子

package com.java_min.test;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriter.MaxFieldLength;
import org.apache.lucene.queryParser.MultiFieldQueryParser;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Filter;
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.FSDirectory;
import org.junit.Test;

import com.java_min.util.File2DocumentUtils;

public class HelloWorld {

 private String filePath = "D://workspace//luceneDemo//luceneDateSource//test.txt";
 private String indexPath = "D://workspace//luceneDemo//luceneIndex";
 private Analyzer analyzer = new StandardAnalyzer();
 
 /**
  *
  * @throws Exception
  * Administrator  Jun 15, 2010
  *
  * 创建索引
  * IndexWriter是用来操作(增、删、改)索引库的
  *
  */
 @Test
 public void createIndex() throws Exception{
  
  /**
   * 文件系统路径(将索引放入磁盘)
   */
  Directory directory = FSDirectory.getDirectory(indexPath);
  
  /**
   * 内存路径(将索引放入内存)
   */
  //Directory directory = new RAMDirectory();
  
  Document doc = File2DocumentUtils.file2Document(filePath);
  
  IndexWriter indexWriter = new IndexWriter(directory,analyzer,true,MaxFieldLength.LIMITED);
  indexWriter.addDocument(doc);
  indexWriter.close();
 }
 
 //搜索
 @Test
 public void searchWord() throws Exception {
  String queryStr = "中国足球";
  
  //1.把要搜索的文本解析为Query
  String[] fields = {"name","context"};
  QueryParser queryParser = new MultiFieldQueryParser(fields,analyzer);
  Query query = queryParser.parse(queryStr);
  
  //2.进行查询
  IndexSearcher indexSearcher = new IndexSearcher(indexPath);
  Filter filter = null;
  TopDocs topDocs = indexSearcher.search(query, filter,100000);
  System.out.println("当前共搜索到【"+topDocs.totalHits+"】条匹配结果");
  
  //3.打印结果
  for(ScoreDoc scoreDoc:topDocs.scoreDocs){
   int doc = scoreDoc.doc; //文档内部编号
   Document document = indexSearcher.doc(doc); //根据编号取出相应文档
   File2DocumentUtils.printDocumentInfo(document); //打印出文档信息
  }
 }
}

 

 

 

 

package com.java_min.util;

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

import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.NumberTools;
import org.apache.lucene.document.Field.Index;
import org.apache.lucene.document.Field.Store;

public class File2DocumentUtils {

 /**
  *
  * @param path
  * @return
  * Administrator  Jun 16, 2010
  *
  * file到document的转换
  */
 public static Document file2Document(String path){

  File file = new File(path);
  
  Document document = new Document();
  document.add(new Field("name",file.getName(),Store.YES,Index.ANALYZED));
  document.add(new Field("context",getFileContext(file),Store.YES,Index.ANALYZED));
  document.add(new Field("size", NumberTools.longToString(file.length()),Store.YES,Index.NOT_ANALYZED));
  document.add(new Field("path",file.getAbsolutePath(),Store.YES,Index.NO));
  
  return document;
 }
 
 /**
  *
  * @param doc
  * Administrator  Jun 16, 2010
  *
  * document到file的转换
  */
 public static void document2File(Document doc){
  
 }
 
 /**
  *
  * @param file
  * @return
  * Administrator  Jun 16, 2010
  *
  * 得到文件内容
  */
 public static String getFileContext(File file){
  StringBuffer context = new StringBuffer();
  try {
   BufferedReader bf = new BufferedReader(new InputStreamReader(new FileInputStream(file)));
   for(String line = null;(line = bf.readLine()) != null;){
    context.append(line).append("/n");
   }
  } catch (Exception e) {
   throw new RuntimeException(e);
  }
  return context.toString() ;
 }
 
 /**
  *
  * @param document
  * Administrator  Jun 16, 2010
  *
  * 打印document
  *
  * 获取name属性的值的两种方法：
  * 1. Field f = doc.getField("name");
  *    f.stringValue();
  *  
  * 2. doc.get("name")
  */
 public static void printDocumentInfo(Document document){
  System.out.println("文件名为--------------" + document.get("name"));
  System.out.println("文件内容为-------------" + document.get("context"));
  System.out.println("文件大小为-------------" + NumberTools.stringToLong(document.get("size")));
  System.out.println("文件路径为-------------" + document.get("path"));
 }
}