Lucene之初

Lucene之开山篇

功能: 实现为本地磁盘文件（文本类型文件）建索引，并提供查询功能!

说明: Lucene 2.0.0 http://lucene.apache.org/

作者: 寒江风

日期: 2006-08-08

 

㊣ Constants

 

package edu.whu.mylucene;

 

/**

 * 常量定义

 * @author bbflyerwww

 * @date 2006 - 08 - 08

 */

 

public class Constants {

 

    // 要索引文件的存放路径

    public final static String INDEX_FILE_PATH = "E://FILES";

 

    // 索引存放的位置

    public final static String INDEX_STORE_PATH = "E://INDEX";

 

}

 

㊣ ExIndexer

 

package edu.whu.mylucene;

 

import java.io.BufferedReader;

import java.io.File;

import java.io.FileInputStream;

import java.io.IOException;

import java.io.InputStreamReader;

import java.io.Reader;

import java.util.Date;

 

import org.apache.lucene.analysis.Analyzer;

import org.apache.lucene.analysis.standard.StandardAnalyzer;

import org.apache.lucene.document.Document;

import org.apache.lucene.document.Field;

import org.apache.lucene.index.IndexWriter;

 

/**

 * 为本地磁盘目录的文件建索引

 * @author bbflyerwww

 * @date 2006 - 08 - 08

 */

 

public class ExIndexer {

 

    // 索引器

    private IndexWriter writer = null;

 

    public ExIndexer() {

    }

 

    public void init() {

       // 初始化索引器

       try {

           Analyzer analyzer = new StandardAnalyzer();

           writer = new IndexWriter(Constants.INDEX_STORE_PATH, analyzer, true);

           writer.setMergeFactor(50);

           writer.setMaxMergeDocs(5000);

       } catch (IOException ioe) {

           ioe.printStackTrace();

           System.exit(-1);

       }

    }

 

    public void index(File file) {

       // 为File建索引 （文件夹 文件）

       if (!file.exists()) {

           return;

       }

       try {

           if (file.isDirectory()) {

              if (!file.canRead()) {

                  return;

              }

              File[] files = file.listFiles();

              for (int i = 0; i < files.length; i++) {

                  index(files[i]);

              }

           } else {

              if (file.isHidden() || !file.canRead()) {

                  return;

              }

              System.out.println("Indexing " + file.getPath());

              String path = file.getCanonicalPath();

              String date = new Date(file.lastModified()).toString();

              Reader reader = new BufferedReader(new InputStreamReader(new FileInputStream(file)));

              Document doc = new Document();

              doc.add(new Field("path", path, Field.Store.YES, Field.Index.UN_TOKENIZED));

              doc.add(new Field("modified", date, Field.Store.YES, Field.Index.UN_TOKENIZED));

               doc.add(new Field("contents", reader));

              writer.addDocument(doc);

           }

       } catch (IOException ioe) {

           ioe.printStackTrace();

       }

    }

 

    public void close() {

       // 优化索引 关闭索引器

       try {

           writer.optimize();

           writer.close();

       } catch (IOException ioe) {

           ioe.printStackTrace();

           System.exit(-1);

       }

    }

 

    public static void main(String[] args) {

       long start = System.currentTimeMillis();

       ExIndexer ex = new ExIndexer();

       ex.init();

       ex.index(new File(Constants.INDEX_FILE_PATH));

       ex.close();

       long end = System.currentTimeMillis();

       System.out.println("Cost : " + (end - start) + " ms");

    }

 

}

 

㊣ ExSearcher

 

package edu.whu.mylucene;

 

import java.io.IOException;

 

import org.apache.lucene.analysis.Analyzer;

import org.apache.lucene.analysis.standard.StandardAnalyzer;

import org.apache.lucene.document.Document;

import org.apache.lucene.index.IndexReader;

import org.apache.lucene.queryParser.ParseException;

import org.apache.lucene.queryParser.QueryParser;

import org.apache.lucene.search.Hits;

import org.apache.lucene.search.IndexSearcher;

import org.apache.lucene.search.Query;

 

/**

 * 检索工具

 * @author bbflyerwww

 * @date 2006 - 08 - 08

 */

 

public class ExSearcher {

   

    // 索引查询器

    private IndexSearcher searcher = null;

   

    // 索引查询解析器

    private QueryParser parser = null;

   

    public ExSearcher() {

    }

   

    public void init() {

       // 初始化查询器和查询解析器

       try {

           IndexReader reader = IndexReader.open(Constants.INDEX_STORE_PATH);

           searcher = new IndexSearcher(reader);

           Analyzer analyzer = new StandardAnalyzer();

           parser = new QueryParser("contents", analyzer);

       } catch (IOException ioe) {

           ioe.printStackTrace();

           System.exit(-1);

       }

    }

   

    public Hits search(String keyword) {

       // 查询关键字

       System.out.println("正在检索关键字 : " + keyword);

       Hits hits = null;

       try {

           Query query = parser.parse(keyword);

           hits = searcher.search(query);

       } catch (IOException ioe) {

           ioe.printStackTrace();

       } catch (ParseException pe) {

           pe.printStackTrace();

       }

       return hits;

    }

   

    public void close() {

       // 关闭索引查询器

       try {

           searcher.close();

       } catch (IOException ioe) {

           ioe.printStackTrace();

           System.exit(-1);

       }

    }

   

    public static void main(String[] args) {

       ExSearcher ex = new ExSearcher();

       ex.init();

       try {

           Hits hits = ex.search("table");

           int k = hits.length();

           for (int i = 0; i < k; i++) {

              Document doc = hits.doc(i);

              System.out.println(i + "/t" + hits.score(i) + "/t" + doc.get("path"));

           }

       } catch (IOException ioe) {

           ioe.printStackTrace();

       }

       ex.close();

    }

   

}