lucene in action_index and search

在这里给大家来一些关于lucene in action的一些东东

你可以到:http://lucene.apache.org/ 了解更新，更全的关于lucene的信息。

下面我做的demo，分享给大家：

项目结构：

运行Index时，Run Configurations：

[两个参数之间有空格]

args[0] = "C:\Users\hongjie\Desktop\hongten_temp\hongten_index";

args[1] = "C:\Users\hongjie\Desktop\hongten_temp\lucene-3.5.0";

运行效果：

运行Searcher时，Run Configurations：

[两个参数之间有空格]

args[0] = "C:\Users\hongjie\Desktop\hongten_temp\hongten_index";

args[1] = "cnhances";

运行效果：

============================================================

代码部分：

============================================================

/lucene/src/com/b510/index/Indexer.java

/**
 * 
 */
package com.b510.index;

import java.io.File;
import java.io.FileFilter;
import java.io.FileReader;

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;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

/**
 * 建立索引
 * 
 * @author hongten(hongtenzone@foxmail.com)<br>
 * @date 2013-4-5
 */
public class Indexer {

    public static void main(String[] args) throws Exception {
        if (args.length != 2) {
            throw new IllegalArgumentException("Usage: java " + Indexer.class.getName() + " <index dir><data dir>");
        }
        // 在指定目录创建索引
        String indexDir = args[0];
        String dataDir = args[1];

        long start = System.currentTimeMillis();
        Indexer index = new Indexer(indexDir);
        int numIndexed;
        try {
            numIndexed = index.index(dataDir, new TextFilesFilter());
        } finally {
            index.close();
        }
        long end = System.currentTimeMillis();

        System.out.println("indexing " + numIndexed + " files took " + (end - start) + " millseconds!");
    }

    private IndexWriter writer;

    @SuppressWarnings("deprecation")
    public Indexer(String indexDir) throws Exception {
        Directory dir = FSDirectory.open(new File(indexDir));
        // create lucene index writer
        writer = new IndexWriter(dir, new StandardAnalyzer(Version.LUCENE_35), true, IndexWriter.MaxFieldLength.UNLIMITED);
    }

    /**
     * close the IndexWriter
     * 
     * @throws Exception
     */
    public void close() throws Exception {
        writer.close();
    }

    /**
     * 返回被索引文件数
     * 
     * @param dataDir
     *            文件目录
     * @param filter
     * @return
     * @throws Exception
     */
    public int index(String dataDir, FileFilter filter) throws Exception {
        File[] files = new File(dataDir).listFiles();

        for (File f : files) {
            if (!f.isDirectory() && !f.isHidden() && f.exists() && f.canRead() && (filter == null || filter.accept(f))) {
                indexFile(f);
            }
        }
        // 返回被索引的文档数目
        return writer.numDocs();
    }

    /**
     * 向lucene中添加文档
     * 
     * @param f
     *            文档
     * @throws Exception
     */
    private void indexFile(File f) throws Exception {
        System.out.println("Indexing " + f.getCanonicalPath());
        Document doc = getDocument(f);
        writer.addDocument(doc);
    }

    /**
     * 添加索引
     * 
     * @param f
     *            被索引的文件
     * @return
     * @throws Exception
     */
    protected Document getDocument(File f) throws Exception {
        Document doc = new Document();
        doc.add(new Field("contents", new FileReader(f)));
        doc.add(new Field("filename", f.getName(), Field.Store.YES, Field.Index.NOT_ANALYZED));
        doc.add(new Field("fullpath", f.getCanonicalPath(), Field.Store.YES, Field.Index.NOT_ANALYZED));
        return doc;
    }

    /**
     * 只索引.txt文件，采用FileFilter
     * 
     * @author hongten(hongtenzone@foxmail.com)<br>
     * @date 2013-4-5
     */
    private static class TextFilesFilter implements FileFilter {
        @Override
        public boolean accept(File pathname) {
            return pathname.getName().toLowerCase().endsWith(".txt");
        }
    }

}

/lucene/src/com/b510/search/Searcher.java

/**
 * 
 */
package com.b510.search;

import java.io.File;
import java.io.IOException;

import org.apache.lucene.analysis.standard.StandardAnalyzer;
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.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

import com.b510.index.Indexer;

/**
 * 搜索功能
 * @author hongten(hongtenzone@foxmail.com)<br>
 * @date 2013-4-5
 */
public class Searcher {

    public static void main(String[] args) throws IllegalArgumentException, IOException, ParseException {
        if (args.length != 2) {
            throw new IllegalArgumentException("Usage: java " + Indexer.class.getName() + " <index dir><data dir>");
        }
        // 在指定目录创建索引
        String indexDir = args[0];
        String q = args[1];

        search(indexDir, q);
    }

    /**
     * 搜索
     * @param indexDir 搜索目录
     * @param q 关键字
     * @throws IOException
     * @throws ParseException
     */
    public static void search(String indexDir, String q) throws IOException, ParseException {
        Directory dir = FSDirectory.open(new File(indexDir));
        IndexSearcher is = new IndexSearcher(dir);
        
        QueryParser parser = new QueryParser(Version.LUCENE_35,"contents",new StandardAnalyzer(Version.LUCENE_35));
        Query query = parser.parse(q);
        long start = System.currentTimeMillis();
        TopDocs hits = is.search(query, 10);
        long end = System.currentTimeMillis();
        
        System.out.println("Found "+hits.totalHits + " document(s) (in " + (end - start) +" millsecondes) that matched query '"+ q+"':");
        
        for(ScoreDoc scoreDoc : hits.scoreDocs){
            Document doc = is.doc(scoreDoc.doc);
            System.out.println(doc.get("fullpath"));
        }
        
        is.close();
    }
}