lucene4入门（2）搜索

欢迎转载http://www.cnblogs.com/shizhongtao/p/3440479.html

接着上一篇，这里继续搜索，对于搜索和创建一样，首先你要确定搜索位置，然后用规定的类来读取。还要注意一点，确定分词器，因为不同的分词器所创建的分词规则不同。上篇我使用的是默认的分词器，这里我也先不管分词器。为了方便阅读，代码就全部粘上。

package com.bing.test;

import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileReader;
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.document.Field.Store;
import org.apache.lucene.document.FieldType;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.queryparser.classic.ParseException;
import org.apache.lucene.queryparser.classic.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;

/**
 * @author bingyulei
 * 
 */
public class HelloLucene
{

    Directory directory = null;
    Document doc;
    IndexWriter writer = null;

    /**
     * 
     * @param indexWriterPath
     *            索引创建路径
     * @param filePath
     *            读取文件路径
     */
    public void createIndex(String indexWriterPath, String filePath)
    {

        // 创建indexwriter
        Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_45);// 设置标准分词器
                                                                    // ,默认是一元分词
        IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_45,
                analyzer);// 设置IndexWriterConfig

        try
        {
            // 创建directory
            // directory=RAMDirectory();//创建在内存中
            // 创建在硬盘上
            directory = FSDirectory.open(new File(indexWriterPath));// 打开存放索引的路径
            writer = new IndexWriter(directory, iwc);

            // 为document添加field
            addFile(writer, filePath);

            System.out.println("添加成功");
        } catch (IOException e)
        {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }

    }

    private void addFile(IndexWriter writer, String filePath)
    {
        File f = new File(filePath);
        FieldType ft = new FieldType();
        ft.setIndexed(true);// 索引
        ft.setStored(true);// 存储，数据量比较大，一般都是不鼓励存储，放在索引文件中会把索引文件撑大
        ft.setTokenized(true);
        for (File file : f.listFiles())
        {
            try
            {
                // 创建Document对象
                doc = new Document();
                // doc.add(new Field("content", new FileReader(file), ft));
                doc.add(new TextField("content", new FileReader(file)));
                doc.add(new TextField("filename", file.getName(), Store.YES));
                doc.add(new StringField("path", file.getPath(), Store.YES));
                // 添加文档
                writer.addDocument(doc);
                writer.commit();// 提交数据
            } catch (FileNotFoundException e)
            {
                // TODO Auto-generated catch block
                e.printStackTrace();
            } catch (IOException e)
            {
                // TODO Auto-generated catch block
                e.printStackTrace();
            }

        }
    }

    /**
     * 搜索
     * 
     * @param path
     *            搜索路径
     * @param indexReaderPath
     *            索引存放路径
     */
    public void seacher(String indexReaderPath, String searthText)
    {
        IndexReader reader=null;
        try
        {
            directory = FSDirectory.open(new File(indexReaderPath));
            // 创建读取索引的reader
             reader = DirectoryReader.open(directory);
            // 根据reader创建search
            IndexSearcher searcher = new IndexSearcher(reader);
            // 创建查询,第二个参数表示查询的字段名，第三个是分词器
            QueryParser parser = new QueryParser(Version.LUCENE_45, "content",
                    new StandardAnalyzer(Version.LUCENE_45));
            // 搜索包含searthText的内容
            Query query = parser.parse(searthText);
            // 搜索返回10条记录
            TopDocs tds = searcher.search(query, 10);
            
             //获取scoredoc对象组，
             ScoreDoc[] sds=tds.scoreDocs;
             for(ScoreDoc sd:sds){
                 //获取具体的doc
                 Document doc=searcher.doc(sd.doc);
                 System.out.println(doc.get("filename")+":"+doc.get("path"));
             }
        } catch (IOException e)
        {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }// 打开存放索引的路径
        catch (ParseException e)
        {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }finally{
            if (reader!=null)
            {
                try
                {
                    reader.close();
                } catch (IOException e)
                {
                    // TODO Auto-generated catch block
                    e.printStackTrace();
                }
            }
        }
    }
}

说明，"D:\lucene\file"是我复制lucene官方文档上的两段话，不过当你创建完索引之后，然后再修改文件内容，新加的内容并不能搜索出来。这个应该很好理解。

然后进行测试：searchTest,就可以得到那个文本文件中有"Changing Similarity"这段字符

package com.bing.test;

import org.junit.Test;

public class HelloLuceneTest
{
    @Test
    public void writertest(){
        HelloLucene test=new HelloLucene();
        test.createIndex("D:\lucene\index","D:\lucene\file");
    }
    @Test
    public void searchTest(){
        HelloLucene test=new HelloLucene();
        test.seacher("D:\lucene\index", "Changing Similarity");
    }
}