Lucene介绍和创建索引和搜索初步

Lucene是apache软件基金会4 jakarta项目组的一个子项目，是一个开放源代码的全文检索引擎工具包，即它不是一个完整的全文检索引擎，而是一个全文检索引擎的架构，提供了完整的查询引擎和索引引擎，部分文本分析引擎（英文与德文两种西方语言）。Lucene的目的是为软件开发人员提供一个简单易用的工具包，以方便的在目标系统中实现全文检索的功能，或者是以此为基础建立起完整的全文检索引擎。

以上介绍来自百度百科。

在全文索引工具中，都是由三部分组成的：

1，索引部分

2，分词部分

3，搜索部分

下面进入Lucene的学习，由lucene创建索引

创建工程引入jar包lucene-core-3.6.2.jar

HelloLucene.java

 

import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.io.Reader;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
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.store.LockObtainFailedException;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;


public class HelloLucene {
    /**
     * 建立索引
     */
    public void index(){
        IndexWriter writer = null;

        try {
            //1,创建词典
//          Directory directory = new RAMDirectory();//存储到内存
            Directory directory = FSDirectory.open(new File("D:\\lucene\\index"));
            //2,创建IndexWriter索引笔
            IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_35, new StandardAnalyzer(Version.LUCENE_35));
            writer = new IndexWriter(directory, config);

            //3，创建Document对象
            Document doc = null;
            File file = new File("d:/lucene/file");
            for(File f : file.listFiles()){
                doc = new Document();
                //4，为Document添加Field
                doc.add(new Field("content",new FileReader(f)));
                doc.add(new Field("filename",f.getName(),Field.Store.YES,Field.Index.NOT_ANALYZED));
                doc.add(new Field("path",f.getAbsolutePath(),Field.Store.YES,Field.Index.NOT_ANALYZED));
                //5，通过IndexWriter添加文档到索引中
                writer.addDocument(doc);
            }
        } catch (CorruptIndexException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (LockObtainFailedException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }finally{
            if(writer!=null){
                try {
                    writer.close();
                } catch (CorruptIndexException e) {
                    // TODO Auto-generated catch block
                    e.printStackTrace();
                } catch (IOException e) {
                    // TODO Auto-generated catch block
                    e.printStackTrace();
                }
            }
        }
    }
    /**
     * 搜索
     */
    public void search(){
        IndexReader reader = null;
        try {
            //1，创建Directory
            Directory directory = FSDirectory.open(new File("d:/lucene/index"));
            //2，创建IndexReader
            reader = IndexReader.open(directory);
            //3，根据IndexReader创建IndexSearcher
            IndexSearcher searcher = new IndexSearcher(reader);
            //4，创建搜索的Query
            QueryParser parser = new QueryParser(Version.LUCENE_35, "content", new StandardAnalyzer(Version.LUCENE_35));
            Query query = parser.parse("Apache License");
            //5，根据searcher搜索并返回TopDocs
            TopDocs tds = searcher.search(query, 10);
            //6，根据TopDocs获取ScoreDoc对象
            ScoreDoc[] sds = tds.scoreDocs;
            //7，根据searcher和ScoreDoc对象获取具体的Document对象
            for(ScoreDoc sd:sds){
                Document doc = searcher.doc(sd.doc);
                //8，根据Document对象获取需要的值
                System.out.println(doc.get("filename")+":"+doc.get("path"));
            }
        } catch (IOException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        } catch (ParseException e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }finally{
            //9，关闭reader
            if(reader!=null){
                try {
                    reader.close();
                } catch (IOException e) {
                    // TODO Auto-generated catch block
                    e.printStackTrace();
                }
            }
        }

    }
}

测试 

import static org.junit.Assert.*;

import org.junit.BeforeClass;
import org.junit.Test;


public class TestCase {

    @BeforeClass
    public static void setUpBeforeClass() throws Exception {
    }

    @Test
    public void testIndex() {
        new HelloLucene().index();
    }

    @Test
    public void testSearch(){
        new HelloLucene().search();
    }
}