Lucene介紹和建立索引和搜索初步

Lucene是apache軟件基金會4 jakarta項目組的一個子項目，是一個開放源代碼的全文檢索引擎工具包，即它不是一個完整的全文檢索引擎，而是一個全文檢索引擎的架構，提供了完整的查詢引擎和索引引擎，部分文本分析引擎（英文與德文兩種西方語言）。Lucene的目的是爲軟件開發人員提供一個簡單易用的工具包，以方便的在目標系統中實現全文檢索的功能，或者是以此爲基礎創建起完整的全文檢索引擎。

以上介紹來自百度百科。

在全文索引工具中，都是由三部分組成的：

1，索引部分

2，分詞部分

3，搜索部分

下面進入Lucene的學習，由lucene建立索引

建立工程引入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 {
    /**
     * 創建索引
     */
    public void index(){
        IndexWriter writer = null;

        try {
            //1,建立詞典
//          Directory directory = new RAMDirectory();//存儲到內存
            Directory directory = FSDirectory.open(new File("D:\\lucene\\index"));
            //2,建立IndexWriter索引筆
            IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_35, new StandardAnalyzer(Version.LUCENE_35));
            writer = new IndexWriter(directory, config);

            //3，建立Document對象
            Document doc = null;
            File file = new File("d:/lucene/file");
            for(File f : file.listFiles()){
                doc = new Document();
                //4，爲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，經過IndexWriter添加文檔到索引中
                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，建立Directory
            Directory directory = FSDirectory.open(new File("d:/lucene/index"));
            //2，建立IndexReader
            reader = IndexReader.open(directory);
            //3，根據IndexReader建立IndexSearcher
            IndexSearcher searcher = new IndexSearcher(reader);
            //4，建立搜索的Query
            QueryParser parser = new QueryParser(Version.LUCENE_35, "content", new StandardAnalyzer(Version.LUCENE_35));
            Query query = parser.parse("Apache License");
            //5，根據searcher搜索並返回TopDocs
            TopDocs tds = searcher.search(query, 10);
            //6，根據TopDocs獲取ScoreDoc對象
            ScoreDoc[] sds = tds.scoreDocs;
            //7，根據searcher和ScoreDoc對象獲取具體的Document對象
            for(ScoreDoc sd:sds){
                Document doc = searcher.doc(sd.doc);
                //8，根據Document對象獲取須要的值
                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，關閉reader
            if(reader!=null){
                try {
                    reader.close();
                } catch (IOException e) {
                    // TODO Auto-generated catch block
                    e.printStackTrace();
                }
            }
        }

    }
}

測試 

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();
    }
}