使用Lucene的java api 写入和读取索引库

Posted 2020-12-28 bdqnjs

import org.apache.commons.io.FileUtils;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.NumericDocValuesField;
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.junit.Test;

import java.io.File;
import java.io.IOException;
import java.nio.file.Path;
import java.nio.file.Paths;

public class Day01 {
    public String dataDir="E:\data";
    //2.search检索
    @Test
    public void search() throws IOException, ParseException {
      //01.
        Path path=Paths.get("./luceneindex/");
        Directory directory=FSDirectory.open(path);
        IndexReader indexReader=DirectoryReader.open(directory);
        //索引查询工具
        IndexSearcher indexSearcher=new IndexSearcher(indexReader);
        String word="战斗";
        QueryParser queryParser=new QueryParser("filename",new StandardAnalyzer());
        Query query=queryParser.parse(word);
        TopDocs topDocs = indexSearcher.search(query, 10);

        long count = topDocs.totalHits;
        System.out.println("总记录数："+count);

        ScoreDoc[] scoreDocs = topDocs.scoreDocs;
        for (ScoreDoc item:scoreDocs) {
            int docid = item.doc; //文档编号
            Document document = indexReader.document(docid);
            String filename = document.get("filename");
            System.out.println(filename);
        }
    }
    @Test
    //1.创建索引
    public void createIndex() throws IOException {
      //01.准备一个写入索引的目录
       Path path = Paths.get("./luceneindex/");
       //02.将路径与Directory进行绑定
        Directory directory=FSDirectory.open(path);
        //03.这行code在底层默认已经关联绑定了一个StandardAnalyzer 标准分词器
        IndexWriterConfig config=new IndexWriterConfig();
        //04.给config设置一个模式  Create:每次都抹掉原来的索引文件，重新构建新的索引文件
        config.setOpenMode(IndexWriterConfig.OpenMode.CREATE);
        //05.索引写入器需要两个入参，一个是目录，另一个是配置
        IndexWriter writer=new IndexWriter(directory,config);
        //06.准备加入索引库的内容
        File file = new File(dataDir);
        //07.某个目录下的文件集合
        File[] files = file.listFiles();
        for (File item:files) {
            //08.将内容幻化成----->Document
            Document document=new Document();
            String filename=item.getName(); //file--->String
            System.out.println(filename);
            System.out.println("===============================");
            String filecontent=FileUtils.readFileToString(item);
            Long modifydate=item.lastModified();
            //09.真正的给Document的field赋值
            document.add(new TextField("filename",filename,Field.Store.YES));
            document.add(new TextField("filecontent",filecontent,Field.Store.YES));
            document.add(new NumericDocValuesField("modifydate",modifydate));
            //10.将单个Document(一条记录)  保存到  索引库中
            writer.addDocument(document);
        }
        //11.关闭索引库
        writer.close();
        System.out.println("add indexes ok!");
    }
}