使用Lucene的java api 寫入和讀取索引庫

標籤：new   nio   parse   .text   lis   arc   path   rect   comm   

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檢索
    @Test
    public void search() throws IOException, ParseException {
      //01.
        Path path=Paths.get("./luceneindex/");
        Directory directory=FSDirectory.open(path);
        IndexReader indexReader=DirectoryReader.open(directory);
        //索引查詢工具
        IndexSearcher indexSearcher=new IndexSearcher(indexReader);
        String word="戰鬥";
        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("總記錄數："+count);

        ScoreDoc[] scoreDocs = topDocs.scoreDocs;
        for (ScoreDoc item:scoreDocs) {
            int docid = item.doc; //文檔編號
            Document document = indexReader.document(docid);
            String filename = document.get("filename");
            System.out.println(filename);
        }
    }
    @Test
    //1.建立索引
    public void createIndex() throws IOException {
      //01.準備一個寫入索引的目錄
       Path path = Paths.get("./luceneindex/");
       //02.將路徑與Directory進行綁定
        Directory directory=FSDirectory.open(path);
        //03.這行code在底層預設已經關聯綁定了一個StandardAnalyzer 標準分詞器
        IndexWriterConfig config=new IndexWriterConfig();
        //04.給config設定一個模式  Create:每次都抹掉原來的索引檔案，重新構建新的索引檔案
        config.setOpenMode(IndexWriterConfig.OpenMode.CREATE);
        //05.索引寫入器需要兩個入參，一個是目錄，另一個是配置
        IndexWriter writer=new IndexWriter(directory,config);
        //06.準備加入索引庫的內容
        File file = new File(dataDir);
        //07.某個目錄下的檔案集合
        File[] files = file.listFiles();
        for (File item:files) {
            //08.將內容幻化成----->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.真正的給Document的field賦值
            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.將單個Document(一條記錄)  儲存到  索引庫中
            writer.addDocument(document);
        }
        //11.關閉索引庫
        writer.close();
        System.out.println("add indexes ok!");
    }
}

使用Lucene的java api 寫入和讀取索引庫