Practice Every Day_9(更新索引)

最新推荐文章于 2024-11-07 11:28:28 发布

SherryWang0622

最新推荐文章于 2024-11-07 11:28:28 发布

阅读量747

点赞数

分类专栏： Lucene 文章标签： lucene string import path file excel

本文链接：https://blog.csdn.net/supersnow0622/article/details/7518511

版权

Lucene 专栏收录该内容

11 篇文章 0 订阅

订阅专栏

今天写的代码貌似不到100行，主要看了看关于pdf，word还有excel文件解析的内容，终于明白了怎么回事，但还没有具体操作，明天争取写出对这些文件建立索引和搜索的代码。以下是更新索引的代码：

import java.io.File;
import java.io.IOException;

import org.apache.lucene.analysis.Analyzer;建立索引
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.Fieldable;
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.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryParser.ParseException;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.Version;

public class MyUpdateIndexer{
    public static final String STORE_PATH = "E:/lucene_index";
    public static void updateIndexes(String field , String keyword) throws
             CorruptIndexException, IOException, ParseException
    {

        //首先，我们需要先将相应的document删除
        Directory dir = FSDirectory.open(new File(STORE_PATH));
        IndexReader reader = IndexReader.open(dir,false);
        Term term = new Term(field,keyword);
        reader.deleteDocuments(term);
        reader.close();
        //然后，将新的document加入索引
        Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_35);

        IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_35,analyzer).setOpenMode(OpenMode.CREATE);
        IndexWriter writer = new IndexWriter(dir, config);
        for(int i = 0;i<100;i++)
        {
            Document doc = new Document();
            doc.add((Fieldable) new Field("title", "lucene title"+i, Field.Store.YES, Field.Index.ANALYZED));
            doc.add(new Field("content", "Apache Lucene(TM) is a high-performance", Field.Store.YES, Field.Index.ANALYZED));
            //纯文本文件索引起来，而不想自己将它们读入字符串创建field
            //这里的file就是该文本文件。该构造函数实际上是读去文件内容，并对其进行索引，但不存储。
            //doc.add(new Field("path", new FileReader(new File("路径"))));
            writer.addDocument(doc);
        }

        writer.close();
    }
}