txtindexer.java

全文搜索源码,基于开源项目Lucene编写,开发语言为JAVA,本程序做为LUCENE的示例DEMO

package com.ht.lucenedemo;

import java.io.File;
import java.io.FileReader;
import java.io.Reader;
import java.util.Date;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import com.ht.gis.service.*;

public class TxtIndexer {
  private static Log log = LogFactory.getLog("WebGIS");

  public TxtIndexer() {
  }

  public static void main(String[] args)throws Exception{
    File   indexDir = new File("D:\\luceneIndex");
    File   dataDir  = new File("D:\\luceneData");
    Analyzer luceneAnalyzer = new StandardAnalyzer();
    File[] dataFiles  = dataDir.listFiles();
    IndexWriter indexWriter = new IndexWriter(indexDir,luceneAnalyzer,true);
    long startTime = new Date().getTime();
    for (int i = 0; i < dataFiles.length; i++) {
      if (dataFiles[i].isFile() && dataFiles[i].getName().endsWith(".txt")) {
        log.debug("Indexing file " + dataFiles[i].getCanonicalPath());
        Document document = new Document();
        Reader txtReader = new FileReader(dataFiles[i]);
        document.add(Field.Text("path", dataFiles[i].getCanonicalPath()));
        document.add(Field.Text("contents", txtReader));
        indexWriter.addDocument(document);
      }
    }
    indexWriter.optimize();
    indexWriter.close();
    long endTime = new Date().getTime();
    log.debug("索引时间: " + (endTime - startTime) + " 毫秒 在目录 " + dataDir.getPath());
  }
}