txtsearcher.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 org.apache.lucene.document.Document;
import org.apache.lucene.index.Term;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.search.*;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.store.FSDirectory;
import java.util.Date;
import com.ht.gis.service.*;

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

  public TxtSearcher() {
  }
  public static void main(String[] args) throws Exception{
    String queryStr = "福田";
    File indexDir = new File("D:\\luceneIndex");
    FSDirectory directory = FSDirectory.getDirectory(indexDir, false);
    IndexSearcher searcher = new IndexSearcher(directory);
    if (!indexDir.exists()) {
      log.error("The Lucene index is not exist");
      return;
    }
    Analyzer analyzer = new StandardAnalyzer();
    QueryParser parser = new QueryParser("contents" , analyzer);
    long startTime = new Date().getTime();
    Query query = parser.parse(queryStr);
    //Term term = new Term("contents", queryStr.toLowerCase());
    //TermQuery query = new TermQuery(term);
    Hits hits = searcher.search(query);
    for (int i = 0; i < hits.length(); i++) {
      Document document = hits.doc(i);
      log.debug("File: " + document.get("path"));
    }
    long endTime = new Date().getTime();
    log.debug("搜索时间: " + (endTime - startTime) + " 毫秒");
  }
}