test.java

目前只用于文本文件和网页文件的全文检索,而且几乎没有界面的存在,运行时只有一个搜索词输入框.感兴趣的朋友可以下载下来自己实现界面功能.

import java.io.BufferedReader;
import java.io.File;
import java.io.FileReader;
import java.io.StringReader;
import java.util.Date;

import javax.swing.JOptionPane;

import jeasy.analysis.MMAnalyzer;

import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.queryParser.MultiFieldQueryParser;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.SimpleFragmenter;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
public class test
{
	public static void main(String[] args)
	{
		searcher s=new searcher();
		try
		{
			s.action();
		}
		catch(Exception e)
		{
			e.printStackTrace();
		}
	}
}

class searcher
{
	MMAnalyzer analyzer=new MMAnalyzer();
	String s;
	String dir_Path="E:/amusement and rest/文章欣赏";//需要被检索的文件目录
	public void setKeyword(String keyword)
	{
		s=keyword;
	}
	public void setDirPath(String dir_Path)
	{
		this.dir_Path=dir_Path;
	}
	public void action()
	{
		String search_field="contents";//要搜索的字段名,目前有title,contents,path字段
		String index_path="./indexs";//设置索引所在目录
		File f=new File(index_path);
		try
		{
			if(!f.exists())
			{
				//定义目录路径并建立索引
				IndexWriter index=new IndexWriter("./indexs",analyzer,true);
				//index.setMaxFieldLength(1000);
				idx(index,dir_Path);
				index.close();
			}
			s=JOptionPane.showInputDialog("输入要查找的关键词：").trim();
			//开始检索
			Date begin=new Date();
			IndexSearcher is=new IndexSearcher(index_path);
			BooleanClause.Occur[] clause={BooleanClause.Occur.SHOULD,BooleanClause.Occur.SHOULD};
			Query qa=MultiFieldQueryParser.parse(s,new String[]{"title",search_field},clause,analyzer);
			Hits hits=is.search(qa);
			Date end=new Date();
			System.out.println("总共搜索出：" + hits.length()+"个结果        "
					+"用时："+(end.getTime()-begin.getTime())+"毫秒");
			Highlighter highlighter = new Highlighter(new QueryScorer(qa));  
			for(int i=0;i<hits.length();i++)
			{
				System.out.println(i+1);
				System.out.println("文档标题：" + hits.doc(i).get("title"));
				//返回文件所在路径
				System.out.println("文档路径：" +hits.doc(i).get("path"));
				//高亮显示部分内容
				String suffer=hits.doc(i).get("path").substring(hits.doc(i).get("path").length()-4).toLowerCase();
				if(suffer.equals(".txt")||suffer.equals(".htm")||suffer.equals("html")||suffer.equals(".asp")||suffer.equals("aspx")||suffer.equals(".xml"))
					s = loadFile(new File(hits.doc(i).get("path")));
				else
					s=null;
				String result="";
				if(s!=null)
				{
					SimpleHTMLFormatter smt=new SimpleHTMLFormatter("<font color='red'>","</font>");
					highlighter = new Highlighter(smt,new QueryScorer(qa));      
					highlighter.setTextFragmenter(new SimpleFragmenter(100));
					TokenStream tokenStream =analyzer.tokenStream("contents", new StringReader(hits.doc(i).get("contents")));
					result=highlighter.getBestFragments(tokenStream,hits.doc(i).get("contents"),3, "……");
				}
				
				System.out.println("内容：" + result); 
			}
			is.close();
		}
		catch(Exception e)
		{
			e.printStackTrace();
			System.exit(0);
		}
		System.exit(0);
	}
	private void idx(IndexWriter index,String strPath) throws Exception
	{
		File   f=new   File(strPath);
		File[]   fList=f.listFiles();     
		for(int   j=0;j<fList.length;j++)     
		{     
			if(fList[j].isDirectory())     
			{
				idx(index,fList[j].getPath());   //在idx函数里面又调用了idx函数本身     
			} 
			else if(fList[j].isFile())     
			{
				String doc_path=fList[j].getParent()+"\\"+fList[j].getName();
				Document doc=new Document();
				Field f1=new Field("title",fList[j].getName(),Field.Store.YES,Field.Index.TOKENIZED,Field.TermVector.WITH_POSITIONS_OFFSETS);
				Field f3=new Field("path",doc_path,Field.Store.YES,Field.Index.NO);
				doc.add(f1);
				doc.add(f3);
				int i_path=doc_path.lastIndexOf(".");
				String suffer=doc_path.substring(i_path).toLowerCase();
				if(suffer.equals(".txt")||suffer.equals(".htm")||suffer.equals("html")||suffer.equals(".asp")||suffer.equals("aspx")||suffer.equals(".xml"))
				{
					Field f2=new Field("contents",loadFile(fList[j]),Field.Store.YES,Field.Index.TOKENIZED,Field.TermVector.WITH_POSITIONS_OFFSETS);
					doc.add(f2);
				}
				
				index.addDocument(doc);
			}
		}     
		
		
	}
	
	private String loadFile(File file)
	{
		try
		{
			BufferedReader br=new BufferedReader(new FileReader(file));
			StringBuffer sb=new StringBuffer();
			String line=br.readLine();
			while(line!=null)
			{
				sb.append(line);
				line=br.readLine();
			}
			br.close();
			return sb.toString();
		}
		catch(Exception e)
		{
			return null;
		}
	}
	
	
	public void rebuild_index() throws Exception
	{
		//建立索引
		IndexWriter index=new IndexWriter("./indexs",analyzer,true);
		//index.setMaxFieldLength(1000);
		idx(index,dir_Path);
		index.close();
	}
}