inputproxy.java

lucene 是java 的版的搜索引擎公共模块

package com.microvois.luence;
import org.apache.lucene.analysis.*;
import org.apache.lucene.document.*;
import org.apache.lucene.store.*;
import org.apache.lucene.index.*;
import org.apache.lucene.analysis.cn.*;
import java.io.*;
import org.apache.log4j.Logger;

public class inputproxy 
{
	 /**
     * The maximum number of results to return with a search.
     */
    private static final Logger log = Logger.getLogger(Config.class);

    private static IndexWriter writer;
    private static Directory searchDirectory = null;
    protected static Analyzer analyzer = new ChineseAnalyzer();
    private static int ninputcount = 1;
    static
    {
    	if(searchDirectory == null)
    	{
    		try
    		{
    			
    			searchDirectory= FSDirectory.getDirectory(new File(Config.StrDataDirectroy));
    			if(searchDirectory.fileExists("write.lock"))
    			{
    				searchDirectory.deleteFile("write.lock");
    				System.out.println("delete luence lock file ...");    		    
    			}
    			
    			
    		}catch(Exception se)
    		{
    			
    		}
    		
    	}
    	
    	
    	
    }
/**
 * 
 * delete document from searchDB via url . 
 * @param url: key of url string 
 * @return
 */
    public static synchronized  boolean deleteURL(String url)
    {
    	boolean nret = false;
    	try
    	{
    		IndexWriter	awriter= getDirectoryWriter();     	
    		Term tm = new Term("url",url);
    		awriter.deleteDocuments(tm);
 		   nret = true;
    	}catch(Exception se)
    	{
    		log.equals(se.getMessage());
    		se.printStackTrace();
    	}
    	return nret;
    }
 
    public static synchronized  boolean inputData(String strtitle, String strdata, String url)
    {
    	boolean nret = false;
    	try
    	{
    		IndexWriter	awriter= getDirectoryWriter();     	
    	    Document doc = new Document();
    	    doc.add(new Field("title", strtitle, Field.Store.YES,Field.Index.NO));
 		    doc.add(new Field("data", strdata, Field.Store.YES,Field.Index.TOKENIZED));		    
 		    doc.add(new Field("url", url, Field.Store.YES, Field.Index.UN_TOKENIZED));
 		    
 		    awriter.addDocument(doc); 
 		    ninputcount++;
 		    if(ninputcount % 100 ==0)
 		    	awriter.flush();
 		    
 		   nret = true;
    	}catch(Exception se)
    	{
    		log.equals(se.getMessage());
    		se.printStackTrace();
    	}
    	return nret;
    }
    
    /**
     * if first work , implement create directroy . 
     * 
     * @return
     */
    private static synchronized  IndexWriter getDirectoryWriter() throws Exception 
    {
    	if(searchDirectory ==null)
    	{
    	      searchDirectory = FSDirectory.getDirectory(new File(Config.StrDataDirectroy));
    	}
    	if(writer == null)
    	{    		
    		writer= new IndexWriter(searchDirectory, analyzer);     	    
    	}
    	return writer;    	
    }
    
    private static boolean indexExists(String indexPath) {
        File segments = new File(indexPath+ File.separator + "segments");
        return segments.exists();
    }
    
    public static void flush()
    {
    	try
    	{
    	if(writer!=null)
    		writer.flush();
    	}catch(Exception se)
    	{
    		
    	}
    }
    public static synchronized void close() 
    {
    	try
    	{
    	if(writer != null)
    	{    		
    		writer.optimize();    		
    		writer.close();    	    		
    	}
    	
    	if(searchDirectory !=null)
    	{
    		searchDirectory.close();    		
    	}
    	
    	searchDirectory = null;
    	writer= null;
    	
    	}catch(Exception see)
    	{
    		see.printStackTrace();
    	}
    	
    }
    /**
     * 
     * 
     * @param args
     */
    public static void main(String args[])
    {
    	for(int i=0;i<1;i++)
    	{
    		boolean bb = inputproxy.inputData("测试标题"+i, "您正abcd在查找的页当前不可用。 网站可能遇到支持问题，或者您需要 调整您的浏览器设置。", "http://www.localhost.com/aa.html");    	
    		System.out.println(i+"="+bb);
    	}
    	inputproxy.close();
    	
    }
    
}