java判断文本字符集

/*这是一个sourceforge项目,能够判断指定文本或流的字符集*/

/*下面是这个库的简单封装*/

package me.jor.util;

import info.monitorenter.cpdetector.io.ByteOrderMarkDetector;
import info.monitorenter.cpdetector.io.CodepageDetectorProxy;
import info.monitorenter.cpdetector.io.JChardetFacade;
import info.monitorenter.cpdetector.io.ParsingDetector;
import info.monitorenter.cpdetector.io.UnicodeDetector;

import java.io.File;
import java.io.IOException;
import java.net.MalformedURLException;
import java.util.concurrent.atomic.AtomicInteger;

public class CodeDetectUtil {
    private static CodepageDetectorProxy codeDetector;
    private static AtomicInteger threads;

/**初始化*/
    public static void initCodeDetector(){
        if(threads==null){
            synchronized(CodeDetectUtil.class){
                if(threads==null){
                    threads=new AtomicInteger(1);
                    codeDetector=CodepageDetectorProxy.getInstance();
                    codeDetector.add(new ParsingDetector(false));//根据xml文件头判断xml字符集
                    codeDetector.add(JChardetFacade.getInstance());//通用库判断字符集
                    codeDetector.add(UnicodeDetector.getInstance());//判断是否unicode
                    codeDetector.add(new ByteOrderMarkDetector());//根据字节顺序判断字符集
                }else{
                    threads.incrementAndGet();
                }
            }
        }else{
            threads.incrementAndGet();
        }
    }
/**判断结束要反初始化*/
    public static void endCodeDetector(){
        if(threads.get()>0){
            threads.decrementAndGet();
        }
        if(threads.get()<=0){
            synchronized(CodeDetectUtil.class){
                if(threads.get()<=0){
                    codeDetector=null;
                    threads=null;
                }
            }
        }
    }
     /**判断指定文件的字符集*/
     public static String detectCharset (File file) throws MalformedURLException, IOException{
        return codeDetector.detectCodepage(file.toURI().toURL()).name();
    }
}

 

你可能感兴趣的:(java)