txt文件编码判断

Bertha 。 2022-08-08 14:46 200阅读 0赞

txt文件，首先分有无bom(Byte Order Mark)。有的话，相对简单，没有的话，还要区分uft-8和ANSI的区别。代码如下：

private static boolean isutf8(byte[] str)
    	{
    	    int i = 0;
    	    int size = str.length;
    	 
    	    while(i < size)
    	    {
    	        int step = 0;
    	        if((str[i] & 0x80) == 0x00)
    	        {
    	            step = 1;
    	        }
    	        else if((str[i] & 0xe0) == 0xc0)
    	        {
    	            if(i + 1 >= size) return false;
    	            if((str[i + 1] & 0xc0) != 0x80) return false;
    	 
    	            step = 2;
    	        }
    	        else if((str[i] & 0xf0) == 0xe0)
    	        {
    	            if(i + 2 >= size) return false;
    	            if((str[i + 1] & 0xc0) != 0x80) return false;
    	            if((str[i + 2] & 0xc0) != 0x80) return false;
    	 
    	            step = 3;
    	        }
    	        else
    	        {
    	            return false;
    	        }
    	 
    	        i += step;
    	    }
    	 
    	    if(i == size) return true;
    	 
    	    return false;
    	}
    
    	private static String getCode(byte[] bytes){
    		InputStream in = new ByteArrayInputStream(bytes);
    		BufferedInputStream bin = new BufferedInputStream(in);
    		String code = null;//判断字符编码
    		try {
    			int p = (bin.read() << 8) + bin.read();
    			switch (p) {
    			case 0xefbb:
    				code = "UTF-8";
    				break;
    			case 0xfffe:
    				code = "Unicode";
    				break;
    			case 0xfeff:
    				code = "UTF-16BE";
    				break;
    			default:
    				if(isutf8(bytes))
    					code = "UTF-8";
    				else{
    					code = "GBK";
    				}
    				
    			}
    		} catch (IOException e1) {
    			// TODO Auto-generated catch block
    			e1.printStackTrace();
    		}finally{
    			try {
    				bin.close();
    			} catch (IOException e) {
    				// TODO Auto-generated catch block
    				e.printStackTrace();
    			}
    		}
    		return code;
    	}

private static String getCode(byte[] bytes) {
    		String hexCode = "";
    		if(bytes.length > 1){
    			for (int i = 0; i < 2; i++) {
    				String hex = Integer.toHexString(bytes[i] & 0xFF);
    				if (hex.length() == 1) {
    					hex = '0' + hex;
    				}
    				hexCode+=hex;
    			}
    		}
    		
    		String code = null;//判断字符编码
    		if(hexCode.toLowerCase().equals("efbb"))
    				code = "UTF-8";
    		else if(hexCode.toLowerCase().equals("fffe"))
    				code = "Unicode";
    		else if(hexCode.toLowerCase().equals("feff"))
    				code = "UTF-16BE";
    		else{
    			if(isutf8(bytes))
    				code = "UTF-8";
    			else{
    				code = "GBK";
    			}
    		}
    		return code;
    	}