Java-获取文件的编码

获取任意文件的编码格式。

首先，需要获取Java系统支持的所有编码集：

Set<String> charsetNames = Charset.availableCharsets().keySet();

然后通过读取文件的一小部分字节，对应每个编码类型逐一进行匹配，最终得出文件的编码，代码如下：

import java.io.BufferedInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.nio.ByteBuffer;
import java.nio.charset.CharacterCodingException;
import java.nio.charset.Charset;
import java.nio.charset.CharsetDecoder;
import java.util.Set;

public class CharsetDetector {
 
    public Charset detectCharset(File f, String[] charsets) {
 
        Charset charset = null;
 
        for (String charsetName : charsets) {
            charset = detectCharset(f, Charset.forName(charsetName));
            if (charset != null) {
                break;
            }
        }
 
        return charset;
    }
 
    private Charset detectCharset(File f, Charset charset) {
        try {
            BufferedInputStream input = new BufferedInputStream(new FileInputStream(f));
 
            CharsetDecoder decoder = charset.newDecoder();
            decoder.reset();
 
            byte[] buffer = new byte[512];
            boolean identified = false;
            while ((input.read(buffer) != -1) && (!identified)) {
                identified = identify(buffer, decoder);
            }
 
            input.close();
 
            if (identified) {
                return charset;
            } else {
                return null;
            }
 
        } catch (Exception e) {
            return null;
        }
    }
 
    private boolean identify(byte[] bytes, CharsetDecoder decoder) {
        try {
            decoder.decode(ByteBuffer.wrap(bytes));
        } catch (CharacterCodingException e) {
            return false;
        }
        return true;
    }
 
    public static void main(String[] args) {
    	try{
        File f = new File("/Users/YI/Desktop/audio.pcm");
 
        Set<String> charsetNames = Charset.availableCharsets().keySet();  
        String[] tmp = new String[charsetNames.size()];
        String[] charsetsToBeTested = charsetNames.toArray(tmp);
 
        CharsetDetector cd = new CharsetDetector();
        Charset charset = cd.detectCharset(f, charsetsToBeTested);
 
        if (charset != null) {
            	System.out.println(charset.toString());
            	FileInputStream is = new FileInputStream(f);
                while(true){
                	byte[] by = new byte[1024];
                	int read = is.read(by);
                	if(read == -1)
                		break;
                }
 
        }else{
            System.out.println("Unrecognized charset.");
        }
    	}catch(Exception e){
    		
    	}
    }
}