java判断文本文件编码格式

上篇文章需要读取当前java或者配置文件的编码格式，这里主要支持UTF-8、GBK、UTF-16、Unicode等

/**
	 * 判断文件的编码格式
	 * @param fileName :file
	 * @return 文件编码格式
	 * @throws Exception
	 */
	public static String codeString(File fileName) throws Exception{
		BufferedInputStream bin = new BufferedInputStream(
		new FileInputStream(fileName));
		int p = (bin.read() << 8) + bin.read();
		String code = null;
		
		switch (p) {
			case 0xefbb:
				code = "UTF-8";
				break;
			case 0xfffe:
				code = "Unicode";
				break;
			case 0xfeff:
				code = "UTF-16BE";
				break;
			default:
				code = "GBK";
		}
		IOUtils.closeQuietly(bin);
		return code;
	}

上面这段代码只能判断带bom的文本，如果非bom文本，还有两种方式
1、 轮询常用的编码，知道找到匹配的，如下面一段测试代码

  

/*
 *  Copyright 2010 Georgios Migdos .
 * 
 *  Licensed under the Apache License, Version 2.0 (the "License");
 *  you may not use this file except in compliance with the License.
 *  You may obtain a copy of the License at
 * 
 *       http://www.apache.org/licenses/LICENSE-2.0
 * 
 *  Unless required by applicable law or agreed to in writing, software
 *  distributed under the License is distributed on an "AS IS" BASIS,
 *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 *  See the License for the specific language governing permissions and
 *  limitations under the License.
 *  under the License.
 */

import java.io.BufferedInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStreamReader;
import java.nio.ByteBuffer;
import java.nio.charset.CharacterCodingException;
import java.nio.charset.Charset;
import java.nio.charset.CharsetDecoder;

/**
 *
 * @author Georgios Migdos 
 */
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) {
        File f = new File("example.txt");

        String[] charsetsToBeTested = {"UTF-8", "windows-1253", "ISO-8859-7"};

        CharsetDetector cd = new CharsetDetector();
        Charset charset = cd.detectCharset(f, charsetsToBeTested);

        if (charset != null) {
            try {
                InputStreamReader reader = new InputStreamReader(new FileInputStream(f), charset);
                int c = 0;
                while ((c = reader.read()) != -1) {
                    System.out.print((char)c);
                }
                reader.close();
            } catch (FileNotFoundException fnfe) {
                fnfe.printStackTrace();
            }catch(IOException ioe){
                ioe.printStackTrace();
            }

        }else{
            System.out.println("Unrecognized charset.");
        }
    }
}
    

2、 使用谷歌依赖库来进行判断
https://code.google.com/archive/p/juniversalchardet/