判断文件实际编码格式

package com.icitic.data.comp.txt.parser;

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.nio.charset.Charset;

import com.google.common.base.Charsets;

/**
 * 判断文件类型
 * @author Administrator
 *
 */
public class EncodingDetect {
	
	public static Charset detectEncoding(File file) {
		int[] head = new int[4];
		InputStream inputStream = null;
		try {
			inputStream = new FileInputStream(file);
			for (int i = 0; i < 4; i++) {
				head[i] = inputStream.read();
			}
		} catch (IOException e) {
			e.printStackTrace();
		} finally {
			try {
				inputStream.close();
			} catch (IOException e) {
			}
		}

		Charset code = Charset.forName("GBK");
		if (head[0] == 0xef && head[1] == 0xbb && head[2] == 0xbf) {
			code = Charsets.UTF_8;

		} else if (head[0] == 0xfe && head[1] == 0xff) {
			code = Charsets.UTF_16LE;

		} else if (head[0] == 0xff && head[1] == 0xfe) {
			code = Charsets.UTF_16BE;

		} else if (head[0] == 0xff && head[1] == 0xfe && head[2] == 0x0 && head[3] == 0x0) {
			code = Charsets.UTF_16LE;

		} else if (head[0] == 0x0 && head[1] == 0x0 && head[2] == 0xfe && head[3] == 0xff) {
			code = Charsets.UTF_16BE;
		}
		return code;
	}

	public static Charset detectEncoding(String path) {
		return detectEncoding(new File(path));
	}

}