当读取文件时,我们一般都会指定文本或字符串使用的编码格式,但有时我们不清楚是什么编码的时候,我们需要分析文件或字符是什么编码,我们可以使用以下代码.
/**
* 获取文件编码
* @param file 要分析的文件
**/
public static String getCharset(File file) {
String charset = "GBK"; // 默认编码
byte[] first3Bytes = new byte[3];
BufferedInputStream bis = null;
try {
boolean checked = false;
bis = new BufferedInputStream(new FileInputStream(file));
bis.mark(0);
int read = bis.read(first3Bytes, 0, 3);
if (read == -1)
return charset;
if (first3Bytes[0] == (byte) 0xFF && first3Bytes[1] == (byte) 0xFE) {
charset = "UTF-16LE";
checked = true;
} else if (first3Bytes[0] == (byte) 0xEF
&& first3Bytes[1] == (byte) 0xBB
&& first3Bytes[2] == (byte) 0xBF) {
charset = "UTF-8";
checked = true;
}
bis.reset();
if (!checked) {
int loc = 0;
while ((read = bis.read()) != -1) {
loc++;
if (read >= 0xF0)
break;
// 单独出现BF以下的,也算是GBK
if (0x80 <= read && read <= 0xBF)
break;
if (0xC0 <= read && read <= 0xDF) {
read = bis.read();
if (0x80 <= read && read <= 0xBF)// 双字节 (0xC0 - 0xDF)
// (0x80 -0xBF),也可能在GB编码内
continue;
else
break;
// 也有可能出错,但是机率较小
} else if (0xE0 <= read && read <= 0xEF) {
read = bis.read();
if (0x80 <= read && read <= 0xBF) {
read = bis.read();
if (0x80 <= read && read <= 0xBF) {
charset = "UTF-8";
break;
} else
break;
} else
break;
}
}
System.out.println(loc + " " + Integer.toHexString(read));
}
bis.close();
} catch (Exception e) {
e.printStackTrace();
} finally {
if (bis != null) {
try {
bis.close();
} catch (Exception e) {
e.printStackTrace();
}
}
}
return charset;
}