转 java 读取文件的字符集
(2012-05-21 15:40:34)
标签:
it
public static String getCharset(File file) {
String charset = "GBK";
byte[] first3Bytes = new byte[3];
try {
boolean checked = false;
BufferedInputStream 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) 0xFE && first3Bytes[1]
== (byte) 0xFF) {
charset = "UTF-16BE";
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,但是几率较小
} 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();
}
return charset;
}
分享:
喜欢
0
赠金笔
加载中,请稍候......
评论加载中,请稍候...
发评论
登录名: 密码: 找回密码 注册记住登录状态
昵 称:
评论并转载此博文
发评论
以上网友发言只代表其个人观点,不代表新浪网的观点或立场。