http://blog.163.com/wf_shunqiziran/blog/static/176307209201258102217810/
private String getFilecharset(File sourceFile) {
byte[] first3Bytes = new byte[3];
try (BufferedInputStream bis = new BufferedInputStream(new FileInputStream(sourceFile))) {
bis.mark(0);
int read = bis.read(first3Bytes, 0, 3);
if (read == -1) {
return "GBK"; // 文件编码为 ANSI
}
if (first3Bytes[0] == (byte) 0xFF && first3Bytes[1] == (byte) 0xFE) {
return "UTF-16LE"; // 文件编码为 Unicode
}
if (first3Bytes[0] == (byte) 0xFE && first3Bytes[1] == (byte) 0xFF) {
return "UTF-16BE"; // 文件编码为 Unicode big endian
}
if (first3Bytes[0] == (byte) 0xEF && first3Bytes[1] == (byte) 0xBB && first3Bytes[2] == (byte) 0xBF) {
return "UTF-8"; // 文件编码为 UTF-8
}
bis.reset();
while ((read = bis.read()) != -1) {
if (read >= 0xF0) {
break;
}
if (0x80 <= read && read <= 0xBF) {
break;
}
if (0xC0 <= read && read <= 0xDF) {
read = bis.read();
if (0x80 <= read && read <= 0xBF) {
// (0x80 - 0xBF),也可能在GB编码内
continue;
}
break;
} else if (0xE0 <= read && read <= 0xEF) {// 也有可能出错，但是几率较小
read = bis.read();
if (0x80 <= read && read <= 0xBF) {
read = bis.read();
if (0x80 <= read && read <= 0xBF) {
return "UTF-8";
}
break;
}
break;
}
}
} catch (Exception e) {
e.printStackTrace();
}
return "GBK";
}
最近java读取文件的时候，经常碰到中文乱码，特研究了一下java 的编码格式，在java 中
java编码与txt编码对应 | java | txt |
| unicode | unicode big endian |
| utf-8 | utf-8 |
| utf-16 | unicode |
| gb2312 | ANSI |
java 读取txt如果编码格式不对就会出现乱码格式，通过下边方法获取文本文件编码格式，然后以指定的编码读取文件，就不会出现乱码(简单测试了一下，但是也不保证100%)
private static String getFilecharset(File sourceFile) {
String charset = "GBK";
byte[] first3Bytes = new byte[3];
try {
boolean checked = false;
BufferedInputStream bis = new BufferedInputStream(new FileInputStream(sourceFile));
bis.mark(0);
int read = bis.read(first3Bytes, 0, 3);
if (read == -1) {
return charset; //文件编码为 ANSI
} else if (first3Bytes[0] == (byte) 0xFF
&& first3Bytes[1] == (byte) 0xFE) {
charset = "UTF-16LE"; //文件编码为 Unicode
checked = true;
} else if (first3Bytes[0] == (byte) 0xFE
&& first3Bytes[1] == (byte) 0xFF) {
charset = "UTF-16BE"; //文件编码为 Unicode big endian
checked = true;
} else if (first3Bytes[0] == (byte) 0xEF
&& first3Bytes[1] == (byte) 0xBB
&& first3Bytes[2] == (byte) 0xBF) {
charset = "UTF-8"; //文件编码为 UTF-8
checked = true;
}
bis.reset();
if (!checked) {
int loc = 0;
while ((read = bis.read()) != -1) {
loc++;
if (read >= 0xF0)
break;
if (0x80 <= read && read <= 0xBF) // 单独出现BF以下的，也算是GBK
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;
} else if (0xE0 <= read && read <= 0xEF) {// 也有可能出错，但是几率较小
read = bis.read();
if (0x80 <= read && read <= 0xBF) {
read = bis.read();
if (0x80 <= read && read <= 0xBF) {
charset = "UTF-8";
break;
} else
break;
} else
break;
}
}
}
bis.close();
} catch (Exception e) {
e.printStackTrace();
}
return charset;
}
posted on 2015-05-07 15:48
SIMONE 阅读(1505)
评论(0) 编辑 收藏