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"; // 文件編碼為 ANSI
}
if (first3Bytes[0] == (byte) 0xFF && first3Bytes[1] == (byte) 0xFE) {
return "UTF-16LE"; // 文件編碼為 Unicode
}
if (first3Bytes[0] == (byte) 0xFE && first3Bytes[1] == (byte) 0xFF) {
return "UTF-16BE"; // 文件編碼為 Unicode big endian
}
if (first3Bytes[0] == (byte) 0xEF && first3Bytes[1] == (byte) 0xBB && first3Bytes[2] == (byte) 0xBF) {
return "UTF-8"; // 文件編碼為 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編碼內
continue;
}
break;
} else if (0xE0 <= read && read <= 0xEF) {// 也有可能出錯，但是幾率較小
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讀取文件的時候，經常碰到中文亂碼，特研究了一下java 的編碼格式，在java 中
java編碼與txt編碼對應 | java | txt |
| unicode | unicode big endian |
| utf-8 | utf-8 |
| utf-16 | unicode |
| gb2312 | ANSI |
java 讀取txt如果編碼格式不對就會出現亂碼格式，通過下邊方法獲取文本文件編碼格式，然后以指定的編碼讀取文件，就不會出現亂碼(簡單測試了一下，但是也不保證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; //文件編碼為 ANSI
} else if (first3Bytes[0] == (byte) 0xFF
&& first3Bytes[1] == (byte) 0xFE) {
charset = "UTF-16LE"; //文件編碼為 Unicode
checked = true;
} else if (first3Bytes[0] == (byte) 0xFE
&& first3Bytes[1] == (byte) 0xFF) {
charset = "UTF-16BE"; //文件編碼為 Unicode big endian
checked = true;
} else if (first3Bytes[0] == (byte) 0xEF
&& first3Bytes[1] == (byte) 0xBB
&& first3Bytes[2] == (byte) 0xBF) {
charset = "UTF-8"; //文件編碼為 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) // 單獨出現BF以下的，也算是GBK
break;
if (0xC0 <= read && read <= 0xDF) {
read = bis.read();
if (0x80 <= read && read <= 0xBF) // 雙字節 (0xC0 - 0xDF)
// (0x80
// - 0xBF),也可能在GB編碼內
continue;
else
break;
} else if (0xE0 <= read && read <= 0xEF) {// 也有可能出錯，但是幾率較小
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 閱讀(1511)
評論(0) 編輯 收藏