java detect charset code example
Example: how to know if a file is iso-8859-1 encoded in java
FileInputStream fIn = new FileInputStream(myFile);
byte[] buf = new byte[4096];
UniversalDetector detector = new UniversalDetector(null);
int nread;
while ((nread = fIn.read(buf)) > 0 && !detector.isDone()) {
detector.handleData(buf, 0, nread);
}
detector.dataEnd();
String encoding = detector.getDetectedCharset();
String chartsetName = null;
if (encoding.equalsIgnoreCase("WINDOWS-1252")){
chartsetName = "ISO-8859-1";
}
if (encoding.equalsIgnoreCase("UTF-8")){
chartsetName = "UTF-8";
}
BufferedReader myReader = new BufferedReader(new InputStreamReader(fIn, chartsetName));