// 使用之前请调用getAllDetectableCharsets()检查是否满足要求,中文仅有{gb18030, big5,utf-*}
import com.ibm.icu.text.CharsetDetector;
import com.ibm.icu.text.CharsetMatch;
static HashSet<String> getWhiteList(String fileName) {
if (fileName == null) {
return null;
}
HashSet<String> rs = null;
InputStreamReader isr = null;
BufferedReader br = null;
try {
FileInputStream fis = new FileInputStream(fileName);
BufferedInputStream bis = new BufferedInputStream(fis);// markSupported
CharsetMatch charsetMatch = new CharsetDetector().setText(bis).detect();
if (charsetMatch != null) {
isr = new InputStreamReader(bis, charsetMatch.getName());
System.out.println("Open '" + fileName + " ' with charset: " + charsetMatch.getName());
} else {
isr = new InputStreamReader(bis);
System.out.println(
"Open '" + fileName + " ' with charset( default, because no charset is detected by IBM.ICU4J): "
+ isr.getEncoding());
}
br = new BufferedReader(isr);
String line = null;
rs = new HashSet<String>();
while ((line = br.readLine()) != null) {
rs.add(line);
}
} catch (FileNotFoundException e) {
System.out.println("WARNING: File '" + fileName + "' is not exist.");
} catch (IOException e) {
System.out.println("WARNING: IOException occured when read Whitelist.");
} finally {
try {
if (br != null) {
br.close();
}
} catch (IOException e) {
System.out.println("WARNING: IOException occured when close BufferedReader.");
}
}
return rs;
}