一段很好用的判断字符串转换后乱码问题的代码,分享一下。
/**
* 判断字符串是否乱码
* @author yang.shen
* @param strName
* @return boolean
*/
public static boolean isMessyCode(String strName) {
Pattern p = Pattern.compile("\\s*|\t*|\r*|\n*");
Matcher m = p.matcher(strName);
String after = m.replaceAll("");
String temp = after.replaceAll("\\p{P}", "");
char[] ch = temp.trim().toCharArray();
float chLength = 0;
float count = 0;
for (int i = 0; i < ch.length; i++) {
char c = ch[i];
if (!Character.isLetterOrDigit(c)) {
if (!isChinese(c)) {
count = count + 1;
}
chLength++;
}
}
float result = count / chLength;
if (result > 0.4) {
return true;
} else {
return false;
}
}
private static boolean isChinese(char c) {
Character.UnicodeBlock ub = Character.UnicodeBlock.of(c);
if (ub == Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS
|| ub == Character.UnicodeBlock.CJK_COMPATIBILITY_IDEOGRAPHS
|| ub == Character.UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS_EXTENSION_A
|| ub == Character.UnicodeBlock.GENERAL_PUNCTUATION
|| ub == Character.UnicodeBlock.CJK_SYMBOLS_AND_PUNCTUATION
|| ub == Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS) {
return true;
}
return false;
}