检测中文
描述：判断是否包含中文
代码语言：javascript复制public static boolean isChinese(String s) {
return s.codePoints().anyMatch(
codepoint ->
Character.UnicodeScript.of(codepoint) == Character.UnicodeScript.HAN);
}
public static boolean isChinese(char c) {
Character.UnicodeScript sc = Character.UnicodeScript.of(c);
if (sc == Character.UnicodeScript.HAN) {
return true;
}
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;
}
true：包含中文
false：不包含中文检测乱码
代码语言：javascript复制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;
}
