Java判断中文字符串是否乱码

下面是编程之家 jb51.cc 通过网络收集整理的代码片段。

编程之家小编现在分享给大家，也给大家做个参考。

import java.util.regex.Matcher;
import java.util.regex.Pattern;
 
public class ChineseUtill {
 
    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;
    }
     
    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;
        }
    }
     
     
    public static String tochinese(String msg){
        if(isMessyCode(msg)){
            try {
                return new String(msg.getBytes("ISO8859-1"),"UTF-8");
            } catch (Exception e) {
            }
        }
        return msg ; 
    }
}

以上是编程之家(jb51.cc)为你收集整理的全部代码内容，希望文章能够帮你解决所遇到的程序开发问题。

如果觉得编程之家网站内容还不错，欢迎将编程之家网站推荐给程序员好友。