Java判断中文字符串是否乱码-优快云博客

本文链接：https://blog.youkuaiyun.com/pyzheng/article/details/84712981

本文介绍了一个Java工具类，用于检测字符串中是否包含中文字符及判断文本是否为乱码。通过Unicode块来识别中文字符，并提供了一种方法将ISO-8859-1编码的中文乱码文本转换为正确的UTF-8编码。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

[url]http://my.oschina.net/cevin15/blog/402975[/url]

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 ; 
    }
}