Java判断中文乱码

在网页爬取或多系统对接数据传输经常会遇到中文乱码的问题，因此需要判断是否出现中文乱码现象。一个简单的判断方法如下：

       /**

    * 是否乱码

    * @param strName

    * @return

    */

   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 = ch.length; 

      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; 

             } 

          } 

      } 

      float result = count / chLength; 

      return result > 0 ? true : false ;

   }

 

   /**

    * 是否为中文

    * @param c

    * @return

    */

   public 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; 

   }