Java判断字符串是否是乱码（亲测可用）

经过几天的努力，终于给爱酷学习网（http://www.icoolxue.com）加上了搜索引擎的支持，现在你可以搜索自己喜欢的视频教程啦。
PS：爱酷学习网是一个全面的视频教程网站，有各类计算机类视频如Java/C/C++/Android/Hiberante等等。

而由此也带来了一个问题，在用户输入查询字符串之后，虽然我已经想尽一切办法解决了乱码问题，但是真正在线上的时候，还是遇到了乱码，百思而不得其解：

可以看到，乱码问题一直存在，于是我在想，如果能判断搜索字符串如果是乱码的话，就不将该条搜索进行处理（意思就是说只搜索，而不将该字符串存放到数据库中），好吧，代码如下：

Java

/** * 判断字符是否是中文 * * @param c 字符 * @return 是否是中文 */ 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; } /** * 判断字符串是否是乱码 * * @param strName 字符串 * @return 是否是乱码 */ 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; if (result > 0.4) { return true; } else { return false; } } public static void main(String[] args) { System.out.println(isMessyCode("韩顺平")); System.out.println(isMessyCode("你好")); }

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54

/**      * 判断字符是否是中文      *      * @param c 字符      * @return 是否是中文      */      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 ;      }        /**      * 判断字符串是否是乱码      *      * @param strName 字符串      * @return 是否是乱码      */      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 ;          if ( result > 0.4 ) {              return true ;          } else {              return false ;          }        }        public static void main ( String [ ] args ) {          System . out . println ( isMessyCode ( "韩顺平" ) ) ;          System . out . println ( isMessyCode ( "你好" ) ) ;      }

相关代码已经注释，谢谢支持。