emoji处理方法

在做微信公众号开发时碰到了获取微信基本信息的需求，但是在像数据库保存用户昵称的时候出错了，

出错原因是微信用户的昵称中包含emoji等特殊符号，表情图片，

mysql数据库使用的是utf8,最大存储3个字节，而emoji等以4个字节进行的保存，所以保存不了

处理方法：

1：修改数据库编码由utf8升级为utf8mb4，utf8mb4是utf8的超级，包含全部unicode编码；该方法没有具体操作；

2：进行过滤，对获取到的用户昵称进行编码过滤，对emoji等替换为“”空；但是该方法在碰到iso上的一些emoji就失败了。在下方增加了一些处理过滤方法；

该过滤方法找自于网上
 /**
     * 检测是否有emoji字符
     * @param source
     * @return 一旦含有就抛出
     */
    public static boolean containsEmoji(String source) {
        if (StringUtils.isBlank(source)) {
            return false;
        }

        int len = source.length();

        for (int i = ; i < len; i++) {
            char codePoint = source.charAt(i);

            if (isEmojiCharacter(codePoint)) {
                //do nothing，判断到了这里表明，确认有表情字符
                return true;
            }
        }

        return false;
    }

    private static boolean isEmojiCharacter(char codePoint) {
         return (codePoint == 0x0) ||
                 (codePoint == 0x9) ||
                 (codePoint == 0xA) ||
                 (codePoint == 0xD) ||
                 ((codePoint >= 0x20) && (codePoint <= 0xD7FF)) ||
                 ((codePoint >= 0xE000) && (codePoint <= 0xFFFD)) ||
                 ((codePoint >= 0x10000) && (codePoint <= 0x10FFFF));
    }

    /**
     * 过滤emoji 或者 其他非文字类型的字符
     * @param source
     * @return
     */
    public static String filterEmoji(String source) {

        if (!containsEmoji(source)) {
　　　　　　　//特殊处理
　　　　　　　source = filterSpecialCharacter(source);
            return source;//如果不包含，直接返回
        }
        //到这里铁定包含
        StringBuilder buf = null;

        int len = source.length();

        for (int i = ; i < len; i++) {
            char codePoint = source.charAt(i);

            if (isEmojiCharacter(codePoint)) {
                if (buf == null) {
                    buf = new StringBuilder(source.length());
                }

                buf.append(codePoint);
            } else {
            }
        }

        if (buf == null) {
            return source;//如果没有找到 emoji表情，则返回源字符串
        } else {
            if (buf.length() == len) {//这里的意义在于尽可能少的toString，因为会重新生成字符串
                buf = null;
                return source;
            } else {
                return buf.toString();
            }
        }

    }

 /**
     * 判断特殊字符，替换成空格
     *
     * @param source
     * @return 过滤后的字符串
     */
    public static String filterSpecialCharacter(String source) {
        if(StringUtils.isNotBlank(source)){
            Pattern emoji = Pattern.compile("[\ud83c\udc00-\ud83c\udfff]|[\ud83d\udc00-\ud83d\udfff]|[\u2600-\u27ff]",Pattern . UNICODE_CASE | Pattern . CASE_INSENSITIVE);
                Matcher emojiMatcher = emoji.matcher(source);
                if (emojiMatcher.find()) {
                   return source.replaceAll("[\\ud800\\udc00-\\udbff\\udfff\\ud800-\\udfff]", "");
             }else{
                 return source;
             }
        }else{
            return source;
        }
    } 

方法3：

    /**
     * 过滤掉超过3个字节的UTF8字符
     * @param text
     * @return
     * @throws UnsupportedEncodingException
     */
    public static String filterOffUtf8Mb4(String text) throws UnsupportedEncodingException {
        byte[] bytes = text.getBytes("utf-8");
        ByteBuffer buffer = ByteBuffer.allocate(bytes.length);
        int i = ;
        while (i < bytes.length) {
            short b = bytes[i];
            if (b > ) {
                buffer.put(bytes[i++]);
                continue;
            }

            b += ; // 去掉符号位

            if (((b >> ) ^ 0x6) == ) {
                buffer.put(bytes, i, );
                i += ;
            } else if (((b >> ) ^ 0xE) == ) {
                buffer.put(bytes, i, );
                i += ;
            } else if (((b >> ) ^ 0x1E) == ) {
                i += ;
            } else if (((b >> ) ^ 0x3E) == ) {
                i += ;
            } else if (((b >> ) ^ 0x7E) == ) {
                i += ;
            } else {
                buffer.put(bytes[i++]);
            }
        }
        buffer.flip();
        return new String(buffer.array(), "utf-8");
    }

方法4：进行编码转换保存

将需要处理的字符串进行编码转换，存储到数据库

/**
    * 字符串转换ascii
    */
   public static String string2Unicode(String string) {
       StringBuffer unicode = new StringBuffer();
       for (int i = ; i < string.length(); i++) {
           // 取出每一个字符
           char c = string.charAt(i);
           // 转换为unicode
           unicode.append("\\u" + Integer.toHexString(c));
       }
       return unicode.toString();
   }
   /**
    * ascii 转字符串
    */
   public static String unicode2String(String unicode) {
       StringBuffer string = new StringBuffer();
       String[] hex = unicode.split("\\\\u");
       for (int i = ; i < hex.length; i++) {
           // 转换出每一个代码点
           int data = Integer.parseInt(hex[i], );
           // 追加成string
           string.append((char) data);
       }
       return string.toString();
   }

在页面获取的时候进行处理

//js ascii转string
function ascii2native(){
    //var character=document.getElementById("nikeunicode").value.split("\\u");
    var x=document.getElementsByClassName("nikeunicode");

    var k;
    for (k = ; k < x.length; k++) {
        console.log(x[k].innerHTML);
        var character=x[k].innerHTML.split("\\u");
        var native=character[];
        console.log(native);
        for(var i=;i<character.length;i++){
            var code=character[i];
            native+=String.fromCharCode(parseInt("0x"+code.substring(,)));
            if(code.length>){
                native+=code.substring(,code.length);
            }
        }
        x[k].innerHTML=native;
    }

    //document.getElementById("nikeunicode").value=native1;
}

页面处理过的效果

上文中的方法在android输入法自带的emoji下,没有起到效果,在上文方法2的if (isEmojiCharacter(codePoint)) 处加入下列判断

private static boolean isChinese(char c) {
        Character.UnicodeScript sc = Character.UnicodeScript.of(c);
        if (sc == Character.UnicodeScript.HAN) {
            return true;
        }
        return false;
    }

    public static boolean isPunctuation(char c) {
        Character.UnicodeBlock ub = Character.UnicodeBlock.of(c);
        if (    // punctuation, spacing, and formatting characters
                ub == Character.UnicodeBlock.GENERAL_PUNCTUATION
                // symbols and punctuation in the unified Chinese, Japanese and Korean script
                || ub == Character.UnicodeBlock.CJK_SYMBOLS_AND_PUNCTUATION
                // fullwidth character or a halfwidth character
                || ub == Character.UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS
                // vertical glyph variants for east Asian compatibility
                || ub == Character.UnicodeBlock.CJK_COMPATIBILITY_FORMS
                // vertical punctuation for compatibility characters with the Chinese Standard GB 18030
                || ub == Character.UnicodeBlock.VERTICAL_FORMS
                // ascii
                || ub == Character.UnicodeBlock.BASIC_LATIN
                ) {
            return true;
        } else {
            return false;
        }
    }

    private static Boolean isUserDefined(char c) {
        Character.UnicodeBlock ub = Character.UnicodeBlock.of(c);
        if (ub == Character.UnicodeBlock.NUMBER_FORMS
                || ub == Character.UnicodeBlock.ENCLOSED_ALPHANUMERICS
                || ub == Character.UnicodeBlock.LETTERLIKE_SYMBOLS
                || c == '\ufeff'
                || c == '\u00a0'
                )
            return true;
        return false;
    }

    public static boolean isMessy(String str)  {
        float chlength = ;
        float count = ;
        for(int i = ; i < str.length(); i++) {
            char c = str.charAt(i);
            if(isPunctuation(c) || isUserDefined(c))
                continue;
            else {
                if(!isChinese(c)) {
                    count = count + ;
                }
                chlength ++;
            }
        }
        float result = count / chlength;
        if(result > 0.3){
            return true;
        }else{
            return false;
        }

    }