Emoji 特殊字符處理

Emoji 特殊字符處理 ，對UTF-8的MYSQL數據庫插入Emoji等 特殊字符時會報錯。

1. 過濾

2. MYSQL字符設置爲utf8mb4

public class EmojiFilter {


    /**
     * 檢測是否有emoji字符
     * 
     * @param source
     * @return 一旦含有就拋出
     */
    public static boolean containsEmoji(String source) {
        if (StringUtils.isEmpty(source)) {
            return false;
        }
        int len = source.length();
        for (int i = 0; i < len; i++) {
            char codePoint = source.charAt(i);
            if (isEmojiCharacter(codePoint)) {
                // do nothing，判斷到了這裏表明，確認有表情字符
                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));
    }


    /**
     * 過濾emoji 或者 其他非文字類型的字符
     * 
     * @param source
     * @return
     */
    public static String filterEmoji(String source) {
        if (!containsEmoji(source)) {
            return source;// 如果不包含，直接返回
        }
        // 到這裏鐵定包含
        StringBuilder buf = null;
        int len = source.length();
        for (int i = 0; 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;// 如果沒有找到 emoji表情，則返回源字符串
        } else {
            if (buf.length() == len) {// 這裏的意義在於儘可能少的toString，因爲會重新生成字符串
                buf = null;
                return source;
            } else {
                return buf.toString();
            }
        }
    }
}