基于Java编写emoji表情处理工具类

<!-- https://mvnrepository.com/artifact/com.vdurmont/emoji-java -->
<dependency>
    <groupId>com.vdurmont</groupId>
    <artifactId>emoji-java</artifactId>
    <version>5.1.1</version>
</dependency>

import java.io.UnsupportedEncodingException;
import java.net.URLDecoder;
import java.net.URLEncoder;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

import org.apache.commons.lang.StringUtils;

import com.vdurmont.emoji.EmojiParser;

/**
 * emoji表情过滤
 * @author madaha
 *
 */
public class EmojiFilter {
	   
	/**
	 * 判断是否存在Emoji
	 * @author madaha
	 *
	 * @param codePoint
	 * @return
	 */
	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
	 * @author madaha
	 *
	 * @param source 待过滤字符串
	 * @return
	 */
    public static String filterEmoji(String source) {
        if (StringUtils.isBlank(source)) {
            return source;
        }
        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);
            }
        }
        if (buf == null) {
            return source;
        } else {
            if (buf.length() == len) {
                buf = null;
                return source;
            } else {
                return buf.toString();
            }
        }
    }
    
    /**
	* @Description 将字符串中的emoji表情转换成可以在utf-8字符集数据库中保存的格式（表情占4个字节，需要utf8mb4字符集）
	* @param str 待转换字符串
	* @return 转换后字符串
	* @throws UnsupportedEncodingException
	* exception
	*/
	public static String emojiConvert1(String str) throws UnsupportedEncodingException {
		String patternString = "([\\x{10000}-\\x{10ffff}\ud800-\udfff])";

		Pattern pattern = Pattern.compile(patternString);
		Matcher matcher = pattern.matcher(str);
		StringBuffer sb = new StringBuffer();
		while (matcher.find()) {
			try {
				matcher.appendReplacement(sb, "[[" + URLEncoder.encode(matcher.group(1), "UTF-8") + "]]");
			} catch (UnsupportedEncodingException e) {
				System.out.println(e);
				throw e;
			}
		}
		matcher.appendTail(sb);
		// System.out.println("emojiConvert " + str + " to " + sb.toString() + ", len：" + sb.length());
		return sb.toString();
	}
    
	/**
	* @Description 还原utf8数据库中保存的含转换后emoji表情的字符串
	* @param str 转换前的字符串
	* @return 转换后的字符串
	* @throws UnsupportedEncodingException
	* exception
	*/
	public static String emojiRecovery2(String str) throws UnsupportedEncodingException {
		String patternString = "\\[\\[(.*?)\\]\\]";

		Pattern pattern = Pattern.compile(patternString);
		Matcher matcher = pattern.matcher(str);

		StringBuffer sb = new StringBuffer();
		while (matcher.find()) {
			try {
				matcher.appendReplacement(sb, URLDecoder.decode(matcher.group(1), "UTF-8"));
			} catch (UnsupportedEncodingException e) {
				System.out.println(e);
				throw e;
			}
		}
		matcher.appendTail(sb);
		// System.out.println("emojiRecovery " + str + " to " + sb.toString());
		return sb.toString();
	}
	
	/**
	 * emoji表情处理测试方法
	 * @author madaha
	 *
	 * @param args
	 */
	public static void main(String[] args) {
		String str = "emoji表情😁😁输入测试😁😂";
		System.out.println("原始字符为：\n" + str);
		System.out.println("to aliases 之后：\n" + EmojiParser.parseToAliases(str));
		
		str = EmojiParser.parseToAliases(str);
		System.out.println("还原：\n" + EmojiParser.parseToUnicode(str));
	}
    
}