Java过滤Emoji字符

发表于

微信昵称支持Emoji表情，存储微信昵称时，若线上mysql编码未采用utfmb4，依然使用utf-8，向数据库写数据时就要过滤掉昵称中的Emoji表情。
过滤emoji可选用以下方法：

方法一：

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
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
public class EmojiFilter {
    /**
     * 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 (source == null || "".equals(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))
        {
            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 = 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();
            }
        }
    }
}

单元测试如下：

1
2
3
4
5
6
7
8
public void testEmojiFilter1() {
    boolean expireRight = true;
    String predictStr = "An awesome string with a few emojis!";
    String nickname= "An 😀awesome 😃string with a few 😉emojis!";
    String newNickname =  EmojiFilter.filterEmoji(nickname);
    System.out.println("newNickname: "+newNickname);
    assertTrue("newNickname result: " + newNickname, newNickname.equals(predictStr));
}

方法二：

如果是maven项目，在pom中引入

1
2
3
4
5
<dependency>
    <groupId>com.vdurmont</groupId>
    <artifactId>emoji-java</artifactId>
    <version>3.3.0</version>
</dependency>

使用库封装的方法：

1
String resultStr = EmojiParser.removeAllEmojis(str);

简单封装：

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
public class EmojiFilterUtil {
    /**
     * 检测是否有emoji字符
     */
    public static boolean containsEmoji(String source) {
        if (source == null || "".equals(source)) {
            return false;
        }
        if (source.length() == EmojiParser.removeAllEmojis(source).length()) {
            return false;
        }
        return true;
    }
}

EmojiParser提供emoji处理的各种方法，感兴趣自己试下。

方法三（推荐）：

过滤utf8mb4中非utf8字符，不仅仅是emoji

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
public class FilterUtf8Mb4Util {
    private static Logger logger = LoggerFactory.getLogger(FilterUtf8Mb4Util.class);
    /**
     * 过滤非汉字的utf8的字符（包括emoji）
     *
     * @param text 原字符串
     * @return 过滤后的字符串
     */
    public static String filterOffUtf8Mb4(String text) {
        byte[] bytes = new byte[0];
        try {
            bytes = text.getBytes("utf-8");
        } catch (UnsupportedEncodingException e) {
            logger.error("filterOffUtf8Mb4 text to bytes, UnsupportedEncodingException: {}", e);
        }
        ByteBuffer buffer = ByteBuffer.allocate(bytes.length);
        int i = 0;
        while (i < bytes.length) {
            short b = bytes[i];
            if (b > 0) {
                buffer.put(bytes[i++]);
                continue;
            }
            b += 256; //去掉符号位
            if (((b >> 5) ^ 0x06) == 0) {
                buffer.put(bytes, i, 2);
                i += 2;
                System.out.println("2");
            } else if (((b >> 4) ^ 0x0E) == 0) {
                System.out.println("3");
                buffer.put(bytes, i, 3);
                i += 3;
            } else if (((b >> 3) ^ 0x1E) == 0) {
                i += 4;
                System.out.println("4");
            } else if (((b >> 2) ^ 0xBE) == 0) {
                i += 5;
                System.out.println("5");
            } else {
                i += 6;
                System.out.println("6");
            }
        }
        buffer.flip();
        try {
            return new String(buffer.array(), "utf-8");
        } catch (UnsupportedEncodingException e) {
            logger.error("filterOffUtf8Mb4 result, UnsupportedEncodingException: {}", e);
            return "";
        }
    }
}

单元测试如下：

1
2
3
4
5
6
7
8
9
public class FilterUtf8Mb4UtilTest extends TestCase {
    public void testFilterOffUtf8Mb4() throws Exception {
        String illegalStr1 = "An 馃榾awesome 馃槂string with a few 馃槈emojis!";
        String illegalStr2 = "\uD83C\uDFFB鎯呫偡";
        assertTrue(!FilterUtf8Mb4Util.filterOffUtf8Mb4(illegalStr1).equals(illegalStr1));
        assertTrue(!FilterUtf8Mb4Util.filterOffUtf8Mb4(illegalStr2).equals(illegalStr2));
    }
}