表情符号过滤

来源：互联网发布：威宁谢成本数据库编辑：程序博客网时间：2024/05/06 08:22

public class EmojiFilter {
/**
* 过滤emoji 或者其他非文字类型的字符
*
* @param source 需要被过滤的字符串
* @return
*/
public static String filterEmoji(Object source) {
String sourceStr = " ";//针对微信传递过来的值为空数据时，默认为空字符串
if(Toolkit.isEmpty(source)){
return sourceStr;
}

sourceStr = source.toString();

Pattern emoji = Pattern.compile("[\ud83c\udc00-\ud83c\udfff]|[\ud83d\udc00-\ud83d\udfff]|[\u2600-\u27ff]",
Pattern.UNICODE_CASE | Pattern.CASE_INSENSITIVE);
Matcher emojiMatcher = emoji.matcher(sourceStr);
if (emojiMatcher.find()) {
sourceStr = emojiMatcher.replaceAll("");
return sourceStr;
}

return sourceStr;
}

// emoji表情字符串 mysql utf8数据库无法o.
public static String filterEmoji1(String source) {
if(source != null)
{
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())
{
source = emojiMatcher.replaceAll("*");
return source ;
}
return source;
}
return source;
}

/**
* 将emoji表情替换成*
*
* @param source
* @return 过滤后的字符串
*/
public static String filterEmoji(String source) {
if(StringUtils.isNotBlank(source)){
return source.replaceAll("[\\ud800\\udc00-\\udbff\\udfff\\ud800-\\udfff]", "*");
}else{
return source;
}
}
public static void main(String[] arg ){
try{
String text = "啦啦啦\uD83C\uDFA6 face\uD860\uDD5D \uD860\uDE07 \uD860\uDEE2 \uD863\uDCCA \uD863\uDCCD \uD863\uDCD2 \uD867\uDD98 ";
String text1 = EmojiFilter.emojiConvert1(text);
System.out.println(text1);

String text2 = EmojiFilter.emojiRecovery2(text1);
System.out.println(text2);
}catch (Exception ex){
ex.printStackTrace();
}
}


/**
* @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) {
// LOG.error("emojiConvert error", e);
throw e;
}
}
matcher.appendTail(sb);
// LOG.debug("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
* 转换后的字符串
* @return 转换前的字符串
* @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) {
// LOG.error("emojiRecovery error", e);
throw e;
}
}
matcher.appendTail(sb);
// LOG.debug("emojiRecovery " + str + " to " + sb.toString());
return sb.toString();
}

}

0 0