ps:如果是因为服务器不支持Emoji,需要剔除Emoji的话,其实不用那么麻烦,把字符串内容Unicode编码一下就OK了,另附一个Unicode编码/解码
2019.7.1更新加上了matchesInStringWithRegex方法。
2020.9.10 增加Swift版
不废话 上代码,让广大码农来检测。。。
=======================================================
OC版:
- (NSArray *)isContainsEmoji {
NSMutableArray *array1 = [[NSMutableArray alloc] init];
NSMutableArray *array2 = [[NSMutableArray alloc] init];
NSRange range;
NSString *emoji = @"aas d!`2完 全䴎无力❤️⚽️。。..~#$, 包括生僻字()";
for (int i = 0; i < emoji.length; i += range.length) {
range = [emoji rangeOfComposedCharacterSequenceAtIndex:i];
NSString *string = [emoji substringWithRange:range];
NSUInteger length = [string lengthOfBytesUsingEncoding:NSUTF8StringEncoding];
if (length >= 4) {
//正则4个字节或以上的生僻字、其他字符集
NSString *regex = @"[\\uD840\\uDC00-\\uD87A\\uDFEF]";
NSArray *matches = [string matchesInStringWithRegex:regex];
if (!matches.count) {
[array1 addObject:MOStringWithFormat(@"字符串:'%@', 字节:'%ld'", string, length)];
} else {
[array2 addObject:MOStringWithFormat(@"字符串:'%@', 字节:'%ld'", string, length)];
}
} else {
[array2 addObject:MOStringWithFormat(@"字符串:'%@', 字节:'%ld'", string, length)];
}
}
NSLog(@"Emoji>> %@, \n非Emoji>> %@", array1, array2);
return array1;
}
- (NSArray *)matchesInStringWithRegex:(NSString *)regex {
NSString *string = [NSString stringWithString:self];
NSRegularExpression *regular = [NSRegularExpression regularExpressionWithPattern:regex options:NSRegularExpressionCaseInsensitive error:nil];
NSArray *matches = [regular matchesInString:string options:NSMatchingReportCompletion range:NSMakeRange(0, string.length)];
if (!matches.count) {
return nil;
}
return matches;
}
=======================================================
log:
Emoji>> (
"字符串:'', 字节:'4'",
"字符串:'', 字节:'4'",
"字符串:'', 字节:'4'",
"字符串:'', 字节:'4'",
"字符串:'', 字节:'4'",
"字符串:'', 字节:'4'",
"字符串:'', 字节:'4'",
"字符串:'', 字节:'4'",
"字符串:'', 字节:'4'",
"字符串:'', 字节:'4'",
"字符串:'', 字节:'8'",
"字符串:'', 字节:'8'",
"字符串:'', 字节:'8'",
"字符串:'❤️', 字节:'27'",
"字符串:'', 字节:'25'",
"字符串:'', 字节:'18'",
"字符串:'', 字节:'4'",
"字符串:'', 字节:'4'",
"字符串:'⚽️', 字节:'6'",
"字符串:'', 字节:'8'",
"字符串:'', 字节:'8'",
"字符串:'', 字节:'4'",
"字符串:'', 字节:'4'",
"字符串:'', 字节:'4'",
"字符串:'', 字节:'4'",
),
非Emoji>> (
"字符串:'a', 字节:'1'",
"字符串:'a', 字节:'1'",
"字符串:'s', 字节:'1'",
"字符串:' ', 字节:'1'",
"字符串:'d', 字节:'1'",
"字符串:'!', 字节:'1'",
"字符串:'`', 字节:'1'",
"字符串:'2', 字节:'1'",
"字符串:'完', 字节:'3'",
"字符串:' ', 字节:'1'",
"字符串:' ', 字节:'1'",
"字符串:'全', 字节:'3'",
"字符串:'䴎', 字节:'3'",
"字符串:'无', 字节:'3'",
"字符串:'力', 字节:'3'",
"字符串:'。', 字节:'3'",
"字符串:'。', 字节:'3'",
"字符串:'.', 字节:'1'",
"字符串:'.', 字节:'1'",
"字符串:'~', 字节:'1'",
"字符串:'#', 字节:'1'",
"字符串:'$', 字节:'1'",
"字符串:',', 字节:'1'",
"字符串:' ', 字节:'1'",
"字符串:'包', 字节:'3'",
"字符串:'括', 字节:'3'",
"字符串:'生', 字节:'3'",
"字符串:'僻', 字节:'3'",
"字符串:'字', 字节:'3'",
"字符串:'(', 字节:'1'",
"字符串:'', 字节:'4'",
"字符串:')', 字节:'1'",
)
=======================================================
Swift版:
/// 检测是否包含Emoji表情
var isContainsEmoji: Bool {
for char in self {
let str = String(char)
if str.lengthOfBytes(using: .utf8) >= 4 {
if str.matches("[\\uD840\\uDC00-\\uD87A\\uDFEF]").isEmpty {
return true
}
}
}
return false
}
/// 匹配正则表达式,并返回匹配结果
/// - Parameter regex: 正则表达式
/// - Returns: 匹配结果
func matches(_ regex: String) -> [NSTextCheckingResult] {
guard let regular = try? NSRegularExpression(pattern: regex, options: .caseInsensitive) else {
return []
}
return regular.matches(in: self, options: .reportCompletion, range: NSRange(location: 0, length: count))
}
=======================================================
该方法无需更新所谓的列表,可以无视后续增加emoji,一劳永逸。
妈妈再也不用担心检测不到emoji了!!!
欢迎吐槽!