Created
December 4, 2012 07:57
-
-
Save siqin/4201667 to your computer and use it in GitHub Desktop.
Remove Emoji in NSString
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// XCode 4.2.1 | |
@implementation NSString(EmojiExtension) | |
- (NSString*)removeEmoji { | |
__block NSMutableString* temp = [NSMutableString string]; | |
[self enumerateSubstringsInRange: NSMakeRange(0, [self length]) options:NSStringEnumerationByComposedCharacterSequences usingBlock: | |
^(NSString *substring, NSRange substringRange, NSRange enclosingRange, BOOL *stop){ | |
const unichar hs = [substring characterAtIndex: 0]; | |
// surrogate pair | |
if (0xd800 <= hs && hs <= 0xdbff) { | |
const unichar ls = [substring characterAtIndex: 1]; | |
const int uc = ((hs - 0xd800) * 0x400) + (ls - 0xdc00) + 0x10000; | |
[temp appendString: (0x1d000 <= uc && uc <= 0x1f77f)? @"": substring]; // U+1D000-1F77F | |
// non surrogate | |
} else { | |
[temp appendString: (0x2100 <= hs && hs <= 0x26ff)? @"": substring]; // U+2100-26FF | |
} | |
}]; | |
return temp; | |
} | |
@end |
just to followup. -- apparently the [:emoji:]
property used in the ICU transform includes digits, some punctuation, other things not generally though to be emoji.
I am finding this method on an NSString category working better
- (NSString *)stringByRemovingEmoji {
static NSRegularExpression * regex = nil;
static dispatch_once_t onceToken;
dispatch_once(&onceToken, ^{
// remove all emoji less those that are digits, punctuation, letters, latin 1 supplement or letter like symbols
// or BIDI Non-Spacing Mark
NSError * error = nil;
regex = [NSRegularExpression regularExpressionWithPattern:@"([[:emoji:]--[:digit:]--[:punctuation:]--[:letter:]--[:block=Latin-1_sup:]--[:block=letter-like-symbols:]]|\\uFE0F)" options: 0 error:&error];
if (error){
NSLog(@"Error forming regex");
}
});
return [regex stringByReplacingMatchesInString:self options:0 range:NSMakeRange(0, self.length) withTemplate:@""];
}
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Much simpler way is to use a string transform: -- this will move all emoji code points, and preserve non-latin characters, accents etc
Eg
[@"🤯!!! ক❤️testé🧡💚💛せぬ❤️🔥👩🏿🦰" stringByApplyingTransform: @"[:emoji:] remove" reverse:NO]
returns
!!! ক️testéせぬ️