NSString+Canonical

NSString+Canonical.h

#import <Foundation/Foundation.h>

@interface NSString (Canonical)

- (NSString *)canonicalizedString;

@end

NSString+Canonical.m

#import "NSString+Canonical.h"

@implementation NSString (Canonical)

- (NSString *)canonicalizedString
{
    NSCharacterSet *set = [NSCharacterSet alphanumericCharacterSet];
    
    NSString *lowercaseString = self.lowercaseString;
    
    NSRange range = NSMakeRange(0, lowercaseString.length);
    unichar *inputBuffer = malloc(range.length * sizeof(unichar));
    [lowercaseString getCharacters:inputBuffer range:range];
    
    unichar *outputBuffer = calloc(1, range.length * sizeof(unichar));
    size_t bufferOffset = 0;
    
    for (NSUInteger i = 0; i < range.length; i++)
    {
        unichar character = inputBuffer[i];
        if ([set characterIsMember:character])
            outputBuffer[bufferOffset++] = character;
    }
    
    NSString *canonicalizedString = [[NSString alloc] initWithCharacters:outputBuffer length:bufferOffset];
    
    free(inputBuffer);
    free(outputBuffer);
    
    return canonicalizedString;
}

@end