HTML character decoding in Objective-C / Cocoa Touch

Question

First of all, I found this: Objective C HTML escape/unescape, but it doesn\'t work for me.

My encoded characters (come from a RSS feed, btw) look like this: &a

Answer 1

As if you need another solution! This one is pretty simple and quite effective:

@interface NSString (NSStringCategory)
- (NSString *) stringByReplacingISO8859Codes;
@end


@implementation NSString (NSStringCategory)
- (NSString *) stringByReplacingISO8859Codes
{
    NSString *dataString = self;
    do {
        //*** See if string contains &# prefix
        NSRange range = [dataString rangeOfString: @"&#" options: NSRegularExpressionSearch];
        if (range.location == NSNotFound) {
            break;
        }
        //*** Get the next three charaters after the prefix
        NSString *isoHex = [dataString substringWithRange: NSMakeRange(range.location + 2, 3)];
        //*** Create the full code for replacement
        NSString *isoString = [NSString stringWithFormat: @"&#%@;", isoHex];
        //*** Convert to decimal integer
        unsigned decimal = 0;
        NSScanner *scanner = [NSScanner scannerWithString: [NSString stringWithFormat: @"0%@", isoHex]];
        [scanner scanHexInt: &decimal];
        //*** Use decimal code to get unicode character
        NSString *unicode = [NSString stringWithFormat:@"%C", decimal];
        //*** Replace all occurences of this code in the string
        dataString = [dataString stringByReplacingOccurrencesOfString: isoString withString: unicode];
    } while (TRUE); //*** Loop until we hit the NSNotFound

    return dataString;
}
@end