Wondering if there is an easy way to do a simple HTML escape/unescape in Objective C. What I want is something like this psuedo code:
NSString *string = @"<span>Foo</span>";
[string stringByUnescapingHTML];
Which returns
<span>Foo</span>
Hopefully unescaping all other HTML entities as well and even ASCII codes like Ӓ and the like.
Is there any methods in Cocoa Touch/UIKit to do this?
This link contains the solution below. Cocoa CF has the CFXMLCreateStringByUnescapingEntities function but that's not available on the iPhone.
@interface MREntitiesConverter : NSObject <NSXMLParserDelegate>{
NSMutableString* resultString;
}
@property (nonatomic, retain) NSMutableString* resultString;
- (NSString*)convertEntitiesInString:(NSString*)s;
@end
@implementation MREntitiesConverter
@synthesize resultString;
- (id)init
{
if([super init]) {
resultString = [[NSMutableString alloc] init];
}
return self;
}
- (void)parser:(NSXMLParser *)parser foundCharacters:(NSString *)s {
[self.resultString appendString:s];
}
- (NSString*)convertEntitiesInString:(NSString*)s {
if (!s) {
NSLog(@"ERROR : Parameter string is nil");
}
NSString* xmlStr = [NSString stringWithFormat:@"<d>%@</d>", s];
NSData *data = [xmlStr dataUsingEncoding:NSUTF8StringEncoding allowLossyConversion:YES];
NSXMLParser* xmlParse = [[[NSXMLParser alloc] initWithData:data] autorelease];
[xmlParse setDelegate:self];
[xmlParse parse];
return [NSString stringWithFormat:@"%@",resultString];
}
- (void)dealloc {
[resultString release];
[super dealloc];
}
@end
The MREntitiesConverter above is an HTML stripper, not encoder.
If you need an encoder, go here: Encode NSString for XML/HTML