Some utility code for examining strings for UTF-8-ness

utf8utility.m

enum UTF8SequenceLength {
	Bytes1   = 0,
	Bytes2   = 0b11000000,
	Bytes3   = 0b11100000,
	Bytes4   = 0b11110000,
	BytesErr = 0b10000000,
};

enum UTF8ParsingMode {
	UTF8ParsingModeNone = 0,
	UTF8ParsingModeParsing = 1
};

typedef enum UTF8SequenceLength UTF8SequenceLength;
typedef enum UTF8ParsingMode UTF8ParsingMode;

#define UTF8SequenceMask	(0xF0)

@implementation NSMutableString (AppendBinaryString)

- (void) appendBinaryStringForValue: (char)c {
	int i = 8;
	while (i) {
		[self appendString: (c&0x80)?@"1":@"0"];
		
		c <<= 1;
		i--;
	}
}

@end

@implementation NSString (UTF8Dump)

- (NSString *)dumpUTF8Decode {
	NSMutableString *result = [@"" mutableCopy];
	NSUInteger stringIndex = 0;
	
	NSData *data = [self dataUsingEncoding:NSUTF8StringEncoding];
	if (!data) return nil;
	
	const char *bytes = data.bytes;
	
	NSUInteger byteCount = 0;
	UTF8ParsingMode currentMode = UTF8ParsingModeNone;
	
	for (NSUInteger i = 0; i<data.length; i++) {
		char deesaByte = bytes[i];
		UTF8SequenceLength deesaLength = deesaByte & UTF8SequenceMask;
		
		if (byteCount == 0) {
			[result appendFormat:@"%C ", [self characterAtIndex:stringIndex++]];
			
			switch (deesaLength) {
				case Bytes2:
					byteCount = 2;
					currentMode = UTF8ParsingModeParsing;
					break;
					
				case Bytes3:
					byteCount = 3;
					currentMode = UTF8ParsingModeParsing;
					break;
					
				case Bytes4:
					byteCount = 4;
					currentMode = UTF8ParsingModeParsing;
					break;
					
				case BytesErr:
					[result appendString:@" err "];
					break;
					
				default:
					byteCount = 1;
					currentMode = UTF8ParsingModeNone;
					break;
			}
		}
		
		[result appendBinaryStringForValue:deesaByte];
		byteCount--;
		
		if (byteCount == 0) {
			[result appendString:@"\n"];
		}
		else {
			[result appendString:@" "];
		}
	}
	
	return result;
}

@end