TCPDF_FONTS::getUniord()

Complexity

Conditions	15
Paths	25

Size

Total Lines	57
Code Lines	41

Duplication

Lines	0
Ratio	0 %

Importance

Changes	1
Bugs	0	Features	0

<?php
	public static function getUniord($uch) {
		if (function_exists('mb_convert_encoding')) {
			list(, $char) = @unpack('N', mb_convert_encoding($uch, 'UCS-4BE', 'UTF-8'));

It seems like mb_convert_encoding($uch, 'UCS-4BE', 'UTF-8') can also be of type array; however, parameter $string of unpack() does only seem to accept string, maybe add an additional type check?

			if ($char >= 0) {
				return $char;
			}
		}
		$bytes = array(); // array containing single character byte sequences
		$countbytes = 0;
		$numbytes = 1; // number of octetc needed to represent the UTF-8 character
		$length = strlen($uch);
		for ($i = 0; $i < $length; ++$i) {
			$char = ord($uch[$i]); // get one string character at time
			if ($countbytes == 0) { // get starting octect
				if ($char <= 0x7F) {
					return $char; // use the character "as is" because is ASCII
				} elseif (($char >> 0x05) == 0x06) { // 2 bytes character (0x06 = 110 BIN)
					$bytes[] = ($char - 0xC0) << 0x06;
					++$countbytes;
					$numbytes = 2;
				} elseif (($char >> 0x04) == 0x0E) { // 3 bytes character (0x0E = 1110 BIN)
					$bytes[] = ($char - 0xE0) << 0x0C;
					++$countbytes;
					$numbytes = 3;
				} elseif (($char >> 0x03) == 0x1E) { // 4 bytes character (0x1E = 11110 BIN)
					$bytes[] = ($char - 0xF0) << 0x12;
					++$countbytes;
					$numbytes = 4;
				} else {
					// use replacement character for other invalid sequences
					return 0xFFFD;
				}
			} elseif (($char >> 0x06) == 0x02) { // bytes 2, 3 and 4 must start with 0x02 = 10 BIN
				$bytes[] = $char - 0x80;
				++$countbytes;
				if ($countbytes == $numbytes) {
					// compose UTF-8 bytes to a single unicode value
					$char = $bytes[0];
					for ($j = 1; $j < $numbytes; ++$j) {
						$char += ($bytes[$j] << (($numbytes - $j - 1) * 0x06));
					}
					if ((($char >= 0xD800) AND ($char <= 0xDFFF)) OR ($char >= 0x10FFFF)) {
						// The definition of UTF-8 prohibits encoding character numbers between
						// U+D800 and U+DFFF, which are reserved for use with the UTF-16
						// encoding form (as surrogate pairs) and do not directly represent
						// characters.
						return 0xFFFD; // use replacement character
					} else {
						return $char;
					}
				}
			} else {
				// use replacement character for other invalid sequences
				return 0xFFFD;
			}
		}
		return 0xFFFD;
	}