Requests::compatible_gzinflate( string $gz_data ): string|bool

Source

public static function compatible_gzinflate($gz_data) {
	if (is_string($gz_data) === false) {
		throw InvalidArgument::create(1, '$gz_data', 'string', gettype($gz_data));
	}

	if (trim($gz_data) === '') {
		return false;
	}

	// Compressed data might contain a full zlib header, if so strip it for
	// gzinflate()
	if (substr($gz_data, 0, 3) === "\x1f\x8b\x08") {
		$i   = 10;
		$flg = ord(substr($gz_data, 3, 1));
		if ($flg > 0) {
			if ($flg & 4) {
				list($xlen) = unpack('v', substr($gz_data, $i, 2));
				$i         += 2 + $xlen;
			}

			if ($flg & 8) {
				$i = strpos($gz_data, "\0", $i) + 1;
			}

			if ($flg & 16) {
				$i = strpos($gz_data, "\0", $i) + 1;
			}

			if ($flg & 2) {
				$i += 2;
			}
		}

		$decompressed = self::compatible_gzinflate(substr($gz_data, $i));
		if ($decompressed !== false) {
			return $decompressed;
		}
	}

	// If the data is Huffman Encoded, we must first strip the leading 2
	// byte Huffman marker for gzinflate()
	// The response is Huffman coded by many compressors such as
	// java.util.zip.Deflater, Ruby's Zlib::Deflate, and .NET's
	// System.IO.Compression.DeflateStream.
	//
	// See https://decompres.blogspot.com/ for a quick explanation of this
	// data type
	$huffman_encoded = false;

	// low nibble of first byte should be 0x08
	list(, $first_nibble) = unpack('h', $gz_data);

	// First 2 bytes should be divisible by 0x1F
	list(, $first_two_bytes) = unpack('n', $gz_data);

	if ($first_nibble === 0x08 && ($first_two_bytes % 0x1F) === 0) {
		$huffman_encoded = true;
	}

	if ($huffman_encoded) {
		$decompressed = @gzinflate(substr($gz_data, 2));
		if ($decompressed !== false) {
			return $decompressed;
		}
	}

	if (substr($gz_data, 0, 4) === "\x50\x4b\x03\x04") {
		// ZIP file format header
		// Offset 6: 2 bytes, General-purpose field
		// Offset 26: 2 bytes, filename length
		// Offset 28: 2 bytes, optional field length
		// Offset 30: Filename field, followed by optional field, followed
		// immediately by data
		list(, $general_purpose_flag) = unpack('v', substr($gz_data, 6, 2));

		// If the file has been compressed on the fly, 0x08 bit is set of
		// the general purpose field. We can use this to differentiate
		// between a compressed document, and a ZIP file
		$zip_compressed_on_the_fly = ((0x08 & $general_purpose_flag) === 0x08);

		if (!$zip_compressed_on_the_fly) {
			// Don't attempt to decode a compressed zip file
			return $gz_data;
		}

		// Determine the first byte of data, based on the above ZIP header
		// offsets:
		$first_file_start = array_sum(unpack('v2', substr($gz_data, 26, 4)));
		$decompressed     = @gzinflate(substr($gz_data, 30 + $first_file_start));
		if ($decompressed !== false) {
			return $decompressed;
		}

		return false;
	}

	// Finally fall back to straight gzinflate
	$decompressed = @gzinflate($gz_data);
	if ($decompressed !== false) {
		return $decompressed;
	}

	// Fallback for all above failing, not expected, but included for
	// debugging and preventing regressions and to track stats
	$decompressed = @gzinflate(substr($gz_data, 2));
	if ($decompressed !== false) {
		return $decompressed;
	}

	return false;
}

View all references View on Trac View on GitHub