1: <?php declare(strict_types = 1);
2:
3: namespace PHPStan\PhpDocParser\Ast\ConstExpr;
4:
5: use PHPStan\PhpDocParser\Ast\NodeAttributes;
6: use function addcslashes;
7: use function assert;
8: use function dechex;
9: use function ord;
10: use function preg_replace_callback;
11: use function sprintf;
12: use function str_pad;
13: use function strlen;
14: use const STR_PAD_LEFT;
15:
16: class ConstExprStringNode implements ConstExprNode
17: {
18:
19: public const SINGLE_QUOTED = 1;
20: public const DOUBLE_QUOTED = 2;
21:
22: use NodeAttributes;
23:
24: public string $value;
25:
26: /** @var self::SINGLE_QUOTED|self::DOUBLE_QUOTED */
27: public $quoteType;
28:
29: /**
30: * @param self::SINGLE_QUOTED|self::DOUBLE_QUOTED $quoteType
31: */
32: public function __construct(string $value, int $quoteType)
33: {
34: $this->value = $value;
35: $this->quoteType = $quoteType;
36: }
37:
38:
39: public function __toString(): string
40: {
41: if ($this->quoteType === self::SINGLE_QUOTED) {
42: // from https://github.com/nikic/PHP-Parser/blob/0ffddce52d816f72d0efc4d9b02e276d3309ef01/lib/PhpParser/PrettyPrinter/Standard.php#L1007
43: return sprintf("'%s'", addcslashes($this->value, '\'\\'));
44: }
45:
46: // from https://github.com/nikic/PHP-Parser/blob/0ffddce52d816f72d0efc4d9b02e276d3309ef01/lib/PhpParser/PrettyPrinter/Standard.php#L1010-L1040
47: return sprintf('"%s"', $this->escapeDoubleQuotedString());
48: }
49:
50: private function escapeDoubleQuotedString(): string
51: {
52: $quote = '"';
53: $escaped = addcslashes($this->value, "\n\r\t\f\v$" . $quote . '\\');
54:
55: // Escape control characters and non-UTF-8 characters.
56: // Regex based on https://stackoverflow.com/a/11709412/385378.
57: $regex = '/(
58: [\x00-\x08\x0E-\x1F] # Control characters
59: | [\xC0-\xC1] # Invalid UTF-8 Bytes
60: | [\xF5-\xFF] # Invalid UTF-8 Bytes
61: | \xE0(?=[\x80-\x9F]) # Overlong encoding of prior code point
62: | \xF0(?=[\x80-\x8F]) # Overlong encoding of prior code point
63: | [\xC2-\xDF](?![\x80-\xBF]) # Invalid UTF-8 Sequence Start
64: | [\xE0-\xEF](?![\x80-\xBF]{2}) # Invalid UTF-8 Sequence Start
65: | [\xF0-\xF4](?![\x80-\xBF]{3}) # Invalid UTF-8 Sequence Start
66: | (?<=[\x00-\x7F\xF5-\xFF])[\x80-\xBF] # Invalid UTF-8 Sequence Middle
67: | (?<![\xC2-\xDF]|[\xE0-\xEF]|[\xE0-\xEF][\x80-\xBF]|[\xF0-\xF4]|[\xF0-\xF4][\x80-\xBF]|[\xF0-\xF4][\x80-\xBF]{2})[\x80-\xBF] # Overlong Sequence
68: | (?<=[\xE0-\xEF])[\x80-\xBF](?![\x80-\xBF]) # Short 3 byte sequence
69: | (?<=[\xF0-\xF4])[\x80-\xBF](?![\x80-\xBF]{2}) # Short 4 byte sequence
70: | (?<=[\xF0-\xF4][\x80-\xBF])[\x80-\xBF](?![\x80-\xBF]) # Short 4 byte sequence (2)
71: )/x';
72: return preg_replace_callback($regex, static function ($matches) {
73: assert(strlen($matches[0]) === 1);
74: $hex = dechex(ord($matches[0]));
75:
76: return '\\x' . str_pad($hex, 2, '0', STR_PAD_LEFT);
77: }, $escaped);
78: }
79:
80: }
81: