| 1 |
<?php declare(strict_types=1); |
| 2 |
|
| 3 |
namespace PhpParser\Node\Scalar; |
| 4 |
|
| 5 |
use PhpParser\Error; |
| 6 |
use PhpParser\Node\Scalar; |
| 7 |
|
| 8 |
class String_ extends Scalar |
| 9 |
{ |
| 10 |
/* For use in "kind" attribute */ |
| 11 |
const KIND_SINGLE_QUOTED = 1; |
| 12 |
const KIND_DOUBLE_QUOTED = 2; |
| 13 |
const KIND_HEREDOC = 3; |
| 14 |
const KIND_NOWDOC = 4; |
| 15 |
|
| 16 |
/** @var string String value */ |
| 17 |
public $value; |
| 18 |
|
| 19 |
protected static $replacements = [ |
| 20 |
'\\' => '\\', |
| 21 |
'$' => '$', |
| 22 |
'n' => "\n", |
| 23 |
'r' => "\r", |
| 24 |
't' => "\t", |
| 25 |
'f' => "\f", |
| 26 |
'v' => "\v", |
| 27 |
'e' => "\x1B", |
| 28 |
]; |
| 29 |
|
| 30 |
/** |
| 31 |
* Constructs a string scalar node. |
| 32 |
* |
| 33 |
* @param string $value Value of the string |
| 34 |
* @param array $attributes Additional attributes |
| 35 |
*/ |
| 36 |
public function __construct(string $value, array $attributes = []) { |
| 37 |
$this->attributes = $attributes; |
| 38 |
$this->value = $value; |
| 39 |
} |
| 40 |
|
| 41 |
public function getSubNodeNames() : array { |
| 42 |
return ['value']; |
| 43 |
} |
| 44 |
|
| 45 |
/** |
| 46 |
* @param bool $parseUnicodeEscape Whether to parse PHP 7 \u escapes |
| 47 |
*/ |
| 48 |
public static function fromString(string $str, array $attributes = [], bool $parseUnicodeEscape = true): self |
| 49 |
{ |
| 50 |
$attributes['kind'] = ($str[0] === "'" || ($str[1] === "'" && ($str[0] === 'b' || $str[0] === 'B'))) |
| 51 |
? Scalar\String_::KIND_SINGLE_QUOTED |
| 52 |
: Scalar\String_::KIND_DOUBLE_QUOTED; |
| 53 |
|
| 54 |
$attributes['rawValue'] = $str; |
| 55 |
|
| 56 |
$string = self::parse($str, $parseUnicodeEscape); |
| 57 |
|
| 58 |
return new self($string, $attributes); |
| 59 |
} |
| 60 |
|
| 61 |
/** |
| 62 |
* @internal |
| 63 |
* |
| 64 |
* Parses a string token. |
| 65 |
* |
| 66 |
* @param string $str String token content |
| 67 |
* @param bool $parseUnicodeEscape Whether to parse PHP 7 \u escapes |
| 68 |
* |
| 69 |
* @return string The parsed string |
| 70 |
*/ |
| 71 |
public static function parse(string $str, bool $parseUnicodeEscape = true) : string { |
| 72 |
$bLength = 0; |
| 73 |
if ('b' === $str[0] || 'B' === $str[0]) { |
| 74 |
$bLength = 1; |
| 75 |
} |
| 76 |
|
| 77 |
if ('\'' === $str[$bLength]) { |
| 78 |
return str_replace( |
| 79 |
['\\\\', '\\\''], |
| 80 |
['\\', '\''], |
| 81 |
substr($str, $bLength + 1, -1) |
| 82 |
); |
| 83 |
} else { |
| 84 |
return self::parseEscapeSequences( |
| 85 |
substr($str, $bLength + 1, -1), '"', $parseUnicodeEscape |
| 86 |
); |
| 87 |
} |
| 88 |
} |
| 89 |
|
| 90 |
/** |
| 91 |
* @internal |
| 92 |
* |
| 93 |
* Parses escape sequences in strings (all string types apart from single quoted). |
| 94 |
* |
| 95 |
* @param string $str String without quotes |
| 96 |
* @param null|string $quote Quote type |
| 97 |
* @param bool $parseUnicodeEscape Whether to parse PHP 7 \u escapes |
| 98 |
* |
| 99 |
* @return string String with escape sequences parsed |
| 100 |
*/ |
| 101 |
public static function parseEscapeSequences(string $str, $quote, bool $parseUnicodeEscape = true) : string { |
| 102 |
if (null !== $quote) { |
| 103 |
$str = str_replace('\\' . $quote, $quote, $str); |
| 104 |
} |
| 105 |
|
| 106 |
$extra = ''; |
| 107 |
if ($parseUnicodeEscape) { |
| 108 |
$extra = '|u\{([0-9a-fA-F]+)\}'; |
| 109 |
} |
| 110 |
|
| 111 |
return preg_replace_callback( |
| 112 |
'~\\\\([\\\\$nrtfve]|[xX][0-9a-fA-F]{1,2}|[0-7]{1,3}' . $extra . ')~', |
| 113 |
function($matches) { |
| 114 |
$str = $matches[1]; |
| 115 |
|
| 116 |
if (isset(self::$replacements[$str])) { |
| 117 |
return self::$replacements[$str]; |
| 118 |
} elseif ('x' === $str[0] || 'X' === $str[0]) { |
| 119 |
return chr(hexdec(substr($str, 1))); |
| 120 |
} elseif ('u' === $str[0]) { |
| 121 |
return self::codePointToUtf8(hexdec($matches[2])); |
| 122 |
} else { |
| 123 |
return chr(octdec($str) & 255); |
| 124 |
} |
| 125 |
}, |
| 126 |
$str |
| 127 |
); |
| 128 |
} |
| 129 |
|
| 130 |
/** |
| 131 |
* Converts a Unicode code point to its UTF-8 encoded representation. |
| 132 |
* |
| 133 |
* @param int $num Code point |
| 134 |
* |
| 135 |
* @return string UTF-8 representation of code point |
| 136 |
*/ |
| 137 |
private static function codePointToUtf8(int $num) : string { |
| 138 |
if ($num <= 0x7F) { |
| 139 |
return chr($num); |
| 140 |
} |
| 141 |
if ($num <= 0x7FF) { |
| 142 |
return chr(($num>>6) + 0xC0) . chr(($num&0x3F) + 0x80); |
| 143 |
} |
| 144 |
if ($num <= 0xFFFF) { |
| 145 |
return chr(($num>>12) + 0xE0) . chr((($num>>6)&0x3F) + 0x80) . chr(($num&0x3F) + 0x80); |
| 146 |
} |
| 147 |
if ($num <= 0x1FFFFF) { |
| 148 |
return chr(($num>>18) + 0xF0) . chr((($num>>12)&0x3F) + 0x80) |
| 149 |
. chr((($num>>6)&0x3F) + 0x80) . chr(($num&0x3F) + 0x80); |
| 150 |
} |
| 151 |
throw new Error('Invalid UTF-8 codepoint escape sequence: Codepoint too large'); |
| 152 |
} |
| 153 |
|
| 154 |
public function getType() : string { |
| 155 |
return 'Scalar_String'; |
| 156 |
} |
| 157 |
} |
| 158 |
|