|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
namespace PhpParser\Node\Scalar; |
|
4
|
|
|
|
|
5
|
|
|
use PhpParser\Error; |
|
6
|
|
|
use PhpParser\Node\Scalar; |
|
7
|
|
|
|
|
8
|
|
|
class String_ extends Scalar |
|
9
|
|
|
{ |
|
10
|
|
|
/** @var string String value */ |
|
11
|
|
|
public $value; |
|
12
|
|
|
|
|
13
|
|
|
protected static $replacements = array( |
|
14
|
|
|
'\\' => '\\', |
|
15
|
|
|
'$' => '$', |
|
16
|
|
|
'n' => "\n", |
|
17
|
|
|
'r' => "\r", |
|
18
|
|
|
't' => "\t", |
|
19
|
|
|
'f' => "\f", |
|
20
|
|
|
'v' => "\v", |
|
21
|
|
|
'e' => "\x1B", |
|
22
|
|
|
); |
|
23
|
|
|
|
|
24
|
|
|
/** |
|
25
|
|
|
* Constructs a string scalar node. |
|
26
|
|
|
* |
|
27
|
|
|
* @param string $value Value of the string |
|
28
|
|
|
* @param array $attributes Additional attributes |
|
29
|
|
|
*/ |
|
30
|
|
|
public function __construct($value, array $attributes = array()) { |
|
31
|
|
|
parent::__construct($attributes); |
|
32
|
|
|
$this->value = $value; |
|
33
|
|
|
} |
|
34
|
|
|
|
|
35
|
|
|
public function getSubNodeNames() { |
|
36
|
|
|
return array('value'); |
|
37
|
|
|
} |
|
38
|
|
|
|
|
39
|
|
|
/** |
|
40
|
|
|
* @internal |
|
41
|
|
|
* |
|
42
|
|
|
* Parses a string token. |
|
43
|
|
|
* |
|
44
|
|
|
* @param string $str String token content |
|
45
|
|
|
* @param bool $parseUnicodeEscape Whether to parse PHP 7 \u escapes |
|
46
|
|
|
* |
|
47
|
|
|
* @return string The parsed string |
|
48
|
|
|
*/ |
|
49
|
|
|
public static function parse($str, $parseUnicodeEscape = true) { |
|
50
|
|
|
$bLength = 0; |
|
51
|
|
|
if ('b' === $str[0]) { |
|
52
|
|
|
$bLength = 1; |
|
53
|
|
|
} |
|
54
|
|
|
|
|
55
|
|
|
if ('\'' === $str[$bLength]) { |
|
56
|
|
|
return str_replace( |
|
57
|
|
|
array('\\\\', '\\\''), |
|
58
|
|
|
array( '\\', '\''), |
|
59
|
|
|
substr($str, $bLength + 1, -1) |
|
60
|
|
|
); |
|
61
|
|
|
} else { |
|
62
|
|
|
return self::parseEscapeSequences( |
|
63
|
|
|
substr($str, $bLength + 1, -1), '"', $parseUnicodeEscape |
|
64
|
|
|
); |
|
65
|
|
|
} |
|
66
|
|
|
} |
|
67
|
|
|
|
|
68
|
|
|
/** |
|
69
|
|
|
* @internal |
|
70
|
|
|
* |
|
71
|
|
|
* Parses escape sequences in strings (all string types apart from single quoted). |
|
72
|
|
|
* |
|
73
|
|
|
* @param string $str String without quotes |
|
74
|
|
|
* @param null|string $quote Quote type |
|
75
|
|
|
* @param bool $parseUnicodeEscape Whether to parse PHP 7 \u escapes |
|
76
|
|
|
* |
|
77
|
|
|
* @return string String with escape sequences parsed |
|
78
|
|
|
*/ |
|
79
|
|
|
public static function parseEscapeSequences($str, $quote, $parseUnicodeEscape = true) { |
|
80
|
|
|
if (null !== $quote) { |
|
81
|
|
|
$str = str_replace('\\' . $quote, $quote, $str); |
|
82
|
|
|
} |
|
83
|
|
|
|
|
84
|
|
|
$extra = ''; |
|
85
|
|
|
if ($parseUnicodeEscape) { |
|
86
|
|
|
$extra = '|u\{([0-9a-fA-F]+)\}'; |
|
87
|
|
|
} |
|
88
|
|
|
|
|
89
|
|
|
return preg_replace_callback( |
|
90
|
|
|
'~\\\\([\\\\$nrtfve]|[xX][0-9a-fA-F]{1,2}|[0-7]{1,3}' . $extra . ')~', |
|
91
|
|
|
function($matches) { |
|
92
|
|
|
$str = $matches[1]; |
|
93
|
|
|
|
|
94
|
|
|
if (isset(self::$replacements[$str])) { |
|
95
|
|
|
return self::$replacements[$str]; |
|
96
|
|
View Code Duplication |
} elseif ('x' === $str[0] || 'X' === $str[0]) { |
|
|
|
|
|
|
97
|
|
|
return chr(hexdec($str)); |
|
98
|
|
|
} elseif ('u' === $str[0]) { |
|
99
|
|
|
return self::codePointToUtf8(hexdec($matches[2])); |
|
100
|
|
|
} else { |
|
101
|
|
|
return chr(octdec($str)); |
|
102
|
|
|
} |
|
103
|
|
|
}, |
|
104
|
|
|
$str |
|
105
|
|
|
); |
|
106
|
|
|
} |
|
107
|
|
|
|
|
108
|
|
|
private static function codePointToUtf8($num) { |
|
109
|
|
|
if ($num <= 0x7F) { |
|
110
|
|
|
return chr($num); |
|
111
|
|
|
} |
|
112
|
|
|
if ($num <= 0x7FF) { |
|
113
|
|
|
return chr(($num>>6) + 0xC0) . chr(($num&0x3F) + 0x80); |
|
114
|
|
|
} |
|
115
|
|
|
if ($num <= 0xFFFF) { |
|
116
|
|
|
return chr(($num>>12) + 0xE0) . chr((($num>>6)&0x3F) + 0x80) . chr(($num&0x3F) + 0x80); |
|
117
|
|
|
} |
|
118
|
|
|
if ($num <= 0x1FFFFF) { |
|
119
|
|
|
return chr(($num>>18) + 0xF0) . chr((($num>>12)&0x3F) + 0x80) |
|
120
|
|
|
. chr((($num>>6)&0x3F) + 0x80) . chr(($num&0x3F) + 0x80); |
|
121
|
|
|
} |
|
122
|
|
|
throw new Error('Invalid UTF-8 codepoint escape sequence: Codepoint too large'); |
|
123
|
|
|
} |
|
124
|
|
|
|
|
125
|
|
|
/** |
|
126
|
|
|
* @internal |
|
127
|
|
|
* |
|
128
|
|
|
* Parses a constant doc string. |
|
129
|
|
|
* |
|
130
|
|
|
* @param string $startToken Doc string start token content (<<<SMTHG) |
|
131
|
|
|
* @param string $str String token content |
|
132
|
|
|
* @param bool $parseUnicodeEscape Whether to parse PHP 7 \u escapes |
|
133
|
|
|
* |
|
134
|
|
|
* @return string Parsed string |
|
135
|
|
|
*/ |
|
136
|
|
|
public static function parseDocString($startToken, $str, $parseUnicodeEscape = true) { |
|
137
|
|
|
// strip last newline (thanks tokenizer for sticking it into the string!) |
|
138
|
|
|
$str = preg_replace('~(\r\n|\n|\r)\z~', '', $str); |
|
139
|
|
|
|
|
140
|
|
|
// nowdoc string |
|
141
|
|
|
if (false !== strpos($startToken, '\'')) { |
|
142
|
|
|
return $str; |
|
143
|
|
|
} |
|
144
|
|
|
|
|
145
|
|
|
return self::parseEscapeSequences($str, null, $parseUnicodeEscape); |
|
146
|
|
|
} |
|
147
|
|
|
} |
|
148
|
|
|
|
nikic /
PHP-Parser
Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation.
You can also find more detailed suggestions in the “Code” section of your repository.