|
1
|
|
|
<?php |
|
2
|
|
|
/** |
|
3
|
|
|
* File containing the class {@see \AppUtils\FileHelper\UnicodeHandling}. |
|
4
|
|
|
* |
|
5
|
|
|
* @package Application Utils |
|
6
|
|
|
* @subpackage FileHelper |
|
7
|
|
|
* @see \AppUtils\FileHelper\UnicodeHandling |
|
8
|
|
|
*/ |
|
9
|
|
|
|
|
10
|
|
|
declare(strict_types=1); |
|
11
|
|
|
|
|
12
|
|
|
namespace AppUtils\FileHelper; |
|
13
|
|
|
|
|
14
|
|
|
use AppUtils\FileHelper; |
|
15
|
|
|
use AppUtils\FileHelper_Exception; |
|
16
|
|
|
use DirectoryIterator; |
|
17
|
|
|
|
|
18
|
|
|
/** |
|
19
|
|
|
* Collection of methods related to unicode-safe file |
|
20
|
|
|
* operations and information access. |
|
21
|
|
|
* |
|
22
|
|
|
* @package Application Utils |
|
23
|
|
|
* @subpackage FileHelper |
|
24
|
|
|
* @author Sebastian Mordziol <[email protected]> |
|
25
|
|
|
*/ |
|
26
|
|
|
class UnicodeHandling |
|
27
|
|
|
{ |
|
28
|
|
|
/** |
|
29
|
|
|
* @var array<string,string>|NULL |
|
30
|
|
|
*/ |
|
31
|
|
|
protected static ?array $utfBoms = null; |
|
32
|
|
|
|
|
33
|
|
|
/** |
|
34
|
|
|
* @var string[]|NULL |
|
35
|
|
|
*/ |
|
36
|
|
|
protected static ?array $encodings = null; |
|
37
|
|
|
|
|
38
|
|
|
public function __construct() |
|
39
|
|
|
{ |
|
40
|
|
|
$this->initBOMs(); |
|
41
|
|
|
$this->initEncodings(); |
|
42
|
|
|
} |
|
43
|
|
|
|
|
44
|
|
|
/** |
|
45
|
|
|
* Detects the UTF BOM in the target file, if any. Returns |
|
46
|
|
|
* the encoding matching the BOM, which can be any of the |
|
47
|
|
|
* following: |
|
48
|
|
|
* |
|
49
|
|
|
* <ul> |
|
50
|
|
|
* <li>UTF32-BE</li> |
|
51
|
|
|
* <li>UTF32-LE</li> |
|
52
|
|
|
* <li>UTF16-BE</li> |
|
53
|
|
|
* <li>UTF16-LE</li> |
|
54
|
|
|
* <li>UTF8</li> |
|
55
|
|
|
* </ul> |
|
56
|
|
|
* |
|
57
|
|
|
* @param string|PathInfoInterface|DirectoryIterator $file |
|
58
|
|
|
* @return string|NULL |
|
59
|
|
|
* @throws FileHelper_Exception |
|
60
|
|
|
* @see FileHelper::ERROR_CANNOT_OPEN_FILE_TO_DETECT_BOM |
|
61
|
|
|
*/ |
|
62
|
|
|
public function detectUTFBom($file) : ?string |
|
63
|
|
|
{ |
|
64
|
|
|
$file = FileHelper::getFileInfo($file) |
|
65
|
|
|
->requireExists(FileHelper::ERROR_CANNOT_OPEN_FILE_TO_DETECT_BOM) |
|
66
|
|
|
->requireReadable(FileHelper::ERROR_CANNOT_OPEN_FILE_TO_DETECT_BOM); |
|
67
|
|
|
|
|
68
|
|
|
$fp = fopen($file->getPath(), 'rb'); |
|
69
|
|
|
|
|
70
|
|
|
$text = fread($fp, 20); |
|
71
|
|
|
|
|
72
|
|
|
fclose($fp); |
|
73
|
|
|
|
|
74
|
|
|
foreach(self::$utfBoms as $bom => $value) |
|
75
|
|
|
{ |
|
76
|
|
|
if(mb_strpos($text, $value) === 0) |
|
77
|
|
|
{ |
|
78
|
|
|
return $bom; |
|
79
|
|
|
} |
|
80
|
|
|
} |
|
81
|
|
|
|
|
82
|
|
|
return null; |
|
83
|
|
|
} |
|
84
|
|
|
|
|
85
|
|
|
private function initBOMs() : void |
|
86
|
|
|
{ |
|
87
|
|
|
if(isset(self::$utfBoms)) |
|
88
|
|
|
{ |
|
89
|
|
|
return; |
|
90
|
|
|
} |
|
91
|
|
|
|
|
92
|
|
|
self::$utfBoms = array( |
|
93
|
|
|
'UTF32-BE' => chr(0x00) . chr(0x00) . chr(0xFE) . chr(0xFF), |
|
94
|
|
|
'UTF32-LE' => chr(0xFF) . chr(0xFE) . chr(0x00) . chr(0x00), |
|
95
|
|
|
'UTF16-BE' => chr(0xFE) . chr(0xFF), |
|
96
|
|
|
'UTF16-LE' => chr(0xFF) . chr(0xFE), |
|
97
|
|
|
'UTF8' => chr(0xEF) . chr(0xBB) . chr(0xBF) |
|
98
|
|
|
); |
|
99
|
|
|
} |
|
100
|
|
|
|
|
101
|
|
|
private function initEncodings() : void |
|
102
|
|
|
{ |
|
103
|
|
|
if(isset(self::$encodings)) |
|
104
|
|
|
{ |
|
105
|
|
|
return; |
|
106
|
|
|
} |
|
107
|
|
|
|
|
108
|
|
|
$encodings = $this->getKnownEncodings(); |
|
109
|
|
|
|
|
110
|
|
|
self::$encodings = array(); |
|
111
|
|
|
|
|
112
|
|
|
foreach($encodings as $string) |
|
113
|
|
|
{ |
|
114
|
|
|
$withHyphen = str_replace('UTF', 'UTF-', $string); |
|
115
|
|
|
|
|
116
|
|
|
self::$encodings[] = $string; |
|
117
|
|
|
self::$encodings[] = $withHyphen; |
|
118
|
|
|
self::$encodings[] = str_replace(array('-BE', '-LE'), '', $string); |
|
119
|
|
|
self::$encodings[] = str_replace(array('-BE', '-LE'), '', $withHyphen); |
|
120
|
|
|
} |
|
121
|
|
|
} |
|
122
|
|
|
|
|
123
|
|
|
/** |
|
124
|
|
|
* Retrieves a list of all UTF byte order mark character |
|
125
|
|
|
* sequences, as an associative array with |
|
126
|
|
|
* UTF encoding => bom sequence pairs. |
|
127
|
|
|
* |
|
128
|
|
|
* @return array<string,string> |
|
129
|
|
|
*/ |
|
130
|
|
|
public function getUTFBOMs() : array |
|
131
|
|
|
{ |
|
132
|
|
|
return self::$utfBoms; |
|
|
|
|
|
|
133
|
|
|
} |
|
134
|
|
|
|
|
135
|
|
|
/** |
|
136
|
|
|
* Checks whether the specified encoding is a valid |
|
137
|
|
|
* unicode encoding, for example "UTF16-LE" or "UTF8". |
|
138
|
|
|
* Also accounts for alternate way to write them, like |
|
139
|
|
|
* "UTF-8", and omitting little/big endian suffixes. |
|
140
|
|
|
* |
|
141
|
|
|
* @param string $encoding |
|
142
|
|
|
* @return boolean |
|
143
|
|
|
*/ |
|
144
|
|
|
public function isValidEncoding(string $encoding) : bool |
|
145
|
|
|
{ |
|
146
|
|
|
return in_array($encoding, self::$encodings, true); |
|
|
|
|
|
|
147
|
|
|
} |
|
148
|
|
|
|
|
149
|
|
|
/** |
|
150
|
|
|
* Retrieves a list of all known unicode file encodings. |
|
151
|
|
|
* @return string[] |
|
152
|
|
|
*/ |
|
153
|
|
|
public function getKnownEncodings() : array |
|
154
|
|
|
{ |
|
155
|
|
|
return array_keys(self::$utfBoms); |
|
|
|
|
|
|
156
|
|
|
} |
|
157
|
|
|
} |
|
158
|
|
|
|
Mistralys /
application-utils
Loading history...