|
1
|
|
|
<?php |
|
2
|
|
|
/** |
|
3
|
|
|
* Some of these functions are adapted from places in MediaWiki. |
|
4
|
|
|
* Should probably merge them for consistency. |
|
5
|
|
|
* |
|
6
|
|
|
* Copyright © 2004 Brion Vibber <[email protected]> |
|
7
|
|
|
* https://www.mediawiki.org/ |
|
8
|
|
|
* |
|
9
|
|
|
* This program is free software; you can redistribute it and/or modify |
|
10
|
|
|
* it under the terms of the GNU General Public License as published by |
|
11
|
|
|
* the Free Software Foundation; either version 2 of the License, or |
|
12
|
|
|
* (at your option) any later version. |
|
13
|
|
|
* |
|
14
|
|
|
* This program is distributed in the hope that it will be useful, |
|
15
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
|
16
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
|
17
|
|
|
* GNU General Public License for more details. |
|
18
|
|
|
* |
|
19
|
|
|
* You should have received a copy of the GNU General Public License along |
|
20
|
|
|
* with this program; if not, write to the Free Software Foundation, Inc., |
|
21
|
|
|
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. |
|
22
|
|
|
* http://www.gnu.org/copyleft/gpl.html |
|
23
|
|
|
* |
|
24
|
|
|
* @file |
|
25
|
|
|
* @ingroup UtfNormal |
|
26
|
|
|
*/ |
|
27
|
|
|
|
|
28
|
|
|
use UtfNormal\Utils; |
|
29
|
|
|
|
|
30
|
|
|
/** |
|
31
|
|
|
* Return UTF-8 sequence for a given Unicode code point. |
|
32
|
|
|
* |
|
33
|
|
|
* @param int $codepoint |
|
34
|
|
|
* @return string |
|
35
|
|
|
* @throws InvalidArgumentException if fed out of range data. |
|
36
|
|
|
* @public |
|
37
|
|
|
* @deprecated since 1.25, use UtfNormal\Utils directly |
|
38
|
|
|
*/ |
|
39
|
|
|
function codepointToUtf8( $codepoint ) { |
|
40
|
|
|
return Utils::codepointToUtf8( $codepoint ); |
|
41
|
|
|
} |
|
42
|
|
|
|
|
43
|
|
|
/** |
|
44
|
|
|
* Take a series of space-separated hexadecimal numbers representing |
|
45
|
|
|
* Unicode code points and return a UTF-8 string composed of those |
|
46
|
|
|
* characters. Used by UTF-8 data generation and testing routines. |
|
47
|
|
|
* |
|
48
|
|
|
* @param string $sequence |
|
49
|
|
|
* @return string |
|
50
|
|
|
* @throws InvalidArgumentException if fed out of range data. |
|
51
|
|
|
* @private |
|
52
|
|
|
* @deprecated since 1.25, use UtfNormal\Utils directly |
|
53
|
|
|
*/ |
|
54
|
|
|
function hexSequenceToUtf8( $sequence ) { |
|
55
|
|
|
return Utils::hexSequenceToUtf8( $sequence ); |
|
56
|
|
|
} |
|
57
|
|
|
|
|
58
|
|
|
/** |
|
59
|
|
|
* Take a UTF-8 string and return a space-separated series of hex |
|
60
|
|
|
* numbers representing Unicode code points. For debugging. |
|
61
|
|
|
* |
|
62
|
|
|
* @fixme this is private but extensions + maint scripts are using it |
|
63
|
|
|
* @param string $str UTF-8 string. |
|
64
|
|
|
* @return string |
|
65
|
|
|
* @private |
|
66
|
|
|
*/ |
|
67
|
|
|
function utf8ToHexSequence( $str ) { |
|
68
|
|
|
$buf = ''; |
|
69
|
|
|
foreach ( preg_split( '//u', $str, -1, PREG_SPLIT_NO_EMPTY ) as $cp ) { |
|
70
|
|
|
$buf .= sprintf( '%04x ', UtfNormal\Utils::utf8ToCodepoint( $cp ) ); |
|
71
|
|
|
} |
|
72
|
|
|
|
|
73
|
|
|
return rtrim( $buf ); |
|
74
|
|
|
} |
|
75
|
|
|
|
|
76
|
|
|
/** |
|
77
|
|
|
* Determine the Unicode codepoint of a single-character UTF-8 sequence. |
|
78
|
|
|
* Does not check for invalid input data. |
|
79
|
|
|
* |
|
80
|
|
|
* @param string $char |
|
81
|
|
|
* @return int |
|
82
|
|
|
* @public |
|
83
|
|
|
* @deprecated since 1.25, use UtfNormal\Utils directly |
|
84
|
|
|
*/ |
|
85
|
|
|
function utf8ToCodepoint( $char ) { |
|
86
|
|
|
return Utils::utf8ToCodepoint( $char ); |
|
87
|
|
|
} |
|
88
|
|
|
|
|
89
|
|
|
/** |
|
90
|
|
|
* Escape a string for inclusion in a PHP single-quoted string literal. |
|
91
|
|
|
* |
|
92
|
|
|
* @param string $string string to be escaped. |
|
93
|
|
|
* @return String: escaped string. |
|
|
|
|
|
|
94
|
|
|
* @public |
|
95
|
|
|
* @deprecated since 1.25, use UtfNormal\Utils directly |
|
96
|
|
|
*/ |
|
97
|
|
|
function escapeSingleString( $string ) { |
|
98
|
|
|
return Utils::escapeSingleString( $string ); |
|
99
|
|
|
} |
|
100
|
|
|
|
This check marks PHPDoc comments that could not be parsed by our parser. To see which comment annotations we can parse, please refer to our documentation on supported doc-types.