1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
|
<?php
/**
* Fallback functions for PHP installed without mbstring support.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License along
* with this program; if not, write to the Free Software Foundation, Inc.,
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
* http://www.gnu.org/copyleft/gpl.html
*
* @file
*/
/**
* Fallback functions for PHP installed without mbstring support
*/
class Fallback {
/**
* Fallback implementation for mb_substr, hardcoded to UTF-8.
* Attempts to be at least _moderately_ efficient; best optimized
* for relatively small offset and count values -- about 5x slower
* than native mb_string in my testing.
*
* Larger offsets are still fairly efficient for Latin text, but
* can be up to 100x slower than native if the text is heavily
* multibyte and we have to slog through a few hundred kb.
*
* @param string $str
* @param int $start
* @param string $count
*
* @return string
*/
public static function mb_substr( $str, $start, $count = 'end' ) {
if ( $start != 0 ) {
$split = self::mb_substr_split_unicode( $str, intval( $start ) );
$str = substr( $str, $split );
}
if ( $count !== 'end' ) {
$split = self::mb_substr_split_unicode( $str, intval( $count ) );
$str = substr( $str, 0, $split );
}
return $str;
}
/**
* @param string $str
* @param int $splitPos
* @return int
*/
public static function mb_substr_split_unicode( $str, $splitPos ) {
if ( $splitPos == 0 ) {
return 0;
}
$byteLen = strlen( $str );
if ( $splitPos > 0 ) {
if ( $splitPos > 256 ) {
// Optimize large string offsets by skipping ahead N bytes.
// This will cut out most of our slow time on Latin-based text,
// and 1/2 to 1/3 on East European and Asian scripts.
$bytePos = $splitPos;
while ( $bytePos < $byteLen && $str[$bytePos] >= "\x80" && $str[$bytePos] < "\xc0" ) {
++$bytePos;
}
$charPos = mb_strlen( substr( $str, 0, $bytePos ) );
} else {
$charPos = 0;
$bytePos = 0;
}
while ( $charPos++ < $splitPos ) {
++$bytePos;
// Move past any tail bytes
while ( $bytePos < $byteLen && $str[$bytePos] >= "\x80" && $str[$bytePos] < "\xc0" ) {
++$bytePos;
}
}
} else {
$splitPosX = $splitPos + 1;
$charPos = 0; // relative to end of string; we don't care about the actual char position here
$bytePos = $byteLen;
while ( $bytePos > 0 && $charPos-- >= $splitPosX ) {
--$bytePos;
// Move past any tail bytes
while ( $bytePos > 0 && $str[$bytePos] >= "\x80" && $str[$bytePos] < "\xc0" ) {
--$bytePos;
}
}
}
return $bytePos;
}
/**
* Fallback implementation of mb_strlen, hardcoded to UTF-8.
* @param string $str
* @param string $enc Optional encoding; ignored
* @return int
*/
public static function mb_strlen( $str, $enc = '' ) {
$counts = count_chars( $str );
$total = 0;
// Count ASCII bytes
for ( $i = 0; $i < 0x80; $i++ ) {
$total += $counts[$i];
}
// Count multibyte sequence heads
for ( $i = 0xc0; $i < 0xff; $i++ ) {
$total += $counts[$i];
}
return $total;
}
/**
* Fallback implementation of mb_strpos, hardcoded to UTF-8.
* @param string $haystack
* @param string $needle
* @param string $offset Optional start position
* @param string $encoding Optional encoding; ignored
* @return int
*/
public static function mb_strpos( $haystack, $needle, $offset = 0, $encoding = '' ) {
$needle = preg_quote( $needle, '/' );
$ar = array();
preg_match( '/' . $needle . '/u', $haystack, $ar, PREG_OFFSET_CAPTURE, $offset );
if ( isset( $ar[0][1] ) ) {
return $ar[0][1];
} else {
return false;
}
}
/**
* Fallback implementation of mb_strrpos, hardcoded to UTF-8.
* @param string $haystack
* @param string $needle
* @param string $offset Optional start position
* @param string $encoding Optional encoding; ignored
* @return int
*/
public static function mb_strrpos( $haystack, $needle, $offset = 0, $encoding = '' ) {
$needle = preg_quote( $needle, '/' );
$ar = array();
preg_match_all( '/' . $needle . '/u', $haystack, $ar, PREG_OFFSET_CAPTURE, $offset );
if ( isset( $ar[0] ) && count( $ar[0] ) > 0 &&
isset( $ar[0][count( $ar[0] ) - 1][1] ) ) {
return $ar[0][count( $ar[0] ) - 1][1];
} else {
return false;
}
}
}
|
