| 1 |
lars |
1 |
<?php
|
|
|
2 |
/* SVN FILE: $Id: multibyte.php 8004 2009-01-16 20:15:21Z gwoo $ */
|
|
|
3 |
/**
|
|
|
4 |
* Multibyte handling methods.
|
|
|
5 |
*
|
|
|
6 |
*
|
|
|
7 |
* PHP versions 4 and 5
|
|
|
8 |
*
|
|
|
9 |
* CakePHP(tm) : Rapid Development Framework (http://www.cakephp.org)
|
|
|
10 |
* Copyright 2005-2008, Cake Software Foundation, Inc. (http://www.cakefoundation.org)
|
|
|
11 |
*
|
|
|
12 |
* Licensed under The MIT License
|
|
|
13 |
* Redistributions of files must retain the above copyright notice.
|
|
|
14 |
*
|
|
|
15 |
* @filesource
|
|
|
16 |
* @copyright Copyright 2005-2008, Cake Software Foundation, Inc. (http://www.cakefoundation.org)
|
|
|
17 |
* @link http://www.cakefoundation.org/projects/info/cakephp CakePHP(tm) Project
|
|
|
18 |
* @package cake
|
|
|
19 |
* @subpackage cake.cake.libs
|
|
|
20 |
* @since CakePHP(tm) v 1.2.0.6833
|
|
|
21 |
* @version $Revision: 8004 $
|
|
|
22 |
* @modifiedby $LastChangedBy: gwoo $
|
|
|
23 |
* @lastmodified $Date: 2009-01-16 12:15:21 -0800 (Fri, 16 Jan 2009) $
|
|
|
24 |
* @license http://www.opensource.org/licenses/mit-license.php The MIT License
|
|
|
25 |
*/
|
|
|
26 |
if (function_exists('mb_internal_encoding')) {
|
|
|
27 |
$encoding = Configure::read('App.encoding');
|
|
|
28 |
if (!empty($encoding)) {
|
|
|
29 |
mb_internal_encoding($encoding);
|
|
|
30 |
}
|
|
|
31 |
}
|
|
|
32 |
/**
|
|
|
33 |
* Find position of first occurrence of a case-insensitive string.
|
|
|
34 |
*
|
|
|
35 |
* @param string $haystack The string from which to get the position of the first occurrence of $needle.
|
|
|
36 |
* @param string $needle The string to find in $haystack.
|
|
|
37 |
* @param integer $offset The position in $haystack to start searching.
|
|
|
38 |
* @param string $encoding Character encoding name to use. If it is omitted, internal character encoding is used.
|
|
|
39 |
* @return integer|boolean The numeric position of the first occurrence of $needle in the $haystack string, or false if $needle is not found.
|
|
|
40 |
*/
|
|
|
41 |
if (!function_exists('mb_stripos')) {
|
|
|
42 |
function mb_stripos($haystack, $needle, $offset = 0, $encoding = null) {
|
|
|
43 |
return Multibyte::stripos($haystack, $needle, $offset);
|
|
|
44 |
}
|
|
|
45 |
}
|
|
|
46 |
/**
|
|
|
47 |
* Finds first occurrence of a string within another, case insensitive.
|
|
|
48 |
*
|
|
|
49 |
* @param string $haystack The string from which to get the first occurrence of $needle.
|
|
|
50 |
* @param string $needle The string to find in $haystack.
|
|
|
51 |
* @param boolean $part Determines which portion of $haystack this function returns.
|
|
|
52 |
* If set to true, it returns all of $haystack from the beginning to the first occurrence of $needle.
|
|
|
53 |
* If set to false, it returns all of $haystack from the first occurrence of $needle to the end, Default value is false.
|
|
|
54 |
* @param string $encoding Character encoding name to use. If it is omitted, internal character encoding is used.
|
|
|
55 |
* @return string|boolean The portion of $haystack, or false if $needle is not found.
|
|
|
56 |
*/
|
|
|
57 |
if (!function_exists('mb_stristr')) {
|
|
|
58 |
function mb_stristr($haystack, $needle, $part = false, $encoding = null) {
|
|
|
59 |
return Multibyte::stristr($haystack, $needle, $part);
|
|
|
60 |
}
|
|
|
61 |
}
|
|
|
62 |
/**
|
|
|
63 |
* Get string length.
|
|
|
64 |
*
|
|
|
65 |
* @param string $string The string being checked for length.
|
|
|
66 |
* @param string $encoding Character encoding name to use. If it is omitted, internal character encoding is used.
|
|
|
67 |
* @return integer The number of characters in string $string having character encoding encoding.
|
|
|
68 |
* A multi-byte character is counted as 1.
|
|
|
69 |
*/
|
|
|
70 |
if (!function_exists('mb_strlen')) {
|
|
|
71 |
function mb_strlen($string, $encoding = null) {
|
|
|
72 |
return Multibyte::strlen($string);
|
|
|
73 |
}
|
|
|
74 |
}
|
|
|
75 |
/**
|
|
|
76 |
* Find position of first occurrence of a string.
|
|
|
77 |
*
|
|
|
78 |
* @param string $haystack The string being checked.
|
|
|
79 |
* @param string $needle The position counted from the beginning of haystack.
|
|
|
80 |
* @param integer $offset The search offset. If it is not specified, 0 is used.
|
|
|
81 |
* @param string $encoding Character encoding name to use. If it is omitted, internal character encoding is used.
|
|
|
82 |
* @return integer|boolean The numeric position of the first occurrence of $needle in the $haystack string.
|
|
|
83 |
* If $needle is not found, it returns false.
|
|
|
84 |
*/
|
|
|
85 |
if (!function_exists('mb_strpos')) {
|
|
|
86 |
function mb_strpos($haystack, $needle, $offset = 0, $encoding = null) {
|
|
|
87 |
return Multibyte::strpos($haystack, $needle, $offset);
|
|
|
88 |
}
|
|
|
89 |
}
|
|
|
90 |
/**
|
|
|
91 |
* Finds the last occurrence of a character in a string within another.
|
|
|
92 |
*
|
|
|
93 |
* @param string $haystack The string from which to get the last occurrence of $needle.
|
|
|
94 |
* @param string $needle The string to find in $haystack.
|
|
|
95 |
* @param boolean $part Determines which portion of $haystack this function returns.
|
|
|
96 |
* If set to true, it returns all of $haystack from the beginning to the last occurrence of $needle.
|
|
|
97 |
* If set to false, it returns all of $haystack from the last occurrence of $needle to the end, Default value is false.
|
|
|
98 |
* @param string $encoding Character encoding name to use. If it is omitted, internal character encoding is used.
|
|
|
99 |
* @return string|boolean The portion of $haystack. or false if $needle is not found.
|
|
|
100 |
*/
|
|
|
101 |
if (!function_exists('mb_strrchr')) {
|
|
|
102 |
function mb_strrchr($haystack, $needle, $part = false, $encoding = null) {
|
|
|
103 |
return Multibyte::strrchr($haystack, $needle, $part);
|
|
|
104 |
}
|
|
|
105 |
}
|
|
|
106 |
/**
|
|
|
107 |
* Finds the last occurrence of a character in a string within another, case insensitive.
|
|
|
108 |
*
|
|
|
109 |
* @param string $haystack The string from which to get the last occurrence of $needle.
|
|
|
110 |
* @param string $needle The string to find in $haystack.
|
|
|
111 |
* @param boolean $part Determines which portion of $haystack this function returns.
|
|
|
112 |
* If set to true, it returns all of $haystack from the beginning to the last occurrence of $needle.
|
|
|
113 |
* If set to false, it returns all of $haystack from the last occurrence of $needle to the end, Default value is false.
|
|
|
114 |
* @param string $encoding Character encoding name to use. If it is omitted, internal character encoding is used.
|
|
|
115 |
* @return string|boolean The portion of $haystack. or false if $needle is not found.
|
|
|
116 |
*/
|
|
|
117 |
if (!function_exists('mb_strrichr')) {
|
|
|
118 |
function mb_strrichr($haystack, $needle, $part = false, $encoding = null) {
|
|
|
119 |
return Multibyte::strrichr($haystack, $needle, $part);
|
|
|
120 |
}
|
|
|
121 |
}
|
|
|
122 |
/**
|
|
|
123 |
* Finds position of last occurrence of a string within another, case insensitive
|
|
|
124 |
*
|
|
|
125 |
* @param string $haystack The string from which to get the position of the last occurrence of $needle.
|
|
|
126 |
* @param string $needle The string to find in $haystack.
|
|
|
127 |
* @param integer $offset The position in $haystack to start searching.
|
|
|
128 |
* @param string $encoding Character encoding name to use. If it is omitted, internal character encoding is used.
|
|
|
129 |
* @return integer|boolean The numeric position of the last occurrence of $needle in the $haystack string, or false if $needle is not found.
|
|
|
130 |
*/
|
|
|
131 |
if (!function_exists('mb_strripos')) {
|
|
|
132 |
function mb_strripos($haystack, $needle, $offset = 0, $encoding = null) {
|
|
|
133 |
return Multibyte::strripos($haystack, $needle, $offset);
|
|
|
134 |
}
|
|
|
135 |
}
|
|
|
136 |
/**
|
|
|
137 |
* Find position of last occurrence of a string in a string.
|
|
|
138 |
*
|
|
|
139 |
* @param string $haystack The string being checked, for the last occurrence of $needle.
|
|
|
140 |
* @param string $needle The string to find in $haystack.
|
|
|
141 |
* @param integer $offset May be specified to begin searching an arbitrary number of characters into the string.
|
|
|
142 |
* Negative values will stop searching at an arbitrary point prior to the end of the string.
|
|
|
143 |
* @param string $encoding Character encoding name to use. If it is omitted, internal character encoding is used.
|
|
|
144 |
* @return integer|boolean The numeric position of the last occurrence of $needle in the $haystack string. If $needle is not found, it returns false.
|
|
|
145 |
*/
|
|
|
146 |
if (!function_exists('mb_strrpos')) {
|
|
|
147 |
function mb_strrpos($haystack, $needle, $offset = 0, $encoding = null) {
|
|
|
148 |
return Multibyte::strrpos($haystack, $needle, $offset);
|
|
|
149 |
}
|
|
|
150 |
}
|
|
|
151 |
/**
|
|
|
152 |
* Finds first occurrence of a string within another
|
|
|
153 |
*
|
|
|
154 |
* @param string $haystack The string from which to get the first occurrence of $needle.
|
|
|
155 |
* @param string $needle The string to find in $haystack
|
|
|
156 |
* @param boolean $part Determines which portion of $haystack this function returns.
|
|
|
157 |
* If set to true, it returns all of $haystack from the beginning to the first occurrence of $needle.
|
|
|
158 |
* If set to false, it returns all of $haystack from the first occurrence of $needle to the end, Default value is FALSE.
|
|
|
159 |
* @param string $encoding Character encoding name to use. If it is omitted, internal character encoding is used.
|
|
|
160 |
* @return string|boolean The portion of $haystack, or true if $needle is not found.
|
|
|
161 |
*/
|
|
|
162 |
if (!function_exists('mb_strstr')) {
|
|
|
163 |
function mb_strstr($haystack, $needle, $part = false, $encoding = null) {
|
|
|
164 |
return Multibyte::strstr($haystack, $needle, $part);
|
|
|
165 |
}
|
|
|
166 |
}
|
|
|
167 |
/**
|
|
|
168 |
* Make a string lowercase
|
|
|
169 |
*
|
|
|
170 |
* @param string $string The string being lowercased.
|
|
|
171 |
* @param string $encoding Character encoding name to use. If it is omitted, internal character encoding is used.
|
|
|
172 |
* @return string with all alphabetic characters converted to lowercase.
|
|
|
173 |
*/
|
|
|
174 |
if (!function_exists('mb_strtolower')) {
|
|
|
175 |
function mb_strtolower($string, $encoding = null) {
|
|
|
176 |
return Multibyte::strtolower($string);
|
|
|
177 |
}
|
|
|
178 |
}
|
|
|
179 |
/**
|
|
|
180 |
* Make a string uppercase
|
|
|
181 |
*
|
|
|
182 |
* @param string $string The string being uppercased.
|
|
|
183 |
* @param string $encoding Character encoding name to use. If it is omitted, internal character encoding is used.
|
|
|
184 |
* @return string with all alphabetic characters converted to uppercase.
|
|
|
185 |
*/
|
|
|
186 |
if (!function_exists('mb_strtoupper')) {
|
|
|
187 |
function mb_strtoupper($string, $encoding = null) {
|
|
|
188 |
return Multibyte::strtoupper($string);
|
|
|
189 |
}
|
|
|
190 |
}
|
|
|
191 |
/**
|
|
|
192 |
* Count the number of substring occurrences
|
|
|
193 |
*
|
|
|
194 |
* @param string $haystack The string being checked.
|
|
|
195 |
* @param string $needle The string being found.
|
|
|
196 |
* @param string $encoding Character encoding name to use. If it is omitted, internal character encoding is used.
|
|
|
197 |
* @return integer The number of times the $needle substring occurs in the $haystack string.
|
|
|
198 |
*/
|
|
|
199 |
if (!function_exists('mb_substr_count')) {
|
|
|
200 |
function mb_substr_count($haystack, $needle, $encoding = null) {
|
|
|
201 |
return Multibyte::substrCount($haystack, $needle);
|
|
|
202 |
}
|
|
|
203 |
}
|
|
|
204 |
/**
|
|
|
205 |
* Get part of string
|
|
|
206 |
*
|
|
|
207 |
* @param string $string The string being checked.
|
|
|
208 |
* @param integer $start The first position used in $string.
|
|
|
209 |
* @param integer $length The maximum length of the returned string.
|
|
|
210 |
* @param string $encoding Character encoding name to use. If it is omitted, internal character encoding is used.
|
|
|
211 |
* @return string The portion of $string specified by the $string and $length parameters.
|
|
|
212 |
*/
|
|
|
213 |
if (!function_exists('mb_substr')) {
|
|
|
214 |
function mb_substr($string, $start, $length = null, $encoding = null) {
|
|
|
215 |
return Multibyte::substr($string, $start, $length);
|
|
|
216 |
}
|
|
|
217 |
}
|
|
|
218 |
/**
|
|
|
219 |
* Encode string for MIME header
|
|
|
220 |
*
|
|
|
221 |
* @param string $str The string being encoded
|
|
|
222 |
* @param string $charset specifies the name of the character set in which str is represented in.
|
|
|
223 |
* The default value is determined by the current NLS setting (mbstring.language).
|
|
|
224 |
* @param string $transfer_encoding specifies the scheme of MIME encoding. It should be either "B" (Base64) or "Q" (Quoted-Printable).
|
|
|
225 |
* Falls back to "B" if not given.
|
|
|
226 |
* @param string $linefeed specifies the EOL (end-of-line) marker with which mb_encode_mimeheader() performs line-folding
|
|
|
227 |
* (a » RFC term, the act of breaking a line longer than a certain length into multiple lines.
|
|
|
228 |
* The length is currently hard-coded to 74 characters). Falls back to "\r\n" (CRLF) if not given.
|
|
|
229 |
* @param integer $indent [definition unknown and appears to have no affect]
|
|
|
230 |
* @return string A converted version of the string represented in ASCII.
|
|
|
231 |
*/
|
|
|
232 |
if (!function_exists('mb_encode_mimeheader')) {
|
|
|
233 |
function mb_encode_mimeheader($str, $charset = 'UTF-8', $transfer_encoding = 'B', $linefeed = "\r\n", $indent = 1) {
|
|
|
234 |
return Multibyte::mimeEncode($str, $charset, $linefeed);
|
|
|
235 |
}
|
|
|
236 |
}
|
|
|
237 |
/**
|
|
|
238 |
* Multibyte handling methods.
|
|
|
239 |
*
|
|
|
240 |
*
|
|
|
241 |
* @package cake
|
|
|
242 |
* @subpackage cake.cake.libs
|
|
|
243 |
*/
|
|
|
244 |
class Multibyte extends Object {
|
|
|
245 |
/**
|
|
|
246 |
* Holds the case folding values
|
|
|
247 |
*
|
|
|
248 |
* @var array
|
|
|
249 |
* @access private
|
|
|
250 |
*/
|
|
|
251 |
var $__caseFold = array();
|
|
|
252 |
/**
|
|
|
253 |
* Holds an array of Unicode code point ranges
|
|
|
254 |
*
|
|
|
255 |
* @var array
|
|
|
256 |
* @access private
|
|
|
257 |
*/
|
|
|
258 |
var $__codeRange = array();
|
|
|
259 |
/**
|
|
|
260 |
* Holds the current code point range
|
|
|
261 |
*
|
|
|
262 |
* @var string
|
|
|
263 |
* @access private
|
|
|
264 |
*/
|
|
|
265 |
var $__table = null;
|
|
|
266 |
/**
|
|
|
267 |
* Gets a reference to the Multibyte object instance
|
|
|
268 |
*
|
|
|
269 |
* @return object Multibyte instance
|
|
|
270 |
* @access public
|
|
|
271 |
* @static
|
|
|
272 |
*/
|
|
|
273 |
function &getInstance() {
|
|
|
274 |
static $instance = array();
|
|
|
275 |
|
|
|
276 |
if (!$instance) {
|
|
|
277 |
$instance[0] =& new Multibyte();
|
|
|
278 |
}
|
|
|
279 |
return $instance[0];
|
|
|
280 |
}
|
|
|
281 |
/**
|
|
|
282 |
* Converts a multibyte character string
|
|
|
283 |
* to the decimal value of the character
|
|
|
284 |
*
|
|
|
285 |
* @param multibyte string $string
|
|
|
286 |
* @return array
|
|
|
287 |
* @access public
|
|
|
288 |
* @static
|
|
|
289 |
*/
|
|
|
290 |
function utf8($string) {
|
|
|
291 |
$map = array();
|
|
|
292 |
|
|
|
293 |
$values = array();
|
|
|
294 |
$find = 1;
|
|
|
295 |
$length = strlen($string);
|
|
|
296 |
|
|
|
297 |
for ($i = 0; $i < $length; $i++) {
|
|
|
298 |
$value = ord($string[$i]);
|
|
|
299 |
|
|
|
300 |
if ($value < 128) {
|
|
|
301 |
$map[] = $value;
|
|
|
302 |
} else {
|
|
|
303 |
if (count($values) == 0) {
|
|
|
304 |
$find = ($value < 224) ? 2 : 3;
|
|
|
305 |
}
|
|
|
306 |
$values[] = $value;
|
|
|
307 |
|
|
|
308 |
if (count($values) === $find) {
|
|
|
309 |
if ($find == 3) {
|
|
|
310 |
$map[] = (($values[0] % 16) * 4096) + (($values[1] % 64) * 64) + ($values[2] % 64);
|
|
|
311 |
} else {
|
|
|
312 |
$map[] = (($values[0] % 32) * 64) + ($values[1] % 64);
|
|
|
313 |
}
|
|
|
314 |
$values = array();
|
|
|
315 |
$find = 1;
|
|
|
316 |
}
|
|
|
317 |
}
|
|
|
318 |
}
|
|
|
319 |
return $map;
|
|
|
320 |
}
|
|
|
321 |
/**
|
|
|
322 |
* Converts the decimal value of a multibyte character string
|
|
|
323 |
* to a string
|
|
|
324 |
*
|
|
|
325 |
* @param array $array
|
|
|
326 |
* @return string
|
|
|
327 |
* @access public
|
|
|
328 |
* @static
|
|
|
329 |
*/
|
|
|
330 |
function ascii($array) {
|
|
|
331 |
$ascii = '';
|
|
|
332 |
|
|
|
333 |
foreach ($array as $utf8) {
|
|
|
334 |
if ($utf8 < 128) {
|
|
|
335 |
$ascii .= chr($utf8);
|
|
|
336 |
} elseif ($utf8 < 2048) {
|
|
|
337 |
$ascii .= chr(192 + (($utf8 - ($utf8 % 64)) / 64));
|
|
|
338 |
$ascii .= chr(128 + ($utf8 % 64));
|
|
|
339 |
} else {
|
|
|
340 |
$ascii .= chr(224 + (($utf8 - ($utf8 % 4096)) / 4096));
|
|
|
341 |
$ascii .= chr(128 + ((($utf8 % 4096) - ($utf8 % 64)) / 64));
|
|
|
342 |
$ascii .= chr(128 + ($utf8 % 64));
|
|
|
343 |
}
|
|
|
344 |
}
|
|
|
345 |
return $ascii;
|
|
|
346 |
}
|
|
|
347 |
/**
|
|
|
348 |
* Find position of first occurrence of a case-insensitive string.
|
|
|
349 |
*
|
|
|
350 |
* @param multi-byte string $haystack The string from which to get the position of the first occurrence of $needle.
|
|
|
351 |
* @param multi-byte string $needle The string to find in $haystack.
|
|
|
352 |
* @param integer $offset The position in $haystack to start searching.
|
|
|
353 |
* @return integer|boolean The numeric position of the first occurrence of $needle in the $haystack string, or false if $needle is not found.
|
|
|
354 |
* @access public
|
|
|
355 |
* @static
|
|
|
356 |
*/
|
|
|
357 |
function stripos($haystack, $needle, $offset = 0) {
|
|
|
358 |
if (!PHP5 || Multibyte::checkMultibyte($haystack)) {
|
|
|
359 |
$haystack = Multibyte::strtoupper($haystack);
|
|
|
360 |
$needle = Multibyte::strtoupper($needle);
|
|
|
361 |
return Multibyte::strpos($haystack, $needle, $offset);
|
|
|
362 |
}
|
|
|
363 |
return stripos($haystack, $needle, $offset);
|
|
|
364 |
}
|
|
|
365 |
/**
|
|
|
366 |
* Finds first occurrence of a string within another, case insensitive.
|
|
|
367 |
*
|
|
|
368 |
* @param string $haystack The string from which to get the first occurrence of $needle.
|
|
|
369 |
* @param string $needle The string to find in $haystack.
|
|
|
370 |
* @param boolean $part Determines which portion of $haystack this function returns.
|
|
|
371 |
* If set to true, it returns all of $haystack from the beginning to the first occurrence of $needle.
|
|
|
372 |
* If set to false, it returns all of $haystack from the first occurrence of $needle to the end, Default value is false.
|
|
|
373 |
* @return int|boolean The portion of $haystack, or false if $needle is not found.
|
|
|
374 |
* @access public
|
|
|
375 |
* @static
|
|
|
376 |
*/
|
|
|
377 |
function stristr($haystack, $needle, $part = false) {
|
|
|
378 |
$php = (PHP_VERSION < 5.3);
|
|
|
379 |
|
|
|
380 |
if (($php && $part) || Multibyte::checkMultibyte($haystack)) {
|
|
|
381 |
$check = Multibyte::strtoupper($haystack);
|
|
|
382 |
$check = Multibyte::utf8($check);
|
|
|
383 |
$found = false;
|
|
|
384 |
|
|
|
385 |
$haystack = Multibyte::utf8($haystack);
|
|
|
386 |
$haystackCount = count($haystack);
|
|
|
387 |
|
|
|
388 |
$needle = Multibyte::strtoupper($needle);
|
|
|
389 |
$needle = Multibyte::utf8($needle);
|
|
|
390 |
$needleCount = count($needle);
|
|
|
391 |
|
|
|
392 |
$parts = array();
|
|
|
393 |
$position = 0;
|
|
|
394 |
|
|
|
395 |
while (($found === false) && ($position < $haystackCount)) {
|
|
|
396 |
if (isset($needle[0]) && $needle[0] === $check[$position]) {
|
|
|
397 |
for ($i = 1; $i < $needleCount; $i++) {
|
|
|
398 |
if ($needle[$i] !== $check[$position + $i]) {
|
|
|
399 |
break;
|
|
|
400 |
}
|
|
|
401 |
}
|
|
|
402 |
if ($i === $needleCount) {
|
|
|
403 |
$found = true;
|
|
|
404 |
}
|
|
|
405 |
}
|
|
|
406 |
if (!$found) {
|
|
|
407 |
$parts[] = $haystack[$position];
|
|
|
408 |
unset($haystack[$position]);
|
|
|
409 |
}
|
|
|
410 |
$position++;
|
|
|
411 |
}
|
|
|
412 |
|
|
|
413 |
if ($found && $part && !empty($parts)) {
|
|
|
414 |
return Multibyte::ascii($parts);
|
|
|
415 |
} elseif ($found && !empty($haystack)) {
|
|
|
416 |
return Multibyte::ascii($haystack);
|
|
|
417 |
}
|
|
|
418 |
return false;
|
|
|
419 |
}
|
|
|
420 |
|
|
|
421 |
if (!$php) {
|
|
|
422 |
return stristr($haystack, $needle, $part);
|
|
|
423 |
}
|
|
|
424 |
return stristr($haystack, $needle);
|
|
|
425 |
}
|
|
|
426 |
/**
|
|
|
427 |
* Get string length.
|
|
|
428 |
*
|
|
|
429 |
* @param string $string The string being checked for length.
|
|
|
430 |
* @return integer The number of characters in string $string
|
|
|
431 |
* @access public
|
|
|
432 |
* @static
|
|
|
433 |
*/
|
|
|
434 |
function strlen($string) {
|
|
|
435 |
if (Multibyte::checkMultibyte($string)) {
|
|
|
436 |
$string = Multibyte::utf8($string);
|
|
|
437 |
return count($string);
|
|
|
438 |
}
|
|
|
439 |
return strlen($string);
|
|
|
440 |
}
|
|
|
441 |
/**
|
|
|
442 |
* Find position of first occurrence of a string.
|
|
|
443 |
*
|
|
|
444 |
* @param string $haystack The string being checked.
|
|
|
445 |
* @param string $needle The position counted from the beginning of haystack.
|
|
|
446 |
* @param integer $offset The search offset. If it is not specified, 0 is used.
|
|
|
447 |
* @return integer|boolean The numeric position of the first occurrence of $needle in the $haystack string.
|
|
|
448 |
* If $needle is not found, it returns false.
|
|
|
449 |
* @access public
|
|
|
450 |
* @static
|
|
|
451 |
*/
|
|
|
452 |
function strpos($haystack, $needle, $offset = 0) {
|
|
|
453 |
if (Multibyte::checkMultibyte($haystack)) {
|
|
|
454 |
$found = false;
|
|
|
455 |
|
|
|
456 |
$haystack = Multibyte::utf8($haystack);
|
|
|
457 |
$haystackCount = count($haystack);
|
|
|
458 |
|
|
|
459 |
$needle = Multibyte::utf8($needle);
|
|
|
460 |
$needleCount = count($needle);
|
|
|
461 |
|
|
|
462 |
$position = $offset;
|
|
|
463 |
|
|
|
464 |
while (($found === false) && ($position < $haystackCount)) {
|
|
|
465 |
if (isset($needle[0]) && $needle[0] === $haystack[$position]) {
|
|
|
466 |
for ($i = 1; $i < $needleCount; $i++) {
|
|
|
467 |
if ($needle[$i] !== $haystack[$position + $i]) {
|
|
|
468 |
break;
|
|
|
469 |
}
|
|
|
470 |
}
|
|
|
471 |
if ($i === $needleCount) {
|
|
|
472 |
$found = true;
|
|
|
473 |
$position--;
|
|
|
474 |
}
|
|
|
475 |
}
|
|
|
476 |
$position++;
|
|
|
477 |
}
|
|
|
478 |
if ($found) {
|
|
|
479 |
return $position;
|
|
|
480 |
}
|
|
|
481 |
return false;
|
|
|
482 |
}
|
|
|
483 |
return strpos($haystack, $needle, $offset);
|
|
|
484 |
}
|
|
|
485 |
/**
|
|
|
486 |
* Finds the last occurrence of a character in a string within another.
|
|
|
487 |
*
|
|
|
488 |
* @param string $haystack The string from which to get the last occurrence of $needle.
|
|
|
489 |
* @param string $needle The string to find in $haystack.
|
|
|
490 |
* @param boolean $part Determines which portion of $haystack this function returns.
|
|
|
491 |
* If set to true, it returns all of $haystack from the beginning to the last occurrence of $needle.
|
|
|
492 |
* If set to false, it returns all of $haystack from the last occurrence of $needle to the end, Default value is false.
|
|
|
493 |
* @return string|boolean The portion of $haystack. or false if $needle is not found.
|
|
|
494 |
* @access public
|
|
|
495 |
* @static
|
|
|
496 |
*/
|
|
|
497 |
function strrchr($haystack, $needle, $part = false) {
|
|
|
498 |
$check = Multibyte::utf8($haystack);
|
|
|
499 |
$found = false;
|
|
|
500 |
|
|
|
501 |
$haystack = Multibyte::utf8($haystack);
|
|
|
502 |
$haystackCount = count($haystack);
|
|
|
503 |
|
|
|
504 |
$matches = array_count_values($check);
|
|
|
505 |
|
|
|
506 |
$needle = Multibyte::utf8($needle);
|
|
|
507 |
$needleCount = count($needle);
|
|
|
508 |
|
|
|
509 |
$parts = array();
|
|
|
510 |
$position = 0;
|
|
|
511 |
|
|
|
512 |
while (($found === false) && ($position < $haystackCount)) {
|
|
|
513 |
if (isset($needle[0]) && $needle[0] === $check[$position]) {
|
|
|
514 |
for ($i = 1; $i < $needleCount; $i++) {
|
|
|
515 |
if ($needle[$i] !== $check[$position + $i]) {
|
|
|
516 |
if ($needle[$i] === $check[($position + $i) -1]) {
|
|
|
517 |
$found = true;
|
|
|
518 |
}
|
|
|
519 |
unset($parts[$position - 1]);
|
|
|
520 |
$haystack = array_merge(array($haystack[$position]), $haystack);
|
|
|
521 |
break;
|
|
|
522 |
}
|
|
|
523 |
}
|
|
|
524 |
if (isset($matches[$needle[0]]) && $matches[$needle[0]] > 1) {
|
|
|
525 |
$matches[$needle[0]] = $matches[$needle[0]] - 1;
|
|
|
526 |
} elseif ($i === $needleCount) {
|
|
|
527 |
$found = true;
|
|
|
528 |
}
|
|
|
529 |
}
|
|
|
530 |
|
|
|
531 |
if (!$found && isset($haystack[$position])) {
|
|
|
532 |
$parts[] = $haystack[$position];
|
|
|
533 |
unset($haystack[$position]);
|
|
|
534 |
}
|
|
|
535 |
$position++;
|
|
|
536 |
}
|
|
|
537 |
|
|
|
538 |
if ($found && $part && !empty($parts)) {
|
|
|
539 |
return Multibyte::ascii($parts);
|
|
|
540 |
} elseif ($found && !empty($haystack)) {
|
|
|
541 |
return Multibyte::ascii($haystack);
|
|
|
542 |
}
|
|
|
543 |
return false;
|
|
|
544 |
}
|
|
|
545 |
/**
|
|
|
546 |
* Finds the last occurrence of a character in a string within another, case insensitive.
|
|
|
547 |
*
|
|
|
548 |
* @param string $haystack The string from which to get the last occurrence of $needle.
|
|
|
549 |
* @param string $needle The string to find in $haystack.
|
|
|
550 |
* @param boolean $part Determines which portion of $haystack this function returns.
|
|
|
551 |
* If set to true, it returns all of $haystack from the beginning to the last occurrence of $needle.
|
|
|
552 |
* If set to false, it returns all of $haystack from the last occurrence of $needle to the end, Default value is false.
|
|
|
553 |
* @return string|boolean The portion of $haystack. or false if $needle is not found.
|
|
|
554 |
* @access public
|
|
|
555 |
* @static
|
|
|
556 |
*/
|
|
|
557 |
function strrichr($haystack, $needle, $part = false) {
|
|
|
558 |
$check = Multibyte::strtoupper($haystack);
|
|
|
559 |
$check = Multibyte::utf8($check);
|
|
|
560 |
$found = false;
|
|
|
561 |
|
|
|
562 |
$haystack = Multibyte::utf8($haystack);
|
|
|
563 |
$haystackCount = count($haystack);
|
|
|
564 |
|
|
|
565 |
$matches = array_count_values($check);
|
|
|
566 |
|
|
|
567 |
$needle = Multibyte::strtoupper($needle);
|
|
|
568 |
$needle = Multibyte::utf8($needle);
|
|
|
569 |
$needleCount = count($needle);
|
|
|
570 |
|
|
|
571 |
$parts = array();
|
|
|
572 |
$position = 0;
|
|
|
573 |
|
|
|
574 |
while (($found === false) && ($position < $haystackCount)) {
|
|
|
575 |
if (isset($needle[0]) && $needle[0] === $check[$position]) {
|
|
|
576 |
for ($i = 1; $i < $needleCount; $i++) {
|
|
|
577 |
if ($needle[$i] !== $check[$position + $i]) {
|
|
|
578 |
if ($needle[$i] === $check[($position + $i) -1]) {
|
|
|
579 |
$found = true;
|
|
|
580 |
}
|
|
|
581 |
unset($parts[$position - 1]);
|
|
|
582 |
$haystack = array_merge(array($haystack[$position]), $haystack);
|
|
|
583 |
break;
|
|
|
584 |
}
|
|
|
585 |
}
|
|
|
586 |
if (isset($matches[$needle[0]]) && $matches[$needle[0]] > 1) {
|
|
|
587 |
$matches[$needle[0]] = $matches[$needle[0]] - 1;
|
|
|
588 |
} elseif ($i === $needleCount) {
|
|
|
589 |
$found = true;
|
|
|
590 |
}
|
|
|
591 |
}
|
|
|
592 |
|
|
|
593 |
if (!$found && isset($haystack[$position])) {
|
|
|
594 |
$parts[] = $haystack[$position];
|
|
|
595 |
unset($haystack[$position]);
|
|
|
596 |
}
|
|
|
597 |
$position++;
|
|
|
598 |
}
|
|
|
599 |
|
|
|
600 |
if ($found && $part && !empty($parts)) {
|
|
|
601 |
return Multibyte::ascii($parts);
|
|
|
602 |
} elseif ($found && !empty($haystack)) {
|
|
|
603 |
return Multibyte::ascii($haystack);
|
|
|
604 |
}
|
|
|
605 |
return false;
|
|
|
606 |
}
|
|
|
607 |
/**
|
|
|
608 |
* Finds position of last occurrence of a string within another, case insensitive
|
|
|
609 |
*
|
|
|
610 |
* @param string $haystack The string from which to get the position of the last occurrence of $needle.
|
|
|
611 |
* @param string $needle The string to find in $haystack.
|
|
|
612 |
* @param integer $offset The position in $haystack to start searching.
|
|
|
613 |
* @return integer|boolean The numeric position of the last occurrence of $needle in the $haystack string, or false if $needle is not found.
|
|
|
614 |
* @access public
|
|
|
615 |
* @static
|
|
|
616 |
*/
|
|
|
617 |
function strripos($haystack, $needle, $offset = 0) {
|
|
|
618 |
if (!PHP5 || Multibyte::checkMultibyte($haystack)) {
|
|
|
619 |
$found = false;
|
|
|
620 |
$haystack = Multibyte::strtoupper($haystack);
|
|
|
621 |
$haystack = Multibyte::utf8($haystack);
|
|
|
622 |
$haystackCount = count($haystack);
|
|
|
623 |
|
|
|
624 |
$matches = array_count_values($haystack);
|
|
|
625 |
|
|
|
626 |
$needle = Multibyte::strtoupper($needle);
|
|
|
627 |
$needle = Multibyte::utf8($needle);
|
|
|
628 |
$needleCount = count($needle);
|
|
|
629 |
|
|
|
630 |
$position = $offset;
|
|
|
631 |
|
|
|
632 |
while (($found === false) && ($position < $haystackCount)) {
|
|
|
633 |
if (isset($needle[0]) && $needle[0] === $haystack[$position]) {
|
|
|
634 |
for ($i = 1; $i < $needleCount; $i++) {
|
|
|
635 |
if ($needle[$i] !== $haystack[$position + $i]) {
|
|
|
636 |
if ($needle[$i] === $haystack[($position + $i) -1]) {
|
|
|
637 |
$position--;
|
|
|
638 |
$found = true;
|
|
|
639 |
continue;
|
|
|
640 |
}
|
|
|
641 |
}
|
|
|
642 |
}
|
|
|
643 |
|
|
|
644 |
if (!$offset && isset($matches[$needle[0]]) && $matches[$needle[0]] > 1) {
|
|
|
645 |
$matches[$needle[0]] = $matches[$needle[0]] - 1;
|
|
|
646 |
} elseif ($i === $needleCount) {
|
|
|
647 |
$found = true;
|
|
|
648 |
$position--;
|
|
|
649 |
}
|
|
|
650 |
}
|
|
|
651 |
$position++;
|
|
|
652 |
}
|
|
|
653 |
return ($found) ? $position : false;
|
|
|
654 |
}
|
|
|
655 |
return strripos($haystack, $needle, $offset);
|
|
|
656 |
}
|
|
|
657 |
|
|
|
658 |
/**
|
|
|
659 |
* Find position of last occurrence of a string in a string.
|
|
|
660 |
*
|
|
|
661 |
* @param string $haystack The string being checked, for the last occurrence of $needle.
|
|
|
662 |
* @param string $needle The string to find in $haystack.
|
|
|
663 |
* @param integer $offset May be specified to begin searching an arbitrary number of characters into the string.
|
|
|
664 |
* Negative values will stop searching at an arbitrary point prior to the end of the string.
|
|
|
665 |
* @return integer|boolean The numeric position of the last occurrence of $needle in the $haystack string. If $needle is not found, it returns false.
|
|
|
666 |
* @access public
|
|
|
667 |
* @static
|
|
|
668 |
*/
|
|
|
669 |
function strrpos($haystack, $needle, $offset = 0) {
|
|
|
670 |
if (!PHP5 || Multibyte::checkMultibyte($haystack)) {
|
|
|
671 |
$found = false;
|
|
|
672 |
|
|
|
673 |
$haystack = Multibyte::utf8($haystack);
|
|
|
674 |
$haystackCount = count($haystack);
|
|
|
675 |
|
|
|
676 |
$matches = array_count_values($haystack);
|
|
|
677 |
|
|
|
678 |
$needle = Multibyte::utf8($needle);
|
|
|
679 |
$needleCount = count($needle);
|
|
|
680 |
|
|
|
681 |
$position = $offset;
|
|
|
682 |
|
|
|
683 |
while (($found === false) && ($position < $haystackCount)) {
|
|
|
684 |
if (isset($needle[0]) && $needle[0] === $haystack[$position]) {
|
|
|
685 |
for ($i = 1; $i < $needleCount; $i++) {
|
|
|
686 |
if ($needle[$i] !== $haystack[$position + $i]) {
|
|
|
687 |
if ($needle[$i] === $haystack[($position + $i) -1]) {
|
|
|
688 |
$position--;
|
|
|
689 |
$found = true;
|
|
|
690 |
continue;
|
|
|
691 |
}
|
|
|
692 |
}
|
|
|
693 |
}
|
|
|
694 |
|
|
|
695 |
if (!$offset && isset($matches[$needle[0]]) && $matches[$needle[0]] > 1) {
|
|
|
696 |
$matches[$needle[0]] = $matches[$needle[0]] - 1;
|
|
|
697 |
} elseif ($i === $needleCount) {
|
|
|
698 |
$found = true;
|
|
|
699 |
$position--;
|
|
|
700 |
}
|
|
|
701 |
}
|
|
|
702 |
$position++;
|
|
|
703 |
}
|
|
|
704 |
return ($found) ? $position : false;
|
|
|
705 |
}
|
|
|
706 |
return strrpos($haystack, $needle, $offset);
|
|
|
707 |
}
|
|
|
708 |
/**
|
|
|
709 |
* Finds first occurrence of a string within another
|
|
|
710 |
*
|
|
|
711 |
* @param string $haystack The string from which to get the first occurrence of $needle.
|
|
|
712 |
* @param string $needle The string to find in $haystack
|
|
|
713 |
* @param boolean $part Determines which portion of $haystack this function returns.
|
|
|
714 |
* If set to true, it returns all of $haystack from the beginning to the first occurrence of $needle.
|
|
|
715 |
* If set to false, it returns all of $haystack from the first occurrence of $needle to the end, Default value is FALSE.
|
|
|
716 |
* @return string|boolean The portion of $haystack, or true if $needle is not found.
|
|
|
717 |
* @access public
|
|
|
718 |
* @static
|
|
|
719 |
*/
|
|
|
720 |
function strstr($haystack, $needle, $part = false) {
|
|
|
721 |
$php = (PHP_VERSION < 5.3);
|
|
|
722 |
|
|
|
723 |
if (($php && $part) || Multibyte::checkMultibyte($haystack)) {
|
|
|
724 |
$check = Multibyte::utf8($haystack);
|
|
|
725 |
$found = false;
|
|
|
726 |
|
|
|
727 |
$haystack = Multibyte::utf8($haystack);
|
|
|
728 |
$haystackCount = count($haystack);
|
|
|
729 |
|
|
|
730 |
$needle = Multibyte::utf8($needle);
|
|
|
731 |
$needleCount = count($needle);
|
|
|
732 |
|
|
|
733 |
$parts = array();
|
|
|
734 |
$position = 0;
|
|
|
735 |
|
|
|
736 |
while (($found === false) && ($position < $haystackCount)) {
|
|
|
737 |
if (isset($needle[0]) && $needle[0] === $check[$position]) {
|
|
|
738 |
for ($i = 1; $i < $needleCount; $i++) {
|
|
|
739 |
if ($needle[$i] !== $check[$position + $i]) {
|
|
|
740 |
break;
|
|
|
741 |
}
|
|
|
742 |
}
|
|
|
743 |
if ($i === $needleCount) {
|
|
|
744 |
$found = true;
|
|
|
745 |
}
|
|
|
746 |
}
|
|
|
747 |
if (!$found) {
|
|
|
748 |
$parts[] = $haystack[$position];
|
|
|
749 |
unset($haystack[$position]);
|
|
|
750 |
}
|
|
|
751 |
$position++;
|
|
|
752 |
}
|
|
|
753 |
|
|
|
754 |
if ($found && $part && !empty($parts)) {
|
|
|
755 |
return Multibyte::ascii($parts);
|
|
|
756 |
} elseif ($found && !empty($haystack)) {
|
|
|
757 |
return Multibyte::ascii($haystack);
|
|
|
758 |
}
|
|
|
759 |
return false;
|
|
|
760 |
}
|
|
|
761 |
|
|
|
762 |
if (!$php) {
|
|
|
763 |
return strstr($haystack, $needle, $part);
|
|
|
764 |
}
|
|
|
765 |
return strstr($haystack, $needle);
|
|
|
766 |
}
|
|
|
767 |
/**
|
|
|
768 |
* Make a string lowercase
|
|
|
769 |
*
|
|
|
770 |
* @param string $string The string being lowercased.
|
|
|
771 |
* @return string with all alphabetic characters converted to lowercase.
|
|
|
772 |
* @access public
|
|
|
773 |
* @static
|
|
|
774 |
*/
|
|
|
775 |
function strtolower($string) {
|
|
|
776 |
$_this =& Multibyte::getInstance();
|
|
|
777 |
$utf8Map = Multibyte::utf8($string);
|
|
|
778 |
|
|
|
779 |
$length = count($utf8Map);
|
|
|
780 |
$lowerCase = array();
|
|
|
781 |
$matched = false;
|
|
|
782 |
|
|
|
783 |
for ($i = 0 ; $i < $length; $i++) {
|
|
|
784 |
$char = $utf8Map[$i];
|
|
|
785 |
|
|
|
786 |
if ($char < 128) {
|
|
|
787 |
$str = strtolower(chr($char));
|
|
|
788 |
$strlen = strlen($str);
|
|
|
789 |
for ($ii = 0 ; $ii < $strlen; $ii++) {
|
|
|
790 |
$lower = ord(substr($str, $ii, 1));
|
|
|
791 |
}
|
|
|
792 |
$lowerCase[] = $lower;
|
|
|
793 |
$matched = true;
|
|
|
794 |
} else {
|
|
|
795 |
$matched = false;
|
|
|
796 |
$keys = $_this->__find($char, 'upper');
|
|
|
797 |
|
|
|
798 |
if (!empty($keys)) {
|
|
|
799 |
foreach ($keys as $key => $value) {
|
|
|
800 |
if ($keys[$key]['upper'] == $char && count($keys[$key]['lower'][0]) === 1) {
|
|
|
801 |
$lowerCase[] = $keys[$key]['lower'][0];
|
|
|
802 |
$matched = true;
|
|
|
803 |
break 1;
|
|
|
804 |
}
|
|
|
805 |
}
|
|
|
806 |
}
|
|
|
807 |
}
|
|
|
808 |
if ($matched === false) {
|
|
|
809 |
$lowerCase[] = $char;
|
|
|
810 |
}
|
|
|
811 |
}
|
|
|
812 |
return Multibyte::ascii($lowerCase);
|
|
|
813 |
}
|
|
|
814 |
/**
|
|
|
815 |
* Make a string uppercase
|
|
|
816 |
*
|
|
|
817 |
* @param string $string The string being uppercased.
|
|
|
818 |
* @param string $encoding Character encoding name to use. If it is omitted, internal character encoding is used.
|
|
|
819 |
* @return string with all alphabetic characters converted to uppercase.
|
|
|
820 |
* @access public
|
|
|
821 |
* @static
|
|
|
822 |
*/
|
|
|
823 |
function strtoupper($string) {
|
|
|
824 |
$_this =& Multibyte::getInstance();
|
|
|
825 |
$utf8Map = Multibyte::utf8($string);
|
|
|
826 |
|
|
|
827 |
$length = count($utf8Map);
|
|
|
828 |
$matched = false;
|
|
|
829 |
$replaced = array();
|
|
|
830 |
$upperCase = array();
|
|
|
831 |
|
|
|
832 |
for ($i = 0 ; $i < $length; $i++) {
|
|
|
833 |
$char = $utf8Map[$i];
|
|
|
834 |
|
|
|
835 |
if ($char < 128) {
|
|
|
836 |
$str = strtoupper(chr($char));
|
|
|
837 |
$strlen = strlen($str);
|
|
|
838 |
for ($ii = 0 ; $ii < $strlen; $ii++) {
|
|
|
839 |
$upper = ord(substr($str, $ii, 1));
|
|
|
840 |
}
|
|
|
841 |
$upperCase[] = $upper;
|
|
|
842 |
$matched = true;
|
|
|
843 |
|
|
|
844 |
} else {
|
|
|
845 |
$matched = false;
|
|
|
846 |
$keys = $_this->__find($char);
|
|
|
847 |
$keyCount = count($keys);
|
|
|
848 |
|
|
|
849 |
if (!empty($keys)) {
|
|
|
850 |
foreach ($keys as $key => $value) {
|
|
|
851 |
$matched = false;
|
|
|
852 |
$replace = 0;
|
|
|
853 |
if ($length > 1 && count($keys[$key]['lower']) > 1) {
|
|
|
854 |
$j = 0;
|
|
|
855 |
|
|
|
856 |
for ($ii = 0; $ii < count($keys[$key]['lower']); $ii++) {
|
|
|
857 |
$nextChar = $utf8Map[$i + $ii];
|
|
|
858 |
|
|
|
859 |
if (isset($nextChar) && ($nextChar == $keys[$key]['lower'][$j + $ii])) {
|
|
|
860 |
$replace++;
|
|
|
861 |
}
|
|
|
862 |
}
|
|
|
863 |
if ($replace == count($keys[$key]['lower'])) {
|
|
|
864 |
$upperCase[] = $keys[$key]['upper'];
|
|
|
865 |
$replaced = array_merge($replaced, array_values($keys[$key]['lower']));
|
|
|
866 |
$matched = true;
|
|
|
867 |
break 1;
|
|
|
868 |
}
|
|
|
869 |
} elseif ($length > 1 && $keyCount > 1) {
|
|
|
870 |
$j = 0;
|
|
|
871 |
for ($ii = 1; $ii < $keyCount; $ii++) {
|
|
|
872 |
$nextChar = $utf8Map[$i + $ii - 1];
|
|
|
873 |
|
|
|
874 |
if (in_array($nextChar, $keys[$ii]['lower'])) {
|
|
|
875 |
|
|
|
876 |
for ($jj = 0; $jj < count($keys[$ii]['lower']); $jj++) {
|
|
|
877 |
$nextChar = $utf8Map[$i + $jj];
|
|
|
878 |
|
|
|
879 |
if (isset($nextChar) && ($nextChar == $keys[$ii]['lower'][$j + $jj])) {
|
|
|
880 |
$replace++;
|
|
|
881 |
}
|
|
|
882 |
}
|
|
|
883 |
if ($replace == count($keys[$ii]['lower'])) {
|
|
|
884 |
$upperCase[] = $keys[$ii]['upper'];
|
|
|
885 |
$replaced = array_merge($replaced, array_values($keys[$ii]['lower']));
|
|
|
886 |
$matched = true;
|
|
|
887 |
break 2;
|
|
|
888 |
}
|
|
|
889 |
}
|
|
|
890 |
}
|
|
|
891 |
}
|
|
|
892 |
if ($keys[$key]['lower'][0] == $char) {
|
|
|
893 |
$upperCase[] = $keys[$key]['upper'];
|
|
|
894 |
$matched = true;
|
|
|
895 |
break 1;
|
|
|
896 |
}
|
|
|
897 |
}
|
|
|
898 |
}
|
|
|
899 |
}
|
|
|
900 |
if ($matched === false && !in_array($char, $replaced, true)) {
|
|
|
901 |
$upperCase[] = $char;
|
|
|
902 |
}
|
|
|
903 |
}
|
|
|
904 |
return Multibyte::ascii($upperCase);
|
|
|
905 |
}
|
|
|
906 |
/**
|
|
|
907 |
* Count the number of substring occurrences
|
|
|
908 |
*
|
|
|
909 |
* @param string $haystack The string being checked.
|
|
|
910 |
* @param string $needle The string being found.
|
|
|
911 |
* @return integer The number of times the $needle substring occurs in the $haystack string.
|
|
|
912 |
* @access public
|
|
|
913 |
* @static
|
|
|
914 |
*/
|
|
|
915 |
function substrCount($haystack, $needle) {
|
|
|
916 |
$count = 0;
|
|
|
917 |
$haystack = Multibyte::utf8($haystack);
|
|
|
918 |
$haystackCount = count($haystack);
|
|
|
919 |
$matches = array_count_values($haystack);
|
|
|
920 |
$needle = Multibyte::utf8($needle);
|
|
|
921 |
$needleCount = count($needle);
|
|
|
922 |
|
|
|
923 |
if ($needleCount === 1 && isset($matches[$needle[0]])) {
|
|
|
924 |
return $matches[$needle[0]];
|
|
|
925 |
}
|
|
|
926 |
|
|
|
927 |
for ($i = 0; $i < $haystackCount; $i++) {
|
|
|
928 |
if (isset($needle[0]) && $needle[0] === $haystack[$i]) {
|
|
|
929 |
for ($ii = 1; $ii < $needleCount; $ii++) {
|
|
|
930 |
if ($needle[$ii] === $haystack[$i + 1]) {
|
|
|
931 |
if ((isset($needle[$ii + 1]) && $haystack[$i + 2]) && $needle[$ii + 1] !== $haystack[$i + 2]) {
|
|
|
932 |
$count--;
|
|
|
933 |
} else {
|
|
|
934 |
$count++;
|
|
|
935 |
}
|
|
|
936 |
}
|
|
|
937 |
}
|
|
|
938 |
}
|
|
|
939 |
}
|
|
|
940 |
return $count;
|
|
|
941 |
}
|
|
|
942 |
/**
|
|
|
943 |
* Get part of string
|
|
|
944 |
*
|
|
|
945 |
* @param string $string The string being checked.
|
|
|
946 |
* @param integer $start The first position used in $string.
|
|
|
947 |
* @param integer $length The maximum length of the returned string.
|
|
|
948 |
* @return string The portion of $string specified by the $string and $length parameters.
|
|
|
949 |
* @access public
|
|
|
950 |
* @static
|
|
|
951 |
*/
|
|
|
952 |
function substr($string, $start, $length = null) {
|
|
|
953 |
if ($start === 0 && $length === null) {
|
|
|
954 |
return $string;
|
|
|
955 |
}
|
|
|
956 |
|
|
|
957 |
$string = Multibyte::utf8($string);
|
|
|
958 |
$stringCount = count($string);
|
|
|
959 |
|
|
|
960 |
for ($i = 1; $i <= $start; $i++) {
|
|
|
961 |
unset($string[$i - 1]);
|
|
|
962 |
}
|
|
|
963 |
|
|
|
964 |
if ($length === null || count($string) < $length) {
|
|
|
965 |
return Multibyte::ascii($string);
|
|
|
966 |
}
|
|
|
967 |
$string = array_values($string);
|
|
|
968 |
|
|
|
969 |
$value = array();
|
|
|
970 |
for ($i = 0; $i < $length; $i++) {
|
|
|
971 |
$value[] = $string[$i];
|
|
|
972 |
}
|
|
|
973 |
return Multibyte::ascii($value);
|
|
|
974 |
}
|
|
|
975 |
/**
|
|
|
976 |
* Prepare a string for mail transport, using the provided encoding
|
|
|
977 |
*
|
|
|
978 |
* @param string $string value to encode
|
|
|
979 |
* @param string $charset charset to use for encoding. defaults to UTF-8
|
|
|
980 |
* @param string $newline
|
|
|
981 |
* @return string
|
|
|
982 |
* @access public
|
|
|
983 |
* @static
|
|
|
984 |
* @TODO: add support for 'Q'('Quoted Printable') encoding
|
|
|
985 |
*/
|
|
|
986 |
function mimeEncode($string, $charset = null, $newline = "\r\n") {
|
|
|
987 |
if (!Multibyte::checkMultibyte($string) && strlen($string) < 75) {
|
|
|
988 |
return $string;
|
|
|
989 |
}
|
|
|
990 |
|
|
|
991 |
if (empty($charset)) {
|
|
|
992 |
$charset = Configure::read('App.encoding');
|
|
|
993 |
}
|
|
|
994 |
$charset = strtoupper($charset);
|
|
|
995 |
|
|
|
996 |
$start = '=?' . $charset . '?B?';
|
|
|
997 |
$end = '?=';
|
|
|
998 |
$spacer = $end . $newline . ' ' . $start;
|
|
|
999 |
|
|
|
1000 |
$length = 75 - strlen($start) - strlen($end);
|
|
|
1001 |
$length = $length - ($length % 4);
|
|
|
1002 |
if ($charset == 'UTF-8') {
|
|
|
1003 |
$parts = array();
|
|
|
1004 |
$maxchars = floor(($length * 3) / 4);
|
|
|
1005 |
while (strlen($string) > $maxchars) {
|
|
|
1006 |
$i = $maxchars;
|
|
|
1007 |
$test = ord($string[$i]);
|
|
|
1008 |
while ($test >= 128 && $test <= 191) {
|
|
|
1009 |
$i--;
|
|
|
1010 |
$test = ord($string[$i]);
|
|
|
1011 |
}
|
|
|
1012 |
$parts[] = base64_encode(substr($string, 0, $i));
|
|
|
1013 |
$string = substr($string, $i);
|
|
|
1014 |
}
|
|
|
1015 |
$parts[] = base64_encode($string);
|
|
|
1016 |
$string = implode($spacer, $parts);
|
|
|
1017 |
} else {
|
|
|
1018 |
$string = chunk_split(base64_encode($string), $length, $spacer);
|
|
|
1019 |
$string = preg_replace('/' . preg_quote($spacer) . '$/', '', $string);
|
|
|
1020 |
}
|
|
|
1021 |
return $start . $string . $end;
|
|
|
1022 |
}
|
|
|
1023 |
/**
|
|
|
1024 |
* Return the Code points range for Unicode characters
|
|
|
1025 |
*
|
|
|
1026 |
* @param interger $decimal
|
|
|
1027 |
* @return string
|
|
|
1028 |
* @access private
|
|
|
1029 |
*/
|
|
|
1030 |
function __codepoint ($decimal) {
|
|
|
1031 |
if ($decimal > 128 && $decimal < 256) {
|
|
|
1032 |
$return = '0080_00ff'; // Latin-1 Supplement
|
|
|
1033 |
} elseif ($decimal < 384) {
|
|
|
1034 |
$return = '0100_017f'; // Latin Extended-A
|
|
|
1035 |
} elseif ($decimal < 592) {
|
|
|
1036 |
$return = '0180_024F'; // Latin Extended-B
|
|
|
1037 |
} elseif ($decimal < 688) {
|
|
|
1038 |
$return = '0250_02af'; // IPA Extensions
|
|
|
1039 |
} elseif ($decimal >= 880 && $decimal < 1024) {
|
|
|
1040 |
$return = '0370_03ff'; // Greek and Coptic
|
|
|
1041 |
} elseif ($decimal < 1280) {
|
|
|
1042 |
$return = '0400_04ff'; // Cyrillic
|
|
|
1043 |
} elseif ($decimal < 1328) {
|
|
|
1044 |
$return = '0500_052f'; // Cyrillic Supplement
|
|
|
1045 |
} elseif ($decimal < 1424) {
|
|
|
1046 |
$return = '0530_058f'; // Armenian
|
|
|
1047 |
} elseif ($decimal >= 7680 && $decimal < 7936) {
|
|
|
1048 |
$return = '1e00_1eff'; // Latin Extended Additional
|
|
|
1049 |
} elseif ($decimal < 8192) {
|
|
|
1050 |
$return = '1f00_1fff'; // Greek Extended
|
|
|
1051 |
} elseif ($decimal >= 8448 && $decimal < 8528) {
|
|
|
1052 |
$return = '2100_214f'; // Letterlike Symbols
|
|
|
1053 |
} elseif ($decimal < 8592) {
|
|
|
1054 |
$return = '2150_218f'; // Number Forms
|
|
|
1055 |
} elseif ($decimal >= 9312 && $decimal < 9472) {
|
|
|
1056 |
$return = '2460_24ff'; // Enclosed Alphanumerics
|
|
|
1057 |
} elseif ($decimal >= 11264 && $decimal < 11360) {
|
|
|
1058 |
$return = '2c00_2c5f'; // Glagolitic
|
|
|
1059 |
} elseif ($decimal < 11392) {
|
|
|
1060 |
$return = '2c60_2c7f'; // Latin Extended-C
|
|
|
1061 |
} elseif ($decimal < 11520) {
|
|
|
1062 |
$return = '2c80_2cff'; // Coptic
|
|
|
1063 |
} elseif ($decimal >= 65280 && $decimal < 65520) {
|
|
|
1064 |
$return = 'ff00_ffef'; // Halfwidth and Fullwidth Forms
|
|
|
1065 |
} else {
|
|
|
1066 |
$return = false;
|
|
|
1067 |
}
|
|
|
1068 |
$this->__codeRange[$decimal] = $return;
|
|
|
1069 |
return $return;
|
|
|
1070 |
}
|
|
|
1071 |
/**
|
|
|
1072 |
* Find the related code folding values for $char
|
|
|
1073 |
*
|
|
|
1074 |
* @param integer $char decimal value of character
|
|
|
1075 |
* @param string $type
|
|
|
1076 |
* @return array
|
|
|
1077 |
* @access private
|
|
|
1078 |
*/
|
|
|
1079 |
function __find($char, $type = 'lower') {
|
|
|
1080 |
$value = false;
|
|
|
1081 |
$found = array();
|
|
|
1082 |
if (!isset($this->__codeRange[$char])) {
|
|
|
1083 |
$range = $this->__codepoint($char);
|
|
|
1084 |
if ($range === false) {
|
|
|
1085 |
return null;
|
|
|
1086 |
}
|
|
|
1087 |
Configure::load('unicode' . DS . 'casefolding' . DS . $range);
|
|
|
1088 |
$this->__caseFold[$range] = Configure::read($range);
|
|
|
1089 |
Configure::delete($range);
|
|
|
1090 |
}
|
|
|
1091 |
|
|
|
1092 |
if (!$this->__codeRange[$char]) {
|
|
|
1093 |
return null;
|
|
|
1094 |
}
|
|
|
1095 |
$this->__table = $this->__codeRange[$char];
|
|
|
1096 |
$count = count($this->__caseFold[$this->__table]);
|
|
|
1097 |
|
|
|
1098 |
for ($i = 0; $i < $count; $i++) {
|
|
|
1099 |
if ($type === 'lower' && $this->__caseFold[$this->__table][$i][$type][0] === $char) {
|
|
|
1100 |
$found[] = $this->__caseFold[$this->__table][$i];
|
|
|
1101 |
} elseif ($type === 'upper' && $this->__caseFold[$this->__table][$i][$type] === $char) {
|
|
|
1102 |
$found[] = $this->__caseFold[$this->__table][$i];
|
|
|
1103 |
}
|
|
|
1104 |
}
|
|
|
1105 |
return $found;
|
|
|
1106 |
}
|
|
|
1107 |
/**
|
|
|
1108 |
* Check the $string for multibyte characters
|
|
|
1109 |
* @param string $string value to test
|
|
|
1110 |
* @return boolean
|
|
|
1111 |
* @access public
|
|
|
1112 |
* @static
|
|
|
1113 |
*/
|
|
|
1114 |
function checkMultibyte($string) {
|
|
|
1115 |
$length = strlen($string);
|
|
|
1116 |
|
|
|
1117 |
for ($i = 0; $i < $length; $i++ ) {
|
|
|
1118 |
$value = ord(($string[$i]));
|
|
|
1119 |
if ($value > 128) {
|
|
|
1120 |
return true;
|
|
|
1121 |
}
|
|
|
1122 |
}
|
|
|
1123 |
return false;
|
|
|
1124 |
}
|
|
|
1125 |
}
|
|
|
1126 |
?>
|