| 148 |
lars |
1 |
<?php
|
|
|
2 |
|
|
|
3 |
/*
|
|
|
4 |
* This file is part of the Symfony package.
|
|
|
5 |
*
|
|
|
6 |
* (c) Fabien Potencier <fabien@symfony.com>
|
|
|
7 |
*
|
|
|
8 |
* For the full copyright and license information, please view the LICENSE
|
|
|
9 |
* file that was distributed with this source code.
|
|
|
10 |
*/
|
|
|
11 |
|
|
|
12 |
namespace Symfony\Polyfill\Mbstring;
|
|
|
13 |
|
|
|
14 |
/**
|
|
|
15 |
* Partial mbstring implementation in PHP, iconv based, UTF-8 centric.
|
|
|
16 |
*
|
|
|
17 |
* Implemented:
|
|
|
18 |
* - mb_chr - Returns a specific character from its Unicode code point
|
|
|
19 |
* - mb_convert_encoding - Convert character encoding
|
|
|
20 |
* - mb_convert_variables - Convert character code in variable(s)
|
|
|
21 |
* - mb_decode_mimeheader - Decode string in MIME header field
|
|
|
22 |
* - mb_encode_mimeheader - Encode string for MIME header XXX NATIVE IMPLEMENTATION IS REALLY BUGGED
|
|
|
23 |
* - mb_decode_numericentity - Decode HTML numeric string reference to character
|
|
|
24 |
* - mb_encode_numericentity - Encode character to HTML numeric string reference
|
|
|
25 |
* - mb_convert_case - Perform case folding on a string
|
|
|
26 |
* - mb_detect_encoding - Detect character encoding
|
|
|
27 |
* - mb_get_info - Get internal settings of mbstring
|
|
|
28 |
* - mb_http_input - Detect HTTP input character encoding
|
|
|
29 |
* - mb_http_output - Set/Get HTTP output character encoding
|
|
|
30 |
* - mb_internal_encoding - Set/Get internal character encoding
|
|
|
31 |
* - mb_list_encodings - Returns an array of all supported encodings
|
|
|
32 |
* - mb_ord - Returns the Unicode code point of a character
|
|
|
33 |
* - mb_output_handler - Callback function converts character encoding in output buffer
|
|
|
34 |
* - mb_scrub - Replaces ill-formed byte sequences with substitute characters
|
|
|
35 |
* - mb_strlen - Get string length
|
|
|
36 |
* - mb_strpos - Find position of first occurrence of string in a string
|
|
|
37 |
* - mb_strrpos - Find position of last occurrence of a string in a string
|
|
|
38 |
* - mb_str_split - Convert a string to an array
|
|
|
39 |
* - mb_strtolower - Make a string lowercase
|
|
|
40 |
* - mb_strtoupper - Make a string uppercase
|
|
|
41 |
* - mb_substitute_character - Set/Get substitution character
|
|
|
42 |
* - mb_substr - Get part of string
|
|
|
43 |
* - mb_stripos - Finds position of first occurrence of a string within another, case insensitive
|
|
|
44 |
* - mb_stristr - Finds first occurrence of a string within another, case insensitive
|
|
|
45 |
* - mb_strrchr - Finds the last occurrence of a character in a string within another
|
|
|
46 |
* - mb_strrichr - Finds the last occurrence of a character in a string within another, case insensitive
|
|
|
47 |
* - mb_strripos - Finds position of last occurrence of a string within another, case insensitive
|
|
|
48 |
* - mb_strstr - Finds first occurrence of a string within another
|
|
|
49 |
* - mb_strwidth - Return width of string
|
|
|
50 |
* - mb_substr_count - Count the number of substring occurrences
|
|
|
51 |
*
|
|
|
52 |
* Not implemented:
|
|
|
53 |
* - mb_convert_kana - Convert "kana" one from another ("zen-kaku", "han-kaku" and more)
|
|
|
54 |
* - mb_ereg_* - Regular expression with multibyte support
|
|
|
55 |
* - mb_parse_str - Parse GET/POST/COOKIE data and set global variable
|
|
|
56 |
* - mb_preferred_mime_name - Get MIME charset string
|
|
|
57 |
* - mb_regex_encoding - Returns current encoding for multibyte regex as string
|
|
|
58 |
* - mb_regex_set_options - Set/Get the default options for mbregex functions
|
|
|
59 |
* - mb_send_mail - Send encoded mail
|
|
|
60 |
* - mb_split - Split multibyte string using regular expression
|
|
|
61 |
* - mb_strcut - Get part of string
|
|
|
62 |
* - mb_strimwidth - Get truncated string with specified width
|
|
|
63 |
*
|
|
|
64 |
* @author Nicolas Grekas <p@tchwork.com>
|
|
|
65 |
*
|
|
|
66 |
* @internal
|
|
|
67 |
*/
|
|
|
68 |
final class Mbstring
|
|
|
69 |
{
|
|
|
70 |
public const MB_CASE_FOLD = \PHP_INT_MAX;
|
|
|
71 |
|
|
|
72 |
private const CASE_FOLD = [
|
|
|
73 |
['µ', 'ſ', "\xCD\x85", 'ς', "\xCF\x90", "\xCF\x91", "\xCF\x95", "\xCF\x96", "\xCF\xB0", "\xCF\xB1", "\xCF\xB5", "\xE1\xBA\x9B", "\xE1\xBE\xBE"],
|
|
|
74 |
['μ', 's', 'ι', 'σ', 'β', 'θ', 'φ', 'π', 'κ', 'ρ', 'ε', "\xE1\xB9\xA1", 'ι'],
|
|
|
75 |
];
|
|
|
76 |
|
|
|
77 |
private static $encodingList = ['ASCII', 'UTF-8'];
|
|
|
78 |
private static $language = 'neutral';
|
|
|
79 |
private static $internalEncoding = 'UTF-8';
|
|
|
80 |
|
|
|
81 |
public static function mb_convert_encoding($s, $toEncoding, $fromEncoding = null)
|
|
|
82 |
{
|
|
|
83 |
if (\is_array($fromEncoding) || (null !== $fromEncoding && false !== strpos($fromEncoding, ','))) {
|
|
|
84 |
$fromEncoding = self::mb_detect_encoding($s, $fromEncoding);
|
|
|
85 |
} else {
|
|
|
86 |
$fromEncoding = self::getEncoding($fromEncoding);
|
|
|
87 |
}
|
|
|
88 |
|
|
|
89 |
$toEncoding = self::getEncoding($toEncoding);
|
|
|
90 |
|
|
|
91 |
if ('BASE64' === $fromEncoding) {
|
|
|
92 |
$s = base64_decode($s);
|
|
|
93 |
$fromEncoding = $toEncoding;
|
|
|
94 |
}
|
|
|
95 |
|
|
|
96 |
if ('BASE64' === $toEncoding) {
|
|
|
97 |
return base64_encode($s);
|
|
|
98 |
}
|
|
|
99 |
|
|
|
100 |
if ('HTML-ENTITIES' === $toEncoding || 'HTML' === $toEncoding) {
|
|
|
101 |
if ('HTML-ENTITIES' === $fromEncoding || 'HTML' === $fromEncoding) {
|
|
|
102 |
$fromEncoding = 'Windows-1252';
|
|
|
103 |
}
|
|
|
104 |
if ('UTF-8' !== $fromEncoding) {
|
|
|
105 |
$s = iconv($fromEncoding, 'UTF-8//IGNORE', $s);
|
|
|
106 |
}
|
|
|
107 |
|
|
|
108 |
return preg_replace_callback('/[\x80-\xFF]+/', [__CLASS__, 'html_encoding_callback'], $s);
|
|
|
109 |
}
|
|
|
110 |
|
|
|
111 |
if ('HTML-ENTITIES' === $fromEncoding) {
|
|
|
112 |
$s = html_entity_decode($s, \ENT_COMPAT, 'UTF-8');
|
|
|
113 |
$fromEncoding = 'UTF-8';
|
|
|
114 |
}
|
|
|
115 |
|
|
|
116 |
return iconv($fromEncoding, $toEncoding.'//IGNORE', $s);
|
|
|
117 |
}
|
|
|
118 |
|
|
|
119 |
public static function mb_convert_variables($toEncoding, $fromEncoding, &...$vars)
|
|
|
120 |
{
|
|
|
121 |
$ok = true;
|
|
|
122 |
array_walk_recursive($vars, function (&$v) use (&$ok, $toEncoding, $fromEncoding) {
|
|
|
123 |
if (false === $v = self::mb_convert_encoding($v, $toEncoding, $fromEncoding)) {
|
|
|
124 |
$ok = false;
|
|
|
125 |
}
|
|
|
126 |
});
|
|
|
127 |
|
|
|
128 |
return $ok ? $fromEncoding : false;
|
|
|
129 |
}
|
|
|
130 |
|
|
|
131 |
public static function mb_decode_mimeheader($s)
|
|
|
132 |
{
|
|
|
133 |
return iconv_mime_decode($s, 2, self::$internalEncoding);
|
|
|
134 |
}
|
|
|
135 |
|
|
|
136 |
public static function mb_encode_mimeheader($s, $charset = null, $transferEncoding = null, $linefeed = null, $indent = null)
|
|
|
137 |
{
|
|
|
138 |
trigger_error('mb_encode_mimeheader() is bugged. Please use iconv_mime_encode() instead', \E_USER_WARNING);
|
|
|
139 |
}
|
|
|
140 |
|
|
|
141 |
public static function mb_decode_numericentity($s, $convmap, $encoding = null)
|
|
|
142 |
{
|
|
|
143 |
if (null !== $s && !\is_scalar($s) && !(\is_object($s) && method_exists($s, '__toString'))) {
|
|
|
144 |
trigger_error('mb_decode_numericentity() expects parameter 1 to be string, '.\gettype($s).' given', \E_USER_WARNING);
|
|
|
145 |
|
|
|
146 |
return null;
|
|
|
147 |
}
|
|
|
148 |
|
|
|
149 |
if (!\is_array($convmap) || (80000 > \PHP_VERSION_ID && !$convmap)) {
|
|
|
150 |
return false;
|
|
|
151 |
}
|
|
|
152 |
|
|
|
153 |
if (null !== $encoding && !\is_scalar($encoding)) {
|
|
|
154 |
trigger_error('mb_decode_numericentity() expects parameter 3 to be string, '.\gettype($s).' given', \E_USER_WARNING);
|
|
|
155 |
|
|
|
156 |
return ''; // Instead of null (cf. mb_encode_numericentity).
|
|
|
157 |
}
|
|
|
158 |
|
|
|
159 |
$s = (string) $s;
|
|
|
160 |
if ('' === $s) {
|
|
|
161 |
return '';
|
|
|
162 |
}
|
|
|
163 |
|
|
|
164 |
$encoding = self::getEncoding($encoding);
|
|
|
165 |
|
|
|
166 |
if ('UTF-8' === $encoding) {
|
|
|
167 |
$encoding = null;
|
|
|
168 |
if (!preg_match('//u', $s)) {
|
|
|
169 |
$s = @iconv('UTF-8', 'UTF-8//IGNORE', $s);
|
|
|
170 |
}
|
|
|
171 |
} else {
|
|
|
172 |
$s = iconv($encoding, 'UTF-8//IGNORE', $s);
|
|
|
173 |
}
|
|
|
174 |
|
|
|
175 |
$cnt = floor(\count($convmap) / 4) * 4;
|
|
|
176 |
|
|
|
177 |
for ($i = 0; $i < $cnt; $i += 4) {
|
|
|
178 |
// collector_decode_htmlnumericentity ignores $convmap[$i + 3]
|
|
|
179 |
$convmap[$i] += $convmap[$i + 2];
|
|
|
180 |
$convmap[$i + 1] += $convmap[$i + 2];
|
|
|
181 |
}
|
|
|
182 |
|
|
|
183 |
$s = preg_replace_callback('/&#(?:0*([0-9]+)|x0*([0-9a-fA-F]+))(?!&);?/', function (array $m) use ($cnt, $convmap) {
|
|
|
184 |
$c = isset($m[2]) ? (int) hexdec($m[2]) : $m[1];
|
|
|
185 |
for ($i = 0; $i < $cnt; $i += 4) {
|
|
|
186 |
if ($c >= $convmap[$i] && $c <= $convmap[$i + 1]) {
|
|
|
187 |
return self::mb_chr($c - $convmap[$i + 2]);
|
|
|
188 |
}
|
|
|
189 |
}
|
|
|
190 |
|
|
|
191 |
return $m[0];
|
|
|
192 |
}, $s);
|
|
|
193 |
|
|
|
194 |
if (null === $encoding) {
|
|
|
195 |
return $s;
|
|
|
196 |
}
|
|
|
197 |
|
|
|
198 |
return iconv('UTF-8', $encoding.'//IGNORE', $s);
|
|
|
199 |
}
|
|
|
200 |
|
|
|
201 |
public static function mb_encode_numericentity($s, $convmap, $encoding = null, $is_hex = false)
|
|
|
202 |
{
|
|
|
203 |
if (null !== $s && !\is_scalar($s) && !(\is_object($s) && method_exists($s, '__toString'))) {
|
|
|
204 |
trigger_error('mb_encode_numericentity() expects parameter 1 to be string, '.\gettype($s).' given', \E_USER_WARNING);
|
|
|
205 |
|
|
|
206 |
return null;
|
|
|
207 |
}
|
|
|
208 |
|
|
|
209 |
if (!\is_array($convmap) || (80000 > \PHP_VERSION_ID && !$convmap)) {
|
|
|
210 |
return false;
|
|
|
211 |
}
|
|
|
212 |
|
|
|
213 |
if (null !== $encoding && !\is_scalar($encoding)) {
|
|
|
214 |
trigger_error('mb_encode_numericentity() expects parameter 3 to be string, '.\gettype($s).' given', \E_USER_WARNING);
|
|
|
215 |
|
|
|
216 |
return null; // Instead of '' (cf. mb_decode_numericentity).
|
|
|
217 |
}
|
|
|
218 |
|
|
|
219 |
if (null !== $is_hex && !\is_scalar($is_hex)) {
|
|
|
220 |
trigger_error('mb_encode_numericentity() expects parameter 4 to be boolean, '.\gettype($s).' given', \E_USER_WARNING);
|
|
|
221 |
|
|
|
222 |
return null;
|
|
|
223 |
}
|
|
|
224 |
|
|
|
225 |
$s = (string) $s;
|
|
|
226 |
if ('' === $s) {
|
|
|
227 |
return '';
|
|
|
228 |
}
|
|
|
229 |
|
|
|
230 |
$encoding = self::getEncoding($encoding);
|
|
|
231 |
|
|
|
232 |
if ('UTF-8' === $encoding) {
|
|
|
233 |
$encoding = null;
|
|
|
234 |
if (!preg_match('//u', $s)) {
|
|
|
235 |
$s = @iconv('UTF-8', 'UTF-8//IGNORE', $s);
|
|
|
236 |
}
|
|
|
237 |
} else {
|
|
|
238 |
$s = iconv($encoding, 'UTF-8//IGNORE', $s);
|
|
|
239 |
}
|
|
|
240 |
|
|
|
241 |
static $ulenMask = ["\xC0" => 2, "\xD0" => 2, "\xE0" => 3, "\xF0" => 4];
|
|
|
242 |
|
|
|
243 |
$cnt = floor(\count($convmap) / 4) * 4;
|
|
|
244 |
$i = 0;
|
|
|
245 |
$len = \strlen($s);
|
|
|
246 |
$result = '';
|
|
|
247 |
|
|
|
248 |
while ($i < $len) {
|
|
|
249 |
$ulen = $s[$i] < "\x80" ? 1 : $ulenMask[$s[$i] & "\xF0"];
|
|
|
250 |
$uchr = substr($s, $i, $ulen);
|
|
|
251 |
$i += $ulen;
|
|
|
252 |
$c = self::mb_ord($uchr);
|
|
|
253 |
|
|
|
254 |
for ($j = 0; $j < $cnt; $j += 4) {
|
|
|
255 |
if ($c >= $convmap[$j] && $c <= $convmap[$j + 1]) {
|
|
|
256 |
$cOffset = ($c + $convmap[$j + 2]) & $convmap[$j + 3];
|
|
|
257 |
$result .= $is_hex ? sprintf('&#x%X;', $cOffset) : '&#'.$cOffset.';';
|
|
|
258 |
continue 2;
|
|
|
259 |
}
|
|
|
260 |
}
|
|
|
261 |
$result .= $uchr;
|
|
|
262 |
}
|
|
|
263 |
|
|
|
264 |
if (null === $encoding) {
|
|
|
265 |
return $result;
|
|
|
266 |
}
|
|
|
267 |
|
|
|
268 |
return iconv('UTF-8', $encoding.'//IGNORE', $result);
|
|
|
269 |
}
|
|
|
270 |
|
|
|
271 |
public static function mb_convert_case($s, $mode, $encoding = null)
|
|
|
272 |
{
|
|
|
273 |
$s = (string) $s;
|
|
|
274 |
if ('' === $s) {
|
|
|
275 |
return '';
|
|
|
276 |
}
|
|
|
277 |
|
|
|
278 |
$encoding = self::getEncoding($encoding);
|
|
|
279 |
|
|
|
280 |
if ('UTF-8' === $encoding) {
|
|
|
281 |
$encoding = null;
|
|
|
282 |
if (!preg_match('//u', $s)) {
|
|
|
283 |
$s = @iconv('UTF-8', 'UTF-8//IGNORE', $s);
|
|
|
284 |
}
|
|
|
285 |
} else {
|
|
|
286 |
$s = iconv($encoding, 'UTF-8//IGNORE', $s);
|
|
|
287 |
}
|
|
|
288 |
|
|
|
289 |
if (\MB_CASE_TITLE == $mode) {
|
|
|
290 |
static $titleRegexp = null;
|
|
|
291 |
if (null === $titleRegexp) {
|
|
|
292 |
$titleRegexp = self::getData('titleCaseRegexp');
|
|
|
293 |
}
|
|
|
294 |
$s = preg_replace_callback($titleRegexp, [__CLASS__, 'title_case'], $s);
|
|
|
295 |
} else {
|
|
|
296 |
if (\MB_CASE_UPPER == $mode) {
|
|
|
297 |
static $upper = null;
|
|
|
298 |
if (null === $upper) {
|
|
|
299 |
$upper = self::getData('upperCase');
|
|
|
300 |
}
|
|
|
301 |
$map = $upper;
|
|
|
302 |
} else {
|
|
|
303 |
if (self::MB_CASE_FOLD === $mode) {
|
|
|
304 |
$s = str_replace(self::CASE_FOLD[0], self::CASE_FOLD[1], $s);
|
|
|
305 |
}
|
|
|
306 |
|
|
|
307 |
static $lower = null;
|
|
|
308 |
if (null === $lower) {
|
|
|
309 |
$lower = self::getData('lowerCase');
|
|
|
310 |
}
|
|
|
311 |
$map = $lower;
|
|
|
312 |
}
|
|
|
313 |
|
|
|
314 |
static $ulenMask = ["\xC0" => 2, "\xD0" => 2, "\xE0" => 3, "\xF0" => 4];
|
|
|
315 |
|
|
|
316 |
$i = 0;
|
|
|
317 |
$len = \strlen($s);
|
|
|
318 |
|
|
|
319 |
while ($i < $len) {
|
|
|
320 |
$ulen = $s[$i] < "\x80" ? 1 : $ulenMask[$s[$i] & "\xF0"];
|
|
|
321 |
$uchr = substr($s, $i, $ulen);
|
|
|
322 |
$i += $ulen;
|
|
|
323 |
|
|
|
324 |
if (isset($map[$uchr])) {
|
|
|
325 |
$uchr = $map[$uchr];
|
|
|
326 |
$nlen = \strlen($uchr);
|
|
|
327 |
|
|
|
328 |
if ($nlen == $ulen) {
|
|
|
329 |
$nlen = $i;
|
|
|
330 |
do {
|
|
|
331 |
$s[--$nlen] = $uchr[--$ulen];
|
|
|
332 |
} while ($ulen);
|
|
|
333 |
} else {
|
|
|
334 |
$s = substr_replace($s, $uchr, $i - $ulen, $ulen);
|
|
|
335 |
$len += $nlen - $ulen;
|
|
|
336 |
$i += $nlen - $ulen;
|
|
|
337 |
}
|
|
|
338 |
}
|
|
|
339 |
}
|
|
|
340 |
}
|
|
|
341 |
|
|
|
342 |
if (null === $encoding) {
|
|
|
343 |
return $s;
|
|
|
344 |
}
|
|
|
345 |
|
|
|
346 |
return iconv('UTF-8', $encoding.'//IGNORE', $s);
|
|
|
347 |
}
|
|
|
348 |
|
|
|
349 |
public static function mb_internal_encoding($encoding = null)
|
|
|
350 |
{
|
|
|
351 |
if (null === $encoding) {
|
|
|
352 |
return self::$internalEncoding;
|
|
|
353 |
}
|
|
|
354 |
|
|
|
355 |
$normalizedEncoding = self::getEncoding($encoding);
|
|
|
356 |
|
|
|
357 |
if ('UTF-8' === $normalizedEncoding || false !== @iconv($normalizedEncoding, $normalizedEncoding, ' ')) {
|
|
|
358 |
self::$internalEncoding = $normalizedEncoding;
|
|
|
359 |
|
|
|
360 |
return true;
|
|
|
361 |
}
|
|
|
362 |
|
|
|
363 |
if (80000 > \PHP_VERSION_ID) {
|
|
|
364 |
return false;
|
|
|
365 |
}
|
|
|
366 |
|
|
|
367 |
throw new \ValueError(sprintf('Argument #1 ($encoding) must be a valid encoding, "%s" given', $encoding));
|
|
|
368 |
}
|
|
|
369 |
|
|
|
370 |
public static function mb_language($lang = null)
|
|
|
371 |
{
|
|
|
372 |
if (null === $lang) {
|
|
|
373 |
return self::$language;
|
|
|
374 |
}
|
|
|
375 |
|
|
|
376 |
switch ($normalizedLang = strtolower($lang)) {
|
|
|
377 |
case 'uni':
|
|
|
378 |
case 'neutral':
|
|
|
379 |
self::$language = $normalizedLang;
|
|
|
380 |
|
|
|
381 |
return true;
|
|
|
382 |
}
|
|
|
383 |
|
|
|
384 |
if (80000 > \PHP_VERSION_ID) {
|
|
|
385 |
return false;
|
|
|
386 |
}
|
|
|
387 |
|
|
|
388 |
throw new \ValueError(sprintf('Argument #1 ($language) must be a valid language, "%s" given', $lang));
|
|
|
389 |
}
|
|
|
390 |
|
|
|
391 |
public static function mb_list_encodings()
|
|
|
392 |
{
|
|
|
393 |
return ['UTF-8'];
|
|
|
394 |
}
|
|
|
395 |
|
|
|
396 |
public static function mb_encoding_aliases($encoding)
|
|
|
397 |
{
|
|
|
398 |
switch (strtoupper($encoding)) {
|
|
|
399 |
case 'UTF8':
|
|
|
400 |
case 'UTF-8':
|
|
|
401 |
return ['utf8'];
|
|
|
402 |
}
|
|
|
403 |
|
|
|
404 |
return false;
|
|
|
405 |
}
|
|
|
406 |
|
|
|
407 |
public static function mb_check_encoding($var = null, $encoding = null)
|
|
|
408 |
{
|
|
|
409 |
if (null === $encoding) {
|
|
|
410 |
if (null === $var) {
|
|
|
411 |
return false;
|
|
|
412 |
}
|
|
|
413 |
$encoding = self::$internalEncoding;
|
|
|
414 |
}
|
|
|
415 |
|
|
|
416 |
return self::mb_detect_encoding($var, [$encoding]) || false !== @iconv($encoding, $encoding, $var);
|
|
|
417 |
}
|
|
|
418 |
|
|
|
419 |
public static function mb_detect_encoding($str, $encodingList = null, $strict = false)
|
|
|
420 |
{
|
|
|
421 |
if (null === $encodingList) {
|
|
|
422 |
$encodingList = self::$encodingList;
|
|
|
423 |
} else {
|
|
|
424 |
if (!\is_array($encodingList)) {
|
|
|
425 |
$encodingList = array_map('trim', explode(',', $encodingList));
|
|
|
426 |
}
|
|
|
427 |
$encodingList = array_map('strtoupper', $encodingList);
|
|
|
428 |
}
|
|
|
429 |
|
|
|
430 |
foreach ($encodingList as $enc) {
|
|
|
431 |
switch ($enc) {
|
|
|
432 |
case 'ASCII':
|
|
|
433 |
if (!preg_match('/[\x80-\xFF]/', $str)) {
|
|
|
434 |
return $enc;
|
|
|
435 |
}
|
|
|
436 |
break;
|
|
|
437 |
|
|
|
438 |
case 'UTF8':
|
|
|
439 |
case 'UTF-8':
|
|
|
440 |
if (preg_match('//u', $str)) {
|
|
|
441 |
return 'UTF-8';
|
|
|
442 |
}
|
|
|
443 |
break;
|
|
|
444 |
|
|
|
445 |
default:
|
|
|
446 |
if (0 === strncmp($enc, 'ISO-8859-', 9)) {
|
|
|
447 |
return $enc;
|
|
|
448 |
}
|
|
|
449 |
}
|
|
|
450 |
}
|
|
|
451 |
|
|
|
452 |
return false;
|
|
|
453 |
}
|
|
|
454 |
|
|
|
455 |
public static function mb_detect_order($encodingList = null)
|
|
|
456 |
{
|
|
|
457 |
if (null === $encodingList) {
|
|
|
458 |
return self::$encodingList;
|
|
|
459 |
}
|
|
|
460 |
|
|
|
461 |
if (!\is_array($encodingList)) {
|
|
|
462 |
$encodingList = array_map('trim', explode(',', $encodingList));
|
|
|
463 |
}
|
|
|
464 |
$encodingList = array_map('strtoupper', $encodingList);
|
|
|
465 |
|
|
|
466 |
foreach ($encodingList as $enc) {
|
|
|
467 |
switch ($enc) {
|
|
|
468 |
default:
|
|
|
469 |
if (strncmp($enc, 'ISO-8859-', 9)) {
|
|
|
470 |
return false;
|
|
|
471 |
}
|
|
|
472 |
// no break
|
|
|
473 |
case 'ASCII':
|
|
|
474 |
case 'UTF8':
|
|
|
475 |
case 'UTF-8':
|
|
|
476 |
}
|
|
|
477 |
}
|
|
|
478 |
|
|
|
479 |
self::$encodingList = $encodingList;
|
|
|
480 |
|
|
|
481 |
return true;
|
|
|
482 |
}
|
|
|
483 |
|
|
|
484 |
public static function mb_strlen($s, $encoding = null)
|
|
|
485 |
{
|
|
|
486 |
$encoding = self::getEncoding($encoding);
|
|
|
487 |
if ('CP850' === $encoding || 'ASCII' === $encoding) {
|
|
|
488 |
return \strlen($s);
|
|
|
489 |
}
|
|
|
490 |
|
|
|
491 |
return @iconv_strlen($s, $encoding);
|
|
|
492 |
}
|
|
|
493 |
|
|
|
494 |
public static function mb_strpos($haystack, $needle, $offset = 0, $encoding = null)
|
|
|
495 |
{
|
|
|
496 |
$encoding = self::getEncoding($encoding);
|
|
|
497 |
if ('CP850' === $encoding || 'ASCII' === $encoding) {
|
|
|
498 |
return strpos($haystack, $needle, $offset);
|
|
|
499 |
}
|
|
|
500 |
|
|
|
501 |
$needle = (string) $needle;
|
|
|
502 |
if ('' === $needle) {
|
|
|
503 |
if (80000 > \PHP_VERSION_ID) {
|
|
|
504 |
trigger_error(__METHOD__.': Empty delimiter', \E_USER_WARNING);
|
|
|
505 |
|
|
|
506 |
return false;
|
|
|
507 |
}
|
|
|
508 |
|
|
|
509 |
return 0;
|
|
|
510 |
}
|
|
|
511 |
|
|
|
512 |
return iconv_strpos($haystack, $needle, $offset, $encoding);
|
|
|
513 |
}
|
|
|
514 |
|
|
|
515 |
public static function mb_strrpos($haystack, $needle, $offset = 0, $encoding = null)
|
|
|
516 |
{
|
|
|
517 |
$encoding = self::getEncoding($encoding);
|
|
|
518 |
if ('CP850' === $encoding || 'ASCII' === $encoding) {
|
|
|
519 |
return strrpos($haystack, $needle, $offset);
|
|
|
520 |
}
|
|
|
521 |
|
|
|
522 |
if ($offset != (int) $offset) {
|
|
|
523 |
$offset = 0;
|
|
|
524 |
} elseif ($offset = (int) $offset) {
|
|
|
525 |
if ($offset < 0) {
|
|
|
526 |
if (0 > $offset += self::mb_strlen($needle)) {
|
|
|
527 |
$haystack = self::mb_substr($haystack, 0, $offset, $encoding);
|
|
|
528 |
}
|
|
|
529 |
$offset = 0;
|
|
|
530 |
} else {
|
|
|
531 |
$haystack = self::mb_substr($haystack, $offset, 2147483647, $encoding);
|
|
|
532 |
}
|
|
|
533 |
}
|
|
|
534 |
|
|
|
535 |
$pos = '' !== $needle || 80000 > \PHP_VERSION_ID
|
|
|
536 |
? iconv_strrpos($haystack, $needle, $encoding)
|
|
|
537 |
: self::mb_strlen($haystack, $encoding);
|
|
|
538 |
|
|
|
539 |
return false !== $pos ? $offset + $pos : false;
|
|
|
540 |
}
|
|
|
541 |
|
|
|
542 |
public static function mb_str_split($string, $split_length = 1, $encoding = null)
|
|
|
543 |
{
|
|
|
544 |
if (null !== $string && !\is_scalar($string) && !(\is_object($string) && method_exists($string, '__toString'))) {
|
|
|
545 |
trigger_error('mb_str_split() expects parameter 1 to be string, '.\gettype($string).' given', \E_USER_WARNING);
|
|
|
546 |
|
|
|
547 |
return null;
|
|
|
548 |
}
|
|
|
549 |
|
|
|
550 |
if (1 > $split_length = (int) $split_length) {
|
|
|
551 |
if (80000 > \PHP_VERSION_ID) {
|
|
|
552 |
trigger_error('The length of each segment must be greater than zero', \E_USER_WARNING);
|
|
|
553 |
|
|
|
554 |
return false;
|
|
|
555 |
}
|
|
|
556 |
|
|
|
557 |
throw new \ValueError('Argument #2 ($length) must be greater than 0');
|
|
|
558 |
}
|
|
|
559 |
|
|
|
560 |
if (null === $encoding) {
|
|
|
561 |
$encoding = mb_internal_encoding();
|
|
|
562 |
}
|
|
|
563 |
|
|
|
564 |
if ('UTF-8' === $encoding = self::getEncoding($encoding)) {
|
|
|
565 |
$rx = '/(';
|
|
|
566 |
while (65535 < $split_length) {
|
|
|
567 |
$rx .= '.{65535}';
|
|
|
568 |
$split_length -= 65535;
|
|
|
569 |
}
|
|
|
570 |
$rx .= '.{'.$split_length.'})/us';
|
|
|
571 |
|
|
|
572 |
return preg_split($rx, $string, -1, \PREG_SPLIT_DELIM_CAPTURE | \PREG_SPLIT_NO_EMPTY);
|
|
|
573 |
}
|
|
|
574 |
|
|
|
575 |
$result = [];
|
|
|
576 |
$length = mb_strlen($string, $encoding);
|
|
|
577 |
|
|
|
578 |
for ($i = 0; $i < $length; $i += $split_length) {
|
|
|
579 |
$result[] = mb_substr($string, $i, $split_length, $encoding);
|
|
|
580 |
}
|
|
|
581 |
|
|
|
582 |
return $result;
|
|
|
583 |
}
|
|
|
584 |
|
|
|
585 |
public static function mb_strtolower($s, $encoding = null)
|
|
|
586 |
{
|
|
|
587 |
return self::mb_convert_case($s, \MB_CASE_LOWER, $encoding);
|
|
|
588 |
}
|
|
|
589 |
|
|
|
590 |
public static function mb_strtoupper($s, $encoding = null)
|
|
|
591 |
{
|
|
|
592 |
return self::mb_convert_case($s, \MB_CASE_UPPER, $encoding);
|
|
|
593 |
}
|
|
|
594 |
|
|
|
595 |
public static function mb_substitute_character($c = null)
|
|
|
596 |
{
|
|
|
597 |
if (null === $c) {
|
|
|
598 |
return 'none';
|
|
|
599 |
}
|
|
|
600 |
if (0 === strcasecmp($c, 'none')) {
|
|
|
601 |
return true;
|
|
|
602 |
}
|
|
|
603 |
if (80000 > \PHP_VERSION_ID) {
|
|
|
604 |
return false;
|
|
|
605 |
}
|
|
|
606 |
if (\is_int($c) || 'long' === $c || 'entity' === $c) {
|
|
|
607 |
return false;
|
|
|
608 |
}
|
|
|
609 |
|
|
|
610 |
throw new \ValueError('Argument #1 ($substitute_character) must be "none", "long", "entity" or a valid codepoint');
|
|
|
611 |
}
|
|
|
612 |
|
|
|
613 |
public static function mb_substr($s, $start, $length = null, $encoding = null)
|
|
|
614 |
{
|
|
|
615 |
$encoding = self::getEncoding($encoding);
|
|
|
616 |
if ('CP850' === $encoding || 'ASCII' === $encoding) {
|
|
|
617 |
return (string) substr($s, $start, null === $length ? 2147483647 : $length);
|
|
|
618 |
}
|
|
|
619 |
|
|
|
620 |
if ($start < 0) {
|
|
|
621 |
$start = iconv_strlen($s, $encoding) + $start;
|
|
|
622 |
if ($start < 0) {
|
|
|
623 |
$start = 0;
|
|
|
624 |
}
|
|
|
625 |
}
|
|
|
626 |
|
|
|
627 |
if (null === $length) {
|
|
|
628 |
$length = 2147483647;
|
|
|
629 |
} elseif ($length < 0) {
|
|
|
630 |
$length = iconv_strlen($s, $encoding) + $length - $start;
|
|
|
631 |
if ($length < 0) {
|
|
|
632 |
return '';
|
|
|
633 |
}
|
|
|
634 |
}
|
|
|
635 |
|
|
|
636 |
return (string) iconv_substr($s, $start, $length, $encoding);
|
|
|
637 |
}
|
|
|
638 |
|
|
|
639 |
public static function mb_stripos($haystack, $needle, $offset = 0, $encoding = null)
|
|
|
640 |
{
|
|
|
641 |
$haystack = self::mb_convert_case($haystack, self::MB_CASE_FOLD, $encoding);
|
|
|
642 |
$needle = self::mb_convert_case($needle, self::MB_CASE_FOLD, $encoding);
|
|
|
643 |
|
|
|
644 |
return self::mb_strpos($haystack, $needle, $offset, $encoding);
|
|
|
645 |
}
|
|
|
646 |
|
|
|
647 |
public static function mb_stristr($haystack, $needle, $part = false, $encoding = null)
|
|
|
648 |
{
|
|
|
649 |
$pos = self::mb_stripos($haystack, $needle, 0, $encoding);
|
|
|
650 |
|
|
|
651 |
return self::getSubpart($pos, $part, $haystack, $encoding);
|
|
|
652 |
}
|
|
|
653 |
|
|
|
654 |
public static function mb_strrchr($haystack, $needle, $part = false, $encoding = null)
|
|
|
655 |
{
|
|
|
656 |
$encoding = self::getEncoding($encoding);
|
|
|
657 |
if ('CP850' === $encoding || 'ASCII' === $encoding) {
|
|
|
658 |
$pos = strrpos($haystack, $needle);
|
|
|
659 |
} else {
|
|
|
660 |
$needle = self::mb_substr($needle, 0, 1, $encoding);
|
|
|
661 |
$pos = iconv_strrpos($haystack, $needle, $encoding);
|
|
|
662 |
}
|
|
|
663 |
|
|
|
664 |
return self::getSubpart($pos, $part, $haystack, $encoding);
|
|
|
665 |
}
|
|
|
666 |
|
|
|
667 |
public static function mb_strrichr($haystack, $needle, $part = false, $encoding = null)
|
|
|
668 |
{
|
|
|
669 |
$needle = self::mb_substr($needle, 0, 1, $encoding);
|
|
|
670 |
$pos = self::mb_strripos($haystack, $needle, $encoding);
|
|
|
671 |
|
|
|
672 |
return self::getSubpart($pos, $part, $haystack, $encoding);
|
|
|
673 |
}
|
|
|
674 |
|
|
|
675 |
public static function mb_strripos($haystack, $needle, $offset = 0, $encoding = null)
|
|
|
676 |
{
|
|
|
677 |
$haystack = self::mb_convert_case($haystack, self::MB_CASE_FOLD, $encoding);
|
|
|
678 |
$needle = self::mb_convert_case($needle, self::MB_CASE_FOLD, $encoding);
|
|
|
679 |
|
|
|
680 |
return self::mb_strrpos($haystack, $needle, $offset, $encoding);
|
|
|
681 |
}
|
|
|
682 |
|
|
|
683 |
public static function mb_strstr($haystack, $needle, $part = false, $encoding = null)
|
|
|
684 |
{
|
|
|
685 |
$pos = strpos($haystack, $needle);
|
|
|
686 |
if (false === $pos) {
|
|
|
687 |
return false;
|
|
|
688 |
}
|
|
|
689 |
if ($part) {
|
|
|
690 |
return substr($haystack, 0, $pos);
|
|
|
691 |
}
|
|
|
692 |
|
|
|
693 |
return substr($haystack, $pos);
|
|
|
694 |
}
|
|
|
695 |
|
|
|
696 |
public static function mb_get_info($type = 'all')
|
|
|
697 |
{
|
|
|
698 |
$info = [
|
|
|
699 |
'internal_encoding' => self::$internalEncoding,
|
|
|
700 |
'http_output' => 'pass',
|
|
|
701 |
'http_output_conv_mimetypes' => '^(text/|application/xhtml\+xml)',
|
|
|
702 |
'func_overload' => 0,
|
|
|
703 |
'func_overload_list' => 'no overload',
|
|
|
704 |
'mail_charset' => 'UTF-8',
|
|
|
705 |
'mail_header_encoding' => 'BASE64',
|
|
|
706 |
'mail_body_encoding' => 'BASE64',
|
|
|
707 |
'illegal_chars' => 0,
|
|
|
708 |
'encoding_translation' => 'Off',
|
|
|
709 |
'language' => self::$language,
|
|
|
710 |
'detect_order' => self::$encodingList,
|
|
|
711 |
'substitute_character' => 'none',
|
|
|
712 |
'strict_detection' => 'Off',
|
|
|
713 |
];
|
|
|
714 |
|
|
|
715 |
if ('all' === $type) {
|
|
|
716 |
return $info;
|
|
|
717 |
}
|
|
|
718 |
if (isset($info[$type])) {
|
|
|
719 |
return $info[$type];
|
|
|
720 |
}
|
|
|
721 |
|
|
|
722 |
return false;
|
|
|
723 |
}
|
|
|
724 |
|
|
|
725 |
public static function mb_http_input($type = '')
|
|
|
726 |
{
|
|
|
727 |
return false;
|
|
|
728 |
}
|
|
|
729 |
|
|
|
730 |
public static function mb_http_output($encoding = null)
|
|
|
731 |
{
|
|
|
732 |
return null !== $encoding ? 'pass' === $encoding : 'pass';
|
|
|
733 |
}
|
|
|
734 |
|
|
|
735 |
public static function mb_strwidth($s, $encoding = null)
|
|
|
736 |
{
|
|
|
737 |
$encoding = self::getEncoding($encoding);
|
|
|
738 |
|
|
|
739 |
if ('UTF-8' !== $encoding) {
|
|
|
740 |
$s = iconv($encoding, 'UTF-8//IGNORE', $s);
|
|
|
741 |
}
|
|
|
742 |
|
|
|
743 |
$s = preg_replace('/[\x{1100}-\x{115F}\x{2329}\x{232A}\x{2E80}-\x{303E}\x{3040}-\x{A4CF}\x{AC00}-\x{D7A3}\x{F900}-\x{FAFF}\x{FE10}-\x{FE19}\x{FE30}-\x{FE6F}\x{FF00}-\x{FF60}\x{FFE0}-\x{FFE6}\x{20000}-\x{2FFFD}\x{30000}-\x{3FFFD}]/u', '', $s, -1, $wide);
|
|
|
744 |
|
|
|
745 |
return ($wide << 1) + iconv_strlen($s, 'UTF-8');
|
|
|
746 |
}
|
|
|
747 |
|
|
|
748 |
public static function mb_substr_count($haystack, $needle, $encoding = null)
|
|
|
749 |
{
|
|
|
750 |
return substr_count($haystack, $needle);
|
|
|
751 |
}
|
|
|
752 |
|
|
|
753 |
public static function mb_output_handler($contents, $status)
|
|
|
754 |
{
|
|
|
755 |
return $contents;
|
|
|
756 |
}
|
|
|
757 |
|
|
|
758 |
public static function mb_chr($code, $encoding = null)
|
|
|
759 |
{
|
|
|
760 |
if (0x80 > $code %= 0x200000) {
|
|
|
761 |
$s = \chr($code);
|
|
|
762 |
} elseif (0x800 > $code) {
|
|
|
763 |
$s = \chr(0xC0 | $code >> 6).\chr(0x80 | $code & 0x3F);
|
|
|
764 |
} elseif (0x10000 > $code) {
|
|
|
765 |
$s = \chr(0xE0 | $code >> 12).\chr(0x80 | $code >> 6 & 0x3F).\chr(0x80 | $code & 0x3F);
|
|
|
766 |
} else {
|
|
|
767 |
$s = \chr(0xF0 | $code >> 18).\chr(0x80 | $code >> 12 & 0x3F).\chr(0x80 | $code >> 6 & 0x3F).\chr(0x80 | $code & 0x3F);
|
|
|
768 |
}
|
|
|
769 |
|
|
|
770 |
if ('UTF-8' !== $encoding = self::getEncoding($encoding)) {
|
|
|
771 |
$s = mb_convert_encoding($s, $encoding, 'UTF-8');
|
|
|
772 |
}
|
|
|
773 |
|
|
|
774 |
return $s;
|
|
|
775 |
}
|
|
|
776 |
|
|
|
777 |
public static function mb_ord($s, $encoding = null)
|
|
|
778 |
{
|
|
|
779 |
if ('UTF-8' !== $encoding = self::getEncoding($encoding)) {
|
|
|
780 |
$s = mb_convert_encoding($s, 'UTF-8', $encoding);
|
|
|
781 |
}
|
|
|
782 |
|
|
|
783 |
if (1 === \strlen($s)) {
|
|
|
784 |
return \ord($s);
|
|
|
785 |
}
|
|
|
786 |
|
|
|
787 |
$code = ($s = unpack('C*', substr($s, 0, 4))) ? $s[1] : 0;
|
|
|
788 |
if (0xF0 <= $code) {
|
|
|
789 |
return (($code - 0xF0) << 18) + (($s[2] - 0x80) << 12) + (($s[3] - 0x80) << 6) + $s[4] - 0x80;
|
|
|
790 |
}
|
|
|
791 |
if (0xE0 <= $code) {
|
|
|
792 |
return (($code - 0xE0) << 12) + (($s[2] - 0x80) << 6) + $s[3] - 0x80;
|
|
|
793 |
}
|
|
|
794 |
if (0xC0 <= $code) {
|
|
|
795 |
return (($code - 0xC0) << 6) + $s[2] - 0x80;
|
|
|
796 |
}
|
|
|
797 |
|
|
|
798 |
return $code;
|
|
|
799 |
}
|
|
|
800 |
|
|
|
801 |
private static function getSubpart($pos, $part, $haystack, $encoding)
|
|
|
802 |
{
|
|
|
803 |
if (false === $pos) {
|
|
|
804 |
return false;
|
|
|
805 |
}
|
|
|
806 |
if ($part) {
|
|
|
807 |
return self::mb_substr($haystack, 0, $pos, $encoding);
|
|
|
808 |
}
|
|
|
809 |
|
|
|
810 |
return self::mb_substr($haystack, $pos, null, $encoding);
|
|
|
811 |
}
|
|
|
812 |
|
|
|
813 |
private static function html_encoding_callback(array $m)
|
|
|
814 |
{
|
|
|
815 |
$i = 1;
|
|
|
816 |
$entities = '';
|
|
|
817 |
$m = unpack('C*', htmlentities($m[0], \ENT_COMPAT, 'UTF-8'));
|
|
|
818 |
|
|
|
819 |
while (isset($m[$i])) {
|
|
|
820 |
if (0x80 > $m[$i]) {
|
|
|
821 |
$entities .= \chr($m[$i++]);
|
|
|
822 |
continue;
|
|
|
823 |
}
|
|
|
824 |
if (0xF0 <= $m[$i]) {
|
|
|
825 |
$c = (($m[$i++] - 0xF0) << 18) + (($m[$i++] - 0x80) << 12) + (($m[$i++] - 0x80) << 6) + $m[$i++] - 0x80;
|
|
|
826 |
} elseif (0xE0 <= $m[$i]) {
|
|
|
827 |
$c = (($m[$i++] - 0xE0) << 12) + (($m[$i++] - 0x80) << 6) + $m[$i++] - 0x80;
|
|
|
828 |
} else {
|
|
|
829 |
$c = (($m[$i++] - 0xC0) << 6) + $m[$i++] - 0x80;
|
|
|
830 |
}
|
|
|
831 |
|
|
|
832 |
$entities .= '&#'.$c.';';
|
|
|
833 |
}
|
|
|
834 |
|
|
|
835 |
return $entities;
|
|
|
836 |
}
|
|
|
837 |
|
|
|
838 |
private static function title_case(array $s)
|
|
|
839 |
{
|
|
|
840 |
return self::mb_convert_case($s[1], \MB_CASE_UPPER, 'UTF-8').self::mb_convert_case($s[2], \MB_CASE_LOWER, 'UTF-8');
|
|
|
841 |
}
|
|
|
842 |
|
|
|
843 |
private static function getData($file)
|
|
|
844 |
{
|
|
|
845 |
if (file_exists($file = __DIR__.'/Resources/unidata/'.$file.'.php')) {
|
|
|
846 |
return require $file;
|
|
|
847 |
}
|
|
|
848 |
|
|
|
849 |
return false;
|
|
|
850 |
}
|
|
|
851 |
|
|
|
852 |
private static function getEncoding($encoding)
|
|
|
853 |
{
|
|
|
854 |
if (null === $encoding) {
|
|
|
855 |
return self::$internalEncoding;
|
|
|
856 |
}
|
|
|
857 |
|
|
|
858 |
if ('UTF-8' === $encoding) {
|
|
|
859 |
return 'UTF-8';
|
|
|
860 |
}
|
|
|
861 |
|
|
|
862 |
$encoding = strtoupper($encoding);
|
|
|
863 |
|
|
|
864 |
if ('8BIT' === $encoding || 'BINARY' === $encoding) {
|
|
|
865 |
return 'CP850';
|
|
|
866 |
}
|
|
|
867 |
|
|
|
868 |
if ('UTF8' === $encoding) {
|
|
|
869 |
return 'UTF-8';
|
|
|
870 |
}
|
|
|
871 |
|
|
|
872 |
return $encoding;
|
|
|
873 |
}
|
|
|
874 |
}
|