1 | <?php |
||||
2 | /** |
||||
3 | * @link http://www.yiiframework.com/ |
||||
4 | * @copyright Copyright (c) 2008 Yii Software LLC |
||||
5 | * @license http://www.yiiframework.com/license/ |
||||
6 | */ |
||||
7 | |||||
8 | namespace yii\helpers; |
||||
9 | |||||
10 | use Yii; |
||||
11 | |||||
12 | /** |
||||
13 | * BaseStringHelper provides concrete implementation for [[StringHelper]]. |
||||
14 | * |
||||
15 | * Do not use BaseStringHelper. Use [[StringHelper]] instead. |
||||
16 | * |
||||
17 | * @author Qiang Xue <[email protected]> |
||||
18 | * @author Alex Makarov <[email protected]> |
||||
19 | * @since 2.0 |
||||
20 | */ |
||||
21 | class BaseStringHelper |
||||
22 | { |
||||
23 | /** |
||||
24 | * Returns the number of bytes in the given string. |
||||
25 | * This method ensures the string is treated as a byte array by using `mb_strlen()`. |
||||
26 | * @param string $string the string being measured for length |
||||
27 | * @return int the number of bytes in the given string. |
||||
28 | */ |
||||
29 | 437 | public static function byteLength($string) |
|||
30 | { |
||||
31 | 437 | return mb_strlen($string, '8bit'); |
|||
32 | } |
||||
33 | |||||
34 | /** |
||||
35 | * Returns the portion of string specified by the start and length parameters. |
||||
36 | * This method ensures the string is treated as a byte array by using `mb_substr()`. |
||||
37 | * @param string $string the input string. Must be one character or longer. |
||||
38 | * @param int $start the starting position |
||||
39 | * @param int $length the desired portion length. If not specified or `null`, there will be |
||||
40 | * no limit on length i.e. the output will be until the end of the string. |
||||
41 | * @return string the extracted part of string, or FALSE on failure or an empty string. |
||||
42 | * @see https://secure.php.net/manual/en/function.substr.php |
||||
43 | */ |
||||
44 | 113 | public static function byteSubstr($string, $start, $length = null) |
|||
45 | { |
||||
46 | 113 | return mb_substr($string, $start, $length === null ? mb_strlen($string, '8bit') : $length, '8bit'); |
|||
47 | } |
||||
48 | |||||
49 | /** |
||||
50 | * Returns the trailing name component of a path. |
||||
51 | * This method is similar to the php function `basename()` except that it will |
||||
52 | * treat both \ and / as directory separators, independent of the operating system. |
||||
53 | * This method was mainly created to work on php namespaces. When working with real |
||||
54 | * file paths, php's `basename()` should work fine for you. |
||||
55 | * Note: this method is not aware of the actual filesystem, or path components such as "..". |
||||
56 | * |
||||
57 | * @param string $path A path string. |
||||
58 | * @param string $suffix If the name component ends in suffix this will also be cut off. |
||||
59 | * @return string the trailing name component of the given path. |
||||
60 | * @see https://secure.php.net/manual/en/function.basename.php |
||||
61 | */ |
||||
62 | 27 | public static function basename($path, $suffix = '') |
|||
63 | { |
||||
64 | 27 | if (($len = mb_strlen($suffix)) > 0 && mb_substr($path, -$len) === $suffix) { |
|||
65 | 1 | $path = mb_substr($path, 0, -$len); |
|||
66 | } |
||||
67 | 27 | $path = rtrim(str_replace('\\', '/', $path), '/\\'); |
|||
68 | 27 | if (($pos = mb_strrpos($path, '/')) !== false) { |
|||
69 | 27 | return mb_substr($path, $pos + 1); |
|||
70 | } |
||||
71 | |||||
72 | 1 | return $path; |
|||
73 | } |
||||
74 | |||||
75 | /** |
||||
76 | * Returns parent directory's path. |
||||
77 | * This method is similar to `dirname()` except that it will treat |
||||
78 | * both \ and / as directory separators, independent of the operating system. |
||||
79 | * |
||||
80 | * @param string $path A path string. |
||||
81 | * @return string the parent directory's path. |
||||
82 | * @see https://secure.php.net/manual/en/function.basename.php |
||||
83 | */ |
||||
84 | 5 | public static function dirname($path) |
|||
85 | { |
||||
86 | 5 | $pos = mb_strrpos(str_replace('\\', '/', $path), '/'); |
|||
87 | 5 | if ($pos !== false) { |
|||
88 | 5 | return mb_substr($path, 0, $pos); |
|||
89 | } |
||||
90 | |||||
91 | return ''; |
||||
92 | } |
||||
93 | |||||
94 | /** |
||||
95 | * Truncates a string to the number of characters specified. |
||||
96 | * |
||||
97 | * @param string $string The string to truncate. |
||||
98 | * @param int $length How many characters from original string to include into truncated string. |
||||
99 | * @param string $suffix String to append to the end of truncated string. |
||||
100 | * @param string $encoding The charset to use, defaults to charset currently used by application. |
||||
101 | * @param bool $asHtml Whether to treat the string being truncated as HTML and preserve proper HTML tags. |
||||
102 | * This parameter is available since version 2.0.1. |
||||
103 | * @return string the truncated string. |
||||
104 | */ |
||||
105 | 1 | public static function truncate($string, $length, $suffix = '...', $encoding = null, $asHtml = false) |
|||
106 | { |
||||
107 | 1 | if ($encoding === null) { |
|||
108 | 1 | $encoding = Yii::$app ? Yii::$app->charset : 'UTF-8'; |
|||
109 | } |
||||
110 | 1 | if ($asHtml) { |
|||
111 | 1 | return static::truncateHtml($string, $length, $suffix, $encoding); |
|||
112 | } |
||||
113 | |||||
114 | 1 | if (mb_strlen($string, $encoding) > $length) { |
|||
115 | 1 | return rtrim(mb_substr($string, 0, $length, $encoding)) . $suffix; |
|||
116 | } |
||||
117 | |||||
118 | 1 | return $string; |
|||
119 | } |
||||
120 | |||||
121 | /** |
||||
122 | * Truncates a string to the number of words specified. |
||||
123 | * |
||||
124 | * @param string $string The string to truncate. |
||||
125 | * @param int $count How many words from original string to include into truncated string. |
||||
126 | * @param string $suffix String to append to the end of truncated string. |
||||
127 | * @param bool $asHtml Whether to treat the string being truncated as HTML and preserve proper HTML tags. |
||||
128 | * This parameter is available since version 2.0.1. |
||||
129 | * @return string the truncated string. |
||||
130 | */ |
||||
131 | 1 | public static function truncateWords($string, $count, $suffix = '...', $asHtml = false) |
|||
132 | { |
||||
133 | 1 | if ($asHtml) { |
|||
134 | 1 | return static::truncateHtml($string, $count, $suffix); |
|||
135 | } |
||||
136 | |||||
137 | 1 | $words = preg_split('/(\s+)/u', trim($string), null, PREG_SPLIT_DELIM_CAPTURE); |
|||
138 | 1 | if (count($words) / 2 > $count) { |
|||
139 | 1 | return implode('', array_slice($words, 0, ($count * 2) - 1)) . $suffix; |
|||
140 | } |
||||
141 | |||||
142 | 1 | return $string; |
|||
143 | } |
||||
144 | |||||
145 | /** |
||||
146 | * Truncate a string while preserving the HTML. |
||||
147 | * |
||||
148 | * @param string $string The string to truncate |
||||
149 | * @param int $count |
||||
150 | * @param string $suffix String to append to the end of the truncated string. |
||||
151 | * @param string|bool $encoding |
||||
152 | * @return string |
||||
153 | * @since 2.0.1 |
||||
154 | */ |
||||
155 | 2 | protected static function truncateHtml($string, $count, $suffix, $encoding = false) |
|||
156 | { |
||||
157 | 2 | $config = \HTMLPurifier_Config::create(null); |
|||
158 | 2 | if (Yii::$app !== null) { |
|||
159 | $config->set('Cache.SerializerPath', Yii::$app->getRuntimePath()); |
||||
160 | } |
||||
161 | 2 | $lexer = \HTMLPurifier_Lexer::create($config); |
|||
162 | 2 | $tokens = $lexer->tokenizeHTML($string, $config, new \HTMLPurifier_Context()); |
|||
163 | 2 | $openTokens = []; |
|||
164 | 2 | $totalCount = 0; |
|||
165 | 2 | $depth = 0; |
|||
166 | 2 | $truncated = []; |
|||
167 | 2 | foreach ($tokens as $token) { |
|||
168 | 2 | if ($token instanceof \HTMLPurifier_Token_Start) { //Tag begins |
|||
169 | 2 | $openTokens[$depth] = $token->name; |
|||
170 | 2 | $truncated[] = $token; |
|||
171 | 2 | ++$depth; |
|||
172 | 2 | } elseif ($token instanceof \HTMLPurifier_Token_Text && $totalCount <= $count) { //Text |
|||
173 | 2 | if (false === $encoding) { |
|||
174 | 1 | preg_match('/^(\s*)/um', $token->data, $prefixSpace) ?: $prefixSpace = ['', '']; |
|||
175 | 1 | $token->data = $prefixSpace[1] . self::truncateWords(ltrim($token->data), $count - $totalCount, ''); |
|||
176 | 1 | $currentCount = self::countWords($token->data); |
|||
177 | } else { |
||||
178 | 1 | $token->data = self::truncate($token->data, $count - $totalCount, '', $encoding); |
|||
0 ignored issues
–
show
Bug
introduced
by
Loading history...
|
|||||
179 | 1 | $currentCount = mb_strlen($token->data, $encoding); |
|||
0 ignored issues
–
show
It seems like
$encoding can also be of type true ; however, parameter $encoding of mb_strlen() does only seem to accept null|string , maybe add an additional type check?
(
Ignorable by Annotation
)
If this is a false-positive, you can also ignore this issue in your code via the
Loading history...
|
|||||
180 | } |
||||
181 | 2 | $totalCount += $currentCount; |
|||
182 | 2 | $truncated[] = $token; |
|||
183 | 2 | } elseif ($token instanceof \HTMLPurifier_Token_End) { //Tag ends |
|||
184 | 2 | if ($token->name === $openTokens[$depth - 1]) { |
|||
185 | 2 | --$depth; |
|||
186 | 2 | unset($openTokens[$depth]); |
|||
187 | 2 | $truncated[] = $token; |
|||
188 | } |
||||
189 | 2 | } elseif ($token instanceof \HTMLPurifier_Token_Empty) { //Self contained tags, i.e. <img/> etc. |
|||
190 | 2 | $truncated[] = $token; |
|||
191 | } |
||||
192 | 2 | if ($totalCount >= $count) { |
|||
193 | 2 | if (0 < count($openTokens)) { |
|||
194 | 2 | krsort($openTokens); |
|||
195 | 2 | foreach ($openTokens as $name) { |
|||
196 | 2 | $truncated[] = new \HTMLPurifier_Token_End($name); |
|||
197 | } |
||||
198 | } |
||||
199 | 2 | break; |
|||
200 | } |
||||
201 | } |
||||
202 | 2 | $context = new \HTMLPurifier_Context(); |
|||
203 | 2 | $generator = new \HTMLPurifier_Generator($config, $context); |
|||
204 | 2 | return $generator->generateFromTokens($truncated) . ($totalCount >= $count ? $suffix : ''); |
|||
205 | } |
||||
206 | |||||
207 | /** |
||||
208 | * Check if given string starts with specified substring. |
||||
209 | * Binary and multibyte safe. |
||||
210 | * |
||||
211 | * @param string $string Input string |
||||
212 | * @param string $with Part to search inside the $string |
||||
213 | * @param bool $caseSensitive Case sensitive search. Default is true. When case sensitive is enabled, $with must exactly match the starting of the string in order to get a true value. |
||||
214 | * @return bool Returns true if first input starts with second input, false otherwise |
||||
215 | */ |
||||
216 | 20 | public static function startsWith($string, $with, $caseSensitive = true) |
|||
217 | { |
||||
218 | 20 | if (!$bytes = static::byteLength($with)) { |
|||
219 | 3 | return true; |
|||
220 | } |
||||
221 | 17 | if ($caseSensitive) { |
|||
222 | 16 | return strncmp($string, $with, $bytes) === 0; |
|||
223 | |||||
224 | } |
||||
225 | 15 | $encoding = Yii::$app ? Yii::$app->charset : 'UTF-8'; |
|||
226 | 15 | return mb_strtolower(mb_substr($string, 0, $bytes, '8bit'), $encoding) === mb_strtolower($with, $encoding); |
|||
227 | } |
||||
228 | |||||
229 | /** |
||||
230 | * Check if given string ends with specified substring. |
||||
231 | * Binary and multibyte safe. |
||||
232 | * |
||||
233 | * @param string $string Input string to check |
||||
234 | * @param string $with Part to search inside of the $string. |
||||
235 | * @param bool $caseSensitive Case sensitive search. Default is true. When case sensitive is enabled, $with must exactly match the ending of the string in order to get a true value. |
||||
236 | * @return bool Returns true if first input ends with second input, false otherwise |
||||
237 | */ |
||||
238 | 30 | public static function endsWith($string, $with, $caseSensitive = true) |
|||
239 | { |
||||
240 | 30 | if (!$bytes = static::byteLength($with)) { |
|||
241 | 3 | return true; |
|||
242 | } |
||||
243 | 27 | if ($caseSensitive) { |
|||
244 | // Warning check, see https://secure.php.net/manual/en/function.substr-compare.php#refsect1-function.substr-compare-returnvalues |
||||
245 | 16 | if (static::byteLength($string) < $bytes) { |
|||
246 | 3 | return false; |
|||
247 | } |
||||
248 | |||||
249 | 13 | return substr_compare($string, $with, -$bytes, $bytes) === 0; |
|||
250 | } |
||||
251 | |||||
252 | 25 | $encoding = Yii::$app ? Yii::$app->charset : 'UTF-8'; |
|||
253 | 25 | return mb_strtolower(mb_substr($string, -$bytes, mb_strlen($string, '8bit'), '8bit'), $encoding) === mb_strtolower($with, $encoding); |
|||
254 | } |
||||
255 | |||||
256 | /** |
||||
257 | * Explodes string into array, optionally trims values and skips empty ones. |
||||
258 | * |
||||
259 | * @param string $string String to be exploded. |
||||
260 | * @param string $delimiter Delimiter. Default is ','. |
||||
261 | * @param mixed $trim Whether to trim each element. Can be: |
||||
262 | * - boolean - to trim normally; |
||||
263 | * - string - custom characters to trim. Will be passed as a second argument to `trim()` function. |
||||
264 | * - callable - will be called for each value instead of trim. Takes the only argument - value. |
||||
265 | * @param bool $skipEmpty Whether to skip empty strings between delimiters. Default is false. |
||||
266 | * @return array |
||||
267 | * @since 2.0.4 |
||||
268 | */ |
||||
269 | 1 | public static function explode($string, $delimiter = ',', $trim = true, $skipEmpty = false) |
|||
270 | { |
||||
271 | 1 | $result = explode($delimiter, $string); |
|||
272 | 1 | if ($trim !== false) { |
|||
273 | 1 | if ($trim === true) { |
|||
274 | 1 | $trim = 'trim'; |
|||
275 | 1 | } elseif (!is_callable($trim)) { |
|||
276 | $trim = function ($v) use ($trim) { |
||||
277 | 1 | return trim($v, $trim); |
|||
278 | 1 | }; |
|||
279 | } |
||||
280 | 1 | $result = array_map($trim, $result); |
|||
281 | } |
||||
282 | 1 | if ($skipEmpty) { |
|||
283 | // Wrapped with array_values to make array keys sequential after empty values removing |
||||
284 | $result = array_values(array_filter($result, function ($value) { |
||||
285 | 1 | return $value !== ''; |
|||
286 | 1 | })); |
|||
287 | } |
||||
288 | |||||
289 | 1 | return $result; |
|||
290 | } |
||||
291 | |||||
292 | /** |
||||
293 | * Counts words in a string. |
||||
294 | * @since 2.0.8 |
||||
295 | * |
||||
296 | * @param string $string |
||||
297 | * @return int |
||||
298 | */ |
||||
299 | 2 | public static function countWords($string) |
|||
300 | { |
||||
301 | 2 | return count(preg_split('/\s+/u', $string, null, PREG_SPLIT_NO_EMPTY)); |
|||
302 | } |
||||
303 | |||||
304 | /** |
||||
305 | * Returns string representation of number value with replaced commas to dots, if decimal point |
||||
306 | * of current locale is comma. |
||||
307 | * @param int|float|string $value |
||||
308 | * @return string |
||||
309 | * @since 2.0.11 |
||||
310 | */ |
||||
311 | 32 | public static function normalizeNumber($value) |
|||
312 | { |
||||
313 | 32 | $value = (string)$value; |
|||
314 | |||||
315 | 32 | $localeInfo = localeconv(); |
|||
316 | 32 | $decimalSeparator = isset($localeInfo['decimal_point']) ? $localeInfo['decimal_point'] : null; |
|||
317 | |||||
318 | 32 | if ($decimalSeparator !== null && $decimalSeparator !== '.') { |
|||
319 | 4 | $value = str_replace($decimalSeparator, '.', $value); |
|||
320 | } |
||||
321 | |||||
322 | 32 | return $value; |
|||
323 | } |
||||
324 | |||||
325 | /** |
||||
326 | * Encodes string into "Base 64 Encoding with URL and Filename Safe Alphabet" (RFC 4648). |
||||
327 | * |
||||
328 | * > Note: Base 64 padding `=` may be at the end of the returned string. |
||||
329 | * > `=` is not transparent to URL encoding. |
||||
330 | * |
||||
331 | * @see https://tools.ietf.org/html/rfc4648#page-7 |
||||
332 | * @param string $input the string to encode. |
||||
333 | * @return string encoded string. |
||||
334 | * @since 2.0.12 |
||||
335 | */ |
||||
336 | 104 | public static function base64UrlEncode($input) |
|||
337 | { |
||||
338 | 104 | return strtr(base64_encode($input), '+/', '-_'); |
|||
339 | } |
||||
340 | |||||
341 | /** |
||||
342 | * Decodes "Base 64 Encoding with URL and Filename Safe Alphabet" (RFC 4648). |
||||
343 | * |
||||
344 | * @see https://tools.ietf.org/html/rfc4648#page-7 |
||||
345 | * @param string $input encoded string. |
||||
346 | * @return string decoded string. |
||||
347 | * @since 2.0.12 |
||||
348 | */ |
||||
349 | 13 | public static function base64UrlDecode($input) |
|||
350 | { |
||||
351 | 13 | return base64_decode(strtr($input, '-_', '+/')); |
|||
352 | } |
||||
353 | |||||
354 | /** |
||||
355 | * Safely casts a float to string independent of the current locale. |
||||
356 | * |
||||
357 | * The decimal separator will always be `.`. |
||||
358 | * @param float|int $number a floating point number or integer. |
||||
359 | * @return string the string representation of the number. |
||||
360 | * @since 2.0.13 |
||||
361 | */ |
||||
362 | 18 | public static function floatToString($number) |
|||
363 | { |
||||
364 | // . and , are the only decimal separators known in ICU data, |
||||
365 | // so its safe to call str_replace here |
||||
366 | 18 | return str_replace(',', '.', (string) $number); |
|||
367 | } |
||||
368 | |||||
369 | /** |
||||
370 | * Checks if the passed string would match the given shell wildcard pattern. |
||||
371 | * This function emulates [[fnmatch()]], which may be unavailable at certain environment, using PCRE. |
||||
372 | * @param string $pattern the shell wildcard pattern. |
||||
373 | * @param string $string the tested string. |
||||
374 | * @param array $options options for matching. Valid options are: |
||||
375 | * |
||||
376 | * - caseSensitive: bool, whether pattern should be case sensitive. Defaults to `true`. |
||||
377 | * - escape: bool, whether backslash escaping is enabled. Defaults to `true`. |
||||
378 | * - filePath: bool, whether slashes in string only matches slashes in the given pattern. Defaults to `false`. |
||||
379 | * |
||||
380 | * @return bool whether the string matches pattern or not. |
||||
381 | * @since 2.0.14 |
||||
382 | */ |
||||
383 | 238 | public static function matchWildcard($pattern, $string, $options = []) |
|||
384 | { |
||||
385 | 238 | if ($pattern === '*' && empty($options['filePath'])) { |
|||
386 | 5 | return true; |
|||
387 | } |
||||
388 | |||||
389 | $replacements = [ |
||||
390 | 234 | '\\\\\\\\' => '\\\\', |
|||
391 | '\\\\\\*' => '[*]', |
||||
392 | '\\\\\\?' => '[?]', |
||||
393 | '\*' => '.*', |
||||
394 | '\?' => '.', |
||||
395 | '\[\!' => '[^', |
||||
396 | '\[' => '[', |
||||
397 | '\]' => ']', |
||||
398 | '\-' => '-', |
||||
399 | ]; |
||||
400 | |||||
401 | 234 | if (isset($options['escape']) && !$options['escape']) { |
|||
402 | 9 | unset($replacements['\\\\\\\\']); |
|||
403 | 9 | unset($replacements['\\\\\\*']); |
|||
404 | 9 | unset($replacements['\\\\\\?']); |
|||
405 | } |
||||
406 | |||||
407 | 234 | if (!empty($options['filePath'])) { |
|||
408 | 12 | $replacements['\*'] = '[^/\\\\]*'; |
|||
409 | 12 | $replacements['\?'] = '[^/\\\\]'; |
|||
410 | } |
||||
411 | |||||
412 | 234 | $pattern = strtr(preg_quote($pattern, '#'), $replacements); |
|||
413 | 234 | $pattern = '#^' . $pattern . '$#us'; |
|||
414 | |||||
415 | 234 | if (isset($options['caseSensitive']) && !$options['caseSensitive']) { |
|||
416 | 2 | $pattern .= 'i'; |
|||
417 | } |
||||
418 | |||||
419 | 234 | return preg_match($pattern, $string) === 1; |
|||
420 | } |
||||
421 | |||||
422 | /** |
||||
423 | * This method provides a unicode-safe implementation of built-in PHP function `ucfirst()`. |
||||
424 | * |
||||
425 | * @param string $string the string to be proceeded |
||||
426 | * @param string $encoding Optional, defaults to "UTF-8" |
||||
427 | * @return string |
||||
428 | * @see https://secure.php.net/manual/en/function.ucfirst.php |
||||
429 | * @since 2.0.16 |
||||
430 | */ |
||||
431 | 239 | public static function mb_ucfirst($string, $encoding = 'UTF-8') |
|||
432 | { |
||||
433 | 239 | $firstChar = mb_substr($string, 0, 1, $encoding); |
|||
434 | 239 | $rest = mb_substr($string, 1, null, $encoding); |
|||
435 | |||||
436 | 239 | return mb_strtoupper($firstChar, $encoding) . $rest; |
|||
437 | } |
||||
438 | |||||
439 | /** |
||||
440 | * This method provides a unicode-safe implementation of built-in PHP function `ucwords()`. |
||||
441 | * |
||||
442 | * @param string $string the string to be proceeded |
||||
443 | * @param string $encoding Optional, defaults to "UTF-8" |
||||
444 | * @return string |
||||
445 | * @see https://secure.php.net/manual/en/function.ucwords.php |
||||
446 | * @since 2.0.16 |
||||
447 | */ |
||||
448 | 235 | public static function mb_ucwords($string, $encoding = 'UTF-8') |
|||
449 | { |
||||
450 | 235 | $words = preg_split("/\s/u", $string, -1, PREG_SPLIT_NO_EMPTY); |
|||
451 | |||||
452 | 235 | $titelized = array_map(function ($word) use ($encoding) { |
|||
453 | 233 | return static::mb_ucfirst($word, $encoding); |
|||
454 | 235 | }, $words); |
|||
455 | |||||
456 | 235 | return implode(' ', $titelized); |
|||
457 | } |
||||
458 | } |
||||
459 |