| 13532 |
anikendra |
1 |
<?php
|
|
|
2 |
/**
|
|
|
3 |
* String handling methods.
|
|
|
4 |
*
|
|
|
5 |
* CakePHP(tm) : Rapid Development Framework (http://cakephp.org)
|
|
|
6 |
* Copyright (c) Cake Software Foundation, Inc. (http://cakefoundation.org)
|
|
|
7 |
*
|
|
|
8 |
* Licensed under The MIT License
|
|
|
9 |
* For full copyright and license information, please see the LICENSE.txt
|
|
|
10 |
* Redistributions of files must retain the above copyright notice.
|
|
|
11 |
*
|
|
|
12 |
* @copyright Copyright (c) Cake Software Foundation, Inc. (http://cakefoundation.org)
|
|
|
13 |
* @link http://cakephp.org CakePHP(tm) Project
|
|
|
14 |
* @package Cake.Utility
|
|
|
15 |
* @since CakePHP(tm) v 1.2.0.5551
|
|
|
16 |
* @license http://www.opensource.org/licenses/mit-license.php MIT License
|
|
|
17 |
*/
|
|
|
18 |
|
|
|
19 |
/**
|
|
|
20 |
* String handling methods.
|
|
|
21 |
*
|
|
|
22 |
*
|
|
|
23 |
* @package Cake.Utility
|
|
|
24 |
*/
|
|
|
25 |
class String {
|
|
|
26 |
|
|
|
27 |
/**
|
|
|
28 |
* Generate a random UUID
|
|
|
29 |
*
|
|
|
30 |
* @see http://www.ietf.org/rfc/rfc4122.txt
|
|
|
31 |
* @return RFC 4122 UUID
|
|
|
32 |
*/
|
|
|
33 |
public static function uuid() {
|
|
|
34 |
$node = env('SERVER_ADDR');
|
|
|
35 |
|
|
|
36 |
if (strpos($node, ':') !== false) {
|
|
|
37 |
if (substr_count($node, '::')) {
|
|
|
38 |
$node = str_replace(
|
|
|
39 |
'::', str_repeat(':0000', 8 - substr_count($node, ':')) . ':', $node
|
|
|
40 |
);
|
|
|
41 |
}
|
|
|
42 |
$node = explode(':', $node);
|
|
|
43 |
$ipSix = '';
|
|
|
44 |
|
|
|
45 |
foreach ($node as $id) {
|
|
|
46 |
$ipSix .= str_pad(base_convert($id, 16, 2), 16, 0, STR_PAD_LEFT);
|
|
|
47 |
}
|
|
|
48 |
$node = base_convert($ipSix, 2, 10);
|
|
|
49 |
|
|
|
50 |
if (strlen($node) < 38) {
|
|
|
51 |
$node = null;
|
|
|
52 |
} else {
|
|
|
53 |
$node = crc32($node);
|
|
|
54 |
}
|
|
|
55 |
} elseif (empty($node)) {
|
|
|
56 |
$host = env('HOSTNAME');
|
|
|
57 |
|
|
|
58 |
if (empty($host)) {
|
|
|
59 |
$host = env('HOST');
|
|
|
60 |
}
|
|
|
61 |
|
|
|
62 |
if (!empty($host)) {
|
|
|
63 |
$ip = gethostbyname($host);
|
|
|
64 |
|
|
|
65 |
if ($ip === $host) {
|
|
|
66 |
$node = crc32($host);
|
|
|
67 |
} else {
|
|
|
68 |
$node = ip2long($ip);
|
|
|
69 |
}
|
|
|
70 |
}
|
|
|
71 |
} elseif ($node !== '127.0.0.1') {
|
|
|
72 |
$node = ip2long($node);
|
|
|
73 |
} else {
|
|
|
74 |
$node = null;
|
|
|
75 |
}
|
|
|
76 |
|
|
|
77 |
if (empty($node)) {
|
|
|
78 |
$node = crc32(Configure::read('Security.salt'));
|
|
|
79 |
}
|
|
|
80 |
|
|
|
81 |
if (function_exists('hphp_get_thread_id')) {
|
|
|
82 |
$pid = hphp_get_thread_id();
|
|
|
83 |
} elseif (function_exists('zend_thread_id')) {
|
|
|
84 |
$pid = zend_thread_id();
|
|
|
85 |
} else {
|
|
|
86 |
$pid = getmypid();
|
|
|
87 |
}
|
|
|
88 |
|
|
|
89 |
if (!$pid || $pid > 65535) {
|
|
|
90 |
$pid = mt_rand(0, 0xfff) | 0x4000;
|
|
|
91 |
}
|
|
|
92 |
|
|
|
93 |
list($timeMid, $timeLow) = explode(' ', microtime());
|
|
|
94 |
return sprintf(
|
|
|
95 |
"%08x-%04x-%04x-%02x%02x-%04x%08x", (int)$timeLow, (int)substr($timeMid, 2) & 0xffff,
|
|
|
96 |
mt_rand(0, 0xfff) | 0x4000, mt_rand(0, 0x3f) | 0x80, mt_rand(0, 0xff), $pid, $node
|
|
|
97 |
);
|
|
|
98 |
}
|
|
|
99 |
|
|
|
100 |
/**
|
|
|
101 |
* Tokenizes a string using $separator, ignoring any instance of $separator that appears between
|
|
|
102 |
* $leftBound and $rightBound
|
|
|
103 |
*
|
|
|
104 |
* @param string $data The data to tokenize
|
|
|
105 |
* @param string $separator The token to split the data on.
|
|
|
106 |
* @param string $leftBound The left boundary to ignore separators in.
|
|
|
107 |
* @param string $rightBound The right boundary to ignore separators in.
|
|
|
108 |
* @return array Array of tokens in $data.
|
|
|
109 |
*/
|
|
|
110 |
public static function tokenize($data, $separator = ',', $leftBound = '(', $rightBound = ')') {
|
|
|
111 |
if (empty($data) || is_array($data)) {
|
|
|
112 |
return $data;
|
|
|
113 |
}
|
|
|
114 |
|
|
|
115 |
$depth = 0;
|
|
|
116 |
$offset = 0;
|
|
|
117 |
$buffer = '';
|
|
|
118 |
$results = array();
|
|
|
119 |
$length = strlen($data);
|
|
|
120 |
$open = false;
|
|
|
121 |
|
|
|
122 |
while ($offset <= $length) {
|
|
|
123 |
$tmpOffset = -1;
|
|
|
124 |
$offsets = array(
|
|
|
125 |
strpos($data, $separator, $offset),
|
|
|
126 |
strpos($data, $leftBound, $offset),
|
|
|
127 |
strpos($data, $rightBound, $offset)
|
|
|
128 |
);
|
|
|
129 |
for ($i = 0; $i < 3; $i++) {
|
|
|
130 |
if ($offsets[$i] !== false && ($offsets[$i] < $tmpOffset || $tmpOffset == -1)) {
|
|
|
131 |
$tmpOffset = $offsets[$i];
|
|
|
132 |
}
|
|
|
133 |
}
|
|
|
134 |
if ($tmpOffset !== -1) {
|
|
|
135 |
$buffer .= substr($data, $offset, ($tmpOffset - $offset));
|
|
|
136 |
if (!$depth && $data{$tmpOffset} == $separator) {
|
|
|
137 |
$results[] = $buffer;
|
|
|
138 |
$buffer = '';
|
|
|
139 |
} else {
|
|
|
140 |
$buffer .= $data{$tmpOffset};
|
|
|
141 |
}
|
|
|
142 |
if ($leftBound != $rightBound) {
|
|
|
143 |
if ($data{$tmpOffset} == $leftBound) {
|
|
|
144 |
$depth++;
|
|
|
145 |
}
|
|
|
146 |
if ($data{$tmpOffset} == $rightBound) {
|
|
|
147 |
$depth--;
|
|
|
148 |
}
|
|
|
149 |
} else {
|
|
|
150 |
if ($data{$tmpOffset} == $leftBound) {
|
|
|
151 |
if (!$open) {
|
|
|
152 |
$depth++;
|
|
|
153 |
$open = true;
|
|
|
154 |
} else {
|
|
|
155 |
$depth--;
|
|
|
156 |
}
|
|
|
157 |
}
|
|
|
158 |
}
|
|
|
159 |
$offset = ++$tmpOffset;
|
|
|
160 |
} else {
|
|
|
161 |
$results[] = $buffer . substr($data, $offset);
|
|
|
162 |
$offset = $length + 1;
|
|
|
163 |
}
|
|
|
164 |
}
|
|
|
165 |
if (empty($results) && !empty($buffer)) {
|
|
|
166 |
$results[] = $buffer;
|
|
|
167 |
}
|
|
|
168 |
|
|
|
169 |
if (!empty($results)) {
|
|
|
170 |
return array_map('trim', $results);
|
|
|
171 |
}
|
|
|
172 |
|
|
|
173 |
return array();
|
|
|
174 |
}
|
|
|
175 |
|
|
|
176 |
/**
|
|
|
177 |
* Replaces variable placeholders inside a $str with any given $data. Each key in the $data array
|
|
|
178 |
* corresponds to a variable placeholder name in $str.
|
|
|
179 |
* Example: `String::insert(':name is :age years old.', array('name' => 'Bob', '65'));`
|
|
|
180 |
* Returns: Bob is 65 years old.
|
|
|
181 |
*
|
|
|
182 |
* Available $options are:
|
|
|
183 |
*
|
|
|
184 |
* - before: The character or string in front of the name of the variable placeholder (Defaults to `:`)
|
|
|
185 |
* - after: The character or string after the name of the variable placeholder (Defaults to null)
|
|
|
186 |
* - escape: The character or string used to escape the before character / string (Defaults to `\`)
|
|
|
187 |
* - format: A regex to use for matching variable placeholders. Default is: `/(?<!\\)\:%s/`
|
|
|
188 |
* (Overwrites before, after, breaks escape / clean)
|
|
|
189 |
* - clean: A boolean or array with instructions for String::cleanInsert
|
|
|
190 |
*
|
|
|
191 |
* @param string $str A string containing variable placeholders
|
|
|
192 |
* @param array $data A key => val array where each key stands for a placeholder variable name
|
|
|
193 |
* to be replaced with val
|
|
|
194 |
* @param array $options An array of options, see description above
|
|
|
195 |
* @return string
|
|
|
196 |
*/
|
|
|
197 |
public static function insert($str, $data, $options = array()) {
|
|
|
198 |
$defaults = array(
|
|
|
199 |
'before' => ':', 'after' => null, 'escape' => '\\', 'format' => null, 'clean' => false
|
|
|
200 |
);
|
|
|
201 |
$options += $defaults;
|
|
|
202 |
$format = $options['format'];
|
|
|
203 |
$data = (array)$data;
|
|
|
204 |
if (empty($data)) {
|
|
|
205 |
return ($options['clean']) ? String::cleanInsert($str, $options) : $str;
|
|
|
206 |
}
|
|
|
207 |
|
|
|
208 |
if (!isset($format)) {
|
|
|
209 |
$format = sprintf(
|
|
|
210 |
'/(?<!%s)%s%%s%s/',
|
|
|
211 |
preg_quote($options['escape'], '/'),
|
|
|
212 |
str_replace('%', '%%', preg_quote($options['before'], '/')),
|
|
|
213 |
str_replace('%', '%%', preg_quote($options['after'], '/'))
|
|
|
214 |
);
|
|
|
215 |
}
|
|
|
216 |
|
|
|
217 |
if (strpos($str, '?') !== false && is_numeric(key($data))) {
|
|
|
218 |
$offset = 0;
|
|
|
219 |
while (($pos = strpos($str, '?', $offset)) !== false) {
|
|
|
220 |
$val = array_shift($data);
|
|
|
221 |
$offset = $pos + strlen($val);
|
|
|
222 |
$str = substr_replace($str, $val, $pos, 1);
|
|
|
223 |
}
|
|
|
224 |
return ($options['clean']) ? String::cleanInsert($str, $options) : $str;
|
|
|
225 |
}
|
|
|
226 |
|
|
|
227 |
asort($data);
|
|
|
228 |
|
|
|
229 |
$dataKeys = array_keys($data);
|
|
|
230 |
$hashKeys = array_map('crc32', $dataKeys);
|
|
|
231 |
$tempData = array_combine($dataKeys, $hashKeys);
|
|
|
232 |
krsort($tempData);
|
|
|
233 |
|
|
|
234 |
foreach ($tempData as $key => $hashVal) {
|
|
|
235 |
$key = sprintf($format, preg_quote($key, '/'));
|
|
|
236 |
$str = preg_replace($key, $hashVal, $str);
|
|
|
237 |
}
|
|
|
238 |
$dataReplacements = array_combine($hashKeys, array_values($data));
|
|
|
239 |
foreach ($dataReplacements as $tmpHash => $tmpValue) {
|
|
|
240 |
$tmpValue = (is_array($tmpValue)) ? '' : $tmpValue;
|
|
|
241 |
$str = str_replace($tmpHash, $tmpValue, $str);
|
|
|
242 |
}
|
|
|
243 |
|
|
|
244 |
if (!isset($options['format']) && isset($options['before'])) {
|
|
|
245 |
$str = str_replace($options['escape'] . $options['before'], $options['before'], $str);
|
|
|
246 |
}
|
|
|
247 |
return ($options['clean']) ? String::cleanInsert($str, $options) : $str;
|
|
|
248 |
}
|
|
|
249 |
|
|
|
250 |
/**
|
|
|
251 |
* Cleans up a String::insert() formatted string with given $options depending on the 'clean' key in
|
|
|
252 |
* $options. The default method used is text but html is also available. The goal of this function
|
|
|
253 |
* is to replace all whitespace and unneeded markup around placeholders that did not get replaced
|
|
|
254 |
* by String::insert().
|
|
|
255 |
*
|
|
|
256 |
* @param string $str
|
|
|
257 |
* @param array $options
|
|
|
258 |
* @return string
|
|
|
259 |
* @see String::insert()
|
|
|
260 |
*/
|
|
|
261 |
public static function cleanInsert($str, $options) {
|
|
|
262 |
$clean = $options['clean'];
|
|
|
263 |
if (!$clean) {
|
|
|
264 |
return $str;
|
|
|
265 |
}
|
|
|
266 |
if ($clean === true) {
|
|
|
267 |
$clean = array('method' => 'text');
|
|
|
268 |
}
|
|
|
269 |
if (!is_array($clean)) {
|
|
|
270 |
$clean = array('method' => $options['clean']);
|
|
|
271 |
}
|
|
|
272 |
switch ($clean['method']) {
|
|
|
273 |
case 'html':
|
|
|
274 |
$clean = array_merge(array(
|
|
|
275 |
'word' => '[\w,.]+',
|
|
|
276 |
'andText' => true,
|
|
|
277 |
'replacement' => '',
|
|
|
278 |
), $clean);
|
|
|
279 |
$kleenex = sprintf(
|
|
|
280 |
'/[\s]*[a-z]+=(")(%s%s%s[\s]*)+\\1/i',
|
|
|
281 |
preg_quote($options['before'], '/'),
|
|
|
282 |
$clean['word'],
|
|
|
283 |
preg_quote($options['after'], '/')
|
|
|
284 |
);
|
|
|
285 |
$str = preg_replace($kleenex, $clean['replacement'], $str);
|
|
|
286 |
if ($clean['andText']) {
|
|
|
287 |
$options['clean'] = array('method' => 'text');
|
|
|
288 |
$str = String::cleanInsert($str, $options);
|
|
|
289 |
}
|
|
|
290 |
break;
|
|
|
291 |
case 'text':
|
|
|
292 |
$clean = array_merge(array(
|
|
|
293 |
'word' => '[\w,.]+',
|
|
|
294 |
'gap' => '[\s]*(?:(?:and|or)[\s]*)?',
|
|
|
295 |
'replacement' => '',
|
|
|
296 |
), $clean);
|
|
|
297 |
|
|
|
298 |
$kleenex = sprintf(
|
|
|
299 |
'/(%s%s%s%s|%s%s%s%s)/',
|
|
|
300 |
preg_quote($options['before'], '/'),
|
|
|
301 |
$clean['word'],
|
|
|
302 |
preg_quote($options['after'], '/'),
|
|
|
303 |
$clean['gap'],
|
|
|
304 |
$clean['gap'],
|
|
|
305 |
preg_quote($options['before'], '/'),
|
|
|
306 |
$clean['word'],
|
|
|
307 |
preg_quote($options['after'], '/')
|
|
|
308 |
);
|
|
|
309 |
$str = preg_replace($kleenex, $clean['replacement'], $str);
|
|
|
310 |
break;
|
|
|
311 |
}
|
|
|
312 |
return $str;
|
|
|
313 |
}
|
|
|
314 |
|
|
|
315 |
/**
|
|
|
316 |
* Wraps text to a specific width, can optionally wrap at word breaks.
|
|
|
317 |
*
|
|
|
318 |
* ### Options
|
|
|
319 |
*
|
|
|
320 |
* - `width` The width to wrap to. Defaults to 72.
|
|
|
321 |
* - `wordWrap` Only wrap on words breaks (spaces) Defaults to true.
|
|
|
322 |
* - `indent` String to indent with. Defaults to null.
|
|
|
323 |
* - `indentAt` 0 based index to start indenting at. Defaults to 0.
|
|
|
324 |
*
|
|
|
325 |
* @param string $text The text to format.
|
|
|
326 |
* @param array|integer $options Array of options to use, or an integer to wrap the text to.
|
|
|
327 |
* @return string Formatted text.
|
|
|
328 |
*/
|
|
|
329 |
public static function wrap($text, $options = array()) {
|
|
|
330 |
if (is_numeric($options)) {
|
|
|
331 |
$options = array('width' => $options);
|
|
|
332 |
}
|
|
|
333 |
$options += array('width' => 72, 'wordWrap' => true, 'indent' => null, 'indentAt' => 0);
|
|
|
334 |
if ($options['wordWrap']) {
|
|
|
335 |
$wrapped = self::wordWrap($text, $options['width'], "\n");
|
|
|
336 |
} else {
|
|
|
337 |
$wrapped = trim(chunk_split($text, $options['width'] - 1, "\n"));
|
|
|
338 |
}
|
|
|
339 |
if (!empty($options['indent'])) {
|
|
|
340 |
$chunks = explode("\n", $wrapped);
|
|
|
341 |
for ($i = $options['indentAt'], $len = count($chunks); $i < $len; $i++) {
|
|
|
342 |
$chunks[$i] = $options['indent'] . $chunks[$i];
|
|
|
343 |
}
|
|
|
344 |
$wrapped = implode("\n", $chunks);
|
|
|
345 |
}
|
|
|
346 |
return $wrapped;
|
|
|
347 |
}
|
|
|
348 |
|
|
|
349 |
/**
|
|
|
350 |
* Unicode aware version of wordwrap.
|
|
|
351 |
*
|
|
|
352 |
* @param string $text The text to format.
|
|
|
353 |
* @param integer $width The width to wrap to. Defaults to 72.
|
|
|
354 |
* @param string $break The line is broken using the optional break parameter. Defaults to '\n'.
|
|
|
355 |
* @param boolean $cut If the cut is set to true, the string is always wrapped at the specified width.
|
|
|
356 |
* @return string Formatted text.
|
|
|
357 |
*/
|
|
|
358 |
public static function wordWrap($text, $width = 72, $break = "\n", $cut = false) {
|
|
|
359 |
if ($cut) {
|
|
|
360 |
$parts = array();
|
|
|
361 |
while (mb_strlen($text) > 0) {
|
|
|
362 |
$part = mb_substr($text, 0, $width);
|
|
|
363 |
$parts[] = trim($part);
|
|
|
364 |
$text = trim(mb_substr($text, mb_strlen($part)));
|
|
|
365 |
}
|
|
|
366 |
return implode($break, $parts);
|
|
|
367 |
}
|
|
|
368 |
|
|
|
369 |
$parts = array();
|
|
|
370 |
while (mb_strlen($text) > 0) {
|
|
|
371 |
if ($width >= mb_strlen($text)) {
|
|
|
372 |
$parts[] = trim($text);
|
|
|
373 |
break;
|
|
|
374 |
}
|
|
|
375 |
|
|
|
376 |
$part = mb_substr($text, 0, $width);
|
|
|
377 |
$nextChar = mb_substr($text, $width, 1);
|
|
|
378 |
if ($nextChar !== ' ') {
|
|
|
379 |
$breakAt = mb_strrpos($part, ' ');
|
|
|
380 |
if ($breakAt === false) {
|
|
|
381 |
$breakAt = mb_strpos($text, ' ', $width);
|
|
|
382 |
}
|
|
|
383 |
if ($breakAt === false) {
|
|
|
384 |
$parts[] = trim($text);
|
|
|
385 |
break;
|
|
|
386 |
}
|
|
|
387 |
$part = mb_substr($text, 0, $breakAt);
|
|
|
388 |
}
|
|
|
389 |
|
|
|
390 |
$part = trim($part);
|
|
|
391 |
$parts[] = $part;
|
|
|
392 |
$text = trim(mb_substr($text, mb_strlen($part)));
|
|
|
393 |
}
|
|
|
394 |
|
|
|
395 |
return implode($break, $parts);
|
|
|
396 |
}
|
|
|
397 |
|
|
|
398 |
/**
|
|
|
399 |
* Highlights a given phrase in a text. You can specify any expression in highlighter that
|
|
|
400 |
* may include the \1 expression to include the $phrase found.
|
|
|
401 |
*
|
|
|
402 |
* ### Options:
|
|
|
403 |
*
|
|
|
404 |
* - `format` The piece of html with that the phrase will be highlighted
|
|
|
405 |
* - `html` If true, will ignore any HTML tags, ensuring that only the correct text is highlighted
|
|
|
406 |
* - `regex` a custom regex rule that is used to match words, default is '|$tag|iu'
|
|
|
407 |
*
|
|
|
408 |
* @param string $text Text to search the phrase in
|
|
|
409 |
* @param string $phrase The phrase that will be searched
|
|
|
410 |
* @param array $options An array of html attributes and options.
|
|
|
411 |
* @return string The highlighted text
|
|
|
412 |
* @link http://book.cakephp.org/2.0/en/core-libraries/helpers/text.html#TextHelper::highlight
|
|
|
413 |
*/
|
|
|
414 |
public static function highlight($text, $phrase, $options = array()) {
|
|
|
415 |
if (empty($phrase)) {
|
|
|
416 |
return $text;
|
|
|
417 |
}
|
|
|
418 |
|
|
|
419 |
$default = array(
|
|
|
420 |
'format' => '<span class="highlight">\1</span>',
|
|
|
421 |
'html' => false,
|
|
|
422 |
'regex' => "|%s|iu"
|
|
|
423 |
);
|
|
|
424 |
$options = array_merge($default, $options);
|
|
|
425 |
extract($options);
|
|
|
426 |
|
|
|
427 |
if (is_array($phrase)) {
|
|
|
428 |
$replace = array();
|
|
|
429 |
$with = array();
|
|
|
430 |
|
|
|
431 |
foreach ($phrase as $key => $segment) {
|
|
|
432 |
$segment = '(' . preg_quote($segment, '|') . ')';
|
|
|
433 |
if ($html) {
|
|
|
434 |
$segment = "(?![^<]+>)$segment(?![^<]+>)";
|
|
|
435 |
}
|
|
|
436 |
|
|
|
437 |
$with[] = (is_array($format)) ? $format[$key] : $format;
|
|
|
438 |
$replace[] = sprintf($options['regex'], $segment);
|
|
|
439 |
}
|
|
|
440 |
|
|
|
441 |
return preg_replace($replace, $with, $text);
|
|
|
442 |
}
|
|
|
443 |
|
|
|
444 |
$phrase = '(' . preg_quote($phrase, '|') . ')';
|
|
|
445 |
if ($html) {
|
|
|
446 |
$phrase = "(?![^<]+>)$phrase(?![^<]+>)";
|
|
|
447 |
}
|
|
|
448 |
|
|
|
449 |
return preg_replace(sprintf($options['regex'], $phrase), $format, $text);
|
|
|
450 |
}
|
|
|
451 |
|
|
|
452 |
/**
|
|
|
453 |
* Strips given text of all links (<a href=....)
|
|
|
454 |
*
|
|
|
455 |
* @param string $text Text
|
|
|
456 |
* @return string The text without links
|
|
|
457 |
* @link http://book.cakephp.org/2.0/en/core-libraries/helpers/text.html#TextHelper::stripLinks
|
|
|
458 |
*/
|
|
|
459 |
public static function stripLinks($text) {
|
|
|
460 |
return preg_replace('|<a\s+[^>]+>|im', '', preg_replace('|<\/a>|im', '', $text));
|
|
|
461 |
}
|
|
|
462 |
|
|
|
463 |
/**
|
|
|
464 |
* Truncates text starting from the end.
|
|
|
465 |
*
|
|
|
466 |
* Cuts a string to the length of $length and replaces the first characters
|
|
|
467 |
* with the ellipsis if the text is longer than length.
|
|
|
468 |
*
|
|
|
469 |
* ### Options:
|
|
|
470 |
*
|
|
|
471 |
* - `ellipsis` Will be used as Beginning and prepended to the trimmed string
|
|
|
472 |
* - `exact` If false, $text will not be cut mid-word
|
|
|
473 |
*
|
|
|
474 |
* @param string $text String to truncate.
|
|
|
475 |
* @param integer $length Length of returned string, including ellipsis.
|
|
|
476 |
* @param array $options An array of options.
|
|
|
477 |
* @return string Trimmed string.
|
|
|
478 |
*/
|
|
|
479 |
public static function tail($text, $length = 100, $options = array()) {
|
|
|
480 |
$default = array(
|
|
|
481 |
'ellipsis' => '...', 'exact' => true
|
|
|
482 |
);
|
|
|
483 |
$options = array_merge($default, $options);
|
|
|
484 |
extract($options);
|
|
|
485 |
|
|
|
486 |
if (!function_exists('mb_strlen')) {
|
|
|
487 |
class_exists('Multibyte');
|
|
|
488 |
}
|
|
|
489 |
|
|
|
490 |
if (mb_strlen($text) <= $length) {
|
|
|
491 |
return $text;
|
|
|
492 |
}
|
|
|
493 |
|
|
|
494 |
$truncate = mb_substr($text, mb_strlen($text) - $length + mb_strlen($ellipsis));
|
|
|
495 |
if (!$exact) {
|
|
|
496 |
$spacepos = mb_strpos($truncate, ' ');
|
|
|
497 |
$truncate = $spacepos === false ? '' : trim(mb_substr($truncate, $spacepos));
|
|
|
498 |
}
|
|
|
499 |
|
|
|
500 |
return $ellipsis . $truncate;
|
|
|
501 |
}
|
|
|
502 |
|
|
|
503 |
/**
|
|
|
504 |
* Truncates text.
|
|
|
505 |
*
|
|
|
506 |
* Cuts a string to the length of $length and replaces the last characters
|
|
|
507 |
* with the ellipsis if the text is longer than length.
|
|
|
508 |
*
|
|
|
509 |
* ### Options:
|
|
|
510 |
*
|
|
|
511 |
* - `ellipsis` Will be used as Ending and appended to the trimmed string (`ending` is deprecated)
|
|
|
512 |
* - `exact` If false, $text will not be cut mid-word
|
|
|
513 |
* - `html` If true, HTML tags would be handled correctly
|
|
|
514 |
*
|
|
|
515 |
* @param string $text String to truncate.
|
|
|
516 |
* @param integer $length Length of returned string, including ellipsis.
|
|
|
517 |
* @param array $options An array of html attributes and options.
|
|
|
518 |
* @return string Trimmed string.
|
|
|
519 |
* @link http://book.cakephp.org/2.0/en/core-libraries/helpers/text.html#TextHelper::truncate
|
|
|
520 |
*/
|
|
|
521 |
public static function truncate($text, $length = 100, $options = array()) {
|
|
|
522 |
$default = array(
|
|
|
523 |
'ellipsis' => '...', 'exact' => true, 'html' => false
|
|
|
524 |
);
|
|
|
525 |
if (isset($options['ending'])) {
|
|
|
526 |
$default['ellipsis'] = $options['ending'];
|
|
|
527 |
} elseif (!empty($options['html']) && Configure::read('App.encoding') === 'UTF-8') {
|
|
|
528 |
$default['ellipsis'] = "\xe2\x80\xa6";
|
|
|
529 |
}
|
|
|
530 |
$options = array_merge($default, $options);
|
|
|
531 |
extract($options);
|
|
|
532 |
|
|
|
533 |
if (!function_exists('mb_strlen')) {
|
|
|
534 |
class_exists('Multibyte');
|
|
|
535 |
}
|
|
|
536 |
|
|
|
537 |
if ($html) {
|
|
|
538 |
if (mb_strlen(preg_replace('/<.*?>/', '', $text)) <= $length) {
|
|
|
539 |
return $text;
|
|
|
540 |
}
|
|
|
541 |
$totalLength = mb_strlen(strip_tags($ellipsis));
|
|
|
542 |
$openTags = array();
|
|
|
543 |
$truncate = '';
|
|
|
544 |
|
|
|
545 |
preg_match_all('/(<\/?([\w+]+)[^>]*>)?([^<>]*)/', $text, $tags, PREG_SET_ORDER);
|
|
|
546 |
foreach ($tags as $tag) {
|
|
|
547 |
if (!preg_match('/img|br|input|hr|area|base|basefont|col|frame|isindex|link|meta|param/s', $tag[2])) {
|
|
|
548 |
if (preg_match('/<[\w]+[^>]*>/s', $tag[0])) {
|
|
|
549 |
array_unshift($openTags, $tag[2]);
|
|
|
550 |
} elseif (preg_match('/<\/([\w]+)[^>]*>/s', $tag[0], $closeTag)) {
|
|
|
551 |
$pos = array_search($closeTag[1], $openTags);
|
|
|
552 |
if ($pos !== false) {
|
|
|
553 |
array_splice($openTags, $pos, 1);
|
|
|
554 |
}
|
|
|
555 |
}
|
|
|
556 |
}
|
|
|
557 |
$truncate .= $tag[1];
|
|
|
558 |
|
|
|
559 |
$contentLength = mb_strlen(preg_replace('/&[0-9a-z]{2,8};|&#[0-9]{1,7};|&#x[0-9a-f]{1,6};/i', ' ', $tag[3]));
|
|
|
560 |
if ($contentLength + $totalLength > $length) {
|
|
|
561 |
$left = $length - $totalLength;
|
|
|
562 |
$entitiesLength = 0;
|
|
|
563 |
if (preg_match_all('/&[0-9a-z]{2,8};|&#[0-9]{1,7};|&#x[0-9a-f]{1,6};/i', $tag[3], $entities, PREG_OFFSET_CAPTURE)) {
|
|
|
564 |
foreach ($entities[0] as $entity) {
|
|
|
565 |
if ($entity[1] + 1 - $entitiesLength <= $left) {
|
|
|
566 |
$left--;
|
|
|
567 |
$entitiesLength += mb_strlen($entity[0]);
|
|
|
568 |
} else {
|
|
|
569 |
break;
|
|
|
570 |
}
|
|
|
571 |
}
|
|
|
572 |
}
|
|
|
573 |
|
|
|
574 |
$truncate .= mb_substr($tag[3], 0, $left + $entitiesLength);
|
|
|
575 |
break;
|
|
|
576 |
} else {
|
|
|
577 |
$truncate .= $tag[3];
|
|
|
578 |
$totalLength += $contentLength;
|
|
|
579 |
}
|
|
|
580 |
if ($totalLength >= $length) {
|
|
|
581 |
break;
|
|
|
582 |
}
|
|
|
583 |
}
|
|
|
584 |
} else {
|
|
|
585 |
if (mb_strlen($text) <= $length) {
|
|
|
586 |
return $text;
|
|
|
587 |
}
|
|
|
588 |
$truncate = mb_substr($text, 0, $length - mb_strlen($ellipsis));
|
|
|
589 |
}
|
|
|
590 |
if (!$exact) {
|
|
|
591 |
$spacepos = mb_strrpos($truncate, ' ');
|
|
|
592 |
if ($html) {
|
|
|
593 |
$truncateCheck = mb_substr($truncate, 0, $spacepos);
|
|
|
594 |
$lastOpenTag = mb_strrpos($truncateCheck, '<');
|
|
|
595 |
$lastCloseTag = mb_strrpos($truncateCheck, '>');
|
|
|
596 |
if ($lastOpenTag > $lastCloseTag) {
|
|
|
597 |
preg_match_all('/<[\w]+[^>]*>/s', $truncate, $lastTagMatches);
|
|
|
598 |
$lastTag = array_pop($lastTagMatches[0]);
|
|
|
599 |
$spacepos = mb_strrpos($truncate, $lastTag) + mb_strlen($lastTag);
|
|
|
600 |
}
|
|
|
601 |
$bits = mb_substr($truncate, $spacepos);
|
|
|
602 |
preg_match_all('/<\/([a-z]+)>/', $bits, $droppedTags, PREG_SET_ORDER);
|
|
|
603 |
if (!empty($droppedTags)) {
|
|
|
604 |
if (!empty($openTags)) {
|
|
|
605 |
foreach ($droppedTags as $closingTag) {
|
|
|
606 |
if (!in_array($closingTag[1], $openTags)) {
|
|
|
607 |
array_unshift($openTags, $closingTag[1]);
|
|
|
608 |
}
|
|
|
609 |
}
|
|
|
610 |
} else {
|
|
|
611 |
foreach ($droppedTags as $closingTag) {
|
|
|
612 |
$openTags[] = $closingTag[1];
|
|
|
613 |
}
|
|
|
614 |
}
|
|
|
615 |
}
|
|
|
616 |
}
|
|
|
617 |
$truncate = mb_substr($truncate, 0, $spacepos);
|
|
|
618 |
}
|
|
|
619 |
$truncate .= $ellipsis;
|
|
|
620 |
|
|
|
621 |
if ($html) {
|
|
|
622 |
foreach ($openTags as $tag) {
|
|
|
623 |
$truncate .= '</' . $tag . '>';
|
|
|
624 |
}
|
|
|
625 |
}
|
|
|
626 |
|
|
|
627 |
return $truncate;
|
|
|
628 |
}
|
|
|
629 |
|
|
|
630 |
/**
|
|
|
631 |
* Extracts an excerpt from the text surrounding the phrase with a number of characters on each side
|
|
|
632 |
* determined by radius.
|
|
|
633 |
*
|
|
|
634 |
* @param string $text String to search the phrase in
|
|
|
635 |
* @param string $phrase Phrase that will be searched for
|
|
|
636 |
* @param integer $radius The amount of characters that will be returned on each side of the founded phrase
|
|
|
637 |
* @param string $ellipsis Ending that will be appended
|
|
|
638 |
* @return string Modified string
|
|
|
639 |
* @link http://book.cakephp.org/2.0/en/core-libraries/helpers/text.html#TextHelper::excerpt
|
|
|
640 |
*/
|
|
|
641 |
public static function excerpt($text, $phrase, $radius = 100, $ellipsis = '...') {
|
|
|
642 |
if (empty($text) || empty($phrase)) {
|
|
|
643 |
return self::truncate($text, $radius * 2, array('ellipsis' => $ellipsis));
|
|
|
644 |
}
|
|
|
645 |
|
|
|
646 |
$append = $prepend = $ellipsis;
|
|
|
647 |
|
|
|
648 |
$phraseLen = mb_strlen($phrase);
|
|
|
649 |
$textLen = mb_strlen($text);
|
|
|
650 |
|
|
|
651 |
$pos = mb_strpos(mb_strtolower($text), mb_strtolower($phrase));
|
|
|
652 |
if ($pos === false) {
|
|
|
653 |
return mb_substr($text, 0, $radius) . $ellipsis;
|
|
|
654 |
}
|
|
|
655 |
|
|
|
656 |
$startPos = $pos - $radius;
|
|
|
657 |
if ($startPos <= 0) {
|
|
|
658 |
$startPos = 0;
|
|
|
659 |
$prepend = '';
|
|
|
660 |
}
|
|
|
661 |
|
|
|
662 |
$endPos = $pos + $phraseLen + $radius;
|
|
|
663 |
if ($endPos >= $textLen) {
|
|
|
664 |
$endPos = $textLen;
|
|
|
665 |
$append = '';
|
|
|
666 |
}
|
|
|
667 |
|
|
|
668 |
$excerpt = mb_substr($text, $startPos, $endPos - $startPos);
|
|
|
669 |
$excerpt = $prepend . $excerpt . $append;
|
|
|
670 |
|
|
|
671 |
return $excerpt;
|
|
|
672 |
}
|
|
|
673 |
|
|
|
674 |
/**
|
|
|
675 |
* Creates a comma separated list where the last two items are joined with 'and', forming natural English
|
|
|
676 |
*
|
|
|
677 |
* @param array $list The list to be joined
|
|
|
678 |
* @param string $and The word used to join the last and second last items together with. Defaults to 'and'
|
|
|
679 |
* @param string $separator The separator used to join all the other items together. Defaults to ', '
|
|
|
680 |
* @return string The glued together string.
|
|
|
681 |
* @link http://book.cakephp.org/2.0/en/core-libraries/helpers/text.html#TextHelper::toList
|
|
|
682 |
*/
|
|
|
683 |
public static function toList($list, $and = 'and', $separator = ', ') {
|
|
|
684 |
if (count($list) > 1) {
|
|
|
685 |
return implode($separator, array_slice($list, null, -1)) . ' ' . $and . ' ' . array_pop($list);
|
|
|
686 |
}
|
|
|
687 |
|
|
|
688 |
return array_pop($list);
|
|
|
689 |
}
|
|
|
690 |
}
|