URLify::add_chars() - Code Metrics - Cherry-Pie/Jarboe - Measure and Improve Code Quality continuously with Scrutinizer

URLify::add_chars() A
last analyzed 2024-09-13 11:39 UTC

↳ Parent: URLify

Complexity

Conditions	2
Paths	2

Size

Total Lines	8
Code Lines	5

Duplication

Lines	0
Ratio	0 %

Importance

Changes	1
Bugs	0	Features	1

Metric	Value
cc	2
eloc	5
c	1
b	0
f	1
nc	2
nop	1
dl	0
loc	8
rs	10

1			<?php
2
3			namespace Yaro\Jarboe\Helpers;
4
5			/* port of https://github.com/jbroadway/urlify */
6
7			/*
8			Copyright (c) Django Software Foundation and individual contributors.
9			All rights reserved.
10
11			Redistribution and use in source and binary forms, with or without modification,
12			are permitted provided that the following conditions are met:
13
14			1. Redistributions of source code must retain the above copyright notice,
15			this list of conditions and the following disclaimer.
16
17			2. Redistributions in binary form must reproduce the above copyright
18			notice, this list of conditions and the following disclaimer in the
19			documentation and/or other materials provided with the distribution.
20
21			3. Neither the name of Django nor the names of its contributors may be used
22			to endorse or promote products derived from this software without
23			specific prior written permission.
24
25			THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
26			ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
27			WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
28			DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
29			ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
30			(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
31			LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
32			ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
33			(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
34			SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
35			© 2019 GitHub, Inc.
36			*/
37
38			/**
39			* A PHP port of URLify.js from the Django project
40			* (https://github.com/django/django/blob/master/django/contrib/admin/static/admin/js/urlify.js).
41			* Handles symbols from Latin languages, Greek, Turkish, Bulgarian, Russian,
42			* Ukrainian, Czech, Polish, Romanian, Latvian, Lithuanian, Vietnamese, Arabic,
43			* Serbian, Azerbaijani, Kazakh and Slovak. Symbols it cannot transliterate
44			* it will simply omit.
45			*
46			* Usage:
47			*
48			* echo URLify::filter (' J\'étudie le français ');
49			* // "jetudie-le-francais"
50			*
51			* echo URLify::filter ('Lo siento, no hablo español.');
52			* // "lo-siento-no-hablo-espanol"
53			*/
54			class URLify
55			{
56			public static $maps = [
57			'de' => [ /* German */
58			'Ä' => 'Ae',
59			'Ö' => 'Oe',
60			'Ü' => 'Ue',
61			'ä' => 'ae',
62			'ö' => 'oe',
63			'ü' => 'ue',
64			'ß' => 'ss',
65			'ẞ' => 'SS',
66			],
67			'latin' => [
68			'À' => 'A',
69			'Á' => 'A',
70			'Â' => 'A',
71			'Ã' => 'A',
72			'Ä' => 'A',
73			'Å' => 'A',
74			'Ă' => 'A',
75			'Æ' => 'AE',
76			'Ç' => 'C',
77			'È' => 'E',
78			'É' => 'E',
79			'Ê' => 'E',
80			'Ë' => 'E',
81			'Ì' => 'I',
82			'Í' => 'I',
83			'Î' => 'I',
84			'Ï' => 'I',
85			'Ð' => 'D',
86			'Ñ' => 'N',
87			'Ò' => 'O',
88			'Ó' => 'O',
89			'Ô' => 'O',
90			'Õ' => 'O',
91			'Ö' => 'O',
92			'Ő' => 'O',
93			'Ø' => 'O',
94			'Œ' => 'OE',
95			'Ș' => 'S',
96			'Ț' => 'T',
97			'Ù' => 'U',
98			'Ú' => 'U',
99			'Û' => 'U',
100			'Ü' => 'U',
101			'Ű' => 'U',
102			'Ý' => 'Y',
103			'Þ' => 'TH',
104			'ß' => 'ss',
105			'à' => 'a',
106			'á' => 'a',
107			'â' => 'a',
108			'ã' => 'a',
109			'ä' => 'a',
110			'å' => 'a',
111			'ă' => 'a',
112			'æ' => 'ae',
113			'ç' => 'c',
114			'è' => 'e',
115			'é' => 'e',
116			'ê' => 'e',
117			'ë' => 'e',
118			'ì' => 'i',
119			'í' => 'i',
120			'î' => 'i',
121			'ï' => 'i',
122			'ð' => 'd',
123			'ñ' => 'n',
124			'ò' => 'o',
125			'ó' => 'o',
126			'ô' => 'o',
127			'õ' => 'o',
128			'ö' => 'o',
129			'ő' => 'o',
130			'ø' => 'o',
131			'œ' => 'oe',
132			'ș' => 's',
133			'ț' => 't',
134			'ù' => 'u',
135			'ú' => 'u',
136			'û' => 'u',
137			'ü' => 'u',
138			'ű' => 'u',
139			'ý' => 'y',
140			'þ' => 'th',
141			'ÿ' => 'y',
142			],
143			'latin_symbols' => [
144			'©' => '(c)',
145			],
146			'el' => [ /* Greek */
147			'α' => 'a',
148			'β' => 'b',
149			'γ' => 'g',
150			'δ' => 'd',
151			'ε' => 'e',
152			'ζ' => 'z',
153			'η' => 'h',
154			'θ' => '8',
155			'ι' => 'i',
156			'κ' => 'k',
157			'λ' => 'l',
158			'μ' => 'm',
159			'ν' => 'n',
160			'ξ' => '3',
161			'ο' => 'o',
162			'π' => 'p',
163			'ρ' => 'r',
164			'σ' => 's',
165			'τ' => 't',
166			'υ' => 'y',
167			'φ' => 'f',
168			'χ' => 'x',
169			'ψ' => 'ps',
170			'ω' => 'w',
171			'ά' => 'a',
172			'έ' => 'e',
173			'ί' => 'i',
174			'ό' => 'o',
175			'ύ' => 'y',
176			'ή' => 'h',
177			'ώ' => 'w',
178			'ς' => 's',
179			'ϊ' => 'i',
180			'ΰ' => 'y',
181			'ϋ' => 'y',
182			'ΐ' => 'i',
183			'Α' => 'A',
184			'Β' => 'B',
185			'Γ' => 'G',
186			'Δ' => 'D',
187			'Ε' => 'E',
188			'Ζ' => 'Z',
189			'Η' => 'H',
190			'Θ' => '8',
191			'Ι' => 'I',
192			'Κ' => 'K',
193			'Λ' => 'L',
194			'Μ' => 'M',
195			'Ν' => 'N',
196			'Ξ' => '3',
197			'Ο' => 'O',
198			'Π' => 'P',
199			'Ρ' => 'R',
200			'Σ' => 'S',
201			'Τ' => 'T',
202			'Υ' => 'Y',
203			'Φ' => 'F',
204			'Χ' => 'X',
205			'Ψ' => 'PS',
206			'Ω' => 'W',
207			'Ά' => 'A',
208			'Έ' => 'E',
209			'Ί' => 'I',
210			'Ό' => 'O',
211			'Ύ' => 'Y',
212			'Ή' => 'H',
213			'Ώ' => 'W',
214			'Ϊ' => 'I',
215			'Ϋ' => 'Y',
216			],
217			'tr' => [ /* Turkish */
218			'ş' => 's',
219			'Ş' => 'S',
220			'ı' => 'i',
221			'İ' => 'I',
222			'ç' => 'c',
223			'Ç' => 'C',
224			'ü' => 'u',
225			'Ü' => 'U',
226			'ö' => 'o',
227			'Ö' => 'O',
228			'ğ' => 'g',
229			'Ğ' => 'G',
230			],
231			'bg' => [ /* Bulgarian */
232			'Щ' => 'Sht',
233			'Ш' => 'Sh',
234			'Ч' => 'Ch',
235			'Ц' => 'C',
236			'Ю' => 'Yu',
237			'Я' => 'Ya',
238			'Ж' => 'J',
239			'А' => 'A',
240			'Б' => 'B',
241			'В' => 'V',
242			'Г' => 'G',
243			'Д' => 'D',
244			'Е' => 'E',
245			'З' => 'Z',
246			'И' => 'I',
247			'Й' => 'Y',
248			'К' => 'K',
249			'Л' => 'L',
250			'М' => 'M',
251			'Н' => 'N',
252			'О' => 'O',
253			'П' => 'P',
254			'Р' => 'R',
255			'С' => 'S',
256			'Т' => 'T',
257			'У' => 'U',
258			'Ф' => 'F',
259			'Х' => 'H',
260			'Ь' => '',
261			'Ъ' => 'A',
262			'щ' => 'sht',
263			'ш' => 'sh',
264			'ч' => 'ch',
265			'ц' => 'c',
266			'ю' => 'yu',
267			'я' => 'ya',
268			'ж' => 'j',
269			'а' => 'a',
270			'б' => 'b',
271			'в' => 'v',
272			'г' => 'g',
273			'д' => 'd',
274			'е' => 'e',
275			'з' => 'z',
276			'и' => 'i',
277			'й' => 'y',
278			'к' => 'k',
279			'л' => 'l',
280			'м' => 'm',
281			'н' => 'n',
282			'о' => 'o',
283			'п' => 'p',
284			'р' => 'r',
285			'с' => 's',
286			'т' => 't',
287			'у' => 'u',
288			'ф' => 'f',
289			'х' => 'h',
290			'ь' => '',
291			'ъ' => 'a',
292			],
293			'ru' => [ /* Russian */
294			'а' => 'a',
295			'б' => 'b',
296			'в' => 'v',
297			'г' => 'g',
298			'д' => 'd',
299			'е' => 'e',
300			'ё' => 'yo',
301			'ж' => 'zh',
302			'з' => 'z',
303			'и' => 'i',
304			'й' => 'i',
305			'к' => 'k',
306			'л' => 'l',
307			'м' => 'm',
308			'н' => 'n',
309			'о' => 'o',
310			'п' => 'p',
311			'р' => 'r',
312			'с' => 's',
313			'т' => 't',
314			'у' => 'u',
315			'ф' => 'f',
316			'х' => 'h',
317			'ц' => 'c',
318			'ч' => 'ch',
319			'ш' => 'sh',
320			'щ' => 'sh',
321			'ъ' => '',
322			'ы' => 'y',
323			'ь' => '',
324			'э' => 'e',
325			'ю' => 'yu',
326			'я' => 'ya',
327			'А' => 'A',
328			'Б' => 'B',
329			'В' => 'V',
330			'Г' => 'G',
331			'Д' => 'D',
332			'Е' => 'E',
333			'Ё' => 'Yo',
334			'Ж' => 'Zh',
335			'З' => 'Z',
336			'И' => 'I',
337			'Й' => 'I',
338			'К' => 'K',
339			'Л' => 'L',
340			'М' => 'M',
341			'Н' => 'N',
342			'О' => 'O',
343			'П' => 'P',
344			'Р' => 'R',
345			'С' => 'S',
346			'Т' => 'T',
347			'У' => 'U',
348			'Ф' => 'F',
349			'Х' => 'H',
350			'Ц' => 'C',
351			'Ч' => 'Ch',
352			'Ш' => 'Sh',
353			'Щ' => 'Sh',
354			'Ъ' => '',
355			'Ы' => 'Y',
356			'Ь' => '',
357			'Э' => 'E',
358			'Ю' => 'Yu',
359			'Я' => 'Ya',
360			'№' => '',
361			],
362			'uk' => [ /* Ukrainian */
363			'Є' => 'Ye',
364			'І' => 'I',
365			'Ї' => 'Yi',
366			'Ґ' => 'G',
367			'є' => 'ye',
368			'і' => 'i',
369			'ї' => 'yi',
370			'ґ' => 'g',
371			],
372			'kk' => [ /* Kazakh */
373			'Ә' => 'A',
374			'Ғ' => 'G',
375			'Қ' => 'Q',
376			'Ң' => 'N',
377			'Ө' => 'O',
378			'Ұ' => 'U',
379			'Ү' => 'U',
380			'Һ' => 'H',
381			'ә' => 'a',
382			'ғ' => 'g',
383			'қ' => 'q',
384			'ң' => 'n',
385			'ө' => 'o',
386			'ұ' => 'u',
387			'ү' => 'u',
388			'һ' => 'h',
389			],
390			'cs' => [ /* Czech */
391			'č' => 'c',
392			'ď' => 'd',
393			'ě' => 'e',
394			'ň' => 'n',
395			'ř' => 'r',
396			'š' => 's',
397			'ť' => 't',
398			'ů' => 'u',
399			'ž' => 'z',
400			'Č' => 'C',
401			'Ď' => 'D',
402			'Ě' => 'E',
403			'Ň' => 'N',
404			'Ř' => 'R',
405			'Š' => 'S',
406			'Ť' => 'T',
407			'Ů' => 'U',
408			'Ž' => 'Z',
409			],
410			'pl' => [ /* Polish */
411			'ą' => 'a',
412			'ć' => 'c',
413			'ę' => 'e',
414			'ł' => 'l',
415			'ń' => 'n',
416			'ó' => 'o',
417			'ś' => 's',
418			'ź' => 'z',
419			'ż' => 'z',
420			'Ą' => 'A',
421			'Ć' => 'C',
422			'Ę' => 'e',
423			'Ł' => 'L',
424			'Ń' => 'N',
425			'Ó' => 'O',
426			'Ś' => 'S',
427			'Ź' => 'Z',
428			'Ż' => 'Z',
429			],
430			'ro' => [ /* Romanian */
431			'ă' => 'a',
432			'â' => 'a',
433			'î' => 'i',
434			'ș' => 's',
435			'ț' => 't',
436			'Ţ' => 'T',
437			'ţ' => 't',
438			],
439			'lv' => [ /* Latvian */
440			'ā' => 'a',
441			'č' => 'c',
442			'ē' => 'e',
443			'ģ' => 'g',
444			'ī' => 'i',
445			'ķ' => 'k',
446			'ļ' => 'l',
447			'ņ' => 'n',
448			'š' => 's',
449			'ū' => 'u',
450			'ž' => 'z',
451			'Ā' => 'A',
452			'Č' => 'C',
453			'Ē' => 'E',
454			'Ģ' => 'G',
455			'Ī' => 'i',
456			'Ķ' => 'k',
457			'Ļ' => 'L',
458			'Ņ' => 'N',
459			'Š' => 'S',
460			'Ū' => 'u',
461			'Ž' => 'Z',
462			],
463			'lt' => [ /* Lithuanian */
464			'ą' => 'a',
465			'č' => 'c',
466			'ę' => 'e',
467			'ė' => 'e',
468			'į' => 'i',
469			'š' => 's',
470			'ų' => 'u',
471			'ū' => 'u',
472			'ž' => 'z',
473			'Ą' => 'A',
474			'Č' => 'C',
475			'Ę' => 'E',
476			'Ė' => 'E',
477			'Į' => 'I',
478			'Š' => 'S',
479			'Ų' => 'U',
480			'Ū' => 'U',
481			'Ž' => 'Z',
482			],
483			'vi' => [ /* Vietnamese */
484			'Á' => 'A',
485			'À' => 'A',
486			'Ả' => 'A',
487			'Ã' => 'A',
488			'Ạ' => 'A',
489			'Ă' => 'A',
490			'Ắ' => 'A',
491			'Ằ' => 'A',
492			'Ẳ' => 'A',
493			'Ẵ' => 'A',
494			'Ặ' => 'A',
495			'Â' => 'A',
496			'Ấ' => 'A',
497			'Ầ' => 'A',
498			'Ẩ' => 'A',
499			'Ẫ' => 'A',
500			'Ậ' => 'A',
501			'á' => 'a',
502			'à' => 'a',
503			'ả' => 'a',
504			'ã' => 'a',
505			'ạ' => 'a',
506			'ă' => 'a',
507			'ắ' => 'a',
508			'ằ' => 'a',
509			'ẳ' => 'a',
510			'ẵ' => 'a',
511			'ặ' => 'a',
512			'â' => 'a',
513			'ấ' => 'a',
514			'ầ' => 'a',
515			'ẩ' => 'a',
516			'ẫ' => 'a',
517			'ậ' => 'a',
518			'É' => 'E',
519			'È' => 'E',
520			'Ẻ' => 'E',
521			'Ẽ' => 'E',
522			'Ẹ' => 'E',
523			'Ê' => 'E',
524			'Ế' => 'E',
525			'Ề' => 'E',
526			'Ể' => 'E',
527			'Ễ' => 'E',
528			'Ệ' => 'E',
529			'é' => 'e',
530			'è' => 'e',
531			'ẻ' => 'e',
532			'ẽ' => 'e',
533			'ẹ' => 'e',
534			'ê' => 'e',
535			'ế' => 'e',
536			'ề' => 'e',
537			'ể' => 'e',
538			'ễ' => 'e',
539			'ệ' => 'e',
540			'Í' => 'I',
541			'Ì' => 'I',
542			'Ỉ' => 'I',
543			'Ĩ' => 'I',
544			'Ị' => 'I',
545			'í' => 'i',
546			'ì' => 'i',
547			'ỉ' => 'i',
548			'ĩ' => 'i',
549			'ị' => 'i',
550			'Ó' => 'O',
551			'Ò' => 'O',
552			'Ỏ' => 'O',
553			'Õ' => 'O',
554			'Ọ' => 'O',
555			'Ô' => 'O',
556			'Ố' => 'O',
557			'Ồ' => 'O',
558			'Ổ' => 'O',
559			'Ỗ' => 'O',
560			'Ộ' => 'O',
561			'Ơ' => 'O',
562			'Ớ' => 'O',
563			'Ờ' => 'O',
564			'Ở' => 'O',
565			'Ỡ' => 'O',
566			'Ợ' => 'O',
567			'ó' => 'o',
568			'ò' => 'o',
569			'ỏ' => 'o',
570			'õ' => 'o',
571			'ọ' => 'o',
572			'ô' => 'o',
573			'ố' => 'o',
574			'ồ' => 'o',
575			'ổ' => 'o',
576			'ỗ' => 'o',
577			'ộ' => 'o',
578			'ơ' => 'o',
579			'ớ' => 'o',
580			'ờ' => 'o',
581			'ở' => 'o',
582			'ỡ' => 'o',
583			'ợ' => 'o',
584			'Ú' => 'U',
585			'Ù' => 'U',
586			'Ủ' => 'U',
587			'Ũ' => 'U',
588			'Ụ' => 'U',
589			'Ư' => 'U',
590			'Ứ' => 'U',
591			'Ừ' => 'U',
592			'Ử' => 'U',
593			'Ữ' => 'U',
594			'Ự' => 'U',
595			'ú' => 'u',
596			'ù' => 'u',
597			'ủ' => 'u',
598			'ũ' => 'u',
599			'ụ' => 'u',
600			'ư' => 'u',
601			'ứ' => 'u',
602			'ừ' => 'u',
603			'ử' => 'u',
604			'ữ' => 'u',
605			'ự' => 'u',
606			'Ý' => 'Y',
607			'Ỳ' => 'Y',
608			'Ỷ' => 'Y',
609			'Ỹ' => 'Y',
610			'Ỵ' => 'Y',
611			'ý' => 'y',
612			'ỳ' => 'y',
613			'ỷ' => 'y',
614			'ỹ' => 'y',
615			'ỵ' => 'y',
616			'Đ' => 'D',
617			'đ' => 'd',
618			],
619			'ar' => [ /* Arabic */
620			'أ' => 'a',
621			'ب' => 'b',
622			'ت' => 't',
623			'ث' => 'th',
624			'ج' => 'g',
625			'ح' => 'h',
626			'خ' => 'kh',
627			'د' => 'd',
628			'ذ' => 'th',
629			'ر' => 'r',
630			'ز' => 'z',
631			'س' => 's',
632			'ش' => 'sh',
633			'ص' => 's',
634			'ض' => 'd',
635			'ط' => 't',
636			'ظ' => 'th',
637			'ع' => 'aa',
638			'غ' => 'gh',
639			'ف' => 'f',
640			'ق' => 'k',
641			'ك' => 'k',
642			'ل' => 'l',
643			'م' => 'm',
644			'ن' => 'n',
645			'ه' => 'h',
646			'و' => 'o',
647			'ي' => 'y',
648			'ا' => 'a',
649			'إ' => 'a',
650			'آ' => 'a',
651			'ؤ' => 'o',
652			'ئ' => 'y',
653			'ء' => 'aa',
654			'٠' => '0',
655			'١' => '1',
656			'٢' => '2',
657			'٣' => '3',
658			'٤' => '4',
659			'٥' => '5',
660			'٦' => '6',
661			'٧' => '7',
662			'٨' => '8',
663			'٩' => '9',
664			],
665			'fa' => [ /* Persian */
666			'گ' => 'g',
667			'ژ' => 'j',
668			'پ' => 'p',
669			'چ' => 'ch',
670			'ی' => 'y',
671			'ک' => 'k',
672			'۰' => '0',
673			'۱' => '1',
674			'۲' => '2',
675			'۳' => '3',
676			'۴' => '4',
677			'۵' => '5',
678			'۶' => '6',
679			'۷' => '7',
680			'۸' => '8',
681			'۹' => '9',
682			],
683			'sr' => [ /* Serbian */
684			'ђ' => 'dj',
685			'ј' => 'j',
686			'љ' => 'lj',
687			'њ' => 'nj',
688			'ћ' => 'c',
689			'џ' => 'dz',
690			'đ' => 'dj',
691			'Ђ' => 'Dj',
692			'Ј' => 'j',
693			'Љ' => 'Lj',
694			'Њ' => 'Nj',
695			'Ћ' => 'C',
696			'Џ' => 'Dz',
697			'Đ' => 'Dj',
698			],
699			'az' => [ /* Azerbaijani */
700			'ç' => 'c',
701			'ə' => 'e',
702			'ğ' => 'g',
703			'ı' => 'i',
704			'ö' => 'o',
705			'ş' => 's',
706			'ü' => 'u',
707			'Ç' => 'C',
708			'Ə' => 'E',
709			'Ğ' => 'G',
710			'İ' => 'I',
711			'Ö' => 'O',
712			'Ş' => 'S',
713			'Ü' => 'U',
714			],
715			'sk' => [ /* Slovak */
716			'ĺ' => 'l',
717			'ľ' => 'l',
718			'ŕ' => 'r',
719			],
720			'other' => [
721			'Ÿ' => 'Y',
722			'µ' => 'u',
723			'¥' => 'Y',
724			'Ĉ' => 'C',
725			'ĉ' => 'c',
726			'Ċ' => 'C',
727			'ċ' => 'c',
728			'Ĝ' => 'G',
729			'ĝ' => 'g',
730			'Ġ' => 'G',
731			'ġ' => 'g',
732			'Ĥ' => 'H',
733			'ĥ' => 'h',
734			'Ħ' => 'H',
735			'ħ' => 'h',
736			'Ĕ' => 'E',
737			'ĕ' => 'e',
738			'Ĭ' => 'I',
739			'ĭ' => 'i',
740			'Ĵ' => 'J',
741			'ĵ' => 'j',
742			'Ĺ' => 'L',
743			'ĺ' => 'l',
744			'Ľ' => 'L',
745			'ľ' => 'l',
746			'Ŀ' => 'L',
747			'ŀ' => 'l',
748			'ŉ' => 'n',
749			'Ō' => 'O',
750			'ō' => 'o',
751			'Ŏ' => 'O',
752			'ŏ' => 'o',
753			'Ŕ' => 'R',
754			'ŕ' => 'r',
755			'Ŗ' => 'R',
756			'ŗ' => 'r',
757			'Ŝ' => 'S',
758			'ŝ' => 's',
759			'Ŧ' => 'T',
760			'ŧ' => 't',
761			'Ŭ' => 'U',
762			'ŭ' => 'u',
763			'Ŵ' => 'W',
764			'ŵ' => 'w',
765			'Ŷ' => 'Y',
766			'ŷ' => 'y',
767			'ſ' => 'i',
768			'ƒ' => 'f',
769			'O' => 'O',
770			'o' => 'o',
771			'U' => 'U',
772			'u' => 'u',
773			'Ǎ' => 'A',
774			'ǎ' => 'a',
775			'Ǐ' => 'I',
776			'ǐ' => 'i',
777			'Ǒ' => 'O',
778			'ǒ' => 'o',
779			'Ǔ' => 'U',
780			'ǔ' => 'u',
781			'Ǖ' => 'U',
782			'ǖ' => 'u',
783			'Ǘ' => 'U',
784			'ǘ' => 'u',
785			'Ǚ' => 'U',
786			'ǚ' => 'u',
787			'Ǜ' => 'U',
788			'ǜ' => 'u',
789			'Ǻ' => 'A',
790			'ǻ' => 'a',
791			'Ǿ' => 'O',
792			'ǿ' => 'o',
793			'Ǽ' => 'Ae',
794			'ǽ' => 'ae',
795			'Ĳ' => 'IJ',
796			'ĳ' => 'ij',
797			'J' => 'J',
798			'ĸ' => 'k',
799			'Ŋ' => 'N',
800			'ŋ' => 'n',
801			'Ẁ' => 'W',
802			'ẁ' => 'w',
803			'Ẃ' => 'W',
804			'ẃ' => 'w',
805			'Ẅ' => 'W',
806			'ẅ' => 'w',
807			],
808			];
809
810			/**
811			* List of words to remove from URLs.
812			*/
813			public static $remove_list = [
814			'a',
815			'an',
816			'as',
817			'at',
818			'before',
819			'but',
820			'by',
821			'for',
822			'from',
823			'is',
824			'in',
825			'into',
826			'like',
827			'of',
828			'off',
829			'on',
830			'onto',
831			'per',
832			'since',
833			'than',
834			'the',
835			'this',
836			'that',
837			'to',
838			'up',
839			'via',
840			'with',
841			];
842
843			/**
844			* The character map.
845			*/
846			private static $map = [];
847
848			/**
849			* The character list as a string.
850			*/
851			private static $chars = '';
852
853			/**
854			* The character list as a regular expression.
855			*/
856			private static $regex = '';
857
858			/**
859			* The current language
860			*/
861			private static $language = '';
862
863			/**
864			* Initializes the character map.
865			* @param string $language
866			*/
867			private static function init($language = "")
868			{
869			if (count(self::$map) > 0 && (($language == "") \|\| ($language == self::$language))) {
870			return;
871			}
872
873			/* Is a specific map associated with $language ? */
874			if (isset(self::$maps[$language]) && is_array(self::$maps[$language])) {
875			/* Move this map to end. This means it will have priority over others */
876			$m = self::$maps[$language];
877			unset(self::$maps[$language]);
878			self::$maps[$language] = $m;
879			}
880			/* Reset static vars */
881			self::$language = $language;
882			self::$map = [];
883			self::$chars = '';
884
885			foreach (self::$maps as $map) {
886			foreach ($map as $orig => $conv) {
887			self::$map[$orig] = $conv;
888			self::$chars .= $orig;
889			}
890			}
891
892			self::$regex = '/[' . preg_quote(self::$chars, '/') . ']/u';
893			}
894
895			/**
896			* Add new characters to the list. `$map` should be a hash.
897			* @param array $map
898			*/
899			public static function add_chars($map)
900			{
901			if (!is_array($map)) {
			0 ignored issues – show introduced 2021-09-12 19:22 UTC by Report Bug Copy Issue Report The condition `is_array($map)` is always `true`. Loading history...
902			throw new \LogicException('$map must be an associative array.');
903			}
904			self::$maps[] = $map;
905			self::$map = [];
906			self::$chars = '';
907			}
908
909			/**
910			* Append words to the remove list. Accepts either single words
911			* or an array of words.
912			* @param mixed $words
913			*/
914			public static function remove_words($words)
915			{
916			$words = is_array($words) ? $words : [$words];
917			self::$remove_list = array_unique(array_merge(self::$remove_list, $words));
918			}
919
920			/**
921			* Transliterates characters to their ASCII equivalents.
922			* $language specifies a priority for a specific language.
923			* The latter is useful if languages have different rules for the same character.
924			* @param string $text
925			* @param string $language
926			* @return string
927			*/
928			public static function downcode($text, $language = "")
929			{
930			self::init($language);
931
932			if (preg_match_all(self::$regex, $text, $matches)) {
933			for ($i = 0; $i < count($matches[0]); $i++) {
			0 ignored issues – show Performance Best Practice introduced 2021-09-12 19:22 UTC by Report Bug Copy Issue Report It seems like you are calling the size function `count()` as part of the test condition. You might want to compute the size beforehand, and not on each iteration. If the size of the collection does not change during the iteration, it is generally a good practice to compute it beforehand, and not on each iteration: for ($i=0; $i<count($array); $i++) { // calls count() on each iteration } // Better for ($i=0, $c=count($array); $i<$c; $i++) { // calls count() just once } Loading history...
934			$char = $matches[0][$i];
935			if (isset(self::$map[$char])) {
936			$text = str_replace($char, self::$map[$char], $text);
937			}
938			}
939			}
940			return $text;
941			}
942
943			/**
944			* Filters a string, e.g., "Petty theft" to "petty-theft"
945			* @param string $text The text to return filtered
946			* @param int $length The length (after filtering) of the string to be returned
947			* @param string $language The transliteration language, passed down to downcode()
948			* @param bool $file_name Whether there should be and additional filter considering this is a filename
949			* @param bool $use_remove_list Whether you want to remove specific elements previously set in self::$remove_list
950			* @param bool $lower_case Whether you want the filter to maintain casing or lowercase everything (default)
951			* @param bool $treat_underscore_as_space Treat underscore as space, so it will replaced with "-"
952			* @return string
953			*/
954			public static function filter(
955			$text,
956			$length = 60,
957			$language = "",
958			$file_name = false,
959			$use_remove_list = true,
960			$lower_case = true,
961			$treat_underscore_as_space = true
962			) {
963			$text = self::downcode($text, $language);
964
965			if ($use_remove_list) {
966			// remove all these words from the string before urlifying
967			$text = preg_replace('/\b(' . join('\|', self::$remove_list) . ')\b/i', '', $text);
968			}
969
970			// if downcode doesn't hit, the char will be stripped here
971			$remove_pattern = ($file_name) ? '/[^_\-.\-a-zA-Z0-9\s]/u' : '/[^\s_\-a-zA-Z0-9]/u';
972			$text = preg_replace($remove_pattern, '', $text); // remove unneeded chars
973			if ($treat_underscore_as_space) {
974			$text = str_replace('_', ' ', $text); // treat underscores as spaces
975			}
976			$text = preg_replace('/^\s+\|\s+$/u', '', $text); // trim leading/trailing spaces
977			$text = preg_replace('/[-\s]+/u', '-', $text); // convert spaces to hyphens
978			if ($lower_case) {
979			$text = strtolower($text); // convert to lowercase
980			}
981
982			return trim(substr($text, 0, $length), '-'); // trim to first $length chars
983			}
984
985			/**
986			* Alias of `URLify::downcode()`.
987			*/
988			public static function transliterate($text)
989			{
990			return self::downcode($text);
991			}
992			}
993

Cherry-Pie / Jarboe

URLify::add_chars() A last analyzed 2024-09-13 11:39 UTC

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like

URLify::add_chars() A
last analyzed 2024-09-13 11:39 UTC