29770052588

Committed 20 Jul 2026 06:55PM UTC coverage: 92.619% (-0.1%) from 92.722%

Build # 29770052588

Build Type

push

github

Committed by

web-flow

Commit Message

Merge pull request #57 from JBZoo/release/8.0

8.0.0 — PHP 8.3+ floor & lock-step major

Coverage Stats

15 of 16 new or added lines in 7 files covered. (93.75%)

106 existing lines in 13 files now uncovered.

1669 of 1802 relevant lines covered (92.62%)

41.2 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

87.76

/src/Slug.php

1	<?php
2
3	/**
4	* JBZoo Toolbox - Utils.
5	*
6	* This file is part of the JBZoo Toolbox project.
7	* For the full copyright and license information, please view the LICENSE
8	* file that was distributed with this source code.
9	*
10	* @license MIT
11	* @copyright Copyright (C) JBZoo.com, All rights reserved.
12	* @see https://github.com/JBZoo/Utils
13	*/
14
15	declare(strict_types=1);
16
17	namespace JBZoo\Utils;
18
19	/**
20	* @psalm-suppress UnusedClass
21	*/
22	final class Slug
23	{
24	// The map to convert characters to ASCII characters.
25	public static array $maps = [
26	'de' => [// German
27	'Ä' => 'Ae',
28	'Ö' => 'Oe',
29	'Ü' => 'Ue',
30	'ä' => 'ae',
31	'ö' => 'oe',
32	'ü' => 'ue',
33	'ß' => 'ss',
34	'ẞ' => 'SS',
35	],
36
37	'latin' => [
38	'À' => 'A',
39	'Á' => 'A',
40	'Â' => 'A',
41	'Ã' => 'A',
42	'Ä' => 'A',
43	'Å' => 'A',
44	'Ă' => 'A',
45	'Æ' => 'AE',
46	'Ç' => 'C',
47	'È' => 'E',
48	'É' => 'E',
49	'Ê' => 'E',
50	'Ë' => 'E',
51	'Ì' => 'I',
52	'Í' => 'I',
53	'Î' => 'I',
54	'Ï' => 'I',
55	'Ð' => 'D',
56	'Ñ' => 'N',
57	'Ò' => 'O',
58	'Ó' => 'O',
59	'Ô' => 'O',
60	'Õ' => 'O',
61	'Ö' => 'O',
62	'Ő' => 'O',
63	'Ø' => 'O',
64	'Ș' => 'S',
65	'Ț' => 'T',
66	'Ù' => 'U',
67	'Ú' => 'U',
68	'Û' => 'U',
69	'Ü' => 'U',
70	'Ű' => 'U',
71	'Ý' => 'Y',
72	'Þ' => 'TH',
73	'ß' => 'ss',
74	'à' => 'a',
75	'á' => 'a',
76	'â' => 'a',
77	'ã' => 'a',
78	'ä' => 'a',
79	'å' => 'a',
80	'ă' => 'a',
81	'æ' => 'ae',
82	'ç' => 'c',
83	'è' => 'e',
84	'é' => 'e',
85	'ê' => 'e',
86	'ë' => 'e',
87	'ì' => 'i',
88	'í' => 'i',
89	'î' => 'i',
90	'ï' => 'i',
91	'ð' => 'd',
92	'ñ' => 'n',
93	'ò' => 'o',
94	'ó' => 'o',
95	'ô' => 'o',
96	'õ' => 'o',
97	'ö' => 'o',
98	'ő' => 'o',
99	'ø' => 'o',
100	'ș' => 's',
101	'ț' => 't',
102	'ù' => 'u',
103	'ú' => 'u',
104	'û' => 'u',
105	'ü' => 'u',
106	'ű' => 'u',
107	'ý' => 'y',
108	'þ' => 'th',
109	'ÿ' => 'y',
110	],
111
112	'latin_symbols' => [
113	'©' => '(c)',
114	],
115
116	'el' => [// Greek
117	'α' => 'a',
118	'β' => 'b',
119	'γ' => 'g',
120	'δ' => 'd',
121	'ε' => 'e',
122	'ζ' => 'z',
123	'η' => 'h',
124	'θ' => '8',
125	'ι' => 'i',
126	'κ' => 'k',
127	'λ' => 'l',
128	'μ' => 'm',
129	'ν' => 'n',
130	'ξ' => '3',
131	'ο' => 'o',
132	'π' => 'p',
133	'ρ' => 'r',
134	'σ' => 's',
135	'τ' => 't',
136	'υ' => 'y',
137	'φ' => 'f',
138	'χ' => 'x',
139	'ψ' => 'ps',
140	'ω' => 'w',
141	'ά' => 'a',
142	'έ' => 'e',
143	'ί' => 'i',
144	'ό' => 'o',
145	'ύ' => 'y',
146	'ή' => 'h',
147	'ώ' => 'w',
148	'ς' => 's',
149	'ϊ' => 'i',
150	'ΰ' => 'y',
151	'ϋ' => 'y',
152	'ΐ' => 'i',
153	'Α' => 'A',
154	'Β' => 'B',
155	'Γ' => 'G',
156	'Δ' => 'D',
157	'Ε' => 'E',
158	'Ζ' => 'Z',
159	'Η' => 'H',
160	'Θ' => '8',
161	'Ι' => 'I',
162	'Κ' => 'K',
163	'Λ' => 'L',
164	'Μ' => 'M',
165	'Ν' => 'N',
166	'Ξ' => '3',
167	'Ο' => 'O',
168	'Π' => 'P',
169	'Ρ' => 'R',
170	'Σ' => 'S',
171	'Τ' => 'T',
172	'Υ' => 'Y',
173	'Φ' => 'F',
174	'Χ' => 'X',
175	'Ψ' => 'PS',
176	'Ω' => 'W',
177	'Ά' => 'A',
178	'Έ' => 'E',
179	'Ί' => 'I',
180	'Ό' => 'O',
181	'Ύ' => 'Y',
182	'Ή' => 'H',
183	'Ώ' => 'W',
184	'Ϊ' => 'I',
185	'Ϋ' => 'Y',
186	],
187
188	'tr' => [// Turkish
189	'ş' => 's',
190	'Ş' => 'S',
191	'ı' => 'i',
192	'İ' => 'I',
193	'ç' => 'c',
194	'Ç' => 'C',
195	'ü' => 'u',
196	'Ü' => 'U',
197	'ö' => 'o',
198	'Ö' => 'O',
199	'ğ' => 'g',
200	'Ğ' => 'G',
201	],
202
203	'bg' => [// Bulgarian
204	'Щ' => 'Sht',
205	'Ш' => 'Sh',
206	'Ч' => 'Ch',
207	'Ц' => 'C',
208	'Ю' => 'Yu',
209	'Я' => 'Ya',
210	'Ж' => 'J',
211	'А' => 'A',
212	'Б' => 'B',
213	'В' => 'V',
214	'Г' => 'G',
215	'Д' => 'D',
216	'Е' => 'E',
217	'З' => 'Z',
218	'И' => 'I',
219	'Й' => 'Y',
220	'К' => 'K',
221	'Л' => 'L',
222	'М' => 'M',
223	'Н' => 'N',
224	'О' => 'O',
225	'П' => 'P',
226	'Р' => 'R',
227	'С' => 'S',
228	'Т' => 'T',
229	'У' => 'U',
230	'Ф' => 'F',
231	'Х' => 'H',
232	'Ь' => '',
233	'Ъ' => 'A',
234	'щ' => 'sht',
235	'ш' => 'sh',
236	'ч' => 'ch',
237	'ц' => 'c',
238	'ю' => 'yu',
239	'я' => 'ya',
240	'ж' => 'j',
241	'а' => 'a',
242	'б' => 'b',
243	'в' => 'v',
244	'г' => 'g',
245	'д' => 'd',
246	'е' => 'e',
247	'з' => 'z',
248	'и' => 'i',
249	'й' => 'y',
250	'к' => 'k',
251	'л' => 'l',
252	'м' => 'm',
253	'н' => 'n',
254	'о' => 'o',
255	'п' => 'p',
256	'р' => 'r',
257	'с' => 's',
258	'т' => 't',
259	'у' => 'u',
260	'ф' => 'f',
261	'х' => 'h',
262	'ь' => '',
263	'ъ' => 'a',
264	],
265
266	'ru' => [// Russian
267	'а' => 'a',
268	'б' => 'b',
269	'в' => 'v',
270	'г' => 'g',
271	'д' => 'd',
272	'е' => 'e',
273	'ё' => 'yo',
274	'ж' => 'zh',
275	'з' => 'z',
276	'и' => 'i',
277	'й' => 'j',
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	'ц' => 'c',
291	'ч' => 'ch',
292	'ш' => 'sh',
293	'щ' => 'sh',
294	'ъ' => '',
295	'ы' => 'y',
296	'ь' => '',
297	'э' => 'e',
298	'ю' => 'yu',
299	'я' => 'ya',
300	'А' => 'A',
301	'Б' => 'B',
302	'В' => 'V',
303	'Г' => 'G',
304	'Д' => 'D',
305	'Е' => 'E',
306	'Ё' => 'Yo',
307	'Ж' => 'Zh',
308	'З' => 'Z',
309	'И' => 'I',
310	'Й' => 'J',
311	'К' => 'K',
312	'Л' => 'L',
313	'М' => 'M',
314	'Н' => 'N',
315	'О' => 'O',
316	'П' => 'P',
317	'Р' => 'R',
318	'С' => 'S',
319	'Т' => 'T',
320	'У' => 'U',
321	'Ф' => 'F',
322	'Х' => 'H',
323	'Ц' => 'C',
324	'Ч' => 'Ch',
325	'Ш' => 'Sh',
326	'Щ' => 'Sh',
327	'Ъ' => '',
328	'Ы' => 'Y',
329	'Ь' => '',
330	'Э' => 'E',
331	'Ю' => 'Yu',
332	'Я' => 'Ya',
333	'№' => '',
334	],
335
336	'uk' => [// Ukrainian
337	'Є' => 'Ye',
338	'І' => 'I',
339	'Ї' => 'Yi',
340	'Ґ' => 'G',
341	'є' => 'ye',
342	'і' => 'i',
343	'ї' => 'yi',
344	'ґ' => 'g',
345	],
346
347	'cs' => [// Czech
348	'č' => 'c',
349	'ď' => 'd',
350	'ě' => 'e',
351	'ň' => 'n',
352	'ř' => 'r',
353	'š' => 's',
354	'ť' => 't',
355	'ů' => 'u',
356	'ž' => 'z',
357	'Č' => 'C',
358	'Ď' => 'D',
359	'Ě' => 'E',
360	'Ň' => 'N',
361	'Ř' => 'R',
362	'Š' => 'S',
363	'Ť' => 'T',
364	'Ů' => 'U',
365	'Ž' => 'Z',
366	],
367
368	'pl' => [// Polish
369	'ą' => 'a',
370	'ć' => 'c',
371	'ę' => 'e',
372	'ł' => 'l',
373	'ń' => 'n',
374	'ó' => 'o',
375	'ś' => 's',
376	'ź' => 'z',
377	'ż' => 'z',
378	'Ą' => 'A',
379	'Ć' => 'C',
380	'Ę' => 'e',
381	'Ł' => 'L',
382	'Ń' => 'N',
383	'Ó' => 'O',
384	'Ś' => 'S',
385	'Ź' => 'Z',
386	'Ż' => 'Z',
387	],
388
389	'ro' => [// Romanian
390	'ă' => 'a',
391	'â' => 'a',
392	'î' => 'i',
393	'ș' => 's',
394	'ț' => 't',
395	'Ţ' => 'T',
396	'ţ' => 't',
397	],
398
399	'lv' => [// Latvian
400	'ā' => 'a',
401	'č' => 'c',
402	'ē' => 'e',
403	'ģ' => 'g',
404	'ī' => 'i',
405	'ķ' => 'k',
406	'ļ' => 'l',
407	'ņ' => 'n',
408	'š' => 's',
409	'ū' => 'u',
410	'ž' => 'z',
411	'Ā' => 'A',
412	'Č' => 'C',
413	'Ē' => 'E',
414	'Ģ' => 'G',
415	'Ī' => 'i',
416	'Ķ' => 'k',
417	'Ļ' => 'L',
418	'Ņ' => 'N',
419	'Š' => 'S',
420	'Ū' => 'u',
421	'Ž' => 'Z',
422	],
423
424	'lt' => [// Lithuanian
425	'ą' => 'a',
426	'č' => 'c',
427	'ę' => 'e',
428	'ė' => 'e',
429	'į' => 'i',
430	'š' => 's',
431	'ų' => 'u',
432	'ū' => 'u',
433	'ž' => 'z',
434	'Ą' => 'A',
435	'Č' => 'C',
436	'Ę' => 'E',
437	'Ė' => 'E',
438	'Į' => 'I',
439	'Š' => 'S',
440	'Ų' => 'U',
441	'Ū' => 'U',
442	'Ž' => 'Z',
443	],
444
445	'vn' => [// Vietnamese
446	'Á' => 'A',
447	'À' => 'A',
448	'Ả' => 'A',
449	'Ã' => 'A',
450	'Ạ' => 'A',
451	'Ă' => 'A',
452	'Ắ' => 'A',
453	'Ằ' => 'A',
454	'Ẳ' => 'A',
455	'Ẵ' => 'A',
456	'Ặ' => 'A',
457	'Â' => 'A',
458	'Ấ' => 'A',
459	'Ầ' => 'A',
460	'Ẩ' => 'A',
461	'Ẫ' => 'A',
462	'Ậ' => 'A',
463	'á' => 'a',
464	'à' => 'a',
465	'ả' => 'a',
466	'ã' => 'a',
467	'ạ' => 'a',
468	'ă' => 'a',
469	'ắ' => 'a',
470	'ằ' => 'a',
471	'ẳ' => 'a',
472	'ẵ' => 'a',
473	'ặ' => 'a',
474	'â' => 'a',
475	'ấ' => 'a',
476	'ầ' => 'a',
477	'ẩ' => 'a',
478	'ẫ' => 'a',
479	'ậ' => 'a',
480	'É' => 'E',
481	'È' => 'E',
482	'Ẻ' => 'E',
483	'Ẽ' => 'E',
484	'Ẹ' => 'E',
485	'Ê' => 'E',
486	'Ế' => 'E',
487	'Ề' => 'E',
488	'Ể' => 'E',
489	'Ễ' => 'E',
490	'Ệ' => 'E',
491	'é' => 'e',
492	'è' => 'e',
493	'ẻ' => 'e',
494	'ẽ' => 'e',
495	'ẹ' => 'e',
496	'ê' => 'e',
497	'ế' => 'e',
498	'ề' => 'e',
499	'ể' => 'e',
500	'ễ' => 'e',
501	'ệ' => 'e',
502	'Í' => 'I',
503	'Ì' => 'I',
504	'Ỉ' => 'I',
505	'Ĩ' => 'I',
506	'Ị' => 'I',
507	'í' => 'i',
508	'ì' => 'i',
509	'ỉ' => 'i',
510	'ĩ' => 'i',
511	'ị' => 'i',
512	'Ó' => 'O',
513	'Ò' => 'O',
514	'Ỏ' => 'O',
515	'Õ' => 'O',
516	'Ọ' => 'O',
517	'Ô' => 'O',
518	'Ố' => 'O',
519	'Ồ' => 'O',
520	'Ổ' => 'O',
521	'Ỗ' => 'O',
522	'Ộ' => 'O',
523	'Ơ' => 'O',
524	'Ớ' => 'O',
525	'Ờ' => 'O',
526	'Ở' => 'O',
527	'Ỡ' => 'O',
528	'Ợ' => 'O',
529	'ó' => 'o',
530	'ò' => 'o',
531	'ỏ' => 'o',
532	'õ' => 'o',
533	'ọ' => 'o',
534	'ô' => 'o',
535	'ố' => 'o',
536	'ồ' => 'o',
537	'ổ' => 'o',
538	'ỗ' => 'o',
539	'ộ' => 'o',
540	'ơ' => 'o',
541	'ớ' => 'o',
542	'ờ' => 'o',
543	'ở' => 'o',
544	'ỡ' => 'o',
545	'ợ' => 'o',
546	'Ú' => 'U',
547	'Ù' => 'U',
548	'Ủ' => 'U',
549	'Ũ' => 'U',
550	'Ụ' => 'U',
551	'Ư' => 'U',
552	'Ứ' => 'U',
553	'Ừ' => 'U',
554	'Ử' => 'U',
555	'Ữ' => 'U',
556	'Ự' => 'U',
557	'ú' => 'u',
558	'ù' => 'u',
559	'ủ' => 'u',
560	'ũ' => 'u',
561	'ụ' => 'u',
562	'ư' => 'u',
563	'ứ' => 'u',
564	'ừ' => 'u',
565	'ử' => 'u',
566	'ữ' => 'u',
567	'ự' => 'u',
568	'Ý' => 'Y',
569	'Ỳ' => 'Y',
570	'Ỷ' => 'Y',
571	'Ỹ' => 'Y',
572	'Ỵ' => 'Y',
573	'ý' => 'y',
574	'ỳ' => 'y',
575	'ỷ' => 'y',
576	'ỹ' => 'y',
577	'ỵ' => 'y',
578	'Đ' => 'D',
579	'đ' => 'd',
580	],
581
582	'ar' => [// Arabic
583	'أ' => 'a',
584	'ب' => 'b',
585	'ت' => 't',
586	'ث' => 'th',
587	'ج' => 'g',
588	'ح' => 'h',
589	'خ' => 'kh',
590	'د' => 'd',
591	'ذ' => 'th',
592	'ر' => 'r',
593	'ز' => 'z',
594	'س' => 's',
595	'ش' => 'sh',
596	'ص' => 's',
597	'ض' => 'd',
598	'ط' => 't',
599	'ظ' => 'th',
600	'ع' => 'aa',
601	'غ' => 'gh',
602	'ف' => 'f',
603	'ق' => 'k',
604	'ك' => 'k',
605	'ل' => 'l',
606	'م' => 'm',
607	'ن' => 'n',
608	'ه' => 'h',
609	'و' => 'o',
610	'ي' => 'y',
611	],
612
613	'sr' => [// Serbian
614	'ђ' => 'dj',
615	'ј' => 'j',
616	'љ' => 'lj',
617	'њ' => 'nj',
618	'ћ' => 'c',
619	'џ' => 'dz',
620	'đ' => 'dj',
621	'Ђ' => 'Dj',
622	'Ј' => 'j',
623	'Љ' => 'Lj',
624	'Њ' => 'Nj',
625	'Ћ' => 'C',
626	'Џ' => 'Dz',
627	'Đ' => 'Dj',
628	],
629
630	'az' => [// Azerbaijani
631	'ç' => 'c',
632	'ə' => 'e',
633	'ğ' => 'g',
634	'ı' => 'i',
635	'ö' => 'o',
636	'ş' => 's',
637	'ü' => 'u',
638	'Ç' => 'C',
639	'Ə' => 'E',
640	'Ğ' => 'G',
641	'İ' => 'I',
642	'Ö' => 'O',
643	'Ş' => 'S',
644	'Ü' => 'U',
645	],
646	];
647
648	/** The character map. */
649	private static array $map = [];
650
651	/** The character list as a string. */
652	private static string $chars = '';
653
654	/** The character list as a regular expression. */
655	private static string $regex = '';
656
657	/** The current language. */
658	private static string $language = '';
659
660	/**
661	* Converts any accent characters to their equivalent normal characters and converts any other non-alphanumeric
662	* characters to dashes, then converts any sequence of two or more dashes to a single dash. This function generates
663	* slugs safe for use as URLs, and if you pass true as the second parameter, it will create strings safe for
664	* use as CSS classes or IDs.
665	* @param null\|string $string A string to convert to a slug
666	* @param string $separator The string to separate words with
667	* @param bool $cssMode Whether to generate strings safe for CSS classes/IDs (Default to false)
668	*/
669	public static function filter(?string $string, string $separator = '-', bool $cssMode = false): string
670	{
671	$slug = (string)\preg_replace('/([^a-z0-9]+)/', $separator, \strtolower(self::removeAccents((string)$string)));	24✔
672	$slug = \trim($slug, $separator);	24✔
673
674	if ($cssMode) {	24✔
675	$firstLetter = (int)$slug[0];	6✔
676	$digits = ['zero', 'one', 'two', 'three', 'four', 'five', 'six', 'seven', 'eight', 'nine'];	6✔
677	if (isset($digits[$firstLetter])) {	6✔
678	$slug = $digits[$firstLetter] . $separator . \substr($slug, 1);	6✔
679	}
680	}
681
682	return $slug;	24✔
683	}
684
685	/**
686	* Checks to see if a string is utf8 encoded.
687	* NOTE: This function checks for 5-Byte sequences, UTF8 has Bytes Sequences with a maximum length of 4.
688	* Written by Tony Ferrara <http://blog.ircmaxwell.com>.
689	* @param string $string The string to be checked
690	*/
691	public static function seemsUTF8(string $string): bool
692	{
693	if (Str::isMBString()) {	12✔
694	// If mbstring is available, this is significantly faster than
695	// using PHP regexps.
696	return \mb_check_encoding($string, Str::$encoding);	12✔
697	}
698
UNCOV 699	return self::seemsUtf8Regex($string);	×
700	}
701
702	/**
703	* Transliterates characters to their ASCII equivalents.
704	* Part of the URLify.php Project <https://github.com/jbroadway/urlify/>.
705	* @see https://github.com/jbroadway/urlify/blob/master/URLify.php
706	* @param string $text Text that might have not-ASCII characters
707	* @param string $language specifies a priority for a specific language
708	* @return string Filtered string with replaced "nice" characters
709	*/
710	public static function downCode(string $text, string $language = ''): string
711	{
712	self::initLanguageMap($language);	12✔
713
714	if (self::$regex !== '' && self::seemsUTF8($text)) {	12✔
715	if (\preg_match_all(self::$regex, $text, $matches) > 0) {	12✔
716	$matchesCount = \count($matches[0]);	12✔
717
718	/** @noinspection ForeachInvariantsInspection */
719	for ($i = 0; $i < $matchesCount; $i++) {	12✔
720	$char = $matches[0][$i];	12✔
721
722	if (\array_key_exists($char, self::$map)) {	12✔
723	$text = \str_replace($char, self::$map[$char], $text);	12✔
724	}
725	}
726	}
727	} else {
728	// Not a UTF-8 string so we assume its ISO-8859-1
729	$search = "\x80\x83\x8a\x8e\x9a\x9e\x9f\xa2\xa5\xb5\xc0\xc1\xc2\xc3\xc4\xc5\xc7\xc8\xc9\xca\xcb\xcc\xcd";	6✔
730	$search .= "\xce\xcf\xd1\xd2\xd3\xd4\xd5\xd6\xd8\xd9\xda\xdb\xdc\xdd\xe0\xe1\xe2\xe3\xe4\xe5\xe7\xe8\xe9";	6✔
731	$search .= "\xea\xeb\xec\xed\xee\xef\xf1\xf2\xf3\xf4\xf5\xf6\xf8\xf9\xfa\xfb\xfc\xfd\xff";	6✔
732	$text = \strtr($text, $search, 'EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy');	6✔
733
734	// These latin characters should be represented by two characters, so
735	// we can't use strtr
736	$complexSearch = ["\x8c", "\x9c", "\xc6", "\xd0", "\xde", "\xdf", "\xe6", "\xf0", "\xfe"];	6✔
737	$complexReplace = ['OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th'];	6✔
738	$text = \str_replace($complexSearch, $complexReplace, $text);	6✔
739	}
740
741	return $text;	12✔
742	}
743
744	/**
745	* Converts all accent characters to ASCII characters.
746	* If there are no accent characters, then the string given is just returned.
747	* @param string $string Text that might have accent characters
748	* @param string $language specifies a priority for a specific language
749	* @return string Filtered string with replaced "nice" characters
750	*/
751	public static function removeAccents(string $string, string $language = ''): string
752	{
753	if (\preg_match('/[\x80-\xff]/', $string) === 0) {	42✔
754	return $string;	30✔
755	}
756
757	return self::downCode($string, $language);	12✔
758	}
759
760	/**
761	* Initializes the character map.
762	* Part of the URLify.php Project <https://github.com/jbroadway/urlify/>.
763	* @see https://github.com/jbroadway/urlify/blob/master/URLify.php
764	*/
765	private static function initLanguageMap(string $language = ''): void
766	{
767	if ((isStrEmpty($language) \|\| $language === self::$language) && \count(self::$map) > 0) {	12✔
768	return;	6✔
769	}
770
771	// Is a specific map associated with $language?
772
773	if (\array_key_exists($language, self::$maps) && \is_array(self::$maps[$language])) {	12✔
774	// Move this map to end. This means it will have priority over others
775	$langMap = self::$maps[$language];	6✔
776	unset(self::$maps[$language]);	6✔
777	self::$maps[$language] = $langMap;	6✔
778	}
779
780	// Reset static vars
781	self::$language = $language;	12✔
782	self::$map = [];	12✔
783	self::$chars = '';	12✔
784
785	foreach (self::$maps as $map) {	12✔
786	foreach ((array)$map as $orig => $conv) {	12✔
787	self::$map[$orig] = $conv;	12✔
788	self::$chars .= $orig;	12✔
789	}
790	}
791
792	self::$regex = '/[' . self::$chars . ']/u';	12✔
793	}
794
795	/**
796	* A non-Mbstring UTF-8 checker.
797	* @see http://stackoverflow.com/a/11709412/430062
798	*/
799	private static function seemsUtf8Regex(string $string): bool
800	{
UNCOV 801	$regex = '/(	×
802	[\xC0-\xC1] # Invalid UTF-8 Bytes
803	\| [\xF5-\xFF] # Invalid UTF-8 Bytes
804	\| \xE0[\x80-\x9F] # Overlong encoding of prior code point
805	\| \xF0[\x80-\x8F] # Overlong encoding of prior code point
806	\| [\xC2-\xDF](?![\x80-\xBF]) # Invalid UTF-8 Sequence Start
807	\| [\xE0-\xEF](?![\x80-\xBF]{2}) # Invalid UTF-8 Sequence Start
808	\| [\xF0-\xF4](?![\x80-\xBF]{3}) # Invalid UTF-8 Sequence Start
809	\| (?<=[\x0-\x7F\xF5-\xFF])[\x80-\xBF] # Invalid UTF-8 Sequence Middle
UNCOV 810	\| (?<![\xC2-\xDF]\|[\xE0-\xEF]\|[\xE0-\xEF][\x80-\xBF]\|[\xF0-\xF4]\|'	×
UNCOV 811	. '[\xF0-\xF4][\x80-\xBF]\|[\xF0-\xF4][\x80-\xBF]{2})[\x80-\xBF] # Overlong Sequence	×
812	\| (?<=[\xE0-\xEF])[\x80-\xBF](?![\x80-\xBF]) # Short 3 byte sequence
813	\| (?<=[\xF0-\xF4])[\x80-\xBF](?![\x80-\xBF]{2}) # Short 4 byte sequence
814	\| (?<=[\xF0-\xF4][\x80-\xBF])[\x80-\xBF](?![\x80-\xBF]) # Short 4 byte sequence (2)
UNCOV 815	)/x';	×
816
UNCOV 817	return \preg_match($regex, $string) === 0;	×
818	}
819	}

JBZoo / Utils / 29770052588

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous