Inflector::capitalize() - Code Metrics - Inspection of "Port Doctrine1 Inflector urlize functionality." - doctrine/inflector - Measure and Improve Code Quality continuously with Scrutinizer

Failed Conditions

Pull Request — master (#103)

by Jonathan

created 2019-01-09 21:09 UTC

Inflector::capitalize() A

↳ Parent: Inflector

Complexity

Conditions	1
Paths	1

Size

Total Lines	3
Code Lines	1

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	2
CRAP Score	1

Importance

Changes

Metric	Value
cc	1
eloc	1
nc	1
nop	2
dl	0
loc	3
ccs	2
cts	2
cp	1
crap	1
rs	10
c	0
b	0
f	0

1		<?php
2
3		declare(strict_types=1);
4
5		namespace Doctrine\Inflector;
6
7		use function chr;
8		use function function_exists;
9		use function lcfirst;
10		use function mb_strtolower;
11		use function ord;
12		use function preg_match;
13		use function preg_replace;
14		use function str_replace;
15		use function strlen;
16		use function strtolower;
17		use function strtr;
18		use function trim;
19		use function ucwords;
20
21		class Inflector
22		{
23		/** @var WordInflector */
24		private $singularizer;
25
26		/** @var WordInflector */
27		private $pluralizer;
28
29	1090	public function __construct(WordInflector $singularizer, WordInflector $pluralizer)
30		{
31	1090	$this->singularizer = $singularizer;
32	1090	$this->pluralizer = $pluralizer;
33	1090	}
34
35		/**
36		* Converts a word into the format for a Doctrine table name. Converts 'ModelName' to 'model_name'.
37		*/
38	4	public function tableize(string $word) : string
39		{
40	4	return mb_strtolower(preg_replace('~(?<=\\w)([A-Z])~u', '_$1', $word));
41		}
42
43		/**
44		* Converts a word into the format for a Doctrine class name. Converts 'table_name' to 'TableName'.
45		*/
46	13	public function classify(string $word) : string
47		{
48	13	return str_replace([' ', '_', '-'], '', ucwords($word, ' _-'));
49		}
50
51		/**
52		* Camelizes a word. This uses the classify() method and turns the first character to lowercase.
53		*/
54	6	public function camelize(string $word) : string
55		{
56	6	return lcfirst($this->classify($word));
57		}
58
59		/**
60		* Uppercases words with configurable delimiters between words.
61		*
62		* Takes a string and capitalizes all of the words, like PHP's built-in
63		* ucwords function. This extends that behavior, however, by allowing the
64		* word delimiters to be configured, rather than only separating on
65		* whitespace.
66		*
67		* Here is an example:
68		* <code>
69		* <?php
70		* $string = 'top-o-the-morning to all_of_you!';
71		* echo $inflector->capitalize($string);
72		* // Top-O-The-Morning To All_of_you!
73		*
74		* echo $inflector->capitalize($string, '-_ ');
75		* // Top-O-The-Morning To All_Of_You!
76		* ?>
77		* </code>
78		*
79		* @param string $string The string to operate on.
80		* @param string $delimiters A list of word separators.
81		*
82		* @return string The string with all delimiter-separated words capitalized.
83		*/
84	3	public function capitalize(string $string, string $delimiters = " \n\t\r\0\x0B-") : string
85		{
86	3	return ucwords($string, $delimiters);
87		}
88
89		/**
90		* Checks if the given string seems like it has utf8 characters in it.
91		*
92		* @param string $string The string to check for utf8 characters in.
93		*/
94	6	public function seemsUtf8(string $string) : bool
95		{
96	6	for ($i = 0; $i < strlen($string); $i++) {
97	6	if (ord($string[$i]) < 0x80) {
98	6	continue; // 0bbbbbbb
99	5	} elseif ((ord($string[$i]) & 0xE0) === 0xC0) {
100	5	$n = 1; // 110bbbbb
101		} elseif ((ord($string[$i]) & 0xF0) === 0xE0) {
102		$n = 2; // 1110bbbb
103		} elseif ((ord($string[$i]) & 0xF8) === 0xF0) {
104		$n = 3; // 11110bbb
105		} elseif ((ord($string[$i]) & 0xFC) === 0xF8) {
106		$n = 4; // 111110bb
107		} elseif ((ord($string[$i]) & 0xFE) === 0xFC) {
108		$n = 5; // 1111110b
109		} else {
110		return false; // Does not match any model
111		}
112
113	5	for ($j = 0; $j < $n; $j++) { // n bytes matching 10bbbbbb follow ?
114	5	if ((++$i === strlen($string)) \|\| ((ord($string[$i]) & 0xC0) !== 0x80)) {
		0 ignored issues – show introduced 2019-01-09 21:14 UTC by Report Bug Copy Issue Report Useless parentheses. Loading history...
115		return false;
116		}
117		}
118		}
119
120	6	return true;
121		}
122
123		/**
124		* Remove any illegal characters, accents, etc.
125		*
126		* @param string $string String to unaccent
		0 ignored issues – show introduced 2019-01-09 21:14 UTC by Report Bug Copy Issue Report Incorrect annotations group. Loading history...
127		* @return string Unaccented string
128		*/
129	5	public function unaccent(string $string) : string
130		{
131	5	if (preg_match('/[\x80-\xff]/', $string) === false) {
132		return $string;
133		}
134
135	5	if ($this->seemsUtf8($string)) {
136		$characters = [
137		// Decompositions for Latin-1 Supplement
138	5	chr(195) . chr(128) => 'A',
139	5	chr(195) . chr(129) => 'A',
140	5	chr(195) . chr(130) => 'A',
141	5	chr(195) . chr(131) => 'A',
142	5	chr(195) . chr(132) => 'A',
143	5	chr(195) . chr(133) => 'A',
144	5	chr(195) . chr(135) => 'C',
145	5	chr(195) . chr(136) => 'E',
146	5	chr(195) . chr(137) => 'E',
147	5	chr(195) . chr(138) => 'E',
148	5	chr(195) . chr(139) => 'E',
149	5	chr(195) . chr(140) => 'I',
150	5	chr(195) . chr(141) => 'I',
151	5	chr(195) . chr(142) => 'I',
152	5	chr(195) . chr(143) => 'I',
153	5	chr(195) . chr(145) => 'N',
154	5	chr(195) . chr(146) => 'O',
155	5	chr(195) . chr(147) => 'O',
156	5	chr(195) . chr(148) => 'O',
157	5	chr(195) . chr(149) => 'O',
158	5	chr(195) . chr(150) => 'O',
159	5	chr(195) . chr(153) => 'U',
160	5	chr(195) . chr(154) => 'U',
161	5	chr(195) . chr(155) => 'U',
162	5	chr(195) . chr(156) => 'U',
163	5	chr(195) . chr(157) => 'Y',
164	5	chr(195) . chr(159) => 's',
165	5	chr(195) . chr(160) => 'a',
166	5	chr(195) . chr(161) => 'a',
167	5	chr(195) . chr(162) => 'a',
168	5	chr(195) . chr(163) => 'a',
169	5	chr(195) . chr(164) => 'a',
170	5	chr(195) . chr(165) => 'a',
171	5	chr(195) . chr(167) => 'c',
172	5	chr(195) . chr(168) => 'e',
173	5	chr(195) . chr(169) => 'e',
174	5	chr(195) . chr(170) => 'e',
175	5	chr(195) . chr(171) => 'e',
176	5	chr(195) . chr(172) => 'i',
177	5	chr(195) . chr(173) => 'i',
178	5	chr(195) . chr(174) => 'i',
179	5	chr(195) . chr(175) => 'i',
180	5	chr(195) . chr(177) => 'n',
181	5	chr(195) . chr(178) => 'o',
182	5	chr(195) . chr(179) => 'o',
183	5	chr(195) . chr(180) => 'o',
184	5	chr(195) . chr(181) => 'o',
185	5	chr(195) . chr(182) => 'o',
186	5	chr(195) . chr(182) => 'o',
187	5	chr(195) . chr(185) => 'u',
188	5	chr(195) . chr(186) => 'u',
189	5	chr(195) . chr(187) => 'u',
190	5	chr(195) . chr(188) => 'u',
191	5	chr(195) . chr(189) => 'y',
192	5	chr(195) . chr(191) => 'y',
193		// Decompositions for Latin Extended-A
194	5	chr(196) . chr(128) => 'A',
195	5	chr(196) . chr(129) => 'a',
196	5	chr(196) . chr(130) => 'A',
197	5	chr(196) . chr(131) => 'a',
198	5	chr(196) . chr(132) => 'A',
199	5	chr(196) . chr(133) => 'a',
200	5	chr(196) . chr(134) => 'C',
201	5	chr(196) . chr(135) => 'c',
202	5	chr(196) . chr(136) => 'C',
203	5	chr(196) . chr(137) => 'c',
204	5	chr(196) . chr(138) => 'C',
205	5	chr(196) . chr(139) => 'c',
206	5	chr(196) . chr(140) => 'C',
207	5	chr(196) . chr(141) => 'c',
208	5	chr(196) . chr(142) => 'D',
209	5	chr(196) . chr(143) => 'd',
210	5	chr(196) . chr(144) => 'D',
211	5	chr(196) . chr(145) => 'd',
212	5	chr(196) . chr(146) => 'E',
213	5	chr(196) . chr(147) => 'e',
214	5	chr(196) . chr(148) => 'E',
215	5	chr(196) . chr(149) => 'e',
216	5	chr(196) . chr(150) => 'E',
217	5	chr(196) . chr(151) => 'e',
218	5	chr(196) . chr(152) => 'E',
219	5	chr(196) . chr(153) => 'e',
220	5	chr(196) . chr(154) => 'E',
221	5	chr(196) . chr(155) => 'e',
222	5	chr(196) . chr(156) => 'G',
223	5	chr(196) . chr(157) => 'g',
224	5	chr(196) . chr(158) => 'G',
225	5	chr(196) . chr(159) => 'g',
226	5	chr(196) . chr(160) => 'G',
227	5	chr(196) . chr(161) => 'g',
228	5	chr(196) . chr(162) => 'G',
229	5	chr(196) . chr(163) => 'g',
230	5	chr(196) . chr(164) => 'H',
231	5	chr(196) . chr(165) => 'h',
232	5	chr(196) . chr(166) => 'H',
233	5	chr(196) . chr(167) => 'h',
234	5	chr(196) . chr(168) => 'I',
235	5	chr(196) . chr(169) => 'i',
236	5	chr(196) . chr(170) => 'I',
237	5	chr(196) . chr(171) => 'i',
238	5	chr(196) . chr(172) => 'I',
239	5	chr(196) . chr(173) => 'i',
240	5	chr(196) . chr(174) => 'I',
241	5	chr(196) . chr(175) => 'i',
242	5	chr(196) . chr(176) => 'I',
243	5	chr(196) . chr(177) => 'i',
244	5	chr(196) . chr(178) => 'IJ',
245	5	chr(196) . chr(179) => 'ij',
246	5	chr(196) . chr(180) => 'J',
247	5	chr(196) . chr(181) => 'j',
248	5	chr(196) . chr(182) => 'K',
249	5	chr(196) . chr(183) => 'k',
250	5	chr(196) . chr(184) => 'k',
251	5	chr(196) . chr(185) => 'L',
252	5	chr(196) . chr(186) => 'l',
253	5	chr(196) . chr(187) => 'L',
254	5	chr(196) . chr(188) => 'l',
255	5	chr(196) . chr(189) => 'L',
256	5	chr(196) . chr(190) => 'l',
257	5	chr(196) . chr(191) => 'L',
258	5	chr(197) . chr(128) => 'l',
259	5	chr(197) . chr(129) => 'L',
260	5	chr(197) . chr(130) => 'l',
261	5	chr(197) . chr(131) => 'N',
262	5	chr(197) . chr(132) => 'n',
263	5	chr(197) . chr(133) => 'N',
264	5	chr(197) . chr(134) => 'n',
265	5	chr(197) . chr(135) => 'N',
266	5	chr(197) . chr(136) => 'n',
267	5	chr(197) . chr(137) => 'N',
268	5	chr(197) . chr(138) => 'n',
269	5	chr(197) . chr(139) => 'N',
270	5	chr(197) . chr(140) => 'O',
271	5	chr(197) . chr(141) => 'o',
272	5	chr(197) . chr(142) => 'O',
273	5	chr(197) . chr(143) => 'o',
274	5	chr(197) . chr(144) => 'O',
275	5	chr(197) . chr(145) => 'o',
276	5	chr(197) . chr(146) => 'OE',
277	5	chr(197) . chr(147) => 'oe',
278	5	chr(197) . chr(148) => 'R',
279	5	chr(197) . chr(149) => 'r',
280	5	chr(197) . chr(150) => 'R',
281	5	chr(197) . chr(151) => 'r',
282	5	chr(197) . chr(152) => 'R',
283	5	chr(197) . chr(153) => 'r',
284	5	chr(197) . chr(154) => 'S',
285	5	chr(197) . chr(155) => 's',
286	5	chr(197) . chr(156) => 'S',
287	5	chr(197) . chr(157) => 's',
288	5	chr(197) . chr(158) => 'S',
289	5	chr(197) . chr(159) => 's',
290	5	chr(197) . chr(160) => 'S',
291	5	chr(197) . chr(161) => 's',
292	5	chr(197) . chr(162) => 'T',
293	5	chr(197) . chr(163) => 't',
294	5	chr(197) . chr(164) => 'T',
295	5	chr(197) . chr(165) => 't',
296	5	chr(197) . chr(166) => 'T',
297	5	chr(197) . chr(167) => 't',
298	5	chr(197) . chr(168) => 'U',
299	5	chr(197) . chr(169) => 'u',
300	5	chr(197) . chr(170) => 'U',
301	5	chr(197) . chr(171) => 'u',
302	5	chr(197) . chr(172) => 'U',
303	5	chr(197) . chr(173) => 'u',
304	5	chr(197) . chr(174) => 'U',
305	5	chr(197) . chr(175) => 'u',
306	5	chr(197) . chr(176) => 'U',
307	5	chr(197) . chr(177) => 'u',
308	5	chr(197) . chr(178) => 'U',
309	5	chr(197) . chr(179) => 'u',
310	5	chr(197) . chr(180) => 'W',
311	5	chr(197) . chr(181) => 'w',
312	5	chr(197) . chr(182) => 'Y',
313	5	chr(197) . chr(183) => 'y',
314	5	chr(197) . chr(184) => 'Y',
315	5	chr(197) . chr(185) => 'Z',
316	5	chr(197) . chr(186) => 'z',
317	5	chr(197) . chr(187) => 'Z',
318	5	chr(197) . chr(188) => 'z',
319	5	chr(197) . chr(189) => 'Z',
320	5	chr(197) . chr(190) => 'z',
321	5	chr(197) . chr(191) => 's',
322		// Euro Sign
323	5	chr(226) . chr(130) . chr(172) => 'E',
324		// GBP (Pound) Sign
325	5	chr(194) . chr(163) => '',
326	5	'Ä' => 'Ae',
327	5	'ä' => 'ae',
328	5	'Ü' => 'Ue',
329	5	'ü' => 'ue',
330	5	'Ö' => 'Oe',
331	5	'ö' => 'oe',
332	5	'ß' => 'ss',
333		// Norwegian characters
334	5	'Å'=>'Aa',
335	5	'Æ'=>'Ae',
336	5	'Ø'=>'O',
337	5	'æ'=>'a',
338	5	'ø'=>'o',
339	5	'å'=>'aa',
340		];
341
342	5	$string = strtr($string, $characters);
343		} else {
344		$characters = [];
345
346		// Assume ISO-8859-1 if not UTF-8
347		$characters['in'] =
348		chr(128)
349		. chr(131)
350		. chr(138)
351		. chr(142)
352		. chr(154)
353		. chr(158)
354		. chr(159)
355		. chr(162)
356		. chr(165)
357		. chr(181)
358		. chr(192)
359		. chr(193)
360		. chr(194)
361		. chr(195)
362		. chr(196)
363		. chr(197)
364		. chr(199)
365		. chr(200)
366		. chr(201)
367		. chr(202)
368		. chr(203)
369		. chr(204)
370		. chr(205)
371		. chr(206)
372		. chr(207)
373		. chr(209)
374		. chr(210)
375		. chr(211)
376		. chr(212)
377		. chr(213)
378		. chr(214)
379		. chr(216)
380		. chr(217)
381		. chr(218)
382		. chr(219)
383		. chr(220)
384		. chr(221)
385		. chr(224)
386		. chr(225)
387		. chr(226)
388		. chr(227)
389		. chr(228)
390		. chr(229)
391		. chr(231)
392		. chr(232)
393		. chr(233)
394		. chr(234)
395		. chr(235)
396		. chr(236)
397		. chr(237)
398		. chr(238)
399		. chr(239)
400		. chr(241)
401		. chr(242)
402		. chr(243)
403		. chr(244)
404		. chr(245)
405		. chr(246)
406		. chr(248)
407		. chr(249)
408		. chr(250)
409		. chr(251)
410		. chr(252)
411		. chr(253)
412		. chr(255)
413		;
		0 ignored issues – show Coding Style introduced 2019-01-09 21:14 UTC by Report Bug Copy Issue Report Space found before semicolon; expected ");" but found ") ;" Loading history...
414
415		$characters['out'] = 'EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy';
416
417		$string = strtr($string, $characters['in'], $characters['out']);
418
419		$doubleChars = [];
420
421		$doubleChars['in'] = [
422		chr(140),
423		chr(156),
424		chr(198),
425		chr(208),
426		chr(222),
427		chr(223),
428		chr(230),
429		chr(240),
430		chr(254),
431		];
432
433		$doubleChars['out'] = ['OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th'];
434
435		$string = str_replace($doubleChars['in'], $doubleChars['out'], $string);
436		}
437
438	5	return $string;
439		}
440
441		/**
442		* Convert any passed string to a url friendly string.
443		* Converts 'My first blog post' to 'my-first-blog-post'
444		*
445		* @param string $string String to urlize.
		0 ignored issues – show introduced 2019-01-09 21:14 UTC by Report Bug Copy Issue Report Incorrect annotations group. Loading history...
446		* @return string Urlized string.
447		*/
448	4	public function urlize(string $string) : string
449		{
450		// Remove all non url friendly characters with the unaccent function
451	4	$string = $this->unaccent($string);
452
453	4	if (function_exists('mb_strtolower')) {
454	4	$string = mb_strtolower($string);
455		} else {
456		$string = strtolower($string);
457		}
458
459		// Remove all none word characters
460	4	$string = preg_replace('/\W/', ' ', $string);
461
462		// More stripping. Replace spaces with dashes
463	4	$string = strtolower(preg_replace(
464	4	'/[^A-Z^a-z^0-9^\/]+/',
465	4	'-',
466	4	preg_replace(
467	4	'/([a-z\d])([A-Z])/',
468	4	'\1_\2',
469	4	preg_replace(
470	4	'/([A-Z]+)([A-Z][a-z])/',
471	4	'\1_\2',
472	4	preg_replace('/::/', '/', $string)
473		)
474		)
475		));
476
477	4	return trim($string, '-');
478		}
479
480		/**
481		* Returns a word in singular form.
482		*
483		* @param string $word The word in plural form.
484		*
485		* @return string The word in singular form.
486		*/
487	532	public function singularize(string $word) : string
488		{
489	532	return $this->singularizer->inflect($word);
490		}
491
492		/**
493		* Returns a word in plural form.
494		*
495		* @param string $word The word in singular form.
496		*
497		* @return string The word in plural form.
498		*/
499	532	public function pluralize(string $word) : string
500		{
501	532	return $this->pluralizer->inflect($word);
502		}
503		}
504

doctrine / inflector

Pull Request — master (#103)

Inflector::capitalize() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like