Total Complexity | 92 |
Total Lines | 426 |
Duplicated Lines | 0 % |
Changes | 0 |
Complex classes like Url often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
While breaking up the class, it is a good idea to analyze how other classes use Url, and based on these observations, apply Extract Interface, too.
1 | <?php |
||
7 | class Url implements \Validate\Contracts\Validate |
||
8 | { |
||
9 | use FakeNameTrait; |
||
10 | |||
11 | public static function toDatabase(string $url) |
||
16 | } |
||
17 | |||
18 | public static function toUser($url) |
||
19 | { |
||
20 | return 'https://'.$url; |
||
21 | } |
||
22 | |||
23 | public static function validate($url) |
||
24 | { |
||
25 | if (strpos($url, ' ') !== false) { |
||
26 | return false; |
||
27 | } |
||
28 | return true; |
||
29 | } |
||
30 | |||
31 | public static function break(string $url) |
||
34 | } |
||
35 | |||
36 | public static function isSame(string $to, string $from) |
||
37 | { |
||
38 | return (self::toDatabase($to)===self::toDatabase($from)); |
||
39 | } |
||
40 | |||
41 | |||
42 | /** |
||
43 | * Given a URL calculates the page's directory |
||
44 | * |
||
45 | * @params string $url target URL |
||
46 | * @return string Directory |
||
47 | */ |
||
48 | public function parseDir($url) { |
||
49 | $slash = strrpos($url,'/'); |
||
50 | return substr($url,0,$slash+1); |
||
51 | } |
||
52 | |||
53 | /** |
||
54 | * Link Checking Functions |
||
55 | */ |
||
56 | |||
57 | /** |
||
58 | * Uniformly cleans a link to avoid duplicates |
||
59 | * |
||
60 | * 1. Changes relative links to absolute (/bar to http://www.foo.com/bar) |
||
61 | * 2. Removes anchor tags (foo.html#bar to foo.html) |
||
62 | * 3. Adds trailing slash if directory (foo.com/bar to foo.com/bar/) |
||
63 | * 4. Adds www if there is not a subdomain (foo.com to www.foo.com but not bar.foo.com) |
||
64 | * |
||
65 | * @params string $relativeUrl link to clean |
||
66 | * @parmas string $baseUrl directory of parent (linking) page |
||
67 | * @return strin cleaned link |
||
|
|||
68 | */ |
||
69 | public function cleanLink($relativeUrl, $baseUrl) { |
||
70 | |||
71 | $relativeUrl = self::urlToAbsolute($baseUrl, $relativeUrl); //make them absolute, not relative |
||
72 | |||
73 | if (stripos($relativeUrl,'#') != FALSE) { |
||
74 | $relativeUrl = substr($relativeUrl,0,stripos($relativeUrl,'#')); //remove anchors |
||
75 | } |
||
76 | |||
77 | if (!preg_match('#(^http://(.*)/$)|http://(.*)/(.*)\.([A-Za-z0-9]+)|http://(.*)/([^\?\#]*)(\?|\#)([^/]*)#i',$relativeUrl)) { |
||
78 | $relativeUrl .= '/'; |
||
79 | } |
||
80 | |||
81 | $relativeUrl = preg_replace('#http://([^.]+).([a-zA-z]{3})/#i','http://www.$1.$2/',$relativeUrl); |
||
82 | return $relativeUrl; |
||
83 | } |
||
84 | |||
85 | |||
86 | /** |
||
87 | * Performs a regular expression to see if a given link is an image |
||
88 | * |
||
89 | * @params string $link target link |
||
90 | * @return bool true on image, false on anything else |
||
91 | */ |
||
92 | public static function isImage($link) { |
||
93 | if (preg_match('%\.(gif|jpe?g|png|bmp)$%i',$link)) return true; |
||
94 | else return false; |
||
95 | } |
||
96 | |||
97 | /** |
||
98 | * Checks to see that a given link is within the domain/host whitelist |
||
99 | * |
||
100 | * Improved from original to use regular expression and match hosts. |
||
101 | * |
||
102 | * @params string $link target link |
||
103 | * @return bool true if out of domain, false if on domain whitelist |
||
104 | */ |
||
105 | public static function outOfDomain($link, $domainArray) { |
||
106 | if (!is_array($domainArray)) { |
||
107 | $domainArray[] = $domainArray; |
||
108 | } |
||
109 | |||
110 | // get host name from URL |
||
111 | preg_match("/^(http:\/\/)?([^\/]+)/i", $link, $matches); |
||
112 | $host = $matches[2]; |
||
113 | // echo "<br />host: $host"; |
||
114 | // get last two segments of host name |
||
115 | // preg_match("/[^\.\/]+\.[^\.\/]+$/", $host, $matches); |
||
116 | foreach ($domainArray as $domain) { |
||
117 | if ($domain == $host) { |
||
118 | return FALSE; |
||
119 | } |
||
120 | } |
||
121 | return TRUE; |
||
122 | } |
||
123 | |||
124 | /** |
||
125 | * Checks to see that a given link matches a pattern in the exclude list |
||
126 | * |
||
127 | * @params string $link target link |
||
128 | * @return bool true if matches exclude, false if no match |
||
129 | */ |
||
130 | public function excludeByPattern($link, $excludedArray = []) { |
||
131 | if (!is_array($excludedArray)) { |
||
132 | $excludedArray[] = $excludedArray; |
||
133 | } |
||
134 | |||
135 | foreach ($excludedArray as $pattern) { |
||
136 | if ( preg_match($pattern, urldecode($link)) ) { |
||
137 | echo "<p>matched exclude pattern <b>$pattern</b> in ".urldecode($link)."</p>"; |
||
138 | return TRUE; |
||
139 | } |
||
140 | } |
||
141 | return FALSE; |
||
142 | } |
||
143 | |||
144 | /** |
||
145 | * Checks to see if a given link is in fact a mailto: link |
||
146 | * |
||
147 | * @params string $link Link to check |
||
148 | * @return bool true on mailto:, false on everything else |
||
149 | */ |
||
150 | public static function isMailto($link) { |
||
151 | if (stripos($link,'mailto:')===FALSE) return false; |
||
152 | else return true; |
||
153 | } |
||
154 | |||
155 | /* Depreciated (I think) |
||
156 | |||
157 | public function count_slashes($url) { |
||
158 | if (strlen($url)<7) return 0; |
||
159 | return substr_count($url,'/',7); |
||
160 | } |
||
161 | |||
162 | public function get_slashes($url) { |
||
163 | if (preg_match_all('#/#',$url,$matches,PREG_OFFSET_CAPTURE,7)) return $matches[0]; |
||
164 | else return array(); |
||
165 | } |
||
166 | */ |
||
167 | |||
168 | /** |
||
169 | * Converts a relative URL (/bar) to an absolute URL (http://www.foo.com/bar) |
||
170 | * |
||
171 | * Inspired from code available at http://nadeausoftware.com/node/79, |
||
172 | * Code distributed under OSI BSD (http://www.opensource.org/licenses/bsd-license.php) |
||
173 | * |
||
174 | * @params string $baseUrl Directory of linking page |
||
175 | * @params string $relativeURL URL to convert to absolute |
||
176 | * @return string Absolute URL |
||
177 | */ |
||
178 | public static function urlToAbsolute( $baseUrl, $relativeUrl ) { |
||
179 | // If relative URL has a scheme, clean path and return. |
||
180 | $r = self::splitUrl( $relativeUrl ); |
||
181 | if ( $r === FALSE ) { |
||
182 | return FALSE; |
||
183 | } |
||
184 | |||
185 | |||
186 | if ( !empty( $r['scheme'] ) ) |
||
187 | { |
||
188 | if ( !empty( $r['path'] ) && $r['path'][0] == '/' ) { |
||
189 | $r['path'] = self::urlRemoveDotSegments( $r['path'] ); |
||
190 | } |
||
191 | |||
192 | return self::joinUrl( $r ); |
||
193 | } |
||
194 | |||
195 | // Make sure the base URL is absolute. |
||
196 | $b = self::splitUrl( $baseUrl ); |
||
197 | if ( $b === FALSE || empty( $b['scheme'] ) || empty( $b['host'] ) ) { |
||
198 | return FALSE; |
||
199 | } |
||
200 | |||
201 | $r['scheme'] = $b['scheme']; |
||
202 | |||
203 | // If relative URL has an authority, clean path and return. |
||
204 | if ( isset( $r['host'] ) ) |
||
205 | { |
||
206 | if ( !empty( $r['path'] ) ) { |
||
207 | $r['path'] = self::urlRemoveDotSegments( $r['path'] ); |
||
208 | } |
||
209 | |||
210 | return self::joinUrl( $r ); |
||
211 | } |
||
212 | unset( $r['port'] ); |
||
213 | unset( $r['user'] ); |
||
214 | unset( $r['pass'] ); |
||
215 | |||
216 | // Copy base authority. |
||
217 | $r['host'] = $b['host']; |
||
218 | if ( isset( $b['port'] ) ) $r['port'] = $b['port']; |
||
219 | if ( isset( $b['user'] ) ) $r['user'] = $b['user']; |
||
220 | if ( isset( $b['pass'] ) ) $r['pass'] = $b['pass']; |
||
221 | |||
222 | // If relative URL has no path, use base path |
||
223 | if ( empty( $r['path'] ) ) |
||
224 | { |
||
225 | if ( !empty( $b['path'] ) ) { |
||
226 | $r['path'] = $b['path']; |
||
227 | } |
||
228 | |||
229 | if ( !isset( $r['query'] ) && isset( $b['query'] ) ) { |
||
230 | $r['query'] = $b['query']; |
||
231 | } |
||
232 | |||
233 | return self::joinUrl( $r ); |
||
234 | } |
||
235 | |||
236 | // If relative URL path doesn't start with /, merge with base path |
||
237 | if ( $r['path'][0] != '/' ) |
||
238 | { |
||
239 | $base = mb_strrchr( $b['path'], '/', TRUE, 'UTF-8' ); |
||
240 | if ( $base === FALSE ) $base = ''; |
||
241 | $r['path'] = $base . '/' . $r['path']; |
||
242 | } |
||
243 | $r['path'] = self::urlRemoveDotSegments( $r['path'] ); |
||
244 | return self::joinUrl( $r ); |
||
245 | } |
||
246 | |||
247 | /** |
||
248 | * Required public function of URL to absolute |
||
249 | * |
||
250 | * Inspired from code available at http://nadeausoftware.com/node/79, |
||
251 | * Code distributed under OSI BSD (http://www.opensource.org/licenses/bsd-license.php) |
||
252 | * |
||
253 | */ |
||
254 | public static function urlRemoveDotSegments( $path ) { |
||
255 | // multi-byte character explode |
||
256 | $inSegs = preg_split( '!/!u', $path ); |
||
257 | $outSegs = array( ); |
||
258 | foreach ( $inSegs as $seg ) |
||
259 | { |
||
260 | if ( $seg == '' || $seg == '.') { |
||
261 | continue; |
||
262 | } |
||
263 | if ( $seg == '..' ) { |
||
264 | array_pop( $outSegs ); |
||
265 | } else { |
||
266 | array_push( $outSegs, $seg ); |
||
267 | } |
||
268 | } |
||
269 | $outPath = implode( '/', $outSegs ); |
||
270 | if ( $path[0] == '/' ) { |
||
271 | $outPath = '/' . $outPath; |
||
272 | } |
||
273 | |||
274 | // compare last multi-byte character against '/' |
||
275 | if ( $outPath != '/' && |
||
276 | (mb_strlen($path)-1) == mb_strrpos( $path, '/', 'UTF-8' ) ) { |
||
277 | $outPath .= '/'; |
||
278 | } |
||
279 | |||
280 | return $outPath; |
||
281 | } |
||
282 | |||
283 | /** |
||
284 | * Required public function of URL to absolute |
||
285 | * |
||
286 | * Inspired from code available at http://nadeausoftware.com/node/79, |
||
287 | * Code distributed under OSI BSD (http://www.opensource.org/licenses/bsd-license.php) |
||
288 | * |
||
289 | */ |
||
290 | public static function splitUrl( $url, $decode=TRUE ) |
||
291 | { |
||
292 | $m = []; |
||
293 | $xunressub = 'a-zA-Z\d\-._~\!$&\'()*+,;='; |
||
294 | $xpchar = $xunressub . ':@%'; |
||
295 | |||
296 | $xscheme = '([a-zA-Z][a-zA-Z\d+-.]*)'; |
||
297 | |||
298 | $xuserinfo = '(([' . $xunressub . '%]*)' . |
||
299 | '(:([' . $xunressub . ':%]*))?)'; |
||
300 | |||
301 | $xipv4 = '(\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3})'; |
||
302 | |||
303 | $xipv6 = '(\[([a-fA-F\d.:]+)\])'; |
||
304 | |||
305 | $xhost_name = '([a-zA-Z%]+)'; |
||
306 | // $xhost_name = '([a-zA-Z\d-.%]+)'; @todo alterado pq tava dando erro nesse parser |
||
307 | |||
308 | $xhost = '(' . $xhost_name . '|' . $xipv4 . '|' . $xipv6 . ')'; |
||
309 | $xport = '(\d*)'; |
||
310 | $xauthority = '((' . $xuserinfo . '@)?' . $xhost . |
||
311 | '?(:' . $xport . ')?)'; |
||
312 | |||
313 | $xslash_seg = '(/[' . $xpchar . ']*)'; |
||
314 | $xpath_authabs = '((//' . $xauthority . ')((/[' . $xpchar . ']*)*))'; |
||
315 | $xpath_rel = '([' . $xpchar . ']+' . $xslash_seg . '*)'; |
||
316 | $xpath_abs = '(/(' . $xpath_rel . ')?)'; |
||
317 | $xapath = '(' . $xpath_authabs . '|' . $xpath_abs . |
||
318 | '|' . $xpath_rel . ')'; |
||
319 | |||
320 | $xqueryfrag = '([' . $xpchar . '/?' . ']*)'; |
||
321 | |||
322 | $xurl = '^(' . $xscheme . ':)?' . $xapath . '?' . |
||
323 | '(\?' . $xqueryfrag . ')?(#' . $xqueryfrag . ')?$'; |
||
324 | |||
325 | |||
326 | // Split the URL into components. |
||
327 | if ( !preg_match( '!' . $xurl . '!', $url, $m ) ) { |
||
328 | return FALSE; |
||
329 | } |
||
330 | |||
331 | if ( !empty($m[2]) ) $parts['scheme'] = strtolower($m[2]); |
||
332 | |||
333 | if ( !empty($m[7]) ) { |
||
334 | if ( isset( $m[9] ) ) $parts['user'] = $m[9]; |
||
335 | else $parts['user'] = ''; |
||
336 | } |
||
337 | if ( !empty($m[10]) ) $parts['pass'] = $m[11]; |
||
338 | |||
339 | if ( !empty($m[13]) ) $h=$parts['host'] = $m[13]; |
||
340 | else if ( !empty($m[14]) ) $parts['host'] = $m[14]; |
||
341 | else if ( !empty($m[16]) ) $parts['host'] = $m[16]; |
||
342 | else if ( !empty( $m[5] ) ) $parts['host'] = ''; |
||
343 | if ( !empty($m[17]) ) $parts['port'] = $m[18]; |
||
344 | |||
345 | if ( !empty($m[19]) ) $parts['path'] = $m[19]; |
||
346 | else if ( !empty($m[21]) ) $parts['path'] = $m[21]; |
||
347 | else if ( !empty($m[25]) ) $parts['path'] = $m[25]; |
||
348 | |||
349 | if ( !empty($m[27]) ) $parts['query'] = $m[28]; |
||
350 | if ( !empty($m[29]) ) $parts['fragment']= $m[30]; |
||
351 | |||
352 | if ( !$decode ) |
||
353 | return $parts; |
||
354 | if ( !empty($parts['user']) ) |
||
355 | $parts['user'] = rawurldecode( $parts['user'] ); |
||
356 | if ( !empty($parts['pass']) ) |
||
357 | $parts['pass'] = rawurldecode( $parts['pass'] ); |
||
358 | if ( !empty($parts['path']) ) |
||
359 | $parts['path'] = rawurldecode( $parts['path'] ); |
||
360 | if ( isset($h) ) |
||
361 | $parts['host'] = rawurldecode( $parts['host'] ); |
||
362 | if ( !empty($parts['query']) ) |
||
363 | $parts['query'] = rawurldecode( $parts['query'] ); |
||
364 | if ( !empty($parts['fragment']) ) |
||
365 | $parts['fragment'] = rawurldecode( $parts['fragment'] ); |
||
366 | return $parts; |
||
367 | } |
||
368 | |||
369 | /** |
||
370 | * Required public function of URL to absolute |
||
371 | * |
||
372 | * Inspired from code available at http://nadeausoftware.com/node/79, |
||
373 | * Code distributed under OSI BSD (http://www.opensource.org/licenses/bsd-license.php) |
||
374 | * |
||
375 | */ |
||
376 | public static function joinUrl( $parts, $encode=TRUE ) |
||
433 | } |
||
434 | |||
435 | } |
||
436 |
The issue could also be caused by a filter entry in the build configuration. If the path has been excluded in your configuration, e.g.
excluded_paths: ["lib/*"]
, you can move it to the dependency path list as follows:For further information see https://scrutinizer-ci.com/docs/tools/php/php-scrutinizer/#list-dependency-paths