Duplicate code is one of the most pungent code smells. A rule that is often used is to re-structure code once it is duplicated in three or more places.
Common duplication problems, and corresponding solutions are:
Complex classes like LinkTrait 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. You can also have a look at the cohesion graph to spot any un-connected, or weakly-connected components.
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 LinkTrait, and based on these observations, apply Extract Interface, too.
1 | <?php |
||
38 | trait LinkTrait |
||
39 | { |
||
40 | /** |
||
41 | * @var array a list of defined references in this document. |
||
42 | */ |
||
43 | protected $references = []; |
||
44 | |||
45 | /** |
||
46 | * Remove backslash from escaped characters |
||
47 | * @param $text |
||
48 | * @return string |
||
49 | */ |
||
50 | 52 | protected function replaceEscape($text) |
|
51 | { |
||
52 | 52 | $strtr = []; |
|
53 | 52 | foreach($this->escapeCharacters as $char) { |
|
54 | 52 | $strtr["\\$char"] = $char; |
|
55 | } |
||
56 | 52 | return strtr($text, $strtr); |
|
57 | } |
||
58 | |||
59 | /** |
||
60 | * Parses a link indicated by `[`. |
||
61 | * @marker [ |
||
62 | */ |
||
63 | 49 | protected function parseLink($markdown) |
|
64 | { |
||
65 | 49 | if (!in_array('parseLink', array_slice($this->context, 1)) && ($parts = $this->parseLinkOrImage($markdown)) !== false) { |
|
66 | 49 | list($text, $url, $title, $offset, $key) = $parts; |
|
67 | return [ |
||
68 | [ |
||
69 | 49 | 'link', |
|
70 | 49 | 'text' => $this->parseInline($text), |
|
71 | 49 | 'url' => $url, |
|
72 | 49 | 'title' => $title, |
|
73 | 49 | 'refkey' => $key, |
|
74 | 49 | 'orig' => substr($markdown, 0, $offset), |
|
75 | ], |
||
76 | 49 | $offset |
|
77 | ]; |
||
78 | View Code Duplication | } else { |
|
79 | // remove all starting [ markers to avoid next one to be parsed as link |
||
80 | 10 | $result = '['; |
|
81 | 10 | $i = 1; |
|
82 | 10 | while (isset($markdown[$i]) && $markdown[$i] == '[') { |
|
83 | $result .= '['; |
||
84 | $i++; |
||
85 | } |
||
86 | 10 | return [['text', $result], $i]; |
|
87 | } |
||
88 | } |
||
89 | |||
90 | /** |
||
91 | * Parses an image indicated by `![`. |
||
92 | * @marker ![ |
||
93 | */ |
||
94 | 7 | protected function parseImage($markdown) |
|
95 | { |
||
96 | 7 | if (($parts = $this->parseLinkOrImage(substr($markdown, 1))) !== false) { |
|
97 | 7 | list($text, $url, $title, $offset, $key) = $parts; |
|
98 | |||
99 | return [ |
||
100 | [ |
||
101 | 7 | 'image', |
|
102 | 7 | 'text' => $text, |
|
103 | 7 | 'url' => $url, |
|
104 | 7 | 'title' => $title, |
|
105 | 7 | 'refkey' => $key, |
|
106 | 7 | 'orig' => substr($markdown, 0, $offset + 1), |
|
107 | ], |
||
108 | 7 | $offset + 1 |
|
109 | ]; |
||
110 | View Code Duplication | } else { |
|
111 | // remove all starting [ markers to avoid next one to be parsed as link |
||
112 | 3 | $result = '!'; |
|
113 | 3 | $i = 1; |
|
114 | 3 | while (isset($markdown[$i]) && $markdown[$i] == '[') { |
|
115 | 3 | $result .= '['; |
|
116 | 3 | $i++; |
|
117 | } |
||
118 | 3 | return [['text', $result], $i]; |
|
119 | } |
||
120 | } |
||
121 | |||
122 | 49 | protected function parseLinkOrImage($markdown) |
|
123 | { |
||
124 | 49 | if (strpos($markdown, ']') !== false && preg_match('/\[((?>[^\]\[]+|(?R))*)\]/', $markdown, $textMatches)) { // TODO improve bracket regex |
|
125 | 49 | $text = $textMatches[1]; |
|
126 | 49 | $offset = strlen($textMatches[0]); |
|
127 | 49 | $markdown = substr($markdown, $offset); |
|
128 | |||
129 | $pattern = <<<REGEXP |
||
130 | /(?(R) # in case of recursion match parentheses |
||
131 | \(((?>[^\s()]+)|(?R))*\) |
||
132 | | # else match a link with title |
||
133 | ^\(\s*(((?>[^\s()]+)|(?R))*)(\s+"(.*?)")?\s*\) |
||
134 | 49 | )/x |
|
135 | REGEXP; |
||
136 | 49 | if (preg_match($pattern, $markdown, $refMatches)) { |
|
137 | // inline link |
||
138 | return [ |
||
139 | 33 | $text, |
|
140 | 33 | isset($refMatches[2]) ? $this->replaceEscape($refMatches[2]) : '', // url |
|
141 | 33 | empty($refMatches[5]) ? null: $refMatches[5], // title |
|
142 | 33 | $offset + strlen($refMatches[0]), // offset |
|
143 | null, // reference key |
||
144 | ]; |
||
145 | 39 | } elseif (preg_match('/^([ \n]?\[(.*?)\])?/s', $markdown, $refMatches)) { |
|
146 | // reference style link |
||
147 | 39 | if (empty($refMatches[2])) { |
|
148 | 32 | $key = strtolower($text); |
|
149 | } else { |
||
150 | 17 | $key = strtolower($refMatches[2]); |
|
151 | } |
||
152 | return [ |
||
153 | 39 | $text, |
|
154 | null, // url |
||
155 | null, // title |
||
156 | 39 | $offset + strlen($refMatches[0]), // offset |
|
157 | 39 | $key, |
|
158 | ]; |
||
159 | } |
||
160 | } |
||
161 | 3 | return false; |
|
162 | } |
||
163 | |||
164 | /** |
||
165 | * Parses inline HTML. |
||
166 | * @marker < |
||
167 | */ |
||
168 | 30 | protected function parseLt($text) |
|
169 | { |
||
170 | 30 | if (strpos($text, '>') !== false) { |
|
171 | 26 | if (!in_array('parseLink', $this->context)) { // do not allow links in links |
|
172 | 26 | View Code Duplication | if (preg_match('/^<([^\s]*?@[^\s]*?\.\w+?)>/', $text, $matches)) { |
173 | // email address |
||
174 | return [ |
||
175 | 3 | ['email', $this->replaceEscape($matches[1])], |
|
176 | 3 | strlen($matches[0]) |
|
177 | ]; |
||
178 | 26 | } elseif (preg_match('/^<([a-z]{3,}:\/\/[^\s]+?)>/', $text, $matches)) { |
|
179 | // URL |
||
180 | return [ |
||
181 | 10 | ['url', $this->replaceEscape($matches[1])], |
|
182 | 10 | strlen($matches[0]) |
|
183 | ]; |
||
184 | } |
||
185 | } |
||
186 | // try inline HTML if it was neither a URL nor email if HtmlTrait is included. |
||
187 | 16 | if (method_exists($this, 'parseInlineHtml')) { |
|
188 | 16 | return $this->parseInlineHtml($text); |
|
189 | } |
||
190 | } |
||
191 | 11 | return [['text', '<'], 1]; |
|
192 | } |
||
193 | |||
194 | 3 | protected function renderEmail($block) |
|
199 | |||
200 | 10 | View Code Duplication | protected function renderUrl($block) |
208 | |||
209 | 39 | protected function lookupReference($key) |
|
217 | |||
218 | 33 | protected function renderLink($block) |
|
219 | { |
||
220 | 33 | View Code Duplication | if (isset($block['refkey'])) { |
221 | 24 | if (($ref = $this->lookupReference($block['refkey'])) !== false) { |
|
222 | 19 | $block = array_merge($block, $ref); |
|
223 | } else { |
||
224 | 11 | return $block['orig']; |
|
225 | } |
||
226 | } |
||
227 | 32 | return '<a href="' . htmlspecialchars($block['url'], ENT_COMPAT | ENT_HTML401, 'UTF-8') . '"' |
|
228 | 32 | . (empty($block['title']) ? '' : ' title="' . htmlspecialchars($block['title'], ENT_COMPAT | ENT_HTML401 | ENT_SUBSTITUTE, 'UTF-8') . '"') |
|
229 | 32 | . '>' . $this->renderAbsy($block['text']) . '</a>'; |
|
230 | } |
||
231 | |||
232 | 4 | protected function renderImage($block) |
|
233 | { |
||
234 | 4 | View Code Duplication | if (isset($block['refkey'])) { |
235 | 2 | if (($ref = $this->lookupReference($block['refkey'])) !== false) { |
|
236 | $block = array_merge($block, $ref); |
||
237 | } else { |
||
238 | 2 | return $block['orig']; |
|
239 | } |
||
240 | } |
||
241 | 4 | return '<img src="' . htmlspecialchars($block['url'], ENT_COMPAT | ENT_HTML401, 'UTF-8') . '"' |
|
242 | 4 | . ' alt="' . htmlspecialchars($block['text'], ENT_COMPAT | ENT_HTML401 | ENT_SUBSTITUTE, 'UTF-8') . '"' |
|
243 | 4 | . (empty($block['title']) ? '' : ' title="' . htmlspecialchars($block['title'], ENT_COMPAT | ENT_HTML401 | ENT_SUBSTITUTE, 'UTF-8') . '"') |
|
244 | 4 | . ($this->html5 ? '>' : ' />'); |
|
245 | } |
||
246 | |||
247 | // references |
||
248 | |||
249 | 139 | protected function identifyReference($line) |
|
253 | |||
254 | /** |
||
255 | * Consume link references |
||
256 | */ |
||
257 | 19 | protected function consumeReference($lines, $current) |
|
258 | { |
||
259 | 19 | while (isset($lines[$current]) && preg_match('/^ {0,3}\[(.+?)\]:\s*(.+?)(?:\s+[\(\'"](.+?)[\)\'"])?\s*$/', $lines[$current], $matches)) { |
|
260 | 19 | $label = strtolower($matches[1]); |
|
278 | } |
||
279 |
Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation.
You can also find more detailed suggestions in the “Code” section of your repository.