@@ -47,7 +47,7 @@ |
||
47 | 47 | * node object. |
48 | 48 | * |
49 | 49 | * @param AbstractNode $node |
50 | - * @return array|Collection |
|
50 | + * @return Collection |
|
51 | 51 | */ |
52 | 52 | public function find(AbstractNode $node) |
53 | 53 | { |
@@ -15,361 +15,361 @@ |
||
15 | 15 | class Selector |
16 | 16 | { |
17 | 17 | |
18 | - /** |
|
19 | - * Pattern of CSS selectors, modified from 'mootools' |
|
20 | - * |
|
21 | - * @var string |
|
22 | - */ |
|
23 | - protected $pattern = "/([\w-:\*>]*)(?:\#([\w-]+)|\.([\w-]+))?(?:\[@?(!?[\w-:]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is"; |
|
24 | - |
|
25 | - protected $selectors = []; |
|
26 | - |
|
27 | - /** |
|
28 | - * Constructs with the selector string |
|
29 | - * |
|
30 | - * @param string $selector |
|
31 | - */ |
|
32 | - public function __construct($selector) |
|
33 | - { |
|
34 | - $this->parseSelectorString($selector); |
|
35 | - } |
|
36 | - |
|
37 | - /** |
|
38 | - * Returns the selectors that where found in __construct |
|
39 | - * |
|
40 | - * @return array |
|
41 | - */ |
|
42 | - public function getSelectors() |
|
43 | - { |
|
44 | - return $this->selectors; |
|
45 | - } |
|
46 | - |
|
47 | - /** |
|
48 | - * Attempts to find the selectors starting from the given |
|
49 | - * node object. |
|
50 | - * |
|
51 | - * @param AbstractNode $node |
|
52 | - * @return array|Collection |
|
53 | - */ |
|
54 | - public function find(AbstractNode $node) |
|
55 | - { |
|
56 | - $results = new Collection; |
|
57 | - foreach ($this->selectors as $selector) { |
|
58 | - $nodes = [$node]; |
|
59 | - if (count($selector) == 0) { |
|
60 | - continue; |
|
61 | - } |
|
62 | - |
|
63 | - $options = []; |
|
64 | - foreach ($selector as $rule) { |
|
65 | - if ($rule['alterNext']) { |
|
66 | - $options[] = $this->alterNext($rule); |
|
67 | - continue; |
|
68 | - } |
|
69 | - $nodes = $this->seek($nodes, $rule, $options); |
|
70 | - // clear the options |
|
71 | - $options = []; |
|
72 | - } |
|
73 | - |
|
74 | - // this is the final set of nodes |
|
75 | - foreach ($nodes as $result) { |
|
76 | - $results[] = $result; |
|
77 | - } |
|
78 | - } |
|
79 | - |
|
80 | - return $results; |
|
81 | - } |
|
82 | - |
|
83 | - /** |
|
84 | - * Parses the selector string |
|
85 | - * |
|
86 | - * @param string $selector |
|
87 | - */ |
|
88 | - protected function parseSelectorString($selector) |
|
89 | - { |
|
90 | - $matches = []; |
|
91 | - preg_match_all($this->pattern, trim($selector).' ', $matches, PREG_SET_ORDER); |
|
92 | - |
|
93 | - // skip tbody |
|
94 | - $result = []; |
|
95 | - foreach ($matches as $match) { |
|
96 | - // default values |
|
97 | - $tag = strtolower(trim($match[1])); |
|
98 | - $operator = '='; |
|
99 | - $key = null; |
|
100 | - $value = null; |
|
101 | - $noKey = false; |
|
102 | - $alterNext = false; |
|
103 | - |
|
104 | - // check for elements that alter the behavior of the next element |
|
105 | - if ($tag == '>') { |
|
106 | - $alterNext = true; |
|
107 | - } |
|
108 | - |
|
109 | - // check for id selector |
|
110 | - if ( ! empty($match[2])) { |
|
111 | - $key = 'id'; |
|
112 | - $value = $match[2]; |
|
113 | - } |
|
114 | - |
|
115 | - // check for class selector |
|
116 | - if ( ! empty($match[3])) { |
|
117 | - $key = 'class'; |
|
118 | - $value = $match[3]; |
|
119 | - } |
|
120 | - |
|
121 | - // and final attribute selector |
|
122 | - if ( ! empty($match[4])) { |
|
123 | - $key = strtolower($match[4]); |
|
124 | - } |
|
125 | - if ( ! empty($match[5])) { |
|
126 | - $operator = $match[5]; |
|
127 | - } |
|
128 | - if ( ! empty($match[6])) { |
|
129 | - $value = $match[6]; |
|
130 | - } |
|
131 | - |
|
132 | - // check for elements that do not have a specified attribute |
|
133 | - if (isset($key[0]) && $key[0] == '!') { |
|
134 | - $key = substr($key, 1); |
|
135 | - $noKey = true; |
|
136 | - } |
|
137 | - |
|
138 | - $result[] = [ |
|
139 | - 'tag' => $tag, |
|
140 | - 'key' => $key, |
|
141 | - 'value' => $value, |
|
142 | - 'operator' => $operator, |
|
143 | - 'noKey' => $noKey, |
|
144 | - 'alterNext' => $alterNext, |
|
145 | - ]; |
|
146 | - if (trim($match[7]) == ',') { |
|
147 | - $this->selectors[] = $result; |
|
148 | - $result = []; |
|
149 | - } |
|
150 | - } |
|
151 | - |
|
152 | - // save last results |
|
153 | - if (count($result) > 0) { |
|
154 | - $this->selectors[] = $result; |
|
155 | - } |
|
156 | - } |
|
157 | - |
|
158 | - /** |
|
159 | - * Attempts to find all children that match the rule |
|
160 | - * given. |
|
161 | - * |
|
162 | - * @param array $nodes |
|
163 | - * @param array $rule |
|
164 | - * @param array $options |
|
165 | - * @return array |
|
166 | - * @recursive |
|
167 | - */ |
|
168 | - protected function seek(array $nodes, array $rule, array $options) |
|
169 | - { |
|
170 | - // XPath index |
|
171 | - if (count($rule['tag']) > 0 && |
|
172 | - count($rule['key']) > 0 && |
|
173 | - is_numeric($rule['key']) |
|
174 | - ) { |
|
175 | - $count = 0; |
|
176 | - /** @var AbstractNode $node */ |
|
177 | - foreach ($nodes as $node) { |
|
178 | - if ($rule['tag'] == '*' || |
|
179 | - $rule['tag'] == $node->getTag()->name()) { |
|
180 | - ++$count; |
|
181 | - if ($count == $rule['key']) { |
|
182 | - // found the node we wanted |
|
183 | - return [$node]; |
|
184 | - } |
|
185 | - } |
|
186 | - } |
|
187 | - |
|
188 | - return []; |
|
189 | - } |
|
190 | - |
|
191 | - $options = $this->flattenOptions($options); |
|
192 | - |
|
193 | - $return = []; |
|
194 | - /** @var InnerNode $node */ |
|
195 | - foreach ($nodes as $node) { |
|
196 | - // check if we are a leaf |
|
197 | - if ($node instanceof LeafNode || |
|
198 | - ! $node->hasChildren()) { |
|
199 | - continue; |
|
200 | - } |
|
201 | - |
|
202 | - $children = []; |
|
203 | - $child = $node->firstChild(); |
|
204 | - while ( ! is_null($child)) { |
|
205 | - // wild card, grab all |
|
206 | - if ($rule['tag'] == '*' && is_null($rule['key'])) { |
|
207 | - $return[] = $child; |
|
208 | - try { |
|
209 | - $child = $node->nextChild($child->id()); |
|
210 | - } catch (ChildNotFoundException $e) { |
|
211 | - // no more children |
|
212 | - $child = null; |
|
213 | - } |
|
214 | - continue; |
|
215 | - } |
|
216 | - |
|
217 | - $pass = true; |
|
218 | - // check tag |
|
219 | - if ( ! empty($rule['tag']) && $rule['tag'] != $child->getTag()->name() && |
|
220 | - $rule['tag'] != '*' |
|
221 | - ) { |
|
222 | - // child failed tag check |
|
223 | - $pass = false; |
|
224 | - } |
|
225 | - |
|
226 | - // check key |
|
227 | - if ($pass && ! is_null($rule['key'])) { |
|
228 | - if ($rule['noKey']) { |
|
229 | - if ( ! is_null($child->getAttribute($rule['key']))) { |
|
230 | - $pass = false; |
|
231 | - } |
|
232 | - } else { |
|
233 | - if ($rule['key'] != 'plaintext' && |
|
234 | - is_null($child->getAttribute($rule['key'])) |
|
235 | - ) { |
|
236 | - $pass = false; |
|
237 | - } |
|
238 | - } |
|
239 | - } |
|
240 | - |
|
241 | - // compare values |
|
242 | - if ($pass && ! is_null($rule['key']) && |
|
243 | - ! is_null($rule['value']) && $rule['value'] != '*' |
|
244 | - ) { |
|
245 | - if ($rule['key'] == 'plaintext') { |
|
246 | - // plaintext search |
|
247 | - $nodeValue = $child->text(); |
|
248 | - } else { |
|
249 | - // normal search |
|
250 | - $nodeValue = $child->getAttribute($rule['key']); |
|
251 | - } |
|
252 | - |
|
253 | - $check = $this->match($rule['operator'], $rule['value'], $nodeValue); |
|
254 | - |
|
255 | - // handle multiple classes |
|
256 | - if ( ! $check && $rule['key'] == 'class') { |
|
257 | - $childClasses = explode(' ', $child->getAttribute('class')); |
|
258 | - foreach ($childClasses as $class) { |
|
259 | - if ( ! empty($class)) { |
|
260 | - $check = $this->match($rule['operator'], $rule['value'], $class); |
|
261 | - } |
|
262 | - if ($check) { |
|
263 | - break; |
|
264 | - } |
|
265 | - } |
|
266 | - } |
|
267 | - |
|
268 | - if ( ! $check) { |
|
269 | - $pass = false; |
|
270 | - } |
|
271 | - } |
|
272 | - |
|
273 | - if ($pass) { |
|
274 | - // it passed all checks |
|
275 | - $return[] = $child; |
|
276 | - } else { |
|
277 | - // this child failed to be matched |
|
278 | - if ($child instanceof InnerNode && |
|
279 | - $child->hasChildren()) { |
|
280 | - // we still want to check its children |
|
281 | - $children[] = $child; |
|
282 | - } |
|
283 | - } |
|
284 | - |
|
285 | - try { |
|
286 | - // get next child |
|
287 | - $child = $node->nextChild($child->id()); |
|
288 | - } catch (ChildNotFoundException $e) { |
|
289 | - // no more children |
|
290 | - $child = null; |
|
291 | - } |
|
292 | - } |
|
293 | - |
|
294 | - if (( ! isset($options['checkGrandChildren']) || |
|
295 | - $options['checkGrandChildren']) |
|
296 | - && count($children) > 0 |
|
297 | - ) { |
|
298 | - // we have children that failed but are not leaves. |
|
299 | - $matches = $this->seek($children, $rule, $options); |
|
300 | - foreach ($matches as $match) { |
|
301 | - $return[] = $match; |
|
302 | - } |
|
303 | - } |
|
304 | - } |
|
305 | - |
|
306 | - return $return; |
|
307 | - } |
|
308 | - |
|
309 | - /** |
|
310 | - * Attempts to match the given arguments with the given operator. |
|
311 | - * |
|
312 | - * @param string $operator |
|
313 | - * @param string $pattern |
|
314 | - * @param string $value |
|
315 | - * @return bool |
|
316 | - */ |
|
317 | - protected function match($operator, $pattern, $value) |
|
318 | - { |
|
319 | - $value = strtolower($value); |
|
320 | - $pattern = strtolower($pattern); |
|
321 | - switch ($operator) { |
|
322 | - case '=': |
|
323 | - return $value === $pattern; |
|
324 | - case '!=': |
|
325 | - return $value !== $pattern; |
|
326 | - case '^=': |
|
327 | - return preg_match('/^'.preg_quote($pattern, '/').'/', $value); |
|
328 | - case '$=': |
|
329 | - return preg_match('/'.preg_quote($pattern, '/').'$/', $value); |
|
330 | - case '*=': |
|
331 | - if ($pattern[0] == '/') { |
|
332 | - return preg_match($pattern, $value); |
|
333 | - } |
|
334 | - |
|
335 | - return preg_match("/".$pattern."/i", $value); |
|
336 | - } |
|
337 | - |
|
338 | - return false; |
|
339 | - } |
|
340 | - |
|
341 | - /** |
|
342 | - * Attempts to figure out what the alteration will be for |
|
343 | - * the next element. |
|
344 | - * |
|
345 | - * @param array $rule |
|
346 | - * @return array |
|
347 | - */ |
|
348 | - protected function alterNext($rule) |
|
349 | - { |
|
350 | - $options = []; |
|
351 | - if ($rule['tag'] == '>') { |
|
352 | - $options['checkGrandChildren'] = false; |
|
353 | - } |
|
354 | - |
|
355 | - return $options; |
|
356 | - } |
|
357 | - |
|
358 | - /** |
|
359 | - * Flattens the option array. |
|
360 | - * |
|
361 | - * @param array $optionsArray |
|
362 | - * @return array |
|
363 | - */ |
|
364 | - protected function flattenOptions(array $optionsArray) |
|
365 | - { |
|
366 | - $options = []; |
|
367 | - foreach ($optionsArray as $optionArray) { |
|
368 | - foreach ($optionArray as $key => $option) { |
|
369 | - $options[$key] = $option; |
|
370 | - } |
|
371 | - } |
|
372 | - |
|
373 | - return $options; |
|
374 | - } |
|
18 | + /** |
|
19 | + * Pattern of CSS selectors, modified from 'mootools' |
|
20 | + * |
|
21 | + * @var string |
|
22 | + */ |
|
23 | + protected $pattern = "/([\w-:\*>]*)(?:\#([\w-]+)|\.([\w-]+))?(?:\[@?(!?[\w-:]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is"; |
|
24 | + |
|
25 | + protected $selectors = []; |
|
26 | + |
|
27 | + /** |
|
28 | + * Constructs with the selector string |
|
29 | + * |
|
30 | + * @param string $selector |
|
31 | + */ |
|
32 | + public function __construct($selector) |
|
33 | + { |
|
34 | + $this->parseSelectorString($selector); |
|
35 | + } |
|
36 | + |
|
37 | + /** |
|
38 | + * Returns the selectors that where found in __construct |
|
39 | + * |
|
40 | + * @return array |
|
41 | + */ |
|
42 | + public function getSelectors() |
|
43 | + { |
|
44 | + return $this->selectors; |
|
45 | + } |
|
46 | + |
|
47 | + /** |
|
48 | + * Attempts to find the selectors starting from the given |
|
49 | + * node object. |
|
50 | + * |
|
51 | + * @param AbstractNode $node |
|
52 | + * @return array|Collection |
|
53 | + */ |
|
54 | + public function find(AbstractNode $node) |
|
55 | + { |
|
56 | + $results = new Collection; |
|
57 | + foreach ($this->selectors as $selector) { |
|
58 | + $nodes = [$node]; |
|
59 | + if (count($selector) == 0) { |
|
60 | + continue; |
|
61 | + } |
|
62 | + |
|
63 | + $options = []; |
|
64 | + foreach ($selector as $rule) { |
|
65 | + if ($rule['alterNext']) { |
|
66 | + $options[] = $this->alterNext($rule); |
|
67 | + continue; |
|
68 | + } |
|
69 | + $nodes = $this->seek($nodes, $rule, $options); |
|
70 | + // clear the options |
|
71 | + $options = []; |
|
72 | + } |
|
73 | + |
|
74 | + // this is the final set of nodes |
|
75 | + foreach ($nodes as $result) { |
|
76 | + $results[] = $result; |
|
77 | + } |
|
78 | + } |
|
79 | + |
|
80 | + return $results; |
|
81 | + } |
|
82 | + |
|
83 | + /** |
|
84 | + * Parses the selector string |
|
85 | + * |
|
86 | + * @param string $selector |
|
87 | + */ |
|
88 | + protected function parseSelectorString($selector) |
|
89 | + { |
|
90 | + $matches = []; |
|
91 | + preg_match_all($this->pattern, trim($selector).' ', $matches, PREG_SET_ORDER); |
|
92 | + |
|
93 | + // skip tbody |
|
94 | + $result = []; |
|
95 | + foreach ($matches as $match) { |
|
96 | + // default values |
|
97 | + $tag = strtolower(trim($match[1])); |
|
98 | + $operator = '='; |
|
99 | + $key = null; |
|
100 | + $value = null; |
|
101 | + $noKey = false; |
|
102 | + $alterNext = false; |
|
103 | + |
|
104 | + // check for elements that alter the behavior of the next element |
|
105 | + if ($tag == '>') { |
|
106 | + $alterNext = true; |
|
107 | + } |
|
108 | + |
|
109 | + // check for id selector |
|
110 | + if ( ! empty($match[2])) { |
|
111 | + $key = 'id'; |
|
112 | + $value = $match[2]; |
|
113 | + } |
|
114 | + |
|
115 | + // check for class selector |
|
116 | + if ( ! empty($match[3])) { |
|
117 | + $key = 'class'; |
|
118 | + $value = $match[3]; |
|
119 | + } |
|
120 | + |
|
121 | + // and final attribute selector |
|
122 | + if ( ! empty($match[4])) { |
|
123 | + $key = strtolower($match[4]); |
|
124 | + } |
|
125 | + if ( ! empty($match[5])) { |
|
126 | + $operator = $match[5]; |
|
127 | + } |
|
128 | + if ( ! empty($match[6])) { |
|
129 | + $value = $match[6]; |
|
130 | + } |
|
131 | + |
|
132 | + // check for elements that do not have a specified attribute |
|
133 | + if (isset($key[0]) && $key[0] == '!') { |
|
134 | + $key = substr($key, 1); |
|
135 | + $noKey = true; |
|
136 | + } |
|
137 | + |
|
138 | + $result[] = [ |
|
139 | + 'tag' => $tag, |
|
140 | + 'key' => $key, |
|
141 | + 'value' => $value, |
|
142 | + 'operator' => $operator, |
|
143 | + 'noKey' => $noKey, |
|
144 | + 'alterNext' => $alterNext, |
|
145 | + ]; |
|
146 | + if (trim($match[7]) == ',') { |
|
147 | + $this->selectors[] = $result; |
|
148 | + $result = []; |
|
149 | + } |
|
150 | + } |
|
151 | + |
|
152 | + // save last results |
|
153 | + if (count($result) > 0) { |
|
154 | + $this->selectors[] = $result; |
|
155 | + } |
|
156 | + } |
|
157 | + |
|
158 | + /** |
|
159 | + * Attempts to find all children that match the rule |
|
160 | + * given. |
|
161 | + * |
|
162 | + * @param array $nodes |
|
163 | + * @param array $rule |
|
164 | + * @param array $options |
|
165 | + * @return array |
|
166 | + * @recursive |
|
167 | + */ |
|
168 | + protected function seek(array $nodes, array $rule, array $options) |
|
169 | + { |
|
170 | + // XPath index |
|
171 | + if (count($rule['tag']) > 0 && |
|
172 | + count($rule['key']) > 0 && |
|
173 | + is_numeric($rule['key']) |
|
174 | + ) { |
|
175 | + $count = 0; |
|
176 | + /** @var AbstractNode $node */ |
|
177 | + foreach ($nodes as $node) { |
|
178 | + if ($rule['tag'] == '*' || |
|
179 | + $rule['tag'] == $node->getTag()->name()) { |
|
180 | + ++$count; |
|
181 | + if ($count == $rule['key']) { |
|
182 | + // found the node we wanted |
|
183 | + return [$node]; |
|
184 | + } |
|
185 | + } |
|
186 | + } |
|
187 | + |
|
188 | + return []; |
|
189 | + } |
|
190 | + |
|
191 | + $options = $this->flattenOptions($options); |
|
192 | + |
|
193 | + $return = []; |
|
194 | + /** @var InnerNode $node */ |
|
195 | + foreach ($nodes as $node) { |
|
196 | + // check if we are a leaf |
|
197 | + if ($node instanceof LeafNode || |
|
198 | + ! $node->hasChildren()) { |
|
199 | + continue; |
|
200 | + } |
|
201 | + |
|
202 | + $children = []; |
|
203 | + $child = $node->firstChild(); |
|
204 | + while ( ! is_null($child)) { |
|
205 | + // wild card, grab all |
|
206 | + if ($rule['tag'] == '*' && is_null($rule['key'])) { |
|
207 | + $return[] = $child; |
|
208 | + try { |
|
209 | + $child = $node->nextChild($child->id()); |
|
210 | + } catch (ChildNotFoundException $e) { |
|
211 | + // no more children |
|
212 | + $child = null; |
|
213 | + } |
|
214 | + continue; |
|
215 | + } |
|
216 | + |
|
217 | + $pass = true; |
|
218 | + // check tag |
|
219 | + if ( ! empty($rule['tag']) && $rule['tag'] != $child->getTag()->name() && |
|
220 | + $rule['tag'] != '*' |
|
221 | + ) { |
|
222 | + // child failed tag check |
|
223 | + $pass = false; |
|
224 | + } |
|
225 | + |
|
226 | + // check key |
|
227 | + if ($pass && ! is_null($rule['key'])) { |
|
228 | + if ($rule['noKey']) { |
|
229 | + if ( ! is_null($child->getAttribute($rule['key']))) { |
|
230 | + $pass = false; |
|
231 | + } |
|
232 | + } else { |
|
233 | + if ($rule['key'] != 'plaintext' && |
|
234 | + is_null($child->getAttribute($rule['key'])) |
|
235 | + ) { |
|
236 | + $pass = false; |
|
237 | + } |
|
238 | + } |
|
239 | + } |
|
240 | + |
|
241 | + // compare values |
|
242 | + if ($pass && ! is_null($rule['key']) && |
|
243 | + ! is_null($rule['value']) && $rule['value'] != '*' |
|
244 | + ) { |
|
245 | + if ($rule['key'] == 'plaintext') { |
|
246 | + // plaintext search |
|
247 | + $nodeValue = $child->text(); |
|
248 | + } else { |
|
249 | + // normal search |
|
250 | + $nodeValue = $child->getAttribute($rule['key']); |
|
251 | + } |
|
252 | + |
|
253 | + $check = $this->match($rule['operator'], $rule['value'], $nodeValue); |
|
254 | + |
|
255 | + // handle multiple classes |
|
256 | + if ( ! $check && $rule['key'] == 'class') { |
|
257 | + $childClasses = explode(' ', $child->getAttribute('class')); |
|
258 | + foreach ($childClasses as $class) { |
|
259 | + if ( ! empty($class)) { |
|
260 | + $check = $this->match($rule['operator'], $rule['value'], $class); |
|
261 | + } |
|
262 | + if ($check) { |
|
263 | + break; |
|
264 | + } |
|
265 | + } |
|
266 | + } |
|
267 | + |
|
268 | + if ( ! $check) { |
|
269 | + $pass = false; |
|
270 | + } |
|
271 | + } |
|
272 | + |
|
273 | + if ($pass) { |
|
274 | + // it passed all checks |
|
275 | + $return[] = $child; |
|
276 | + } else { |
|
277 | + // this child failed to be matched |
|
278 | + if ($child instanceof InnerNode && |
|
279 | + $child->hasChildren()) { |
|
280 | + // we still want to check its children |
|
281 | + $children[] = $child; |
|
282 | + } |
|
283 | + } |
|
284 | + |
|
285 | + try { |
|
286 | + // get next child |
|
287 | + $child = $node->nextChild($child->id()); |
|
288 | + } catch (ChildNotFoundException $e) { |
|
289 | + // no more children |
|
290 | + $child = null; |
|
291 | + } |
|
292 | + } |
|
293 | + |
|
294 | + if (( ! isset($options['checkGrandChildren']) || |
|
295 | + $options['checkGrandChildren']) |
|
296 | + && count($children) > 0 |
|
297 | + ) { |
|
298 | + // we have children that failed but are not leaves. |
|
299 | + $matches = $this->seek($children, $rule, $options); |
|
300 | + foreach ($matches as $match) { |
|
301 | + $return[] = $match; |
|
302 | + } |
|
303 | + } |
|
304 | + } |
|
305 | + |
|
306 | + return $return; |
|
307 | + } |
|
308 | + |
|
309 | + /** |
|
310 | + * Attempts to match the given arguments with the given operator. |
|
311 | + * |
|
312 | + * @param string $operator |
|
313 | + * @param string $pattern |
|
314 | + * @param string $value |
|
315 | + * @return bool |
|
316 | + */ |
|
317 | + protected function match($operator, $pattern, $value) |
|
318 | + { |
|
319 | + $value = strtolower($value); |
|
320 | + $pattern = strtolower($pattern); |
|
321 | + switch ($operator) { |
|
322 | + case '=': |
|
323 | + return $value === $pattern; |
|
324 | + case '!=': |
|
325 | + return $value !== $pattern; |
|
326 | + case '^=': |
|
327 | + return preg_match('/^'.preg_quote($pattern, '/').'/', $value); |
|
328 | + case '$=': |
|
329 | + return preg_match('/'.preg_quote($pattern, '/').'$/', $value); |
|
330 | + case '*=': |
|
331 | + if ($pattern[0] == '/') { |
|
332 | + return preg_match($pattern, $value); |
|
333 | + } |
|
334 | + |
|
335 | + return preg_match("/".$pattern."/i", $value); |
|
336 | + } |
|
337 | + |
|
338 | + return false; |
|
339 | + } |
|
340 | + |
|
341 | + /** |
|
342 | + * Attempts to figure out what the alteration will be for |
|
343 | + * the next element. |
|
344 | + * |
|
345 | + * @param array $rule |
|
346 | + * @return array |
|
347 | + */ |
|
348 | + protected function alterNext($rule) |
|
349 | + { |
|
350 | + $options = []; |
|
351 | + if ($rule['tag'] == '>') { |
|
352 | + $options['checkGrandChildren'] = false; |
|
353 | + } |
|
354 | + |
|
355 | + return $options; |
|
356 | + } |
|
357 | + |
|
358 | + /** |
|
359 | + * Flattens the option array. |
|
360 | + * |
|
361 | + * @param array $optionsArray |
|
362 | + * @return array |
|
363 | + */ |
|
364 | + protected function flattenOptions(array $optionsArray) |
|
365 | + { |
|
366 | + $options = []; |
|
367 | + foreach ($optionsArray as $optionArray) { |
|
368 | + foreach ($optionArray as $key => $option) { |
|
369 | + $options[$key] = $option; |
|
370 | + } |
|
371 | + } |
|
372 | + |
|
373 | + return $options; |
|
374 | + } |
|
375 | 375 | } |
@@ -57,7 +57,7 @@ discard block |
||
57 | 57 | * new object. |
58 | 58 | * |
59 | 59 | * @param string $str |
60 | - * @return $this |
|
60 | + * @return Dom |
|
61 | 61 | */ |
62 | 62 | public static function load($str) |
63 | 63 | { |
@@ -72,7 +72,7 @@ discard block |
||
72 | 72 | * new object. |
73 | 73 | * |
74 | 74 | * @param string $file |
75 | - * @return $this |
|
75 | + * @return Dom |
|
76 | 76 | */ |
77 | 77 | public static function loadFromFile($file) |
78 | 78 | { |
@@ -88,7 +88,7 @@ discard block |
||
88 | 88 | * |
89 | 89 | * @param string $url |
90 | 90 | * @param CurlInterface $curl |
91 | - * @return $this |
|
91 | + * @return Dom |
|
92 | 92 | */ |
93 | 93 | public static function loadFromUrl($url, CurlInterface $curl = null) |
94 | 94 | { |
@@ -11,102 +11,102 @@ |
||
11 | 11 | final class StaticDom |
12 | 12 | { |
13 | 13 | |
14 | - private static $dom = null; |
|
14 | + private static $dom = null; |
|
15 | 15 | |
16 | - /** |
|
17 | - * Attempts to call the given method on the most recent created dom |
|
18 | - * from bellow. |
|
19 | - * |
|
20 | - * @param string $method |
|
21 | - * @param array $arguments |
|
22 | - * @throws NotLoadedException |
|
23 | - * @return mixed |
|
24 | - */ |
|
25 | - public static function __callStatic($method, $arguments) |
|
26 | - { |
|
27 | - if (self::$dom instanceof Dom) { |
|
28 | - return call_user_func_array([self::$dom, $method], $arguments); |
|
29 | - } else { |
|
30 | - throw new NotLoadedException('The dom is not loaded. Can not call a dom method.'); |
|
31 | - } |
|
32 | - } |
|
16 | + /** |
|
17 | + * Attempts to call the given method on the most recent created dom |
|
18 | + * from bellow. |
|
19 | + * |
|
20 | + * @param string $method |
|
21 | + * @param array $arguments |
|
22 | + * @throws NotLoadedException |
|
23 | + * @return mixed |
|
24 | + */ |
|
25 | + public static function __callStatic($method, $arguments) |
|
26 | + { |
|
27 | + if (self::$dom instanceof Dom) { |
|
28 | + return call_user_func_array([self::$dom, $method], $arguments); |
|
29 | + } else { |
|
30 | + throw new NotLoadedException('The dom is not loaded. Can not call a dom method.'); |
|
31 | + } |
|
32 | + } |
|
33 | 33 | |
34 | - /** |
|
35 | - * Call this to mount the static facade. The facade allows you to use |
|
36 | - * this object as a $className. |
|
37 | - * |
|
38 | - * @param string $className |
|
39 | - * @param Dom $dom |
|
40 | - * @return bool |
|
41 | - */ |
|
42 | - public static function mount($className = 'Dom', Dom $dom = null) |
|
43 | - { |
|
44 | - if (class_exists($className)) { |
|
45 | - return false; |
|
46 | - } |
|
47 | - class_alias(__CLASS__, $className); |
|
48 | - if ($dom instanceof Dom) { |
|
49 | - self::$dom = $dom; |
|
50 | - } |
|
34 | + /** |
|
35 | + * Call this to mount the static facade. The facade allows you to use |
|
36 | + * this object as a $className. |
|
37 | + * |
|
38 | + * @param string $className |
|
39 | + * @param Dom $dom |
|
40 | + * @return bool |
|
41 | + */ |
|
42 | + public static function mount($className = 'Dom', Dom $dom = null) |
|
43 | + { |
|
44 | + if (class_exists($className)) { |
|
45 | + return false; |
|
46 | + } |
|
47 | + class_alias(__CLASS__, $className); |
|
48 | + if ($dom instanceof Dom) { |
|
49 | + self::$dom = $dom; |
|
50 | + } |
|
51 | 51 | |
52 | - return true; |
|
53 | - } |
|
52 | + return true; |
|
53 | + } |
|
54 | 54 | |
55 | - /** |
|
56 | - * Creates a new dom object and calls load() on the |
|
57 | - * new object. |
|
58 | - * |
|
59 | - * @param string $str |
|
60 | - * @return $this |
|
61 | - */ |
|
62 | - public static function load($str) |
|
63 | - { |
|
64 | - $dom = new Dom; |
|
65 | - self::$dom = $dom; |
|
55 | + /** |
|
56 | + * Creates a new dom object and calls load() on the |
|
57 | + * new object. |
|
58 | + * |
|
59 | + * @param string $str |
|
60 | + * @return $this |
|
61 | + */ |
|
62 | + public static function load($str) |
|
63 | + { |
|
64 | + $dom = new Dom; |
|
65 | + self::$dom = $dom; |
|
66 | 66 | |
67 | - return $dom->load($str); |
|
68 | - } |
|
67 | + return $dom->load($str); |
|
68 | + } |
|
69 | 69 | |
70 | - /** |
|
71 | - * Creates a new dom object and calls loadFromFile() on the |
|
72 | - * new object. |
|
73 | - * |
|
74 | - * @param string $file |
|
75 | - * @return $this |
|
76 | - */ |
|
77 | - public static function loadFromFile($file) |
|
78 | - { |
|
79 | - $dom = new Dom; |
|
80 | - self::$dom = $dom; |
|
70 | + /** |
|
71 | + * Creates a new dom object and calls loadFromFile() on the |
|
72 | + * new object. |
|
73 | + * |
|
74 | + * @param string $file |
|
75 | + * @return $this |
|
76 | + */ |
|
77 | + public static function loadFromFile($file) |
|
78 | + { |
|
79 | + $dom = new Dom; |
|
80 | + self::$dom = $dom; |
|
81 | 81 | |
82 | - return $dom->loadFromFile($file); |
|
83 | - } |
|
82 | + return $dom->loadFromFile($file); |
|
83 | + } |
|
84 | 84 | |
85 | - /** |
|
86 | - * Creates a new dom object and calls loadFromUrl() on the |
|
87 | - * new object. |
|
88 | - * |
|
89 | - * @param string $url |
|
90 | - * @param CurlInterface $curl |
|
91 | - * @return $this |
|
92 | - */ |
|
93 | - public static function loadFromUrl($url, CurlInterface $curl = null) |
|
94 | - { |
|
95 | - $dom = new Dom; |
|
96 | - self::$dom = $dom; |
|
97 | - if (is_null($curl)) { |
|
98 | - // use the default curl interface |
|
99 | - $curl = new Curl; |
|
100 | - } |
|
85 | + /** |
|
86 | + * Creates a new dom object and calls loadFromUrl() on the |
|
87 | + * new object. |
|
88 | + * |
|
89 | + * @param string $url |
|
90 | + * @param CurlInterface $curl |
|
91 | + * @return $this |
|
92 | + */ |
|
93 | + public static function loadFromUrl($url, CurlInterface $curl = null) |
|
94 | + { |
|
95 | + $dom = new Dom; |
|
96 | + self::$dom = $dom; |
|
97 | + if (is_null($curl)) { |
|
98 | + // use the default curl interface |
|
99 | + $curl = new Curl; |
|
100 | + } |
|
101 | 101 | |
102 | - return $dom->loadFromUrl($url, $curl); |
|
103 | - } |
|
102 | + return $dom->loadFromUrl($url, $curl); |
|
103 | + } |
|
104 | 104 | |
105 | - /** |
|
106 | - * Sets the $dom variable to null. |
|
107 | - */ |
|
108 | - public static function unload() |
|
109 | - { |
|
110 | - self::$dom = null; |
|
111 | - } |
|
105 | + /** |
|
106 | + * Sets the $dom variable to null. |
|
107 | + */ |
|
108 | + public static function unload() |
|
109 | + { |
|
110 | + self::$dom = null; |
|
111 | + } |
|
112 | 112 | } |
@@ -12,76 +12,76 @@ |
||
12 | 12 | class Options |
13 | 13 | { |
14 | 14 | |
15 | - /** |
|
16 | - * The default options array |
|
17 | - * |
|
18 | - * @param array |
|
19 | - */ |
|
20 | - protected $defaults = [ |
|
21 | - 'whitespaceTextNode' => true, |
|
22 | - 'strict' => false, |
|
23 | - 'enforceEncoding' => null, |
|
24 | - 'cleanupInput' => true, |
|
25 | - 'removeScripts' => true, |
|
26 | - 'removeStyles' => true, |
|
27 | - 'preserveLineBreaks' => false, |
|
28 | - ]; |
|
15 | + /** |
|
16 | + * The default options array |
|
17 | + * |
|
18 | + * @param array |
|
19 | + */ |
|
20 | + protected $defaults = [ |
|
21 | + 'whitespaceTextNode' => true, |
|
22 | + 'strict' => false, |
|
23 | + 'enforceEncoding' => null, |
|
24 | + 'cleanupInput' => true, |
|
25 | + 'removeScripts' => true, |
|
26 | + 'removeStyles' => true, |
|
27 | + 'preserveLineBreaks' => false, |
|
28 | + ]; |
|
29 | 29 | |
30 | - /** |
|
31 | - * The list of all current options set. |
|
32 | - * |
|
33 | - * @param array |
|
34 | - */ |
|
35 | - protected $options = []; |
|
30 | + /** |
|
31 | + * The list of all current options set. |
|
32 | + * |
|
33 | + * @param array |
|
34 | + */ |
|
35 | + protected $options = []; |
|
36 | 36 | |
37 | - /** |
|
38 | - * Sets the default options in the options array |
|
39 | - */ |
|
40 | - public function __construct() |
|
41 | - { |
|
42 | - $this->options = $this->defaults; |
|
43 | - } |
|
37 | + /** |
|
38 | + * Sets the default options in the options array |
|
39 | + */ |
|
40 | + public function __construct() |
|
41 | + { |
|
42 | + $this->options = $this->defaults; |
|
43 | + } |
|
44 | 44 | |
45 | - /** |
|
46 | - * A magic get to call the get() method. |
|
47 | - * |
|
48 | - * @param string $key |
|
49 | - * @return mixed |
|
50 | - * @uses $this->get() |
|
51 | - */ |
|
52 | - public function __get($key) |
|
53 | - { |
|
54 | - return $this->get($key); |
|
55 | - } |
|
45 | + /** |
|
46 | + * A magic get to call the get() method. |
|
47 | + * |
|
48 | + * @param string $key |
|
49 | + * @return mixed |
|
50 | + * @uses $this->get() |
|
51 | + */ |
|
52 | + public function __get($key) |
|
53 | + { |
|
54 | + return $this->get($key); |
|
55 | + } |
|
56 | 56 | |
57 | - /** |
|
58 | - * Sets a new options param to override the current option array. |
|
59 | - * |
|
60 | - * @param array $options |
|
61 | - * @return $this |
|
62 | - */ |
|
63 | - public function setOptions(array $options) |
|
64 | - { |
|
65 | - foreach ($options as $key => $option) { |
|
66 | - $this->options[$key] = $option; |
|
67 | - } |
|
57 | + /** |
|
58 | + * Sets a new options param to override the current option array. |
|
59 | + * |
|
60 | + * @param array $options |
|
61 | + * @return $this |
|
62 | + */ |
|
63 | + public function setOptions(array $options) |
|
64 | + { |
|
65 | + foreach ($options as $key => $option) { |
|
66 | + $this->options[$key] = $option; |
|
67 | + } |
|
68 | 68 | |
69 | - return $this; |
|
70 | - } |
|
69 | + return $this; |
|
70 | + } |
|
71 | 71 | |
72 | - /** |
|
73 | - * Gets the value associated to the key, or null if the key is not |
|
74 | - * found. |
|
75 | - * |
|
76 | - * @param string |
|
77 | - * @return mixed |
|
78 | - */ |
|
79 | - public function get($key) |
|
80 | - { |
|
81 | - if (isset($this->options[$key])) { |
|
82 | - return $this->options[$key]; |
|
83 | - } |
|
72 | + /** |
|
73 | + * Gets the value associated to the key, or null if the key is not |
|
74 | + * found. |
|
75 | + * |
|
76 | + * @param string |
|
77 | + * @return mixed |
|
78 | + */ |
|
79 | + public function get($key) |
|
80 | + { |
|
81 | + if (isset($this->options[$key])) { |
|
82 | + return $this->options[$key]; |
|
83 | + } |
|
84 | 84 | |
85 | - return null; |
|
86 | - } |
|
85 | + return null; |
|
86 | + } |
|
87 | 87 | } |
@@ -9,244 +9,244 @@ |
||
9 | 9 | class Content |
10 | 10 | { |
11 | 11 | |
12 | - /** |
|
13 | - * The content string. |
|
14 | - * |
|
15 | - * @var string |
|
16 | - */ |
|
17 | - protected $content; |
|
18 | - |
|
19 | - /** |
|
20 | - * The size of the content. |
|
21 | - * |
|
22 | - * @var integer |
|
23 | - */ |
|
24 | - protected $size; |
|
25 | - |
|
26 | - /** |
|
27 | - * The current position we are in the content. |
|
28 | - * |
|
29 | - * @var integer |
|
30 | - */ |
|
31 | - protected $pos; |
|
32 | - |
|
33 | - /** |
|
34 | - * The following 4 strings are tags that are important to us. |
|
35 | - * |
|
36 | - * @var string |
|
37 | - */ |
|
38 | - protected $blank = " \t\r\n"; |
|
39 | - protected $equal = ' =/>'; |
|
40 | - protected $slash = " />\r\n\t"; |
|
41 | - protected $attr = ' >'; |
|
42 | - |
|
43 | - /** |
|
44 | - * Content constructor. |
|
45 | - * |
|
46 | - * @param $content |
|
47 | - */ |
|
48 | - public function __construct($content) |
|
49 | - { |
|
50 | - $this->content = $content; |
|
51 | - $this->size = strlen($content); |
|
52 | - $this->pos = 0; |
|
53 | - } |
|
54 | - |
|
55 | - /** |
|
56 | - * Returns the current position of the content. |
|
57 | - * |
|
58 | - * @return int |
|
59 | - */ |
|
60 | - public function getPosition() |
|
61 | - { |
|
62 | - return $this->pos; |
|
63 | - } |
|
64 | - |
|
65 | - /** |
|
66 | - * Gets the current character we are at. |
|
67 | - * |
|
68 | - * @param int $char |
|
69 | - * @return string |
|
70 | - */ |
|
71 | - public function char($char = null) |
|
72 | - { |
|
73 | - $pos = $this->pos; |
|
74 | - if ( ! is_null($char)) { |
|
75 | - $pos = $char; |
|
76 | - } |
|
77 | - |
|
78 | - if ( ! isset($this->content[$pos])) { |
|
79 | - return ''; |
|
80 | - } |
|
81 | - |
|
82 | - return $this->content[$pos]; |
|
83 | - } |
|
84 | - |
|
85 | - /** |
|
86 | - * Moves the current position forward. |
|
87 | - * |
|
88 | - * @param int $count |
|
89 | - * @return $this |
|
90 | - */ |
|
91 | - public function fastForward($count) |
|
92 | - { |
|
93 | - $this->pos += $count; |
|
94 | - |
|
95 | - return $this; |
|
96 | - } |
|
97 | - |
|
98 | - /** |
|
99 | - * Moves the current position backward. |
|
100 | - * |
|
101 | - * @param int $count |
|
102 | - * @return $this |
|
103 | - */ |
|
104 | - public function rewind($count) |
|
105 | - { |
|
106 | - $this->pos -= $count; |
|
107 | - if ($this->pos < 0) { |
|
108 | - $this->pos = 0; |
|
109 | - } |
|
110 | - |
|
111 | - return $this; |
|
112 | - } |
|
113 | - |
|
114 | - /** |
|
115 | - * Copy the content until we find the given string. |
|
116 | - * |
|
117 | - * @param string $string |
|
118 | - * @param bool $char |
|
119 | - * @param bool $escape |
|
120 | - * @return string |
|
121 | - */ |
|
122 | - public function copyUntil($string, $char = false, $escape = false) |
|
123 | - { |
|
124 | - if ($this->pos >= $this->size) { |
|
125 | - // nothing left |
|
126 | - return ''; |
|
127 | - } |
|
128 | - |
|
129 | - if ($escape) { |
|
130 | - $position = $this->pos; |
|
131 | - $found = false; |
|
132 | - while ( ! $found) { |
|
133 | - $position = strpos($this->content, $string, $position); |
|
134 | - if ($position === false) { |
|
135 | - // reached the end |
|
136 | - $found = true; |
|
137 | - continue; |
|
138 | - } |
|
139 | - |
|
140 | - if ($this->char($position - 1) == '\\') { |
|
141 | - // this character is escaped |
|
142 | - ++$position; |
|
143 | - continue; |
|
144 | - } |
|
145 | - |
|
146 | - $found = true; |
|
147 | - } |
|
148 | - } elseif ($char) { |
|
149 | - $position = strcspn($this->content, $string, $this->pos); |
|
150 | - $position += $this->pos; |
|
151 | - } else { |
|
152 | - $position = strpos($this->content, $string, $this->pos); |
|
153 | - } |
|
154 | - |
|
155 | - if ($position === false) { |
|
156 | - // could not find character, just return the remaining of the content |
|
157 | - $return = substr($this->content, $this->pos, $this->size - $this->pos); |
|
158 | - $this->pos = $this->size; |
|
159 | - |
|
160 | - return $return; |
|
161 | - } |
|
162 | - |
|
163 | - if ($position == $this->pos) { |
|
164 | - // we are at the right place |
|
165 | - return ''; |
|
166 | - } |
|
167 | - |
|
168 | - $return = substr($this->content, $this->pos, $position - $this->pos); |
|
169 | - // set the new position |
|
170 | - $this->pos = $position; |
|
171 | - |
|
172 | - return $return; |
|
173 | - } |
|
174 | - |
|
175 | - /** |
|
176 | - * Copies the content until the string is found and return it |
|
177 | - * unless the 'unless' is found in the substring. |
|
178 | - * |
|
179 | - * @param string $string |
|
180 | - * @param string $unless |
|
181 | - * @return string |
|
182 | - */ |
|
183 | - public function copyUntilUnless($string, $unless) |
|
184 | - { |
|
185 | - $lastPos = $this->pos; |
|
186 | - $this->fastForward(1); |
|
187 | - $foundString = $this->copyUntil($string, true, true); |
|
188 | - |
|
189 | - $position = strcspn($foundString, $unless); |
|
190 | - if ($position == strlen($foundString)) { |
|
191 | - return $string.$foundString; |
|
192 | - } |
|
193 | - // rewind changes and return nothing |
|
194 | - $this->pos = $lastPos; |
|
195 | - |
|
196 | - return ''; |
|
197 | - } |
|
198 | - |
|
199 | - /** |
|
200 | - * Copies the content until it reaches the token string., |
|
201 | - * |
|
202 | - * @param string $token |
|
203 | - * @param bool $char |
|
204 | - * @param bool $escape |
|
205 | - * @return string |
|
206 | - * @uses $this->copyUntil() |
|
207 | - */ |
|
208 | - public function copyByToken($token, $char = false, $escape = false) |
|
209 | - { |
|
210 | - $string = $this->$token; |
|
211 | - |
|
212 | - return $this->copyUntil($string, $char, $escape); |
|
213 | - } |
|
214 | - |
|
215 | - /** |
|
216 | - * Skip a given set of characters. |
|
217 | - * |
|
218 | - * @param string $string |
|
219 | - * @param bool $copy |
|
220 | - * @return $this|string |
|
221 | - */ |
|
222 | - public function skip($string, $copy = false) |
|
223 | - { |
|
224 | - $len = strspn($this->content, $string, $this->pos); |
|
225 | - |
|
226 | - // make it chainable if they don't want a copy |
|
227 | - $return = $this; |
|
228 | - if ($copy) { |
|
229 | - $return = substr($this->content, $this->pos, $len); |
|
230 | - } |
|
231 | - |
|
232 | - // update the position |
|
233 | - $this->pos += $len; |
|
234 | - |
|
235 | - return $return; |
|
236 | - } |
|
237 | - |
|
238 | - /** |
|
239 | - * Skip a given token of pre-defined characters. |
|
240 | - * |
|
241 | - * @param string $token |
|
242 | - * @param bool $copy |
|
243 | - * @return null|string |
|
244 | - * @uses $this->skip() |
|
245 | - */ |
|
246 | - public function skipByToken($token, $copy = false) |
|
247 | - { |
|
248 | - $string = $this->$token; |
|
249 | - |
|
250 | - return $this->skip($string, $copy); |
|
251 | - } |
|
12 | + /** |
|
13 | + * The content string. |
|
14 | + * |
|
15 | + * @var string |
|
16 | + */ |
|
17 | + protected $content; |
|
18 | + |
|
19 | + /** |
|
20 | + * The size of the content. |
|
21 | + * |
|
22 | + * @var integer |
|
23 | + */ |
|
24 | + protected $size; |
|
25 | + |
|
26 | + /** |
|
27 | + * The current position we are in the content. |
|
28 | + * |
|
29 | + * @var integer |
|
30 | + */ |
|
31 | + protected $pos; |
|
32 | + |
|
33 | + /** |
|
34 | + * The following 4 strings are tags that are important to us. |
|
35 | + * |
|
36 | + * @var string |
|
37 | + */ |
|
38 | + protected $blank = " \t\r\n"; |
|
39 | + protected $equal = ' =/>'; |
|
40 | + protected $slash = " />\r\n\t"; |
|
41 | + protected $attr = ' >'; |
|
42 | + |
|
43 | + /** |
|
44 | + * Content constructor. |
|
45 | + * |
|
46 | + * @param $content |
|
47 | + */ |
|
48 | + public function __construct($content) |
|
49 | + { |
|
50 | + $this->content = $content; |
|
51 | + $this->size = strlen($content); |
|
52 | + $this->pos = 0; |
|
53 | + } |
|
54 | + |
|
55 | + /** |
|
56 | + * Returns the current position of the content. |
|
57 | + * |
|
58 | + * @return int |
|
59 | + */ |
|
60 | + public function getPosition() |
|
61 | + { |
|
62 | + return $this->pos; |
|
63 | + } |
|
64 | + |
|
65 | + /** |
|
66 | + * Gets the current character we are at. |
|
67 | + * |
|
68 | + * @param int $char |
|
69 | + * @return string |
|
70 | + */ |
|
71 | + public function char($char = null) |
|
72 | + { |
|
73 | + $pos = $this->pos; |
|
74 | + if ( ! is_null($char)) { |
|
75 | + $pos = $char; |
|
76 | + } |
|
77 | + |
|
78 | + if ( ! isset($this->content[$pos])) { |
|
79 | + return ''; |
|
80 | + } |
|
81 | + |
|
82 | + return $this->content[$pos]; |
|
83 | + } |
|
84 | + |
|
85 | + /** |
|
86 | + * Moves the current position forward. |
|
87 | + * |
|
88 | + * @param int $count |
|
89 | + * @return $this |
|
90 | + */ |
|
91 | + public function fastForward($count) |
|
92 | + { |
|
93 | + $this->pos += $count; |
|
94 | + |
|
95 | + return $this; |
|
96 | + } |
|
97 | + |
|
98 | + /** |
|
99 | + * Moves the current position backward. |
|
100 | + * |
|
101 | + * @param int $count |
|
102 | + * @return $this |
|
103 | + */ |
|
104 | + public function rewind($count) |
|
105 | + { |
|
106 | + $this->pos -= $count; |
|
107 | + if ($this->pos < 0) { |
|
108 | + $this->pos = 0; |
|
109 | + } |
|
110 | + |
|
111 | + return $this; |
|
112 | + } |
|
113 | + |
|
114 | + /** |
|
115 | + * Copy the content until we find the given string. |
|
116 | + * |
|
117 | + * @param string $string |
|
118 | + * @param bool $char |
|
119 | + * @param bool $escape |
|
120 | + * @return string |
|
121 | + */ |
|
122 | + public function copyUntil($string, $char = false, $escape = false) |
|
123 | + { |
|
124 | + if ($this->pos >= $this->size) { |
|
125 | + // nothing left |
|
126 | + return ''; |
|
127 | + } |
|
128 | + |
|
129 | + if ($escape) { |
|
130 | + $position = $this->pos; |
|
131 | + $found = false; |
|
132 | + while ( ! $found) { |
|
133 | + $position = strpos($this->content, $string, $position); |
|
134 | + if ($position === false) { |
|
135 | + // reached the end |
|
136 | + $found = true; |
|
137 | + continue; |
|
138 | + } |
|
139 | + |
|
140 | + if ($this->char($position - 1) == '\\') { |
|
141 | + // this character is escaped |
|
142 | + ++$position; |
|
143 | + continue; |
|
144 | + } |
|
145 | + |
|
146 | + $found = true; |
|
147 | + } |
|
148 | + } elseif ($char) { |
|
149 | + $position = strcspn($this->content, $string, $this->pos); |
|
150 | + $position += $this->pos; |
|
151 | + } else { |
|
152 | + $position = strpos($this->content, $string, $this->pos); |
|
153 | + } |
|
154 | + |
|
155 | + if ($position === false) { |
|
156 | + // could not find character, just return the remaining of the content |
|
157 | + $return = substr($this->content, $this->pos, $this->size - $this->pos); |
|
158 | + $this->pos = $this->size; |
|
159 | + |
|
160 | + return $return; |
|
161 | + } |
|
162 | + |
|
163 | + if ($position == $this->pos) { |
|
164 | + // we are at the right place |
|
165 | + return ''; |
|
166 | + } |
|
167 | + |
|
168 | + $return = substr($this->content, $this->pos, $position - $this->pos); |
|
169 | + // set the new position |
|
170 | + $this->pos = $position; |
|
171 | + |
|
172 | + return $return; |
|
173 | + } |
|
174 | + |
|
175 | + /** |
|
176 | + * Copies the content until the string is found and return it |
|
177 | + * unless the 'unless' is found in the substring. |
|
178 | + * |
|
179 | + * @param string $string |
|
180 | + * @param string $unless |
|
181 | + * @return string |
|
182 | + */ |
|
183 | + public function copyUntilUnless($string, $unless) |
|
184 | + { |
|
185 | + $lastPos = $this->pos; |
|
186 | + $this->fastForward(1); |
|
187 | + $foundString = $this->copyUntil($string, true, true); |
|
188 | + |
|
189 | + $position = strcspn($foundString, $unless); |
|
190 | + if ($position == strlen($foundString)) { |
|
191 | + return $string.$foundString; |
|
192 | + } |
|
193 | + // rewind changes and return nothing |
|
194 | + $this->pos = $lastPos; |
|
195 | + |
|
196 | + return ''; |
|
197 | + } |
|
198 | + |
|
199 | + /** |
|
200 | + * Copies the content until it reaches the token string., |
|
201 | + * |
|
202 | + * @param string $token |
|
203 | + * @param bool $char |
|
204 | + * @param bool $escape |
|
205 | + * @return string |
|
206 | + * @uses $this->copyUntil() |
|
207 | + */ |
|
208 | + public function copyByToken($token, $char = false, $escape = false) |
|
209 | + { |
|
210 | + $string = $this->$token; |
|
211 | + |
|
212 | + return $this->copyUntil($string, $char, $escape); |
|
213 | + } |
|
214 | + |
|
215 | + /** |
|
216 | + * Skip a given set of characters. |
|
217 | + * |
|
218 | + * @param string $string |
|
219 | + * @param bool $copy |
|
220 | + * @return $this|string |
|
221 | + */ |
|
222 | + public function skip($string, $copy = false) |
|
223 | + { |
|
224 | + $len = strspn($this->content, $string, $this->pos); |
|
225 | + |
|
226 | + // make it chainable if they don't want a copy |
|
227 | + $return = $this; |
|
228 | + if ($copy) { |
|
229 | + $return = substr($this->content, $this->pos, $len); |
|
230 | + } |
|
231 | + |
|
232 | + // update the position |
|
233 | + $this->pos += $len; |
|
234 | + |
|
235 | + return $return; |
|
236 | + } |
|
237 | + |
|
238 | + /** |
|
239 | + * Skip a given token of pre-defined characters. |
|
240 | + * |
|
241 | + * @param string $token |
|
242 | + * @param bool $copy |
|
243 | + * @return null|string |
|
244 | + * @uses $this->skip() |
|
245 | + */ |
|
246 | + public function skipByToken($token, $copy = false) |
|
247 | + { |
|
248 | + $string = $this->$token; |
|
249 | + |
|
250 | + return $this->skip($string, $copy); |
|
251 | + } |
|
252 | 252 | } |
@@ -9,11 +9,11 @@ |
||
9 | 9 | interface CurlInterface |
10 | 10 | { |
11 | 11 | |
12 | - /** |
|
13 | - * This method should return the content of the url in a string |
|
14 | - * |
|
15 | - * @param string $url |
|
16 | - * @return string |
|
17 | - */ |
|
18 | - public function get($url); |
|
12 | + /** |
|
13 | + * This method should return the content of the url in a string |
|
14 | + * |
|
15 | + * @param string $url |
|
16 | + * @return string |
|
17 | + */ |
|
18 | + public function get($url); |
|
19 | 19 | } |
@@ -11,31 +11,31 @@ |
||
11 | 11 | class Curl implements CurlInterface |
12 | 12 | { |
13 | 13 | |
14 | - /** |
|
15 | - * A simple curl implementation to get the content of the url. |
|
16 | - * |
|
17 | - * @param string $url |
|
18 | - * @return string |
|
19 | - * @throws CurlException |
|
20 | - */ |
|
21 | - public function get($url) |
|
22 | - { |
|
23 | - $ch = curl_init($url); |
|
14 | + /** |
|
15 | + * A simple curl implementation to get the content of the url. |
|
16 | + * |
|
17 | + * @param string $url |
|
18 | + * @return string |
|
19 | + * @throws CurlException |
|
20 | + */ |
|
21 | + public function get($url) |
|
22 | + { |
|
23 | + $ch = curl_init($url); |
|
24 | 24 | |
25 | - if ( ! ini_get('open_basedir')) { |
|
26 | - curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true); |
|
27 | - } |
|
25 | + if ( ! ini_get('open_basedir')) { |
|
26 | + curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true); |
|
27 | + } |
|
28 | 28 | |
29 | - curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); |
|
30 | - curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 5); |
|
29 | + curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); |
|
30 | + curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 5); |
|
31 | 31 | |
32 | - $content = curl_exec($ch); |
|
33 | - if ($content === false) { |
|
34 | - // there was a problem |
|
35 | - $error = curl_error($ch); |
|
36 | - throw new CurlException('Error retrieving "'.$url.'" ('.$error.')'); |
|
37 | - } |
|
32 | + $content = curl_exec($ch); |
|
33 | + if ($content === false) { |
|
34 | + // there was a problem |
|
35 | + $error = curl_error($ch); |
|
36 | + throw new CurlException('Error retrieving "'.$url.'" ('.$error.')'); |
|
37 | + } |
|
38 | 38 | |
39 | - return $content; |
|
40 | - } |
|
39 | + return $content; |
|
40 | + } |
|
41 | 41 | } |
@@ -15,154 +15,154 @@ |
||
15 | 15 | class Collection implements IteratorAggregate, ArrayAccess, Countable |
16 | 16 | { |
17 | 17 | |
18 | - /** |
|
19 | - * The collection of Nodes. |
|
20 | - * |
|
21 | - * @param array |
|
22 | - */ |
|
23 | - protected $collection = []; |
|
18 | + /** |
|
19 | + * The collection of Nodes. |
|
20 | + * |
|
21 | + * @param array |
|
22 | + */ |
|
23 | + protected $collection = []; |
|
24 | 24 | |
25 | - /** |
|
26 | - * Attempts to call the method on the first node in |
|
27 | - * the collection. |
|
28 | - * |
|
29 | - * @param string $method |
|
30 | - * @param array $arguments |
|
31 | - * @return mixed; |
|
32 | - * @throws EmptyCollectionException |
|
33 | - */ |
|
34 | - public function __call($method, $arguments) |
|
35 | - { |
|
36 | - $node = reset($this->collection); |
|
37 | - if ($node instanceof AbstractNode) { |
|
38 | - return call_user_func_array([$node, $method], $arguments); |
|
39 | - } else { |
|
40 | - throw new EmptyCollectionException('The collection does not contain any Nodes.'); |
|
41 | - } |
|
42 | - } |
|
25 | + /** |
|
26 | + * Attempts to call the method on the first node in |
|
27 | + * the collection. |
|
28 | + * |
|
29 | + * @param string $method |
|
30 | + * @param array $arguments |
|
31 | + * @return mixed; |
|
32 | + * @throws EmptyCollectionException |
|
33 | + */ |
|
34 | + public function __call($method, $arguments) |
|
35 | + { |
|
36 | + $node = reset($this->collection); |
|
37 | + if ($node instanceof AbstractNode) { |
|
38 | + return call_user_func_array([$node, $method], $arguments); |
|
39 | + } else { |
|
40 | + throw new EmptyCollectionException('The collection does not contain any Nodes.'); |
|
41 | + } |
|
42 | + } |
|
43 | 43 | |
44 | - /** |
|
45 | - * Attempts to apply the magic get to the first node |
|
46 | - * in the collection. |
|
47 | - * |
|
48 | - * @param mixed $key |
|
49 | - * @return mixed |
|
50 | - * @throws EmptyCollectionException |
|
51 | - */ |
|
52 | - public function __get($key) |
|
53 | - { |
|
54 | - $node = reset($this->collection); |
|
55 | - if ($node instanceof AbstractNode) { |
|
56 | - return $node->$key; |
|
57 | - } else { |
|
58 | - throw new EmptyCollectionException('The collection does not contain any Nodes.'); |
|
59 | - } |
|
60 | - } |
|
44 | + /** |
|
45 | + * Attempts to apply the magic get to the first node |
|
46 | + * in the collection. |
|
47 | + * |
|
48 | + * @param mixed $key |
|
49 | + * @return mixed |
|
50 | + * @throws EmptyCollectionException |
|
51 | + */ |
|
52 | + public function __get($key) |
|
53 | + { |
|
54 | + $node = reset($this->collection); |
|
55 | + if ($node instanceof AbstractNode) { |
|
56 | + return $node->$key; |
|
57 | + } else { |
|
58 | + throw new EmptyCollectionException('The collection does not contain any Nodes.'); |
|
59 | + } |
|
60 | + } |
|
61 | 61 | |
62 | - /** |
|
63 | - * Applies the magic string method to the first node in |
|
64 | - * the collection. |
|
65 | - * |
|
66 | - * @return string |
|
67 | - * @throws EmptyCollectionException |
|
68 | - */ |
|
69 | - public function __toString() |
|
70 | - { |
|
71 | - $node = reset($this->collection); |
|
72 | - if ($node instanceof AbstractNode) { |
|
73 | - return (string)$node; |
|
74 | - } else { |
|
75 | - throw new EmptyCollectionException('The collection does not contain any Nodes.'); |
|
76 | - } |
|
77 | - } |
|
62 | + /** |
|
63 | + * Applies the magic string method to the first node in |
|
64 | + * the collection. |
|
65 | + * |
|
66 | + * @return string |
|
67 | + * @throws EmptyCollectionException |
|
68 | + */ |
|
69 | + public function __toString() |
|
70 | + { |
|
71 | + $node = reset($this->collection); |
|
72 | + if ($node instanceof AbstractNode) { |
|
73 | + return (string)$node; |
|
74 | + } else { |
|
75 | + throw new EmptyCollectionException('The collection does not contain any Nodes.'); |
|
76 | + } |
|
77 | + } |
|
78 | 78 | |
79 | - /** |
|
80 | - * Returns the count of the collection. |
|
81 | - * |
|
82 | - * @return int |
|
83 | - */ |
|
84 | - public function count() |
|
85 | - { |
|
86 | - return count($this->collection); |
|
87 | - } |
|
79 | + /** |
|
80 | + * Returns the count of the collection. |
|
81 | + * |
|
82 | + * @return int |
|
83 | + */ |
|
84 | + public function count() |
|
85 | + { |
|
86 | + return count($this->collection); |
|
87 | + } |
|
88 | 88 | |
89 | - /** |
|
90 | - * Returns an iterator for the collection. |
|
91 | - * |
|
92 | - * @return ArrayIterator |
|
93 | - */ |
|
94 | - public function getIterator() |
|
95 | - { |
|
96 | - return new ArrayIterator($this->collection); |
|
97 | - } |
|
89 | + /** |
|
90 | + * Returns an iterator for the collection. |
|
91 | + * |
|
92 | + * @return ArrayIterator |
|
93 | + */ |
|
94 | + public function getIterator() |
|
95 | + { |
|
96 | + return new ArrayIterator($this->collection); |
|
97 | + } |
|
98 | 98 | |
99 | - /** |
|
100 | - * Set an attribute by the given offset |
|
101 | - * |
|
102 | - * @param mixed $offset |
|
103 | - * @param mixed $value |
|
104 | - */ |
|
105 | - public function offsetSet($offset, $value) |
|
106 | - { |
|
107 | - if (is_null($offset)) { |
|
108 | - $this->collection[] = $value; |
|
109 | - } else { |
|
110 | - $this->collection[$offset] = $value; |
|
111 | - } |
|
112 | - } |
|
99 | + /** |
|
100 | + * Set an attribute by the given offset |
|
101 | + * |
|
102 | + * @param mixed $offset |
|
103 | + * @param mixed $value |
|
104 | + */ |
|
105 | + public function offsetSet($offset, $value) |
|
106 | + { |
|
107 | + if (is_null($offset)) { |
|
108 | + $this->collection[] = $value; |
|
109 | + } else { |
|
110 | + $this->collection[$offset] = $value; |
|
111 | + } |
|
112 | + } |
|
113 | 113 | |
114 | - /** |
|
115 | - * Checks if an offset exists. |
|
116 | - * |
|
117 | - * @param mixed $offset |
|
118 | - * @return bool |
|
119 | - */ |
|
120 | - public function offsetExists($offset) |
|
121 | - { |
|
122 | - return isset($this->collection[$offset]); |
|
123 | - } |
|
114 | + /** |
|
115 | + * Checks if an offset exists. |
|
116 | + * |
|
117 | + * @param mixed $offset |
|
118 | + * @return bool |
|
119 | + */ |
|
120 | + public function offsetExists($offset) |
|
121 | + { |
|
122 | + return isset($this->collection[$offset]); |
|
123 | + } |
|
124 | 124 | |
125 | - /** |
|
126 | - * Unset a collection Node. |
|
127 | - * |
|
128 | - * @param mixed $offset |
|
129 | - */ |
|
130 | - public function offsetUnset($offset) |
|
131 | - { |
|
132 | - unset($this->collection[$offset]); |
|
133 | - } |
|
125 | + /** |
|
126 | + * Unset a collection Node. |
|
127 | + * |
|
128 | + * @param mixed $offset |
|
129 | + */ |
|
130 | + public function offsetUnset($offset) |
|
131 | + { |
|
132 | + unset($this->collection[$offset]); |
|
133 | + } |
|
134 | 134 | |
135 | - /** |
|
136 | - * Gets a node at the given offset, or null |
|
137 | - * |
|
138 | - * @param mixed $offset |
|
139 | - * @return mixed |
|
140 | - */ |
|
141 | - public function offsetGet($offset) |
|
142 | - { |
|
143 | - return isset($this->collection[$offset]) ? $this->collection[$offset] : null; |
|
144 | - } |
|
135 | + /** |
|
136 | + * Gets a node at the given offset, or null |
|
137 | + * |
|
138 | + * @param mixed $offset |
|
139 | + * @return mixed |
|
140 | + */ |
|
141 | + public function offsetGet($offset) |
|
142 | + { |
|
143 | + return isset($this->collection[$offset]) ? $this->collection[$offset] : null; |
|
144 | + } |
|
145 | 145 | |
146 | - /** |
|
147 | - * Returns this collection as an array. |
|
148 | - * |
|
149 | - * @return array |
|
150 | - */ |
|
151 | - public function toArray() |
|
152 | - { |
|
153 | - return $this->collection; |
|
154 | - } |
|
146 | + /** |
|
147 | + * Returns this collection as an array. |
|
148 | + * |
|
149 | + * @return array |
|
150 | + */ |
|
151 | + public function toArray() |
|
152 | + { |
|
153 | + return $this->collection; |
|
154 | + } |
|
155 | 155 | |
156 | - /** |
|
157 | - * Similar to jQuery "each" method. Calls the callback with each |
|
158 | - * Node in this collection. |
|
159 | - * |
|
160 | - * @param callback $callback |
|
161 | - */ |
|
162 | - public function each($callback) |
|
163 | - { |
|
164 | - foreach ($this->collection as $key => $value) { |
|
165 | - $callback($value, $key); |
|
166 | - } |
|
167 | - } |
|
156 | + /** |
|
157 | + * Similar to jQuery "each" method. Calls the callback with each |
|
158 | + * Node in this collection. |
|
159 | + * |
|
160 | + * @param callback $callback |
|
161 | + */ |
|
162 | + public function each($callback) |
|
163 | + { |
|
164 | + foreach ($this->collection as $key => $value) { |
|
165 | + $callback($value, $key); |
|
166 | + } |
|
167 | + } |
|
168 | 168 | } |
@@ -12,189 +12,189 @@ |
||
12 | 12 | class HtmlNode extends ArrayNode |
13 | 13 | { |
14 | 14 | |
15 | - /** |
|
16 | - * Remembers what the innerHtml was if it was scanned previously. |
|
17 | - */ |
|
18 | - protected $innerHtml = null; |
|
19 | - |
|
20 | - /** |
|
21 | - * Remembers what the outerHtml was if it was scanned previously. |
|
22 | - * |
|
23 | - * @var string |
|
24 | - */ |
|
25 | - protected $outerHtml = null; |
|
26 | - |
|
27 | - /** |
|
28 | - * Remembers what the text was if it was scanned previously. |
|
29 | - * |
|
30 | - * @var string |
|
31 | - */ |
|
32 | - protected $text = null; |
|
33 | - |
|
34 | - /** |
|
35 | - * Remembers what the text was when we looked into all our |
|
36 | - * children nodes. |
|
37 | - * |
|
38 | - * @var string |
|
39 | - */ |
|
40 | - protected $textWithChildren = null; |
|
41 | - |
|
42 | - /** |
|
43 | - * Sets up the tag of this node. |
|
44 | - * |
|
45 | - * @param $tag |
|
46 | - */ |
|
47 | - public function __construct($tag) |
|
48 | - { |
|
49 | - if ( ! $tag instanceof Tag) { |
|
50 | - $tag = new Tag($tag); |
|
51 | - } |
|
52 | - $this->tag = $tag; |
|
53 | - parent::__construct(); |
|
54 | - } |
|
55 | - |
|
56 | - /** |
|
57 | - * Gets the inner html of this node. |
|
58 | - * |
|
59 | - * @return string |
|
60 | - * @throws UnknownChildTypeException |
|
61 | - */ |
|
62 | - public function innerHtml() |
|
63 | - { |
|
64 | - if ( ! $this->hasChildren()) { |
|
65 | - // no children |
|
66 | - return ''; |
|
67 | - } |
|
68 | - |
|
69 | - if ( ! is_null($this->innerHtml)) { |
|
70 | - // we already know the result. |
|
71 | - return $this->innerHtml; |
|
72 | - } |
|
73 | - |
|
74 | - $child = $this->firstChild(); |
|
75 | - $string = ''; |
|
76 | - |
|
77 | - // continue to loop until we are out of children |
|
78 | - while ( ! is_null($child)) { |
|
79 | - if ($child instanceof TextNode) { |
|
80 | - $string .= $child->text(); |
|
81 | - } elseif ($child instanceof HtmlNode) { |
|
82 | - $string .= $child->outerHtml(); |
|
83 | - } else { |
|
84 | - throw new UnknownChildTypeException('Unknown child type "'.get_class($child).'" found in node'); |
|
85 | - } |
|
86 | - |
|
87 | - try { |
|
88 | - $child = $this->nextChild($child->id()); |
|
89 | - } catch (ChildNotFoundException $e) { |
|
90 | - // no more children |
|
91 | - $child = null; |
|
92 | - } |
|
93 | - } |
|
94 | - |
|
95 | - // remember the results |
|
96 | - $this->innerHtml = $string; |
|
97 | - |
|
98 | - return $string; |
|
99 | - } |
|
100 | - |
|
101 | - /** |
|
102 | - * Gets the html of this node, including it's own |
|
103 | - * tag. |
|
104 | - * |
|
105 | - * @return string |
|
106 | - */ |
|
107 | - public function outerHtml() |
|
108 | - { |
|
109 | - // special handling for root |
|
110 | - if ($this->tag->name() == 'root') { |
|
111 | - return $this->innerHtml(); |
|
112 | - } |
|
113 | - |
|
114 | - if ( ! is_null($this->outerHtml)) { |
|
115 | - // we already know the results. |
|
116 | - return $this->outerHtml; |
|
117 | - } |
|
118 | - |
|
119 | - $return = $this->tag->makeOpeningTag(); |
|
120 | - if ($this->tag->isSelfClosing()) { |
|
121 | - // ignore any children... there should not be any though |
|
122 | - return $return; |
|
123 | - } |
|
124 | - |
|
125 | - // get the inner html |
|
126 | - $return .= $this->innerHtml(); |
|
127 | - |
|
128 | - // add closing tag |
|
129 | - $return .= $this->tag->makeClosingTag(); |
|
130 | - |
|
131 | - // remember the results |
|
132 | - $this->outerHtml = $return; |
|
133 | - |
|
134 | - return $return; |
|
135 | - } |
|
136 | - |
|
137 | - /** |
|
138 | - * Gets the text of this node (if there is any text). Or get all the text |
|
139 | - * in this node, including children. |
|
140 | - * |
|
141 | - * @param bool $lookInChildren |
|
142 | - * @return string |
|
143 | - */ |
|
144 | - public function text($lookInChildren = false) |
|
145 | - { |
|
146 | - if ($lookInChildren) { |
|
147 | - if ( ! is_null($this->textWithChildren)) { |
|
148 | - // we already know the results. |
|
149 | - return $this->textWithChildren; |
|
150 | - } |
|
151 | - } elseif ( ! is_null($this->text)) { |
|
152 | - // we already know the results. |
|
153 | - return $this->text; |
|
154 | - } |
|
155 | - |
|
156 | - // find out if this node has any text children |
|
157 | - $text = ''; |
|
158 | - foreach ($this->children as $child) { |
|
159 | - /** @var AbstractNode $node */ |
|
160 | - $node = $child['node']; |
|
161 | - if ($node instanceof TextNode) { |
|
162 | - $text .= $child['node']->text; |
|
163 | - } elseif ($lookInChildren && |
|
164 | - $node instanceof HtmlNode |
|
165 | - ) { |
|
166 | - $text .= $node->text($lookInChildren); |
|
167 | - } |
|
168 | - } |
|
169 | - |
|
170 | - // remember our result |
|
171 | - if ($lookInChildren) { |
|
172 | - $this->textWithChildren = $text; |
|
173 | - } else { |
|
174 | - $this->text = $text; |
|
175 | - } |
|
176 | - |
|
177 | - return $text; |
|
178 | - } |
|
179 | - |
|
180 | - /** |
|
181 | - * Call this when something in the node tree has changed. Like a child has been added |
|
182 | - * or a parent has been changed. |
|
183 | - */ |
|
184 | - protected function clear() |
|
185 | - { |
|
186 | - $this->innerHtml = null; |
|
187 | - $this->outerHtml = null; |
|
188 | - $this->text = null; |
|
189 | - } |
|
190 | - |
|
191 | - /** |
|
192 | - * Returns all children of this html node. |
|
193 | - * |
|
194 | - * @return array |
|
195 | - */ |
|
196 | - protected function getIteratorArray() |
|
197 | - { |
|
198 | - return $this->getChildren(); |
|
199 | - } |
|
15 | + /** |
|
16 | + * Remembers what the innerHtml was if it was scanned previously. |
|
17 | + */ |
|
18 | + protected $innerHtml = null; |
|
19 | + |
|
20 | + /** |
|
21 | + * Remembers what the outerHtml was if it was scanned previously. |
|
22 | + * |
|
23 | + * @var string |
|
24 | + */ |
|
25 | + protected $outerHtml = null; |
|
26 | + |
|
27 | + /** |
|
28 | + * Remembers what the text was if it was scanned previously. |
|
29 | + * |
|
30 | + * @var string |
|
31 | + */ |
|
32 | + protected $text = null; |
|
33 | + |
|
34 | + /** |
|
35 | + * Remembers what the text was when we looked into all our |
|
36 | + * children nodes. |
|
37 | + * |
|
38 | + * @var string |
|
39 | + */ |
|
40 | + protected $textWithChildren = null; |
|
41 | + |
|
42 | + /** |
|
43 | + * Sets up the tag of this node. |
|
44 | + * |
|
45 | + * @param $tag |
|
46 | + */ |
|
47 | + public function __construct($tag) |
|
48 | + { |
|
49 | + if ( ! $tag instanceof Tag) { |
|
50 | + $tag = new Tag($tag); |
|
51 | + } |
|
52 | + $this->tag = $tag; |
|
53 | + parent::__construct(); |
|
54 | + } |
|
55 | + |
|
56 | + /** |
|
57 | + * Gets the inner html of this node. |
|
58 | + * |
|
59 | + * @return string |
|
60 | + * @throws UnknownChildTypeException |
|
61 | + */ |
|
62 | + public function innerHtml() |
|
63 | + { |
|
64 | + if ( ! $this->hasChildren()) { |
|
65 | + // no children |
|
66 | + return ''; |
|
67 | + } |
|
68 | + |
|
69 | + if ( ! is_null($this->innerHtml)) { |
|
70 | + // we already know the result. |
|
71 | + return $this->innerHtml; |
|
72 | + } |
|
73 | + |
|
74 | + $child = $this->firstChild(); |
|
75 | + $string = ''; |
|
76 | + |
|
77 | + // continue to loop until we are out of children |
|
78 | + while ( ! is_null($child)) { |
|
79 | + if ($child instanceof TextNode) { |
|
80 | + $string .= $child->text(); |
|
81 | + } elseif ($child instanceof HtmlNode) { |
|
82 | + $string .= $child->outerHtml(); |
|
83 | + } else { |
|
84 | + throw new UnknownChildTypeException('Unknown child type "'.get_class($child).'" found in node'); |
|
85 | + } |
|
86 | + |
|
87 | + try { |
|
88 | + $child = $this->nextChild($child->id()); |
|
89 | + } catch (ChildNotFoundException $e) { |
|
90 | + // no more children |
|
91 | + $child = null; |
|
92 | + } |
|
93 | + } |
|
94 | + |
|
95 | + // remember the results |
|
96 | + $this->innerHtml = $string; |
|
97 | + |
|
98 | + return $string; |
|
99 | + } |
|
100 | + |
|
101 | + /** |
|
102 | + * Gets the html of this node, including it's own |
|
103 | + * tag. |
|
104 | + * |
|
105 | + * @return string |
|
106 | + */ |
|
107 | + public function outerHtml() |
|
108 | + { |
|
109 | + // special handling for root |
|
110 | + if ($this->tag->name() == 'root') { |
|
111 | + return $this->innerHtml(); |
|
112 | + } |
|
113 | + |
|
114 | + if ( ! is_null($this->outerHtml)) { |
|
115 | + // we already know the results. |
|
116 | + return $this->outerHtml; |
|
117 | + } |
|
118 | + |
|
119 | + $return = $this->tag->makeOpeningTag(); |
|
120 | + if ($this->tag->isSelfClosing()) { |
|
121 | + // ignore any children... there should not be any though |
|
122 | + return $return; |
|
123 | + } |
|
124 | + |
|
125 | + // get the inner html |
|
126 | + $return .= $this->innerHtml(); |
|
127 | + |
|
128 | + // add closing tag |
|
129 | + $return .= $this->tag->makeClosingTag(); |
|
130 | + |
|
131 | + // remember the results |
|
132 | + $this->outerHtml = $return; |
|
133 | + |
|
134 | + return $return; |
|
135 | + } |
|
136 | + |
|
137 | + /** |
|
138 | + * Gets the text of this node (if there is any text). Or get all the text |
|
139 | + * in this node, including children. |
|
140 | + * |
|
141 | + * @param bool $lookInChildren |
|
142 | + * @return string |
|
143 | + */ |
|
144 | + public function text($lookInChildren = false) |
|
145 | + { |
|
146 | + if ($lookInChildren) { |
|
147 | + if ( ! is_null($this->textWithChildren)) { |
|
148 | + // we already know the results. |
|
149 | + return $this->textWithChildren; |
|
150 | + } |
|
151 | + } elseif ( ! is_null($this->text)) { |
|
152 | + // we already know the results. |
|
153 | + return $this->text; |
|
154 | + } |
|
155 | + |
|
156 | + // find out if this node has any text children |
|
157 | + $text = ''; |
|
158 | + foreach ($this->children as $child) { |
|
159 | + /** @var AbstractNode $node */ |
|
160 | + $node = $child['node']; |
|
161 | + if ($node instanceof TextNode) { |
|
162 | + $text .= $child['node']->text; |
|
163 | + } elseif ($lookInChildren && |
|
164 | + $node instanceof HtmlNode |
|
165 | + ) { |
|
166 | + $text .= $node->text($lookInChildren); |
|
167 | + } |
|
168 | + } |
|
169 | + |
|
170 | + // remember our result |
|
171 | + if ($lookInChildren) { |
|
172 | + $this->textWithChildren = $text; |
|
173 | + } else { |
|
174 | + $this->text = $text; |
|
175 | + } |
|
176 | + |
|
177 | + return $text; |
|
178 | + } |
|
179 | + |
|
180 | + /** |
|
181 | + * Call this when something in the node tree has changed. Like a child has been added |
|
182 | + * or a parent has been changed. |
|
183 | + */ |
|
184 | + protected function clear() |
|
185 | + { |
|
186 | + $this->innerHtml = null; |
|
187 | + $this->outerHtml = null; |
|
188 | + $this->text = null; |
|
189 | + } |
|
190 | + |
|
191 | + /** |
|
192 | + * Returns all children of this html node. |
|
193 | + * |
|
194 | + * @return array |
|
195 | + */ |
|
196 | + protected function getIteratorArray() |
|
197 | + { |
|
198 | + return $this->getChildren(); |
|
199 | + } |
|
200 | 200 | } |
@@ -12,237 +12,237 @@ |
||
12 | 12 | class Tag |
13 | 13 | { |
14 | 14 | |
15 | - /** |
|
16 | - * The name of the tag. |
|
17 | - * |
|
18 | - * @var string |
|
19 | - */ |
|
20 | - protected $name; |
|
21 | - |
|
22 | - /** |
|
23 | - * The attributes of the tag. |
|
24 | - * |
|
25 | - * @var array |
|
26 | - */ |
|
27 | - protected $attr = []; |
|
28 | - |
|
29 | - /** |
|
30 | - * Is this tag self closing. |
|
31 | - * |
|
32 | - * @var bool |
|
33 | - */ |
|
34 | - protected $selfClosing = false; |
|
35 | - |
|
36 | - /** |
|
37 | - * Tag noise |
|
38 | - */ |
|
39 | - protected $noise = ''; |
|
40 | - |
|
41 | - /** |
|
42 | - * The encoding class to... encode the tags |
|
43 | - * |
|
44 | - * @var mixed |
|
45 | - */ |
|
46 | - protected $encode = null; |
|
47 | - |
|
48 | - /** |
|
49 | - * Sets up the tag with a name. |
|
50 | - * |
|
51 | - * @param $name |
|
52 | - */ |
|
53 | - public function __construct($name) |
|
54 | - { |
|
55 | - $this->name = $name; |
|
56 | - } |
|
57 | - |
|
58 | - /** |
|
59 | - * Magic method to get any of the attributes. |
|
60 | - * |
|
61 | - * @param string $key |
|
62 | - * @return mixed |
|
63 | - */ |
|
64 | - public function __get($key) |
|
65 | - { |
|
66 | - return $this->getAttribute($key); |
|
67 | - } |
|
68 | - |
|
69 | - /** |
|
70 | - * Magic method to set any attribute. |
|
71 | - * |
|
72 | - * @param string $key |
|
73 | - * @param mixed $value |
|
74 | - */ |
|
75 | - public function __set($key, $value) |
|
76 | - { |
|
77 | - $this->setAttribute($key, $value); |
|
78 | - } |
|
79 | - |
|
80 | - /** |
|
81 | - * Returns the name of this tag. |
|
82 | - * |
|
83 | - * @return string |
|
84 | - */ |
|
85 | - public function name() |
|
86 | - { |
|
87 | - return $this->name; |
|
88 | - } |
|
89 | - |
|
90 | - /** |
|
91 | - * Sets the tag to be self closing. |
|
92 | - * |
|
93 | - * @return $this |
|
94 | - */ |
|
95 | - public function selfClosing() |
|
96 | - { |
|
97 | - $this->selfClosing = true; |
|
98 | - |
|
99 | - return $this; |
|
100 | - } |
|
101 | - |
|
102 | - /** |
|
103 | - * Checks if the tag is self closing. |
|
104 | - * |
|
105 | - * @return bool |
|
106 | - */ |
|
107 | - public function isSelfClosing() |
|
108 | - { |
|
109 | - return $this->selfClosing; |
|
110 | - } |
|
111 | - |
|
112 | - /** |
|
113 | - * Sets the encoding type to be used. |
|
114 | - * |
|
115 | - * @param Encode $encode |
|
116 | - */ |
|
117 | - public function setEncoding(Encode $encode) |
|
118 | - { |
|
119 | - $this->encode = $encode; |
|
120 | - } |
|
121 | - |
|
122 | - /** |
|
123 | - * Sets the noise for this tag (if any) |
|
124 | - * |
|
125 | - * @param $noise |
|
126 | - * @return $this |
|
127 | - */ |
|
128 | - public function noise($noise) |
|
129 | - { |
|
130 | - $this->noise = $noise; |
|
131 | - |
|
132 | - return $this; |
|
133 | - } |
|
134 | - |
|
135 | - /** |
|
136 | - * Set an attribute for this tag. |
|
137 | - * |
|
138 | - * @param string $key |
|
139 | - * @param mixed $value |
|
140 | - * @return $this |
|
141 | - */ |
|
142 | - public function setAttribute($key, $value) |
|
143 | - { |
|
144 | - $key = strtolower($key); |
|
145 | - if ( ! is_array($value)) { |
|
146 | - $value = [ |
|
147 | - 'value' => $value, |
|
148 | - 'doubleQuote' => true, |
|
149 | - ]; |
|
150 | - } |
|
151 | - $this->attr[$key] = $value; |
|
152 | - |
|
153 | - return $this; |
|
154 | - } |
|
155 | - |
|
156 | - /** |
|
157 | - * Sets the attributes for this tag |
|
158 | - * |
|
159 | - * @param array $attr |
|
160 | - * @return $this |
|
161 | - */ |
|
162 | - public function setAttributes(array $attr) |
|
163 | - { |
|
164 | - foreach ($attr as $key => $value) { |
|
165 | - $this->setAttribute($key, $value); |
|
166 | - } |
|
167 | - |
|
168 | - return $this; |
|
169 | - } |
|
170 | - |
|
171 | - /** |
|
172 | - * Returns all attributes of this tag. |
|
173 | - * |
|
174 | - * @return array |
|
175 | - */ |
|
176 | - public function getAttributes() |
|
177 | - { |
|
178 | - $return = []; |
|
179 | - foreach ($this->attr as $attr => $info) { |
|
180 | - $return[$attr] = $this->getAttribute($attr); |
|
181 | - } |
|
182 | - |
|
183 | - return $return; |
|
184 | - } |
|
185 | - |
|
186 | - /** |
|
187 | - * Returns an attribute by the key |
|
188 | - * |
|
189 | - * @param string $key |
|
190 | - * @return mixed |
|
191 | - */ |
|
192 | - public function getAttribute($key) |
|
193 | - { |
|
194 | - if ( ! isset($this->attr[$key])) { |
|
195 | - return null; |
|
196 | - } |
|
197 | - $value = $this->attr[$key]['value']; |
|
198 | - if (is_string($value) && ! is_null($this->encode)) { |
|
199 | - // convert charset |
|
200 | - $this->attr[$key]['value'] = $this->encode->convert($value); |
|
201 | - } |
|
202 | - |
|
203 | - return $this->attr[$key]; |
|
204 | - } |
|
205 | - |
|
206 | - /** |
|
207 | - * Generates the opening tag for this object. |
|
208 | - * |
|
209 | - * @return string |
|
210 | - */ |
|
211 | - public function makeOpeningTag() |
|
212 | - { |
|
213 | - $return = '<'.$this->name; |
|
214 | - |
|
215 | - // add the attributes |
|
216 | - foreach ($this->attr as $key => $info) { |
|
217 | - $info = $this->getAttribute($key); |
|
218 | - $val = $info['value']; |
|
219 | - if (is_null($val)) { |
|
220 | - $return .= ' '.$key; |
|
221 | - } elseif ($info['doubleQuote']) { |
|
222 | - $return .= ' '.$key.'="'.$val.'"'; |
|
223 | - } else { |
|
224 | - $return .= ' '.$key.'=\''.$val.'\''; |
|
225 | - } |
|
226 | - } |
|
227 | - |
|
228 | - if ($this->selfClosing) { |
|
229 | - return $return.' />'; |
|
230 | - } else { |
|
231 | - return $return.'>'; |
|
232 | - } |
|
233 | - } |
|
234 | - |
|
235 | - /** |
|
236 | - * Generates the closing tag for this object. |
|
237 | - * |
|
238 | - * @return string |
|
239 | - */ |
|
240 | - public function makeClosingTag() |
|
241 | - { |
|
242 | - if ($this->selfClosing) { |
|
243 | - return ''; |
|
244 | - } |
|
245 | - |
|
246 | - return '</'.$this->name.'>'; |
|
247 | - } |
|
15 | + /** |
|
16 | + * The name of the tag. |
|
17 | + * |
|
18 | + * @var string |
|
19 | + */ |
|
20 | + protected $name; |
|
21 | + |
|
22 | + /** |
|
23 | + * The attributes of the tag. |
|
24 | + * |
|
25 | + * @var array |
|
26 | + */ |
|
27 | + protected $attr = []; |
|
28 | + |
|
29 | + /** |
|
30 | + * Is this tag self closing. |
|
31 | + * |
|
32 | + * @var bool |
|
33 | + */ |
|
34 | + protected $selfClosing = false; |
|
35 | + |
|
36 | + /** |
|
37 | + * Tag noise |
|
38 | + */ |
|
39 | + protected $noise = ''; |
|
40 | + |
|
41 | + /** |
|
42 | + * The encoding class to... encode the tags |
|
43 | + * |
|
44 | + * @var mixed |
|
45 | + */ |
|
46 | + protected $encode = null; |
|
47 | + |
|
48 | + /** |
|
49 | + * Sets up the tag with a name. |
|
50 | + * |
|
51 | + * @param $name |
|
52 | + */ |
|
53 | + public function __construct($name) |
|
54 | + { |
|
55 | + $this->name = $name; |
|
56 | + } |
|
57 | + |
|
58 | + /** |
|
59 | + * Magic method to get any of the attributes. |
|
60 | + * |
|
61 | + * @param string $key |
|
62 | + * @return mixed |
|
63 | + */ |
|
64 | + public function __get($key) |
|
65 | + { |
|
66 | + return $this->getAttribute($key); |
|
67 | + } |
|
68 | + |
|
69 | + /** |
|
70 | + * Magic method to set any attribute. |
|
71 | + * |
|
72 | + * @param string $key |
|
73 | + * @param mixed $value |
|
74 | + */ |
|
75 | + public function __set($key, $value) |
|
76 | + { |
|
77 | + $this->setAttribute($key, $value); |
|
78 | + } |
|
79 | + |
|
80 | + /** |
|
81 | + * Returns the name of this tag. |
|
82 | + * |
|
83 | + * @return string |
|
84 | + */ |
|
85 | + public function name() |
|
86 | + { |
|
87 | + return $this->name; |
|
88 | + } |
|
89 | + |
|
90 | + /** |
|
91 | + * Sets the tag to be self closing. |
|
92 | + * |
|
93 | + * @return $this |
|
94 | + */ |
|
95 | + public function selfClosing() |
|
96 | + { |
|
97 | + $this->selfClosing = true; |
|
98 | + |
|
99 | + return $this; |
|
100 | + } |
|
101 | + |
|
102 | + /** |
|
103 | + * Checks if the tag is self closing. |
|
104 | + * |
|
105 | + * @return bool |
|
106 | + */ |
|
107 | + public function isSelfClosing() |
|
108 | + { |
|
109 | + return $this->selfClosing; |
|
110 | + } |
|
111 | + |
|
112 | + /** |
|
113 | + * Sets the encoding type to be used. |
|
114 | + * |
|
115 | + * @param Encode $encode |
|
116 | + */ |
|
117 | + public function setEncoding(Encode $encode) |
|
118 | + { |
|
119 | + $this->encode = $encode; |
|
120 | + } |
|
121 | + |
|
122 | + /** |
|
123 | + * Sets the noise for this tag (if any) |
|
124 | + * |
|
125 | + * @param $noise |
|
126 | + * @return $this |
|
127 | + */ |
|
128 | + public function noise($noise) |
|
129 | + { |
|
130 | + $this->noise = $noise; |
|
131 | + |
|
132 | + return $this; |
|
133 | + } |
|
134 | + |
|
135 | + /** |
|
136 | + * Set an attribute for this tag. |
|
137 | + * |
|
138 | + * @param string $key |
|
139 | + * @param mixed $value |
|
140 | + * @return $this |
|
141 | + */ |
|
142 | + public function setAttribute($key, $value) |
|
143 | + { |
|
144 | + $key = strtolower($key); |
|
145 | + if ( ! is_array($value)) { |
|
146 | + $value = [ |
|
147 | + 'value' => $value, |
|
148 | + 'doubleQuote' => true, |
|
149 | + ]; |
|
150 | + } |
|
151 | + $this->attr[$key] = $value; |
|
152 | + |
|
153 | + return $this; |
|
154 | + } |
|
155 | + |
|
156 | + /** |
|
157 | + * Sets the attributes for this tag |
|
158 | + * |
|
159 | + * @param array $attr |
|
160 | + * @return $this |
|
161 | + */ |
|
162 | + public function setAttributes(array $attr) |
|
163 | + { |
|
164 | + foreach ($attr as $key => $value) { |
|
165 | + $this->setAttribute($key, $value); |
|
166 | + } |
|
167 | + |
|
168 | + return $this; |
|
169 | + } |
|
170 | + |
|
171 | + /** |
|
172 | + * Returns all attributes of this tag. |
|
173 | + * |
|
174 | + * @return array |
|
175 | + */ |
|
176 | + public function getAttributes() |
|
177 | + { |
|
178 | + $return = []; |
|
179 | + foreach ($this->attr as $attr => $info) { |
|
180 | + $return[$attr] = $this->getAttribute($attr); |
|
181 | + } |
|
182 | + |
|
183 | + return $return; |
|
184 | + } |
|
185 | + |
|
186 | + /** |
|
187 | + * Returns an attribute by the key |
|
188 | + * |
|
189 | + * @param string $key |
|
190 | + * @return mixed |
|
191 | + */ |
|
192 | + public function getAttribute($key) |
|
193 | + { |
|
194 | + if ( ! isset($this->attr[$key])) { |
|
195 | + return null; |
|
196 | + } |
|
197 | + $value = $this->attr[$key]['value']; |
|
198 | + if (is_string($value) && ! is_null($this->encode)) { |
|
199 | + // convert charset |
|
200 | + $this->attr[$key]['value'] = $this->encode->convert($value); |
|
201 | + } |
|
202 | + |
|
203 | + return $this->attr[$key]; |
|
204 | + } |
|
205 | + |
|
206 | + /** |
|
207 | + * Generates the opening tag for this object. |
|
208 | + * |
|
209 | + * @return string |
|
210 | + */ |
|
211 | + public function makeOpeningTag() |
|
212 | + { |
|
213 | + $return = '<'.$this->name; |
|
214 | + |
|
215 | + // add the attributes |
|
216 | + foreach ($this->attr as $key => $info) { |
|
217 | + $info = $this->getAttribute($key); |
|
218 | + $val = $info['value']; |
|
219 | + if (is_null($val)) { |
|
220 | + $return .= ' '.$key; |
|
221 | + } elseif ($info['doubleQuote']) { |
|
222 | + $return .= ' '.$key.'="'.$val.'"'; |
|
223 | + } else { |
|
224 | + $return .= ' '.$key.'=\''.$val.'\''; |
|
225 | + } |
|
226 | + } |
|
227 | + |
|
228 | + if ($this->selfClosing) { |
|
229 | + return $return.' />'; |
|
230 | + } else { |
|
231 | + return $return.'>'; |
|
232 | + } |
|
233 | + } |
|
234 | + |
|
235 | + /** |
|
236 | + * Generates the closing tag for this object. |
|
237 | + * |
|
238 | + * @return string |
|
239 | + */ |
|
240 | + public function makeClosingTag() |
|
241 | + { |
|
242 | + if ($this->selfClosing) { |
|
243 | + return ''; |
|
244 | + } |
|
245 | + |
|
246 | + return '</'.$this->name.'>'; |
|
247 | + } |
|
248 | 248 | } |