Total Complexity | 113 |
Total Lines | 757 |
Duplicated Lines | 0 % |
Changes | 13 | ||
Bugs | 2 | Features | 2 |
Complex classes like Page 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 Page, and based on these observations, apply Extract Interface, too.
1 | <?php |
||
38 | class Page extends PDFObject |
||
39 | { |
||
40 | /** |
||
41 | * @var Font[] |
||
42 | */ |
||
43 | protected $fonts = null; |
||
44 | |||
45 | /** |
||
46 | * @var PDFObject[] |
||
47 | */ |
||
48 | protected $xobjects = null; |
||
49 | |||
50 | /** |
||
51 | * @var array |
||
52 | */ |
||
53 | protected $dataTm = null; |
||
54 | |||
55 | /** |
||
56 | * @return Font[] |
||
57 | */ |
||
58 | public function getFonts() |
||
59 | { |
||
60 | if (null !== $this->fonts) { |
||
61 | return $this->fonts; |
||
62 | } |
||
63 | |||
64 | $resources = $this->get('Resources'); |
||
65 | |||
66 | if (method_exists($resources, 'has') && $resources->has('Font')) { |
||
67 | if ($resources->get('Font') instanceof Header) { |
||
|
|||
68 | $fonts = $resources->get('Font')->getElements(); |
||
69 | } else { |
||
70 | $fonts = $resources->get('Font')->getHeader()->getElements(); |
||
71 | } |
||
72 | |||
73 | $table = []; |
||
74 | |||
75 | foreach ($fonts as $id => $font) { |
||
76 | if ($font instanceof Font) { |
||
77 | $table[$id] = $font; |
||
78 | |||
79 | // Store too on cleaned id value (only numeric) |
||
80 | $id = preg_replace('/[^0-9\.\-_]/', '', $id); |
||
81 | if ('' != $id) { |
||
82 | $table[$id] = $font; |
||
83 | } |
||
84 | } |
||
85 | } |
||
86 | |||
87 | return $this->fonts = $table; |
||
88 | } |
||
89 | |||
90 | return []; |
||
91 | } |
||
92 | |||
93 | /** |
||
94 | * @param string $id |
||
95 | * |
||
96 | * @return Font|null |
||
97 | */ |
||
98 | public function getFont($id) |
||
113 | } |
||
114 | |||
115 | /** |
||
116 | * Support for XObject |
||
117 | * |
||
118 | * @return PDFObject[] |
||
119 | */ |
||
120 | public function getXObjects() |
||
121 | { |
||
122 | if (null !== $this->xobjects) { |
||
123 | return $this->xobjects; |
||
124 | } |
||
125 | |||
126 | $resources = $this->get('Resources'); |
||
127 | |||
128 | if (method_exists($resources, 'has') && $resources->has('XObject')) { |
||
129 | if ($resources->get('XObject') instanceof Header) { |
||
130 | $xobjects = $resources->get('XObject')->getElements(); |
||
131 | } else { |
||
132 | $xobjects = $resources->get('XObject')->getHeader()->getElements(); |
||
133 | } |
||
134 | |||
135 | $table = []; |
||
136 | |||
137 | foreach ($xobjects as $id => $xobject) { |
||
138 | $table[$id] = $xobject; |
||
139 | |||
140 | // Store too on cleaned id value (only numeric) |
||
141 | $id = preg_replace('/[^0-9\.\-_]/', '', $id); |
||
142 | if ('' != $id) { |
||
143 | $table[$id] = $xobject; |
||
144 | } |
||
145 | } |
||
146 | |||
147 | return $this->xobjects = $table; |
||
148 | } |
||
149 | |||
150 | return []; |
||
151 | } |
||
152 | |||
153 | /** |
||
154 | * @param string $id |
||
155 | * |
||
156 | * @return PDFObject|null |
||
157 | */ |
||
158 | public function getXObject($id) |
||
159 | { |
||
160 | $xobjects = $this->getXObjects(); |
||
161 | |||
162 | if (isset($xobjects[$id])) { |
||
163 | return $xobjects[$id]; |
||
164 | } |
||
165 | |||
166 | return null; |
||
167 | /*$id = preg_replace('/[^0-9\.\-_]/', '', $id); |
||
168 | |||
169 | if (isset($xobjects[$id])) { |
||
170 | return $xobjects[$id]; |
||
171 | } else { |
||
172 | return null; |
||
173 | }*/ |
||
174 | } |
||
175 | |||
176 | /** |
||
177 | * @param Page $page |
||
178 | * |
||
179 | * @return string |
||
180 | */ |
||
181 | public function getText(self $page = null) |
||
182 | { |
||
183 | if ($contents = $this->get('Contents')) { |
||
184 | if ($contents instanceof ElementMissing) { |
||
185 | return ''; |
||
186 | } elseif ($contents instanceof ElementNull) { |
||
187 | return ''; |
||
188 | } elseif ($contents instanceof PDFObject) { |
||
189 | $elements = $contents->getHeader()->getElements(); |
||
190 | |||
191 | if (is_numeric(key($elements))) { |
||
192 | $new_content = ''; |
||
193 | |||
194 | foreach ($elements as $element) { |
||
195 | if ($element instanceof ElementXRef) { |
||
196 | $new_content .= $element->getObject()->getContent(); |
||
197 | } else { |
||
198 | $new_content .= $element->getContent(); |
||
199 | } |
||
200 | } |
||
201 | |||
202 | $header = new Header([], $this->document); |
||
203 | $contents = new PDFObject($this->document, $header, $new_content); |
||
204 | } |
||
205 | } elseif ($contents instanceof ElementArray) { |
||
206 | // Create a virtual global content. |
||
207 | $new_content = ''; |
||
208 | |||
209 | foreach ($contents->getContent() as $content) { |
||
210 | $new_content .= $content->getContent()."\n"; |
||
211 | } |
||
212 | |||
213 | $header = new Header([], $this->document); |
||
214 | $contents = new PDFObject($this->document, $header, $new_content); |
||
215 | } |
||
216 | |||
217 | return $contents->getText($this); |
||
218 | } |
||
219 | |||
220 | return ''; |
||
221 | } |
||
222 | |||
223 | /** |
||
224 | * @param Page $page |
||
225 | * |
||
226 | * @return array |
||
227 | */ |
||
228 | public function getTextArray(self $page = null) |
||
229 | { |
||
230 | if ($contents = $this->get('Contents')) { |
||
231 | if ($contents instanceof ElementMissing) { |
||
232 | return []; |
||
233 | } elseif ($contents instanceof ElementNull) { |
||
234 | return []; |
||
235 | } elseif ($contents instanceof PDFObject) { |
||
236 | $elements = $contents->getHeader()->getElements(); |
||
237 | |||
238 | if (is_numeric(key($elements))) { |
||
239 | $new_content = ''; |
||
240 | |||
241 | /** @var PDFObject $element */ |
||
242 | foreach ($elements as $element) { |
||
243 | if ($element instanceof ElementXRef) { |
||
244 | $new_content .= $element->getObject()->getContent(); |
||
245 | } else { |
||
246 | $new_content .= $element->getContent(); |
||
247 | } |
||
248 | } |
||
249 | |||
250 | $header = new Header([], $this->document); |
||
251 | $contents = new PDFObject($this->document, $header, $new_content); |
||
252 | } |
||
253 | } elseif ($contents instanceof ElementArray) { |
||
254 | // Create a virtual global content. |
||
255 | $new_content = ''; |
||
256 | |||
257 | /** @var PDFObject $content */ |
||
258 | foreach ($contents->getContent() as $content) { |
||
259 | $new_content .= $content->getContent()."\n"; |
||
260 | } |
||
261 | |||
262 | $header = new Header([], $this->document); |
||
263 | $contents = new PDFObject($this->document, $header, $new_content); |
||
264 | } |
||
265 | |||
266 | return $contents->getTextArray($this); |
||
267 | } |
||
268 | |||
269 | return []; |
||
270 | } |
||
271 | |||
272 | /** |
||
273 | * Gets all the text data with its internal representation of the page. |
||
274 | * |
||
275 | * @return array An array with the data and the internal representation |
||
276 | */ |
||
277 | public function extractRawData() |
||
278 | { |
||
279 | /* |
||
280 | * Now you can get the complete content of the object with the text on it |
||
281 | */ |
||
282 | $extractedData = []; |
||
283 | $content = $this->get('Contents'); |
||
284 | $values = $content->getContent(); |
||
285 | if (isset($values) and \is_array($values)) { |
||
286 | $text = ''; |
||
287 | foreach ($values as $section) { |
||
288 | $text .= $section->getContent(); |
||
289 | } |
||
290 | $sectionsText = $this->getSectionsText($text); |
||
291 | foreach ($sectionsText as $sectionText) { |
||
292 | $commandsText = $this->getCommandsText($sectionText); |
||
293 | foreach ($commandsText as $command) { |
||
294 | $extractedData[] = $command; |
||
295 | } |
||
296 | } |
||
297 | } else { |
||
298 | $sectionsText = $content->getSectionsText($content->getContent()); |
||
299 | foreach ($sectionsText as $sectionText) { |
||
300 | $commandsText = $content->getCommandsText($sectionText); |
||
301 | foreach ($commandsText as $command) { |
||
302 | $extractedData[] = $command; |
||
303 | } |
||
304 | } |
||
305 | } |
||
306 | |||
307 | return $extractedData; |
||
308 | } |
||
309 | |||
310 | /** |
||
311 | * Gets all the decoded text data with it internal representation from a page. |
||
312 | * |
||
313 | * @param array $extractedRawData the extracted data return by extractRawData or |
||
314 | * null if extractRawData should be called |
||
315 | * |
||
316 | * @return array An array with the data and the internal representation |
||
317 | */ |
||
318 | public function extractDecodedRawData($extractedRawData = null) |
||
319 | { |
||
320 | if (!isset($extractedRawData) or !$extractedRawData) { |
||
321 | $extractedRawData = $this->extractRawData(); |
||
322 | } |
||
323 | $unicode = true; |
||
324 | $currentFont = null; |
||
325 | foreach ($extractedRawData as &$command) { |
||
326 | if ('Tj' == $command['o'] or 'TJ' == $command['o']) { |
||
327 | $data = $command['c']; |
||
328 | if (!\is_array($data)) { |
||
329 | $tmpText = ''; |
||
330 | if (isset($currentFont)) { |
||
331 | $tmpText = $currentFont->decodeOctal($data); |
||
332 | //$tmpText = $currentFont->decodeHexadecimal($tmpText, false); |
||
333 | } |
||
334 | $tmpText = str_replace( |
||
335 | ['\\\\', '\(', '\)', '\n', '\r', '\t', '\ '], |
||
336 | ['\\', '(', ')', "\n", "\r", "\t", ' '], |
||
337 | $tmpText |
||
338 | ); |
||
339 | $tmpText = utf8_encode($tmpText); |
||
340 | if (isset($currentFont)) { |
||
341 | $tmpText = $currentFont->decodeContent($tmpText, $unicode); |
||
342 | } |
||
343 | $command['c'] = $tmpText; |
||
344 | continue; |
||
345 | } |
||
346 | $numText = \count($data); |
||
347 | for ($i = 0; $i < $numText; ++$i) { |
||
348 | if (0 != ($i % 2)) { |
||
349 | continue; |
||
350 | } |
||
351 | $tmpText = $data[$i]['c']; |
||
352 | $decodedText = ''; |
||
353 | if (isset($currentFont)) { |
||
354 | $decodedText = $currentFont->decodeOctal($tmpText); |
||
355 | //$tmpText = $currentFont->decodeHexadecimal($tmpText, false); |
||
356 | } |
||
357 | $decodedText = str_replace( |
||
358 | ['\\\\', '\(', '\)', '\n', '\r', '\t', '\ '], |
||
359 | ['\\', '(', ')', "\n", "\r", "\t", ' '], |
||
360 | $decodedText |
||
361 | ); |
||
362 | $decodedText = utf8_encode($decodedText); |
||
363 | if (isset($currentFont)) { |
||
364 | $decodedText = $currentFont->decodeContent($decodedText, $unicode); |
||
365 | } |
||
366 | $command['c'][$i]['c'] = $decodedText; |
||
367 | continue; |
||
368 | } |
||
369 | } elseif ('Tf' == $command['o'] or 'TF' == $command['o']) { |
||
370 | $fontId = explode(' ', $command['c'])[0]; |
||
371 | $currentFont = $this->getFont($fontId); |
||
372 | continue; |
||
373 | } |
||
374 | } |
||
375 | |||
376 | return $extractedRawData; |
||
377 | } |
||
378 | |||
379 | /** |
||
380 | * Gets just the Text commands that are involved in text positions and |
||
381 | * Text Matrix (Tm) |
||
382 | * |
||
383 | * It extract just the PDF commands that are involved with text positions, and |
||
384 | * the Text Matrix (Tm). These are: BT, ET, TL, Td, TD, Tm, T*, Tj, ', ", and TJ |
||
385 | * |
||
386 | * @param array $extractedDecodedRawData The data extracted by extractDecodeRawData. |
||
387 | * If it is null, the method extractDecodeRawData is called. |
||
388 | * |
||
389 | * @return array An array with the text command of the page |
||
390 | */ |
||
391 | public function getDataCommands($extractedDecodedRawData = null) |
||
521 | } |
||
522 | |||
523 | /** |
||
524 | * Gets the Text Matrix of the text in the page |
||
525 | * |
||
526 | * Return an array where every item is an array where the first item is the |
||
527 | * Text Matrix (Tm) and the second is a string with the text data. The Text matrix |
||
528 | * is an array of 6 numbers. The last 2 numbers are the coordinates X and Y of the |
||
529 | * text. The first 4 numbers has to be with Scalation, Rotation and Skew of the text. |
||
530 | * |
||
531 | * @param array $dataCommands the data extracted by getDataCommands |
||
532 | * if null getDataCommands is called |
||
533 | * |
||
534 | * @return array an array with the data of the page including the Tm information |
||
535 | * of any text in the page |
||
536 | */ |
||
537 | public function getDataTm($dataCommands = null) |
||
724 | } |
||
725 | |||
726 | /** |
||
727 | * Gets text data that are around the given coordinates (X,Y) |
||
728 | * |
||
729 | * If the text is in near the given coordinates (X,Y) (or the TM info), |
||
730 | * the text is returned. The extractedData return by getDataTm, could be use to see |
||
731 | * where is the coordinates of a given text, using the TM info for it. |
||
732 | * |
||
733 | * @param float $x The X value of the coordinate to search for. if null |
||
734 | * just the Y value is considered (same Row) |
||
735 | * @param float $y The Y value of the coordinate to search for |
||
736 | * just the X value is considered (same column) |
||
737 | * @param float $xError The value less or more to consider an X to be "near" |
||
738 | * @param float $yError The value less or more to consider an Y to be "near" |
||
739 | * |
||
740 | * @return array An array of text that are near the given coordinates. If no text |
||
741 | * "near" the x,y coordinate, an empty array is returned. If Both, x |
||
742 | * and y coordinates are null, null is returned. |
||
743 | */ |
||
744 | public function getTextXY($x = null, $y = null, $xError = 0, $yError = 0) |
||
797 |
This check looks for calls to methods that do not seem to exist on a given type. It looks for the method on the type itself as well as in inherited classes or implemented interfaces.
This is most likely a typographical error or the method has been renamed.