1 | <?php |
||
2 | /* For licensing terms, see /license.txt */ |
||
3 | |||
4 | /** |
||
5 | * Defines the OpenOfficeDocument class, which is meant as a conversion |
||
6 | * tool from Office text documents (.doc, .sxw, .odt, .docx) to |
||
7 | * learning paths. |
||
8 | * |
||
9 | * @package chamilo.learnpath |
||
10 | * |
||
11 | * @author Eric Marguin <[email protected]> |
||
12 | * @license GNU/GPL |
||
13 | */ |
||
14 | /** |
||
15 | * Defines the "OpenOfficeTextDocument" child of class "learnpath". |
||
16 | */ |
||
17 | require_once 'openoffice_document.class.php'; |
||
18 | require_once api_get_path(LIBRARY_PATH).'specific_fields_manager.lib.php'; |
||
19 | |||
20 | /** |
||
21 | * @package chamilo.learnpath.openofficedocument |
||
22 | */ |
||
23 | class OpenOfficeTextDocument extends OpenofficeDocument |
||
24 | { |
||
25 | public $split_steps; |
||
26 | |||
27 | /** |
||
28 | * Class constructor. Calls the parent class and initialises the local attribute split_steps. |
||
29 | * |
||
30 | * @param bool Whether to split steps (true) or make one large page (false) |
||
31 | * @param string Course code |
||
32 | * @param int Resource ID |
||
33 | * @param int Creator user id |
||
34 | */ |
||
35 | public function __construct( |
||
36 | $split_steps = false, |
||
37 | $course_code = null, |
||
38 | $resource_id = null, |
||
39 | $user_id = null |
||
40 | ) { |
||
41 | $this->split_steps = $split_steps; |
||
42 | parent::__construct($course_code, $resource_id, $user_id); |
||
43 | } |
||
44 | |||
45 | /** |
||
46 | * Gets html pages and compose them into a learning path. |
||
47 | * |
||
48 | * @param array The files that will compose the generated learning path. Unused so far. |
||
49 | * |
||
50 | * @return bool False if file does not exit. Nothing otherwise. |
||
51 | */ |
||
52 | public function make_lp($files = []) |
||
53 | { |
||
54 | $_course = api_get_course_info(); |
||
55 | // We get a content where ||page_break|| indicates where the page is broken. |
||
56 | if (!file_exists($this->base_work_dir.'/'.$this->created_dir.'/'.$this->file_name.'.html')) { |
||
57 | return false; |
||
58 | } |
||
59 | $content = file_get_contents($this->base_work_dir.'/'.$this->created_dir.'/'.$this->file_name.'.html'); |
||
60 | |||
61 | unlink($this->base_work_dir.'/'.$this->file_path); |
||
62 | unlink($this->base_work_dir.'/'.$this->created_dir.'/'.$this->file_name.'.html'); |
||
63 | |||
64 | // The file is utf8 encoded and it seems to make problems with special quotes. |
||
65 | // then we htmlentities that, we replace these quotes and html_entity_decode that in good charset. |
||
66 | $charset = api_get_system_encoding(); |
||
67 | $content = api_htmlentities($content, ENT_COMPAT, $this->original_charset); |
||
68 | $content = str_replace('’', '\'', $content); |
||
69 | $content = api_convert_encoding($content, $charset, $this->original_charset); |
||
70 | $content = str_replace($this->original_charset, $charset, $content); |
||
71 | $content = api_html_entity_decode($content, ENT_COMPAT, $charset); |
||
72 | |||
73 | // Set the path to pictures to absolute (so that it can be modified in fckeditor). |
||
74 | $content = preg_replace("|src=\"([^\"]*)|i", "src=\"".api_get_path(REL_COURSE_PATH).$_course['path'].'/document'.$this->created_dir."/\\1", $content); |
||
75 | |||
76 | list($header, $body) = explode('<BODY', $content); |
||
77 | |||
78 | $body = '<BODY'.$body; |
||
79 | |||
80 | // Remove font-family styles. |
||
81 | $header = preg_replace("|font\-family[^;]*;|i", '', $header); |
||
82 | |||
83 | // Chamilo styles. |
||
84 | $my_style = api_get_setting('stylesheets'); |
||
85 | if (empty($my_style)) { |
||
86 | $my_style = 'chamilo'; |
||
87 | } |
||
88 | $style_to_import = "<style type=\"text/css\">\r\n"; |
||
89 | $style_to_import .= '@import "'.api_get_path(WEB_CODE_PATH).'css/'.$my_style.'/default.css";'."\n"; |
||
90 | $style_to_import .= "</style>\r\n"; |
||
91 | $header = preg_replace("|</head>|i", "\r\n$style_to_import\r\n\\0", $header); |
||
92 | |||
93 | // Line break before and after picture. |
||
94 | $header = str_replace('p {', 'p {clear:both;', $header); |
||
95 | |||
96 | $header = str_replace('absolute', 'relative', $header); |
||
97 | |||
98 | switch ($this->split_steps) { |
||
99 | case 'per_page': |
||
100 | $this->dealPerPage($header, $body); |
||
101 | break; |
||
102 | case 'per_chapter': |
||
103 | $this->dealPerChapter($header, $body); |
||
104 | break; |
||
105 | } |
||
106 | } |
||
107 | |||
108 | /** |
||
109 | * Manages dir/chapter splitting. |
||
110 | * |
||
111 | * @param string Chapter header |
||
112 | * @param string Content |
||
113 | */ |
||
114 | public function dealPerChapter($header, $content) |
||
115 | { |
||
116 | $_course = api_get_course_info(); |
||
117 | $content = str_replace('||page_break||', '', $content); |
||
118 | |||
119 | // Get all the h1. |
||
120 | preg_match_all("|<h1[^>]*>([^(h1)+]*)</h1>|is", $content, $matches_temp); |
||
121 | |||
122 | // Empty the fake dir/chapters. |
||
123 | $new_index = 0; |
||
124 | for ($i = 0; $i < count($matches_temp[0]); $i++) { |
||
0 ignored issues
–
show
|
|||
125 | if (trim($matches_temp[1][$i]) !== '') { |
||
126 | $matches[0][$new_index] = $matches_temp[0][$i]; |
||
127 | $matches[1][$new_index] = $matches_temp[1][$i]; |
||
128 | $new_index++; |
||
129 | } |
||
130 | } |
||
131 | |||
132 | // Add intro item. |
||
133 | $intro_content = api_substr($content, 0, api_strpos($content, $matches[0][0])); |
||
134 | $items_to_create[get_lang('Introduction')] = $intro_content; |
||
135 | |||
136 | for ($i = 0; $i < count($matches[0]); $i++) { |
||
137 | if (empty($matches[1][$i])) { |
||
138 | continue; |
||
139 | } |
||
140 | |||
141 | $content = api_strstr($content, $matches[0][$i]); |
||
142 | if ($i + 1 !== count($matches[0])) { |
||
143 | $dir_content = api_substr($content, 0, api_strpos($content, $matches[0][$i + 1])); |
||
144 | } else { |
||
145 | $dir_content = $content; |
||
146 | } |
||
147 | $items_to_create[$matches[1][$i]] = $dir_content; |
||
148 | } |
||
149 | |||
150 | $i = 0; |
||
151 | $previous = 0; // @todo define this variable properly |
||
152 | foreach ($items_to_create as $item_title => $item_content) { |
||
153 | $i++; |
||
154 | $page_content = $this->format_page_content($header, $item_content); |
||
155 | |||
156 | $html_file = $this->created_dir.'-'.$i.'.html'; |
||
157 | $handle = fopen($this->base_work_dir.$this->created_dir.'/'.$html_file, 'w+'); |
||
158 | fwrite($handle, $page_content); |
||
159 | fclose($handle); |
||
160 | |||
161 | $document_id = add_document( |
||
162 | $_course, |
||
163 | $this->created_dir.'/'.$html_file, |
||
164 | 'file', |
||
165 | filesize($this->base_work_dir.$this->created_dir.'/'.$html_file), |
||
166 | $html_file |
||
167 | ); |
||
168 | |||
169 | if ($document_id) { |
||
170 | // Put the document in item_property update. |
||
171 | api_item_property_update( |
||
172 | $_course, |
||
173 | TOOL_DOCUMENT, |
||
174 | $document_id, |
||
175 | 'DocumentAdded', |
||
176 | api_get_user_id(), |
||
177 | 0, |
||
178 | 0, |
||
179 | null, |
||
180 | null, |
||
181 | api_get_session_id() |
||
182 | ); |
||
183 | |||
184 | $infos = pathinfo($this->filepath); |
||
185 | $slide_name = strip_tags(nl2br($item_title)); |
||
186 | $slide_name = str_replace(["\r\n", "\r", "\n"], '', $slide_name); |
||
187 | $slide_name = api_html_entity_decode($slide_name, ENT_COMPAT, api_get_system_encoding()); |
||
188 | $previous = learnpath::add_item( |
||
189 | 0, |
||
190 | $previous, |
||
191 | 'document', |
||
192 | $document_id, |
||
193 | $slide_name, |
||
194 | '' |
||
195 | ); |
||
196 | if ($this->first_item == 0) { |
||
197 | $this->first_item = (int) $previous; |
||
198 | } |
||
199 | } |
||
200 | } |
||
201 | } |
||
202 | |||
203 | /** |
||
204 | * Manages page splitting. |
||
205 | * |
||
206 | * @param string Page header |
||
207 | * @param string Page body |
||
208 | */ |
||
209 | public function dealPerPage($header, $body) |
||
210 | { |
||
211 | $_course = api_get_course_info(); |
||
212 | // Split document to pages. |
||
213 | $pages = explode('||page_break||', $body); |
||
214 | foreach ($pages as $key => $page_content) { |
||
215 | // For every pages, we create a new file. |
||
216 | $key++; |
||
217 | $page_content = $this->format_page_content( |
||
218 | $header, |
||
219 | $page_content, |
||
220 | $this->base_work_dir.$this->created_dir |
||
221 | ); |
||
222 | $html_file = $this->created_dir.'-'.$key.'.html'; |
||
223 | $handle = fopen($this->base_work_dir.$this->created_dir.'/'.$html_file, 'w+'); |
||
224 | fwrite($handle, $page_content); |
||
225 | fclose($handle); |
||
226 | |||
227 | $document_id = add_document( |
||
228 | $_course, |
||
229 | $this->created_dir.$html_file, |
||
230 | 'file', |
||
231 | filesize($this->base_work_dir.$this->created_dir.$html_file), |
||
232 | $html_file |
||
233 | ); |
||
234 | |||
235 | $slide_name = ''; |
||
236 | $previous = 0; // @todo define this variable properly |
||
237 | if ($document_id) { |
||
238 | // Put the document in item_property update. |
||
239 | api_item_property_update( |
||
240 | $_course, |
||
241 | TOOL_DOCUMENT, |
||
242 | $document_id, |
||
243 | 'DocumentAdded', |
||
244 | api_get_user_id(), |
||
245 | 0, |
||
246 | 0, |
||
247 | null, |
||
248 | null, |
||
249 | api_get_session_id() |
||
250 | ); |
||
251 | |||
252 | $infos = pathinfo($this->filepath); |
||
253 | $slide_name = 'Page '.str_repeat('0', 2 - strlen($key)).$key; |
||
254 | $previous = learnpath::add_item( |
||
255 | 0, |
||
256 | $previous, |
||
257 | 'document', |
||
258 | $document_id, |
||
259 | $slide_name, |
||
260 | '' |
||
261 | ); |
||
262 | if ($this->first_item == 0) { |
||
263 | $this->first_item = (int) $previous; |
||
264 | } |
||
265 | // Code for text indexing. |
||
266 | if (isset($_POST['index_document']) && $_POST['index_document']) { |
||
267 | //echo Display::return_message(print_r($_POST)); |
||
268 | $di = new ChamiloIndexer(); |
||
269 | isset($_POST['language']) ? $lang = Database::escape_string($_POST['language']) : $lang = 'english'; |
||
270 | $di->connectDb(null, null, $lang); |
||
271 | $ic_slide = new IndexableChunk(); |
||
272 | $ic_slide->addValue('title', $slide_name); |
||
273 | $specific_fields = get_specific_field_list(); |
||
274 | $all_specific_terms = ''; |
||
275 | foreach ($specific_fields as $specific_field) { |
||
276 | if (isset($_REQUEST[$specific_field['code']])) { |
||
277 | $sterms = trim($_REQUEST[$specific_field['code']]); |
||
278 | $all_specific_terms .= ' '.$sterms; |
||
279 | if (!empty($sterms)) { |
||
280 | $sterms = explode(',', $sterms); |
||
281 | foreach ($sterms as $sterm) { |
||
282 | $ic_slide->addTerm(trim($sterm), $specific_field['code']); |
||
283 | } |
||
284 | } |
||
285 | } |
||
286 | } |
||
287 | $page_content = $all_specific_terms.' '.$page_content; |
||
288 | $ic_slide->addValue('content', $page_content); |
||
289 | // Add a comment to say terms separated by commas. |
||
290 | $courseid = api_get_course_id(); |
||
291 | $ic_slide->addCourseId($courseid); |
||
292 | $ic_slide->addToolId(TOOL_LEARNPATH); |
||
293 | $lp_id = $this->lp_id; |
||
294 | $xapian_data = [ |
||
295 | SE_COURSE_ID => $courseid, |
||
296 | SE_TOOL_ID => TOOL_LEARNPATH, |
||
297 | SE_DATA => [ |
||
298 | 'lp_id' => $lp_id, |
||
299 | 'lp_item' => $previous, |
||
300 | 'document_id' => $document_id, |
||
301 | ], |
||
302 | SE_USER => (int) api_get_user_id(), |
||
303 | ]; |
||
304 | $ic_slide->xapian_data = serialize($xapian_data); |
||
305 | $di->addChunk($ic_slide); |
||
306 | // Index and return search engine document id. |
||
307 | $did = $di->index(); |
||
308 | if ($did) { |
||
309 | // Save it to db. |
||
310 | $tbl_se_ref = Database::get_main_table(TABLE_MAIN_SEARCH_ENGINE_REF); |
||
311 | $sql = 'INSERT INTO %s (id, course_code, tool_id, ref_id_high_level, ref_id_second_level, search_did) |
||
312 | VALUES (NULL , \'%s\', \'%s\', %s, %s, %s)'; |
||
313 | $sql = sprintf( |
||
314 | $sql, |
||
315 | $tbl_se_ref, |
||
316 | api_get_course_id(), |
||
317 | TOOL_LEARNPATH, |
||
318 | $lp_id, |
||
319 | $previous, |
||
320 | $did |
||
321 | ); |
||
322 | Database::query($sql); |
||
323 | } |
||
324 | } |
||
325 | } |
||
326 | } |
||
327 | } |
||
328 | |||
329 | /** |
||
330 | * Returns additional Java command parameters. |
||
331 | * |
||
332 | * @return string The additional parameters to be used in the Java call |
||
333 | */ |
||
334 | public function add_command_parameters() |
||
335 | { |
||
336 | return ' -d woogie ' |
||
337 | .Security::sanitizeExecParam($this->base_work_dir.'/'.$this->file_path) |
||
338 | .' ' |
||
339 | .Security::sanitizeExecParam($this->base_work_dir.$this->created_dir.'/'.$this->file_name.'.html'); |
||
340 | } |
||
341 | |||
342 | /** |
||
343 | * Formats a page content by reorganising the HTML code a little. |
||
344 | * |
||
345 | * @param string Page header |
||
346 | * @param string Page content |
||
347 | * |
||
348 | * @return string Formatted page content |
||
349 | */ |
||
350 | public function format_page_content($header, $content) |
||
351 | { |
||
352 | // Limit the width of the doc. |
||
353 | list($max_width, $max_height) = explode('x', api_get_setting('service_ppt2lp', 'size')); |
||
354 | |||
355 | $content = preg_replace("|<body[^>]*>|i", "\\0\r\n<div style=\"width:".$max_width."\">", $content, -1, $count); |
||
356 | if ($count < 1) { |
||
357 | $content = '<body><div style="width:'.$max_width.'">'.$content; |
||
358 | } |
||
359 | |||
360 | $content = preg_replace('|</body>|i', '</div>\\0', $content, -1, $count); |
||
361 | if ($count < 1) { |
||
362 | $content = $content.'</div></body>'; |
||
363 | } |
||
364 | |||
365 | // Add the headers. |
||
366 | $content = $header.$content; |
||
367 | |||
368 | // Resize all the picture to the max_width-10 |
||
369 | preg_match_all("|<img[^src]*src=\"([^\"]*)\"[^>]*>|i", $content, $images); |
||
370 | |||
371 | foreach ($images[1] as $key => $image) { |
||
372 | // Check if the <img tag soon has a width attribute. |
||
373 | $defined_width = preg_match("|width=([^\s]*)|i", $images[0][$key], $img_width); |
||
374 | $img_width = $img_width[1]; |
||
375 | if (!$defined_width) { |
||
376 | $image_size = api_getimagesize($this->base_work_dir.$this->created_dir.'/'.$image); |
||
377 | $img_width = $image_size['width']; |
||
378 | $img_height = $image_size['height']; |
||
379 | |||
380 | $new_width = $max_width - 10; |
||
381 | if ($img_width > $new_width) { |
||
382 | $picture_resized = str_ireplace('<img', '<img width="'.$new_width.'" ', $images[0][$key]); |
||
383 | $content = str_replace($images[0][$key], $picture_resized, $content); |
||
384 | } |
||
385 | } elseif ($img_width > $max_width - 10) { |
||
386 | $picture_resized = str_ireplace( |
||
387 | 'width='.$img_width, |
||
388 | 'width="'.($max_width - 10).'"', |
||
389 | $images[0][$key] |
||
390 | ); |
||
391 | $content = str_replace( |
||
392 | $images[0][$key], |
||
393 | $picture_resized, |
||
394 | $content |
||
395 | ); |
||
396 | } |
||
397 | } |
||
398 | |||
399 | return $content; |
||
400 | } |
||
401 | |||
402 | /** |
||
403 | * Add documents to the visioconference (to be implemented). |
||
404 | */ |
||
405 | public function add_docs_to_visio() |
||
406 | { |
||
407 | } |
||
408 | } |
||
409 |
If the size of the collection does not change during the iteration, it is generally a good practice to compute it beforehand, and not on each iteration: