openoffice_text.class.php 15 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368
  1. <?php
  2. /* For licensing terms, see /license.txt */
  3. /**
  4. * Defines the OpenofficeDocument class, which is meant as a conversion
  5. * tool from Office text documents (.doc, .sxw, .odt, .docx) to
  6. * learning paths
  7. * @package chamilo.learnpath
  8. * @author Eric Marguin <eric.marguin@dokeos.com>
  9. * @license GNU/GPL
  10. */
  11. /**
  12. * Defines the "OpenofficeText" child of class "learnpath"
  13. */
  14. require_once 'openoffice_document.class.php';
  15. if (api_get_setting('search_enabled') == 'true') {
  16. require_once api_get_path(LIBRARY_PATH).'specific_fields_manager.lib.php';
  17. require_once api_get_path(LIBRARY_PATH).'search/ChamiloIndexer.class.php';
  18. require_once api_get_path(LIBRARY_PATH).'search/IndexableChunk.class.php';
  19. }
  20. /**
  21. * @package chamilo.learnpath.OpenofficeDocument
  22. */
  23. class OpenofficeText extends OpenofficeDocument {
  24. public $split_steps;
  25. /**
  26. * Class constructor. Calls the parent class and initialises the local attribute split_steps
  27. * @param boolean Whether to split steps (true) or make one large page (false)
  28. * @param string Course code
  29. * @param integer Resource ID
  30. * @param integer Creator user id
  31. */
  32. public function __construct($split_steps = false, $course_code = null, $resource_id = null, $user_id = null) {
  33. $this -> split_steps = $split_steps;
  34. parent::__construct($course_code, $resource_id, $user_id);
  35. }
  36. /**
  37. * Gets html pages and compose them into a learning path
  38. * @param array The files that will compose the generated learning path. Unused so far.
  39. * @return boolean False if file does not exit. Nothing otherwise.
  40. */
  41. public function make_lp($files = array())
  42. {
  43. $_course = api_get_course_info();
  44. // We get a content where ||page_break|| indicates where the page is broken.
  45. if (!file_exists($this->base_work_dir.'/'.$this->created_dir.'/'.$this->file_name.'.html')) { return false; }
  46. $content = file_get_contents($this->base_work_dir.'/'.$this->created_dir.'/'.$this->file_name.'.html');
  47. unlink($this->base_work_dir.'/'.$this->file_path);
  48. unlink($this->base_work_dir.'/'.$this->created_dir.'/'.$this->file_name.'.html');
  49. // The file is utf8 encoded and it seems to make problems with special quotes.
  50. // Then we htmlentities that, we replace these quotes and html_entity_decode that in good charset.
  51. $charset = api_get_system_encoding();
  52. $content = api_htmlentities($content, ENT_COMPAT, $this->original_charset);
  53. $content = str_replace('&rsquo;', '\'', $content);
  54. $content = api_convert_encoding($content, $charset, $this->original_charset);
  55. $content = str_replace($this->original_charset, $charset, $content);
  56. $content = api_html_entity_decode($content, ENT_COMPAT, $charset);
  57. // Set the path to pictures to absolute (so that it can be modified in fckeditor).
  58. $content = preg_replace("|src=\"([^\"]*)|i", "src=\"".api_get_path(REL_COURSE_PATH).$_course['path'].'/document'.$this->created_dir."/\\1", $content);
  59. list($header, $body) = explode('<BODY', $content);
  60. $body = '<BODY'.$body;
  61. // Remove font-family styles.
  62. $header = preg_replace("|font\-family[^;]*;|i", '', $header);
  63. // Chamilo styles.
  64. $my_style = api_get_setting('stylesheets');
  65. if (empty($my_style)) { $my_style = 'chamilo'; }
  66. $style_to_import = "<style type=\"text/css\">\r\n";
  67. $style_to_import .= '@import "'.api_get_path(WEB_CODE_PATH).'css/'.$my_style.'/default.css";'."\n";
  68. $style_to_import .= "</style>\r\n";
  69. $header = preg_replace("|</head>|i", "\r\n$style_to_import\r\n\\0", $header);
  70. // Line break before and after picture.
  71. $header = str_replace('p {', 'p {clear:both;', $header);
  72. $header = str_replace('absolute', 'relative', $header);
  73. switch ($this->split_steps) {
  74. case 'per_page':
  75. $this -> dealPerPage($header, $body);
  76. break;
  77. case 'per_chapter':
  78. $this -> dealPerChapter($header, $body);
  79. break;
  80. }
  81. }
  82. /**
  83. * Manages dir/chapter splitting
  84. * @param string Chapter header
  85. * @param string Content
  86. * @return void
  87. */
  88. public function dealPerChapter($header, $content)
  89. {
  90. $_course = api_get_course_info();
  91. $content = str_replace('||page_break||', '', $content);
  92. // Get all the h1.
  93. preg_match_all("|<h1[^>]*>([^(h1)+]*)</h1>|is", $content, $matches_temp);
  94. // Empty the fake chapters.
  95. $new_index = 0;
  96. for ($i = 0; $i < count($matches_temp[0]); $i++) {
  97. if (trim($matches_temp[1][$i]) !== '') {
  98. $matches[0][$new_index] = $matches_temp[0][$i];
  99. $matches[1][$new_index] = $matches_temp[1][$i];
  100. $new_index++;
  101. }
  102. }
  103. // Add intro item.
  104. $intro_content = substr($content, 0, strpos($content, $matches[0][0]));
  105. $items_to_create[get_lang('Introduction')] = $intro_content;
  106. for ($i = 0; $i < count($matches[0]); $i++) {
  107. if (empty($matches[1][$i]))
  108. continue;
  109. $content = strstr($content, $matches[0][$i]);
  110. if ($i + 1 !== count($matches[0])) {
  111. $dir_content = substr($content, 0, strpos($content, $matches[0][$i + 1]));
  112. } else {
  113. $dir_content = $content;
  114. }
  115. $items_to_create[$matches[1][$i]] = $dir_content;
  116. }
  117. $i = 0;
  118. foreach ($items_to_create as $item_title => $item_content) {
  119. $i++;
  120. $page_content = $this->format_page_content($header, $item_content);
  121. $html_file = $this->created_dir.'-'.$i.'.html';
  122. $handle = fopen($this->base_work_dir.$this->created_dir.'/'.$html_file, 'w+');
  123. fwrite($handle, $page_content);
  124. fclose($handle);
  125. $document_id = add_document(
  126. $_course,
  127. $this->created_dir.'/'.$html_file,
  128. 'file',
  129. filesize(
  130. $this->base_work_dir.$this->created_dir.'/'.$html_file
  131. ),
  132. $html_file
  133. );
  134. if ($document_id) {
  135. // Put the document in item_property update.
  136. api_item_property_update(
  137. $_course,
  138. TOOL_DOCUMENT,
  139. $document_id,
  140. 'DocumentAdded',
  141. $_SESSION['_uid'],
  142. 0,
  143. 0,
  144. null,
  145. null,
  146. api_get_session_id()
  147. );
  148. $infos = pathinfo($this->filepath);
  149. $slide_name = strip_tags(nl2br($item_title));
  150. $slide_name = str_replace(array("\r\n", "\r", "\n"), '', $slide_name);
  151. $slide_name = html_entity_decode($slide_name);
  152. $previous = learnpath::add_item(
  153. 0,
  154. $previous,
  155. 'document',
  156. $document_id,
  157. $slide_name,
  158. ''
  159. );
  160. if ($this->first_item == 0) {
  161. $this->first_item = $previous;
  162. }
  163. }
  164. }
  165. }
  166. /**
  167. * Manages page splitting
  168. * @param string Page header
  169. * @param string Page body
  170. * @return void
  171. */
  172. public function dealPerPage($header, $body)
  173. {
  174. $_course = api_get_course_info();
  175. // Split document to pages.
  176. $pages = explode('||page_break||', $body);
  177. $first_item = 0;
  178. foreach ($pages as $key => $page_content) {
  179. // For every pages, we create a new file.
  180. $key += 1;
  181. $page_content = $this->format_page_content($header, $page_content, $this->base_work_dir.$this->created_dir);
  182. $html_file = $this->created_dir.'-'.$key.'.html';
  183. $handle = fopen($this->base_work_dir.$this->created_dir.'/'.$html_file, 'w+');
  184. fwrite($handle, $page_content);
  185. fclose($handle);
  186. $document_id = add_document(
  187. $_course,
  188. $this->created_dir.$html_file,
  189. 'file',
  190. filesize($this->base_work_dir.$this->created_dir.$html_file),
  191. $html_file
  192. );
  193. $slide_name = '';
  194. if ($document_id) {
  195. // Put the document in item_property update.
  196. api_item_property_update(
  197. $_course,
  198. TOOL_DOCUMENT,
  199. $document_id,
  200. 'DocumentAdded',
  201. $_SESSION['_uid'],
  202. 0,
  203. 0,
  204. null,
  205. null,
  206. api_get_session_id()
  207. );
  208. $infos = pathinfo($this->filepath);
  209. $slide_name = 'Page '.str_repeat('0', 2 - strlen($key)).$key;
  210. $previous = learnpath::add_item(0, $previous, 'document', $document_id, $slide_name, '');
  211. if ($this->first_item == 0) {
  212. $this->first_item = $previous;
  213. }
  214. // Code for text indexing.
  215. if (api_get_setting('search_enabled') == 'true') {
  216. if (isset($_POST['index_document']) && $_POST['index_document']) {
  217. //Display::display_normal_message(print_r($_POST));
  218. $di = new ChamiloIndexer();
  219. isset($_POST['language']) ? $lang = Database::escape_string($_POST['language']) : $lang = 'english';
  220. $di->connectDb(NULL, NULL, $lang);
  221. $ic_slide = new IndexableChunk();
  222. $ic_slide->addValue('title', $slide_name);
  223. $specific_fields = get_specific_field_list();
  224. $all_specific_terms = '';
  225. foreach ($specific_fields as $specific_field) {
  226. if (isset($_REQUEST[$specific_field['code']])) {
  227. $sterms = trim($_REQUEST[$specific_field['code']]);
  228. $all_specific_terms .= ' '.$sterms;
  229. if (!empty($sterms)) {
  230. $sterms = explode(',', $sterms);
  231. foreach ($sterms as $sterm) {
  232. $ic_slide->addTerm(trim($sterm), $specific_field['code']);
  233. }
  234. }
  235. }
  236. }
  237. $page_content = $all_specific_terms.' '.$page_content;
  238. $ic_slide->addValue('content', $page_content);
  239. // Add a comment to say terms separated by commas.
  240. $courseid = api_get_course_id();
  241. $ic_slide->addCourseId($courseid);
  242. $ic_slide->addToolId(TOOL_LEARNPATH);
  243. $lp_id = $this->lp_id;
  244. $xapian_data = array(
  245. SE_COURSE_ID => $courseid,
  246. SE_TOOL_ID => TOOL_LEARNPATH,
  247. SE_DATA => array('lp_id' => $lp_id, 'lp_item'=> $previous, 'document_id' => $document_id),
  248. SE_USER => (int) api_get_user_id(),
  249. );
  250. $ic_slide->xapian_data = serialize($xapian_data);
  251. $di->addChunk($ic_slide);
  252. // Index and return search engine document id.
  253. $did = $di->index();
  254. if ($did) {
  255. // Save it to db.
  256. $tbl_se_ref = Database::get_main_table(TABLE_MAIN_SEARCH_ENGINE_REF);
  257. $sql = 'INSERT INTO %s (id, course_code, tool_id, ref_id_high_level, ref_id_second_level, search_did)
  258. VALUES (NULL , \'%s\', \'%s\', %s, %s, %s)';
  259. $sql = sprintf($sql, $tbl_se_ref, api_get_course_id(), TOOL_LEARNPATH, $lp_id, $previous, $did);
  260. Database::query($sql);
  261. }
  262. }
  263. }
  264. }
  265. }
  266. }
  267. /**
  268. * Returns additional Java command parameters
  269. * @return string The additional parameters to be used in the Java call
  270. */
  271. public function add_command_parameters() {
  272. return ' -d woogie "'.$this->base_work_dir.'/'.$this->file_path.'" "'.$this->base_work_dir.$this->created_dir.'/'.$this->file_name.'.html"';
  273. }
  274. /**
  275. * Formats a page content by reorganising the HTML code a little
  276. * @param string Page header
  277. * @param string Page content
  278. * @return string Formatted page content
  279. */
  280. public function format_page_content($header, $content) {
  281. // Limit the width of the doc.
  282. list($max_width, $max_height) = explode('x', api_get_setting('service_ppt2lp', 'size'));
  283. $content = preg_replace("|<body[^>]*>|i", "\\0\r\n<div style=\"width:".$max_width."\">", $content, -1, $count);
  284. if ($count < 1) {
  285. $content = '<body><div style="width:'.$max_width.'">'.$content;
  286. }
  287. $content = preg_replace('|</body>|i', '</div>\\0', $content, -1, $count);
  288. if ($count < 1) {
  289. $content = $content.'</div></body>';
  290. }
  291. // Add the headers.
  292. $content = $header.$content;
  293. // Resize all the picture to the max_width-10
  294. preg_match_all("|<img[^src]*src=\"([^\"]*)\"[^>]*>|i", $content, $images);
  295. foreach ($images[1] as $key => $image) {
  296. // Check if the <img tag soon has a width attribute.
  297. $defined_width = preg_match("|width=([^\s]*)|i", $images[0][$key], $img_width);
  298. $img_width = $img_width[1];
  299. if (!$defined_width) {
  300. list($img_width, $img_height, $type) = getimagesize($this->base_work_dir.$this->created_dir.'/'.$image);
  301. $new_width = $max_width - 10;
  302. if ($img_width > $new_width) {
  303. $picture_resized = str_ireplace('<img', '<img width="'.$new_width.'" ', $images[0][$key]);
  304. $content = str_replace($images[0][$key], $picture_resized, $content);
  305. }
  306. } elseif ($img_width > $max_width - 10) {
  307. $picture_resized = str_ireplace('width='.$img_width, 'width="'.($max_width - 10).'"', $images[0][$key]);
  308. $content = str_replace($images[0][$key], $picture_resized, $content);
  309. }
  310. }
  311. return $content;
  312. }
  313. /**
  314. * Add documents to the visioconference (to be implemented)
  315. */
  316. public function add_docs_to_visio() {
  317. }
  318. }