openoffice_text.class.php 12 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352
  1. <?php //$id:$
  2. /**
  3. * Defines the OpenofficeDocument class, which is meant as a conversion
  4. * tool from Office text documents (.doc, .sxw, .odt, .docx) to
  5. * learning paths
  6. * @package dokeos.learnpath
  7. * @author Eric Marguin <eric.marguin@dokeos.com>
  8. * @license GNU/GPL - See Doke
  9. /**
  10. * Defines the "OpenofficeText" child of class "learnpath"
  11. * @package dokeos.learnpath.OpenofficeDocument
  12. */
  13. require_once('openoffice_document.class.php');
  14. if (api_get_setting('search_enabled')=='true') {
  15. require_once(api_get_path(LIBRARY_PATH) . 'specific_fields_manager.lib.php');
  16. require_once(api_get_path(LIBRARY_PATH).'search/DokeosIndexer.class.php');
  17. require_once(api_get_path(LIBRARY_PATH).'search/IndexableChunk.class.php');
  18. }
  19. class OpenofficeText extends OpenofficeDocument {
  20. public $split_steps;
  21. /**
  22. * Class constructor. Calls the parent class and initialises the local attribute split_steps
  23. * @param boolean Whether to split steps (true) or make one large page (false)
  24. * @param string Course code
  25. * @param integer Resource ID
  26. * @param integer Creator user id
  27. * @return void
  28. */
  29. function OpenofficeText($split_steps=false, $course_code=null, $resource_id=null,$user_id=null)
  30. {
  31. $this -> split_steps = $split_steps;
  32. parent::OpenofficeDocument($course_code, $resource_id, $user_id);
  33. }
  34. /**
  35. * Gets html pages and compose them into a learning path
  36. * @param array The files that will compose the generated learning path. Unused so far.
  37. * @return boolean False if file does not exit. Nothing otherwise.
  38. */
  39. function make_lp($files=array())
  40. {
  41. global $_course;
  42. // we get a content where ||page_break|| indicates where the page is broken
  43. if(!file_exists($this->base_work_dir.'/'.$this->created_dir.'/'.$this->file_name.'.html')){return false;}
  44. $content = file_get_contents($this->base_work_dir.'/'.$this->created_dir.'/'.$this->file_name.'.html');
  45. unlink($this->base_work_dir.'/'.$this->file_path);
  46. unlink($this->base_work_dir.'/'.$this->created_dir.'/'.$this->file_name.'.html');
  47. // the file is utf8 encoded and it seems to make problems with special quotes.
  48. // then we htmlentities that, we replace these quotes and html_entity_decode that in good charset
  49. $charset = api_get_setting('platform_charset');
  50. $content = api_htmlentities($content,ENT_COMPAT,$this->original_charset);
  51. $content = str_replace('&rsquo;','\'',$content);
  52. $content = api_convert_encoding($content, $charset, $this->original_charset);
  53. $content = str_replace($this->original_charset,$charset,$content);
  54. $content = api_html_entity_decode($content, ENT_COMPAT, $charset);
  55. // set the path to pictures to absolute (so that it can be modified in fckeditor)
  56. $content = preg_replace("|src=\"([^\"]*)|i", "src=\"".api_get_path(REL_COURSE_PATH).$_course['path'].'/document'.$this->created_dir."/\\1", $content);
  57. list($header, $body) = explode('<BODY',$content);
  58. $body = '<BODY'.$body;
  59. // remove font-family styles
  60. $header = preg_replace("|font\-family[^;]*;|i", "",$header);
  61. // dokeos styles
  62. $my_style = api_get_setting('stylesheets');
  63. if(empty($my_style)){$my_style = 'dokeos_classic';}
  64. $style_to_import = "<style type=\"text/css\">\r\n";
  65. $style_to_import .= '@import "'.api_get_path(WEB_CODE_PATH).'css/'.$my_style.'/default.css";'."\n";
  66. $style_to_import .= '@import "'.api_get_path(WEB_CODE_PATH).'css/'.$my_style.'/course.css";'."\n";
  67. $style_to_import .= "</style>\r\n";
  68. $header = preg_replace("|</head>|i", "\r\n$style_to_import\r\n\\0",$header);
  69. // line break before and after picture
  70. $header = str_replace('p {','p {clear:both;',$header);
  71. $header = str_replace('absolute','relative',$header);
  72. switch($this->split_steps)
  73. {
  74. case 'per_page' : $this -> dealPerPage($header,$body); break;
  75. case 'per_chapter' : $this -> dealPerChapter($header,$body); break;
  76. }
  77. }
  78. /**
  79. * Manages chapter splitting
  80. * @param string Chapter header
  81. * @param string Content
  82. * @return void
  83. */
  84. function dealPerChapter($header, $content)
  85. {
  86. global $_course;
  87. $content = str_replace('||page_break||','',$content);
  88. // get all the h1
  89. preg_match_all("|<h1[^>]*>([^(h1)+]*)</h1>|is",$content,$matches_temp);
  90. //empty the fake chapters
  91. $new_index = 0;
  92. for ($i=0 ; $i<count($matches_temp[0]) ; $i++) {
  93. if(trim($matches_temp[1][$i])!=='')
  94. {
  95. $matches[0][$new_index] = $matches_temp[0][$i];
  96. $matches[1][$new_index] = $matches_temp[1][$i];
  97. $new_index++;
  98. }
  99. }
  100. // add intro item
  101. $intro_content = substr($content, 0, strpos($content, $matches[0][0]));
  102. $items_to_create[get_lang('Introduction')] = $intro_content;
  103. for ($i=0 ; $i<count($matches[0]) ; $i++) {
  104. if(empty($matches[1][$i]))
  105. continue;
  106. $content = strstr($content,$matches[0][$i]);
  107. if($i+1!==count($matches[0]))
  108. {
  109. $chapter_content = substr($content, 0, strpos($content, $matches[0][$i+1]));
  110. }
  111. else
  112. {
  113. $chapter_content = $content;
  114. }
  115. $items_to_create[$matches[1][$i]] = $chapter_content;
  116. }
  117. $i = 0;
  118. foreach($items_to_create as $item_title=>$item_content)
  119. {
  120. $i++;
  121. $page_content = $this->format_page_content($header, $item_content);
  122. $html_file = $this->created_dir.'-'.$i.'.html';
  123. $handle = fopen($this->base_work_dir.$this->created_dir.'/'.$html_file,'w+');
  124. fwrite($handle, $page_content);
  125. fclose($handle);
  126. $document_id = add_document($_course,$this->created_dir.'/'.$html_file,'file',filesize($this->base_work_dir.$this->created_dir.'/'.$html_file),$html_file);
  127. if ($document_id){
  128. //put the document in item_property update
  129. api_item_property_update($_course,TOOL_DOCUMENT,$document_id,'DocumentAdded',$_SESSION['_uid'],0,0);
  130. $infos = pathinfo($this->filepath);
  131. $slide_name = strip_tags(nl2br($item_title));
  132. $slide_name = str_replace(array("\r\n", "\r", "\n"), "", $slide_name);
  133. $slide_name = html_entity_decode($slide_name);
  134. $previous = learnpath::add_item(0, $previous, 'document', $document_id, $slide_name, '');
  135. if($this->first_item == 0){
  136. $this->first_item = $previous;
  137. }
  138. }
  139. }
  140. }
  141. /**
  142. * Manages page splitting
  143. * @param string Page header
  144. * @param string Page body
  145. * @return void
  146. */
  147. function dealPerPage($header,$body)
  148. {
  149. global $_course;
  150. // split document to pages
  151. $pages = explode('||page_break||',$body);
  152. $first_item = 0;
  153. foreach($pages as $key=>$page_content)
  154. { // for every pages, we create a new file
  155. $key +=1;
  156. $page_content = $this->format_page_content($header, $page_content, $this->base_work_dir.$this->created_dir);
  157. $html_file = $this->created_dir.'-'.$key.'.html';
  158. $handle = fopen($this->base_work_dir.$this->created_dir.'/'.$html_file,'w+');
  159. fwrite($handle, $page_content);
  160. fclose($handle);
  161. $document_id = add_document($_course,$this->created_dir.$html_file,'file',filesize($this->base_work_dir.$this->created_dir.$html_file),$html_file);
  162. $slide_name = '';
  163. if ($document_id) {
  164. //put the document in item_property update
  165. api_item_property_update($_course,TOOL_DOCUMENT,$document_id,'DocumentAdded',$_SESSION['_uid'],0,0);
  166. $infos = pathinfo($this->filepath);
  167. $slide_name = 'Page '.str_repeat('0',2-strlen($key)).$key;
  168. $previous = learnpath::add_item(0, $previous, 'document', $document_id, $slide_name, '');
  169. if($this->first_item == 0) {
  170. $this->first_item = $previous;
  171. }
  172. // code for text indexing
  173. if (api_get_setting('search_enabled')=='true') {
  174. if (isset($_POST['index_document']) && $_POST['index_document']) {
  175. //Display::display_normal_message(print_r($_POST));
  176. $di = new DokeosIndexer();
  177. isset($_POST['language'])? $lang=Database::escape_string($_POST['language']): $lang = 'english';
  178. $di->connectDb(NULL, NULL, $lang);
  179. $ic_slide = new IndexableChunk();
  180. $ic_slide->addValue("title", $slide_name);
  181. $specific_fields = get_specific_field_list();
  182. $all_specific_terms = '';
  183. foreach ($specific_fields as $specific_field) {
  184. if (isset($_REQUEST[$specific_field['code']])) {
  185. $sterms = trim($_REQUEST[$specific_field['code']]);
  186. $all_specific_terms .= ' '. $sterms;
  187. if (!empty($sterms)) {
  188. $sterms = explode(',', $sterms);
  189. foreach ($sterms as $sterm) {
  190. $ic_slide->addTerm(trim($sterm), $specific_field['code']);
  191. }
  192. }
  193. }
  194. }
  195. $page_content = $all_specific_terms .' '. $page_content;
  196. $ic_slide->addValue("content", $page_content);
  197. // add a comment to say terms separated by commas
  198. $courseid=api_get_course_id();
  199. $ic_slide->addCourseId($courseid);
  200. $ic_slide->addToolId(TOOL_LEARNPATH);
  201. $lp_id = $this->lp_id;
  202. $xapian_data = array(
  203. SE_COURSE_ID => $courseid,
  204. SE_TOOL_ID => TOOL_LEARNPATH,
  205. SE_DATA => array('lp_id' => $lp_id, 'lp_item'=> $previous, 'document_id' => $document_id),
  206. SE_USER => (int)api_get_user_id(),
  207. );
  208. $ic_slide->xapian_data = serialize($xapian_data);
  209. $di->addChunk($ic_slide);
  210. //index and return search engine document id
  211. $did = $di->index();
  212. if ($did) {
  213. // save it to db
  214. $tbl_se_ref = Database::get_main_table(TABLE_MAIN_SEARCH_ENGINE_REF);
  215. $sql = 'INSERT INTO %s (id, course_code, tool_id, ref_id_high_level, ref_id_second_level, search_did)
  216. VALUES (NULL , \'%s\', \'%s\', %s, %s, %s)';
  217. $sql = sprintf($sql, $tbl_se_ref, api_get_course_id(), TOOL_LEARNPATH, $lp_id, $previous, $did);
  218. api_sql_query($sql,__FILE__,__LINE__);
  219. }
  220. }
  221. }
  222. }
  223. }
  224. }
  225. /**
  226. * Returns additional Java command parameters
  227. * @return string The additional parameters to be used in the Java call
  228. */
  229. function add_command_parameters(){
  230. return ' -d woogie "'.$this->base_work_dir.'/'.$this->file_path.'" "'.$this->base_work_dir.$this->created_dir.'/'.$this->file_name.'.html"';
  231. }
  232. /**
  233. * Formats a page content by reorganising the HTML code a little
  234. * @param string Page header
  235. * @param string Page content
  236. * @return string Formatted page content
  237. */
  238. function format_page_content($header, $content)
  239. {
  240. // limit the width of the doc
  241. list($max_width, $max_height) = explode('x',api_get_setting('service_ppt2lp','size'));
  242. $content = preg_replace("|<body[^>]*>|i","\\0\r\n<div style=\"width:".$max_width."\">",$content, -1,$count);
  243. if($count < 1)
  244. {
  245. $content = '<body><div style="width:'.$max_width.'">'.$content;
  246. }
  247. $content = preg_replace('|</body>|i','</div>\\0',$content, -1, $count);
  248. if($count < 1)
  249. {
  250. $content = $content.'</div></body>';
  251. }
  252. // add the headers
  253. $content = $header.$content;
  254. // resize all the picture to the max_width-10
  255. preg_match_all("|<img[^src]*src=\"([^\"]*)\"[^>]*>|i",$content,$images);
  256. foreach ($images[1] as $key => $image)
  257. {
  258. // check if the <img tag soon has a width attribute
  259. $defined_width = preg_match("|width=([^\s]*)|i",$images[0][$key], $img_width);
  260. $img_width = $img_width[1];
  261. if(!$defined_width)
  262. {
  263. list($img_width, $img_height, $type) = getimagesize($this->base_work_dir.$this->created_dir.'/'.$image);
  264. $new_width = $max_width-10;
  265. if($img_width > $new_width)
  266. {
  267. $picture_resized = str_ireplace('<img','<img width="'.$new_width.'" ',$images[0][$key]);
  268. $content = str_replace($images[0][$key],$picture_resized,$content);
  269. }
  270. }
  271. else if($img_width > $max_width-10)
  272. {
  273. $picture_resized = str_ireplace('width='.$img_width,'width="'.($max_width-10).'"',$images[0][$key]);
  274. $content = str_replace($images[0][$key],$picture_resized,$content);
  275. }
  276. }
  277. return $content;
  278. }
  279. /**
  280. * Add documents to the visioconference (to be implemented)
  281. */
  282. function add_docs_to_visio (){
  283. }
  284. }
  285. ?>