openoffice_text_document.class.php 12 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350
  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 "OpenOfficeTextDocument" child of class "learnpath"
  11. * @package dokeos.learnpath.openofficedocument
  12. */
  13. require_once('openoffice_document.class.php');
  14. require_once(api_get_path(LIBRARY_PATH) . 'specific_fields_manager.lib.php');
  15. require_once(api_get_path(LIBRARY_PATH).'search/DokeosIndexer.class.php');
  16. require_once(api_get_path(LIBRARY_PATH).'search/IndexableChunk.class.php');
  17. class OpenOfficeTextDocument extends OpenofficeDocument {
  18. public $split_steps;
  19. /**
  20. * Class constructor. Calls the parent class and initialises the local attribute split_steps
  21. * @param boolean Whether to split steps (true) or make one large page (false)
  22. * @param string Course code
  23. * @param integer Resource ID
  24. * @param integer Creator user id
  25. * @return void
  26. */
  27. function OpenofficeTextDocument($split_steps=false, $course_code=null, $resource_id=null,$user_id=null)
  28. {
  29. $this -> split_steps = $split_steps;
  30. parent::OpenofficeDocument($course_code, $resource_id, $user_id);
  31. }
  32. /**
  33. * Gets html pages and compose them into a learning path
  34. * @param array The files that will compose the generated learning path. Unused so far.
  35. * @return boolean False if file does not exit. Nothing otherwise.
  36. */
  37. function make_lp($files=array())
  38. {
  39. global $_course;
  40. // we get a content where ||page_break|| indicates where the page is broken
  41. if(!file_exists($this->base_work_dir.'/'.$this->created_dir.'/'.$this->file_name.'.html')){return false;}
  42. $content = file_get_contents($this->base_work_dir.'/'.$this->created_dir.'/'.$this->file_name.'.html');
  43. unlink($this->base_work_dir.'/'.$this->file_path);
  44. unlink($this->base_work_dir.'/'.$this->created_dir.'/'.$this->file_name.'.html');
  45. // the file is utf8 encoded and it seems to make problems with special quotes.
  46. // then we htmlentities that, we replace these quotes and html_entity_decode that in good charset
  47. $charset = api_get_setting('platform_charset');
  48. $content = api_htmlentities($content,ENT_COMPAT,$this->original_charset);
  49. $content = str_replace('&rsquo;','\'',$content);
  50. $content = api_convert_encoding($content, $charset, $this->original_charset);
  51. $content = str_replace($this->original_charset,$charset,$content);
  52. $content = api_html_entity_decode($content, ENT_COMPAT, $charset);
  53. // set the path to pictures to absolute (so that it can be modified in fckeditor)
  54. $content = preg_replace("|src=\"([^\"]*)|i", "src=\"".api_get_path(REL_COURSE_PATH).$_course['path'].'/document'.$this->created_dir."/\\1", $content);
  55. list($header, $body) = explode('<BODY',$content);
  56. $body = '<BODY'.$body;
  57. // remove font-family styles
  58. $header = preg_replace("|font\-family[^;]*;|i", "",$header);
  59. // dokeos styles
  60. $my_style = api_get_setting('stylesheets');
  61. if(empty($my_style)){$my_style = 'dokeos_classic';}
  62. $style_to_import = "<style type=\"text/css\">\r\n";
  63. $style_to_import .= '@import "'.api_get_path(WEB_CODE_PATH).'css/'.$my_style.'/default.css";'."\n";
  64. $style_to_import .= '@import "'.api_get_path(WEB_CODE_PATH).'css/'.$my_style.'/course.css";'."\n";
  65. $style_to_import .= "</style>\r\n";
  66. $header = preg_replace("|</head>|i", "\r\n$style_to_import\r\n\\0",$header);
  67. // line break before and after picture
  68. $header = str_replace('p {','p {clear:both;',$header);
  69. $header = str_replace('absolute','relative',$header);
  70. switch($this->split_steps)
  71. {
  72. case 'per_page' : $this -> dealPerPage($header,$body); break;
  73. case 'per_chapter' : $this -> dealPerChapter($header,$body); break;
  74. }
  75. }
  76. /**
  77. * Manages chapter splitting
  78. * @param string Chapter header
  79. * @param string Content
  80. * @return void
  81. */
  82. function dealPerChapter($header, $content)
  83. {
  84. global $_course;
  85. $content = str_replace('||page_break||','',$content);
  86. // get all the h1
  87. preg_match_all("|<h1[^>]*>([^(h1)+]*)</h1>|is",$content,$matches_temp);
  88. //empty the fake chapters
  89. $new_index = 0;
  90. for ($i=0 ; $i<count($matches_temp[0]) ; $i++) {
  91. if(trim($matches_temp[1][$i])!=='')
  92. {
  93. $matches[0][$new_index] = $matches_temp[0][$i];
  94. $matches[1][$new_index] = $matches_temp[1][$i];
  95. $new_index++;
  96. }
  97. }
  98. // add intro item
  99. $intro_content = api_substr($content, 0, api_strpos($content, $matches[0][0]));
  100. $items_to_create[get_lang('Introduction')] = $intro_content;
  101. for ($i=0 ; $i<count($matches[0]) ; $i++) {
  102. if(empty($matches[1][$i]))
  103. continue;
  104. $content = api_strstr($content, $matches[0][$i]);
  105. if($i+1!==count($matches[0]))
  106. {
  107. $chapter_content = api_substr($content, 0, api_strpos($content, $matches[0][$i+1]));
  108. }
  109. else
  110. {
  111. $chapter_content = $content;
  112. }
  113. $items_to_create[$matches[1][$i]] = $chapter_content;
  114. }
  115. $i = 0;
  116. foreach($items_to_create as $item_title=>$item_content)
  117. {
  118. $i++;
  119. $page_content = $this->format_page_content($header, $item_content);
  120. $html_file = $this->created_dir.'-'.$i.'.html';
  121. $handle = fopen($this->base_work_dir.$this->created_dir.'/'.$html_file,'w+');
  122. fwrite($handle, $page_content);
  123. fclose($handle);
  124. $document_id = add_document($_course,$this->created_dir.'/'.$html_file,'file',filesize($this->base_work_dir.$this->created_dir.'/'.$html_file),$html_file);
  125. if ($document_id){
  126. //put the document in item_property update
  127. api_item_property_update($_course,TOOL_DOCUMENT,$document_id,'DocumentAdded',$_SESSION['_uid'],0,0,null,null,api_get_session_id());
  128. $infos = pathinfo($this->filepath);
  129. $slide_name = strip_tags(nl2br($item_title));
  130. $slide_name = str_replace(array("\r\n", "\r", "\n"), "", $slide_name);
  131. $slide_name = api_html_entity_decode($slide_name, ENT_COMPAT, api_get_system_encoding());
  132. $previous = learnpath::add_item(0, $previous, 'document', $document_id, $slide_name, '');
  133. if($this->first_item == 0){
  134. $this->first_item = $previous;
  135. }
  136. }
  137. }
  138. }
  139. /**
  140. * Manages page splitting
  141. * @param string Page header
  142. * @param string Page body
  143. * @return void
  144. */
  145. function dealPerPage($header,$body)
  146. {
  147. global $_course;
  148. // split document to pages
  149. $pages = explode('||page_break||',$body);
  150. $first_item = 0;
  151. foreach($pages as $key=>$page_content)
  152. { // for every pages, we create a new file
  153. $key +=1;
  154. $page_content = $this->format_page_content($header, $page_content, $this->base_work_dir.$this->created_dir);
  155. $html_file = $this->created_dir.'-'.$key.'.html';
  156. $handle = fopen($this->base_work_dir.$this->created_dir.'/'.$html_file,'w+');
  157. fwrite($handle, $page_content);
  158. fclose($handle);
  159. $document_id = add_document($_course,$this->created_dir.$html_file,'file',filesize($this->base_work_dir.$this->created_dir.$html_file),$html_file);
  160. $slide_name = '';
  161. if ($document_id){
  162. //put the document in item_property update
  163. api_item_property_update($_course,TOOL_DOCUMENT,$document_id,'DocumentAdded',$_SESSION['_uid'],0,0,null,null,api_get_session_id());
  164. $infos = pathinfo($this->filepath);
  165. $slide_name = 'Page '.str_repeat('0',2-strlen($key)).$key;
  166. $previous = learnpath::add_item(0, $previous, 'document', $document_id, $slide_name, '');
  167. if($this->first_item == 0){
  168. $this->first_item = $previous;
  169. }
  170. // code for text indexing
  171. if (isset($_POST['index_document']) && $_POST['index_document']) {
  172. //Display::display_normal_message(print_r($_POST));
  173. $di = new DokeosIndexer();
  174. isset($_POST['language'])? $lang=Database::escape_string($_POST['language']): $lang = 'english';
  175. $di->connectDb(NULL, NULL, $lang);
  176. $ic_slide = new IndexableChunk();
  177. $ic_slide->addValue("title", $slide_name);
  178. $specific_fields = get_specific_field_list();
  179. $all_specific_terms = '';
  180. foreach ($specific_fields as $specific_field) {
  181. if (isset($_REQUEST[$specific_field['code']])) {
  182. $sterms = trim($_REQUEST[$specific_field['code']]);
  183. $all_specific_terms .= ' '. $sterms;
  184. if (!empty($sterms)) {
  185. $sterms = explode(',', $sterms);
  186. foreach ($sterms as $sterm) {
  187. $ic_slide->addTerm(trim($sterm), $specific_field['code']);
  188. }
  189. }
  190. }
  191. }
  192. $page_content = $all_specific_terms .' '. $page_content;
  193. $ic_slide->addValue("content", $page_content);
  194. // add a comment to say terms separated by commas
  195. $courseid=api_get_course_id();
  196. $ic_slide->addCourseId($courseid);
  197. $ic_slide->addToolId(TOOL_LEARNPATH);
  198. $lp_id = $this->lp_id;
  199. $xapian_data = array(
  200. SE_COURSE_ID => $courseid,
  201. SE_TOOL_ID => TOOL_LEARNPATH,
  202. SE_DATA => array('lp_id' => $lp_id, 'lp_item'=> $previous, 'document_id' => $document_id),
  203. SE_USER => (int)api_get_user_id(),
  204. );
  205. $ic_slide->xapian_data = serialize($xapian_data);
  206. $di->addChunk($ic_slide);
  207. //index and return search engine document id
  208. $did = $di->index();
  209. if ($did) {
  210. // save it to db
  211. $tbl_se_ref = Database::get_main_table(TABLE_MAIN_SEARCH_ENGINE_REF);
  212. $sql = 'INSERT INTO %s (id, course_code, tool_id, ref_id_high_level, ref_id_second_level, search_did)
  213. VALUES (NULL , \'%s\', \'%s\', %s, %s, %s)';
  214. $sql = sprintf($sql, $tbl_se_ref, api_get_course_id(), TOOL_LEARNPATH, $lp_id, $previous, $did);
  215. Database::query($sql,__FILE__,__LINE__);
  216. }
  217. }
  218. }
  219. }
  220. }
  221. /**
  222. * Returns additional Java command parameters
  223. * @return string The additional parameters to be used in the Java call
  224. */
  225. function add_command_parameters(){
  226. return ' -d woogie "'.$this->base_work_dir.'/'.$this->file_path.'" "'.$this->base_work_dir.$this->created_dir.'/'.$this->file_name.'.html"';
  227. }
  228. /**
  229. * Formats a page content by reorganising the HTML code a little
  230. * @param string Page header
  231. * @param string Page content
  232. * @return string Formatted page content
  233. */
  234. function format_page_content($header, $content)
  235. {
  236. // limit the width of the doc
  237. list($max_width, $max_height) = explode('x',api_get_setting('service_ppt2lp','size'));
  238. $content = preg_replace("|<body[^>]*>|i","\\0\r\n<div style=\"width:".$max_width."\">",$content, -1,$count);
  239. if($count < 1)
  240. {
  241. $content = '<body><div style="width:'.$max_width.'">'.$content;
  242. }
  243. $content = preg_replace('|</body>|i','</div>\\0',$content, -1, $count);
  244. if($count < 1)
  245. {
  246. $content = $content.'</div></body>';
  247. }
  248. // add the headers
  249. $content = $header.$content;
  250. // resize all the picture to the max_width-10
  251. preg_match_all("|<img[^src]*src=\"([^\"]*)\"[^>]*>|i",$content,$images);
  252. foreach ($images[1] as $key => $image)
  253. {
  254. // check if the <img tag soon has a width attribute
  255. $defined_width = preg_match("|width=([^\s]*)|i",$images[0][$key], $img_width);
  256. $img_width = $img_width[1];
  257. if(!$defined_width)
  258. {
  259. list($img_width, $img_height, $type) = api_getimagesize($this->base_work_dir.$this->created_dir.'/'.$image);
  260. $new_width = $max_width-10;
  261. if($img_width > $new_width)
  262. {
  263. $picture_resized = str_ireplace('<img','<img width="'.$new_width.'" ',$images[0][$key]);
  264. $content = str_replace($images[0][$key],$picture_resized,$content);
  265. }
  266. }
  267. else if($img_width > $max_width-10)
  268. {
  269. $picture_resized = str_ireplace('width='.$img_width,'width="'.($max_width-10).'"',$images[0][$key]);
  270. $content = str_replace($images[0][$key],$picture_resized,$content);
  271. }
  272. }
  273. return $content;
  274. }
  275. /**
  276. * Add documents to the visioconference (to be implemented)
  277. */
  278. function add_docs_to_visio (){
  279. }
  280. }
  281. ?>