openoffice_text_document.class.php 14 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358
  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 "OpenOfficeTextDocument" child of class "learnpath"
  13. */
  14. require_once 'openoffice_document.class.php';
  15. require_once api_get_path(LIBRARY_PATH).'specific_fields_manager.lib.php';
  16. require_once api_get_path(LIBRARY_PATH).'search/ChamiloIndexer.class.php';
  17. require_once api_get_path(LIBRARY_PATH).'search/IndexableChunk.class.php';
  18. /**
  19. * @package chamilo.learnpath.openofficedocument
  20. */
  21. class OpenOfficeTextDocument extends OpenofficeDocument {
  22. public $split_steps;
  23. /**
  24. * Class constructor. Calls the parent class and initialises the local attribute split_steps
  25. * @param boolean Whether to split steps (true) or make one large page (false)
  26. * @param string Course code
  27. * @param integer Resource ID
  28. * @param integer Creator user id
  29. * @return void
  30. */
  31. public function __construct($split_steps = false, $course_code = null, $resource_id = null, $user_id = null) {
  32. $this -> split_steps = $split_steps;
  33. parent::__construct($course_code, $resource_id, $user_id);
  34. }
  35. /**
  36. * Gets html pages and compose them into a learning path
  37. * @param array The files that will compose the generated learning path. Unused so far.
  38. * @return boolean False if file does not exit. Nothing otherwise.
  39. */
  40. public function make_lp($files = array())
  41. {
  42. $_course = api_get_course_info();
  43. // We get a content where ||page_break|| indicates where the page is broken.
  44. if (!file_exists($this->base_work_dir.'/'.$this->created_dir.'/'.$this->file_name.'.html')) { return false; }
  45. $content = file_get_contents($this->base_work_dir.'/'.$this->created_dir.'/'.$this->file_name.'.html');
  46. unlink($this->base_work_dir.'/'.$this->file_path);
  47. unlink($this->base_work_dir.'/'.$this->created_dir.'/'.$this->file_name.'.html');
  48. // The file is utf8 encoded and it seems to make problems with special quotes.
  49. // then we htmlentities that, we replace these quotes and html_entity_decode that in good charset.
  50. $charset = api_get_system_encoding();
  51. $content = api_htmlentities($content, ENT_COMPAT, $this->original_charset);
  52. $content = str_replace('&rsquo;', '\'', $content);
  53. $content = api_convert_encoding($content, $charset, $this->original_charset);
  54. $content = str_replace($this->original_charset, $charset, $content);
  55. $content = api_html_entity_decode($content, ENT_COMPAT, $charset);
  56. // Set the path to pictures to absolute (so that it can be modified in fckeditor).
  57. $content = preg_replace("|src=\"([^\"]*)|i", "src=\"".api_get_path(REL_COURSE_PATH).$_course['path'].'/document'.$this->created_dir."/\\1", $content);
  58. list($header, $body) = explode('<BODY', $content);
  59. $body = '<BODY'.$body;
  60. // Remove font-family styles.
  61. $header = preg_replace("|font\-family[^;]*;|i", '', $header);
  62. // Chamilo styles.
  63. $my_style = api_get_setting('stylesheets');
  64. if (empty($my_style)) { $my_style = 'chamilo'; }
  65. $style_to_import = "<style type=\"text/css\">\r\n";
  66. $style_to_import .= '@import "'.api_get_path(WEB_CODE_PATH).'css/'.$my_style.'/default.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. case 'per_page':
  74. $this -> dealPerPage($header, $body);
  75. break;
  76. case 'per_chapter':
  77. $this -> dealPerChapter($header, $body);
  78. break;
  79. }
  80. }
  81. /**
  82. * Manages dir/chapter splitting
  83. * @param string Chapter header
  84. * @param string Content
  85. * @return void
  86. */
  87. function dealPerChapter($header, $content)
  88. {
  89. $_course = api_get_course_info();
  90. $content = str_replace('||page_break||', '', $content);
  91. // Get all the h1.
  92. preg_match_all("|<h1[^>]*>([^(h1)+]*)</h1>|is", $content, $matches_temp);
  93. // Empty the fake dir/chapters.
  94. $new_index = 0;
  95. for ($i = 0; $i < count($matches_temp[0]); $i++) {
  96. if (trim($matches_temp[1][$i]) !== '') {
  97. $matches[0][$new_index] = $matches_temp[0][$i];
  98. $matches[1][$new_index] = $matches_temp[1][$i];
  99. $new_index++;
  100. }
  101. }
  102. // Add intro item.
  103. $intro_content = api_substr($content, 0, api_strpos($content, $matches[0][0]));
  104. $items_to_create[get_lang('Introduction')] = $intro_content;
  105. for ($i = 0; $i < count($matches[0]); $i++) {
  106. if (empty($matches[1][$i]))
  107. continue;
  108. $content = api_strstr($content, $matches[0][$i]);
  109. if ($i + 1 !== count($matches[0])) {
  110. $dir_content = api_substr($content, 0, api_strpos($content, $matches[0][$i + 1]));
  111. } else {
  112. $dir_content = $content;
  113. }
  114. $items_to_create[$matches[1][$i]] = $dir_content;
  115. }
  116. $i = 0;
  117. foreach ($items_to_create as $item_title => $item_content) {
  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(
  125. $_course,
  126. $this->created_dir.'/'.$html_file,
  127. 'file',
  128. filesize($this->base_work_dir.$this->created_dir.'/'.$html_file),
  129. $html_file
  130. );
  131. if ($document_id) {
  132. // Put the document in item_property update.
  133. api_item_property_update(
  134. $_course,
  135. TOOL_DOCUMENT,
  136. $document_id,
  137. 'DocumentAdded',
  138. api_get_user_id(),
  139. 0,
  140. 0,
  141. null,
  142. null,
  143. api_get_session_id()
  144. );
  145. $infos = pathinfo($this->filepath);
  146. $slide_name = strip_tags(nl2br($item_title));
  147. $slide_name = str_replace(array("\r\n", "\r", "\n"), '', $slide_name);
  148. $slide_name = api_html_entity_decode($slide_name, ENT_COMPAT, api_get_system_encoding());
  149. $previous = learnpath::add_item(0, $previous, 'document', $document_id, $slide_name, '');
  150. if ($this->first_item == 0) {
  151. $this->first_item = $previous;
  152. }
  153. }
  154. }
  155. }
  156. /**
  157. * Manages page splitting
  158. * @param string Page header
  159. * @param string Page body
  160. * @return void
  161. */
  162. function dealPerPage($header, $body)
  163. {
  164. $_course = api_get_course_info();
  165. // Split document to pages.
  166. $pages = explode('||page_break||', $body);
  167. $first_item = 0;
  168. foreach ($pages as $key => $page_content) {
  169. // For every pages, we create a new file.
  170. $key += 1;
  171. $page_content = $this->format_page_content($header, $page_content, $this->base_work_dir.$this->created_dir);
  172. $html_file = $this->created_dir.'-'.$key.'.html';
  173. $handle = fopen($this->base_work_dir.$this->created_dir.'/'.$html_file, 'w+');
  174. fwrite($handle, $page_content);
  175. fclose($handle);
  176. $document_id = add_document(
  177. $_course,
  178. $this->created_dir.$html_file,
  179. 'file',
  180. filesize($this->base_work_dir.$this->created_dir.$html_file),
  181. $html_file
  182. );
  183. $slide_name = '';
  184. if ($document_id) {
  185. // Put the document in item_property update.
  186. api_item_property_update(
  187. $_course,
  188. TOOL_DOCUMENT,
  189. $document_id,
  190. 'DocumentAdded',
  191. api_get_user_id(),
  192. 0,
  193. 0,
  194. null,
  195. null,
  196. api_get_session_id()
  197. );
  198. $infos = pathinfo($this->filepath);
  199. $slide_name = 'Page '.str_repeat('0', 2 - strlen($key)).$key;
  200. $previous = learnpath::add_item(0, $previous, 'document', $document_id, $slide_name, '');
  201. if ($this->first_item == 0) {
  202. $this->first_item = $previous;
  203. }
  204. // Code for text indexing.
  205. if (isset($_POST['index_document']) && $_POST['index_document']) {
  206. //Display::display_normal_message(print_r($_POST));
  207. $di = new ChamiloIndexer();
  208. isset($_POST['language']) ? $lang = Database::escape_string($_POST['language']) : $lang = 'english';
  209. $di->connectDb(NULL, NULL, $lang);
  210. $ic_slide = new IndexableChunk();
  211. $ic_slide->addValue('title', $slide_name);
  212. $specific_fields = get_specific_field_list();
  213. $all_specific_terms = '';
  214. foreach ($specific_fields as $specific_field) {
  215. if (isset($_REQUEST[$specific_field['code']])) {
  216. $sterms = trim($_REQUEST[$specific_field['code']]);
  217. $all_specific_terms .= ' '.$sterms;
  218. if (!empty($sterms)) {
  219. $sterms = explode(',', $sterms);
  220. foreach ($sterms as $sterm) {
  221. $ic_slide->addTerm(trim($sterm), $specific_field['code']);
  222. }
  223. }
  224. }
  225. }
  226. $page_content = $all_specific_terms.' '.$page_content;
  227. $ic_slide->addValue('content', $page_content);
  228. // Add a comment to say terms separated by commas.
  229. $courseid = api_get_course_id();
  230. $ic_slide->addCourseId($courseid);
  231. $ic_slide->addToolId(TOOL_LEARNPATH);
  232. $lp_id = $this->lp_id;
  233. $xapian_data = array(
  234. SE_COURSE_ID => $courseid,
  235. SE_TOOL_ID => TOOL_LEARNPATH,
  236. SE_DATA => array('lp_id' => $lp_id, 'lp_item' => $previous, 'document_id' => $document_id),
  237. SE_USER => (int) api_get_user_id(),
  238. );
  239. $ic_slide->xapian_data = serialize($xapian_data);
  240. $di->addChunk($ic_slide);
  241. // Index and return search engine document id.
  242. $did = $di->index();
  243. if ($did) {
  244. // Save it to db.
  245. $tbl_se_ref = Database::get_main_table(TABLE_MAIN_SEARCH_ENGINE_REF);
  246. $sql = 'INSERT INTO %s (id, course_code, tool_id, ref_id_high_level, ref_id_second_level, search_did)
  247. VALUES (NULL , \'%s\', \'%s\', %s, %s, %s)';
  248. $sql = sprintf($sql, $tbl_se_ref, api_get_course_id(), TOOL_LEARNPATH, $lp_id, $previous, $did);
  249. Database::query($sql);
  250. }
  251. }
  252. }
  253. }
  254. }
  255. /**
  256. * Returns additional Java command parameters
  257. * @return string The additional parameters to be used in the Java call
  258. */
  259. function add_command_parameters() {
  260. return ' -d woogie "'.$this->base_work_dir.'/'.$this->file_path.'" "'.$this->base_work_dir.$this->created_dir.'/'.$this->file_name.'.html"';
  261. }
  262. /**
  263. * Formats a page content by reorganising the HTML code a little
  264. * @param string Page header
  265. * @param string Page content
  266. * @return string Formatted page content
  267. */
  268. function format_page_content($header, $content) {
  269. // Limit the width of the doc.
  270. list($max_width, $max_height) = explode('x', api_get_setting('service_ppt2lp', 'size'));
  271. $content = preg_replace("|<body[^>]*>|i", "\\0\r\n<div style=\"width:".$max_width."\">", $content, -1, $count);
  272. if ($count < 1) {
  273. $content = '<body><div style="width:'.$max_width.'">'.$content;
  274. }
  275. $content = preg_replace('|</body>|i', '</div>\\0', $content, -1, $count);
  276. if ($count < 1) {
  277. $content = $content.'</div></body>';
  278. }
  279. // Add the headers.
  280. $content = $header.$content;
  281. // Resize all the picture to the max_width-10
  282. preg_match_all("|<img[^src]*src=\"([^\"]*)\"[^>]*>|i", $content, $images);
  283. foreach ($images[1] as $key => $image) {
  284. // Check if the <img tag soon has a width attribute.
  285. $defined_width = preg_match("|width=([^\s]*)|i", $images[0][$key], $img_width);
  286. $img_width = $img_width[1];
  287. if (!$defined_width) {
  288. $image_size = api_getimagesize($this->base_work_dir.$this->created_dir.'/'.$image);
  289. $img_width = $image_size['width'];
  290. $img_height = $image_size['height'];
  291. $new_width = $max_width - 10;
  292. if ($img_width > $new_width) {
  293. $picture_resized = str_ireplace('<img', '<img width="'.$new_width.'" ', $images[0][$key]);
  294. $content = str_replace($images[0][$key], $picture_resized, $content);
  295. }
  296. } elseif ($img_width > $max_width - 10) {
  297. $picture_resized = str_ireplace('width='.$img_width, 'width="'.($max_width - 10).'"', $images[0][$key]);
  298. $content = str_replace($images[0][$key], $picture_resized, $content);
  299. }
  300. }
  301. return $content;
  302. }
  303. /**
  304. * Add documents to the visioconference (to be implemented)
  305. */
  306. function add_docs_to_visio() {
  307. }
  308. }