Search moodle.org's
Developer Documentation

See Release Notes

  • Bug fixes for general core bugs in 4.3.x will end 7 October 2024 (12 months).
  • Bug fixes for security issues in 4.3.x will end 21 April 2025 (18 months).
  • PHP version: minimum PHP 8.0.0 Note: minimum PHP version has increased since Moodle 4.1. PHP 8.2.x is supported too.

Differences Between: [Versions 310 and 403] [Versions 311 and 403] [Versions 39 and 403] [Versions 400 and 403] [Versions 401 and 403] [Versions 402 and 403]

   1  <?php
   2  // This file is part of Moodle - http://moodle.org/
   3  //
   4  // Moodle is free software: you can redistribute it and/or modify
   5  // it under the terms of the GNU General Public License as published by
   6  // the Free Software Foundation, either version 3 of the License, or
   7  // (at your option) any later version.
   8  //
   9  // Moodle is distributed in the hope that it will be useful,
  10  // but WITHOUT ANY WARRANTY; without even the implied warranty of
  11  // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  12  // GNU General Public License for more details.
  13  //
  14  // You should have received a copy of the GNU General Public License
  15  // along with Moodle.  If not, see <http://www.gnu.org/licenses/>.
  16  
  17  /**
  18   * HTML import lib
  19   *
  20   * @package    booktool_importhtml
  21   * @copyright  2011 Petr Skoda {@link http://skodak.org}
  22   * @license    http://www.gnu.org/copyleft/gpl.html GNU GPL v3 or later
  23   */
  24  
  25  defined('MOODLE_INTERNAL') || die;
  26  
  27  require_once (__DIR__.'/lib.php');
  28  require_once($CFG->dirroot.'/mod/book/locallib.php');
  29  
  30  /**
  31   * Import HTML pages packaged into one zip archive
  32   *
  33   * @param stored_file $package
  34   * @param string $type type of the package ('typezipdirs' or 'typezipfiles')
  35   * @param stdClass $book
  36   * @param context_module $context
  37   * @param bool $verbose
  38   */
  39  function toolbook_importhtml_import_chapters($package, $type, $book, $context, $verbose = true) {
  40      global $DB, $OUTPUT;
  41  
  42      $fs = get_file_storage();
  43      $chapterfiles = toolbook_importhtml_get_chapter_files($package, $type);
  44      $packer = get_file_packer('application/zip');
  45      $fs->delete_area_files($context->id, 'mod_book', 'importhtmltemp', 0);
  46      $package->extract_to_storage($packer, $context->id, 'mod_book', 'importhtmltemp', 0, '/');
  47      // $datafiles = $fs->get_area_files($context->id, 'mod_book', 'importhtmltemp', 0, 'id', false);
  48      // echo "<pre>";p(var_export($datafiles, true));
  49  
  50      $chapters = array();
  51  
  52      if ($verbose) {
  53          echo $OUTPUT->notification(get_string('importing', 'booktool_importhtml'), 'notifysuccess');
  54      }
  55      if ($type == 0) {
  56          $chapterfile = reset($chapterfiles);
  57          if ($file = $fs->get_file_by_hash(sha1("$context->id/mod_book/importhtmltemp/0/$chapterfile->pathname"))) {
  58              $htmlcontent = toolbook_importhtml_fix_encoding($file->get_content());
  59              $htmlchapters = toolbook_importhtml_parse_headings(toolbook_importhtml_parse_body($htmlcontent));
  60              // TODO: process h1 as main chapter and h2 as subchapters
  61          }
  62      } else {
  63          foreach ($chapterfiles as $chapterfile) {
  64              if ($file = $fs->get_file_by_hash(sha1("/$context->id/mod_book/importhtmltemp/0/$chapterfile->pathname"))) {
  65                  $chapter = new stdClass();
  66                  $htmlcontent = toolbook_importhtml_fix_encoding($file->get_content());
  67  
  68                  $chapter->bookid        = $book->id;
  69                  $chapter->pagenum       = $DB->get_field_sql('SELECT MAX(pagenum) FROM {book_chapters} WHERE bookid = ?', array($book->id)) + 1;
  70                  $chapter->importsrc     = '/'.$chapterfile->pathname;
  71                  $chapter->content       = toolbook_importhtml_parse_styles($htmlcontent);
  72                  $chapter->content       .= toolbook_importhtml_parse_body($htmlcontent);
  73                  $chapter->title         = toolbook_importhtml_parse_title($htmlcontent, $chapterfile->pathname);
  74                  $chapter->contentformat = FORMAT_HTML;
  75                  $chapter->hidden        = 0;
  76                  $chapter->timecreated   = time();
  77                  $chapter->timemodified  = time();
  78                  if (preg_match('/_sub(\/|\.htm)/i', $chapter->importsrc)) { // If filename or directory ends with *_sub treat as subchapters
  79                      $chapter->subchapter = 1;
  80                  } else {
  81                      $chapter->subchapter = 0;
  82                  }
  83  
  84                  $chapter->id = $DB->insert_record('book_chapters', $chapter);
  85                  $chapter = $DB->get_record('book_chapters', array('id' => $chapter->id));
  86                  $chapters[$chapter->id] = $chapter;
  87  
  88                  \mod_book\event\chapter_created::create_from_chapter($book, $context, $chapter)->trigger();
  89              }
  90          }
  91      }
  92  
  93      if ($verbose) {
  94          echo $OUTPUT->notification(get_string('relinking', 'booktool_importhtml'), 'notifysuccess');
  95      }
  96      $allchapters = $DB->get_records('book_chapters', array('bookid'=>$book->id), 'pagenum');
  97      foreach ($chapters as $chapter) {
  98          // find references to all files and copy them + relink them
  99          $matches = null;
 100          if (preg_match_all('/(src|codebase|name|href)\s*=\s*"([^"]+)"/i', $chapter->content, $matches)) {
 101              $file_record = array('contextid'=>$context->id, 'component'=>'mod_book', 'filearea'=>'chapter', 'itemid'=>$chapter->id);
 102              foreach ($matches[0] as $i => $match) {
 103                  $filepath = dirname($chapter->importsrc).'/'.$matches[2][$i];
 104                  $filepath = toolbook_importhtml_fix_path($filepath);
 105  
 106                  if (strtolower($matches[1][$i]) === 'href') {
 107                      // skip linked html files, we will try chapter relinking later
 108                      foreach ($allchapters as $target) {
 109                          if ($target->importsrc === $filepath) {
 110                              continue 2;
 111                          }
 112                      }
 113                  }
 114  
 115                  if ($file = $fs->get_file_by_hash(sha1("/$context->id/mod_book/importhtmltemp/0$filepath"))) {
 116                      if (!$oldfile = $fs->get_file_by_hash(sha1("/$context->id/mod_book/chapter/$chapter->id$filepath"))) {
 117                          $fs->create_file_from_storedfile($file_record, $file);
 118                      }
 119                      $chapter->content = str_replace($match, $matches[1][$i].'="@@PLUGINFILE@@'.$filepath.'"', $chapter->content);
 120                  }
 121              }
 122              $DB->set_field('book_chapters', 'content', $chapter->content, array('id'=>$chapter->id));
 123          }
 124      }
 125      unset($chapters);
 126  
 127      $allchapters = $DB->get_records('book_chapters', array('bookid'=>$book->id), 'pagenum');
 128      foreach ($allchapters as $chapter) {
 129          $newcontent = $chapter->content;
 130          $matches = null;
 131          if (preg_match_all('/(href)\s*=\s*"([^"]+)"/i', $chapter->content, $matches)) {
 132              foreach ($matches[0] as $i => $match) {
 133                  if (strpos($matches[2][$i], ':') !== false or strpos($matches[2][$i], '@') !== false) {
 134                      // it is either absolute or pluginfile link
 135                      continue;
 136                  }
 137                  $chapterpath = dirname($chapter->importsrc).'/'.$matches[2][$i];
 138                  $chapterpath = toolbook_importhtml_fix_path($chapterpath);
 139                  foreach ($allchapters as $target) {
 140                      if ($target->importsrc === $chapterpath) {
 141                          $newcontent = str_replace($match, 'href="'.new moodle_url('/mod/book/view.php',
 142                                  array('id'=>$context->instanceid, 'chapterid'=>$target->id)).'"', $newcontent);
 143                      }
 144                  }
 145              }
 146          }
 147          if ($newcontent !== $chapter->content) {
 148              $DB->set_field('book_chapters', 'content', $newcontent, array('id'=>$chapter->id));
 149          }
 150      }
 151  
 152      $fs->delete_area_files($context->id, 'mod_book', 'importhtmltemp', 0);
 153  
 154      // update the revision flag - this takes a long time, better to refetch the current value
 155      $book = $DB->get_record('book', array('id'=>$book->id));
 156      $DB->set_field('book', 'revision', $book->revision+1, array('id'=>$book->id));
 157  }
 158  
 159  /**
 160   * Parse the headings of the imported package of type 'typeonefile'
 161   * (currently unsupported)
 162   *
 163   * @param string $html html content to parse
 164   * @todo implement this once the type 'typeonefile' is enabled
 165   */
 166  function toolbook_importhtml_parse_headings($html) {
 167  }
 168  
 169  /**
 170   * Parse the links to external css sheets of the imported html content
 171   *
 172   * @param string $html html content to parse
 173   * @return string all the links to external css sheets
 174   */
 175  function toolbook_importhtml_parse_styles($html) {
 176      $styles = '';
 177      if (preg_match('/<head[^>]*>(.+)<\/head>/is', $html, $matches)) {
 178          $head = $matches[1];
 179          if (preg_match_all('/<link[^>]+rel="stylesheet"[^>]*>/i', $head, $matches)) { // Extract links to css.
 180              for ($i=0; $i<count($matches[0]); $i++) {
 181                  $styles .= $matches[0][$i]."\n";
 182              }
 183          }
 184      }
 185      return $styles;
 186  }
 187  
 188  /**
 189   * Normalize paths to be absolute
 190   *
 191   * @param string $path original path with MS/relative separators
 192   * @return string the normalized and cleaned absolute path
 193   */
 194  function toolbook_importhtml_fix_path($path) {
 195      $path = str_replace('\\', '/', $path); // anti MS hack
 196      $path = '/'.ltrim($path, './'); // dirname() produces . for top level files + our paths start with /
 197  
 198      $cnt = substr_count($path, '..');
 199      for ($i=0; $i<$cnt; $i++) {
 200          $path = preg_replace('|[^/]+/\.\./|', '', $path, 1);
 201      }
 202  
 203      $path = clean_param($path, PARAM_PATH);
 204      return $path;
 205  }
 206  
 207  /**
 208   * Convert some html content to utf8, getting original encoding from html headers
 209   *
 210   * @param string $html html content to convert
 211   * @return string html content converted to utf8
 212   */
 213  function toolbook_importhtml_fix_encoding($html) {
 214      if (preg_match('/<head[^>]*>(.+)<\/head>/is', $html, $matches)) {
 215          $head = $matches[1];
 216          if (preg_match('/charset=([^"]+)/is', $head, $matches)) {
 217              $enc = $matches[1];
 218              return core_text::convert($html, $enc, 'utf-8');
 219          }
 220      }
 221      return iconv('UTF-8', 'UTF-8//IGNORE', $html);
 222  }
 223  
 224  /**
 225   * Extract the body from any html contents
 226   *
 227   * @param string $html the html to parse
 228   * @return string the contents of the body
 229   */
 230  function toolbook_importhtml_parse_body($html) {
 231      $matches = null;
 232      if (preg_match('/<body[^>]*>(.+)<\/body>/is', $html, $matches)) {
 233          return $matches[1];
 234      } else {
 235          return '';
 236      }
 237  }
 238  
 239  /**
 240   * Extract the title of any html content, getting it from the title tag
 241   *
 242   * @param string $html the html to parse
 243   * @param string $default default title to apply if no title is found
 244   * @return string the resulting title
 245   */
 246  function toolbook_importhtml_parse_title($html, $default) {
 247      $matches = null;
 248      if (preg_match('/<title>([^<]+)<\/title>/i', $html, $matches)) {
 249          return $matches[1];
 250      } else {
 251          return $default;
 252      }
 253  }
 254  
 255  /**
 256   * Returns all the html files (chapters) from a file package
 257   *
 258   * @param stored_file $package file to be processed
 259   * @param string $type type of the package ('typezipdirs' or 'typezipfiles')
 260   *
 261   * @return array the html files found in the package
 262   */
 263  function toolbook_importhtml_get_chapter_files($package, $type) {
 264      $packer = get_file_packer('application/zip');
 265      $files = $package->list_files($packer);
 266      $tophtmlfiles = array();
 267      $subhtmlfiles = array();
 268      $topdirs = array();
 269  
 270      foreach ($files as $file) {
 271          if (empty($file->pathname)) {
 272              continue;
 273          }
 274          if (substr($file->pathname, -1) === '/') {
 275              if (substr_count($file->pathname, '/') !== 1) {
 276                  // skip subdirs
 277                  continue;
 278              }
 279              if (!isset($topdirs[$file->pathname])) {
 280                  $topdirs[$file->pathname] = array();
 281              }
 282  
 283          } else {
 284              $mime = mimeinfo('icon', $file->pathname);
 285              if ($mime !== 'markup') {
 286                  continue;
 287              }
 288              $level = substr_count($file->pathname, '/');
 289              if ($level === 0) {
 290                  $tophtmlfiles[$file->pathname] = $file;
 291              } else if ($level === 1) {
 292                  $subhtmlfiles[$file->pathname] = $file;
 293                  $dir = preg_replace('|/.*$|', '', $file->pathname);
 294                  $topdirs[$dir][$file->pathname] = $file;
 295              } else {
 296                  // lower levels are not interesting
 297                  continue;
 298              }
 299          }
 300      }
 301  
 302      core_collator::ksort($tophtmlfiles, core_collator::SORT_NATURAL);
 303      core_collator::ksort($subhtmlfiles, core_collator::SORT_NATURAL);
 304      core_collator::ksort($topdirs, core_collator::SORT_NATURAL);
 305  
 306      $chapterfiles = array();
 307  
 308      if ($type == 2) {
 309          $chapterfiles = $tophtmlfiles;
 310  
 311      } else if ($type == 1) {
 312          foreach ($topdirs as $dir => $htmlfiles) {
 313              if (empty($htmlfiles)) {
 314                  continue;
 315              }
 316              core_collator::ksort($htmlfiles, core_collator::SORT_NATURAL);
 317              if (isset($htmlfiles[$dir.'/index.html'])) {
 318                  $htmlfile = $htmlfiles[$dir.'/index.html'];
 319              } else if (isset($htmlfiles[$dir.'/index.htm'])) {
 320                  $htmlfile = $htmlfiles[$dir.'/index.htm'];
 321              } else if (isset($htmlfiles[$dir.'/Default.htm'])) {
 322                  $htmlfile = $htmlfiles[$dir.'/Default.htm'];
 323              } else {
 324                  $htmlfile = reset($htmlfiles);
 325              }
 326              $chapterfiles[$htmlfile->pathname] = $htmlfile;
 327          }
 328      } else if ($type == 0) {
 329          if ($tophtmlfiles) {
 330              if (isset($tophtmlfiles['index.html'])) {
 331                  $htmlfile = $tophtmlfiles['index.html'];
 332              } else if (isset($tophtmlfiles['index.htm'])) {
 333                  $htmlfile = $tophtmlfiles['index.htm'];
 334              } else if (isset($tophtmlfiles['Default.htm'])) {
 335                  $htmlfile = $tophtmlfiles['Default.htm'];
 336              } else {
 337                  $htmlfile = reset($tophtmlfiles);
 338              }
 339          } else {
 340              $htmlfile = reset($subhtmlfiles);
 341          }
 342          $chapterfiles[$htmlfile->pathname] = $htmlfile;
 343      }
 344  
 345      return $chapterfiles;
 346  }