Feature #272 - Course restorer: Encoding detection for course archives has been added. It is necessary for importing archives that are created with systems older than 1.8.6.1. Next to do: The read/detected encoding value should be used for data conversion.

main/coursecopy/classes/Course.class.php

@@ -109,5 +109,102 @@ class Course
 //		}
 	}
 
+	/**
+	 * Returns sample text based on the imported course content.
+	 * This sample text is to be used for course language or encoding detection if there is missing (meta)data in the archive.
+	 * @return string	The resulting sample text extracted from some common resources' data fields.
+	 */
+	public function get_sample_text() {
+
+		$sample_text = '';
+
+		foreach ($this->resources as $type => & $resources) {
+			if (count($resources) > 0) {
+				foreach ($resources as $id => & $resource) {
+
+					$title = '';
+					$description = '';
+
+					switch ($type) {
+
+						case RESOURCE_ANNOUNCEMENT:
+						case RESOURCE_EVENT:
+						case RESOURCE_WIKI:
+							$title = $resource->title;
+							$description = $resource->content;
+							break;
+
+						case RESOURCE_DOCUMENT:
+							$title = $resource->title;
+							$description = $resource->comment;
+							break;
+
+						case RESOURCE_FORUM:
+						case RESOURCE_FORUMCATEGORY:
+						case RESOURCE_LINK:
+						case RESOURCE_LINKCATEGORY:
+						case RESOURCE_QUIZ:
+							$title = $resource->title;
+							$description = $resource->description;
+							break;
+
+						case RESOURCE_FORUMPOST:
+							$title = $resource->title;
+							$description = $resource->text;
+							break;
+
+						case RESOURCE_GLOSSARY:
+						case RESOURCE_LEARNPATH:
+							$title = $resource->name;
+							$description = $resource->description;
+							break;
+
+						case RESOURCE_FORUMTOPIC:
+						case RESOURCE_SCORM:
+							$title = $resource->title;
+							break;
+
+						case RESOURCE_QUIZQUESTION:
+							$title = $resource->question;
+							$description = $resource->description;
+							break;
+
+						case RESOURCE_SURVEY:
+							$title = $resource->title;
+							$description = $resource->subtitle;
+							break;
+
+						case RESOURCE_SURVEYQUESTION:
+							$title = $resource->survey_question;
+							$description = $resource->survey_question_comment;
+							break;
+
+						case RESOURCE_TOOL_INTRO:
+							$description = $resource->intro_text;
+							break;
+
+						default:
+							break;
+					}
+
+					$title = api_html_to_text($title);
+					$description = api_html_to_text($description);
+
+					if (!empty($title)) {
+						$sample_text .= $title."\n";
+					}
+					if (!empty($description)) {
+						$sample_text .= $description."\n";
+					}
+					if (!empty($title) || !empty($description)) {
+						$sample_text .= "\n";
+					}
+				}
+			}
+		}
+
+		return $sample_text;
+	}
+
 }
 ?>

main/coursecopy/classes/CourseRestorer.class.php

@@ -94,8 +94,23 @@ class CourseRestorer
 			$this->course->destination_db = $course_info['database'];
 			$this->course->destination_path = $course_info['directory'];
 		}
-		// platform encoding
-		$course_charset = $this->course->encoding;
+
+		// Source platform encoding - reading/detection
+		// The correspondent data field has been added as of version 1.8.6.1.
+		if (empty($this->course->encoding)) {
+			// The archive has been created by a system wich is prior to 1.8.6.1 version.
+			// In this case we have to detect the encoding.
+			$sample_text = $this->course->get_sample_text()."\n";
+			// Let us exclude ASCII lines, probably they are English texts.
+			$sample_text = explode("\n", $sample_text);
+			foreach ($sample_text as $key => &$line) {
+				if (api_is_valid_ascii($line)) {
+					unset($sample_text[$key]);
+				}
+			}
+			$sample_text = join("\n", $sample_text);
+			$this->course->encoding = api_detect_encoding($sample_text);
+		}
 
 		if (!empty($session_id)) {
 			$this->restore_documents($session_id,$destination_course_code);