Add EncodingService

Author: Raudius

lib/Service/ApiService.php

@@ -50,17 +50,20 @@ class ApiService {
 	protected $documentService;
 	protected $logger;
 	private $imageService;
+	private $encodingService;
 
 	public function __construct(IRequest $request,
 								SessionService $sessionService,
 								DocumentService $documentService,
 								ImageService $imageService,
+								EncodingService $encodingService,
 								ILogger $logger) {
 		$this->request = $request;
 		$this->sessionService = $sessionService;
 		$this->documentService = $documentService;
 		$this->logger = $logger;
 		$this->imageService = $imageService;
+		$this->encodingService = $encodingService;
 	}
 
 	public function create($fileId = null, $filePath = null, $token = null, $guestName = null, bool $forceRecreate = false): DataResponse {
@@ -105,6 +108,11 @@ public function create($fileId = null, $filePath = null, $token = null, $guestNa
 		try {
 			$baseFile = $this->documentService->getBaseFile($document->getId());
 			$content = $baseFile->getContent();
+
+			$content = $this->encodingService->encodeToUtf8($content);
+			if (!$content) {
+				$this->logger->log(ILogger::WARN, 'Failed to encode file to UTF8. File ID: ' . $file->getId());
+			}
 		} catch (NotFoundException $e) {
 			$this->logger->logException($e, ['level' => ILogger::INFO]);
 			$content = null;

lib/Service/EncodingService.php

@@ -0,0 +1,47 @@
+<?php
+
+declare(strict_types=1);
+
+/**
+ * @copyright Copyright (c) 2022 Raul Ferreira Fuentes <[email protected]>
+ *
+ * @author Raul Ferreira Fuentes <[email protected]>
+ *
+ * @license GNU AGPL version 3 or any later version
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as
+ * published by the Free Software Foundation, either version 3 of the
+ * License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ *
+ */
+namespace OCA\Text\Service;
+
+class EncodingService {
+	const COMMON_ENCODINGS = ['UTF-8', 'WINDOWS-1252', 'ISO-8859-15', 'ISO-8859-1', 'ASCII'];
+
+	public function encodeToUtf8(string $string): ?string {
+		$encoding = mb_detect_encoding($string, $this->getEncodings(), true);
+		if (!$encoding) {
+			return null;
+		}
+
+		return mb_convert_encoding($string, 'UTF-8', $encoding);
+	}
+
+	/**
+	 * @return string[]
+	 */
+	private function getEncodings(): array {
+		$mb_order = mb_detect_order() ?: [];
+		return array_merge($mb_order, self::COMMON_ENCODINGS);
+	}
+}