ci: Restrict RTL characters to RTL languages

Signed-off-by: Joas Schilling <coding@schilljs.com>

build/translation-checker.php

@@ -1,22 +1,7 @@
 <?php
 /**
- * @copyright Copyright (c) 2017 Joas Schilling <coding@schilljs.com>
- *
- * @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/>.
- *
+ * SPDX-FileCopyrightText: 2017 Nextcloud GmbH and Nextcloud contributors
+ * SPDX-License-Identifier: AGPL-3.0-or-later
  */
 
 $directories = [
@@ -25,17 +10,59 @@
 
 $isDebug = in_array('--debug', $argv, true) || in_array('-d', $argv, true);
 
+$txConfig = file_get_contents(__DIR__ . '/../.tx/config');
+
+$untranslatedApps = [
+	'testing',
+];
+
+// Next line only looks messed up, but it works. Don't touch it!
+$rtlCharacters = [
+	'\x{061C}', // ARABIC LETTER MARK
+	'\x{0623}', // ARABIC LETTER ALEF WITH HAMZA ABOVE
+	'\x{200E}', // LEFT-TO-RIGHT MARK
+	'\x{200F}', // RIGHT-TO-LEFT MARK
+	'\x{202A}', // LEFT-TO-RIGHT EMBEDDING
+	'\x{202B}', // RIGHT-TO-LEFT EMBEDDING
+	'\x{202C}', // POP DIRECTIONAL FORMATTING
+	'\x{202D}', // LEFT-TO-RIGHT OVERRIDE
+	'\x{202E}', // RIGHT-TO-LEFT OVERRIDE
+	'\x{2066}', // LEFT-TO-RIGHT ISOLATE
+	'\x{2067}', // RIGHT-TO-LEFT ISOLATE
+	'\x{2068}', // FIRST STRONG ISOLATE
+	'\x{2069}', // POP DIRECTIONAL ISOLATE
+	'\x{206C}', // INHIBIT ARABIC FORM SHAPING
+	'\x{206D}', // ACTIVATE ARABIC FORM SHAPING
+];
+
+$rtlLanguages = [
+	'ar', // Arabic
+	'fa', // Persian
+	'he', // Hebrew
+	'ps', // Pashto,
+	'ug', // 'Uyghurche / Uyghur
+	'ur_PK', // Urdu
+	'uz', // Uzbek Afghan
+];
+
+$valid = 0;
+$errors = [];
 $apps = new \DirectoryIterator(__DIR__ . '/../apps');
 foreach ($apps as $app) {
+	if ($app->isDot() || in_array($app->getBasename(), $untranslatedApps, true)) {
+		continue;
+	}
+
 	if (!file_exists($app->getPathname() . '/l10n')) {
+		if (!str_contains($txConfig, '[o:nextcloud:p:nextcloud:r:' . $app->getBasename() . ']')) {
+			$errors[] = $app->getBasename() . "\n" . '  App is not translation synced via transifex and also not marked as untranslated' . "\n";
+		}
 		continue;
 	}
 
 	$directories[] = $app->getPathname() . '/l10n';
 }
 
-$errors = [];
-$valid = 0;
 foreach ($directories as $dir) {
 	if (!file_exists($dir)) {
 		continue;
@@ -48,6 +75,12 @@
 		}
 
 		$content = file_get_contents($file->getPathname());
+
+		$language = pathinfo($file->getFilename(), PATHINFO_FILENAME);
+		if (!in_array($language, $rtlLanguages, true) && preg_match('/[' . implode('', $rtlCharacters) . ']/u', $content)) {
+			$errors[] = $file->getPathname() . "\n" . '  ' . 'Contains a RTL limited character in the translations.' . "\n";
+		}
+
 		$json = json_decode($content, true);
 
 		$translations = json_encode($json['translations']);
@@ -74,10 +107,10 @@
 }
 
 if (count($errors) > 0) {
-	echo sprintf('ERROR: There were %d errors:', count($errors)) . "\n\n";
+	echo "\033[0;31m" . sprintf('ERROR: There were %d errors:', count($errors)) . "\033[0m\n\n";
 	echo implode("\n", $errors);
 	exit(1);
 }
 
-echo 'OK: ' . $valid . ' files parse' . "\n";
+echo "\033[0;32m" . 'OK: ' . $valid . ' files parse' . "\033[0m\n";
 exit(0);