From 660caf9b88ef58997f446434438237bc0d73a9cd Mon Sep 17 00:00:00 2001
From: jhsoby <jhsoby@gmail.com>
Date: Thu, 7 Dec 2017 14:47:24 +0100
Subject: [PATCH] Add custom collation for Northern Sami

This commit adds a custom collation order for
Northern Sami ('se'). Northern Sami exists in ICU,
but the version of ICU that Wikimedia uses is a
few years old, and does *not* include Northern
Sami. It could be years before Wikimedia's production
servers use the one that includes Northern Sami (see
bug), so this is a temporary workaround to amend this
issue.

Bug: T181503
Change-Id: Ib8a48b8db99bef8ec4b05144aace5dbdcacfeded
---
 autoload.php                                  |  1 +
 includes/collation/Collation.php              |  2 +
 .../NorthernSamiUppercaseCollation.php        | 83 +++++++++++++++++++
 3 files changed, 86 insertions(+)
 create mode 100644 includes/collation/NorthernSamiUppercaseCollation.php

diff --git a/autoload.php b/autoload.php
index 2661fd7ed3..cd01828a6c 100644
--- a/autoload.php
+++ b/autoload.php
@@ -1040,6 +1040,7 @@ $wgAutoloadLocalClasses = [
 	'NewPagesPager' => __DIR__ . '/includes/specials/pagers/NewPagesPager.php',
 	'NewUsersLogFormatter' => __DIR__ . '/includes/logging/NewUsersLogFormatter.php',
 	'NolinesImageGallery' => __DIR__ . '/includes/gallery/NolinesImageGallery.php',
+	'NorthernSamiUppercaseCollation' => __DIR__ . '/includes/collation/NorthernSamiUppercaseCollation.php',
 	'NotRecursiveIterator' => __DIR__ . '/includes/libs/iterators/NotRecursiveIterator.php',
 	'NukeNS' => __DIR__ . '/maintenance/nukeNS.php',
 	'NukePage' => __DIR__ . '/maintenance/nukePage.php',
diff --git a/includes/collation/Collation.php b/includes/collation/Collation.php
index d009168d5e..7171a218ae 100644
--- a/includes/collation/Collation.php
+++ b/includes/collation/Collation.php
@@ -67,6 +67,8 @@ abstract class Collation {
 				return new CollationFa;
 			case 'uppercase-ba':
 				return new BashkirUppercaseCollation;
+			case 'uppercase-se':
+				return new NorthernSamiUppercaseCollation;
 			default:
 				$match = [];
 				if ( preg_match( '/^uca-([A-Za-z@=-]+)$/', $collationName, $match ) ) {
diff --git a/includes/collation/NorthernSamiUppercaseCollation.php b/includes/collation/NorthernSamiUppercaseCollation.php
new file mode 100644
index 0000000000..d373749e54
--- /dev/null
+++ b/includes/collation/NorthernSamiUppercaseCollation.php
@@ -0,0 +1,83 @@
+<?php
+/**
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 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 General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
+ * http://www.gnu.org/copyleft/gpl.html
+ *
+ * @since 1.31
+ *
+ * @file
+ */
+
+/**
+ * Temporary workaround for incorrect collation of Northern Sami
+ * language ('se') in Wikimedia servers (see bug T181503).
+ *
+ * When the ICU's 'se' collation has been included in PHP-intl and Wikimedia
+ * servers updated to that new version of PHP, this file should be deleted
+ * and the collation for 'se' set to 'uca-se'.
+ *
+ * @since 1.31
+ */
+
+class NorthernSamiUppercaseCollation extends CustomUppercaseCollation {
+
+	public function __construct() {
+		parent::__construct( [
+			'A',
+			'Á',
+			'B',
+			'C',
+			'Č',
+			'Æ·', // Not part of modern alphabet, but part of ICU
+			'Ç®', // Not part of modern alphabet, but part of ICU
+			'D',
+			'Đ',
+			'E',
+			'F',
+			'G',
+			'Ǧ', // Not part of modern alphabet, but part of ICU
+			'Ǥ', // Not part of modern alphabet, but part of ICU
+			'H',
+			'I',
+			'J',
+			'K',
+			'Ǩ', // Not part of modern alphabet, but part of ICU
+			'L',
+			'M',
+			'N',
+			'Ŋ',
+			'O',
+			'P',
+			'Q',
+			'R',
+			'S',
+			'Å ',
+			'T',
+			'Ŧ',
+			'U',
+			'V',
+			'W',
+			'X',
+			'Y',
+			'Z',
+			'Ž',
+			'Ø', // Not part of native alphabet, but part of ICU
+			'Æ', // Not part of native alphabet, but part of ICU
+			'Å', // Not part of native alphabet, but part of ICU
+			'Ä', // Not part of native alphabet, but part of ICU
+			'Ö', // Not part of native alphabet, but part of ICU
+		], Language::factory( 'se' ) );
+	}
+}
-- 
2.20.1