From f2e0516934c489bd6883b7602d57accf959018e0 Mon Sep 17 00:00:00 2001
From: "C. Scott Ananian" <cscott@cscott.net>
Date: Fri, 19 Oct 2018 10:40:38 -0400
Subject: [PATCH] Include BCP 47 codes in $wgDummyLanguageCodes, but deprecate
 it

Add BCP 47 codes to $wgDummyLanguageCodes to ensure that
Language::factory() will return a valid MediaWiki-internal code if
given a BCP 47 alias.  We will want to make $wgDummyLanguageCodes a
private property of LanguageCode eventually, but let's start with
removing it from user configuration.

Setting $wgDummyLanguageCodes in LocalSettings.php has been deprecated
since 1.29.  Hard deprecate adding entries to $wgDummyLanguageCodes so
that we can eventually remove manual overrides from user
configuration.

This is a follow-up to 48ab87d0a37da80c2e2ae3a20f645548d2a787f9,
which described the various categories of codes, and
21ead7a98d1a103b77f1e3ba29a85493782d398b, which added the correct
BCP 47 mappings.

Bug: T207433
Change-Id: I9f6dda3360f79ab65f6392f44c98926588d851c8
---
 includes/DefaultSettings.php |  3 +++
 includes/Setup.php           | 13 +++++++++++++
 languages/LanguageCode.php   |  8 +++++---
 3 files changed, 21 insertions(+), 3 deletions(-)

diff --git a/includes/DefaultSettings.php b/includes/DefaultSettings.php
index 15d2627214..e954517888 100644
--- a/includes/DefaultSettings.php
+++ b/includes/DefaultSettings.php
@@ -3002,8 +3002,11 @@ $wgExtraLanguageNames = [];
  * @since 1.29
  */
 $wgExtraLanguageCodes = [
+	// Language codes of macro languages, which get mapped to the main language
 	'bh' => 'bho', // Bihari language family
 	'no' => 'nb', // Norwegian language family
+
+	// Language variants which get mapped to the main language
 	'simple' => 'en', // Simple English
 ];
 
diff --git a/includes/Setup.php b/includes/Setup.php
index bdfce62293..aba050d6e3 100644
--- a/includes/Setup.php
+++ b/includes/Setup.php
@@ -498,11 +498,24 @@ if ( is_array( $wgExtraNamespaces ) ) {
 	$wgCanonicalNamespaceNames = $wgCanonicalNamespaceNames + $wgExtraNamespaces;
 }
 
+// Hard-deprecate setting $wgDummyLanguageCodes in LocalSettings.php
+if ( count( $wgDummyLanguageCodes ) !== 0 ) {
+	wfDeprecated( '$wgDummyLanguageCodes', '1.29' );
+}
 // Merge in the legacy language codes, incorporating overrides from the config
 $wgDummyLanguageCodes += [
+	// Internal language codes of the private-use area which get mapped to
+	// themselves.
 	'qqq' => 'qqq', // Used for message documentation
 	'qqx' => 'qqx', // Used for viewing message keys
 ] + $wgExtraLanguageCodes + LanguageCode::getDeprecatedCodeMapping();
+// Merge in (inverted) BCP 47 mappings
+foreach ( LanguageCode::getNonstandardLanguageCodeMapping() as $code => $bcp47 ) {
+	$bcp47 = strtolower( $bcp47 ); // force case-insensitivity
+	if ( !isset( $wgDummyLanguageCodes[$bcp47] ) ) {
+		$wgDummyLanguageCodes[$bcp47] = $wgDummyLanguageCodes[$code] ?? $code;
+	}
+}
 
 // These are now the same, always
 // To determine the user language, use $wgLang->getCode()
diff --git a/languages/LanguageCode.php b/languages/LanguageCode.php
index b0baec1341..1e10496984 100644
--- a/languages/LanguageCode.php
+++ b/languages/LanguageCode.php
@@ -31,9 +31,10 @@ class LanguageCode {
 	 * Mapping of deprecated language codes that were used in previous
 	 * versions of MediaWiki to up-to-date, current language codes.
 	 * These may or may not be valid BCP 47 codes; they are included here
-	 * because MediaWiki remapped these particular codes at some point.
+	 * because MediaWiki renamed these particular codes at some point.
 	 *
-	 * @var array Mapping from language code to language code
+	 * @var array Mapping from deprecated MediaWiki-internal language code
+	 *   to replacement MediaWiki-internal language code.
 	 *
 	 * @since 1.30
 	 * @see https://meta.wikimedia.org/wiki/Special_language_codes
@@ -71,7 +72,8 @@ class LanguageCode {
 	 * `kk-Cyrl` is a valid code, although some validators may emit
 	 * a warning note.
 	 *
-	 * @var array Mapping from nonstandard codes to BCP 47 codes
+	 * @var array Mapping from nonstandard MediaWiki-internal codes to
+	 *   BCP 47 codes
 	 *
 	 * @since 1.32
 	 * @see https://meta.wikimedia.org/wiki/Special_language_codes
-- 
2.20.1