From 93ee9220270c86f63c5629ffe974f8eccb1c414d Mon Sep 17 00:00:00 2001
From: Timothy Flynn <trflynn89@pm.me>
Date: Wed, 17 Nov 2021 09:56:16 -0500
Subject: [PATCH] LibUnicode: Support locales-without-script aliases for
 ECMA-402

As noted by ECMA-402, if a supported locale contains all of a language,
script, and region subtag, then the implementation must also support the
locale without the script subtag. The most complicated example of this
is the zh-TW locale.

The list of locales in the CLDR database does not include zh-TW or its
maximized zh-Hant-TW variant. Instead, it inlcudes the zh-Hant locale.
However, zh-Hant-TW is listed in the default-content locale list in the
cldr-core package. This defines an alias from zh-Hant-TW to zh-Hant. We
must then also support the zh-Hant-TW alias without the script subtag:
zh-TW. This transitively maps zh-TW to zh-Hant, which is a case quite
heavily tested by test262.
---
 .../LibUnicode/GenerateUnicodeLocale.cpp      | 43 +++++++++++++++++++
 Tests/LibUnicode/TestUnicodeLocale.cpp        |  8 ++++
 2 files changed, 51 insertions(+)

diff --git a/Meta/Lagom/Tools/CodeGenerators/LibUnicode/GenerateUnicodeLocale.cpp b/Meta/Lagom/Tools/CodeGenerators/LibUnicode/GenerateUnicodeLocale.cpp
index 78e64a861c4..f8cf25ec5a0 100644
--- a/Meta/Lagom/Tools/CodeGenerators/LibUnicode/GenerateUnicodeLocale.cpp
+++ b/Meta/Lagom/Tools/CodeGenerators/LibUnicode/GenerateUnicodeLocale.cpp
@@ -427,6 +427,48 @@ static void parse_default_content_locales(String core_path, UnicodeLocaleData& l
     });
 }
 
+static void define_aliases_without_scripts(UnicodeLocaleData& locale_data)
+{
+    // From ECMA-402: https://tc39.es/ecma402/#sec-internal-slots
+    //
+    //     For locales that include a script subtag in addition to language and region, the
+    //     corresponding locale without a script subtag must also be supported.
+    //
+    // So we define aliases for locales that contain all three subtags, but we must also take
+    // care to handle when the locale itself or the locale without a script subtag are an alias
+    // by way of default-content locales.
+    auto find_alias = [&](auto const& locale) {
+        return locale_data.locale_aliases.find_if([&](auto const& alias) { return locale == alias.alias; });
+    };
+
+    auto append_alias_without_script = [&](auto const& locale) {
+        auto parsed_locale = CanonicalLanguageID<StringIndexType>::parse(locale_data.unique_strings, locale);
+        VERIFY(parsed_locale.has_value());
+
+        if ((parsed_locale->language == 0) || (parsed_locale->script == 0) || (parsed_locale->region == 0))
+            return;
+
+        auto locale_without_script = String::formatted("{}-{}",
+            locale_data.unique_strings.get(parsed_locale->language),
+            locale_data.unique_strings.get(parsed_locale->region));
+
+        if (locale_data.locales.contains(locale_without_script))
+            return;
+        if (find_alias(locale_without_script) != locale_data.locale_aliases.end())
+            return;
+
+        if (auto it = find_alias(locale); it != locale_data.locale_aliases.end())
+            locale_data.locale_aliases.append({ it->name, locale_without_script });
+        else
+            locale_data.locale_aliases.append({ locale, locale_without_script });
+    };
+
+    for (auto const& locale : locale_data.locales)
+        append_alias_without_script(locale.key);
+    for (auto const& locale : locale_data.locale_aliases)
+        append_alias_without_script(locale.alias);
+}
+
 static void parse_all_locales(String core_path, String locale_names_path, String misc_path, String numbers_path, UnicodeLocaleData& locale_data)
 {
     auto identity_iterator = path_to_dir_iterator(locale_names_path);
@@ -508,6 +550,7 @@ static void parse_all_locales(String core_path, String locale_names_path, String
     }
 
     parse_default_content_locales(move(core_path), locale_data);
+    define_aliases_without_scripts(locale_data);
 }
 
 static String format_identifier(StringView owner, String identifier)
diff --git a/Tests/LibUnicode/TestUnicodeLocale.cpp b/Tests/LibUnicode/TestUnicodeLocale.cpp
index 34619c8cd78..9f8064212a4 100644
--- a/Tests/LibUnicode/TestUnicodeLocale.cpp
+++ b/Tests/LibUnicode/TestUnicodeLocale.cpp
@@ -463,3 +463,11 @@ TEST_CASE(canonicalize_unicode_locale_id)
     test("zh-Hans-CN"sv, "zh-Hans-CN"sv);
     test("ZH-HANS-CN"sv, "zh-Hans-CN"sv);
 }
+
+TEST_CASE(supports_locale_aliases)
+{
+    EXPECT(Unicode::is_locale_available("zh"sv));
+    EXPECT(Unicode::is_locale_available("zh-Hant"sv));
+    EXPECT(Unicode::is_locale_available("zh-TW"sv));
+    EXPECT(Unicode::is_locale_available("zh-Hant-TW"sv));
+}