LibLocale+LibJS: Update to CLDR version 42.0.0

There were some notable changes to the CLDR JSON format and data in this
release.

The patterns for a date at a specific time, i.e. "{date} at {time}", now
appear under the "atTime" attribute of the "dateTimeFormats" object.

Locale specific changes that affected test-js:

All locales:

* In many patterns, the code points U+00A0 (NO-BREAK SPACE) and U+202F
  (NARROW NO-BREAK SPACE) are now used in place of an ASCII space. For
  example, before the "dayPeriod" fields AM and PM.

* Separators such as U+2013 (EN DASH) are now surrounded by U+2009 (THIN
  SPACE) in place of an ASCII space character.

Locale "en":

* Narrow localizations of time formats are even more narrow. For
  example, the abbreviation "wk." for "week" is now just "wk".

Locale "ar":

* The code point U+060C (ARABIC COMMA) is now used in place of an ASCII
  comma.

* The code point U+200F (RIGHT-TO-LEFT MARK) now appears at the
  beginning of many localizations.

* When the "latn" numbering system is used for currency formatting, the
  currency symbol more consistently is placed at the end of the pattern.

Locale "he":

* The "many" plural rules category has been removed.

Locales "zh" and "es-419":

* Several display-name localizations were changed.

3 files changed, 36 insertions, 19 deletions

diff --git a/Meta/CMake/locale_data.cmake b/Meta/CMake/locale_data.cmake
index a548ff67e6..292247db55 100644
--- a/Meta/CMake/locale_data.cmake
+++ b/Meta/CMake/locale_data.cmake
@@ -1,6 +1,6 @@
 include(${CMAKE_CURRENT_LIST_DIR}/utils.cmake)
 
-set(CLDR_VERSION 41.0.0)
+set(CLDR_VERSION 42.0.0)
 set(CLDR_PATH "${CMAKE_BINARY_DIR}/CLDR" CACHE PATH "Download location for CLDR files")
 set(CLDR_VERSION_FILE "${CLDR_PATH}/version.txt")
 
diff --git a/Meta/Lagom/Tools/CodeGenerators/LibLocale/GenerateDateTimeFormatData.cpp b/Meta/Lagom/Tools/CodeGenerators/LibLocale/GenerateDateTimeFormatData.cpp
index 644bbd0818..d8d6dc0527 100644
--- a/Meta/Lagom/Tools/CodeGenerators/LibLocale/GenerateDateTimeFormatData.cpp
+++ b/Meta/Lagom/Tools/CodeGenerators/LibLocale/GenerateDateTimeFormatData.cpp
@@ -39,8 +39,8 @@ constexpr auto s_calendar_pattern_list_index_type = "u8"sv;
 using CalendarRangePatternIndexType = u16;
 constexpr auto s_calendar_range_pattern_index_type = "u16"sv;
 
-using CalendarRangePatternListIndexType = u8;
-constexpr auto s_calendar_range_pattern_list_index_type = "u8"sv;
+using CalendarRangePatternListIndexType = u16;
+constexpr auto s_calendar_range_pattern_list_index_type = "u16"sv;
 
 using CalendarFormatIndexType = u8;
 constexpr auto s_calendar_format_index_type = "u8"sv;
@@ -764,32 +764,48 @@ static constexpr auto is_char(char ch)
 // "{hour}:{minute} {ampm} {timeZoneName}" becomes "{hour}:{minute} {timeZoneName}" (remove one of the spaces around {ampm})
 static String remove_period_from_pattern(String pattern)
 {
+    auto is_surrounding_space = [&](auto code_point_iterator) {
+        if (code_point_iterator.done())
+            return false;
+
+        constexpr auto spaces = Array { static_cast<u32>(0x0020), 0x00a0, 0x2009, 0x202f };
+        return spaces.span().contains_slow(*code_point_iterator);
+    };
+
+    auto is_opening = [&](auto code_point_iterator) {
+        if (code_point_iterator.done())
+            return false;
+        return *code_point_iterator == '{';
+    };
+
+    auto is_closing = [&](auto code_point_iterator) {
+        if (code_point_iterator.done())
+            return false;
+        return *code_point_iterator == '}';
+    };
+
     for (auto remove : AK::Array { "({ampm})"sv, "{ampm}"sv, "({dayPeriod})"sv, "{dayPeriod}"sv }) {
         auto index = pattern.find(remove);
         if (!index.has_value())
             continue;
 
-        constexpr u32 space = ' ';
-        constexpr u32 open = '{';
-        constexpr u32 close = '}';
-
         Utf8View utf8_pattern { pattern };
-        Optional<u32> before_removal;
-        Optional<u32> after_removal;
+        Utf8CodePointIterator before_removal;
+        Utf8CodePointIterator after_removal;
 
         for (auto it = utf8_pattern.begin(); utf8_pattern.byte_offset_of(it) < *index; ++it)
-            before_removal = *it;
+            before_removal = it;
         if (auto it = utf8_pattern.iterator_at_byte_offset(*index + remove.length()); it != utf8_pattern.end())
-            after_removal = *it;
+            after_removal = it;
 
-        if ((before_removal == space) && (after_removal != open)) {
+        if (is_surrounding_space(before_removal) && !is_opening(after_removal)) {
             pattern = String::formatted("{}{}",
-                pattern.substring_view(0, *index - 1),
+                pattern.substring_view(0, *index - before_removal.underlying_code_point_length_in_bytes()),
                 pattern.substring_view(*index + remove.length()));
-        } else if ((after_removal == space) && (before_removal != close)) {
+        } else if (is_surrounding_space(after_removal) && !is_closing(before_removal)) {
             pattern = String::formatted("{}{}",
                 pattern.substring_view(0, *index),
-                pattern.substring_view(*index + remove.length() + 1));
+                pattern.substring_view(*index + remove.length() + after_removal.underlying_code_point_length_in_bytes()));
         } else {
             pattern = String::formatted("{}{}",
                 pattern.substring_view(0, *index),
@@ -1466,9 +1482,10 @@ static ErrorOr<void> parse_calendars(String locale_calendars_path, CLDR& cldr, L
         auto const& time_skeletons_object = value.as_object().get("timeSkeletons"sv);
         calendar.time_formats = parse_patterns(time_formats_object.as_object(), time_skeletons_object.as_object(), &time_formats);
 
-        auto const& date_time_formats_object = value.as_object().get("dateTimeFormats"sv);
-        calendar.date_time_formats = parse_patterns(date_time_formats_object.as_object(), JsonObject {}, nullptr);
+        auto const& standard_date_time_formats_object = value.as_object().get("dateTimeFormats-atTime"sv).as_object().get("standard"sv);
+        calendar.date_time_formats = parse_patterns(standard_date_time_formats_object.as_object(), JsonObject {}, nullptr);
 
+        auto const& date_time_formats_object = value.as_object().get("dateTimeFormats"sv);
         auto const& available_formats_object = date_time_formats_object.as_object().get("availableFormats"sv);
         available_formats_object.as_object().for_each_member([&](auto const& skeleton, JsonValue const& pattern) {
             auto pattern_index = parse_date_time_pattern(pattern.as_string(), skeleton, cldr);
diff --git a/Meta/Lagom/Tools/CodeGenerators/LibLocale/GenerateLocaleData.cpp b/Meta/Lagom/Tools/CodeGenerators/LibLocale/GenerateLocaleData.cpp
index 32f34ac24b..b8d69c4a99 100644
--- a/Meta/Lagom/Tools/CodeGenerators/LibLocale/GenerateLocaleData.cpp
+++ b/Meta/Lagom/Tools/CodeGenerators/LibLocale/GenerateLocaleData.cpp
@@ -43,8 +43,8 @@ constexpr auto s_currency_list_index_type = "u16"sv;
 using CalendarListIndexType = u8;
 constexpr auto s_calendar_list_index_type = "u8"sv;
 
-using DateFieldListIndexType = u8;
-constexpr auto s_date_field_list_index_type = "u8"sv;
+using DateFieldListIndexType = u16;
+constexpr auto s_date_field_list_index_type = "u16"sv;
 
 using KeywordListIndexType = u8;
 constexpr auto s_keyword_list_index_type = "u8"sv;