LibUnicode: Parse and generate per-locale plural rules from the CLDR

Plural rules in the CLDR are of the form:

"cs": {
    "pluralRule-count-one": "i = 1 and v = 0 @integer 1",
    "pluralRule-count-few": "i = 2..4 and v = 0 @integer 2~4",
    "pluralRule-count-many": "v != 0 @decimal 0.0~1.5, 10.0, 100.0 ...",
    "pluralRule-count-other": "@integer 0, 5~19, 100, 1000, 10000 ..."
}

The syntax is described here:
https://unicode.org/reports/tr35/tr35-numbers.html#Plural_rules_syntax

There are up to 2 sets of rules for each locale, a cardinal set and an
ordinal set. The approach here is to generate a C++ function for each
set of rules. Each condition in the rules (e.g. "i = 1 and v = 0") is
transpiled to a C++ if-statement within its function. Then lookup tables
are generated to match locales to their generated functions.

NOTE: -Wno-parentheses-equality is added to the LibUnicodeData compile
flags because the generated plural rules have lots of extra parentheses
(because e.g. we need to selectively negate and combine rules). The code
to generate only exactly the right number of parentheses is quite hairy,
so this just tells the compiler to ignore the extras.

1 files changed, 17 insertions, 0 deletions

diff --git a/Meta/CMake/unicode_data.cmake b/Meta/CMake/unicode_data.cmake
index b0c66d4edc..0adbed2d50 100644
--- a/Meta/CMake/unicode_data.cmake
+++ b/Meta/CMake/unicode_data.cmake
@@ -141,6 +141,9 @@ if (ENABLE_UNICODE_DATABASE_DOWNLOAD)
     set(UNICODE_NUMBER_FORMAT_HEADER LibUnicode/UnicodeNumberFormat.h)
     set(UNICODE_NUMBER_FORMAT_IMPLEMENTATION LibUnicode/UnicodeNumberFormat.cpp)
 
+    set(UNICODE_PLURAL_RULES_HEADER LibUnicode/UnicodePluralRules.h)
+    set(UNICODE_PLURAL_RULES_IMPLEMENTATION LibUnicode/UnicodePluralRules.cpp)
+
     set(UNICODE_RELATIVE_TIME_FORMAT_HEADER LibUnicode/UnicodeRelativeTimeFormat.h)
     set(UNICODE_RELATIVE_TIME_FORMAT_IMPLEMENTATION LibUnicode/UnicodeRelativeTimeFormat.cpp)
 
@@ -159,6 +162,9 @@ if (ENABLE_UNICODE_DATABASE_DOWNLOAD)
         set(UNICODE_NUMBER_FORMAT_HEADER UnicodeNumberFormat.h)
         set(UNICODE_NUMBER_FORMAT_IMPLEMENTATION UnicodeNumberFormat.cpp)
 
+        set(UNICODE_PLURAL_RULES_HEADER UnicodePluralRules.h)
+        set(UNICODE_PLURAL_RULES_IMPLEMENTATION UnicodePluralRules.cpp)
+
         set(UNICODE_RELATIVE_TIME_FORMAT_HEADER UnicodeRelativeTimeFormat.h)
         set(UNICODE_RELATIVE_TIME_FORMAT_IMPLEMENTATION UnicodeRelativeTimeFormat.cpp)
 
@@ -202,6 +208,15 @@ if (ENABLE_UNICODE_DATABASE_DOWNLOAD)
         arguments -r "${CLDR_CORE_PATH}" -n "${CLDR_NUMBERS_PATH}" -u "${CLDR_UNITS_PATH}"
     )
     invoke_generator(
+        "UnicodePluralRules"
+        Lagom::GenerateUnicodePluralRules
+        "${CLDR_VERSION_FILE}"
+        "${UNICODE_META_TARGET_PREFIX}"
+        "${UNICODE_PLURAL_RULES_HEADER}"
+        "${UNICODE_PLURAL_RULES_IMPLEMENTATION}"
+        arguments -r "${CLDR_CORE_PATH}" -l "${CLDR_LOCALES_PATH}"
+    )
+    invoke_generator(
         "UnicodeRelativeTimeFormat"
         Lagom::GenerateUnicodeRelativeTimeFormat
         "${CLDR_VERSION_FILE}"
@@ -220,6 +235,8 @@ if (ENABLE_UNICODE_DATABASE_DOWNLOAD)
         ${UNICODE_LOCALE_IMPLEMENTATION}
         ${UNICODE_NUMBER_FORMAT_HEADER}
         ${UNICODE_NUMBER_FORMAT_IMPLEMENTATION}
+        ${UNICODE_PLURAL_RULES_HEADER}
+        ${UNICODE_PLURAL_RULES_IMPLEMENTATION}
         ${UNICODE_RELATIVE_TIME_FORMAT_HEADER}
         ${UNICODE_RELATIVE_TIME_FORMAT_IMPLEMENTATION}
     )