1
Fork 0
mirror of https://github.com/RGBCube/serenity synced 2025-05-31 16:38:10 +00:00

LibUnicode: Generate General Category unions and aliases

This downloads the PropertyValueAliases.txt UCD file, which contains a
set of General Category aliases.

This changes the General Category enumeration to now be generated as a
bitmask. This is to easily allow General Category unions. For example,
the LC (Cased_Letter) category is the union of the Ll, Lu, and Lt
categories.
This commit is contained in:
Timothy Flynn 2021-07-31 13:45:05 -04:00 committed by Ali Mohammad Pur
parent f87cc85cd3
commit 16e86ae743
3 changed files with 76 additions and 7 deletions

View file

@ -15,6 +15,9 @@ set(DERIVED_CORE_PROP_PATH ${CMAKE_BINARY_DIR}/UCD/DerivedCoreProperties.txt)
set(PROP_ALIAS_URL https://www.unicode.org/Public/13.0.0/ucd/PropertyAliases.txt)
set(PROP_ALIAS_PATH ${CMAKE_BINARY_DIR}/UCD/PropertyAliases.txt)
set(PROP_VALUE_ALIAS_URL https://www.unicode.org/Public/13.0.0/ucd/PropertyValueAliases.txt)
set(PROP_VALUE_ALIAS_PATH ${CMAKE_BINARY_DIR}/UCD/PropertyValueAliases.txt)
set(WORD_BREAK_URL https://www.unicode.org/Public/13.0.0/ucd/auxiliary/WordBreakProperty.txt)
set(WORD_BREAK_PATH ${CMAKE_BINARY_DIR}/UCD/WordBreakProperty.txt)
@ -39,6 +42,10 @@ if (ENABLE_UNICODE_DATABASE_DOWNLOAD)
message(STATUS "Downloading UCD PropertyAliases.txt from ${PROP_ALIAS_URL}...")
file(DOWNLOAD ${PROP_ALIAS_URL} ${PROP_ALIAS_PATH} INACTIVITY_TIMEOUT 10)
endif()
if (NOT EXISTS ${PROP_VALUE_ALIAS_PATH})
message(STATUS "Downloading UCD PropertyValueAliases.txt from ${PROP_VALUE_ALIAS_URL}...")
file(DOWNLOAD ${PROP_VALUE_ALIAS_URL} ${PROP_VALUE_ALIAS_PATH} INACTIVITY_TIMEOUT 10)
endif()
if (NOT EXISTS ${WORD_BREAK_PATH})
message(STATUS "Downloading UCD WordBreakProperty.txt from ${WORD_BREAK_URL}...")
file(DOWNLOAD ${WORD_BREAK_URL} ${WORD_BREAK_PATH} INACTIVITY_TIMEOUT 10)
@ -54,7 +61,7 @@ if (ENABLE_UNICODE_DATABASE_DOWNLOAD)
add_custom_command(
OUTPUT ${UNICODE_DATA_HEADER}
COMMAND ${write_if_different} ${UNICODE_DATA_HEADER} $<TARGET_FILE:GenerateUnicodeData> -h -u ${UNICODE_DATA_PATH} -s ${SPECIAL_CASING_PATH} -p ${PROP_LIST_PATH} -d ${DERIVED_CORE_PROP_PATH} -a ${PROP_ALIAS_PATH} -w ${WORD_BREAK_PATH}
COMMAND ${write_if_different} ${UNICODE_DATA_HEADER} $<TARGET_FILE:GenerateUnicodeData> -h -u ${UNICODE_DATA_PATH} -s ${SPECIAL_CASING_PATH} -p ${PROP_LIST_PATH} -d ${DERIVED_CORE_PROP_PATH} -a ${PROP_ALIAS_PATH} -v ${PROP_VALUE_ALIAS_PATH} -w ${WORD_BREAK_PATH}
VERBATIM
DEPENDS GenerateUnicodeData
MAIN_DEPENDENCY ${UNICODE_DATA_PATH} ${SPECIAL_CASING_PATH}
@ -62,7 +69,7 @@ if (ENABLE_UNICODE_DATABASE_DOWNLOAD)
add_custom_command(
OUTPUT ${UNICODE_DATA_IMPLEMENTATION}
COMMAND ${write_if_different} ${UNICODE_DATA_IMPLEMENTATION} $<TARGET_FILE:GenerateUnicodeData> -c -u ${UNICODE_DATA_PATH} -s ${SPECIAL_CASING_PATH} -p ${PROP_LIST_PATH} -d ${DERIVED_CORE_PROP_PATH} -a ${PROP_ALIAS_PATH} -w ${WORD_BREAK_PATH}
COMMAND ${write_if_different} ${UNICODE_DATA_IMPLEMENTATION} $<TARGET_FILE:GenerateUnicodeData> -c -u ${UNICODE_DATA_PATH} -s ${SPECIAL_CASING_PATH} -p ${PROP_LIST_PATH} -d ${DERIVED_CORE_PROP_PATH} -a ${PROP_ALIAS_PATH} -v ${PROP_VALUE_ALIAS_PATH} -w ${WORD_BREAK_PATH}
VERBATIM
DEPENDS GenerateUnicodeData
MAIN_DEPENDENCY ${UNICODE_DATA_PATH} ${SPECIAL_CASING_PATH}