mirror of
https://github.com/wxWidgets/wxWidgets.git
synced 2026-08-19 02:42:23 +08:00
Ulrich Telle
57e1c9e1ee
This commit improves the best locale match algorithm by prioritizing closer matches and add many new tests verifying that this works as expected. In order to do this, new information had to be added to the language database, which was extended with it and updated to use the latest Unicode CLDR data and latest Windows 11 locale list. Further, add a set of scripts for maintaining the language database up to date and a GitHub workflow `genlangdb.yml` which can be run manually to regenerate the wxWidgets language-related source and header files from the underlying Windows and Unicode data. It produces 2 artifacts: - wxLanguageDatabaseDist.zip allows to easily update the language-related files in the wxWidgets repository by simply copying all files. - the normal workflow log and wxLanguageDatabaseLog.zip allow to check all temporary files of the regeneration process and to detect potential issues, before the language-related files are actually replaced by the new ones. Finally, fix wxUILocaleImplName::GetPreferredUILanguages: Under Windows 10 and above the Windows API function ::GetUserPreferredUILanguages() returns only the primary UI language plus US English. Additional preferred UI languages installed by the user are ignored, so instead of using this function read the list of user preferred languages from the Windows registry. Closes #24855.
72 lines
2.2 KiB
Lua
72 lines
2.2 KiB
Lua
-- Generate a script map based on ISO 15924 data
|
|
--
|
|
-- Data source: Unicode
|
|
-- URL: https://www.unicode.org/iso15924/iso15924.txt
|
|
-- License: UNICODE, INC. LICENSE AGREEMENT - DATA FILES AND SOFTWARE
|
|
|
|
codeFileName = "unicode/iso15924.txt"
|
|
|
|
function split(str, character)
|
|
result = {}
|
|
|
|
index = 1
|
|
for s in string.gmatch(str .. character, "(.-)"..character) do
|
|
result[index] = s
|
|
index = index + 1
|
|
end
|
|
|
|
return result
|
|
end
|
|
|
|
fo2 = io.open('temp/uni_loadscriptmap.sql','w')
|
|
fo2:write('-- Mapping of script codes based on ISO 15924\n-- Date: ' .. os.date("%Y-%m-%d %H:%M") .. '\n\n')
|
|
fo2:write('-- Data source: Unicode Org (https://www.unicode.org)\n')
|
|
fo2:write('-- URL: https://www.unicode.org/iso15924/iso15924.txt\n')
|
|
fo2:write('-- License: UNICODE, INC. LICENSE AGREEMENT - DATA FILES AND SOFTWARE\n\n')
|
|
|
|
fo2:write("create table if not exists uni_scriptmap (sctag char, scname char, scalias char, primary key (sctag));\n")
|
|
fo2:write('delete from uni_scriptmap;\nbegin;\n')
|
|
|
|
-- Names and order of data columns
|
|
-- Code|N°|English Name|Nom français|Alias|Age|Date
|
|
|
|
noalias = 0
|
|
count = 0
|
|
for line in io.lines(codeFileName) do
|
|
rem = string.sub(line,1,1)
|
|
if rem ~= "#" and rem ~= "" then
|
|
values = split(line, ";")
|
|
sctag = values[1]
|
|
scnum = values[2]
|
|
scname = values[3]
|
|
scname_fr = values[4]
|
|
scalias = values[5]
|
|
scage = values[6]
|
|
scdate = values[7]
|
|
|
|
scname = scname:gsub("'", "''")
|
|
if scalias == "" then
|
|
if sctag == "Hans" or sctag == "Hant" then
|
|
scalias = sctag
|
|
else
|
|
noalias = noalias + 1
|
|
scalias = "-"
|
|
end
|
|
end
|
|
|
|
fo2:write("insert into uni_scriptmap values ('" .. sctag .. "', '" .. scname .. "', '" .. scalias .. "');\n")
|
|
count = count + 1
|
|
end
|
|
end
|
|
print(" Number of script mappings = " .. count)
|
|
print(" Number of missing script aliases = " .. noalias)
|
|
if noalias > 0 then
|
|
print(" Script aliases are used in POSIX locale identifiers where they are")
|
|
print(" used as modifiers to represent the script of a language.")
|
|
print(" Missing script aliases impose a problem only for script identifiers")
|
|
print(" actually used in locale tags supported by wxWidgets.")
|
|
end
|
|
|
|
fo2:write('commit;\n')
|
|
fo2:close()
|