Difference between revisions of "Module:Language/name/data"
Jump to navigation
Jump to search
imported>Lfdder m (Lfdder moved page Module:ISO 639 name/data to Module:Language/name/data without leaving a redirect) |
m (1 revision imported) |
||
| (8 intermediate revisions by 4 users not shown) | |||
| Line 2: | Line 2: | ||
local function __coalesce(...) | local function __coalesce(...) | ||
local coalesced = {} | local coalesced = {} | ||
| − | for | + | for _, langslist in ipairs{...} do |
| − | for | + | for langcode, langnames in pairs(langslist) do |
| − | for | + | for _, langname in pairs(langnames) do |
| − | if not coalesced[ | + | if not coalesced[langcode] then |
| − | coalesced[ | + | coalesced[langcode] = {} |
end | end | ||
| − | table.insert(coalesced[ | + | table.insert(coalesced[langcode], langname) |
end | end | ||
end | end | ||
| Line 20: | Line 20: | ||
local preprocessed = {} | local preprocessed = {} | ||
if first_of_array_in_array then | if first_of_array_in_array then | ||
| + | -- keep only the 1st language name for each code, excluding synonyms | ||
for k, v in pairs(t) do | for k, v in pairs(t) do | ||
preprocessed[k:lower()] = {v[1]} | preprocessed[k:lower()] = {v[1]} | ||
| Line 32: | Line 33: | ||
end | end | ||
| − | local | + | -- all valid primary language subtags for BCP47 from IANA (most of them from ISO 639-1, -2 and -3 with some exclusions) |
| − | local | + | local __iana_languages = __preprocess(require("Module:Language/data/iana languages")); |
| − | local __wp_languages = __preprocess(require("Module:Language/data/wp languages"), true) | + | -- ISO 639-3 contains additional 3-letter codes not inserted in the IANA database as they are aliased to 2-letter codes, |
| − | local iana_scripts = __preprocess(require("Module:Language/data/iana scripts")) | + | -- but excludes some deleted codes still valid in BCP47 (some of them are aliased) |
| − | local iana_regions = __preprocess(require("Module:Language/data/iana regions")) | + | local __iso_639_3 = __preprocess(require("Module:Language/data/ISO 639-3")); |
| − | + | -- Wikimedia wikis uses some non-standard codes and a subset of IANA codes, plus composite codes | |
| + | local __wp_languages = __preprocess(require("Module:Language/data/wp languages"), true); | ||
| + | -- all valid script subtags for BCP47 from IANA (excluding special ISO 15924 codes) | ||
| + | local iana_scripts = __preprocess(require("Module:Language/data/iana scripts")); | ||
| + | -- all valid region subtags for BCP47 from IANA (derived from ISO 3166-1 excluding special codes, and from 3-digit UN M.49 codes for groups of countries) | ||
| + | local iana_regions = __preprocess(require("Module:Language/data/iana regions")); | ||
| + | |||
| + | -- variant subtags from IANA; table format differs from the other IANA data tables | ||
| + | local iana_variants = __preprocess(require("Module:Language/data/iana variants")); | ||
| + | -- suppressed script subtags from IANA; | ||
| + | local iana_suppressed_scripts = __preprocess (require("Module:Language/data/iana suppressed scripts")); | ||
| + | |||
return { | return { | ||
lang = __coalesce(__wp_languages, __iana_languages, __iso_639_3), | lang = __coalesce(__wp_languages, __iana_languages, __iso_639_3), | ||
lang_iana = __iana_languages, | lang_iana = __iana_languages, | ||
script = iana_scripts, | script = iana_scripts, | ||
| − | region = iana_regions | + | region = iana_regions, |
| + | variant = iana_variants, | ||
| + | suppressed = iana_suppressed_scripts, | ||
} | } | ||
Latest revision as of 14:34, 9 March 2020
Documentation for this module may be created at Module:Language/name/data/doc
-- put tables and their tables together
local function __coalesce(...)
local coalesced = {}
for _, langslist in ipairs{...} do
for langcode, langnames in pairs(langslist) do
for _, langname in pairs(langnames) do
if not coalesced[langcode] then
coalesced[langcode] = {}
end
table.insert(coalesced[langcode], langname)
end
end
end
return coalesced
end
-- make the keys lowercase
local function __preprocess(t, first_of_array_in_array)
local preprocessed = {}
if first_of_array_in_array then
-- keep only the 1st language name for each code, excluding synonyms
for k, v in pairs(t) do
preprocessed[k:lower()] = {v[1]}
end
else
for k, v in pairs(t) do
preprocessed[k:lower()] = v
end
end
return preprocessed
end
-- all valid primary language subtags for BCP47 from IANA (most of them from ISO 639-1, -2 and -3 with some exclusions)
local __iana_languages = __preprocess(require("Module:Language/data/iana languages"));
-- ISO 639-3 contains additional 3-letter codes not inserted in the IANA database as they are aliased to 2-letter codes,
-- but excludes some deleted codes still valid in BCP47 (some of them are aliased)
local __iso_639_3 = __preprocess(require("Module:Language/data/ISO 639-3"));
-- Wikimedia wikis uses some non-standard codes and a subset of IANA codes, plus composite codes
local __wp_languages = __preprocess(require("Module:Language/data/wp languages"), true);
-- all valid script subtags for BCP47 from IANA (excluding special ISO 15924 codes)
local iana_scripts = __preprocess(require("Module:Language/data/iana scripts"));
-- all valid region subtags for BCP47 from IANA (derived from ISO 3166-1 excluding special codes, and from 3-digit UN M.49 codes for groups of countries)
local iana_regions = __preprocess(require("Module:Language/data/iana regions"));
-- variant subtags from IANA; table format differs from the other IANA data tables
local iana_variants = __preprocess(require("Module:Language/data/iana variants"));
-- suppressed script subtags from IANA;
local iana_suppressed_scripts = __preprocess (require("Module:Language/data/iana suppressed scripts"));
return {
lang = __coalesce(__wp_languages, __iana_languages, __iso_639_3),
lang_iana = __iana_languages,
script = iana_scripts,
region = iana_regions,
variant = iana_variants,
suppressed = iana_suppressed_scripts,
}