Module:data consistency check

-- TODO:
	-- ietf_subtag field used with a 2/3-letter langauge/family code except qaa-qtz, or a 4-letter script code.
	-- Check against files containing up-to-date ISO data, to cross-check validity.

local m_languages = require("Module:languages")
local m_language_data = require("Module:languages/data/all")
local m_language_codes = require("Module:languages/code to canonical name")
local m_language_canonical_names = require("Module:languages/canonical names")
local m_etym_language_data = require("Module:etymology languages/data")
local m_etym_language_codes = require("Module:etymology languages/code to canonical name")
local m_etym_language_canonical_names = require("Module:etymology languages/canonical names")
local m_family_data = require("Module:families/data")
local m_family_codes = require("Module:families/code to canonical name")
local m_family_canonical_names = require("Module:families/canonical names")
local m_scripts = require("Module:scripts")
local m_script_data = require("Module:scripts/data")
local m_links = require("Module:links")

local m_script_utils = require("Module:script utilities")
local m_str_utils = require("Module:string utilities")
local m_table = require("Module:table")
local Array = require("Module:array")

local codepoint = m_str_utils.codepoint
local concat = table.concat
local dump = mw.dumpObject
local gcodepoint = m_str_utils.gcodepoint
local get_lang = m_languages.getByCode
local insert = table.insert
local list_to_text = mw.text.listToText
local new_title = mw.title.new
local split = m_str_utils.split
local ugmatch = m_str_utils.gmatch
local umatch = m_str_utils.match

local export = {}
local messages

local function discrepancy(modname, ...)
	local ok, result = pcall(function(...) messages[modname]:insert(string.format(...)) end, ...)
	if not ok then
		mw.log(result, ...)
	end
end

local all_codes = {}

local language_names = {}
local etym_language_names = {}
local family_names = {}
local script_names = {}

local nonempty_families = {}
local allowed_empty_families = {tbq = true}
local nonempty_scripts = {}
	
do
	local function link_lang(name)
		if name:find("[Ll]anguage$") then
			return "[[:Category:" .. name .. "|" .. name .. "]]"
		else
			return "[[:Category:" .. name .. " language|" .. name .. " language]]"
		end
	end
	
	local function link_etym_lang(name)
		if name:find("[Ll]anguage$") then
			return name
		else
			return name .. " language"
		end
	end
	
	local function link_family(name)
		if name:match("[Ll]anguages$") or name:match("[Ll]ects$") then
			return "[[:Category:" .. name .. "|" .. name .. " family]]"
		else
			return "[[:Category:" .. name .. " languages|" .. name .. " family]]"
		end
	end
	
	function export.link(data)
		if not data[1] then
			return "???"
		end
		local type = data.type
		return type:match("etymology%-only") and link_etym_lang(data[1]) or
			type:match("family") and link_family(data[1]) or
			link_lang(data[1])
	end
end
local link = export.link
	
local function link_script(name)
	if not name then
		return "???"
	elseif name:find("[Cc]ode$") or name:find("[Ss]emaphore$") then
		return "[[:Category:" .. name:gsub("^%l", string.upper) .. "|" .. name .. "]]"
	else
		return "[[:Category:" .. name .. " script|" .. name .. " script]]"
	end
end

local function invalid_keys_message(modname, code, data, invalid_keys, is_script)
	local plural = #invalid_keys ~= 1
	discrepancy(modname, "The data key%s %s for %s (<code>%s</code>) %s invalid.",
		plural and "s" or "",
		invalid_keys
			:map(
				function(key)
					return "<code>" .. key .. "</code>"
				end)
			:concat(", "),
		(is_script and link_script or link)(data[1]),
		code,
		plural and "are" or "is")
end

local function check_data_keys(valid_keys, is_script)
	valid_keys = Array(valid_keys):to_set()
	
	return function (modname, code, data)
		local invalid_keys
		for k in pairs(data) do
			if not valid_keys[k] then
				invalid_keys = invalid_keys or Array()
				invalid_keys:insert(k)
			end
		end
		if invalid_keys then
			invalid_keys_message(modname, code, data, invalid_keys, is_script)
		end
	end
end

-- Modification of isArray in [[Module:table]].
-- This assumes all keys are either integers or non-numbers.
-- If there are fractional numbers, the results might be incorrect.
-- For instance, find_gap{"a", "b", [0.5] = true} evaluates to 3, but there
-- isn't a gap at 3 in the sense of there being an integer key greater than 3.
local function find_gap(t, can_contain_non_number_keys)
	local i = 0
	for k in pairs(t) do
		if not (can_contain_non_number_keys and type(k) ~= "number") then
			i = i + 1
			if t[i] == nil then
				return i
			end
		end
	end
end

local function check_true_or_string_or_nil(modname, code, data, field_name)
	local field = data[field_name]
	if not (field == nil or field == true or type(field) == "string") then
		discrepancy(modname,
			"%s (<code>%s</code>) has an <code>%s</code> value that is not <code>nil</code>, <code>true</code> or a string: <code>%s</code>",
			link(data), code, field_name,
			dump(data[field_name])
		)
	end
end

local function check_array(modname, code, canonical_name, data, array_name, subarray_name, can_contain_non_number_keys)
	local subtable = data
	if subarray_name then
		subtable = assert(data[subarray_name], subarray_name)
	end
	local array_type = type(subtable[array_name])
	if array_type == "table" then
		local gap = find_gap(subtable[array_name], can_contain_non_number_keys)
		if gap then
			discrepancy(modname, "The %s array in %sthe data table for %s (<code>%s</code>) has a gap at index %d.",
				array_name,
				subarray_name and "the " .. subarray_name .. " field in " or "",
				canonical_name,
				code, gap)
		else
			return true
		end
	else
		discrepancy(modname, "The %s field in %sthe data table for %s (<code>%s</code>) should be an array (table) but is %s.",
			array_name,
			subarray_name and "the " .. subarray_name .. " field in " or "",
			canonical_name,
			code,
			array_type == "nil" and "nil" or "a " .. array_type)
	end
end

local function check_no_alias_codes(modname, mod_data)
	local lookup, discrepancies = {}, {}
	for k, v in pairs(mod_data) do
		local check = lookup[v]
		if check then
			discrepancies[check] = discrepancies[check] or {"<code>" .. check .. "</code>"}
			insert(discrepancies[check], "<code>" .. k .. "</code>")
		else
			lookup[v] = k
		end
	end
	for _, v in pairs(discrepancies) do
		discrepancy(modname, "The codes " .. list_to_text(v, ", ", " and ") .. " are currently alias codes. Only one code should be used in the data.")
	end
end

local function check_wikidata_item(modname, code, data, key)
	local data_item = data[key]
	if data_item == nil then
		return
	elseif type(data_item) == "number" then
		if not require "Module:table".isPositiveInteger(data_item) then
			discrepancy(modname, "%g, the Wikidata item id for %s (<code>%s</code>), is not a positive integer or a string in the correct format.",
				data_item, data[1], code)
		end
	elseif type(data_item) == "string" then
		if not data_item:find "^Q%d+$" then
			discrepancy(modname, "%s, the Wikidata item id for %s (<code>%s</code>), is not a string in the correct format or a positive integer.",
				data_item, data[1], code)
		end
	end
end

local function check_other_names_or_aliases(modname, code, canonical_name, data, data_key, allow_nested)
	local array = data[data_key]
	if not array then
		return
	end
	check_array(modname, code, canonical_name, data, data_key, nil, true)

	local names = {}
	local function check_other_name(other_name)
		if other_name == canonical_name then
			discrepancy(modname,
				"%s, the canonical name for <code>%s</code>, is repeated in the table of <code>%s</code>.",
				canonical_name, code, data_key)
		end
		if names[other_name] then
			discrepancy(modname,
				"The name %s is found twice or more in the list of <code>%s</code> for %s (<code>%s</code>).",
				other_name, data_key, canonical_name, code)
		end
		names[other_name] = true
	end

	for _, other_name in ipairs(array) do
		if type(other_name) == "table" then
			if not allow_nested then
				discrepancy(modname,
					"A nested table is found in the list of <code>%s</code> for %s (<code>%s</code>), but isn't allowed.",
					data_key, canonical_name, code)
			else
				for _, on in ipairs(other_name) do
					check_other_name(on)
				end
			end
		else
			check_other_name(other_name)
		end
	end
end

local function check_other_names_aliases_varieties(modname, code, canonical_name, data)
	if data.otherNames then
		check_other_names_or_aliases(modname, code, canonical_name, data, "otherNames")
	end
	if data.aliases then
		check_other_names_or_aliases(modname, code, canonical_name, data, "aliases")
	end
	if data.varieties then
		check_other_names_or_aliases(modname, code, canonical_name, data, "varieties", true)
	end
end

local function validate_pattern(pattern, modname, code, data, standardChars)
	if type(pattern) ~= "string" then
		discrepancy(modname, "\"%s\", the %spattern for %s (<code>%s</code>), is not a string.",
			pattern, standardChars and "standard character " or "", code, data[1])
	end
	local ranges
	for lower, higher in ugmatch(pattern, "(.)%-%%?(.)") do
		if codepoint(lower) >= codepoint(higher) then
			ranges = ranges or Array()
			insert(ranges, { lower, higher })
		end
	end
	if ranges and ranges[1] then
		local plural = #ranges ~= 1 and "s" or ""
		discrepancy(modname, "%s (<code>%s</code>) specifies an invalid pattern " ..
			"for %scharacter detection: <code>\"%s\"</code>. The first codepoint%s " ..
			"in the range%s %s %s must be less than the second.",
			link(data), code, standardChars and "standard " or "", pattern, plural, plural,
			ranges
				:map(
					function(range)
						return range[1] .. "-" .. range[2] .. (" (U+%X, U+%X)")
							:format(codepoint(range[1]), codepoint(range[2]))
					end)
				:concat(", "),
			#ranges ~= 1 and "are" or "is")
	end
	if not pcall(umatch, "", "[" .. pattern .. "]") then
		discrepancy(modname, "%s (<code>%s</code>) specifies an invalid pattern for " ..
			(standardChars and "standard" or "") .. " character detection: <code>\"%s\"</code>",
			link(data), code, pattern)
	end
end

local remove_exceptions_addition = 0xF0000
local maximum_code_point = 0x10FFFF
local remove_exceptions_maximum_code_point = maximum_code_point - remove_exceptions_addition

local function check_entry_name_or_sortkey(modname, code, data, replacements_name)
	local canonical_name = data[1]
	
	local replacements = data[replacements_name]
	if type(replacements) == "string" then
		if not (replacements_name == "sort_key" or replacements_name == "entry_name") then
			discrepancy(modname, "The %s field in the data table for %s (<code>%s</code>) must be a table.",
				replacements_name, canonical_name, code)
		end
		return
	end
	
	if (replacements.from ~= nil) ~= (replacements.to ~= nil) then
		discrepancy(modname,
			"The <code>from</code> and <code>to</code> arrays in the <code>%s</code> table for %s (<code>%s</code>) are not both defined or both undefined.",
			replacements_name, canonical_name, code)
	elseif replacements.from then
		for _, key in ipairs { "from", "to" } do
			check_array(modname, code, canonical_name, data, key, replacements_name)
		end
	end
	
	if replacements.remove_diacritics and type(replacements.remove_diacritics) ~= "string" then
		discrepancy(modname,
			"The <code>remove_diacritics</code> field in the <code>%s</code> table for %s (<code>%s</code>) table must be a string.",
			replacements_name, canonical_name, code)
	end
	
	if replacements.remove_exceptions then
		if check_array(modname, code, canonical_name, data, "remove_exceptions", replacements_name) then
			for sequence_i, sequence in ipairs(replacements.remove_exceptions) do
				local code_point_i = 0
				for code_point in gcodepoint(sequence) do
					code_point_i = code_point_i + 1
					if code_point > remove_exceptions_maximum_code_point then
						discrepancy(modname,
							"Code point #%d (0x%04X) in field #%d of the <code>remove_exceptions</code> array for %s (<code>%s</code>) is over U+%04X.",
							code_point_i, code_point, sequence_i, canonical_name, code, remove_exceptions_maximum_code_point)
					end
					
				end
			end
		end
	end
	
	if replacements.from and replacements.to
			and m_table.length(replacements.to) > m_table.length(replacements.from) then
		discrepancy(modname,
			"The <code>from</code> array in the <code>%s</code> table for %s (<code>%s</code>) must be shorter or the same length as the <code>to</code> array.",
			replacements_name, canonical_name, code)
	end
end

do
	local function has_ancestor(lang, code)
		for _, anc in ipairs(lang:getAncestors()) do
			if code == anc:getCode() or has_ancestor(anc, code) then
				return true
			end
		end
	end
	
	local function get_default_ancestors(lang)
		if lang:hasType("etymology-only") then
			local parent = lang:getParent()
			if not has_ancestor(parent, lang:getCode()) then
				return parent:getAncestorCodes()
			end
		end
		local fam_code, def_anc = lang:getFamilyCode()
		while fam_code and fam_code ~= "qfa-not" do
			local fam = m_family_data[fam_code]
			def_anc = fam.protoLanguage or
				m_language_data[fam_code .. "-pro"] and fam_code .. "-pro" or
				m_etym_language_data[fam_code .. "-pro"] and fam_code .. "-pro"
			if def_anc and def_anc ~= lang:getCode() then
				return {def_anc}
			end
			fam_code = fam[3]
		end
	end
	
	local function iterate_ancestor(code, data, modname, anc_code, lang)
		local anc = get_lang(anc_code, nil, true)
		if not anc then
			discrepancy(modname,
				"%s (<code>%s</code>) lists the invalid language code <code>%s</code> as its ancestor.",
				link(data), code, anc_code)
			return
		end
		local anc_fam = anc:getFamily()
		if not anc_fam then
			discrepancy(modname,
				"%s has no family.",
				anc_code)
			return
		end
		local anc_fam_code = anc_fam:getCode()
		local def_ancs = get_default_ancestors(lang)
		if def_ancs then
			for _, def_anc in ipairs(def_ancs) do
				def_anc = get_lang(def_anc, nil, true)
				if def_anc and (
					anc_code == def_anc:getCode() or
					has_ancestor(def_anc, anc_code) or
					def_anc:hasParent(anc_code) and not has_ancestor(anc, def_anc:getCode())
				) then
					discrepancy(modname,
						"%s (<code>%s</code>) has the %s (<code>%s</code>) listed in its ancestor field, which is redundant, since it is determined to be ancestral automatically.",
						link(data), code,
						link(anc:getRawData()), anc_code)
				end
			end
		end
		if not lang:inFamily(anc_fam_code) then
			discrepancy(modname,
				"%s (<code>%s</code>) has %s (<code>%s</code>) set as an ancestor, but is not in the %s (<code>%s</code>).",
				link(data), code,
				link(anc:getRawData()), anc_code,
				link(anc_fam:getRawData()), anc_fam_code)
		end
		local fam, proto = lang
		repeat
			fam = fam:getFamily()
			proto = fam and fam:getProtoLanguage()
		until proto or not fam or fam:getCode() == "qfa-not"
		if proto and not (
			proto:getCode() == anc:getCode() or
			proto:hasAncestor(anc:getCode()) or
			anc:hasAncestor(proto:getCode())
		) then
			local fam = lang:getFamily()
			discrepancy(modname,
				"%s (<code>%s</code>) is in the %s (<code>%s</code>) and has %s (<code>%s</code>) set as an ancestor, but it is not possible to form an ancestral chain between them.",
				link(data), code,
				link(fam:getRawData()), fam:getCode(),
				link(anc:getRawData()), anc_code)
		end
	end
	
	function export.check_ancestors(code, data, modname)
		local ancestors = data.ancestors
		if not ancestors then
			return
		elseif type(ancestors) == "string" then
			ancestors = split(ancestors, "%s*,%s*", true)
		end
		local lang = get_lang(code, nil, true)
		for _, anc in ipairs(ancestors) do
			iterate_ancestor(code, data, modname, anc, lang)
		end
	end
end
	
local function check_code_to_name_and_name_to_code_maps(
		source_module_type,
		source_module_description,
		code_to_module_map, name_to_code_map,
		code_to_name_modname, code_to_name_module,
		name_to_code_modname, name_to_code_module)
	local aliases = require("Module:languages/data").aliases
	local function check_code_and_name(modname, code, canonical_name)
		-- Check the code is in code_to_module_map and that it didn't originate from the wrong data module.
		local check_mod = code_to_module_map[code] or code_to_module_map[aliases[code]]
		if not (check_mod and check_mod:match("^" .. source_module_type .. "/data")) then
			if not name_to_code_map[canonical_name] then
				discrepancy(modname,
					"The code <code>%s</code> and the canonical name %s should be removed; they are not found in %s.",
					code, canonical_name, source_module_description)
			else
				discrepancy(modname,
					"<code>%s</code>, the code for the canonical name %s, is wrong; it should be <code>%s</code>.",
					code, canonical_name, name_to_code_map[canonical_name])
			end
		elseif not name_to_code_map[canonical_name] then
			local data_table = require("Module:" .. code_to_module_map[code])[code]
			discrepancy(modname,
				"%s, the canonical name for the code <code>%s</code>, is wrong; it should be %s.",
				canonical_name, code, data_table[1])
		end
	end

	for code, canonical_name in pairs(code_to_name_module) do
		check_code_and_name(code_to_name_modname, code, canonical_name)
	end
	
	for canonical_name, code in pairs(name_to_code_module) do
		check_code_and_name(name_to_code_modname, code, canonical_name)
	end
end

local function check_extraneous_extra_data(
		data_modname, data_module, extra_data_modname, extra_data_module)
	for code, _ in pairs(extra_data_module) do
		if not data_module[code] then
			discrepancy(extra_data_modname,
				"Language code <code>%s</code> is not found in [[Module:%s]], and should be removed from [[Module:%s]].",
				code, data_modname, extra_data_modname
			)
		end
	end
end

-- Just trying to not have a module error when someone puts a script code
-- in the position of a language code.
local function show_family_code(code)
	if type(code) == "string" then
		return "<code>" .. code .. "</code>"
	else
		return require("Module:debug").highlight_dump(code)
	end
end

local function check_languages()
	local check_language_data_keys = check_data_keys{
		1, 2, 3, 4, -- canonical name, wikidata item, family, scripts
		"display_text", "generate_forms", "entry_name", "sort_key",
		"otherNames", "aliases", "varieties", "ietf_subtag",
		"type", "ancestors",
		"wikimedia_codes", "wikipedia_article", "standardChars",
		"translit", "override_translit", "link_tr",
		"dotted_dotless_i"
	}
	
	local function check_language(modname, code, data, mainData, extraData)
		local canonical_name, lang_type = data[1], data.type
		
		check_language_data_keys(modname, code, data)
		
		if all_codes[code] then
			discrepancy(modname, "Code <code>%s</code> is not unique; it is also defined in [[Module:%s]].", code, all_codes[code])
		else
			if not m_language_codes[code] then
				discrepancy("languages/code to canonical name", "The code <code>%s</code> (%s) is missing.", code, canonical_name)
			end
			all_codes[code] = modname
		end
		
		if code:sub(-4) == "-pro" then
			local fam_code = code:sub(1, -5)
			local fam = get_lang(fam_code, nil, true, true)
			if not fam then
				discrepancy(modname,
					"%s (<code>%s</code>) has a proto-language code associated with the invalid code <code>%s</code>.",
					link(data), code, fam_code)
			elseif not fam:hasType("family") then
				discrepancy(modname,
					"%s (<code>%s</code>) has a proto-language code associated with %s (<code>%s</code>), which is not a family.",
					link(data), code, fam:getCanonicalName(), fam_code)
			else
				local expected_name = "Proto-" .. fam:getCanonicalName()
				if canonical_name ~= expected_name then
					discrepancy(modname,
						"%s (<code>%s</code>) does not have the expected name \"%s\", even though it is the proto-language of the %s (<code>%s</code>).",
						link(data), code, expected_name, fam:getCategoryName(), fam_code)
				end
			end
		end
		
		if not canonical_name then
			discrepancy(modname, "Code <code>%s</code> has no canonical name specified.", code)
		elseif language_names[canonical_name] then
			discrepancy(modname,
				"%s (<code>%s</code>) has a canonical name that is not unique; it is also used by the code <code>%s</code>.",
				link(data), code, language_names[canonical_name])
		else
			if not m_language_canonical_names[canonical_name] then
				discrepancy("languages/canonical names", "The canonical name %s (<code>%s</code>) is missing.", canonical_name, code)
			end
			language_names[canonical_name] = code
		end
		
		check_wikidata_item(modname, code, data, 2)

		if extraData then
			check_other_names_aliases_varieties(modname, code, canonical_name, extraData)
		end
		
		if lang_type and not (lang_type == "regular" or lang_type == "reconstructed" or lang_type == "appendix-constructed") then
			discrepancy(modname, "%s (<code>%s</code>) is of an invalid type <code>%s</code>.", link(data), code, data.type)
		end
		
		if mainData.aliases then
			discrepancy(modname, "%s (<code>%s</code>) has the <code>aliases</code> key. This must be moved to [[Module:" .. modname .. "/extra]].", link(data), code)
		end
		
		if mainData.varieties then
			discrepancy(modname, "%s (<code>%s</code>) has the <code>varieties</code> key. This must be moved to [[Module:" .. modname .. "/extra]].", link(data), code)
		end
		
		if mainData.otherNames then
			discrepancy(modname, "%s (<code>%s</code>) has the <code>otherNames</code> key. This must be moved to [[Module:" .. modname .. "/extra]].", link(data), code)
		end
		
		if not extraData then
			discrepancy(modname .. "/extra", "%s (<code>%s</code>) has data in [[Module:" .. modname .. "]], but does not have corresponding data in [[Module:" .. modname .. "/extra]].", link(data), code)
		--elseif extraData.otherNames then
		--	discrepancy(modname .. "/extra", "%s (<code>%s</code>) has <code>otherNames</code> key, but these should be changed to either <code>aliases</code> or <code>varieties</code>.", link(data), code)
		end
		
		local sc = data[4]
		if sc then
			if type(sc) == "string" then
				sc = split(sc, "%s*,%s*", true)
			end
			if type(sc) == "table" then
				if not sc[1] then
					discrepancy(modname, "%s (<code>%s</code>) has no scripts listed.", link(data), code)
				else
					for _, sccode in ipairs(sc) do
						local cur_sc = m_script_data[sccode]
						if not (cur_sc or sccode == "All" or sccode == "Hants") then
							discrepancy(modname,
								"%s (<code>%s</code>) lists the invalid script code <code>%s</code>.",
								link(data), code, sccode)
						-- elseif not cur_sc.characters then
						-- 	discrepancy(modname,
						-- 		"%s (<code>%s</code>) lists a script without characters <code>%s</code> (%s).",
						-- 		link(data), code, sccode, cur_sc[1])
						end
			
						nonempty_scripts[sccode] = true
					end
				end
			else
				discrepancy(modname,
					"The %s field for %s (<code>%s</code>) must be a table or string.",
					4, link(data), code)
			end
		end
		
		if data.ancestors then
			export.check_ancestors(code, data, modname)
		end
		
		if data[3] then
			local family = data[3]
			if not m_family_data[family] then
				discrepancy(modname,
					"%s (<code>%s</code>) has the invalid family code %s.",
					link(data), code, show_family_code(family))
			end
			
			nonempty_families[family] = true
		end
		
		if data.sort_key then
			check_entry_name_or_sortkey(modname, code, data, "sort_key")
		end
		
		if data.entry_name then
			check_entry_name_or_sortkey(modname, code, data, "entry_name")
		end

		if data.display then
			check_entry_name_or_sortkey(modname, code, data, "display")
		end

		if data.standardChars then
			if type(data.standardChars) == "table" then
				local sccodes = {}
				for _, sccode in ipairs(sc) do
					sccodes[sccode] = true
				end
				for sccode in pairs(data.standardChars) do
					if not (sccodes[sccode] or sccode == 1) then
						discrepancy(modname, "The field %s in the standardChars table for %s (<code>%s</code>) does not match any script for that language.",
							sccode, link(data), code)
					end
				end
			elseif data.standardChars and type(data.standardChars) ~= "string" then
				discrepancy(modname, "The standardChars field in the data table for %s (<code>%s</code>) must be a string or table.",
					link(data), code)
			end
		end
		
		check_true_or_string_or_nil(modname, code, data, "override_translit")
		check_true_or_string_or_nil(modname, code, data, "link_tr")
		
		if data.override_translit and not data.translit then
			discrepancy(modname,
				"%s (<code>%s</code>) has <code>override_translit</code> set, but no transliteration module",
				link(data), code)
		end
	end
	
	local function check_module(modname, test)
		local mod_data = mw.loadData("Module:" .. modname)
		local extra_modname = modname .. "/extra"
		local extra_mod_data = mw.loadData("Module:" .. extra_modname)
		for code, data in pairs(mod_data) do
			test(modname, code, data)
			check_language(modname, code, data, mod_data[code], extra_mod_data[code])
		end
		check_no_alias_codes(modname, mod_data)
		check_no_alias_codes(extra_modname, extra_mod_data)
		check_extraneous_extra_data(modname, mod_data, extra_modname, extra_mod_data)
	end
	
	-- Check two-letter codes
	check_module(
		"languages/data/2",
		function(modname, code, data)
			if not code:find("^[a-z][a-z]$") then
				discrepancy(modname, "%s (<code>%s</code>) does not have a two-letter code.", link(data), code)
			end
		end
	)
	
	-- Check three-letter codes
	for i = 0x61, 0x7A do -- a to z
		local letter = string.char(i)
		check_module(
			"languages/data/3/" .. letter,
			function(modname, code, data)
				if not code:find("^" .. letter .. "[a-z][a-z]$") then
					discrepancy(modname,
						"%s (<code>%s</code>) does not have a three-letter code starting with \"<code>%s</code>\".",
						link(data), code, letter)
				end
			end
		)
	end
	
	-- Check exceptional codes
	check_module(
		"languages/data/exceptional",
		function(modname, code, data)
			if code:find("^[a-z][a-z][a-z]?$") then
				discrepancy(modname, "%s (<code>%s</code>) has a two- or three-letter code.", link(data), code)
			end
		end
	)
	
	-- These checks must be done while all_codes only contains language codes:
	-- that is, after language data modules have been processed, but before
	-- etymology languages, families, and scripts have.
	check_code_to_name_and_name_to_code_maps(
		"languages",
		"a submodule of [[Module:languages]]",
		all_codes, language_names,
		"languages/code to canonical name", m_language_codes,
		"languages/canonical names", m_language_canonical_names
	)
	
	-- Check [[Template:langname-lite]]
	local frame = mw.getCurrentFrame()
	local content = new_title("Template:langname-lite"):getContent()
	content = content:gsub("%<%!%-%-.-%-%-%>", "") -- remove comments
	local match = ugmatch(content, "\n\t*|#*([^\n]+)=([^\n]*)")
	while true do
		local code, name = match()
		if not code then return "OK" end
		if code:len() > 1 and code ~= "default" then
			for _, code in pairs(split(code, "|", true)) do
				local lang = get_lang(code, nil, true, true)
				if name:match("etymcode") then
					local nonEtym_name = frame:preprocess(name)
					local nonEtym_real_name = lang:getFullName()
					if nonEtym_name ~= nonEtym_real_name then
						discrepancy("Template:langname-lite", "Code: <code>" .. code .. "</code>. Saw name: " .. nonEtym_name .. ". Expected name: " .. nonEtym_real_name .. ".")
					end
					name = frame:preprocess(name:gsub("{{{allow etym|}}}", "1"))
				elseif name:match("familycode") then
					name = name:match("familycode|(.-)|")
				else
					name = name
				end
				if not lang then
					discrepancy("Template:langname-lite", "Code: <code>" .. code .. "</code>. Saw name: " .. name .. ". Language not present in data.")
				else
					local real_name = lang:getCanonicalName()
					if name ~= real_name then
						discrepancy("Template:langname-lite", "Code: <code>" .. code .. "</code>. Saw name: " .. name .. ". Expected name: " .. real_name .. ".")
					end
				end
			end
		end
	end
end

local function check_etym_languages()
	local modname = "etymology languages/data"
	
	local check_etymology_language_data_keys = check_data_keys{
		1, 2, 3, 4, 5, -- canonical name, wikidata item, family, scripts, parent
		"display_text", "generate_forms", "entry_name", "sort_key",
		"otherNames", "aliases", "varieties", "ietf_subtag",
		"type", "main_code", "ancestors",
		"wikimedia_codes", "wikipedia_article", "standardChars",
		"translit", "override_translit", "link_tr",
		"dotted_dotless_i"
	}
	
	for code, data in pairs(m_etym_language_data) do
		local canonical_name, parent =
			data[1], data[5]
		check_etymology_language_data_keys(modname, code, data)
		
		if all_codes[code] then
			discrepancy(modname, "Code <code>%s</code> is not unique; it is also defined in [[Module:%s]].", code, all_codes[code])
		else
			if not m_etym_language_codes[code] then
				discrepancy("etymology languages/code to canonical name", "The code <code>%s</code> (%s) is missing.", code, canonical_name)
			end
			all_codes[code] = modname
		end
		
		if not canonical_name then
			discrepancy(modname, "Code <code>%s</code> has no canonical name specified.", code)
		elseif language_names[canonical_name] then
			local m_canonical_lang = m_languages.getByCanonicalName(canonical_name, nil, true)
			if not m_canonical_lang then
				discrepancy(modname, "%s (<code>%s</code>) has a canonical name that cannot be looked up.",
					link(data), code)
			elseif data.main_code ~= m_canonical_lang:getCode() then
				discrepancy(modname,
					"%s (<code>%s</code>) has a canonical name that is not unique; it is also used by the code <code>%s</code>.",
					link(data), code, language_names[canonical_name])
			end
		else
			if not m_etym_language_canonical_names[canonical_name] then
				discrepancy("etymology languages/canonical names", "The canonical name %s (<code>%s</code>) is missing.", canonical_name, code)
			end
			etym_language_names[canonical_name] = code
		end
		
		check_other_names_aliases_varieties(modname, code, canonical_name, data)
		
		if parent then
			if type(parent) ~= "string" then
				discrepancy(modname,
					"Etymology-only %s (<code>%s</code>) has a parent language or family code that is %s rather than a string.",
					link(data), code, parent == nil and "nil" or "a " .. type(parent))
			elseif not (m_language_data[parent] or m_family_data[parent] or m_etym_language_data[parent]) then
				discrepancy(modname,
					"Etymology-only %s (<code>%s</code>) has invalid parent language or family code <code>%s</code>.",
					link(data), code, parent)
			end
			nonempty_families[parent] = true
		else
			discrepancy(modname,
				"Etymology-only %s (<code>%s</code>) has no parent language or family code.",
				link(data), code)
		end
		
		if data.ancestors then
			export.check_ancestors(code, data, modname)
		end
		
		if data[3] then
			local family = data[3]
			if not m_family_data[family] then
				discrepancy(modname,
					"%s (<code>%s</code>) has the invalid family code %s.",
					link(data), code, show_family_code(family))
			end
			nonempty_families[family] = true
		end
		
		check_wikidata_item(modname, code, data, 2)
	end

	local checked = {}
	for code, data in pairs(m_etym_language_data) do
		local stack = {}

		while data do
			if checked[data] then
				break	
			end
			if stack[data] then
				discrepancy(modname, "%s (<code>%s</code>) has a cyclic parental relationship to %s (<code>%s</code>)",
					link(data), code,
					link(m_etym_language_data[data[5]]), data.parent or data[5]
				)
				break
			end
			stack[data] = true
			code, data = data[5], data[5] and m_etym_language_data[data[5]]
		end
		
		for data in pairs(stack) do
			checked[data] = true	
		end
	end
	
	check_no_alias_codes(modname, m_etym_language_data)
	
	check_code_to_name_and_name_to_code_maps(
		"etymology languages",
		"[[Module:etymology languages/data]]",
		all_codes, etym_language_names,
		"etymology languages/code to canonical name", m_etym_language_codes,
		"etymology languages/canonical names", m_etym_language_canonical_names)
end

local function check_families()
	local modname = "families/data"
	
	local check_family_data_keys = check_data_keys{
		1, 2, 3, -- canonical name, wikidata item, (parent) family
		"type", "ietf_subtag",
		"protoLanguage", "otherNames", "aliases", "varieties",
	}
	
	for code, data in pairs(m_family_data) do
		check_family_data_keys(modname, code, data)
		
		local canonical_name, family, protolang = data[1], data[3], data.protoLanguage
		
		if all_codes[code] then
			discrepancy(modname, "Code <code>%s</code> is not unique; it is also defined in [[Module:%s]].", code, all_codes[code])
		else
			if not m_family_codes[code] then
				discrepancy("families/code to canonical name", "The code <code>%s</code> (%s) is missing.", code, canonical_name)
			end
			all_codes[code] = modname
		end
		
		if not canonical_name then
			discrepancy(modname, "Code <code>%s</code> has no canonical name specified.", code)
		elseif family_names[canonical_name] then
			discrepancy(modname,
				"%s (<code>%s</code>) has a canonical name that is not unique; it is also used by the code <code>%s</code>.",
				link(data), code, family_names[canonical_name])
		else
			if not m_family_canonical_names[canonical_name] then
				discrepancy("families/canonical names", "The canonical name %s (<code>%s</code>) is missing.", canonical_name, code)
			end
			family_names[canonical_name] = code
		end
		
		if data[2] and type(data[2]) ~= "number" then
			discrepancy(modname, "%s (<code>%s</code>) has a wikidata item value that is not a number or <code>nil</code>: %s", link(data), code, dump(data[2]))
		end
		
		check_other_names_aliases_varieties(modname, code, canonical_name, data)
		
		if family then
			if family == code and code ~= "qfa-not" then
				discrepancy(modname,
					"%s (<code>%s</code>) has itself as its family.",
					link(data), code)
			elseif not m_family_data[family] then
				discrepancy(modname,
					"%s (<code>%s</code>) has the invalid parent family code %s.",
					link(data), code, show_family_code(family))
			end
			
			nonempty_families[family] = true
		end
		
		if protolang then
			local protolang_obj = get_lang(protolang, nil, true)
			if not protolang_obj then
				discrepancy(modname,
					"%s (<code>%s</code>) has the invalid proto-language code <code>%s</code>.",
					canonical_name, code, protolang)
			elseif protolang == code .. "-pro" then
				discrepancy(modname,
					"%s (<code>%s</code>) has %s (<code>%s</code>) listed as its proto-language, which is redundant, since it is determined to be the proto-language automatically.",
					canonical_name, code,
					protolang_obj:getCanonicalName(), protolang)
			elseif protolang:sub(-4) == "-pro" then
				discrepancy(modname,
					"%s (<code>%s</code>) has %s (<code>%s</code>) listed as its proto-language, which is supposed to be the proto-language for the family <code>%s</code>.",
					canonical_name, code,
					protolang_obj:getCanonicalName(), protolang, protolang:sub(1, -5))
			end
		end
		
		check_wikidata_item(modname, code, data, 2)
	end
	
	for code, data in pairs(m_family_data) do
		if not (nonempty_families[code] or allowed_empty_families[code]) then
			discrepancy(modname, "%s (<code>%s</code>) has no child families or languages.", link(data), code)
		end
	end

	local checked = { ["qfa-not"] = true }
	for code, data in pairs(m_family_data) do
		local stack = {}

		while data do
			if checked[code] then
				break	
			end
			if stack[code] then
				discrepancy(modname, "%s (<code>%s</code>) has a cyclic parental relationship to %s (<code>%s</code>)",
					link(data), code,
					link(m_family_data[data[3]]), data[3]
				)
				break
			end
			stack[code] = true
			code, data = data[3], m_family_data[data[3]]
		end
		
		for code in pairs(stack) do
			checked[code] = true	
		end
	end
	
	check_no_alias_codes(modname, m_family_data)
	
	check_code_to_name_and_name_to_code_maps(
		"families",
		"[[Module:families/data]]",
		all_codes, family_names,
		"families/code to canonical name", m_family_codes,
		"families/canonical names", m_family_canonical_names)
end

local function check_scripts()
	local modname = "scripts/data"
	
	local check_script_data_keys = check_data_keys({
		1, 2, -- canonical name, writing systems
		"canonicalName", "otherNames", "aliases", "varieties", "parent", "ietf_subtag",
		"wikipedia_article", "ranges", "characters", "spaces", "capitalized", "translit", "direction",
		"character_category", "normalizationFixes"
	}, true)
	
	local m_script_codes = require("Module:scripts/code to canonical name")
	local m_script_canonical_names = require("Module:scripts/by name")
	
	-- Just to satisfy requirements of check_code_to_name_and_name_to_code_maps.
	local script_code_to_module_map = {}
	
	for code, data in pairs(m_script_data) do
		local canonical_name = data[1]
		if not m_script_codes[code] and #code == 4 then
			discrepancy("scripts/code to canonical name", "<code>%s</code> (%s) is missing", code, canonical_name)
		end
		
		check_script_data_keys(modname, code, data)
		
		if not canonical_name then
			discrepancy(modname, "Code <code>%s</code> has no canonical name specified.", code)
		elseif script_names[canonical_name] then
			--[=[
			discrepancy(modname,
				"%s (<code>%s</code>) has a canonical name that is not unique; it is also used by the code <code>%s</code>.",
				link_script(data.names[1]), code, script_names[data.names[1]])
			--]=]
		else
			if not m_script_canonical_names[canonical_name] and #code == 4 then
				discrepancy("scripts/by name", "%s (<code>%s</code>) is missing", canonical_name, code)
			end
			script_names[canonical_name] = code
		end
		
		check_other_names_aliases_varieties(modname, code, canonical_name, data)
		
		if not nonempty_scripts[code] then
			discrepancy(modname,
				"%s (<code>%s</code>) is not used by any language%s.",
				link_script(canonical_name), code, data.characters and ""
					or " and has no characters listed for auto-detection")
		--[[
		elseif not data.characters then
			discrepancy(modname, "%s (<code>%s</code>) has no characters listed for auto-detection.", link_script(canonical_name), code)
		--]]
		end

		if data.characters then
			validate_pattern(data.characters, modname, code, data, false)
		end
		
		script_code_to_module_map[code] = modname
	end
	
	check_no_alias_codes(modname, m_script_data)
	
	check_code_to_name_and_name_to_code_maps(
		"scripts",
		"a submodule of [[Module:scripts]]",
		script_code_to_module_map, script_names,
		"scripts/code to canonical name", m_script_codes,
		"scripts/by name", m_script_canonical_names)
end

-- FIXME: this is quite messy.
local function check_wikidata_languages()
	local data = mw.text.jsonDecode(new_title("Module:languages/data/wikidata.json"):getContent())
	
	local seen = {{}, {}, {}, [5] = {}}
	for _, item in ipairs(data) do
		local id = item.id
		for k, v in pairs(item) do
			if k ~= "id" then
				local _seen = seen[k]
				for i, code in ipairs(v) do
					local _code = code[1]
					local _type = type(_seen[_code])
					if _type == "table" then
						insert(_seen[_code], id)
					elseif _type == "string" then
						_seen[_code] = {_seen[_code], id}
					else
						_seen[_code] = id
					end
				end
			end
		end
	end
	
	for k, v in pairs(seen) do
		for code, ids in pairs(v) do
			if type(ids) == "table" then
				local t = {}
				for i, id in ipairs(ids) do
					t[i] = ("<code>[[d:%s|%s]]</code>"):format(id, id)
				end
				discrepancy("languages/data/wikidata.json", "<code>%s</code> is set as an ISO 639-%d code on multiple items: %s.",
					code, k, list_to_text(t))
				
			end
		end
	end
end

local function check_labels()
	local check_label_data_keys = check_data_keys{
		"display", "Wikipedia", "glossary",
		"plain_categories", "topical_categories", "pos_categories", "regional_categories", "sense_categories",
		"omit_preComma", "omit_postComma", "omit_preSpace",
		"deprecated", "track"
	}
	
	local function check_label(modname, code, data)
		local _type = type(data)
		if _type == "table" then
			check_label_data_keys(modname, code, data)
		elseif _type ~= "string" then
			discrepancy(modname,
				"The data for label <code>%s</code> is a %s; only tables and strings are allowed.",
				code, _type)
		end
	end
	
	for _, module in ipairs{"", "/regional", "/topical"} do
		local modname = "Module:labels/data" .. module
		module = require(modname)
		for label, data in pairs(module) do
			check_label(modname, label, data)
		end
	end
	
	for code in pairs(m_language_codes) do
		local modname = "Module:labels/data/lang/" .. code
		local ok, module = pcall(require, modname)
		if ok then
			for label, data in pairs(module) do
				check_label(modname, label, data)
			end
		end
	end
end

local function check_zh_trad_simp()
	local m_ts = require("Module:zh/data/ts")
	local m_st = require("Module:zh/data/st")
	local ruby = require("Module:ja-ruby").ruby_auto
	local lang = get_lang("zh")
	local Hant = m_scripts.getByCode("Hant")
	local Hans = m_scripts.getByCode("Hans")
	
	local data = {[0] = m_st, m_ts}
	local mod = {[0] = "st", "ts"}
	local var = {[0] = "Simp.", "Trad."}
	local sc = {[0] = Hans, Hant}
	
	local function find_stable_loop(chars, other, j)
		local display = ruby({["markup"] = "[" .. other .. "](" .. var[(j+1)%2] .. ")"})
		display = m_links.language_link{term = other, alt = display, lang = lang, sc = sc[(j+1)%2], tr = "-"}
		insert(chars, display)
		if data[(j+1)%2][other] == other then
			insert(chars, other)
			return chars, 1
		elseif not data[(j+1)%2][other] then
			insert(chars, "not found")
			return chars, 2
		elseif data[j%2][data[(j+1)%2][other]] ~= other then
			return find_stable_loop(chars, data[(j+1)%2][other], j + 1)
		else
			local display = ruby({["markup"] = "[" .. data[(j+1)%2][other] .. "](" .. var[j%2] .. ")"})
			display = m_links.language_link{term = data[(j+1)%2][other], alt = display, lang = lang, sc = sc[j%2], tr = "-"}
			insert(chars, display .. " (")
			display = ruby({["markup"] = "[" .. data[j%2][data[(j+1)%2][other]] .. "](" .. var[(j+1)%2] .. ")"})
			display = m_links.language_link{term = data[j%2][data[(j+1)%2][other]], alt = display, lang = lang, sc = sc[(j+1)%2], tr = "-"}
			insert(chars, display .. " etc.)")
			return chars, 3
		end
		
		return chars
	end
	
	for i = 0, 1, 1 do
		for char, other in pairs(data[i]) do
			if data[(i+1)%2][other] ~= char then
				local chars, issue = {}
				local display = ruby({["markup"] = "[" .. char .. "](" .. var[i] .. ")"})
				display = m_links.language_link{term = char, alt = display, lang = lang, sc = sc[i], tr = "-"}
				insert(chars, display)
				chars, issue = find_stable_loop(chars, other, i)
				if issue == 1 or issue == 2 then
					local sc_this, mod_this, j = {}
					if chars[#chars-1]:match(var[(i+1)%2]) then
						j = 1
					else
						j = 0
					end
					mod_this = mod[(i+j)%2]
					sc_this = {[0] = sc[(i+j)%2], sc[(i+j+1)%2]}
					for k, char in ipairs(chars) do
						chars[k] = m_script_utils.tag_text(char, lang, sc_this[k%2], "term")
					end
					if issue == 1 then
						discrepancy("zh/data/" .. mod_this, "character references itself: " .. concat(chars, " → "))
					elseif issue == 2 then
						discrepancy("zh/data/" .. mod_this, "missing character: " .. concat(chars, " → "))
					end
				elseif issue == 3 then
					for j, char in ipairs(chars) do
						chars[j] = m_script_utils.tag_text(char, lang, sc[(i+j)%2], "term")
					end
					discrepancy("zh/data/" .. mod[i], "possible mismatched character: " .. concat(chars, " → "))
				end
			end
		end
	end
end

local function check_serialization(modname)
	local serializers = {
		["Hani-sortkey/data/serialized"] = "Hani-sortkey/serializer",
	}
	
	if not serializers[modname] then
		return nil
	end
	
	local serializer = serializers[modname]
	local current_data = require("Module:" .. serializer).main(true)
	local stored_data = require("Module:" .. modname)
	if current_data ~= stored_data then
		discrepancy(modname, "<strong><u>Important!</u> Serialized data is out of sync. Use [[Module: ".. serializer .. "]] to update it. If you have made any changes to the underlying data, the serialized data <u>must</u> be updated before these changes will take effect.</strong>")
	end
end

-- Warning: cannot be called twice in the same module invocation because
-- some module-global variables are not reset between calls.
function export.do_checks(modules)
	messages = setmetatable({}, {
		__index = function (self, k)
			local val = Array()
			self[k] = val
			return val
		end
	})
	
	if modules["zh/data/ts"] or modules["zh/data/st"] then
		check_zh_trad_simp()
	end
	check_languages()
	check_etym_languages()

	-- families and scripts must be checked AFTER languages; languages checks fill out
	-- the nonempty_families and nonempty_scripts tables, used for testing if a family/script
	-- is ever used in the data
	check_families()
	check_scripts()
	
	check_wikidata_languages()
	
	if modules["labels/data"] then
		check_labels()
	end
	
	for module in pairs(modules) do
		check_serialization(module)
	end
	
	setmetatable(messages, nil)
	
	local function find_code(message)
		return string.match(message, "<code>([^<]+)</code>")
	end
	
	find_code = require("Module:fun").memoize(find_code)
	
	local function comp(message1, message2)
		local code1, code2 = find_code(message1), find_code(message2)
		if code1 and code2 then
			return code1 < code2
		else
			return message1 < message2
		end
	end
	
	for _, msglist in pairs(messages) do
		msglist:sort(comp)
	end
	
	local ret = messages
	messages = nil
	return ret
end

function export.format_message(modname, msglist)
	local header; if modname:match("^Module:") or modname:match("^Template:") then
		header = "===[[" .. modname .. "]]==="
	else
		header = "===[[Module:" .. modname .. "]]==="
	end
	return header
		.. msglist
			:map(
				function(msg)
					return "\n* " .. msg
				end)
			:concat()
end

function export.check_modules(args)
	
	local modules = {}
	for _, arg in ipairs(args) do
		modules[arg] = true
	end
	
	local ret = Array()
	local messages = export.do_checks(modules)
	
	for _, module in ipairs(args) do
		local msglist = messages[module]
		if msglist then
			ret:insert(export.format_message(module, msglist))
		end
	end
	return ret:concat("\n")
end

function export.check_modules_t(frame)
	local args = m_table.shallowcopy(frame.args)
	return export.check_modules(args)
end

function export.perform(frame)
	local messages = export.do_checks({})
	
	-- Format the messages
	local ret = Array()
	for modname, msglist in m_table.sortedPairs(messages) do
		ret:insert(export.format_message(modname, msglist))
	end
	
	-- Are there any messages?
	if i == 1 then
		return "<b class=\"success\">Glory to Arstotzka.</b>"
	else
		ret:insert(1, "<b class=\"warning\">Discrepancies detected:</b>")
		
		return ret:concat("\n")
	end
end

return export