Module:gender and number

local export = {}
local data = mw.loadData("Module:gender and number/data")

--[==[ intro:
This module creates standardised displays for gender and number. It converts a gender specification into Wiki/HTML format.

A gender/number specification consists of one or more gender/number elements, separated by hyphens. Examples are:
{"n"} (neuter gender), {"f-p"} (feminine plural), {"m-an-p"} (masculine animate plural),
{"pf"} (perfective aspect). Each gender/number element has the following properties:
# A code, as used in the spec, e.g. {"f"} for feminine, {"p"} for plural.
# A type, e.g. `gender`, `number` or `animacy`. Each element in a given spec must be of a different type.
# A display form, which in turn consists of a display code and a tooltip gloss. The display code
  may not be the same as the spec code, e.g. the spec code {"an"} has display code {"anim"} and tooltip
  gloss ''animate''.
# A category into which lemmas of the right part of speech are placed if they have a gender/number
  spec containing the given element. For example, a noun with gender/number spec {"m-an-p"} is placed
  into the categories `<var>lang</var> masculine nouns`, `<var>lang</var> animate nouns` and `<var>lang</var> pluralia tantum`.
]==]

--[==[
Version of format_list that can be invoked from a template.
]==]
function export.show_list(frame)
	local params = {
		 = {list = true},
		 = {type = "language"},
	}
	local iargs = require("Module:parameters").process(frame.args, params)
	return export.format_list(iargs, iargs.lang)
end


--[==[
Older entry point; equivalent to format_genders() except that it formats the
categories and returns them appended to the formatted gender text rather than
returning the formatted text and categories separately.
]==]
function export.format_list(specs, lang, pos_for_cat, sort_key)
	require("Module:debug/track")("gender and number/old-format-list")
	local text, cats = export.format_genders(specs, lang, pos_for_cat)
	if #cats == 0 then
		return text
	end
	return text .. require("Module:utilities").format_categories(cats, lang, sort_key)
end


local function autoadd_abbr(display)
	if not display then
		error("Internal error: '.display' for gender/number code is missing")
	end
	if display:find("<abbr") then
		return display
	else
		return ('<abbr title="%s">%s</abbr>'):format(display, display)
	end
end
	
--[==[
Format one or more gender/number specifications. Each spec is either a string, e.g. {"f-p"}, or a table of the form
{ {spec = "SPEC", qualifiers = {"QUALIFIER", "QUALIFIER", ...}}} where `.spec` is a gender/number spec such as {"f-p"}
and `.qualifiers` is a list of qualifiers to display before the formatted gender/number spec. `.spec` must be present
but `.qualifiers` may be omitted.

The function returns two values:
# the formatted text;
# a list of the categories to add.

If `lang` (which should be a language object) and `pos_for_cat` (which should be a plural part of speech) are given,
gender categories such as `German masculine nouns` or `Russian imperfective verbs` are added to the categories, and
request categories such as `Requests for gender in <var>lang</var> entries` or
`Requests for animacy in <var>lang</var> entries` may also be added. Otherwise, if only `lang` is given, only request
categories may be returned. If both are omitted, the returned list is empty.
]==]
function export.format_genders(specs, lang, pos_for_cat)
	local formatted_specs = {}
	local categories = {}
	local seen_types = {}
	local category_text = ""
	local all_is_nounclass = nil
	-- Currently we only use the language for categories, so fetch the full parent. Change this if we
	-- use the language for any other purpose.
	lang = lang and lang:getFull() or nil

	local function do_gender_spec(spec, parts)
		local types = {}
		local codes = data.codes

		for key, code in ipairs(parts) do
			-- Is this code valid?
			if not codes then
				error('The tag "' .. code .. '" in the gender specification "' .. spec.spec .. '" is not valid. See ] for a list of valid tags.')
			end
			
			-- Check for multiple genders/numbers/animacies in a single spec.
			local typ = codes.type
			if typ ~= "other" and types then
				error('The gender specification "' .. spec.spec .. '" contains multiple tags of type "' .. typ .. '".')
			end
			types = true
				
			if key == 1 and spec.qualifiers and #spec.qualifiers > 0 then
				parts = require("Module:qualifier").format_qualifier(spec.qualifiers) .. " " ..
					autoadd_abbr(codes.display)
			else
				parts = autoadd_abbr(codes.display)
			end
		
			-- Generate categories if called for.
			if lang and pos_for_cat then
				local cat = codes.cat
				if cat then
					table.insert(categories, lang:getCanonicalName() .. " " .. cat)
				end
				if seen_types and seen_types ~= code then
					cat = data.multicode_cats
					if cat then
						table.insert(categories, lang:getCanonicalName() .. " " .. cat)
					end
				end
				
				seen_types = code
			end
			if lang and codes.req then
				local type_for_req = typ
				if code == "?" then
					-- Keep in mind `pos_for_cat` may be nil here.
					type_for_req = pos_for_cat == "verbs" and "aspect" or "gender"
				end
				table.insert(categories, "Requests for " .. type_for_req .. " in " ..
					lang:getCanonicalName() .. " entries")
			end
		end
		
		-- Add the processed codes together with non-breaking spaces
		if #parts == 1 then
			return parts
		end
		return table.concat(parts, "&nbsp;")
	end

	for _, spec in ipairs(specs) do
		if type(spec) ~= "table" then
			spec = {spec = spec}
		end
		local is_nounclass
		-- If the specification starts with cX, then it is a noun class specification.
		if spec.spec:find("^") or spec.spec:find("^c") then
			is_nounclass = true
			local code = spec.spec:gsub("^c", "")
			
			local text
			if code == "?" then
				text = '<abbr class="noun-class" title="noun class missing">?</abbr>'
			else
				text = '<abbr class="noun-class" title="noun class ' .. code .. '">' .. code .. "</abbr>"
				if lang and pos_for_cat then
					table.insert(categories, lang:getCanonicalName() .. " class " .. code .. " POS")
				end
			end
			local text_with_qual
			if spec.qualifiers and #spec.qualifiers > 0 then
				text_with_qual = require("Module:qualifier").format_qualifier(spec.qualifiers) .. " " .. text
			else
				text_with_qual = text
			end
			table.insert(formatted_specs, text_with_qual)
		else
			-- Split the parts and iterate over each part, converting it into its display form
			local parts = mw.text.split(spec.spec, "%-")
			local combined_codes = data.combinations

			if lang then
				-- Check if the specification is valid
				--elseif langinfo.genders then
				--	local valid_genders = {}
				--	for _, g in ipairs(langinfo.genders) do valid_genders = true end
				--	
				--	if not valid_genders then
				--		local valid_string = {}
				--		for i, g in ipairs(langinfo.genders) do valid_string = g end
				--		error('The gender specification "' .. spec.spec .. '" is not valid for ' .. langinfo.names .. ". Valid are: " .. table.concat(valid_string, ", "))
				--	end
				--end
			end

			local has_combined = false
			for _, code in ipairs(parts) do
				if combined_codes then
					has_combined = true
					break
				end
			end

			if not has_combined then
				if #formatted_specs > 0 then
					table.insert(formatted_specs, "or")
				end
				table.insert(formatted_specs, do_gender_spec(spec, parts))
			else
				-- This logic is to handle combined gender specs like 'mf' and 'mfbysense'.
				local all_parts = {{}}
				local extra_cats
				local extra_displays

				for i, code in ipairs(parts) do
					if combined_codes then
						local new_all_parts = {}
						for _, one_parts in ipairs(all_parts) do
							for _, one_code in ipairs(combined_codes.codes) do
								local new_combined_parts = mw.clone(one_parts)
								table.insert(new_combined_parts, one_code)
								table.insert(new_all_parts, new_combined_parts)
							end
						end
						all_parts = new_all_parts
						if lang and pos_for_cat then
							local extra_cat = combined_codes.cat
							if extra_cat then
								if not extra_cats then
									extra_cats = {}
								end
								table.insert(extra_cats, lang:getCanonicalName() .. " " .. extra_cat)
							end
						end
						local extra_display = combined_codes.display
						if extra_display then
							if not extra_displays then
								extra_displays = {}
							end
							table.insert(extra_displays, autoadd_abbr(extra_display))
						end
					else
						for _, one_parts in ipairs(all_parts) do
							table.insert(one_parts, code)
						end
					end
				end

				for _, parts in ipairs(all_parts) do
					if #formatted_specs > 0 then
						table.insert(formatted_specs, "or")
					end
					table.insert(formatted_specs, do_gender_spec(spec, parts))
				end

				if extra_cats then
					for _, cat in ipairs(extra_cats) do
						table.insert(categories, cat)
					end
				end

				if extra_displays then
					for _, display in ipairs(extra_displays) do
						table.insert(formatted_specs, display)
					end
				end
			end

			is_nounclass = false
		end

		-- Ensure that the specifications are either all noun classes, or none are.
		if all_is_nounclass == nil then
			all_is_nounclass = is_nounclass
		elseif all_is_nounclass ~= is_nounclass then
			error("Noun classes and genders cannot be mixed. Please use either one or the other.")
		end
	end

	if lang and pos_for_cat then
		for i, cat in ipairs(categories) do
			categories = cat:gsub("POS", pos_for_cat)
		end
	end

	if all_is_nounclass then
		-- Add the processed codes together with slashes
		return '<span class="gender">class ' .. table.concat(formatted_specs, "/") .. "</span>", categories
	else
		-- Add the processed codes together with spaces
		return '<span class="gender">' .. table.concat(formatted_specs, " ") .. "</span>", categories
	end
end

return export