Module:vi-sortkey

The following documentation is located at Module:vi-sortkey/documentation. ^[edit]

Useful links: subpage list • transclusions • testcases • sandbox

This module takes Vietnamese words and generates sortkeys.

Alphabetic order: a ă â b c d đ e ê g h i k l m n o ô ơ p q r s t u ư v x y.

Order of tonal diacritics: currently a, à, ả, ã, á, ạ; alternative, a, á, à, ả, ã, ạ.

See the discussion in the Beer Parlour.

Examples

• 八04口05囗08

共和國

• tuye₂n ngo₂n toan1 the₂4 gio₃i4 ve₂1 nha₂n quye₂n1 cua2 lie₂n ho₃p5 quo₂c4

Tuyên ngôn toàn thế giới về nhân quyền của Liên Hợp Quốc

• co₂ng ba₁ng1

công bằng

• d₁ai5

Đại

• ac4 si met4

Ác-si-mét

• ta₂m ly4

tâm lý

• nghề (nghe₂1)
• nghệ (nghe₂5)
• ngon (ngon)
• ngón (ngon4)
• ngọn (ngon5)
• ngoy (ngoy)
• ngôi (ngo₂i)
• ngôn (ngo₂n)
• ngôn (ngo₂n)

• a (a)
• à (a1)
• ả (a2)
• ã (a3)
• á (a4)
• ạ (a5)
• ac (ac)
• àc (ac1)
• ảc (ac2)
• ãc (ac3)
• ác (ac4)
• ạc (ac5)
• an (an)
• àn (an1)
• ản (an2)
• ãn (an3)
• án (an4)
• ạn (an5)
• ă (a₁)
• ằ (a₁1)
• ẳ (a₁2)
• ẵ (a₁3)
• ắ (a₁4)
• ặ (a₁5)
• ăc (a₁c)
• ằc (a₁c1)
• ẳc (a₁c2)
• ẵc (a₁c3)
• ắc (a₁c4)
• ặc (a₁c5)
• ăn (a₁n)
• ằn (a₁n1)
• ẳn (a₁n2)
• ẵn (a₁n3)
• ắn (a₁n4)
• ặn (a₁n5)
• â (a₂)
• ầ (a₂1)
• ẩ (a₂2)
• ẫ (a₂3)
• ấ (a₂4)
• ậ (a₂5)
• âc (a₂c)
• ầc (a₂c1)
• ẩc (a₂c2)
• ẫc (a₂c3)
• ấc (a₂c4)
• ậc (a₂c5)
• ân (a₂n)
• ần (a₂n1)
• ẩn (a₂n2)
• ẫn (a₂n3)
• ấn (a₂n4)
• ận (a₂n5)
• b (b)
• bc (bc)
• bn (bn)
• c (c)
• cc (cc)
• cn (cn)
• d (d)
• dc (dc)
• dn (dn)
• đ (d₁)
• đc (d₁c)
• đn (d₁n)
• e (e)
• è (e1)
• ẻ (e2)
• ẽ (e3)
• é (e4)
• ẹ (e5)
• ec (ec)
• èc (ec1)
• ẻc (ec2)
• ẽc (ec3)
• éc (ec4)
• ẹc (ec5)
• en (en)
• èn (en1)
• ẻn (en2)
• ẽn (en3)
• én (en4)
• ẹn (en5)
• ê (e₂)
• ề (e₂1)
• ể (e₂2)
• ễ (e₂3)
• ế (e₂4)
• ệ (e₂5)
• êc (e₂c)
• ềc (e₂c1)
• ểc (e₂c2)
• ễc (e₂c3)
• ếc (e₂c4)
• ệc (e₂c5)
• ên (e₂n)
• ền (e₂n1)
• ển (e₂n2)
• ễn (e₂n3)
• ến (e₂n4)
• ện (e₂n5)
• g (g)
• gc (gc)
• gn (gn)
• h (h)
• hc (hc)
• hn (hn)
• i (i)
• ì (i1)
• ỉ (i2)
• ĩ (i3)
• í (i4)
• ị (i5)
• ic (ic)
• ìc (ic1)
• ỉc (ic2)
• ĩc (ic3)
• íc (ic4)
• ịc (ic5)
• in (in)
• ìn (in1)
• ỉn (in2)
• ĩn (in3)
• ín (in4)
• ịn (in5)
• k (k)
• kc (kc)
• kn (kn)
• l (l)
• lc (lc)
• ln (ln)
• m (m)
• mc (mc)
• mn (mn)
• n (n)
• nc (nc)
• nn (nn)
• o (o)
• ò (o1)
• ỏ (o2)
• õ (o3)
• ó (o4)
• ọ (o5)
• oc (oc)
• òc (oc1)
• ỏc (oc2)
• õc (oc3)
• óc (oc4)
• ọc (oc5)
• on (on)
• òn (on1)
• ỏn (on2)
• õn (on3)
• ón (on4)
• ọn (on5)
• ô (o₂)
• ồ (o₂1)
• ổ (o₂2)
• ỗ (o₂3)
• ố (o₂4)
• ộ (o₂5)
• ôc (o₂c)
• ồc (o₂c1)
• ổc (o₂c2)
• ỗc (o₂c3)
• ốc (o₂c4)
• ộc (o₂c5)
• ôn (o₂n)
• ồn (o₂n1)
• ổn (o₂n2)
• ỗn (o₂n3)
• ốn (o₂n4)
• ộn (o₂n5)
• ơ (o₃)
• ờ (o₃1)
• ở (o₃2)
• ỡ (o₃3)
• ớ (o₃4)
• ợ (o₃5)
• ơc (o₃c)
• ờc (o₃c1)
• ởc (o₃c2)
• ỡc (o₃c3)
• ớc (o₃c4)
• ợc (o₃c5)
• ơn (o₃n)
• ờn (o₃n1)
• ởn (o₃n2)
• ỡn (o₃n3)
• ớn (o₃n4)
• ợn (o₃n5)
• p (p)
• pc (pc)
• pn (pn)
• q (q)
• qc (qc)
• qn (qn)
• r (r)
• rc (rc)
• rn (rn)
• s (s)
• sc (sc)
• sn (sn)
• t (t)
• tc (tc)
• tn (tn)
• u (u)
• ù (u1)
• ủ (u2)
• ũ (u3)
• ú (u4)
• ụ (u5)
• uc (uc)
• ùc (uc1)
• ủc (uc2)
• ũc (uc3)
• úc (uc4)
• ục (uc5)
• un (un)
• ùn (un1)
• ủn (un2)
• ũn (un3)
• ún (un4)
• ụn (un5)
• ư (u₃)
• ừ (u₃1)
• ử (u₃2)
• ữ (u₃3)
• ứ (u₃4)
• ự (u₃5)
• ưc (u₃c)
• ừc (u₃c1)
• ửc (u₃c2)
• ữc (u₃c3)
• ức (u₃c4)
• ực (u₃c5)
• ưn (u₃n)
• ừn (u₃n1)
• ửn (u₃n2)
• ữn (u₃n3)
• ứn (u₃n4)
• ựn (u₃n5)
• v (v)
• vc (vc)
• vn (vn)
• x (x)
• xc (xc)
• xn (xn)
• y (y)
• ỳ (y1)
• ỷ (y2)
• ỹ (y3)
• ý (y4)
• ỵ (y5)
• yc (yc)
• ỳc (yc1)
• ỷc (yc2)
• ỹc (yc3)
• ýc (yc4)
• ỵc (yc5)
• yn (yn)
• ỳn (yn1)
• ỷn (yn2)
• ỹn (yn3)
• ýn (yn4)
• ỵn (yn5)

---

local export = {}

local U = mw.ustring.char

local breve = U(0x306)
local circum = U(0x302)
local horn = U(0x31B)

local grave = U(0x300)
local hook = U(0x309)
local tilde = U(0x303)
local acute = U(0x301)
local dot = U(0x323)

--[[
local diacritics = breve .. circum .. horn .. grave .. hook .. tilde .. acute .. dot
local diacritic = "[" .. diacritics .. "]"
--]]

-- Determines sort order of diacritics. The full-size numbers are placed at the
-- end of the syllable, the subscript numbers immediately after the vowel.
local replacements = {
	--[[	Diacritics that form separate vowel letters. ]]
	[breve] = "₁",
	[circum] = "₂",
	[horn] = "₃",
	
	--[[	Tonal diacritics ]]
--[[ Order given by Stephen G. Brown
	[acute] = 1,
	[grave] = 2,
	[hook] = 3,
	[tilde] = 4,
	[dot] = 5,
]]
-- Order given by Fumiko Take
	[grave] = 1,
	[hook] = 2,
	[tilde] = 3,
	[acute] = 4,
	[dot] = 5,
	
	["đ"] = "d₁",
	["-"] = " ",
}
	
local vi = require("Module:languages").getByCode("vi")
local function tag(text)
	return require("Module:script utilities").tag_text(text, vi)
end

function export.makeSortKey(text, lang, sc)
	if lang and lang ~= "vi" then
		return text
	end
	
	if not sc then
		sc = text and require("Module:scripts").findBestScript(text, vi):getCode()
	end
	
	if sc then
		if sc == "Hani" then
			return require("Module:zh-sortkey").makeSortKey(text, lang, sc)
		elseif sc ~= "Latn" then
			return text
		end
	end
	
	if not text then
		return nil
	end
	
	local sortkey = text
	
	--[=[
		[[Module:languages]] currently converts text to lowercase
		before applying changes, then to uppercase before outputting
		the result.
	]=]
	if mw.title.getCurrentTitle().nsText == "Module" then
		sortkey = mw.ustring.lower(text)
	end
	
	sortkey = mw.ustring.toNFD(sortkey)
	
	sortkey = sortkey:gsub("[%z\1-\127\194-\244][\128-\191]*", replacements) -- pattern for UTF-8 character
	
	sortkey = mw.ustring.gsub(sortkey, "([0-4])([₀-₃])", "%2%1")
	
	-- move tone number to end of syllable
	sortkey = mw.ustring.gsub(sortkey, '([1-5])([^%s]+)', '%2%1')
	
	return sortkey
end

function export.showSortkey(frame)
	local output = {}
	
	for _, word in ipairs(frame.args) do
		local example = "\n* <code>" .. export.makeSortKey(word) .. "</code>\n: " .. tag(word)
		table.insert(output, example)
	end
	
	return table.concat(output)
end

function export.showSorting(frame)
	local terms = {}
	
	for _, term in ipairs(frame.args) do
		table.insert(terms, term)
	end
	
	local makeSortKey = require("Module:fun").memoize(export.makeSortKey)
	local function comp(term1, term2)
		return makeSortKey(term1) < makeSortKey(term2)
	end
	
	table.sort(terms, comp)
	
	for i, term in pairs(terms) do
		terms[i] = "\n* " .. tag(term) .. " (<code>" .. makeSortKey(term) .. "</code>)"
	end
	
	return table.concat(terms)
end

return export