มอดูล:Mymr-translit

The following documentation is located at มอดูล:Mymr-translit/documentation. ^[edit] Categories were auto-generated by Module:module categorization. ^[edit]

Useful links: subpage list • links • transclusions • testcases • sandbox

This module will transliterate text in the อักษรพม่า. It is used to transliterate บาลี and สันสกฤต. The module should preferably not be called directly from templates or other modules. To use it from a template, use {{xlit}}. Within a module, use Module:languages#Language:transliterate.

For testcases, see Module:Mymr-translit/testcases.

Functions

tr(text, lang, sc)

Transliterates a given piece of text written in the script specified by the code sc, and language specified by the code lang.

When the transliteration fails, returns nil.

---

-- แม่แบบนี้เป็นแม่แบบทดลอง

local export = {}
local gsub = mw.ustring.gsub
local u = mw.ustring.char
local letter_with_mark = "(.["..u(0x0300).."-"..u(0x036F).."]?)"

local tt = {
	-- consonants
	["က"] = "ก", ["ခ"] = "ข", ["ဂ"] = "ค", ["ဃ"] = "ฆ", ["င"] = "ง",
	["စ"] = "จ", ["ဆ"] = "ฉ", ["ဇ"] = "ช", ["ဈ"] = "ฌ", ["ဉ"] = "ญ", ["ည"] = "ญ",
	["ဋ"] = "ฏ", ["ဌ"] = "ฐ", ["ဍ"] = "ฑ", ["ဎ"] = "ฒ", ["ဏ"] = "ณ",
	["တ"] = "ต", ["ထ"] = "ถ", ["ဒ"] = "ท", ["ဓ"] = "ธ", ["န"] = "น",
	["ပ"] = "ป", ["ဖ"] = "ผ", ["ဗ"] = "พ", ["ဘ"] = "ภ", ["မ"] = "ม",
	["ယ"] = "ย", ["ရ"] = "ร", ["လ"] = "ล", ["ဝ"] = "ว",
	["သ"] = "ส", ["ဟ"] = "ห", ["ဠ"] = "ฬ", ["အ"] = "อ",
	["ဢ"] = "อ", ["ဿ"] = "สฺส", ["ၐ"] = "ศ", ["ၑ"] = "ษ",
	["ၚ"] = "ง", ["ၛ"] = "ฌ", ["ၜ"] = "บ", ["ၝ"] = "บ̱", ["ၡ"] = "ศ",
	["ၥ"] = "ถ", ["ၦ"] = "ปฺว", ["ၮ"] = "ณ", ["ၯ"] = "ยฺว", ["ၰ"] = "ฆฺว",
	["ၵ"] = "ก", ["ၶ"] = "ข", ["ၷ"] = "ค", ["ၸ"] = "จ", ["ၹ"] = "ซ",
	["ၺ"] = "ญ", ["ၻ"] = "ท", ["ၼ"] = "น", ["ၽ"] = "ผ",
	["ၾ"] = "ฟ", ["ၿ"] = "พ", ["ႀ"] = "ถ", ["ႁ"] = "ห",
	["ႎ"] = "ฟ",
	["ꩠ"] = "ฆ", ["ꩡ"] = "จ", ["ꩢ"] = "ฉ", ["ꩣ"] = "ช", ["ꩤ"] = "ฌ", ["ꩥ"] = "ญ",
	["ꩦ"] = "ฏ", ["ꩧ"] = "ฐ", ["ꩨ"] = "ฑ", ["ꩩ"] = "ฒ", ["ꩪ"] = "ธ", ["ꩫ"] = "น",
	["ꩬ"] = "ส", ["ꩭ"] = "ห", ["ꩮ"] = "ฬ", ["ꩯ"] = "ฟ",
	["ꩱ"] = "ฅ", ["ꩲ"] = "ซ", ["ꩳ"] = "ร", ["ꩴ"] = "�", ["ꩵ"] = "�", ["ꩶ"] = "�",
	["ꩺ"] = "ร",
	["ꩾ"] = "ฉ", ["ꩿ"] = "ศ",
	["ꧠ"] = "ฆ", ["ꧡ"] = "ฉ", ["ꧢ"] = "ฌ", ["ꧣ"] = "ณ", ["ꧤ"] = "ภ",
	["ꧧ"] = "ญ", ["ꧨ"] = "ฟ", ["ꧩ"] = "ค", ["ꧪ"] = "ฆ",
	["ꧫ"] = "ช", ["ꧬ"] = "ฌ", ["ꧭ"] = "ฑ", ["ꧮ"] = "ฒ", ["ꧯ"] = "ณ",
	["ꧺ"] = "ฬ", ["ꧻ"] = "ท", ["ꧼ"] = "ธ", ["ꧽ"] = "พ", ["ꧾ"] = "ภ",
	-- independent vowels
	["ဣ"] = "อิ", ["ဤ"] = "อี", ["ဥ"] = "อุ", ["ဦ"] = "อู",
	["ဧ"] = "เอ", ["ဨ"] = "เอ", ["ဩ"] = "ออ̂", ["ဪ"] = "เอาะ",
	["ၒ"] = "ฤ", ["ၓ"] = "ฤๅ", ["ၔ"] = "ฦ", ["ၕ"] = "ฦๅ",
	-- dependent vowels and diacritics (excluding front type)
	["ါ"] = "า", ["ာ"] = "า", ["ိ"] = "ิ", ["ီ"] = "ี", ["ု"] = "ุ", ["ူ"] = "ู",
	["ဳ"] = "ี", ["ံ"] = "ํ", ["့"] = "̥", ["း"] = ":", ["္"] = "ฺ", ["်"] = "์",
	["ျ"] = "ฺย", ["ြ"] = "ฺร", ["ွ"] = "ฺว", --["ှ"] = "ฺห",
	["ၖ"] = "ฺฤ", ["ၗ"] = "ฺฤๅ", ["ၘ"] = "ฺฦ", ["ၙ"] = "ฺฦๅ",
	["ၞ"] = "ฺน", ["ၟ"] = "ฺม", ["ၠ"] = "ฺล",
	["ၢ"] = "า", ["ၣ"] = "�", ["ၤ"] = "�",
	["ၧ"] = "�", ["ၨ"] = "ึ", ["ၩ"] = "¹", ["ၪ"] = "²", ["ၫ"] = "³", ["ၬ"] = "⁴", ["ၭ"] = "⁵",
	["ၱ"] = "ิ", ["ၳ"] = "ุ",
	["ႂ"] = "ฺว", ["ႃ"] = "า", ["ႆ"] = "ย",
	["ႇ"] = "²", ["ႈ"] = "³", ["ႉ"] = "⁵", ["ႊ"] = "⁶", ["ႋ"] = "²", ["ႌ"] = "³", ["ႍ"] = "̲",
	["ႏ"] = "⁵",
	["ႚ"] = "¹", ["ႛ"] = "³", ["ႜ"] = "ะ", ["ႝ"] = "า",
	["ꩻ"] = "¹", ["ꩼ"] = "²", ["ꩽ"] = "⁵",
	["ꧥ"] = "�",
	-- marks
	["၊"] = ",", ["။"] = ".",
	["၌"] = "@", ["၍"] = ";", ["၎"] = "ฯ", ["၏"] = ".",
	["႟"] = "!", ["ꩰ"] = "ๆ", ["꩷"] = "!", ["ꧦ"] = "ๆ",
	-- numerals
	["၀"] = "๐", ["၁"] = "๑", ["၂"] = "๒", ["၃"] = "๓", ["၄"] = "๔",
	["၅"] = "๕", ["၆"] = "๖", ["၇"] = "๗", ["၈"] = "๘", ["၉"] = "๙",
	["႐"] = "0", ["႑"] = "1", ["႒"] = "2", ["႓"] = "3", ["႔"] = "4",
	["႕"] = "5", ["႖"] = "6", ["႗"] = "7", ["႘"] = "8", ["႙"] = "9",
	["႞"] = "1",
	["꩸"] = "๑", ["꩹"] = "๒", 
	["꧰"] = "๐", ["꧱"] = "๑", ["꧲"] = "๒", ["꧳"] = "๓", ["꧴"] = "๔",
	["꧵"] = "๕", ["꧶"] = "๖", ["꧷"] = "๗", ["꧸"] = "๘", ["꧹"] = "๙",
	-- zero-width space (display it if it hides in a word)
	[u(0x200B)] = "‼",
}

local adjust1 = {
	-- dependent vowels (front type)
	["ေ"] = "เ%1", ["ဲ"] = "แ%1", ["ဴ"] = "โ%1", ["ဵ"] = "เ%1",
	["ၲ"] = "เ%1อ̂", ["ၴ"] = "เ%1", ["ႄ"] = "เ%1", ["ႅ"] = "เ%1",
	-- other
	["ှ"] = "หฺ%1",
}

function export.tr(text, lang, sc, debug_mode)

	if type(text) == "table" then -- called directly from a template
		text = text.args[1]
	end

	if lang == "my" then
		text = gsub(text, "ရ([ျြွ]?)ှ", "ၡ%1") -- หฺร -> ศ
	end

	text = gsub(text, "(့)([ါ-ှ])", "%2%1") -- swap tone-3 mark and vowel
	text = gsub(text, ".", tt)

	for k, v in pairs(adjust1) do
		text = gsub(text, letter_with_mark..k, v)
	end

	if lang == "my" then
		text = gsub(text, letter_with_mark.."ิุ", "โ%1") -- อิุ -> โอ
		text = gsub(text, "โ"..letter_with_mark.."([ก-รวศษสฬอ]์)", "ไ%1%2") -- โอx์ -> ไอx์ ยกเว้น ลหฮ

		text = gsub(text, "เ"..letter_with_mark.."า", "%1อ̂") -- เอา -> ออ̂
		text = gsub(text, "^"..letter_with_mark.."อ̂์", "เ%1าะ") -- ออ̂์ -> เอาะ
		text = gsub(text, "([^เ])"..letter_with_mark.."อ̂์", "%1เ%2าะ") -- ออ̂์ -> เอาะ
		text = gsub(text, "^"..letter_with_mark.."อ̂([ก-ฮ]์)", "เ%1า%2") -- ออ̂x์ -> เอาx์
		text = gsub(text, "([^เ])"..letter_with_mark.."อ̂([ก-ฮ]์)", "%1เ%2า%3") -- ออ̂x์ -> เอาx์
	end
	if lang == "pi" then
		text = gsub(text, "เ"..letter_with_mark.."า", "โ%1") -- เอา -> โอ --TODO: what about "au" in Sanskrit?
	end

	text = gsub(text, "([เแไโ])อฺ", "อฺ%1")
	text = gsub(text, "([¹²³⁴⁵⁶])์", "์%1")

	return text
 
end
 
return export