Module:fulf-translit: Difference between revisions

From Linguifex
Jump to navigation Jump to search
Melinoë (talk | contribs)
No edit summary
Melinoë (talk | contribs)
No edit summary
Line 106: Line 106:
return nil
return nil
elseif lang == "fulf" then
elseif lang == "fulf" then
return export.MH_tr(text)
return export.BH_tr(text)
elseif lang == "hbo" then --though useless
elseif lang == "hbo" then --though useless
return export.BH_tr(text)
return export.BH_tr(text)

Revision as of 06:25, 28 June 2026


This module will transliterate Fulfathic language text. 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:fulf-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.

local export = {}

--Contributors: Malku H₂n̥rés, Sartma, Erutuon, Metaknowledge

local m_str_utils = require("Module:string utilities")

local gcodepoint = m_str_utils.gcodepoint
local match = m_str_utils.match
local s = m_str_utils.gsub
local U = m_str_utils.char

local bidirectional_control_characters =
	U(0x061C) .. U(0x200E) .. U(0x200F) .. U(0x202A) .. "-" .. U(0x202E)
	.. U(0x2066) .. "-" .. U(0x2069)
local word_end = "%f[%s%z" .. bidirectional_control_characters .. "%-]"
local word_start = "%f[^%s%z" .. bidirectional_control_characters .. "%-]"
-- Bidirectional control characters should be avoided as much as possible,
-- but they are easily picked up when copying and pasting, so the module needs
-- to account for them.
-- This list is from [[w:Bidirectional control character]].

local V = "[aeiou‌āēīōū][̂̄̆]?́?" 
local C = "[ʔḇḡḏhwzḥṭylsʕqrśšṯ'ḵmnfṣbdgptkjc″vḫẓġTZCDK]"

local c = { --direct translit
	--full char ie. C
    ["א"] = "ʔ",
    ["ב"] = "ḇ",
    ["ג"] = "ḡ",
    ["ד"] = "ḏ",
    ["ה"] = "h",
    ["ו"] = "w",
    ["ז"] = "z",
    ["ח"] = "ḥ",
    ["ט"] = "ṭ",
    ["י"] = "y",
    ["ל"] = "l",
    ["ס"] = "s",
    ["ע"] = "ʕ",
    ["ק"] = "q",
    ["ר"] = "r",
    ["ש"] = "š",
    ["ת"] = "ṯ",
	--miscellaneous:
	["׳"] = "'", --geresh
    ["־"] = "-", --hyphen
    ["׃"] = " .", --dot
    ["ּ"] = "·", --dagesh
	["ֽ"] = "+", --meteg
	--niqqud ie. V
	["ַ"] = "a",
	["ָ"] = "ɔ",
	["ֶ"] = "ɛ",
	["ֵ"] = "e",
	["ִ"] = "i",
	["ֳ"] = "ɔ̆",
	["ֲ"] = "ă",
	["ֱ"] = "ɛ̆",
	["ְ"] = "ü",
	["ֹ"] = "o",
	["ֺ"] = "o",
	["ֻ"] = "u",
	["ׇ"] = "ɔ",
}

local b = { --BH

	{"(" .. V .. ")(·?)(+?)([ˊˇ]?'?)", "%5%2%1%4%3"},  --order: s(h)in dot, geresh, dagesh, vowel (niqqud), oleh, meteg
	--bgdkft: fricative + dagesh > stop
	{"ḇ·", "b"},
	{"ḡ·", "g"},
	{"ḏ·", "d"},
	{"ṯ·", "t"},
	{"ḵ·", "k"},
	{"f·", "p"},
	--vowel lengthenings
	{"ey", "ē%1"},
	{"ow", "ō%1"},
	{"aʔ", "ā%1"},
	{"iy", "ī%1"},
	{"uw", "ū%1"},
	{"ē(" .. V .. ")", "ey%1"},
	{"ō(" .. V .. ")", "ow%1"},
	{"ī(" .. V .. ")", "iy%1"},
	{"ū(" .. V .. ")", "uw%1"},
}


function export.BH(text)
	text = s(s(text, '.', c), "[֣֖֣֑֣֣֧֛֖֥֧֛֥֖֑֣֖֥֔֗֗֙֔]", "") --remove cantillation marks so that it works for quotes too
	for a = 1, #b do
		text = s(text, b[a][1], b[a][2])
	end
	return text
end

function export.BH_tr(text)
	return (s(export.BH(text), "+", "")) --metegim kept for MH
end

function export.tr(text, lang, sc)
	if not sc then
		sc = require("Module:languages").getByCode(lang, nil, true):findBestScript(text):getCode()
	end
	if sc ~= "Hebr" or not match(text, "[ְ-ֻ־ׇ״]") then
		return nil
	elseif lang == "fulf" then
		return export.BH_tr(text)
	elseif lang == "hbo" then --though useless
		return export.BH_tr(text)
	end
end

function export.tr_all(frame)
	return export.BH_tr(frame.args[1]) .. ", " .. export.MH_tr(frame.args[1])
end

return export