Module:Thai-sortkey

---

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

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

This module will sort text in the Thai script. It is used to sort Eastern Bru, Western Bru, Bisu, Nyah Kur, Chong, Khün, Western Lawa, Eastern Lawa, Kedah Malay, Pattani Malay, Northern Thai, Nyaw, Sanskrit, Saek, Southern Thai, Thai, Thavung, Isan, Gong, Urak Lawoi', and Yong. The module should preferably not be called directly from templates or other modules. To use it from a template, use {{sortkey}}. Within a module, use Module:languages#Language:makeSortKey.

For testcases, see Module:Thai-sortkey/testcases.

Functions

makeSortKey(text, lang, sc)

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

When the sort fails, returns nil.

local export = {}

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

local gmatch = m_str_utils.gmatch
local gsub = m_str_utils.gsub
local u = m_str_utils.char

local minorMarkSet = "([" .. u(0xE47) .. "-" .. u(0xE4E) .. u(0x302) .. u(0x304) .. u(0x331) .. "])"

local minorMarks = {
	[u(0xE47)] = "0", [u(0xE48)] = "1", [u(0xE49)] = "2", [u(0xE4A)] = "3", [u(0xE4B)] = "4",
	[u(0xE4C)] = "5", [u(0xE4D)] = "6", [u(0xE4E)] = "7", [u(0x302)] = "8", [u(0x304)] = "9", [u(0x331)] = "A"
}

function export.makeSortKey(text, lang, sc)
	local minorKey = ""
	for mark in gmatch(text, minorMarkSet) do
		minorKey = minorKey .. minorMarks[mark]
	end
	text = gsub(text, minorMarkSet, "")
	
	text = gsub(text, "[%pๆ]", "")
	text = gsub(text, "([เแโใไ])(ʼ?[ก-ฮ])", "%2%1")
	
	return text .. minorKey
end

-- compare between Thai texts
function export.string_compare(item1, item2)
	return export.makeSortKey(item1) < export.makeSortKey(item2)
end

return export