มอดูล:category tree/poscatboiler/data/ศัพท์แบ่งตามรากศัพท์

จาก วิกิพจนานุกรม พจนานุกรมเสรี
local str = require("Module:string")

local labels = {}
local raw_categories = {}
local handlers = {}
local raw_handlers = {}



-----------------------------------------------------------------------------
--                                                                         --
--                                  LABELS                                 --
--                                                                         --
-----------------------------------------------------------------------------


labels["ศัพท์แบ่งตามรากศัพท์"] = {
	description = "{{{langname}}} terms categorized by their etymologies.",
	umbrella_parents = "มูลฐาน",
	parents = {{name = "{{{langcat}}}", raw = true}},
}
labels["terms by etymology"] = labels["ศัพท์แบ่งตามรากศัพท์"]

labels["AABB-type reduplications"] = {
	description = "{{{langname}}} terms that underwent [[reduplication]] in an AABB pattern.",
	breadcrumb = "AABB-type",
	parents = {"คำซ้ำ"},
}

labels["apophonic reduplications"] = {
	description = "{{{langname}}} terms that underwent [[reduplication]] with only a change in a vowel sound.",
	breadcrumb = "apophonic",
	parents = {"คำซ้ำ"},
}

labels["การผันรูปย้อนกลับ"] = {
	description = "{{{langname}}} terms formed by reversing a supposed regular formation, removing part of an older term.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}
labels["back-formations"] = labels["การผันรูปย้อนกลับ"]

labels["คำหลอม"] = {
	description = "{{{langname}}} terms formed by combinations of other words.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}
labels["blends"] = labels["คำหลอม"]

labels["ศัพท์ที่ยืมมา"] = {
	description = "{{{langname}}} terms that are loanwords, i.e. words that were directly incorporated from another language.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}
labels["borrowed terms"] = labels["ศัพท์ที่ยืมมา"]

labels["catachreses"] = {
	description = "{{{langname}}} terms derived from misuses or misapplications of other terms.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["ศัพท์ที่บัญญัติ"] = {
	description = "{{{langname}}} terms coined by an identifiable person, organization or other such entity.",
	parents = {"terms attributed to a specific source"},
	umbrella_parents = {name = "terms attributed to a specific source", is_label = true, sort = " "},
}
labels["coinages"] = labels["ศัพท์ที่บัญญัติ"]

labels["coordinated pairs"] = {
	description = "Terms in {{{langname}}} consisting of a pair of terms joined by a [[coordinating conjunction]].",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["coordinated triples"] = {
	description = "Terms in {{{langname}}} consisting of three terms joined by one or more [[coordinating conjunction]]s.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["coordinated quadruples"] = {
	description = "Terms in {{{langname}}} consisting of four terms joined by one or more [[coordinating conjunction]]s.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["coordinated quintuples"] = {
	description = "Terms in {{{langname}}} consisting of five terms joined by one or more [[coordinating conjunction]]s.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["denominals"] = {
	description = "{{{langname}}} terms derived from a noun.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["deverbals"] = {
	description = "{{{langname}}} terms derived from a verb.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["ศัพท์ที่ร่วมราก"] = {
	description = "{{{langname}}} terms that trace their etymology from ultimately the same source as other terms in the same language, but by different routes, and often with subtly or substantially different meanings.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}
labels["doublets"] = labels["ศัพท์ที่ร่วมราก"]

labels["elongated forms"] = {
	description = "{{{langname}}} terms where one or more letters or sounds is repeated for emphasis or effect.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["ศัพท์ที่รับมาจากชื่อบุคคล"] = {
	description = "{{{langname}}} terms derived from names of real or fictitious people.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}
labels["eponyms"] = labels["ศัพท์ที่รับมาจากชื่อบุคคล"]

labels["ศัพท์ที่รับมาจากเครื่องหมายการค้า"] = {
	description = "{{{langname}}} terms that originate from [[trademark]]s, [[brand]]s and company names which have become [[genericized]]; that is, fallen into common usage in the target market's [[vernacular]], even when referring to other competing brands.",
	parents = {"ศัพท์แบ่งตามรากศัพท์", "เครื่องหมายการค้า"},
}
labels["genericized trademarks"] = labels["ศัพท์ที่รับมาจากเครื่องหมายการค้า"]

labels["ghost words"] = {
	description = "{{{langname}}} terms that were originally erroneous or fictitious, published in a reference work as if they were genuine as a result of typographical error, misreading, misinterpretation or another process.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["haplological words"] = {
	description = "{{{langname}}} words that underwent [[haplology]]: thus, their origin involved a loss or omission of a repeated sequence of sounds.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["homophonic translations"] = {
	description = "{{{langname}}} terms that were borrowed by matching the etymon phonetically, without regard for the sense; compare [[phono-semantic matching]] and [[Hobson-Jobson]].",
	parents = {"ศัพท์แบ่งตามรากศัพท์"}
}

labels["hybridisms"] = {
	description = "{{{langname}}} terms formed by elements of different linguistic origins.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["ศัพท์ที่สืบทอด"] = {
	description = "{{{langname}}} terms that were inherited from an earlier stage of the language.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}
labels["inherited terms"] = labels["ศัพท์ที่สืบทอด"]

labels["internationalisms"] = {
	description = "{{{langname}}} loanwords which also exist in many other languages with the same or similar etymology.",
	additional = "Terms should be here preferably only if the immediate source language is not known for certain. Entries are added into this category by [[Template:internationalism]]; see it for more information.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["legal doublets"] = {
	description = "{{{langname}}} legal [[doublet]]s – a legal doublet is a standardized phrase commonly use in legal documents, proceedings etc. which includes two words that are near synonyms.",
	parents = {"coordinated pairs"},
}

labels["legal triplets"] = {
	description = "{{{langname}}} legal [[triplet]]s – a legal triplet is a standardized phrase commonly use in legal documents, proceedings etc which includes three words that are near synonyms.",
	parents = {"coordinated triples"},
}

labels["merisms"] = {
	description = "{{{langname}}} [[merism]]s – terms that are [[coordinate]]s that, combined, are a synonym for a totality.",
	parents = {"coordinated pairs"},
}

labels["metonyms"] = {
	description = "{{{langname}}} terms whose origin involves calling a thing or concept not by its own name, but by the name of something intimately associated with that thing or concept.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["neologisms"] = {
	description = "{{{langname}}} terms that have been only recently acknowledged.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["nonce terms"] = {
	description = "{{{langname}}} terms that have been invented for a single occasion.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["numeronyms"] = {
	description = "{{{langname}}} terms that contain numerals.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["ศัพท์ที่เลียนเสียงธรรมชาติ"] = {
	description = "{{{langname}}} terms that were coined to sound like what they represent.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}
labels["onomatopoeias"] = labels["ศัพท์ที่เลียนเสียงธรรมชาติ"]

labels["piecewise doublets"] = {
	description = "{{{langname}}} terms that are [[Appendix:Glossary#piecewise doublet|piecewise doublets]].",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

--[=[ thwikt don't use specific terms below
for _, ism_and_langname in ipairs({
	{"anglicisms", "English"},
	{"Arabisms", "Arabic"},
	{"Gallicisms", "French"},
	{"Germanisms", "German"},
	{"Hispanisms", "Spanish"},
	{"Italianisms", "Italian"},
	{"Latinisms", "Latin"},
	{"Japonisms", "Japanese"},
}) do
	local ism, langname = unpack(ism_and_langname)
	labels["pseudo-" .. ism] = {
		description = "{{{langname}}} terms that appear to be " .. langname .. ", but are not used or have an unrelated meaning in " .. langname .. " itself.",
		parents = {"pseudo-loans"},
		umbrella_parents = {name = "pseudo-loans", is_label = true, sort = " "},
	}
end
--]=]

labels["rebracketings"] = {
	description = "{{{langname}}} terms that have interacted with another word in such a way that the boundary between the words has been modified.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"}
}

labels["ศัพท์ที่สืบสร้าง"] = {
	description = "{{{langname}}} terms that are not directly attested, but have been reconstructed through other evidence.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"}
}
labels["reconstructed terms"] = labels["ศัพท์ที่สืบสร้าง"]

labels["reduplicated coordinated pairs"] = {
	description = "{{{langname}}} reduplicated coordinated pairs.",
	breadcrumb = "reduplicated",
	parents = {"coordinated pairs", "คำซ้ำ"},
}

labels["reduplicated coordinated triples"] = {
	description = "{{{langname}}} reduplicated coordinated triples.",
	breadcrumb = "reduplicated",
	parents = {"coordinated triples", "คำซ้ำ"},
}

labels["reduplicated coordinated quadruples"] = {
	description = "{{{langname}}} reduplicated coordinated quadruples.",
	breadcrumb = "reduplicated",
	parents = {"coordinated quadruples", "คำซ้ำ"},
}

labels["reduplicated coordinated quintuples"] = {
	description = "{{{langname}}} reduplicated coordinated quintuples.",
	breadcrumb = "reduplicated",
	parents = {"coordinated quintuples", "คำซ้ำ"},
}

labels["คำซ้ำ"] = {
	description = "{{{langname}}} terms that underwent [[reduplication]], so their origin involved a repetition of roots or stems.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}
labels["reduplications"] = labels["คำซ้ำ"]

labels["retronyms"] = {
	description = "{{{langname}}} terms that serve as new unique names for older objects or concepts whose previous names became ambiguous.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["ราก"] = {
	description = "Basic morphemes from which {{{langname}}} words are formed.",
	parents = {"หน่วยคำ"},
}
labels["roots"] = labels["ราก"]

labels["roots by shape"] = {
	description = "{{{langname}}} roots categorized by their shape.",
	breadcrumb = "by shape",
	parents = {{name = "ราก", sort = "shape"}},
}

labels["Sanskritic formations"] = {
	description = "{{{langname}}} terms coined from [[tatsama]] [[word]]s and/or [[affix]]es.",
	parents = {"ศัพท์แบ่งตามรากศัพท์", "ศัพท์ที่รับมาจากภาษาสันสกฤต"},
}

labels["sound-symbolic terms"] = {
	description = "{{{langname}}} terms that use {{w|sound symbolism}} to express ideas but which are not necessarily strictly speaking [[onomatopoeic]].",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["spelled-out initialisms"] = {
	description = "{{{langname}}} initialisms in which the letter names are spelled out.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["spelling pronunciations"] = {
	description = "{{{langname}}} terms whose pronunciation was historically or presently affected by their spelling.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["คำผวน"] = {
	description = "{{{langname}}} terms in which the initial sounds of component parts have been exchanged, as in \"crook and nanny\" for \"nook and cranny\".",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}
labels["spoonerisms"] = labels["คำผวน"]

labels["taxonomic eponyms"] = {
	description = "{{{langname}}} terms derived from names of real or fictitious people, used for [[taxonomy]].",
	parents = {"ศัพท์ที่รับมาจากชื่อบุคคล"},
}

labels["terms attributed to a specific source"] = {
	description = "{{{langname}}} terms coined by an identifiable person or deriving from a known work.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["terms containing fossilized case endings"] = {
	description = "{{{langname}}} terms which preserve case morphology which is no longer analyzable within the contemporary grammatical system or which has been entirely lost from the language.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["terms derived from area codes"] = {
	description = "{{{langname}}} terms derived from [[area code]]s.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["ศัพท์ที่รับมาจากรูปร่างตัวอักษร"] = {
	description = "{{{langname}}} terms derived from the shape of letters. This can include terms derived from the shape of any letter in any alphabet.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}
labels["terms derived from the shape of letters"] = labels["ศัพท์ที่รับมาจากรูปร่างตัวอักษร"]

labels["terms by root"] = {
	description = "{{{langname}}} terms categorized by the root they originate from.",
	parents = {"ศัพท์แบ่งตามรากศัพท์", {name = "ราก", sort = " "}},
}

labels["ศัพท์ที่รับมาจากบันเทิงคดี"] = {
	description = "{{{langname}}} terms that originate from works of [[fiction]].",
	breadcrumb = "บันเทิงคดี",
	parents = {{name = "terms attributed to a specific source", sort = "บันเทิงคดี"}},
}
labels["terms derived from fiction"] = labels["ศัพท์ที่รับมาจากบันเทิงคดี"]

for _, data in ipairs {
	{source="Dickensian works", desc="the works of [[w:Charles Dickens|Charles Dickens]]", topic_parent="Charles Dickens"},
	{source="ดีซีคอมิกส์", desc="[[w:ดีซีคอมิกส์|ดีซีคอมิกส์]]"},
	{source="โดราเอมอน", desc="[[w:Fujiko F. Fujio|Fujiko F. Fujio]]'s ''[[w:โดราเอมอน|โดราเอมอน]]''", displaytitle="''โดราเอมอน''"},
	{source="ดรากอนบอล", desc="[[w:Akira Toriyama|Akira Toriyama]]'s ''[[w:ดรากอนบอล|ดรากอนบอล]]''", displaytitle="''ดรากอนบอล''"},
	{source="ดักเบิร์กและเมาส์ตัน", desc="[[w:The Walt Disney Company|Disney]]'s [[w:Duck universe|Duckburg]] and [[w:Mickey Mouse universe|Mouseton]] universe",
		topic_parent="ดิสนีย์"},
	{source="แฮร์รี่ พอตเตอร์", desc="the ''[[w:แฮร์รี่ พอตเตอร์|แฮร์รี่ พอตเตอร์]]'' series", displaytitle="''แฮร์รี่ พอตเตอร์''",
		topic_parent="แฮร์รี่ พอตเตอร์"},
	{source="Looney Tunes and Merrie Melodies", desc="''{{w|Looney Tunes}}'' and/or ''{{w|Merrie Melodies}}'', by {{w|Warner Bros. Animation}}", displaytitle = "''Looney Tunes'' and ''Merrie Melodies''"},
	{source="หนึ่งเก้าแปดสี่", desc="[[w:George Orwell|George Orwell]]'s ''[[w:Nineteen Eighty-Four|Nineteen Eighty-Four]]''",
		displaytitle="''หนึ่งเก้าแปดสี่''"},
	{source="สตาร์ เทรค", desc="''[[w:สตาร์ เทรค|สตาร์ เทรค]]''", displaytitle="''สตาร์ เทรค''", topic_parent="สตาร์ เทรค"},
	{source="สตาร์ วอร์ส", desc="''[[w:สตาร์ วอร์ส|สตาร์ วอร์ส]]''", displaytitle="''สตาร์ วอร์ส''", topic_parent="สตาร์ วอร์ส"},
	{source="เดอะซิมป์สันส์", desc="''[[w:เดอะซิมป์สันส์|เดอะซิมป์สันส์]]''", displaytitle="''เดอะซิมป์สันส์''", topic_parent="เดอะซิมป์สันส์", sort="ซิมป์สันส์"},
	{source="ปกรณัมของโทลคีน", desc="the [[legendarium]] of [[w:เจ. อาร์. อาร์. โทลคีน|เจ. อาร์. อาร์. โทลคีน]]", topic_parent="เจ. อาร์. อาร์. โทลคีน"},
} do
	local parents = {{name = "ศัพท์ที่รับมาจากบันเทิงคดี", sort = data.sort or data.source}}
	local umbrella_parents = {"หมวดหมู่ย่อยของศัพท์แบ่งตามรากศัพท์แบ่งตามภาษา"}
	if data.topic_parent then
		table.insert(parents, {module = "topic cat", args = {label = data.topic_parent, code = "{{{langcode}}}"}})
		table.insert(umbrella_parents, {module = "topic cat", args = {label = data.topic_parent}})
	end
	labels["ศัพท์ที่รับมาจาก" .. data.source] = {
		description = "{{{langname}}} terms that originate from " .. data.desc .. ".",
		breadcrumb = data.displaytitle or data.source,
		parents = parents,
		umbrella = {
			parents = umbrella_parents,
			displaytitle = data.displaytitle and "ศัพท์ที่รับมาจาก" .. data.displaytitle .. "แบ่งตามภาษา" or nil,
			breadcrumb = data.displaytitle and "ศัพท์ที่รับมาจาก" .. data.displaytitle,
		},
		displaytitle = data.displaytitle and "ศัพท์{{{langcat}}}ที่รับมาจาก" .. data.displaytitle or nil,
	}
end

labels["ศัพท์ที่รับมาจากประมวลเรื่องปรัมปรากรีก"] = {
	description = "{{{langname}}} terms derived from Greek mythology which have acquired an idiomatic meaning.",
	breadcrumb = "ประมวลเรื่องปรัมปรากรีก",
	parents = {{name = "terms attributed to a specific source", sort = "ประมวลเรื่องปรัมปรากรีก"}},
}
labels["terms derived from Greek mythology"] = labels["ศัพท์ที่รับมาจากประมวลเรื่องปรัมปรากรีก"]

labels["ศัพท์ที่รับมาจากอาชีพ"] = {
	description = "{{{langname}}} terms derived from names of occupations.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}
labels["terms derived from occupations"] = labels["ศัพท์ที่รับมาจากอาชีพ"]

labels["ศัพท์ที่รับมาจากภาษาอื่น"] = {
	description = "{{{langname}}} terms that originate from other languages.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}
labels["terms derived from other languages"] = labels["ศัพท์ที่รับมาจากภาษาอื่น"]

labels["ศัพท์ที่รับมาจากไบเบิล"] = {
	description = "{{{langname}}} terms that originate from the [[Bible]].",
	breadcrumb = {name = "ไบเบิล", nocap = true},
	parents = {{name = "terms attributed to a specific source", sort = "ไบเบิล"}},
}
labels["terms derived from the Bible"] = labels["ศัพท์ที่รับมาจากไบเบิล"]

labels["ศัพท์ที่รับมาจากนิทานอีสป"] = {
	description = "{{{langname}}} terms that originate from [[Aesop]]'s Fables.",
	breadcrumb = "นิทานอีสป",
	parents = {{name = "terms attributed to a specific source", sort = "นิทานอีสป"}},
}
labels["terms derived from Aesop's Fables"] = labels["ศัพท์ที่รับมาจากนิทานอีสป"]

labels["terms derived from toponyms"] = {
	description = "{{{langname}}} terms derived from names of real or fictitious places.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["terms making reference to character shapes"] = {
	description = "{{{langname}}} terms making reference to character shapes.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["ศัพท์ที่รับมาจากกีฬา"] = {
	description = "{{{langname}}} terms that originate from sport.",
	breadcrumb = "กีฬา",
	parents = {{name = "terms attributed to a specific source", sort = "กีฬา"}},
}
labels["terms derived from sport"] = labels["ศัพท์ที่รับมาจากกีฬา"]

labels["ศัพท์ที่รับมาจากเบสบอล"] = {
	description = "{{{langname}}} terms that originate from baseball.",
	breadcrumb = "เบสบอล",
	parents = {{name = "ศัพท์ที่รับมาจากกีฬา", sort = "เบสบอล"}},
}
labels["terms derived from baseball"] = labels["ศัพท์ที่รับมาจากเบสบอล"]

labels["terms with Indo-Aryan extensions"] = {
	description = "{{{langname}}} terms extended with particular [[Indo-Aryan]] [[pleonastic]] affixes.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["terms with lemma and non-lemma form etymologies"] = {
	description = "{{{langname}}} terms consisting of both a lemma and non-lemma form, of different origins.",
	breadcrumb = "lemma and non-lemma form",
	parents = {"terms with multiple etymologies"},
}

labels["terms with multiple etymologies"] = {
	description = "{{{langname}}} terms that are derived from multiple origins.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["terms with multiple lemma etymologies"] = {
	description = "{{{langname}}} lemmas that are derived from multiple origins.",
	breadcrumb = "multiple lemmas",
	parents = {"terms with multiple etymologies"},
}

labels["terms with multiple non-lemma form etymologies"] = {
	description = "{{{langname}}} non-lemma forms that are derived from multiple origins.",
	breadcrumb = "multiple non-lemma forms",
	parents = {"terms with multiple etymologies"},
}

labels["ศัพท์ที่ไม่ทราบรากศัพท์"] = {
	description = "{{{langname}}} terms whose etymologies have not yet been established.",
	parents = {{name = "ศัพท์แบ่งตามรากศัพท์", sort = "ไม่ทราบรากศัพท์"}},
}
labels["terms with unknown etymologies"] = labels["ศัพท์ที่ไม่ทราบรากศัพท์"]

labels["univerbations"] = {
	description = "{{{langname}}} terms that result from the agglutination of two or more words.",
	parents = {"ศัพท์แบ่งตามรากศัพท์"},
}

labels["words derived through metathesis"] = {
	description = "{{{langname}}} words that were created through [[metathesis]] from another word.",
	parents = {{name = "ศัพท์แบ่งตามรากศัพท์", sort = "metathesis"}},
}

-- Add 'umbrella_parents' key if not already present.
for key, data in pairs(labels) do
	-- NOTE: umbrella.parents overrides umbrella_parents if both are given.
	if not data.umbrella_parents then
		data.umbrella_parents = "หมวดหมู่ย่อยของศัพท์แบ่งตามรากศัพท์แบ่งตามภาษา"
	end
end



-----------------------------------------------------------------------------
--                                                                         --
--                              RAW CATEGORIES                             --
--                                                                         --
-----------------------------------------------------------------------------


raw_categories["หมวดหมู่ย่อยของศัพท์แบ่งตามรากศัพท์แบ่งตามภาษา"] = {
	description = "Umbrella categories covering topics related to terms categorized by their etymologies, such as types of compounds or borrowings.",
	additional = "{{{umbrella_meta_msg}}}",
	parents = {
		"หมวดหมู่ใหญ่รวมหัวข้อ",
		{name = "ศัพท์แบ่งตามรากศัพท์", is_label = true, sort = " "},
	},
}

raw_categories["หมวดหมู่ย่อยของศัพท์ที่ยืมมาแบ่งตามภาษา"] = {
	description = "Umbrella categories covering topics related to borrowed terms.",
	additional = "{{{umbrella_meta_msg}}}",
	parents = {
		"หมวดหมู่ใหญ่รวมหัวข้อ",
		{name = "ศัพท์ที่ยืมมา", is_label = true, sort = " "},
		{name = "หมวดหมู่ย่อยของศัพท์แบ่งตามรากศัพท์แบ่งตามภาษา", sort = " "},
	},
}

raw_categories["หมวดหมู่ย่อยของศัพท์ที่สืบทอดแบ่งตามภาษา"] = {
	description = "Umbrella categories covering topics related to inherited terms.",
	additional = "{{{umbrella_meta_msg}}}",
	parents = {
		"หมวดหมู่ใหญ่รวมหัวข้อ",
		{name = "ศัพท์ที่สืบสอด", is_label = true, sort = " "},
		{name = "หมวดหมู่ย่อยของศัพท์แบ่งตามรากศัพท์แบ่งตามภาษา", sort = " "},
	},
}

raw_categories["Indo-Aryan extensions"] = {
	description = "Umbrella categories covering terms extended with particular [[Indo-Aryan]] [[pleonastic]] affixes.",
	additional = "{{{umbrella_meta_msg}}}",
	parents = {
		"หมวดหมู่ใหญ่รวมหัวข้อ",
		{name = "หมวดหมู่ย่อยของศัพท์แบ่งตามรากศัพท์แบ่งตามภาษา", sort = " "},
	},
}

raw_categories["Multiple etymology subcategories by language"] = {
	description = "Umbrella categories covering topics related to terms with multiple etymologies.",
	additional = "{{{umbrella_meta_msg}}}",
	parents = {
		"หมวดหมู่ใหญ่รวมหัวข้อ",
		{name = "หมวดหมู่ย่อยของศัพท์แบ่งตามรากศัพท์แบ่งตามภาษา", sort = " "},
	},
}

raw_categories["ศัพท์ที่ยืมกลับไปยังภาษาเดิม"] = {
	description = "Categories with terms in specific languages that were borrowed from a second language that previously borrowed the term from the first language.",
	additional = "A well-known example is {{m+|en|salaryman}}, a term borrowed from Japanese which in turn was borrowed from the English words [[salary]] and [[man]].\n\n{{{umbrella_msg}}}",
	parents = "หมวดหมู่ย่อยของศัพท์แบ่งตามรากศัพท์แบ่งตามภาษา",
}



-----------------------------------------------------------------------------
--                                                                         --
--                                 HANDLERS                                --
--                                                                         --
-----------------------------------------------------------------------------

-----------------------------------------------------------------------------
------------------------------- word handlers -------------------------------
-----------------------------------------------------------------------------

-- Handlers for 'terms derived from the SOURCE word word' must go *BEFORE* the
-- more general 'terms derived from SOURCE' handler.

local function get_source_and_type_desc(source, term_type)
	if source:getCode() == "ine-pro" and term_type:find("^words?$") then
		return "[[w:Proto-Indo-European word|Proto-Indo-European " .. term_type .. "]]"
	else
		return "[[w:" .. source:getWikipediaArticle() .. "|" .. source:getCanonicalName() .. "]] " .. term_type
	end
end

-- Handler for e.g. [[:Category:Yola terms derived from the Proto-Indo-European word *h₂el- (grow)]] and
-- [[:Category:Russian terms derived from the Proto-Indo-European word *swé]], and corresponding umbrella
-- categories [[:Category:Terms derived from the Proto-Indo-European word *h₂el- (grow)]] and
-- [[:Category:Terms derived from the Proto-Indo-European word *swé]]. Replaces the former
-- [[Module:category tree/PIE word cat]], [[Module:category tree/word cat]] and [[Template:PIE word cat]].
table.insert(handlers, function(data)
	local source_name, term_type, term_and_id = data.label:match("^terms derived from the (.+) (word) (.+)$")
	if not source_name then
		source_name, term_type, term_and_id = data.label:match("^terms derived from the (.+) (word) (.+)$")
	end
	if not source_name then
		source_name, term_type, term_and_id = data.label:match("^terms derived from the (.+) (term) (.+)$")
	end

	if source_name then
		local term, id = term_and_id:match("^(.+) %((.-)%)$")
		term = term or term_and_id
		local source = require("Module:languages").getByCanonicalName(source_name, true, "allow etym langs")

		local parents = {
			{ name = "terms by " .. source_name .. " " .. term_type, sort = (source:makeSortKey(term)) }
		}
		local umbrella_parents = {
			{ name = "Terms derived from " .. source_name .. " " .. term_type .. "s", sort = (source:makeSortKey(term)) }
		}
		if id then
			table.insert(parents, { name = "terms derived from the " .. source_name .. " " .. term_type .. " " .. term, sort = " "})
			table.insert(umbrella_parents, { name = "terms derived from the " .. source_name .. " " .. term_type .. " " .. term, is_label = true, sort = " "})
		end
		-- Italicize the word/word in the title.
		local function displaytitle(title, lang)
			return str.plain_gsub(title, term, require("Module:script utilities").tag_text(term, source, nil, "term"))
		end
		local breadcrumb = require("Module:script utilities").tag_text(term, source, nil, "term") .. (id and " (" .. id .. ")" or "")
		return {
			description = "{{{langname}}} terms that originate ultimately from the " .. get_source_and_type_desc(source, term_type) .. " " ..
				require("Module:links").full_link({ term = term, lang = source, gloss = id, id = id }, "term") .. ".",
			displaytitle = displaytitle,
			breadcrumb = breadcrumb,
			parents = parents,
			umbrella = {
				no_by_language = true,
				displaytitle = displaytitle,
				breadcrumb = breadcrumb,
				parents = umbrella_parents,
			}
		}
	end
end)


table.insert(handlers, function(data)
	local labelpref, word_and_id = data.label:match("^(terms belonging to the word )(.+)$")
	if word_and_id then
		local word, id = word_and_id:match("^(.+) %((.-)%)$")
		word = word or word_and_id

		-- See if the language is Semitic.
		local fam = data.lang
		local is_semitic = false
		while true do
			if not fam then
				break
			end
			if fam:getCode() == "qfa-not" then
				-- qfa-not is "not a family" and is its own parent
				break
			end
			if fam:getCode() == "sem" then
				is_semitic = true
				break
			end
			fam = fam:getFamily()
		end
		local word_desc = is_semitic and "[[w:Semitic word|word]]" or "word"
		local parents = {}
		if id then
			table.insert(parents, {name = labelpref .. word, sort = id})
		end
		table.insert(parents, {name = "terms by word", sort = word_and_id})
		local separators = "־ %-"
		local separator_c = "[" .. separators .. "]"
		local not_separator_c = "[^" .. separators .. "]"
		-- remove any leading or trailing separators (e.g. in PIE-style words)
		local word_no_prefix_suffix =
			mw.ustring.gsub(mw.ustring.gsub(word, separator_c .. "$", ""), "^" .. separator_c, "")
		local num_sep = mw.ustring.len(mw.ustring.gsub(word_no_prefix_suffix, not_separator_c, ""))
		local linked_word = data.lang and require("Module:links").full_link({ term = word, lang = data.lang, gloss = id, id = id }, "term") or word
		if num_sep > 0 then
			table.insert(parents, {name = "" .. (num_sep + 1) .. "-letter words", sort = word_and_id})
		end
		-- Italicize the word/word in the title.
		local function displaytitle(title, lang)
			return str.plain_gsub(title, word, require("Module:script utilities").tag_text(word, lang, nil, "term"))
		end
		local breadcrumb = require("Module:script utilities").tag_text(word, data.lang, nil, "term") .. (id and " (" .. id .. ")" or "")
		return {
			description = "{{{langname}}} terms that belong to the " .. word_desc .. " " .. linked_word .. ".",
			displaytitle = displaytitle,
			breadcrumb = breadcrumb,
			parents = parents,
			umbrella = false,
		}
	end
end)

table.insert(handlers, function(data)
	local num_letters = data.label:match("^ศัพท์ที่มีตัวอักษร ([0-9]+) ตัว$")
	if num_letters then
		return {
			description = "{{{langname}}} words with " .. num_letters .. " letters in them.",
			parents = {{name = "ศัพท์ที่มีตัวอักษร", sort = "#" .. num_letters}},
			umbrella_parents = "หมวดหมู่ย่อยของศัพท์แบ่งตามรากศัพท์แบ่งตามภาษา",
		}
	end
end)

table.insert(handlers, function(data)
	local source_name = data.label:match("^terms by (.+) word$")
	if source_name then
		local source = require("Module:languages").getByCanonicalName(source_name, true, "allow etym langs")
		local parents = {"terms by etymology"}
		-- In [[:Category:Proto-Indo-Iranian terms by Proto-Indo-Iranian word]],
		-- don't add parent [[:Category:Proto-Indo-Iranian terms derived from Proto-Indo-Iranian]].
		if not data.lang or data.lang:getCode() ~= source:getCode() then
			table.insert(parents, "ศัพท์ที่รับมาจากภาษา" .. source_name)
		end
		return {
			description = "{{{langname}}} terms categorized by the " .. get_source_and_type_desc(source, "word") .. " they originate from.",
			parents = parents,
			umbrella_parents = "หมวดหมู่ย่อยของศัพท์แบ่งตามรากศัพท์แบ่งตามภาษา",
		}
	end
end)

table.insert(handlers, function(data)
	local word_shape = data.label:match("^(.+)-shape words$")
	if word_shape then
		local description = "{{{langname}}} words with the shape ''" .. word_shape .. "''."
		local additional
		if data.lang and data.lang:getCode() == "ine-pro" then
			additional = [=[
* '''e''' stands for the vowel of the word.
* '''C''' stands for any stop or ''s''.
* '''R''' stands for any resonant.
* '''H''' stands for any laryngeal.
* '''M''' stands for ''m'' or ''w'', when followed by a resonant.
* '''s''' stands for ''s'', when next to a stop.]=]
		end
		return {
			description = description,
			additional = additional,
			breadcrumb = word_shape,
			parents = {{name = "words by shape", sort = word_shape}},
			umbrella = false,
		}
	end
end)

-----------------------------------------------------------------------------
------------------------------- Root handlers -------------------------------
-----------------------------------------------------------------------------

-- Handlers for 'terms derived from the SOURCE root ROOT' must go *BEFORE* the
-- more general 'terms derived from SOURCE' handler.

local function get_source_and_type_desc(source, term_type)
	if source:getCode() == "ine-pro" and term_type:find("^roots?$") then
		return "[[w:Proto-Indo-European root|Proto-Indo-European " .. term_type .. "]]"
	else
		return "[[w:" .. source:getWikipediaArticle() .. "|" .. source:getCanonicalName() .. "]] " .. term_type
	end
end

-- Handler for e.g. [[:Category:Yola terms derived from the Proto-Indo-European root *h₂el- (grow)]] and
-- [[:Category:Russian terms derived from the Proto-Indo-European word *swé]], and corresponding umbrella
-- categories [[:Category:Terms derived from the Proto-Indo-European root *h₂el- (grow)]] and
-- [[:Category:Terms derived from the Proto-Indo-European word *swé]]. Replaces the former
-- [[Module:category tree/PIE root cat]], [[Module:category tree/root cat]] and [[Template:PIE word cat]].
table.insert(handlers, function(data)
	local source_name, term_type, term_and_id = data.label:match("^terms derived from the (.+) (root) (.+)$")
	if not source_name then
		source_name, term_type, term_and_id = data.label:match("^terms derived from the (.+) (word) (.+)$")
	end
	if not source_name then
		source_name, term_type, term_and_id = data.label:match("^terms derived from the (.+) (term) (.+)$")
	end

	if source_name then
		local term, id = term_and_id:match("^(.+) %((.-)%)$")
		term = term or term_and_id
		local source = require("Module:languages").getByCanonicalName(source_name, true, "allow etym langs")

		local parents = {
			{ name = "terms by " .. source_name .. " " .. term_type, sort = (source:makeSortKey(term)) }
		}
		local umbrella_parents = {
			{ name = "Terms derived from " .. source_name .. " " .. term_type .. "s", sort = (source:makeSortKey(term)) }
		}
		if id then
			table.insert(parents, { name = "terms derived from the " .. source_name .. " " .. term_type .. " " .. term, sort = " "})
			table.insert(umbrella_parents, { name = "terms derived from the " .. source_name .. " " .. term_type .. " " .. term, is_label = true, sort = " "})
		end
		-- Italicize the root/word in the title.
		local function displaytitle(title, lang)
			return str.plain_gsub(title, term, require("Module:script utilities").tag_text(term, source, nil, "term"))
		end
		local breadcrumb = require("Module:script utilities").tag_text(term, source, nil, "term") .. (id and " (" .. id .. ")" or "")
		return {
			description = "{{{langname}}} terms that originate ultimately from the " .. get_source_and_type_desc(source, term_type) .. " " ..
				require("Module:links").full_link({ term = term, lang = source, gloss = id, id = id }, "term") .. ".",
			displaytitle = displaytitle,
			breadcrumb = breadcrumb,
			parents = parents,
			umbrella = {
				no_by_language = true,
				displaytitle = displaytitle,
				breadcrumb = breadcrumb,
				parents = umbrella_parents,
			}
		}
	end
end)


table.insert(handlers, function(data)
	local labelpref, root_and_id = data.label:match("^(terms belonging to the root )(.+)$")
	if root_and_id then
		local root, id = root_and_id:match("^(.+) %((.-)%)$")
		root = root or root_and_id

		-- See if the language is Semitic.
		local fam = data.lang
		local is_semitic = false
		while true do
			if not fam then
				break
			end
			if fam:getCode() == "qfa-not" then
				-- qfa-not is "not a family" and is its own parent
				break
			end
			if fam:getCode() == "sem" then
				is_semitic = true
				break
			end
			fam = fam:getFamily()
		end
		local root_desc = is_semitic and "[[w:Semitic root|root]]" or "root"
		local parents = {}
		if id then
			table.insert(parents, {name = labelpref .. root, sort = id})
		end
		table.insert(parents, {name = "terms by root", sort = root_and_id})
		local separators = "־ %-"
		local separator_c = "[" .. separators .. "]"
		local not_separator_c = "[^" .. separators .. "]"
		-- remove any leading or trailing separators (e.g. in PIE-style roots)
		local root_no_prefix_suffix =
			mw.ustring.gsub(mw.ustring.gsub(root, separator_c .. "$", ""), "^" .. separator_c, "")
		local num_sep = mw.ustring.len(mw.ustring.gsub(root_no_prefix_suffix, not_separator_c, ""))
		local linked_root = data.lang and require("Module:links").full_link({ term = root, lang = data.lang, gloss = id, id = id }, "term") or root
		if num_sep > 0 then
			table.insert(parents, {name = "" .. (num_sep + 1) .. "-letter roots", sort = root_and_id})
		end
		-- Italicize the root/word in the title.
		local function displaytitle(title, lang)
			return str.plain_gsub(title, root, require("Module:script utilities").tag_text(root, lang, nil, "term"))
		end
		local breadcrumb = require("Module:script utilities").tag_text(root, data.lang, nil, "term") .. (id and " (" .. id .. ")" or "")
		return {
			description = "{{{langname}}} terms that belong to the " .. root_desc .. " " .. linked_root .. ".",
			displaytitle = displaytitle,
			breadcrumb = breadcrumb,
			parents = parents,
			umbrella = false,
		}
	end
end)

table.insert(handlers, function(data)
	local num_letters = data.label:match("^([1-9]%d*)-letter roots$")
	if num_letters then
		return {
			description = "{{{langname}}} roots with " .. num_letters .. " letters in them.",
			parents = {{name = "roots", sort = "#" .. num_letters}},
			umbrella_parents = "หมวดหมู่ย่อยของศัพท์แบ่งตามรากศัพท์แบ่งตามภาษา",
		}
	end
end)

table.insert(handlers, function(data)
	local source_name = data.label:match("^terms by (.+) root$")
	if source_name then
		local source = require("Module:languages").getByCanonicalName(source_name, true, "allow etym langs")
		local parents = {"terms by etymology"}
		-- In [[:Category:Proto-Indo-Iranian terms by Proto-Indo-Iranian root]],
		-- don't add parent [[:Category:Proto-Indo-Iranian terms derived from Proto-Indo-Iranian]].
		if not data.lang or data.lang:getCode() ~= source:getCode() then
			table.insert(parents, "terms derived from " .. source_name)
		end
		return {
			description = "{{{langname}}} terms categorized by the " .. get_source_and_type_desc(source, "root") .. " they originate from.",
			parents = parents,
			umbrella_parents = "หมวดหมู่ย่อยของศัพท์แบ่งตามรากศัพท์แบ่งตามภาษา",
		}
	end
end)

table.insert(handlers, function(data)
	local root_shape = data.label:match("^(.+)-shape roots$")
	if root_shape then
		local description = "{{{langname}}} roots with the shape ''" .. root_shape .. "''."
		local additional
		if data.lang and data.lang:getCode() == "ine-pro" then
			additional = [=[
* '''e''' stands for the vowel of the root.
* '''C''' stands for any stop or ''s''.
* '''R''' stands for any resonant.
* '''H''' stands for any laryngeal.
* '''M''' stands for ''m'' or ''w'', when followed by a resonant.
* '''s''' stands for ''s'', when next to a stop.]=]
		end
		return {
			description = description,
			additional = additional,
			breadcrumb = root_shape,
			parents = {{name = "roots by shape", sort = root_shape}},
			umbrella = false,
		}
	end
end)


-----------------------------------------------------------------------------
-------------------- Derived/inherited/borrowed handlers --------------------
-----------------------------------------------------------------------------

-- Handler for categories of the form "LANG terms derived from SOURCE", where SOURCE is a language, etymology language
-- or family (e.g. "Indo-European languages"), along with corresponding umbrella categories of the form
-- "Terms derived from SOURCE".
table.insert(handlers, function(data)
	local source_name = data.label:match("^ศัพท์ที่รับมาจากภาษา(.+)$")
	local type = "regular"
	if not source_name then
		source_name = data.label:match("^ศัพท์ที่รับมาจากกลุ่มภาษา(.+)$")
		type = "family"
	end
	if source_name then
		-- FIXME, should we allow 'terms derived from taxonomic names' when mul-tax has canonical name
		-- 'taxonomic name'? This is equivalent to what [[Module:category tree/derived cat]] did.
		-- Maybe fix mul-tax instead.
		local source = require("Module:languages").getByCanonicalName(source_name, true,
			"allow etym langs", "allow families")
		local source_desc = source:makeCategoryLink()

		-- Compute description.
		local desc = "{{{langname}}} terms that originate from " .. source_desc .. "."
		local additional
		if source:hasType("family") then
			additional = "This category should, ideally, contain only other categories. Entries can be categorized here, too, when the proper subcategory is unclear. " ..
				"If you know the exact language from which an entry categorized here is derived, please edit its respective entry."
		end
		
		-- Compute parents.
		local derived_from_variety_of_self = false
		local parent
		local sortkey = source:getDisplayForm()
		if source:hasType("etymology-only") then
			-- By default, `parent` is the source's parent.
			parent = source:getParent()
			-- Check if the source is a variety (or subvariety) of the language.
			if data.lang and source:hasParent(data.lang) then
				derived_from_variety_of_self = true
			end
			-- If the language is the direct parent of the source or the parent is "und", then we use the family of the source as `parent` instead.
			if data.lang and (parent:getCode() == data.lang:getCode() or parent:getCode() == "und") then
				parent = source:getFamily()
			end
		-- Regular language or family.
		else
			local fam = source:getFamily()
			if fam then
				parent = fam
			end
		end
		-- If `parent` does not exist, is the same as `source`, or would be "isolate languages" or "not a family", then we discard it.
		if (not parent) or parent:getCode() == source:getCode() or parent:getCode() == "qfa-iso" or parent:getCode() == "qfa-not" then
			parent = nil
			derived_from_variety_of_self = false
		-- Otherwise, get the display form.
		else
			parent = parent:getCategoryName()
		end
		parent = parent and "ศัพท์ที่รับมาจาก" .. parent or "ศัพท์ที่รับมาจากภาษาอื่น"
		local parents = {{name = parent, sort = sortkey}}
		if derived_from_variety_of_self then
			table.insert(parents, "Category:Categories for terms in a language derived from a term in a subvariety of that language")
		end

		-- Compute umbrella parents.
		local umbrella_parents = {
			source:hasType("family") and {name = source:getCategoryName(), raw = true, sort = " "} or
			source:hasType("etymology-only") and {name = "หมวดหมู่:" .. source:getCategoryName(), sort = "ศัพท์ที่รับมาจาก"} or
			{name = source:getCategoryName(), raw = true, sort = "ศัพท์ที่รับมาจาก"}
		}

		return {
			description = desc,
			additional = additional,
			breadcrumb = source_name,
			parents = parents,
			umbrella = {
				no_by_language = true,
				description = "Categories with terms that originate from " .. source_desc .. ".",
				parents = umbrella_parents,
			},
		}
	end
end)


local function get_source_and_source_desc(source_name)
	local source = require("Module:languages").getByCanonicalName(source_name, true, "allow etym langs", "allow families")
	local source_desc = source:makeCategoryLink()
	if source:hasType("family") then
		source_desc = "unknown " .. source_desc
	end
	return source, source_desc
end


-- Handler for categories of the form "LANG terms inherited/borrowed from SOURCE", where SOURCE is a language,
-- etymology language or family (e.g. "Indo-European languages"). Also handles umbrella categories of the form
-- "Terms inherited/borrowed from SOURCE".
local function inherited_borrowed_handler(etymtype)
	return function(data)
		local source_name = data.label:match("^ศัพท์ที่" .. etymtype .. "จากภาษา(.+)$")
		local famfix = "ภาษา"
		if not source_name then
			source_name = data.label:match("^ศัพท์ที่" .. etymtype .. "จากกลุ่มภาษา(.+)$")
			famfix = "กลุ่มภาษา"
		end
		if source_name then
			local source, source_desc = get_source_and_source_desc(source_name)
			return {
				description = "{{{langname}}} terms " .. etymtype .. " from " .. source_desc .. ".",
				breadcrumb = source_name,
				parents = {
					{ name = "ศัพท์ที่" .. etymtype, sort = source_name },
					{ name = "ศัพท์ที่รับมาจาก" .. famfix .. source_name, sort = " "},
				},
				umbrella = {
					no_by_language = true,
					parents = {
						{ name = "ศัพท์ที่รับมาจาก" .. famfix .. source_name, is_label = true, sort = " " },
						etymtype == "สืบทอด" and
							{ name = "หมวดหมู่ย่อยของศัพท์ที่สืบทอดแบ่งตามภาษา", sort = source_name }
						-- There are several types of borrowings mixed into the following holding category,
						-- so keep these ones sorted under 'Terms borrowed from SOURCE_NAME' instead of just
						-- 'SOURCE_NAME'.
						or "หมวดหมู่ย่อยของศัพท์ที่ยืมมาแบ่งตามภาษา",
					}
				},
			}
		end
	end
end

table.insert(handlers, inherited_borrowed_handler("ยืมมา"))
table.insert(handlers, inherited_borrowed_handler("สืบทอด"))


-----------------------------------------------------------------------------
------------------------ Borrowing subtype handlers -------------------------
-----------------------------------------------------------------------------

local function borrowing_subtype_handler(dest, source_name, parent_cat, desc, categorizing_templates, no_by_language)
	local source, source_desc = get_source_and_source_desc(source_name)
	local extra_templates = {}
	local extra_template_text
	for i, template in ipairs(categorizing_templates) do
		if i > 1 then
			table.insert(extra_templates, ("{{tl|%s|...}}"):format(template))
		end
	end
	if #extra_templates > 0 then
		extra_template_text = (" (or %s, using the same syntax)"):format(
			require("Module:table").serialCommaJoin(extra_templates, {conj = "or"}))
	else
		extra_template_text = ""
	end
	local additional, umbrella_additional
	if dest then
		additional = ("To categorize a term into this category, use {{tl|%s|%s|%s|<var>source_term</var>}}%s, " ..
			"where <code><var>source_term</var></code> is the source-language term that the term in question was " ..
			"borrowed from."):format(categorizing_templates[1], dest:getCode(), source:getCode(), extra_template_text)
	else
		umbrella_additional = ("To categorize a term into a language-specific subcategory, use " ..
			"{{tl|%s|<var>destcode</var>|%s|<var>source_term</var>}}%s, where <code><var>destcode</var></code> is " ..
			"the language code of the language in question (see [[Wiktionary:List of languages]]), and " ..
			"<code><var>source_term</var></code> is the source-language term that the term in question was " ..
			"borrowed from."):format(categorizing_templates[1], source:getCode(), extra_template_text)
	end

	return {
		description = "{{{langname}}} " .. desc:gsub("SOURCE", source_desc),
		additional = additional,
		breadcrumb = source_name,
		parents = {
			{ name = parent_cat, sort = source_name },
			{ name = "ศัพท์ที่ยืมมาจากภาษา" .. source_name, sort = " " },
		},
		umbrella = {
			no_by_language = no_by_language,
			additional = umbrella_additional,
			parents = {
				{ name = "ศัพท์ที่ยืมมาจากภาษา" .. source_name, is_label = true, sort = " " },
				"หมวดหมู่ย่อยของศัพท์ที่ยืมมาแบ่งตามภาษา",
			}
		},
	}
end

-- Specs describing types of borrowings.
-- `from_source_desc` is the English description used in categories of the form "LANGUAGE BORTYPE from SOURCE",
--    e.g. "Arabic semantic loans from English". "SOURCE" in the description is replaced by the source language.
-- `umbrella_desc` is the English description used in categories of the form "LANGUAGE BORTYPE", e.g.
--    "Arabic semantic loans". This is an umbrella category grouping all the source-language-specific categories.
-- `uses_subtype_handler`, if true, means that the handler for "LANGUAGE BORTYPE from SOURCE" categories is
--    implemented by a generic "TYPE borrowings" handler (at the bottom of this section), so we don't need to
--    create a BORTYPE-specific handler.
-- `umbrella_parent`, if given, is the parent category of the umbrella categories of the form "LANGUAGE BORTYPE".
--    By default it is "borrowed terms". Some borrowing types replace this with "terms by etymology". (FIXME:
--    Review whether this is correct.)
-- `label_pattern`, if given, is a Lua pattern that matches the category name minus the language at the beginning.
--    It should have one capture, which is the source language. An example is "^terms partially calqued from (.+)$".
--    If omitted, it is generated from BORTYPE.
-- `no_by_language`, if true, means that the umbrella category grouping borrowings of the appropriate type from a
--    specific source language is named "BORTYPE from SOURCE" in place of "BORTYPE from SOURCE by language"
--    (e.g. "Semantic loans from English" in place of "Semantic loans from English by language").
--
local borrowing_specs = {
	["ศัพท์ที่ยืมโดยเรียนรู้"] = {
		from_source_desc = "terms that are learned [[loanword]]s from SOURCE, that is, terms that were directly incorporated from SOURCE instead of through normal language contact.",
		umbrella_desc = "terms that are learned [[loanword]]s, that is, terms that were directly incorporated from another language instead of through normal language contact.",
		uses_subtype_handler = true,
		categorizing_templates = {"lbor", "learned borrowing"},
	},
	["ศัพท์ที่ยืมโดยกึ่งเรียนรู้"] = {
		from_source_desc = "terms that are [[semi-learned borrowing|semi-learned]] [[loanword]]s from SOURCE, that is, terms borrowed from SOURCE (a [[classical language]]) into the target language (a modern language) and partly reshaped based on later [[sound change]]s or by analogy with [[inherit]]ed terms in the language.",
		umbrella_desc = "terms that are [[semi-learned borrowing|semi-learned]] [[loanword]]s, that is, terms borrowed from a [[classical language]] into a modern language and partly reshaped based on later [[sound change]]s or by analogy with [[inherit]]ed terms in the language.",
		uses_subtype_handler = true,
		categorizing_templates = {"slbor", "semi-learned borrowing"},
	},
	["ศัพท์ที่ยืมอักขรวิธี"]	= {
		from_source_desc = "orthographic loans from SOURCE, i.e. terms that were borrowed from SOURCE in their script forms, not their pronunciations.",
		umbrella_desc = "orthographic loans, i.e. terms that were borrowed in their script forms, not their pronunciations.",
		uses_subtype_handler = true,
		categorizing_templates = {"obor", "orthographic borrowing"},
	},
	["ศัพท์ที่ยืมโดยไม่ดัดแปลง"] = {
		from_source_desc = "[[loanword]]s from SOURCE that have not been conformed to the morpho-syntactic, phonological and/or phonotactical rules of the target language.",
		umbrella_desc = "[[loanword]]s that have not been conformed to the morpho-syntactic, phonological and/or phonotactical rules of the target language.",
		uses_subtype_handler = true,
		categorizing_templates = {"ubor", "unadapted borrowing"},
	},
	["ศัพท์ที่ยืมความหมาย"] = {
		from_source_desc = "[[Appendix:Glossary#semantic loan|semantic loans]] from SOURCE, i.e. terms one or more of whose definitions was borrowed from a term in SOURCE.",
		umbrella_desc = "[[Appendix:Glossary#semantic loan|semantic loans]], i.e. terms one or more of whose definitions was borrowed from a term in another language.",
		umbrella_parent = "ศัพท์แบ่งตามรากศัพท์",
		no_by_language = true,
		categorizing_templates = {"sl", "semantic loan"},
	},
	["ศัพท์ที่แปลตรงตัวบางส่วน"] = {
		from_source_desc = "terms that were [[Appendix:Glossary#partial calque|partially calqued]] from SOURCE, i.e. terms formed partly by piece-by-piece translations of SOURCE terms and partly by direct borrowing.",
		umbrella_desc = "[[Appendix:Glossary#partial calque|partial calques]], i.e. terms formed partly by piece-by-piece translations of terms from other languages and partly by direct borrowing.",
		umbrella_parent = "ศัพท์แบ่งตามรากศัพท์",
		label_pattern = "^ศัพท์ที่แปลตรงตัวบางส่วนจากภาษา(.+)$",
		no_by_language = true,
		categorizing_templates = {"pcal", "pclq", "partial calque"},
	},
	["ศัพท์ที่แปลตรงตัว"] = {
		from_source_desc = "terms that were [[Appendix:Glossary#calque|calqued]] from SOURCE, i.e. terms formed by piece-by-piece translations of SOURCE terms.",
		umbrella_desc = "[[Appendix:Glossary#calque|calques]], i.e. terms formed by piece-by-piece translations of terms from other languages.",
		umbrella_parent = "ศัพท์แบ่งตามรากศัพท์",
		label_pattern = "^ศัพท์ที่แปลตรงตัวจากภาษา(.+)$",
		no_by_language = true,
		categorizing_templates = {"cal", "clq", "calque"},
	},
	["ศัพท์ที่เข้าคู่เสียง-ความหมาย"] = {
		from_source_desc = "[[Appendix:Glossary#phono-semantic matching|phono-semantic matchings]] from SOURCE, i.e. terms that were borrowed by matching the etymon phonetically and semantically.",
		umbrella_desc = "[[Appendix:Glossary#phono-semantic matching|phono-semantic matchings]], i.e. terms that were borrowed by matching the etymon phonetically and semantically.",
		no_by_language = true,
		categorizing_templates = {"psm", "phono-semantic matching"},
	},
	["ศัพท์ที่ยืมเทียม"] = {
		from_source_desc = "[[Appendix:Glossary#pseudo-loan|pseudo-loans]] from SOURCE, i.e. terms that appear to be SOURCE, but are not used or have an unrelated meaning in SOURCE itself.",
		umbrella_desc = "[[Appendix:Glossary#pseudo-loan|pseudo-loans]], i.e. terms that appear to be derived from another language, but are not used or have an unrelated meaning in that language itself.",
		categorizing_templates = {"pl", "pseudo-loan"},
	},
}

for bortype, spec in pairs(borrowing_specs) do
	labels[bortype] = {
		description = "{{{langname}}} " .. spec.umbrella_desc,
		parents = {spec.umbrella_parent or "ศัพท์ที่ยืมมา"},
		umbrella_parents = "หมวดหมู่ย่อยของศัพท์แบ่งตามรากศัพท์แบ่งตามภาษา",
	}
	if not spec.uses_subtype_handler then
		-- If the label pattern isn't specifically given, generate it from the `bortype`; but make sure to
		-- escape hyphens in the pattern.
		local label_pattern =
			spec.label_pattern or "^" .. str.pattern_escape(bortype) .. "จากภาษา(.+)$"
		table.insert(handlers, function(data)
			local source_name = data.label:match(label_pattern)
			if source_name then
				return borrowing_subtype_handler(data.lang, source_name, bortype, spec.from_source_desc,
					spec.categorizing_templates, spec.no_by_language)
			end
		end)
	end
end

table.insert(handlers, function(data)
	local borrowing_type, source_name = data.label:match("^(ศัพท์ที่ยืม.+)จากภาษา(.+)$")
	if borrowing_type then
		local spec = borrowing_specs[borrowing_type]
		return borrowing_subtype_handler(data.lang, source_name, borrowing_type, spec.from_source_desc,
			spec.categorizing_templates, false)
	end
end)


-----------------------------------------------------------------------------
---------------------- Indo-Aryan extension handlers ------------------------
-----------------------------------------------------------------------------

table.insert(handlers, function(data)
	local labelpref, extension = data.label:match("^(terms extended with Indo%-Aryan )(.+)$")
	if extension then
		local lang_inc_ash = require("Module:languages").getByCode("inc-ash")
		local linked_term = require("Module:links").full_link({lang = lang_inc_ash, term = extension}, "term")
		local tagged_term = require("Module:script utilities").tag_text(extension, lang_inc_ash, nil, "term")
		return {
			description = "{{{langname}}} terms extended with the [[Indo-Aryan]] [[pleonastic]] affix " .. linked_term .. ".",
			displaytitle = "{{{langname}}} " .. labelpref .. tagged_term,
			breadcrumb = tagged_term,
			parents = {{name = "terms with Indo-Aryan extensions", sort = extension}},
			umbrella = {
				no_by_language = true,
				parents = "Indo-Aryan extensions",
				displaytitle = "Terms extended with Indo-Aryan " .. tagged_term,
			}
		}
	end
end)


-----------------------------------------------------------------------------
---------------------------- Coined-by handlers -----------------------------
-----------------------------------------------------------------------------

table.insert(handlers, function(data)
	local coiner = data.label:match("^terms coined by (.+)$")
	if coiner then
		-- Sort by last name per request from [[User:Metaknowledge]]
		local last_name = coiner:match(".* ([^ ]+)$")
		return {
			description = "{{{langname}}} terms coined by " .. coiner .. ".",
			breadcrumb = coiner,
			parents = {{
				name = "coinages",
				sort = last_name and last_name .. ", " .. coiner or coiner,
			}},
			umbrella = false,
		}
	end
end)


-----------------------------------------------------------------------------
------------------------ Multiple etymology handlers ------------------------
-----------------------------------------------------------------------------

table.insert(handlers, function(data)
	local pos = data.label:match("^terms with multiple (.+) etymologies$")
	if pos and pos ~= "lemma" and pos ~= "non-lemma form" then
		local plpos = require("Module:string utilities").pluralize(pos)
		local postype = require("Module:headword").pos_lemma_or_nonlemma(plpos, "guess")
		return {
			description = "{{{langname}}} " .. plpos .. " that are derived from multiple origins.",
			umbrella_parents = "Multiple etymology subcategories by language",
			breadcrumb = "multiple " .. plpos,
			parents = {{
				name = "terms with multiple " .. postype .. " etymologies",
				sort = pos,
			}},
		}
	end
end)

table.insert(handlers, function(data)
	local pos1, pos2 = data.label:match("^terms with (.+) and (.+) etymologies$")
	if pos1 and pos1 ~= "lemma" and pos2 ~= "non-lemma form" then
		local m_strutil = require("Module:string utilities")
		local m_headword = require("Module:headword")
		local plpos1 = m_strutil.pluralize(pos1)
		local plpos2 = m_strutil.pluralize(pos2)
		local pos1type = m_headword.pos_lemma_or_nonlemma(plpos1, "guess")
		local pos2type = m_headword.pos_lemma_or_nonlemma(plpos2, "guess")
		local a_pos1 = m_strutil.add_indefinite_article(pos1)
		local a_pos2 = m_strutil.add_indefinite_article(pos2)
		
		return {
			description = "{{{langname}}} terms consisting of " .. a_pos1 .." of one origin and " ..
				a_pos2 .. " of a different origin.",
			umbrella_parents = "Multiple etymology subcategories by language",
			breadcrumb = pos1 .. " and " .. pos2,
			parents = {{
				name = pos1type == pos2type and "terms with multiple " .. pos1type .. " etymologies" or
					"terms with lemma and non-lemma form etymologies",
				sort = pos1 .. " and " .. pos2,
			}},
		}
	end
end)


-----------------------------------------------------------------------------
--------------------------- Borrowed-back handlers --------------------------
-----------------------------------------------------------------------------

-- Handler for categories of the form e.g. [[:Category:English terms borrowed back into English]]. We need to use a handler
-- because the category's language occurs inside the label itself. For the same reason, the umbrella category has a
-- nonstandard name "Terms borrowed back into the same language", so we handle it as a regular parent and disable the
-- built-in umbrella mechanism.
table.insert(handlers, function(data)
	local right_side_lang = data.label:match("^terms borrowed back into (.+)$")
	if data.lang and right_side_lang == data.lang:getCanonicalName() then
		return {
			description = "{{{langname}}} terms that were borrowed from another language that originally borrowed the term from {{{langname}}}.",
			parents = {"ศัพท์แบ่งตามรากศัพท์", "ศัพท์ที่ยืมมา",
				{name = "Terms borrowed back into the same language", raw = true, sort = "{{{langname}}}"}
			},
			umbrella = false, -- Umbrella has a nonstandard name so we treat it as a raw category
		}
	end
end)



-----------------------------------------------------------------------------
--                                                                         --
--                                RAW HANDLERS                             --
--                                                                         --
-----------------------------------------------------------------------------


-- Handler for umbrella metacategories of the form e.g. [[:Category:Terms derived from Proto-Indo-Iranian roots]]
-- and [[:Category:Terms derived from Proto-Indo-European words]]. Replaces the former
-- [[Module:category tree/PIE root cat]], [[Module:category tree/root cat]] and [[Template:PIE word cat]].
table.insert(raw_handlers, function(data)
	--local source_name, terms_type = data.category:match("^Terms derived from (.+) (roots)$")
	local terms_type, source_name = data.category:match("^ศัพท์ที่รับมาจาก(ราก)(.+)$")
	if not source_name then
		--source_name, terms_type = data.category:match("^Terms derived from (.+) (words)$")
		terms_type, source_name = data.category:match("^ศัพท์ที่รับมาจาก(คำ)(.+)$")
	end
	if not source_name then
		--source_name, terms_type = data.category:match("^Terms derived from (.+) (terms)$")
		terms_type, source_name = data.category:match("^ศัพท์ที่รับมาจาก(ศัพท์)(.+)$")
	end
	if source_name then
		local source = require("Module:languages").getByCanonicalName(source_name, true, "allow etym langs")

		return {
			description = "Umbrella categories covering terms derived from particular " .. get_source_and_type_desc(source, terms_type) .. ".",
			additional = "{{{umbrella_meta_msg}}}",
			parents = {
				"หมวดหมู่ใหญ่รวมหัวข้อ",
				{ name = terms_type == "ราก" and "ราก" or "คำหลัก", is_label = true, lang = source:getCode(), sort = " " },
				{ name = "ศัพท์ที่รับมาจาก" .. source_name, is_label = true, sort = " " .. terms_type },
			},
		}
	end
end)

return {LABELS = labels, RAW_CATEGORIES = raw_categories, HANDLERS = handlers, RAW_HANDLERS = raw_handlers}