Module:category tree/lexical properties

---

The following documentation is generated by Template:category tree data submodule documentation. ^[edit]

Useful links: root page • root page’s subpages • links • transclusions • testcases • sandbox

This data submodule defines part of Wiktionary's category structure.

For an introduction to the category tree system and a description of how to add or modify categories, see Module:category tree/documentation.

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

local insert = table.insert
local ucfirst = require("Module:string utilities").ucfirst

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


labels["terms by lexical property"] = {
	description = "{{{langname}}} terms categorized by properties relating to spelling, pronunciation or meaning.",
	umbrella_parents = "Fundamental",
	parents = {{name = "{{{langcat}}}", raw = true}}
}

labels["autohyponyms"] = {
	description = "{{{langname}}} terms that have at least two meanings, one of which is a hyponym of the other.",
	parents = {"terms by lexical property"},
}

labels["contranyms"] = {
	description = "{{{langname}}} terms that have two opposite meanings.",
	parents = {"terms by lexical property"},
}

labels["double negatives"] = {
	description = "{{{langname}}} terms which include a [[wikt:double negative|double negative]], either etymologically or in a definition.",
	parents = {"terms by lexical property"},
}

labels["heteronyms"] = {
	description = "{{{langname}}} terms that have different meanings depending on their etymology and/or on how they are pronounced.",
	parents = {"terms by lexical property"},
}

labels["nuqtaless forms"] = {
	description = "{{{langname}}} terms that are spelled without a [[wikt:nuqta|nuqta]].",
	parents = {"terms by orthographic property"},
}

labels["unhamzated forms"] = {
	description = "{{{langname}}} terms that are spelled without a [[wikt:hamza|hamza]].",
	parents = {"terms by orthographic property"},
}

labels["palindromes"] = {
	description = "{{{langname}}} terms whose characters are read equally both from left to right and vice versa, normally ignoring spaces, [[wikt:diacritic|diacritic]]s and punctuation.",
	parents = {"terms by their sequences of characters"},
}

labels["pleonastic compounds"] = {
	description = "{{{langname}}} compound terms where the head is a hyponym of its other part and whose other part is its synonym.",
	parents = {"terms by lexical property", "compound terms"},
}

labels["pleonastic compound adjectives"] = {
	description = "{{{langname}}} compound adjectives where the head is a hyponym of its other part and whose other part is its synonym.",
	breadcrumb = "adjectives",
	parents = {{name = "pleonastic compounds", sort = "adjectives"}, "compound adjectives"},
}

labels["pleonastic compound nouns"] = {
	description = "{{{langname}}} compound nouns where the head is a hyponym of its other part and where the head is the synonym for the whole.",
	breadcrumb = "nouns",
	parents = {{name = "pleonastic compounds", sort = "nouns"}, "compound nouns"},
}

labels["pronunciation spellings"] = {
	description = "{{{langname}}} terms spelled to represent a pronunciation, often a nonstandard one.",
	parents = {"terms by orthographic property"},
}

labels["tautophrases"] = {
	description = "{{{langname}}} phrases that repeat the same idea or concept using the same words.",
	parents = {"terms by lexical property"},
}

labels["terms by orthographic property"] = {
	description = "{{{langname}}} terms categorized by properties relating to [[wikt:orthography|orthography]] or [[wikt:spelling|spelling]].",
	breadcrumb = "by orthographic property",
	parents = {{name = "terms by lexical property", sort = "orthographic property"}},
}

labels["calculator words"] = {
	description = "{{{langname}}} terms that can be spelled on a [[wikt:seven-segment|seven-segment]] display, as found on pocket calculators, by turning numbers upside-down.",
	parents = {"terms by orthographic property"},
}

labels["words spelled without vowels"] = {
	description = "{{{langname}}} words spelled without vowels.",
	additional = "The letters counted as vowels may differ from language to language but typically include the conventional written vowels (''a'' ''e'' ''i'' ''o'' ''u'' ''y''), and may include other less common letters representing vowels (e.g. ''æ'', ''œ'', ''ø''). Terms in this category may contain vowel sounds in their pronunciation.",
	parents = {"terms by their sequences of characters"},
}

labels["words by number of letters"] = {
	description = "{{{langname}}} words categorized by number of letters.",
	parents = {"terms by orthographic property"},
}

labels["abbreviations by number of letters"] = {
	description = "{{{langname}}} abbreviations categorized by number of letters.",
	parents = {"terms by orthographic property"},
}

labels["roots by number of letters"] = {
	description = "{{{langname}}} {{lg|roots}} categorized by number of letters.",
	breadcrumb = "by number of letters",
	parents = {
		{name = "roots", sort = "number of letters"},
		"terms by orthographic property"
	},
}

labels["roots by shape"] = {
	description = "{{{langname}}} {{lg|roots}} categorized by their shape.",
	breadcrumb = "by shape",
	parents = {
		{name = "roots", sort = "shape"},
		"terms by lexical property"
	},
}

labels["words by number of syllables"] = {
	description = "{{{langname}}} words categorized by number of syllables.",
	parents = {"terms by phonemic property"},
}

labels["terms by their individual characters"] = {
	description = "{{{langname}}} terms categorized by whether they include certain individual characters.",
	breadcrumb = "by their individual characters",
	parents = {{name = "terms by orthographic property", sort = "individual characters"}},
}

labels["terms by their sequences of characters"] = {
	description = "{{{langname}}} terms categorized by whether they include certain sequences of characters.",
	breadcrumb = "by their sequences of characters",
	parents = {{name = "terms by orthographic property", sort = "sequences of characters"}},
}

labels["terms with consecutive instances of the same letter"] = {
	description = "{{{langname}}} words categorized by the number of consecutive instances of the same letter they contain.",
	breadcrumb = "consecutive instances of the same letter",
	parents = {{name = "terms by orthographic property", sort = "consecutive instances of the same letter"}},
}

labels["terms containing italics"] = {
	description = "{{{langname}}} terms containing [[wikt:italics|italics]].",
	breadcrumb = "containing italics",
	parents = {{name = "terms by orthographic property", sort = "containing italics"}},
}

labels["terms containing Roman numerals"] = {
	description = "{{{langname}}} terms containing [[wikt:Roman numeral|Roman numeral]]s.",
	breadcrumb = "containing Roman numbers",
	parents = {{name = "terms by orthographic property", sort = "containing Roman numbers"},
		{name = "terms spelled with numbers", sort = "Roman numerals"}},
}

labels["terms with mixed convergence"] = {
	description = "{{{langname}}} terms where the spelling represents a variant pronunciation that differs from (one of) the current standard pronunciation(s).",
	breadcrumb = "with mixed convergence",
	parents = {{name = "terms by orthographic property", sort = "mixed convergence"}, "terms by phonemic property"},
}

labels["terms with homophones"] = {
	description = "{{{langname}}} terms that have one or more [[wikt:homophones|homophones]]: other terms that are pronounced in the same way but spelled differently.",
	breadcrumb = "with homophones",
	parents = {{name = "terms by lexical property", sort = "homophones"}},
}

labels["terms with honorific transposition"] = {
	description = "{{{langname}}} compound terms where the written order of the elements is reversed due to [[wikt:honorific transposition|honorific transposition]].",
	breadcrumb = "with honorific transposition",
	parents = {{name = "terms by orthographic property", sort = "honorific transposition"}},
}

labels["terms where the adjective follows the noun"] = {
	description = "{{{langname}}} terms where the adjective follows the noun. These adjectives within these terms are sometimes referred to as postpositive or postnominal adjectives.",
	breadcrumb = "adjective follows the noun",
	parents = {{name = "terms by lexical property", sort = "adjective follows the noun"}},
}

labels["terms written in foreign scripts"] = {
	description = "{{{langname}}} terms that are written in a different, non-native script.",
	breadcrumb = "written in foreign scripts",
	parents = {{name = "terms by orthographic property", sort = "written in foreign scripts"}},
}

labels["terms written in multiple scripts"] = {
	description = "{{{langname}}} terms that are written using more than one script.",
	breadcrumb = "written in multiple scripts",
	parents = {{name = "terms by orthographic property", sort = "written in multiple scripts"}},
}

labels["terms by phonemic property"] = {
	description = "{{{langname}}} terms categorized by properties relating to [[wikt:pronunciation|pronunciation]] and [[wikt:phonemics|phonemics]].",
	breadcrumb = "by phonemic property",
	parents = {{name = "terms by lexical property", sort = "phonemic property"}},
}

-- Add 'umbrella_parents' key if not already present.
for _, data in pairs(labels) do
	if not data.umbrella_parents then
		data.umbrella_parents = "Terms by lexical property subcategories by language"
	end
end


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


raw_categories["Terms by lexical property subcategories by language"] = {
	breadcrumb = "subcategories",
	description = "Umbrella categories covering topics related to terms categorized by their lexical properties, such as palindromes and number of letters or syllables in a word.",
	additional = "{{{umbrella_meta_msg}}}",
	parents = {
		{name = "terms by lexical property", is_label = true, sort = " "},
		"Umbrella metacategories",
	},
}

for _, v in ipairs{
	{"words", "letters"},
	{"abbreviations", "letters"},
	{"roots", "letters"},
	{"words", "syllables"}
} do
	raw_categories[("%s by number of %s subcategories by language"):format(ucfirst(v[1]), v[2])] = {
		breadcrumb = "subcategories",
		description = ("Umbrella categories covering topics related to %s categorized by their number of %s."):format(v[1], v[2]),
		additional = "{{{umbrella_meta_msg}}}",
		parents = {
			{name = ("%s by number of %s"):format(v[1], v[2]), is_label = true, sort = " "},
			"Umbrella metacategories",
		},
	}
end

raw_categories["Terms with consecutive instances of the same letter subcategories by language"] = {
	breadcrumb = "subcategories",
	description = "Umbrella categories covering topics related to terms categorized by the number of consecutive instances of the same letter they contain.",
	additional = "{{{umbrella_meta_msg}}}",
	parents = {
		{name = "terms with consecutive instances of the same letter", is_label = true, sort = " "},
		"Umbrella metacategories",
	},
}

raw_categories["Long words by language"] = {
	description = "Categories with terms that are longer than a given (per-language) threshold.",
	additional = "{{{umbrella_msg}}}",
	parents = {
		{name = "terms by lexical property", is_label = true, sort = " "},
	},
}


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

for _, v in ipairs{
	{"words", "letter", "composed of", function(n)
		local pl = n == "1" and "" or "s"
		return ("They have meaning(s) other than their letter%s or the shape of their letter%s which are not abbreviations, numbers or symbols."):format(pl, pl)
	end},
	{"abbreviations", "letter", "composed of"},
	{"roots", "letter", "composed of"},
	{"words", "syllable", "pronounced with"}
} do
	insert(handlers, function(data)
		local n = data.label:match(("^([1-9]%%d*)%%-%s %s$"):format(v[2], v[1]))
		if not n then
			return
		end
		local sortkey = require("Module:category tree").numeral_sortkey(n, 2097152)
		return {
			breadcrumb = n,
			description = ("{{{langname}}} %s that are %s %d %s%s."):format(v[1], v[3], n, v[2], n == "1" and "" or "s"),
			additional = v[4] and v[4](n) or nil,
			umbrella = {
				breadcrumb = ("%d %s"):format(n, v[2]),
				parents = {{name = ("%s by number of %ss subcategories by language"):format(ucfirst(v[1]), v[2]), sort = sortkey}},
			},
			parents = {{name = ("%s by number of %ss"):format(v[1], v[2]), sort = sortkey}}
		}
	end)
end

insert(handlers, function(data)
	local n = data.label:match("^terms with ([1-9]%d*) consecutive instances of the same letter$")
	if not (n and tonumber(n) > 2) then
		return
	end
	local sortkey = require("Module:category tree").numeral_sortkey(n, 2097152)
	return {
		breadcrumb = n,
		description = ("{{{langname}}} terms containing %d consecutive instances of the same letter."):format(n),
		umbrella = {
			breadcrumb = ("%d consecutive instances"):format(n),
			parents = {{name = "Terms with consecutive instances of the same letter subcategories by language", sort = sortkey}},
		},
		parents = {{name = "terms with consecutive instances of the same letter", sort = sortkey}}
	}
end)


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

insert(raw_handlers, function(data)
	local langname = data.category:match("^Long (.*) words$")
	if langname then
		local lang = require("Module:languages").getByCanonicalName(langname)
		if lang then
			local length_threshold = require("Module:headword/data").long_word_thresholds[lang:getCode()]
			if length_threshold then
				return {
					lang = lang:getCode(),
					description = "{{{langname}}} words that are " .. length_threshold .. " letters or longer.",
					parents = {
						{name = "terms by orthographic property", lang = lang:getCode(), is_label = true},
						{name = "Long words by language"},
					},
				}
			end
		end
	end
end)


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