Module:category tree/poscatboiler/data/terms by grammatical category

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



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


labels = {
	description = "{{{langname}}} terms categorized by their grammatical category.",
	umbrella_parents = "Fundamental",
	parents = {{name = "{{{langcat}}}", raw = true}},
}

------- GENDER -------

for _, pos in ipairs { "nouns", "pronouns", "proper nouns", "suffixes" } do
	labels = {
		description = "{{{langname}}} " .. pos .. " organized by the gender they belong to.",
		breadcrumb = "by gender",
		parents = {{name = pos, sort = "gender"}},
	}

	labels = {
		description = "{{{langname}}} " .. pos .. " whose ending is not typical for " .. pos .. " of their gender.",
		breadcrumb = "with irregular gender",
		parents = {{name = "irregular " .. pos, sort = "irregular gender"}},
	}
	
	labels = {
		description = "{{{langname}}} " .. pos .. " that belong to more than one gender.",
		breadcrumb = "with multiple genders",
		parents = {{name = pos .. " by gender", sort = "multiple genders"}},
	}

	labels = {
		description = "{{{langname}}} " .. pos .. " of {{glossary|common gender}}, i.e. belonging to a gender category that combines the function of {{glossary|masculine}} and {{glossary|feminine}} and is opposed to the {{glossary|neuter}} gender.",
		breadcrumb = "common-gender",
		parents = {pos .. " by gender"},
	}

	labels = {
		description = "{{{langname}}} " .. pos .. " of {{glossary|feminine}} gender, i.e. belonging to a gender category that contains (among other things) female beings.",
		breadcrumb = "feminine",
		parents = {pos .. " by gender"},
	}

	labels = {
		description = "{{{langname}}} " .. pos .. " of {{glossary|masculine}} gender, i.e. belonging to a gender category that contains (among other things) male beings.",
		breadcrumb = "masculine",
		parents = {pos .. " by gender"},
	}

	labels = {
		description = "{{{langname}}} " .. pos .. " that may be either {{glossary|masculine}} or {{glossary|feminine}} depending on whether they refer to male or female beings.",
		breadcrumb = "masculine and feminine by sense",
		parents = {pos .. " by gender"},
	}

	labels = {
		description = "{{{langname}}} " .. pos .. " of {{glossary|neuter}} gender, i.e. belonging to a gender category that does not usually contain male or female beings.",
		breadcrumb = "neuter",
		parents = {pos .. " by gender"},
	}

	labels = {
		description = "{{{langname}}} " .. pos .. " that are applicable to all people, independent of gender.",
		breadcrumb = "gender-neutral",
		parents = {pos .. " by gender", "gender-neutral terms"},
	}
end

for _, pos in ipairs({"adjectives", "suffixes"}) do
	labels = {
		description = "{{{langname}}} " .. pos .. " whose form is the same for both {{glossary|masculine}} and {{glossary|feminine}}, in languages whose " .. pos .. " normally distinguish gender.",
		breadcrumb = "epicene",
		parents = {pos .. " by inflection type"},
	}
end

------- NOUN CLASSES -------

labels = {
	description = "{{{langname}}} nouns organized by the class they belong to.",
	breadcrumb = "by class",
	parents = {{name = "nouns", sort = "class"}},
}

labels = {
	description = "{{{langname}}} nouns that are ].",
	breadcrumb = "alienable",
	parents = {"nouns"},
}

labels = {
	description = "{{{langname}}} nouns that are ].",
	breadcrumb = "inalienable",
	parents = {"nouns"},
}


------- ANIMACY -------

for _, pos in ipairs({"nouns", "suffixes", "verbs"}) do
	labels = {
		description = "{{{langname}}} " .. pos .. " that refer to humans or animals.",
		breadcrumb = "animate",
		parents = {pos},
	}
	
	labels = {
		description = "{{{langname}}} " .. pos .. " that refer to inanimate objects (not humans or animals).",
		breadcrumb = "inanimate",
		parents = {pos},
	}
	
	labels = {
		description = "{{{langname}}} " .. pos .. " that belong to more than one animacy.",
		breadcrumb = "with multiple animacies",
		parents = {{name = pos, sort = "multiple animacies"}},
	}
end	

for _, pos in ipairs({"nouns", "suffixes"}) do
	-- This category should be used particularly in languages that have
	-- grammatical distinctions related to animals, such as Ukrainian.
	labels = {
		description = "{{{langname}}} " .. pos .. " that refer to animals.",
		breadcrumb = "animal",
		parents = {"animate " .. pos},
	}
	
	-- This category should be used particularly in languages that have
	-- grammatical distinctions related to men, such as Polish.
	labels = {
		description = "{{{langname}}} plural " .. pos .. " that refer to a group without male humans.",
		breadcrumb = "nonvirile",
		parents = {pos, "pluralia tantum"},
	}
	
	labels = {
		description = "{{{langname}}} " .. pos .. " that refer to humans.",
		breadcrumb = "personal",
		parents = {"animate " .. pos},
	}
	
	-- This category should be used particularly in languages that have
	-- grammatical distinctions related to men, such as Polish.
	labels = {
		description = "{{{langname}}} plural " .. pos .. " that refer to a group with at least one male human.",
		breadcrumb = "virile",
		parents = {pos, "pluralia tantum"},
	}
end

------- INFLECTED PARTS OF SPEECH -------

-- Add "POS by inflection type", "irregular POS" and "POS by tone"
-- categories for (potentially) inflected parts of speech.

local inflected_poses = {
	"adjectives",
	"adverbs",
	"determiners",
	"nouns",
	"numerals",
	"participles",
	"pronouns",
	"proper nouns",
	"suffixes",
	"verbs",
}

for _, pos in ipairs(inflected_poses) do
	labels = {
		description = "{{{langname}}} " .. pos .. " organized by the type of inflection they follow.",
		breadcrumb = "by inflection type",
		parents = {{name = pos, sort = "inflection"}},
	}

	labels = {
		description = "{{{langname}}} " .. pos .. " that follow non-standard patterns of inflection.",
		breadcrumb = "irregular",
		parents = {pos .. " by inflection type"},
	}

	labels = {
		description = "{{{langname}}} " .. pos .. " that lack one or more forms in their inflections.",
		breadcrumb = "defective",
		parents = {pos, "irregular " .. pos},
	}

	labels = {
		description = "{{{langname}}} " .. pos .. " that have inflected forms from different roots.",
		breadcrumb = "suppletive",
		umbrella_parents = "Suppletion subcategories by language",
		parents = {"irregular " .. pos},
	}
	
	if pos ~= "verbs" and pos ~= "adverbs" then
		labels = {
			description = "{{{langname}}} " .. pos .. " that do not display additional grammatical relations by means of declension.",
			breadcrumb = "indeclinable",
			parents = {pos .. " by inflection type"},
		}

		labels = {
			description = "{{{langname}}} " .. pos .. " that follow more than one type of inflection.",
			breadcrumb = "with multiple declensions",
			parents = {{name = pos .. " by inflection type", sort = "multiple declensions"}},
		}
		
		labels = {
			description = "{{{langname}}} " .. pos .. " that have more than one possible plural (sometimes with distinct meanings).",
			breadcrumb = "with multiple plurals",
			parents = {{name = pos .. " by inflection type", sort = "multiple plurals"}},
		}
	end

	labels = {
		description = "{{{langname}}} " .. pos .. " organized by the tone they follow.",
		breadcrumb = "by tone",
		parents = {{name = pos .. " by inflection type", sort = "tone"}},
	}
	
	labels = {
		description = "{{{langname}}} " .. pos .. " organized by the vowel harmony they follow.",
		breadcrumb = "by vowel harmony",
		parents = {{name = pos .. " by inflection type", sort = "vowel harmony"}},
	}
end


-- FIXME: Only used currently for Arabic; probably should be removed as a general category.
labels = {
	description = "{{{langname}}} elative adjectives that follow non-standard patterns of inflection.",
	parents = {"adjectives by inflection type"},
}

for _, pos in ipairs { "nouns", "proper nouns", "pronouns" } do
	labels = {
		description = "{{{langname}}} " .. pos .. " with unattested plurals.",
		breadcrumb = "with unattested plurals",
		parents = {{name = pos, sort = "unattested plurals"}},
	}
	labels = {
		description = "{{{langname}}} " .. pos .. " that are inherently definite and have definite concord.",
		breadcrumb = "definite",
		parents = {pos .. " by inflection type"},
	}
end


------- GERMANIC VERB CLASSES -------

-- FIXME: Not clear this belongs among the general categories.

labels = {
	description = "{{{langname}}} verbs that present different stem vowels in their typically regular conjugated forms.",
	breadcrumb = "strong",
	parents = {"verbs by inflection type"},
}

labels = {
	description = "{{{langname}}} verbs that display dental suffixes in their past tense conjugated forms.",
	breadcrumb = "weak",
	parents = {"verbs by inflection type"},
}

labels = {
	description = "{{{langname}}} verbs that inflect in the present tense like the past tense of strong verbs.",
	breadcrumb = "preterite-present",
	parents = {"verbs by inflection type"},
}

labels = {
	description = "Verbs where the ] vowel was followed by ''-y-'' in Proto-Indo-European.",
	breadcrumb = "class 1",
	parents = {{name = "strong verbs", sort = "1"}},
}

labels = {
	description = "Weak verbs of the first class.",
	breadcrumb = "class 1",
	parents = {{name = "weak verbs", sort = "1"}},
}

labels = {
	description = "Verbs where the ] vowel was followed by ''-w-'' in Proto-Indo-European.",
	breadcrumb = "class 2",
	parents = {{name = "strong verbs", sort = "2"}},
}

labels = {
	description = "Verbs where the ] vowel was *eu in Proto-Germanic.",
	breadcrumb = "class 2a",
	parents = {{name = "class 2 strong verbs", sort = "1"}},
}

labels = {
	description = "Verbs where the ] vowel was *ū in Proto-Germanic.",
	breadcrumb = "class 2b",
	parents = {{name = "class 2 strong verbs", sort = "2"}},
}

labels = {
	description = "Weak verbs of the second class.",
	breadcrumb = "class 2",
	parents = {{name = "weak verbs", sort = "2"}},
}

labels = {
	description = "Weak verbs of the third class.",
	breadcrumb = "class 3",
	parents = {{name = "weak verbs", sort = "3"}},
}

labels = {
	description = "Verbs where the ] vowel was followed by a ] in Proto-Indo-European.",
	breadcrumb = "class 3",
	parents = {{name = "strong verbs", sort = "3"}},
}

labels = {
	description = "Verbs where the ] begins with a nasal consonant.",
	breadcrumb = "class 3a",
	parents = {{name = "class 3 strong verbs", sort = "1"}},
}

labels = {
	description = "Verbs where the ] begins with a lateral consonant or velar fricative.",
	breadcrumb = "class 3b",
	parents = {{name = "class 3 strong verbs", sort = "2"}},
}

labels = {
	description = "Verbs where the ] begins with a rhotic consonant.",
	breadcrumb = "class 3c",
	parents = {{name = "class 3 strong verbs", sort = "3"}},
}

labels = {
	description = "Verbs where the ] vowel was followed by a ] (''m'', ''n'', ''l'', ''r'') but no other consonant in Proto-Indo-European.",
	breadcrumb = "class 4",
	parents = {{name = "strong verbs", sort = "4"}},
}

labels = {
	description = "Weak verbs of the fourth class.",
	breadcrumb = "class 4",
	parents = {{name = "weak verbs", sort = "4"}},
}

labels = {
	description = "Verbs where the ] vowel was followed by ] other than a ] in Proto-Indo-European.",
	breadcrumb = "class 5",
	parents = {{name = "strong verbs", sort = "5"}},
}

labels = {
	description = "The Proto-Indo-European origin of this class is not securely known. It contains verbs with the stem vowel ''-a-'', except those where it is followed by a sonorant and another consonant (this combination was considered a diphthong in PIE and therefore belonged to class 7).",
	breadcrumb = "class 6",
	parents = {{name = "strong verbs", sort = "6"}},
}

labels = {
	description = "Verbs that retained their reduplication in the past tense in Proto-Germanic.",
	breadcrumb = "class 7",
	parents = {{name = "strong verbs", sort = "7"}},
}

labels = {
	description = "Class 7 strong verbs where the root vowel was ''*ai'' in Proto-Germanic, analogous to class 1.",
	breadcrumb = "class 7a",
	parents = {{name = "class 7 strong verbs", sort = "a"}},
}

labels = {
	description = "Class 7 strong verbs where the root vowel was ''*au'' in Proto-Germanic, analogous to class 2.",
	breadcrumb = "class 7b",
	parents = {{name = "class 7 strong verbs", sort = "b"}},
}

labels = {
	description = "Class 7 strong verbs where the root vowel was ''*a'' followed by a ] in Proto-Germanic, analogous to class 3.",
	breadcrumb = "class 7c",
	parents = {{name = "class 7 strong verbs", sort = "c"}},
}

labels = {
	description = "Class 7 strong verbs where the root vowel was ''*ē'' in Proto-Germanic.",
	breadcrumb = "class 7d",
	parents = {{name = "class 7 strong verbs", sort = "d"}},
}

labels = {
	description = "Class 7 strong verbs where the root vowel was ''*ō'' in Proto-Germanic.",
	breadcrumb = "class 7e",
	parents = {{name = "class 7 strong verbs", sort = "e"}},
}

------- TUPIAN LEMMA CLASSES -------

-- FIXME: Present in Old Tupi, Nheengatu, Guaraní and some other Tupian languages; not clear if this belongs among the general categories.

labels = {
	description = "{{{langname}}} adjectives that have a relational prefix added to their stem.",
	breadcrumb = "pluriform",
	parents = {"adjectives by inflection type"},
}

labels = {
	description = "{{{langname}}} nouns that have a relational prefix added to their stem.",
	breadcrumb = "pluriform",
	parents = {"nouns by inflection type"},
}

labels = {
	description = "{{{langname}}} postpositions that have a relational prefix added to their stem.",
	breadcrumb = "pluriform",
	parents = {"postpositions by inflection type"},
}

labels = {
	description = "{{{langname}}} verbs that have a relational prefix added to their stem.",
	breadcrumb = "pluriform",
	parents = {"verbs by inflection type"},
}

local labels2 = {}

-- Add 'umbrella_parents' key if not already present.
for key, data in pairs(labels) do
	labels2 = data
	if not data.umbrella_parents then
		data.umbrella_parents = "Terms by grammatical category subcategories by language"
	end
end



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


raw_categories = {
	description = "Umbrella categories covering topics related to grammatical categories, such as gender, animacy and noun and verb classes.",
	additional = "{{{umbrella_meta_msg}}}",
	parents = {
		"Umbrella metacategories",
		{name = "terms by grammatical category", is_label = true, sort = " "},
	},
}

raw_categories = {
	description = "Umbrella categories covering suppletive terms in specific part-of-speech categories.",
	additional = "{{{umbrella_meta_msg}}}",
	parents = {
		"Umbrella metacategories",
		"Terms by grammatical category subcategories by language",
	},
}


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


table.insert(handlers, function(data)
	local class = data.label:match("^class (+) nouns$")
	if class then
		local classnum, suffix = class:match("^(+)(*)$")
		return {
			description =
				"{{{langname}}} nouns that belong to class " .. class .. ".",
			breadcrumb = class,
			umbrella = false,
			parents = {{
				name = "nouns by class",
				sort = classnum and ("#%02d"):format(classnum) .. suffix or class,
			}},
		}
	end
end)

table.insert(handlers, function(data)
	local pos, tone = data.label:match("^(.+) with tone (+)$")
	if pos then
		return {
			description = "{{{langname}}} " .. pos .. " with tone " .. tone .. ".",
			breadcrumb = tone,
			-- FIXME, should there be an umbrella category e.g. 'Adjectives with tone H by language'?
			umbrella = false,
			parents = {{
				name = pos .. " by tone",
				sort = "" .. tone:len() .. tone,
			}},
		}
	end
end)

table.insert(handlers, function(data)
	local vh, pos = data.label:match("^(.+)-harmonic (+)$")
	if pos then
		return {
			description = "{{{langname}}} " .. pos .. " with vowel harmony in " .. vh .. ".",
			breadcrumb = vh,
			umbrella = false,
			parents = {{
				name = pos .. " by vowel harmony",
				sort = "" .. vh:len() .. vh,
			}},
		}
	end
end)

table.insert(handlers, function(data)
	local pos, classifier = data.label:match("^(nouns) classified by (.+)$")
	if pos then
		local linktext
		if data.lang then
			-- Chinese classifiers may take the form TRAD/SIMP. This will cause problems if passed directly to ],
			-- but the module can accept links of the form TRAD//SIMP and display them correctly.
			if data.lang:getCode() == "zh" then
				classifier = classifier:gsub("/", "//")
			end
			linktext = require("Module:links").full_link({ term = classifier, lang = data.lang }, "term")
		else
			linktext = classifier
		end
		return {
			description = "{{{langname}}} " .. pos .. " using " .. linktext .. " as their classifier.",
			breadcrumb = classifier,
			umbrella = false,
			parents = {{
				name = pos .. " by classifier",
				sort = (data.lang:makeSortKey(classifier)),
			}},
		}
	end
end)


return {LABELS = labels2, RAW_CATEGORIES = raw_categories, HANDLERS = handlers}