Module:auto cat/data

-------------------------
--[[  AUTO CAT DATA  ]]--
-------------------------
-- %l = any language name
-- %u = any language name (different to %l)
-- %c = any language code
-- %p = any part of speech
-- %ps = any part of speech (plural)
-- %s = any string
-------------------------
-- Please note that the order of patterns
-- makes a difference!
-- Patterns higher up in the table will be
-- matched against first.
-------------------------
local pos = {
    "adjective",
    "adverb",
	"article",
    "conjunction",
    "determiner",
    "interjection",
	"noun",
    "numeral",
    "particle",
    "phrase",
    "postposition",
    "preposition",
    "pronoun",
    "proper noun",
    "symbol",
    "verb",
}

local cats = {
    -- Languages
    {"All languages", {"Fundamental"}},
    {"%l language", {"All languages"}},
    {"%l images", {"%l language"}},
    -- Lexember
    {"Lexember 2023: %l", {"%l language"}},
    {"Lexember 2023 Day %s: %l", {"Lexember 2023: %l"}},
    -- Rhymes
    {"Rhymes:%l/%s", {"Rhymes:%l"}},
    {"Rhymes:%l", {"%l language", "Rhymes"}},
    {"Rhymes", {"Fundamental"}},
    -- Lemmas by language
    {"Lemmas by language", {"Fundamental"}},
    {"Lemmas subcategories by language", {"Lemmas by language| "}},
    {"%ps by language", {"Lemmas by language| "}},
    {"Multiword terms by language", {"Lemmas subcategories by language"}},
    -- Language lemmas
    {"%l lemmas", {"%l language", "Lemmas by language"}},
    {"%l %ps", {"%l lemmas", "%ps by language"}},
    {"%l multiword terms", {"%l lemmas", "Multiword terms by language"}},
    -- Non-lemmas by language
    {"Non-lemma forms by language", {"Fundamental"}},
    {"Non-lemma forms subcategories by language", {"Non-lemma forms by language| "}},
    {"%p forms by language", {"Non-lemma forms subcategories by language"}},
    -- Language non-lemmas
    {"%l non-lemma forms", {"%l language", "Non-lemma forms by language"}},
    {"%l %p forms", {"%l non-lemma forms|%p forms", "%l %ps", "%p forms by language"}},
    -- Morphemes by language
    {"Morphemes by language", {"Lemmas subcategories by language"}},
    {"Affixes by language", {"Lemmas subcategories by language"}},
    {"Prefixes by language", {"Affixes by language| "}},
    {"Suffixes by language", {"Affixes by language| "}},
    {"Infixes by language", {"Affixes by language| "}},
    {"Circumfixes by language", {"Affixes by language| "}},
    {"Clitics by language", {"Lemmas subcategories by language"}},
    -- Language morphemes
    {"%l morphemes", {"%l lemmas", "Morphemes by language"}},
    {"%l affixes", {"%l morphemes", "%l lemmas", "Affixes by language"}},
    {"%l prefixes", {"%l morphemes", "%l affixes", "Prefixes by language"}},
    	{"%l %s prefixes", {"%l prefixes"}},
    {"%l suffixes", {"%l morphemes", "%l affixes", "Suffixes by language"}},
    	{"Nominal suffixes by language", {"Lemmas subcategories by language"}},
    	{"Verbal suffixes by language", {"Lemmas subcategories by language"}},
    	{"Adjectival suffixes by language", {"Lemmas subcategories by language"}},
    	{"%l nominal suffixes", {"%l suffixes", "Nominal suffixes by language"}},
		{"%l adjectival suffixes", {"%l suffixes", "Adjectival suffixes by language"}},
    	{"%l verbal suffixes", {"%l suffixes", "Verbal suffixes by language"}},
    	{"%l %s suffixes", {"%l suffixes"}},
    {"%l infixes", {"%l morphemes", "%l affixes", "Infixes by language"}},
    	{"%l %s infixes", {"%l infixes"}},
    {"%l circumfixes", {"%l morphemes", "%l affixes", "Circumfixes by language"}},
    {"%l clitics", {"%l morphemes", "Clitics by language"}},
    -- Types of lemma by language
    {"%s %ps by language", {"Lemmas subcategories by language"}},
    {"Nouns with multiple genders by language", {"Lemmas subcategories by language"}},
    {"Nouns with multiple animacies by language", {"Lemmas subcategories by language"}},
    
    -- Language types of lemma *with cross-linguistic category*
    {"%l comparable adjectives", {"%l adjectives", "Comparable adjectives by language"}},
    {"%l uncomparable adjectives", {"%l adjectives", "Uncomparable adjectives by language"}},
    {"%l possessive pronouns", {"%l pronouns", "Possessive pronouns by language"}},
    {"%l imperfective verbs", {"%l verbs", "Imperfective verbs by language"}},
    {"%l perfective verbs", {"%l verbs", "Perfective verbs by language"}},
    {"%l biaspectual verbs", {"%l verbs", "Biaspectual verbs by language"}},
    {"%l transitive verbs", {"%l verbs", "Transitive verbs by language"}},
    {"%l intransitive verbs", {"%l verbs", "Intransitive verbs by language"}},
    {"%l auxiliary verbs", {"%l verbs", "Auxiliary verbs by language"}},
    {"%l copulative verbs", {"%l verbs", "Copulative verbs by language"}},
    {"%l deponent verbs", {"%l verbs", "Deponent verbs by language"}},
    {"%l ditransitive verbs", {"%l verbs", "Ditransitive verbs by language"}},
    {"%l impersonal verbs", {"%l verbs", "Impersonal verbs by language"}},
    {"%l stative verbs", {"%l verbs", "Stative verbs by language"}},
    {"%l passive verbs", {"%l verbs", "Passive verbs by language"}},
    {"%l reflexive verbs", {"%l verbs", "Reflexive verbs by language"}},
    {"%l mediopassive verbs", {"%l verbs", "Mediopassive verbs by language"}},
    {"%l neuter nouns", {"%l nouns", "Neuter nouns by language"}},
    {"%l feminine nouns", {"%l nouns", "Feminine nouns by language"}},
    {"%l masculine nouns", {"%l nouns", "Masculine nouns by language"}},
    {"%l common nouns", {"%l nouns", "Common nouns by language"}},
    {"%l dualia tantum", {"%l nouns", "Dualia tantum by language"}},
    {"%l pluralia tantum", {"%l nouns", "Pluralia tantum by language"}},
    {"%l inanimate nouns", {"%l nouns", "Inanimate nouns by language"}},
    {"%l animate nouns", {"%l nouns", "Animate nouns by language"}},
    {"%l personal nouns", {"%l nouns", "Personal nouns by language"}},
    {"%l nonpersonal nouns", {"%l nouns", "Nonpersonal nouns by language"}},
    {"%l animal nouns", {"%l nouns", "Animal nouns by language"}},
    {"%l nonvirile nouns", {"%l nouns", "Nonvirile nouns by language"}},
    {"%l virile nouns", {"%l nouns", "Virile nouns by language"}},
    {"%l nouns with multiple genders", {"%l nouns", "Nouns with multiple genders by language"}},
    {"%l nouns with multiple animacies", {"%l nouns", "Nouns with multiple animacies by language"}},
    
    {"%l %s %ps", {"%l %ps"}}, -- sorts all other PoS descriptors under the PoS but not under a cross-linguistic category (e.g. Virile nouns by language). More for language-specific PoS subcategories.
    
    -- Government
    {"%ps governing the %s by language", {"Lemmas subcategories by language"}},
    {"%l %ps governing the %s", {"%l %ps", "%ps governing the %s by language"}},
    
    -- Roots by language
    {"Root-derived terms by language", {"Fundamental"}},
    {"Terms derived from %l roots", {"%l roots", "Terms derived from %l| ", "Root-derived terms by language"}},
    {"Terms derived from the %l root %s", {"Terms derived from %l roots"}},
    {"Terms by root by language", {"Terms by etymology subcategories by language"}},
    {"Roots by language", {"Terms by etymology subcategories by language"}},
    {"Nominal roots by language", {"Roots by language| "}},
    {"Verbal roots by language", {"Roots by language| "}},
    {"Terms by %l root by language", {"Terms by etymology subcategories by language|%l"}},
    -- Language roots
    {"%l roots", {"%l language", "%l morphemes", "Roots by language"}},
    {"%l nominal roots", {"%l roots", "Nominal roots by language"}},
    {"%l verbal roots", {"%l roots", "Verbal roots by language"}},
    {"%l adjectival roots", {"%l roots", "Adjectival roots by language"}},
    {"%l terms by root", {"%l terms by etymology", "%l roots", "Terms by root by language"}},
    {"%l terms belonging to the root %s", {"%l terms by root"}},
    {"%l terms by %u root", {"%l terms by etymology", "%l terms derived from %u", "Terms by %u root by language"}},
    {"%l terms derived from the %u root %s", {"%l terms by %u root", "Terms derived from the %u root %s"}},
    -- Etymology by language
    {"Terms by etymology by language", {"Fundamental"}},
    {"Terms by etymology subcategories by language", {"Terms by etymology by language| "}},
    {"Abbreviations by language", {"Terms by etymology subcategories by language"}},
    {"Acronyms by language", {"Terms by etymology subcategories by language"}},
    {"Adjectivisations by language", {"Terms by etymology subcategories by language"}},
    {"Back-formations by language", {"Terms by etymology subcategories by language"}},
    {"Blends by language", {"Terms by etymology subcategories by language"}},
    {"Clippings by language", {"Terms by etymology subcategories by language"}},
    {"Contractions by language", {"Terms by etymology subcategories by language"}},
    {"Deadjectivals by language", {"Terms by etymology subcategories by language"}},
    {"Denominals by language", {"Terms by etymology subcategories by language"}},
    {"Deverbals by language", {"Terms by etymology subcategories by language"}},
    {"Doublets by language", {"Terms by etymology subcategories by language"}},
    {"Ellipses by language", {"Terms by etymology subcategories by language"}},
    {"Initialisms by language", {"Terms by etymology subcategories by language"}},
    {"Nominalisations by language", {"Terms by etymology subcategories by language"}},
    {"Onomatopoeias by language", {"Terms by etymology subcategories by language"}},
    {"Rebracketings by language", {"Terms by etymology subcategories by language"}},
    {"Reduplications by language", {"Terms by etymology subcategories by language"}},
    {"Terms with unknown etymologies by language", {"Terms by etymology subcategories by language"}},
    {"Terms with multiple etymologies by language", {"Terms by etymology subcategories by language"}},
    {"Verbalisations by language", {"Terms by etymology subcategories by language"}},
    -- Language etymology (no source)
    {"%l abbreviations", {"%l terms by etymology", "Abbreviations by language"}},
    {"%l acronyms", {"%l terms by etymology", "Acronyms by language"}},
    {"%l adjectivisations", {"%l terms by etymology", "Adjectivisations by language"}},
    {"%l back-formations", {"%l terms by etymology", "Back-formations by language"}},
    {"%l blends", {"%l terms by etymology", "Blends by language"}},
    {"%l clippings", {"%l terms by etymology", "Clippings by language"}},
    {"%l contractions", {"%l terms by etymology", "Contractions by language"}},
    {"%l deadjectivals", {"%l terms by etymology", "Deadjectivals by language"}},
    {"%l denominals", {"%l terms by etymology", "Denominals by language"}},
    {"%l deverbals", {"%l terms by etymology", "Deverbals by language"}},
    {"%l doublets", {"%l terms by etymology", "Doublets by language"}},
    {"%l ellipses", {"%l terms by etymology", "Ellipses by language"}},
    {"%l initialisms", {"%l terms by etymology", "Initialisms by language"}},
    {"%l nominalisations", {"%l terms by etymology", "Nominalisations by language"}},
    {"%l onomatopoeias", {"%l terms by etymology", "Onomatopoeias by language"}},
    {"%l rebracketings", {"%l terms by etymology", "Rebracketings by language"}},
    {"%l reduplications", {"%l terms by etymology", "Reduplications by language"}},
    {"%l terms with unknown etymologies", {"%l terms by etymology", "Terms with unknown etymologies by language"}},
    {"%l terms by etymology", {"%l language", "Terms by etymology by language"}},
    {"%l terms with multiple etymologies", {"%l terms by etymology", "Terms with multiple etymologies by language"}},
    {"%l verbalisations", {"%l terms by etymology", "Verbalisations by language"}},
    -- Etymology source by language
    {"Terms derived from %l", {"%l language"}},
    {"Inherited terms by language", {"Terms by etymology subcategories by language"}},
    {"Borrowed terms by language", {"Terms by etymology subcategories by language"}},
    {"Calqued terms by language", {"Terms by etymology subcategories by language"}},
    {"Learned borrowings from %s by language", {"Terms borrowed from %s", "Borrowed terms by language"}},
    {"Orthographic borrowings from %s by language", {"Terms borrowed from %s", "Borrowed terms by language"}},
    {"Semantic loans from %s", {"Terms borrowed from %s", "Borrowed terms by language"}},
    {"Phono-semantic matchings from %s", {"Terms borrowed from %s", "Borrowed terms by language"}},
    {"Transliterations of %s", {"Terms borrowed from %s", "Borrowed terms by language"}},
    {"Terms borrowed from %s", {"Terms derived from %s", "Borrowed terms by language"}},
    {"Terms inherited from %s", {"Terms derived from %s", "Inherited terms by language"}},
    {"Terms calqued from %s", {"Terms borrowed from %s", "Borrowed terms by language"}},
    {"Learned borrowings by language", {"Terms by etymology subcategories by language"}},
    {"Orthographic borrowings by language", {"Terms by etymology subcategories by language"}},
    {"Semantic loans by language", {"Terms by etymology subcategories by language"}},
    {"Phono-semantic matchings by language", {"Terms by etymology subcategories by language"}},
    {"Transliterations by language", {"Terms by etymology subcategories by language"}},
    -- Language etymology (with source)
    {"%l terms borrowed from %s", {"%l borrowed terms", "%l terms derived from %s", "Terms borrowed from %s"}},
    {"%l terms calqued from %s", {"%l calques", "%l terms borrowed from %s", "Terms calqued from %s"}},
    {"%l terms derived from %s", {"Terms derived from %s"}},
    {"%l terms inherited from %s", {"%l inherited terms", "%l terms derived from %s", "Terms inherited from %s"}},
    {"%l learned borrowings from %s", {"%l learned borrowings", "%l terms borrowed from %s", "Learned borrowings from %s by language"}},
    {"%l orthographic borrowings from %s", {"%l orthographic borrowings", "%l terms borrowed from %s", "Orthographic borrowings from %s by language"}},
    {"%l semantic loans from %s", {"%l semantic loans", "%l terms borrowed from %s", "Semantic loans from %s"}},
    {"%l phono-semantic matchings from %s", {"%l phono-semantic matchings", "%l terms borrowed from %s", "Phono-semantic matchings from %s"}},
    {"%l transliterations of %s", {"%l transliterations", "%l terms borrowed from %s", "Transliterations of %s"}},
    {"%l borrowed terms", {"%l terms by etymology", "Borrowed terms by language"}},
    {"%l calques", {"%l terms by etymology", "Calques by language"}},
    {"%l inherited terms", {"%l terms by etymology", "Inherited terms by language"}},
    {"%l learned borrowings", {"%l borrowed terms", "Learned borrowings by language"}},
    {"%l orthographic borrowings", {"%l borrowed terms", "Orthographic borrowings by language"}},
    {"%l semantic loans", {"%l borrowed terms", "Semantic loans by language"}},
    {"%l phono-semantic matchings", {"%l borrowed terms", "Phono-semantic matchings by language"}},
    {"%l transliterations", {"%l borrowed terms", "Transliterations by language"}},
    -- Affix etymology
    {"Compound terms by language", {"Terms by etymology subcategories by language"}},
    {"Terms by prefix by language", {"Terms by etymology subcategories by language"}},
    {"Terms by suffix by language", {"Terms by etymology subcategories by language"}},
    {"Terms by infix by language", {"Terms by etymology subcategories by language"}},
    {"Terms by circumfix by language", {"Terms by etymology subcategories by language"}},
    {"%l terms by prefix", {"%l prefixes", "%l terms by etymology", "Terms by prefix by language"}},
    {"%l terms by suffix", {"%l suffixes", "%l terms by etymology", "Terms by suffix by language"}},
    {"%l terms by infix", {"%l infixes", "%l terms by etymology", "Terms by infix by language"}},
    {"%l terms by circumfix", {"%l circumfixes", "%l terms by etymology", "Terms by circumfix by language"}},
    {"%l terms prefixed with %s", {"%l terms by prefix"}},
    {"%l terms suffixed with %s", {"%l terms by suffix"}},
    {"%l terms infixed with %s", {"%l terms by infix"}},
    {"%l terms circumfixed with %s", {"%l terms by circumfix"}},
    {"%l compound terms", {"%l terms by etymology", "Compound terms by language"}},
    -- Coinage
    {"Coinages by language", {"Terms by etymology subcategories by language"}},
    {"%l coinages", {"%l terms by etymology", "Coinages by language"}},
    -- Entry maintenance
    {"Entry maintenance by language", {"Fundamental"}},
    {"Terms with usage examples by language", {"Entry maintenance by language| "}},
    {"%l entry maintenance", {"%l language", "Entry maintenance by language"}},
    {"%l terms with usage examples", {"%l entry maintenance", "Terms with usage examples by language"}},
    -- Miscellaneous terms (custom)
    {"Interlingual homographs", {"Fundamental"}},
    {"Requested terms by language", {"Fundamental"}},
    {"Nth terms by language", {"Fundamental"}},
    {"%l requested terms", {"%l language", "Requested terms by language"}},
    {"%l terms requested by my boyfriend", {"%l requested terms"}},
    {"%l terms requested by my partner", {"%l requested terms"}},
    {"%l nth terms", {"%l language", "Nth terms by language"}},
    -- Usage labels by language
    {"Terms by usage by language", {"Fundamental"}},
    {"Terms by usage subcategories by language", {"Terms by usage by language| "}},
	    {"Archaic terms by language", {"Terms by usage subcategories by language"}},
	    {"Colloquial terms by language", {"Terms by usage subcategories by language"}},
	    {"Dated terms by language", {"Terms by usage subcategories by language"}},
	    {"Derogatory terms by language", {"Terms by usage subcategories by language"}},
	    {"Dialectal terms by language", {"Terms by usage subcategories by language"}},
	    {"Euphemisms by language", {"Terms by usage subcategories by language"}},
	    {"Formal terms by language", {"Terms by usage subcategories by language"}},
	    {"Gender-neutral terms by language", {"Terms by usage subcategories by language"}},
	    {"Humble terms by language", {"Terms by usage subcategories by language"}},
	    {"Jocular terms by language", {"Terms by usage subcategories by language"}},
	    {"Obsolete terms by language", {"Terms by usage subcategories by language"}},
	    {"Offensive terms by language", {"Terms by usage subcategories by language"}},
	    {"Pejorative terms by language", {"Terms by usage subcategories by language"}},
	    {"Slang terms by language", {"Terms by usage subcategories by language"}},
	    {"Slurs by language", {"Terms by usage subcategories by language"}},
	    {"Vulgar terms by language", {"Terms by usage subcategories by language"}},
    -- Language usage labels
    {"%l terms by usage", {"%l language", "Terms by usage by language"}},
    {"%l archaic terms", {"%l terms by usage", "Archaic terms by language"}},
    {"%l colloquial terms", {"%l terms by usage", "Colloquial terms by language"}},
    {"%l dated terms", {"%l terms by usage", "Dated terms by language"}},
    {"%l derogatory terms", {"%l terms by usage", "Derogatory terms by language"}},
    {"%l dialectal terms", {"%l terms by usage", "Dialectal terms by language"}},
    {"%l euphemisms", {"%l terms by usage", "Euphemisms by language"}},
    {"%l formal terms", {"%l terms by usage", "Formal terms by language"}},
    {"%l gender-neutral terms", {"%l terms by usage", "Gender-neutral terms by language"}},
    {"%l humble terms", {"%l terms by usage", "Humble terms by language"}},
    {"%l jocular terms", {"%l terms by usage", "Jocular terms by language"}},
    {"%l obsolete terms", {"%l terms by usage", "Obsolete terms by language"}},
    {"%l offensive terms", {"%l terms by usage", "Offensive terms by language"}},
    {"%l pejorative terms", {"%l terms by usage", "Pejorative terms by language"}},
    {"%l slang terms", {"%l terms by usage", "Slang terms by language"}},
    {"%l slurs", {"%l terms by usage", "Slurs by language"}},
    {"%l vulgar terms", {"%l terms by usage", "Vulgar terms by language"}},
    -- Topics
    {"Topics by language", {"Fundamental"}},
    {"In-world terms by language", {"Topics by language| "}},
    {"Out-of-world terms by language", {"Topics by language| "}},
    {"Names by language", {"Topics by language| "}},
    {"%s topic by language", {"Topics by language| "}},
    {"%l topics", {"%l language", "Topics by language"}},
    	-- World specificity
	    {"%l in-world terms", {"%l topics", "In-world terms by language"}},
	    {"%l out-of-world terms", {"%l topics", "Out-of-world terms by language"}},
	    -- Names
	    {"%l names", {"%l topics", "Names by language| "}},
	    	{"%l given names", {"%l topics", "Given names by language", "%l names"}},
	    	{"%l surnames", {"%l topics", "Surnames by language", "%l names"}},
    	-- Chemistry sub-topics
    	{"%c:Biochemistry", {"%l topics", "Biochemistry topic by language", "%c:Chemistry"}},
    		{"%c:Enzymes", {"%l topics", "Enzymes topic by language", "%c:Biochemistry"}},
    	{"%c:Organic chemistry", {"%l topics", "Organic chemistry topic by language", "%c:Chemistry"}},
    	{"%c:Sugars", {"%l topics", "Sugars topic by language", "%c:Chemistry"}},
    	-- Biology sub-topics
    	{"%c:Cytology", {"%l topics", "Cytology topic by language", "%c:Biology"}},
	    {"%c:Genetics", {"%l topics", "Genetics topic by language", "%c:Biology"}},
	    {"%c:Molecular biology", {"%l topics", "Molecular biology topic by language", "%c:Biology"}},
	    {"%c:Physiology", {"%l topics", "Physiology topic by language", "%c:Biology"}},
	    {"%c:Taxonomy", {"%l topics", "Taxonomy topic by language", "%c:Biology"}},
    	-- Linguistics sub-topics
    	{"%c:Phonetics", {"%l topics", "Phonetics topic by language", "%c:Linguistics"}},
    	{"%c:Phonology", {"%l topics", "Phonology topic by language", "%c:Linguistics"}},
    	-- Mathematics sub-topics
    	{"%c:Algebra", {"%l topics", "Algebra topic by language", "%c:Mathematics"}},
    	{"%c:Arithmetic", {"%l topics", "Arithmetic topic by language", "%c:Mathematics"}},
    	{"%c:Calculus", {"%l topics", "Calculus topic by language", "%c:Mathematics"}},
    	{"%c:Geometry", {"%l topics", "Geometry topic by language", "%c:Mathematics"}},
    	{"%c:Statistics", {"%l topics", "Statistics topic by language", "%c:Mathematics"}},
    	{"%c:Trigonometry", {"%l topics", "Trigonometry topic by language", "%c:Mathematics"}},
	    	{"%c:Trigonometric functions", {"%l topics", "Trigonometric functions topic by language", "%c:Trigonometry"}},
	    -- Physics sub-topics
	    {"%c:Nuclear physics", {"%l topics", "Nuclear physics topic by language", "%c:Physics"}},
	    -- Time sub-topics
    	{"%c:Months", {"%l topics", "Months topic by language", "%c:Time"}},
    	{"%c:Seasons", {"%l topics", "Seasons topic by language", "%c:Time"}},
    	{"%c:Days", {"%l topics", "Days topic by language", "%c:Time"}},
    	-- End of sub-topics
    {"%c:%s", {"%l topics", "%s topic by language"}},
    -- Templates
    {"Templates", {"Fundamental"}},
    {"Templates by language", {"Templates"}},
    {"Entry templates", {"Templates"}},
    {"Link templates", {"Templates"}},
    {"Banner templates", {"Templates"}},
    {"Encyclopedia templates", {"Templates"}},
    {"Etymology templates", {"Entry templates"}},
    {"Definition templates", {"Entry templates"}},
    {"Pronunciation templates", {"Entry templates"}},
    {"Translation templates", {"Entry templates"}},
    {"%l templates", {"Templates by language"}},
    -- Modules
    {"Modules", {"Fundamental"}},
    {"Modules by language", {"Modules"}},
    {"%l modules", {"Modules by language"}},
}

return {
	cats = cats,
	pos = pos,
}