--[=[
This module lists the more common recognized inflection tags, along with their shortcut aliases, the corresponding
glossary entry or page describing the tag, and the corresponding wikidata entry. The less common tags are in
[[Module:form of/data2]]. We divide the tags this way to save memory space. Be careful adding more tags to this module;
add them to the other module unless you're sure they are common.
TAGS is a table where keys are the canonical form of an inflection tag and the corresponding values are tables
describing the tags, consisting of the following keys:
- 1: Type of the tag ("diri", "number", "gender", "case", "animacy", "tense-aspect", "mood", "voice-valence",
etc.).
- 2: Anchor or page describing the inflection tag, with the following values:
* nil: No link.
* APPENDIX: Anchor in [[Appendix:Glossary]] whose name is the same as the tag
* WIKT: Page in the English Wiktionary whose name is the same as the tag.
* WP: Page in the English Wikipedia whose name is the same as the tag.
* A string: If prefixed by 'w:' the specified page in the English Wikipedia. If prefixed by 'wikt:', the
specified page in the English Wiktionary. Otherwise, an anchor in [[Appendix:Glossary]].
NOTE: GLOSSARY ANCHORS ARE PREFERRED. Other types of entries should be migrated to the glossary, with links to
Wikipedia and/or Wiktionary entries as appropriate.
- 3: List of shortcuts (i.e. aliases for the inflection tag) or a single shortcut string, or nil.
- 4: Numeric value of Wikidata identifier (see wikidata.org) for the concept most closely describing this tag.
(The actual Wikidata identifier is a string formed by prefixing the number with Q.)
- display: If specified, consists of text to display in the definition line, in lieu of the canonical form of the
inflection tag. If there is a glossary entry, the displayed text forms the right side of the two-part
glossary link.
- no_space_on_left: If specified, don't display a space to the left of the tag. Used for punctuation.
- no_space_on_right: If specified, don't display a space to the right of the tag. Used for punctuation.
SHORTCUTS is a table mapping shortcut aliases to canonical inflection tag names. Shortcuts are of one of three types:
(1) A simple alias of a tag. These do not need to be entered explicitly into the table; code at the end of the module
automatically fills in these entries based on the information in TAGS.
(2) An alias to a multipart tag. For example, the alias "mf" maps to the multipart tag "m//f", which will in turn be
expanded into the canonical multipart tag {"masculine", "feminine"}, which will display as (approximately)
"[[Appendix:Glossary#gender|masculine]] and [[Appendix:Glossary#gender|feminine]]". The number of such aliases
should be liminted, and should cover only the most common combinations.
Normally, multipart tags are displayed using serialCommaJoin() in [[Module:table]] to appropriately join the display
form of the individual tags using commas and/or "and". However, some multipart tags are displayed specially; see
DISPLAY_HANDLERS below. Note that aliases to multipart tags can themselves contain simple aliases in them.
(3) An alias to a list of multiple tags (which may themselves be simple or multipart aliases). Specifying the alias is
exactly equivalent to specifying the tags in the list in order, one after another. An example is "1s", which maps to
the list {"1", "s"}. The number of such aliases should be limited, and should cover only the most common
combinations.
NOTE: In some cases below, multiple tags point to the same wikidata, because Wikipedia considers them synonyms. Examples
are indirect case vs. objective case vs. oblique case, and inferential mood vs. renarrative mood. We do this because
(a) we want to allow users to choose their own terminology; (b) we want to be able to use the terminology most common
for the language in question; (c) terms considered synonyms may or may not actually be synonyms, as different languages
may use the terms differently. For example, although the Wikipedia page on [[w:inferential mood]] claims that
inferential and renarrative moods are the same, the page on [[w:Bulgarian_verbs#Evidentials]] claims that Bulgarian has
both, and that they are not the same.
]=]
local m_form_of = require("Module:form of")
local APPENDIX = m_form_of.APPENDIX
local WP = m_form_of.WP
local WIKT = m_form_of.WIKT
local tags = {}
local shortcuts = {}
----------------------- Diri -----------------------
tags["diri pertama"] = {
"diri",
"diri pertama",
"1",
21714344,
}
tags["diri kedua"] = {
"diri",
"diri kedua",
"2",
51929049,
}
tags["diri ketiga"] = {
"diri",
"diri ketiga",
"3",
51929074,
}
tags["impersonal"] = {
"diri",
APPENDIX,
"impers",
}
shortcuts["12"] = "1//2"
shortcuts["13"] = "1//3"
shortcuts["23"] = "2//3"
shortcuts["123"] = "1//2//3"
----------------------- Bilangan -----------------------
tags["mufrad"] = {
"bilangan",
"bilangan mufrad",
{"s", "sg"},
110786,
}
tags["duaan"] = {
"bilangan",
"bilangan duaan",
{"d", "du"},
110022,
}
tags["jamak"] = {
"bilangan",
"bilangan jamak",
{"p", "pl"},
146786,
}
tags["milikan tunggal"] = {
"bilangan",
"bilangan mufrad",
"spos",
110786, -- Singular
}
tags["milikan berbilang"] = {
"bilangan",
"bilangan jamak",
"mpos",
146786, -- Plural
}
shortcuts["1s"] = {"1", "s"}
shortcuts["2s"] = {"2", "s"}
shortcuts["3s"] = {"3", "s"}
shortcuts["1d"] = {"1", "d"}
shortcuts["2d"] = {"2", "d"}
shortcuts["3d"] = {"3", "d"}
shortcuts["1p"] = {"1", "p"}
shortcuts["2p"] = {"2", "p"}
shortcuts["3p"] = {"3", "p"}
----------------------- Genus -----------------------
tags["maskulin"] = {
"genus",
"genus",
"m",
499327,
}
-- Ini berguna contohnya dalam bahasa Sweden.
tags["maskulin semula jadi"] = {
"genus",
"genus",
"natm",
}
tags["feminin"] = {
"genus",
"genus",
"f",
1775415,
}
tags["neuter"] = {
"genus",
"genus",
"n",
1775461,
}
tags["am"] = {
"genus",
"genus",
"c",
1305037,
}
tags["bukan kelelakian"] = {
"genus",
APPENDIX,
"nv",
}
shortcuts["mf"] = "m//f"
shortcuts["mn"] = "m//n"
shortcuts["fn"] = "f//n"
shortcuts["mfn"] = "m//f//n"
----------------------- Kebernyawaan -----------------------
-- (may be useful sometimes for [[Module:object usage]].)
tags["bernyawa"] = {
"kebernyawaan",
APPENDIX,
"an",
51927507,
}
tags["tidak bernyawa"] = {
"kebernyawaan",
APPENDIX,
{"in", "inan"},
51927539,
}
tags["peribadi"] = {
"kebernyawaan",
nil,
{"pr", "pers"},
63302102,
}
----------------------- Kala/aspek -----------------------
tags["kini"] = {
"tense-aspect",
"kala kini",
"pres",
192613,
}
tags["lampau"] = {
"kala-aspek",
"kala lampau",
nil,
1994301,
}
tags["depan"] = {
"kala-aspek",
"kala depan",
{"fut", "futr"},
501405,
}
tags["depan sempurna"] = {
"kala-aspek",
APPENDIX,
{"futp", "fperf"},
1234617,
}
tags["bukan lampau"] = {
"kala-aspek",
"kala bukan lampau",
"npast",
16916993,
}
tags["progresif"] = {
"kala-aspek",
APPENDIX,
"prog",
56653945,
}
tags["preterit"] = {
"kala-aspek",
APPENDIX,
"pret",
442485,
}
tags["sempurna"] = {
"kala-aspek",
APPENDIX,
"perf",
625420,
}
tags["tak sempurna lampau"] = {
"kala-aspek",
APPENDIX,
{"impf", "imperf"},
}
tags["sempurna lampau"] = {
"kala-aspek",
APPENDIX,
{"plup", "pluperf"},
623742,
}
tags["aorist"] = {
"kala-aspek",
"kala aorist",
{"aor", "aori"},
216497,
}
tags["lampau bersejarah"] = {
"kala-aspek",
nil,
"phis",
442485, -- Preterite
}
tags["tak sempurna berterusan"] = {
"kala-aspek",
APPENDIX,
{"impfv", "imperfv"},
371427,
}
tags["sempurna berterusan"] = {
"kala-aspek",
APPENDIX,
{"pfv", "perfv"},
1424306,
}
shortcuts["spast"] = {"selapis", "lampau"}
shortcuts["lampau selapis"] = {"selapis", "lampau"}
shortcuts["spres"] = {"selapis", "kini"}
shortcuts["kini selapis"] = {"selapis", "kini"}
----------------------- Modus -----------------------
tags["imperatif"] = {
"modus",
"modus imperatif",
{"imp", "impr", "impv"},
22716,
}
tags["penyata"] = {
"modus",
"modus penyata",
{"ind", "indc", "indic"},
682111,
}
tags["sembawa"] = {
"modus",
"modus sembawa",
{"sub", "subj"},
473746,
}
tags["bersyarat"] = {
"modus",
"modus bersyarat",
"cond",
625581,
}
tags["harapan"] = {
"modus",
"w:keharapanan (linguistik)",
"mod",
1243600,
}
tags["suruh"] = {
"modus",
"modus suruh",
{"opta", "opt"},
527205,
}
tags["arahan"] = {
"modus",
"modus arahan",
"juss",
462367,
}
tags["galakan"] = {
"modus",
WP,
"hort",
5906629,
}
----------------------- Ragam/valensi -----------------------
-- This tag type combines what is normally called "voice" (active, passive, middle, mediopassive) with other tags that
-- aren't normally called voice but are similar in that they control the valence/valency (number and structure of the
-- arguments of a verb).
tags["aktif"] = {
"ragam-valensi",
"ragam aktif",
{"act", "actv"},
1317831,
}
tags["tengah"] = {
"ragam-valensi",
"ragam tengah",
{"mid", "midl"},
}
tags["pasif"] = {
"ragam-valensi",
"ragam pasif",
{"pass", "pasv"},
1194697,
}
tags["pasif tengah"] = {
"ragam-valensi",
APPENDIX,
{"mp", "mpass", "mpasv", "mpsv"},
1601545,
}
tags["refleksif"] = {
"ragam-valensi",
APPENDIX,
"refl",
13475484, -- for "reflexive verb"
}
tags["transitif"] = {
"ragam-valensi",
"kata kerja transitif",
{"tr", "vt"},
1774805, -- for "transitive verb"
}
tags["tidak transitif"] = {
"ragam-valensi",
"kata kerja tidak transitif",
{"intr", "vi"},
Q1166153, -- for "intransitive verb"
}
tags["dwitransitif"] = {
"ragam-valensi",
"kata kerja dwitransitif",
"ditr",
Q2328313, -- for "ditransitive verb"
}
tags["kausatif"] = {
"ragam-valensi",
APPENDIX,
"caus",
56677011, -- for "causative verb"
}
----------------------- Bukan finit -----------------------
tags["infinitif"] = {
"bukan finit",
APPENDIX,
"inf",
179230,
}
-- A form found in Portuguese and Galician, as well as in Hungarian. This is probably unnecessary and can be replaced
-- with the regular "infinitive" tag. A personal infinitive is not a separate infinitive from the plain infinitive, just
-- an inflection of the infinitive.
tags["infinitif peribadi"] = {
"bukan finit",
"w:Konjugasi kata kerja bahasa Portugis",
"pinf",
}
tags["partisipel"] = {
"bukan finit",
APPENDIX,
{"part", "ptcp"},
814722,
}
tags["kata nama kerjaan"] = {
"bukan finit",
APPENDIX,
"vnoun",
1350145,
}
tags["gerund"] = {
"bukan finit",
APPENDIX,
"ger",
1923028,
}
tags["supinum"] = {
"bukan finit",
APPENDIX,
"sup",
548470,
}
tags["transgresif"] = {
"bukan finit",
APPENDIX,
nil,
904896,
}
----------------------- Kasus -----------------------
tags["ablatif"] = {
"kasus",
"kasus ablatif",
"abl",
156986,
}
tags["akusatif"] = {
"kasus",
"kasus akusatif",
"acc",
146078,
}
tags["datif"] = {
"kasus",
"kasus datif",
"dat",
145599,
}
tags["genitif"] = {
"kasus",
"kasus genitif",
"gen",
146233,
}
tags["perantian"] = {
"kasus",
"kasus perantian",
"ins",
192997,
}
tags["lokatif"] = {
"kasus",
"kasus lokatif",
"loc",
202142,
}
tags["nominatif"] = {
"kasus",
"kasus nominatif",
"nom",
131105,
}
tags["kata depan"] = {
"kasus",
"kasus kata depan",
{"pre", "prep"},
2114906,
}
tags["vokatif"] = {
"kasus",
"kasus vokatif",
"voc",
185077,
}
----------------------- Keadaan -----------------------
tags["binaan"] = {
"keadaan",
"keadaan binaan",
{"cons", "keadaan binaan"},
1641446,
display = "keadaan binaan",
}
tags["pasti"] = {
"keadaan",
APPENDIX,
{"def", "defn", "definite state"},
53997851,
}
tags["tidak pasti"] = {
"keadaan",
APPENDIX,
{"indef", "indf", "indefinite state"},
53997857,
}
tags["posesif"] = {
"keadaan",
WP,
"poss",
2105891,
}
tags["kuat"] = {
"keadaan",
"tidak pasti",
"str",
53997857, -- Indefinite
}
tags["lemah"] = {
"keadaan",
"pasti",
"wk",
53997851, -- Definite
}
tags["campuran"] = {
"keadaan",
APPENDIX,
"mix",
63302161,
}
tags["atribut"] = {
"keadaan",
APPENDIX,
"attr",
}
tags["predikat"] = {
"keadaan",
APPENDIX,
"pred",
}
----------------------- Darjah perbandingan -----------------------
tags["perbandingan positive"] = {
"perbandingan",
"positive",
{"posd", "positive"},
3482678, -- Tidak wujud dalam bahasa Inggeris; hanya dalam bahasa Czech, Estonia, Finland dan pelbagai bahasa Nordik.
}
tags["darjah perbandingan"] = {
"perbandingan",
"perbandingan",
{"comd", "comparative"},
14169499,
}
tags["darjah penghabisan"] = {
"perbandingan",
"penghabisan",
{"supd", "superlative"},
1817208,
}
----------------------- Laras bahasa -----------------------
----------------------- Deiksis -----------------------
----------------------- Klusiviti -----------------------
----------------------- Golongan fleksi -----------------------
tags["kata ganti"] = {
"class",
WIKT,
"pron",
12721180, -- for "pronominal attribute", existing only in the Romanian Wikipedia
}
----------------------- Sikap -----------------------
-- This is a vague tag type grouping augmentative, diminutive and pejorative, which generally indicate the speaker's
-- attitude towards the object in question (as well as often indicating size).
tags["agam"] = {
"sikap",
APPENDIX,
"aug",
1358239,
}
tags["diminutif"] = {
"sikap",
APPENDIX,
"dim",
108709,
}
tags["pejoratif"] = {
"sikap",
APPENDIX,
"pej",
545779,
}
----------------------- Perubahan bunyi -----------------------
tags["terkecut"] = {
"perubahan bunyi",
nil,
"contr",
126473,
}
tags["tidak terkecut"] = {
"perubahan bunyi",
nil,
"uncontr",
}
----------------------- Misc grammar -----------------------
shortcuts["past-cl"] = {"lampau", "-", "kala", "klausa"}
shortcuts["pres-cl"] = {"pres", "-", "kala", "klausa"}
shortcuts["fut-cl"] = {"fut", "-", "kala", "klausa"}
shortcuts["ind-cl"] = {"ind", "klausa"}
shortcuts["sub-cl"] = {"sub", "klausa"}
shortcuts["past-sub-cl"] = {"lampau", "sub", "klausa"}
shortcuts["pres-sub-cl"] = {"pres", "sub", "klausa"}
shortcuts["fut-sub-cl"] = {"fut", "sub", "klausa"}
shortcuts["cond-cl"] = {"cond", "klausa"}
shortcuts["cond-past-cl"] = {"cond", "lampau", "klausa"}
tags["selapis"] = {
"tatabahasa",
nil,
"sim",
}
tags["singkat"] = {
"tatabahasa",
}
tags["panjang"] = {
"tatabahasa",
}
tags["bentuk"] = {
"tatabahasa",
}
tags["beradjektif"] = {
"tatabahasa",
WIKT,
"adj",
}
tags["beradverba"] = {
"tatabahasa",
APPENDIX,
"adv",
}
tags["negatif"] = {
"tatabahasa",
"w:affirmation and negation",
"neg",
63302088,
}
tags["ternominal"] = {
"tatabahasa",
nil,
"nomz",
4683152, -- entry for "nominalized adjective"
}
tags["penominalan"] = {
"tatabahasa",
nil,
"nomzn",
1500667,
}
tags["akar"] = {
"tatabahasa",
nil,
nil,
111029,
}
tags["dasar"] = {
"tatabahasa",
nil,
nil,
210523,
}
tags["bersandar"] = {
"tatabahasa",
nil,
"dep",
1122094, -- entry for "dependent clause"
}
tags["tak bersandar"] = {
"tatabahasa",
nil,
"indep",
1419215, -- entry for "independent clause"
}
tags["subjek"] = {
"tatabahasa",
APPENDIX,
"sbj", -- sub and subj used for subjunctive
164573,
}
tags["objek"] = {
"tatabahasa",
APPENDIX,
"obj",
175026,
}
tags["objek langsung"] = {
"tatabahasa",
APPENDIX,
"dirobj",
2990574,
}
tags["objek tidak langsung"] = {
"tatabahasa",
APPENDIX,
"indirobj",
1094061,
}
tags["kala"] = {
"tatabahasa",
APPENDIX,
nil,
177691,
}
tags["klausa"] = {
"tatabahasa",
APPENDIX,
nil,
117364,
}
tags["frasa"] = {
"tatabahasa",
APPENDIX,
nil,
187931,
}
----------------------- Tag lain -----------------------
-- This consists of non-content words like "and" as well as punctuation characters. If the punctuation characters appear
-- by themselves as tags, we special-case the handling of surrounding spaces so the output looks correct.
tags["dan"] = {
"lain",
}
-- HACK! "in" is a shortcut for "inanimate" so create "!in" to display "in". We should generalize this like for labels.
tags["!in"] = {
"lain",
display = "in",
}
tags[","] = {
"lain",
no_space_on_left = true,
}
tags[":"] = {
"lain",
no_space_on_left = true,
}
tags["/"] = {
"lain",
no_space_on_left = true,
no_space_on_right = true,
}
tags["("] = {
"lain",
no_space_on_right = true,
}
tags[")"] = {
"lain",
no_space_on_left = true,
}
tags["["] = {
"lain",
no_space_on_right = true,
}
tags["]"] = {
"lain",
no_space_on_left = true,
}
tags["-"] = { -- regular hyphen-minus
"lain",
no_space_on_left = true,
no_space_on_right = true,
}
----------------------- Create the shortcuts list -----------------------
m_form_of.finalize_tag_data(tags, shortcuts)
return {tags = tags, shortcuts = shortcuts}
