Linguifex

Module:headword/data: Difference between revisions

← Older edit
No edit summary
No edit summary
 
(One intermediate revision by the same user not shown)
Line 23: Line 23:
"pinyin",
"pinyin",
"rafsi",
"rafsi",
"romaji",
}, function(_, item)
}, function(item)
return item
return item
end)
end)


-- Irregular non-zero plurals AND any regular plurals where the singular ends in "s",
-- Irregular non-zero plurals AND any regular plurals where the singular ends in "s",
-- because the module assumes that inputs ending in "s" are plurals.
-- because the module assumes that inputs ending in "s" are plurals. The singular and
for k, v in next, {
-- plural both need to be added, as the module will generate a default plural if
-- the input doesn't match a key in this table.
for sg, pl in next, {
mora = "morae"
mora = "morae"
} do
} do
irregular_plurals[k] = v
irregular_plurals[sg], irregular_plurals[pl] = pl, pl
irregular_plurals[v] = v -- Ensures singular and plural inputs work as expected.
end
end


data.invariable = irregular_plurals -- To be removed.
data.irregular_plurals = irregular_plurals
data.irregular_plurals = irregular_plurals


Line 150: Line 149:
"nominal participles",
"nominal participles",
"noun case forms",
"noun case forms",
"noun construct forms",
"noun dual forms",
"noun dual forms",
"noun forms",
"noun forms",
Line 162: Line 162:
"passive participles",
"passive participles",
"past active participles",
"past active participles",
"past adverbial participles",
"past participles",
"past participles",
"past participle forms",
"past participle forms",
Line 176: Line 177:
"prepositional pronouns",
"prepositional pronouns",
"present active participles",
"present active participles",
"present adverbial participles",
"present participles",
"present participles",
"present passive participles",
"present passive participles",
"preverb forms",
"pronoun forms",
"pronoun forms",
"pronoun possessive forms",
"pronoun possessive forms",
Line 413: Line 416:
"fi", -- Finnish; hyphen used to separate components in compound words if the final and initial vowels match, respectively
"fi", -- Finnish; hyphen used to separate components in compound words if the final and initial vowels match, respectively
"hil", -- Hiligaynon; hyphens for mid-word glottal stops
"hil", -- Hiligaynon; hyphens for mid-word glottal stops
"hnn", -- Hanunoo; too many false positives
"ilo", -- Ilocano; hyphens for mid-word glottal stops
"ilo", -- Ilocano; hyphens for mid-word glottal stops
"kne", -- Kankanaey; hyphens for mid-word glottal stops
"kne", -- Kankanaey; hyphens for mid-word glottal stops
Line 437: Line 441:
"bbc",
"bbc",
"bug",
"bug",
"cdo",
"cia",
"cia",
"cjm",
"cjm",
"cjy",
"cmn",
"cmn",
"cnp",
"cpi",
"cpi",
"cpx",
"csp",
"czh",
"czo",
"gan",
"hak",
"hak",
"hnm",
"hsn",
"ja",
"ja",
"kzg",
"kzg",
"lad",
"lad",
"ltc",
"luh",
"lzh",
"lzh",
"mnp",
"ms",
"ms",
"mul",
"mul",
"mvi",
"mvi",
"nan",
"nan",
"nan-dat",
"nan-hbl",
"nan-hbl",
"nan-hnm",
"nan-hlh",
"nan-luh",
"nan-lnx",
"nan-tws",
"nan-tws",
"nan-zhe",
"nan-zsh",
"och",
"oj",
"oj",
"okn",
"okn",
Line 460: Line 481:
"ryu",
"ryu",
"sh",
"sh",
"sjc",
"tgt",
"tgt",
"th",
"th",
Line 467: Line 489:
"und",
"und",
"vi",
"vi",
"wuu",
"xug",
"xug",
"yoi",
"yoi",
Line 473: Line 496:
"za",
"za",
"zh",
"zh",
"zhx-sic",
"zhx-tai",
}
}


Line 656: Line 681:
adv = "adverb",
adv = "adverb",
art = "article",
art = "article",
aug = "augmentative",
det = "determiner",
det = "determiner",
cnum = "cardinal number",
dim = "diminutive",
compadj = "comparative adjective",
compadv = "comparative adverb",
conj = "conjunction",
conj = "conjunction",
contr = "contraction",
conv = "converb",
conv = "converb",
int = "interjection",
int = "interjection",
Line 664: Line 693:
intj = "interjection",
intj = "interjection",
n = "noun",
n = "noun",
-- the next two support Algonquian languages; see also vii/vai/vti/vta below
na = "animate noun",
ni = "inanimate noun",
num = "numeral",
num = "numeral",
part = "participle",
part = "participle",
Line 670: Line 702:
pn = "proper noun",
pn = "proper noun",
postp = "postposition",
postp = "postposition",
pre = "preposition",
pref = "prefix",
prep = "preposition",
prep = "preposition",
pro = "pronoun",
prepphr = "prepositional phrase",
pron = "pronoun",
pron = "pronoun",
prop = "proper noun",
prop = "proper noun",
proper = "proper noun",
proper = "proper noun",
onum = "ordinal number",
propn = "proper noun",
rom = "romanization",
suf = "suffix",
supadj = "superlative adjective",
supadv = "superlative adverb",
sym = "symbol",
v = "verb",
v = "verb",
vb = "verb",
vb = "verb",
vi = "intransitive verb",
vi = "intransitive verb",
vt = "transitive verb",
vt = "transitive verb",
vti = "transitive and intransitive verb",
-- the next four support Algonquian languages
vii = "inanimate intransitive verb",
vai = "animate intransitive verb",
vti = "transitive inanimate verb",
vta = "transitive animate verb",
}
}


Line 692: Line 733:
-- We include verbs because impf and pf are valid "genders".
-- We include verbs because impf and pf are valid "genders".
["verbs"] = "verbs",
["verbs"] = "verbs",
}
-- Lower limit for a "long" word in a particular language.
-- Used to categorize terms into e.g. [[:Category:Long English words]] automatically.
-- Languages with no mapping here do not get categorized.
data.long_word_thresholds = {
    ["af"] = 20,
    ["bg"] = 20,
    ["cy"] = 25,
    ["de"] = 20,
    ["en"] = 25,
    ["es"] = 20,
    ["fr"] = 20,
    ["ka"] = 20,
    ["sv"] = 20,
    ["tl"] = 25,
}
}


Retrieved from "https://linguifex.com/wiki/Module:headword/data"