local labels = {}
local raw_categories = {}
local handlers = {}
-----------------------------------------------------------------------------
-- --
-- LABELS --
-- --
-----------------------------------------------------------------------------
labels["ศัพท์แบ่งตามประเภทไวยากรณ์"] = {
description = "{{{langname}}} terms categorized by their grammatical category.",
umbrella_parents = "มูลฐาน",
parents = {{name = "{{{langcat}}}", raw = true}},
}
labels["terms by grammatical category"] = labels["ศัพท์แบ่งตามประเภทไวยากรณ์"]
------- GENDER -------
for _, pos in ipairs { "คำนาม", "คำวิสามานยนาม", "คำสรรพนาม", "ปัจจัย" } do
labels[pos .. "แบ่งตามเพศ"] = {
description = "{{{langname}}} " .. pos .. " organized by the gender they belong to.",
breadcrumb = "แบ่งตามเพศ",
parents = {{name = pos, sort = "เพศ"}},
}
labels[pos .. " with irregular gender"] = {
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[pos .. "ที่มีหลายเพศ"] = {
description = "{{{langname}}} " .. pos .. " that belong to more than one gender.",
breadcrumb = "มีหลายเพศ",
parents = {{name = pos .. "แบ่งตามเพศ", sort = "หลายเพศ"}},
}
labels[pos .. "เพศรวม"] = {
description = "{{{langname}}} " .. pos .. " of [[Appendix:Glossary#common gender|common gender]], i.e. belonging to a gender category that combines the function of [[Appendix:Glossary#masculine|masculine]] and [[Appendix:Glossary#feminine|feminine]] and is opposed to the [[Appendix:Glossary#neuter|neuter]] gender.",
breadcrumb = "เพศรวม",
parents = {pos .. "แบ่งตามเพศ"},
}
labels[pos .. "เพศหญิง"] = {
description = "{{{langname}}} " .. pos .. " of [[Appendix:Glossary#feminine|feminine]] gender, i.e. belonging to a gender category that contains (among other things) female beings.",
breadcrumb = "เพศหญิง",
parents = {pos .. "แบ่งตามเพศ"},
}
labels[pos .. "เพศชาย"] = {
description = "{{{langname}}} " .. pos .. " of [[Appendix:Glossary#masculine|masculine]] gender, i.e. belonging to a gender category that contains (among other things) male beings.",
breadcrumb = "เพศชาย",
parents = {pos .. "แบ่งตามเพศ"},
}
labels[pos .. "ที่เพศขึ้นอยู่กับความหมาย"] = {
description = "{{{langname}}} " .. pos .. " that may be either [[Appendix:Glossary#masculine|masculine]] or [[Appendix:Glossary#feminine|feminine]] depending on whether they refer to male or female beings.",
breadcrumb = "เพศขึ้นอยู่กับความหมาย",
parents = {pos .. "แบ่งตามเพศ"},
}
labels[pos .. "เพศกลาง"] = {
description = "{{{langname}}} " .. pos .. " of [[Appendix:Glossary#neuter|neuter]] gender, i.e. belonging to a gender category that does not usually contain male or female beings.",
breadcrumb = "เพศกลาง",
parents = {pos .. "แบ่งตามเพศ"},
}
end
------- NOUN CLASSES -------
labels["คำนามแบ่งตามคลาส"] = {
description = "{{{langname}}} nouns organized by the class they belong to.",
breadcrumb = "แบ่งตามคลาส",
parents = {{name = "คำนาม", sort = "คลาส"}},
}
------- ANIMACY -------
for _, pos in ipairs({"คำนาม", "ปัจจัย", "คำกริยา"}) do
labels[pos .. "มีชีวิต"] = {
description = "{{{langname}}} " .. pos .. " that refer to humans or animals.",
breadcrumb = "มีชีวิต",
parents = {pos},
}
labels[pos .. "ไม่มีชีวิต"] = {
description = "{{{langname}}} " .. pos .. " that refer to inanimate objects (not humans or animals).",
breadcrumb = "ไม่มีชีวิต",
parents = {pos},
}
labels[pos .. "ที่มีหลายชีวิตภาพ"] = {
description = "{{{langname}}} " .. pos .. " that belong to more than one animacy.",
breadcrumb = "มีหลายชีวิตภาพ",
parents = {{name = pos, sort = "หลายชีวิตภาพ"}},
}
end
for _, pos in ipairs({"คำนาม", "ปัจจัย"}) do
-- This category should be used particularly in languages that have
-- grammatical distinctions related to animals, such as Ukrainian.
labels[pos .. "สัตว์"] = {
description = "{{{langname}}} " .. pos .. " that refer to animals.",
breadcrumb = "สัตว์",
parents = {pos .. "มีชีวิต"},
}
-- This category should be used particularly in languages that have
-- grammatical distinctions related to men, such as Polish.
labels["nonvirile " .. pos] = {
description = "{{{langname}}} plural " .. pos .. " that refer to a group without male humans.",
breadcrumb = "nonvirile",
parents = {pos, "พหูพจน์เท่านั้น"},
}
labels[pos .. "บุคคล"] = {
description = "{{{langname}}} " .. pos .. " that refer to humans.",
breadcrumb = "บุคคล",
parents = {pos .. "มีชีวิต"},
}
-- This category should be used particularly in languages that have
-- grammatical distinctions related to men, such as Polish.
labels["virile " .. pos] = {
description = "{{{langname}}} plural " .. pos .. " that refer to a group with at least one male human.",
breadcrumb = "virile",
parents = {pos, "พหูพจน์เท่านั้น"},
}
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 = {
"คำคุณศัพท์",
"คำกริยาวิเศษณ์",
"คำบ่งชี้",
"คำนาม",
"เลข",
"พาร์ทิซิเพิล",
"คำสรรพนาม",
"คำวิสามานยนาม",
"ปัจจัย",
"คำกริยา",
}
for _, pos in ipairs(inflected_poses) do
labels[pos .. "แบ่งตามชนิดการผันรูป"] = {
description = "{{{langname}}} " .. pos .. " organized by the type of inflection they follow.",
breadcrumb = "แบ่งตามชนิดการผันรูป",
parents = {{name = pos, sort = "การผันรูป"}},
}
labels["irregular " .. pos] = {
description = "{{{langname}}} " .. pos .. " that follow non-standard patterns of inflection.",
breadcrumb = "irregular",
parents = {pos .. "แบ่งตามชนิดการผันรูป"},
}
labels["defective " .. pos] = {
description = "{{{langname}}} " .. pos .. " that lack one or more forms in their inflections.",
breadcrumb = "defective",
parents = {pos, "irregular " .. pos},
}
labels["suppletive " .. pos] = {
description = "{{{langname}}} " .. pos .. " that have inflected forms from different roots.",
breadcrumb = "suppletive",
parents = {"irregular " .. pos},
}
if pos ~= "คำกริยา" and pos ~= "คำกริยาวิเศษณ์" then
labels[pos .. "ผันรูปไม่ได้"] = {
description = "{{{langname}}} " .. pos .. " that do not display additional grammatical relations by means of declension.",
breadcrumb = "ผันรูปไม่ได้",
parents = {pos .. "แบ่งตามชนิดการผันรูป"},
}
labels[pos .. "ที่มีการผันรูปหลายแบบ"] = {
description = "{{{langname}}} " .. pos .. " that follow more than one type of inflection.",
breadcrumb = "มีการผันรูปหลายแบบ",
parents = {{name = pos .. "แบ่งตามชนิดการผันรูป", sort = "การผันรูปหลายแบบ"}},
}
labels[pos .. "ที่มีหลายพหูพจน์"] = {
description = "{{{langname}}} " .. pos .. " that have more than one possible plural (sometimes with distinct meanings).",
breadcrumb = "มีหลายพหูพจน์",
parents = {{name = pos .. "แบ่งตามชนิดการผันรูป", sort = "พหูพจน์"}},
}
end
labels[pos .. " by tone"] = {
description = "{{{langname}}} " .. pos .. " organized by the tone they follow.",
breadcrumb = "by tone",
parents = {{name = pos .. "แบ่งตามชนิดการผันรูป", sort = "tone"}},
}
labels[pos .. " by vowel harmony"] = {
description = "{{{langname}}} " .. pos .. " organized by the vowel harmony they follow.",
breadcrumb = "by vowel harmony",
parents = {{name = pos .. "แบ่งตามชนิดการผันรูป", sort = "vowel harmony"}},
}
end
-- FIXME: Only used currently for Arabic; probably should be removed as a general category.
labels["irregular elative adjectives"] = {
description = "{{{langname}}} elative adjectives that follow non-standard patterns of inflection.",
parents = {"คำคุณศัพท์แบ่งตามชนิดการผันรูป"},
}
for _, pos in ipairs { "คำนาม", "คำวิสามานยนาม", "คำสรรพนาม" } do
labels[pos .. " with unattested plurals"] = {
description = "{{{langname}}} " .. pos .. " with unattested plurals.",
breadcrumb = "with unattested plurals",
parents = {{name = pos, sort = "unattested plurals"}},
}
labels[pos .. "ชี้เฉพาะ"] = {
description = "{{{langname}}} " .. pos .. " that are inherently definite and have definite concord.",
breadcrumb = "ชี้เฉพาะ",
parents = {pos .. "แบ่งตามชนิดการผันรูป"},
}
end
------- GERMANIC VERB CLASSES -------
-- FIXME: Not clear this belongs among the general categories.
labels["คำกริยาแข็ง"] = {
description = "{{{langname}}} verbs that present different stem vowels in their typically regular conjugated forms.",
breadcrumb = "แข็ง",
parents = {"คำกริยาแบ่งตามชนิดการผันรูป"},
}
labels["strong verbs"] = labels["คำกริยาแข็ง"]
labels["คำกริยาอ่อน"] = {
description = "{{{langname}}} verbs that display dental suffixes in their past tense conjugated forms.",
breadcrumb = "อ่อน",
parents = {"คำกริยาแบ่งตามชนิดการผันรูป"},
}
labels["weak verbs"] = labels["คำกริยาอ่อน"]
labels["preterite-present verbs"] = {
description = "{{{langname}}} verbs that inflect in the present tense like the past tense of strong verbs.",
breadcrumb = "preterite-present",
parents = {"คำกริยาแบ่งตามชนิดการผันรูป"},
}
labels["คำกริยาแข็งคลาส 1"] = {
description = "Verbs where the [[ablaut]] vowel was followed by ''-y-'' in Proto-Indo-European.",
breadcrumb = "คลาส 1",
parents = {{name = "คำกริยาแข็ง", sort = "1"}},
}
labels["class 1 strong verbs"] = labels["คำกริยาแข็งคลาส 1"]
labels["คำกริยาอ่อนคลาส 1"] = {
description = "Weak verbs of the first class.",
breadcrumb = "คลาส 1",
parents = {{name = "คำกริยาอ่อน", sort = "1"}},
}
labels["class 1 weak verbs"] = labels["คำกริยาอ่อนคลาส 1"]
labels["คำกริยาแข็งคลาส 2"] = {
description = "Verbs where the [[ablaut]] vowel was followed by ''-w-'' in Proto-Indo-European.",
breadcrumb = "คลาส 2",
parents = {{name = "คำกริยาแข็ง", sort = "2"}},
}
labels["class 2 strong verbs"] = labels["คำกริยาแข็งคลาส 2"]
labels["คำกริยาแข็งคลาส 2a"] = {
description = "Verbs where the [[ablaut]] vowel was *eu in Proto-Germanic.",
breadcrumb = "คลาส 2a",
parents = {{name = "คำกริยาแข็งคลาส 2", sort = "1"}},
}
labels["class 2a strong verbs"] = labels["คำกริยาแข็งคลาส 2a"]
labels["คำกริยาแข็งคลาส 2b"] = {
description = "Verbs where the [[ablaut]] vowel was *ū in Proto-Germanic.",
breadcrumb = "คลาส 2b",
parents = {{name = "คำกริยาแข็งคลาส 2", sort = "2"}},
}
labels["class 2b strong verbs"] = labels["คำกริยาแข็งคลาส 2b"]
labels["คำกริยาอ่อนคลาส 2"] = {
description = "Weak verbs of the second class.",
breadcrumb = "คลาส 2",
parents = {{name = "คำกริยาอ่อน", sort = "2"}},
}
labels["class 2 weak verbs"] = labels["คำกริยาอ่อนคลาส 2"]
labels["คำกริยาอ่อนคลาส 3"] = {
description = "Weak verbs of the third class.",
breadcrumb = "คลาส 3",
parents = {{name = "คำกริยาอ่อน", sort = "3"}},
}
labels["class 3 weak verbs"] = labels["คำกริยาอ่อนคลาส 3"]
labels["คำกริยาแข็งคลาส 3"] = {
description = "Verbs where the [[ablaut]] vowel was followed by a [[consonant cluster]] in Proto-Indo-European.",
breadcrumb = "คลาส 3",
parents = {{name = "คำกริยาแข็ง", sort = "3"}},
}
labels["class 3 strong verbs"] = labels["คำกริยาแข็งคลาส 3"]
labels["คำกริยาแข็งคลาส 3a"] = {
description = "Verbs where the [[consonant cluster]] begins with a nasal consonant.",
breadcrumb = "คลาส 3a",
parents = {{name = "คำกริยาแข็งคลาส 3", sort = "1"}},
}
labels["class 3a strong verbs"] = labels["คำกริยาแข็งคลาส 3a"]
labels["คำกริยาแข็งคลาส 3b"] = {
description = "Verbs where the [[consonant cluster]] begins with a lateral consonant or velar fricative.",
breadcrumb = "คลาส 3b",
parents = {{name = "คำกริยาแข็งคลาส 3", sort = "2"}},
}
labels["class 3b strong verbs"] = labels["คำกริยาแข็งคลาส 3b"]
labels["คำกริยาแข็งคลาส 3c"] = {
description = "Verbs where the [[consonant cluster]] begins with a rhotic consonant.",
breadcrumb = "คลาส 3c",
parents = {{name = "คำกริยาแข็งคลาส 3", sort = "3"}},
}
labels["class 3c strong verbs"] = labels["คำกริยาแข็งคลาส 3c"]
labels["คำกริยาแข็งคลาส 4"] = {
description = "Verbs where the [[ablaut]] vowel was followed by a [[sonorant]] (''m'', ''n'', ''l'', ''r'') but no other consonant in Proto-Indo-European.",
breadcrumb = "คลาส 4",
parents = {{name = "คำกริยาแข็ง", sort = "4"}},
}
labels["class 4 strong verbs"] = labels["คำกริยาแข็งคลาส 4"]
labels["คำกริยาอ่อนคลาส 4"] = {
description = "Weak verbs of the fourth class.",
breadcrumb = "คลาส 4",
parents = {{name = "คำกริยาอ่อน", sort = "4"}},
}
labels["class 4 weak verbs"] = labels["คำกริยาอ่อนคลาส 4"]
labels["คำกริยาแข็งคลาส 5"] = {
description = "Verbs where the [[ablaut]] vowel was followed by [[consonant]] other than a [[sonorant]] in Proto-Indo-European.",
breadcrumb = "คลาส 5",
parents = {{name = "คำกริยาแข็ง", sort = "5"}},
}
labels["class 5 strong verbs"] = labels["คำกริยาแข็งคลาส 5"]
labels["คำกริยาแข็งคลาส 6"] = {
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 = "คลาส 6",
parents = {{name = "คำกริยาแข็ง", sort = "6"}},
}
labels["class 6 strong verbs"] = labels["คำกริยาแข็งคลาส 6"]
labels["คำกริยาแข็งคลาส 7"] = {
description = "Verbs that retained their reduplication in the past tense in Proto-Germanic.",
breadcrumb = "คลาส 7",
parents = {{name = "คำกริยาแข็ง", sort = "7"}},
}
labels["class 7 strong verbs"] = labels["คำกริยาแข็งคลาส 7"]
labels["คำกริยาแข็งคลาส 7a"] = {
description = "Class 7 strong verbs where the root vowel was ''*ai'' in Proto-Germanic, analogous to class 1.",
breadcrumb = "คลาส 7a",
parents = {{name = "คำกริยาแข็งคลาส 7", sort = "a"}},
}
labels["class 7a strong verbs"] = labels["คำกริยาแข็งคลาส 7a"]
labels["คำกริยาแข็งคลาส 7b"] = {
description = "Class 7 strong verbs where the root vowel was ''*au'' in Proto-Germanic, analogous to class 2.",
breadcrumb = "คลาส 7b",
parents = {{name = "คำกริยาแข็งคลาส 7", sort = "b"}},
}
labels["class 7b strong verbs"] = labels["คำกริยาแข็งคลาส 7b"]
labels["คำกริยาแข็งคลาส 7c"] = {
description = "Class 7 strong verbs where the root vowel was ''*a'' followed by a [[consonant cluster]] in Proto-Germanic, analogous to class 3.",
breadcrumb = "คลาส 7c",
parents = {{name = "คำกริยาแข็งคลาส 7", sort = "c"}},
}
labels["class 7c strong verbs"] = labels["คำกริยาแข็งคลาส 7c"]
labels["คำกริยาแข็งคลาส 7d"] = {
description = "Class 7 strong verbs where the root vowel was ''*ē'' in Proto-Germanic.",
breadcrumb = "คลาส 7d",
parents = {{name = "คำกริยาแข็งคลาส 7", sort = "d"}},
}
labels["class 7d strong verbs"] = labels["คำกริยาแข็งคลาส 7d"]
labels["คำกริยาแข็งคลาส 7e"] = {
description = "Class 7 strong verbs where the root vowel was ''*ō'' in Proto-Germanic.",
breadcrumb = "คลาส 7e",
parents = {{name = "คำกริยาแข็งคลาส 7", sort = "e"}},
}
labels["class 7e strong verbs"] = labels["คำกริยาแข็งคลาส 7e"]
local labels2 = {}
-- Add 'umbrella_parents' key if not already present.
for key, data in pairs(labels) do
labels2[key] = data
if not data.umbrella_parents then
data.umbrella_parents = "หมวดหมู่ย่อยของศัพท์แบ่งตามประเภทไวยากรณ์แบ่งตามภาษา"
end
end
-----------------------------------------------------------------------------
-- --
-- RAW CATEGORIES --
-- --
-----------------------------------------------------------------------------
raw_categories["หมวดหมู่ย่อยของศัพท์แบ่งตามประเภทไวยากรณ์แบ่งตามภาษา"] = {
description = "Umbrella categories covering topics related to grammatical categories, such as gender, animacy and noun and verb classes.",
additional = "{{{umbrella_meta_msg}}}",
parents = {
"หมวดหมู่ใหญ่รวมหัวข้อ",
{name = "ศัพท์แบ่งตามประเภทไวยากรณ์", is_label = true, sort = " "},
},
}
-----------------------------------------------------------------------------
-- --
-- HANDLERS --
-- --
-----------------------------------------------------------------------------
table.insert(handlers, function(data)
local class = data.label:match("^คำนามคลาส ([0-9a-z]+)$")
if class then
local classnum, suffix = class:match("^([0-9]+)([a-z]*)$")
return {
description =
"{{{langname}}} nouns that belong to class " .. class .. ".",
breadcrumb = class,
umbrella = false,
parents = {{
name = "คำนามแบ่งตามคลาส",
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("^(คำนาม)ที่ใช้คำลักษณนาม (.+)$")
if pos then
local linktext
if data.lang then
if data.lang:getCode() == "zh" then
linktext = require("Module:zh/link").link(nil, true, { classifier, tr = "-" }, classifier)
else
linktext = require("Module:links").full_link({ term = classifier, lang = data.lang }, "term")
end
else
linktext = classifier
end
return {
description = "{{{langname}}} " .. pos .. " using " .. linktext .. " as their classifier.",
breadcrumb = classifier,
umbrella = false,
parents = {{
name = pos .. "แบ่งตามคำลักษณนาม",
sort = data.lang and data.lang:getCode() == "zh" and require("Module:Hani-sortkey").makeSortKey(classifier) or classifier,
}},
}
end
end)
return {LABELS = labels2, RAW_CATEGORIES = raw_categories, HANDLERS = handlers}
