local export = {}
local gsub = mw.ustring.gsub
local find = mw.ustring.find
local match = mw.ustring.match
local en_utilities = require("Module:en-utilities")
local thai_digits = {"๐", "๑", "๒", "๓", "๔", "๕", "๖", "๗", "๘", "๙"}
local thai_words = {"ศูนย์", "หนึ่ง", "สอง", "สาม", "สี่", "ห้า", "หก", "เจ็ด", "แปด", "เก้า"}
local thai_words2 = {["."]="จุด",["-"]="ขีด",["+"]="บวก",["−"]="ลบ",["/"]="ทับ"}
-- from [[Module:headword/data]]
local thai_pos = {
-- these are lemmas
["abbreviations"] = "คำย่อ",
["acronyms"] = "อักษรอ่านย่อ",
["adjectives"] = "คำคุณศัพท์",
--["adnominals"] = "adnominals",
--["adpositions"] = "adpositions",
["adverbs"] = "คำกริยาวิเศษณ์",
["affixes"] = "หน่วยคำเติม",
--["ambipositions"] = "ambipositions",
["articles"] = "คำกำกับนาม",
["circumfixes"] = "หน่วยคำเติมคร่อม",
--["circumpositions"] = "circumpositions",
["classifiers"] = "คำลักษณนาม",
["cmavo"] = "ชมาโว",
--["cmavo clusters"] = "cmavo clusters",
["cmene"] = "ชเมเน",
--["combining forms"] = "combining forms",
["conjunctions"] = "คำสันธาน",
--["counters"] = "counters",
["determiners"] = "คำกำหนด",
--["diacritical marks"] = "diacritical marks",
["digraphs"] = "ทวิอักษร",
--["equative adjectives"] = "equative adjectives",
["fu'ivla"] = "ฟูฮิฝลา",
["gismu"] = "กิสมู",
["Han characters"] = "อักษรจีน",
["Han tu"] = "ฮั้นถื่อ",
["hanja"] = "ฮันจา",
["hanzi"] = "ฮั่นจื้อ",
--["ideophones"] = "ideophones",
["idioms"] = "สำนวน",
["infixes"] = "อาคม",
["initialisms"] = "อักษรย่อ",
["iteration marks"] = "เครื่องหมายซ้ำ",
["interfixes"] = "หน่วยคำเติมเชื่อม",
["interjections"] = "คำอุทาน",
["kana"] = "คานะ",
["kanji"] = "คันจิ",
["letters"] = "ตัวอักษร",
["ligatures"] = "ตัวอักษรควบ",
--["logograms"] = "logograms",
["lujvo"] = "ลุฌโว",
["morae"] = "มอรา",
["morphemes"] = "หน่วยคำ",
--["non-constituents"] = "non-constituents",
["nouns"] = "คำนาม",
["numbers"] = "จำนวน",
["numeral symbols"] = "ตัวเลข",
["numerals"] = "เลข",
["particles"] = "คำอนุภาค",
["phrases"] = "วลี",
["postpositions"] = "คำปัจฉบท",
--["postpositional phrases"] = "postpositional phrases",
--["predicatives"] = "predicatives",
["prefixes"] = "อุปสรรค",
--["prepositional phrases"] = "prepositional phrases",
["prepositions"] = "คำบุพบท",
["preverbs"] = "คำกริยาเติมหน้า",
--["pronominal adverbs"] = "pronominal adverbs",
["pronouns"] = "คำสรรพนาม",
["proper nouns"] = "คำวิสามานยนาม",
["proverbs"] = "สุภาษิต",
["punctuation marks"] = "เครื่องหมายวรรคตอน",
--["relatives"] = "relatives",
["roots"] = "ราก",
["stems"] = "ต้นเค้าศัพท์",
["suffixes"] = "ปัจจัย",
["syllables"] = "พยางค์",
["symbols"] = "สัญลักษณ์",
["verbs"] = "คำกริยา",
-- these are non-lemmas
["active participle forms"] = "รูปผันพาร์ทิซิเพิลกรรตุวาจก",
["active participles"] = "พาร์ทิซิเพิลกรรตุวาจก",
["adjectival participles"] = "พาร์ทิซิเพิลเชิงคุณศัพท์",
--["adjective case forms"] = "adjective case forms",
["adjective forms"] = "รูปผันคำคุณศัพท์",
--["adjective feminine forms"] = "adjective feminine forms",
["adjective plural forms"] = "รูปผันคำคุณศัพท์พหูพจน์",
["adverb forms"] = "รูปผันคำกริยาวิเศษณ์",
["adverbial participles"] = "พาร์ทิซิเพิลเชิงกริยาวิเศษณ์",
--["agent participles"] = "agent participles",
["article forms"] = "รูปผันคำกำกับนาม",
--["circumfix forms"] = "circumfix forms",
--["combined forms"] = "combined forms",
["comparative adjective forms"] = "รูปผันคำคุณศัพท์ขั้นกว่า",
["comparative adjectives"] = "คำคุณศัพท์ขั้นกว่า",
["comparative adverb forms"] = "รูปผันคำกริยาวิเศษณ์ขั้นกว่า",
["comparative adverbs"] = "คำกริยาวิเศษณ์ขั้นกว่า",
["conjunction forms"] = "รูปผันคำสันธาน",
["contractions"] = "คำหดย่อ",
--["converbs"] = "converbs",
["determiner comparative forms"] = "รูปผันคำกำหนดขั้นกว่า",
["determiner forms"] = "รูปผันคำกำหนด",
["determiner superlative forms"] = "รูปผันคำกำหนดขั้นสุด",
["diminutive nouns"] = "คำนามบอกความเล็ก",
--["elative adjectives"] = "elative adjectives",
--["equative adjective forms"] = "equative adjective forms",
--["equative adjectives"] = "equative adjectives",
["future participles"] = "พาร์ทิซิเพิลอนาคตกาล",
--["gerunds"] = "gerunds",
--["infinitive forms"] = "infinitive forms",
--["infinitives"] = "infinitives",
["interjection forms"] = "รูปผันคำอุทาน",
["jyutping"] = "ยฺหวืดเพ็ง",
--["misspellings"] = "misspellings",
--["negative participles"] = "negative participles",
--["nominal participles"] = "nominal participles",
--["noun case forms"] = "noun case forms",
["noun dual forms"] = "รูปผันคำนามทวิพจน์",
["noun forms"] = "รูปผันคำนาม",
--["noun paucal forms"] = "noun paucal forms",
["noun plural forms"] = "รูปผันคำนามพหูพจน์",
--["noun possessive forms"] = "noun possessive forms",
--["noun singulative forms"] = "noun singulative forms",
["numeral forms"] = "รูปผันเลข",
["participles"] = "พาร์ทิซิเพิล",
["participle forms"] = "รูปผันพาร์ทิซิเพิล",
["particle forms"] = "รูปผันคำอนุภาค",
["passive participles"] = "พาร์ทิซิเพิลกรรมวาจก",
["past active participles"] = "พาร์ทิซิเพิลกรรตุวาจกอดีตกาล",
["past participles"] = "พาร์ทิซิเพิลอดีตกาล",
["past participle forms"] = "รูปผันพาร์ทิซิเพิลอดีตกาล",
["past passive participles"] = "พาร์ทิซิเพิลกรรมวาจกอดีตกาล",
--["perfect active participles"] = "perfect active participles",
--["perfect participles"] = "perfect participles",
--["perfect passive participles"] = "perfect passive participles",
["pinyin"] = "พินอิน",
["plurals"] = "พหูพจน์",
["postposition forms"] = "รูปผันคำปัจฉบท",
["prefix forms"] = "รูปผันอุปสรรค",
--["preposition contractions"] = "preposition contractions",
["preposition forms"] = "รูปผันคำบุพบท",
--["prepositional pronouns"] = "prepositional pronouns",
["present active participles"] = "พาร์ทิซิเพิลกรรตุวาจกปัจจุบันกาล",
["present participles"] = "พาร์ทิซิเพิลปัจจุบันกาล",
["present passive participles"] = "พาร์ทิซิเพิลกรรมวาจกปัจจุบันกาล",
["pronoun forms"] = "รูปผันคำสรรพนาม",
--["pronoun possessive forms"] = "pronoun possessive forms",
["proper noun forms"] = "รูปผันคำวิสามานยนาม",
["proper noun plural forms"] = "รูปผันคำวิสามานยนามพหูพจน์",
["rafsi"] = "รัฟซี",
["romanizations"] = "การถอดเป็นอักษรโรมัน",
--["root forms"] = "root forms",
--["singulatives"] = "singulatives",
["suffix forms"] = "รูปผันปัจจัย",
["superlative adjective forms"] = "รูปผันคำคุณศัพท์ขั้นสุด",
["superlative adjectives"] = "คำคุณศัพท์ขั้นสุด",
["superlative adverb forms"] = "รูปผันคำกริยาวิเศษณ์ขั้นสุด",
["superlative adverbs"] = "คำกริยาวิเศษณ์ขั้นสุด",
["verb forms"] = "รูปผันคำกริยา",
["verbal nouns"] = "คำกริยานาม",
-- these are something else
["cardinal nouns"] = "คำนามเชิงการนับ",
["abstract nouns"] = "คำอาการนาม",
["auxiliary verbs"] = "คำกริยานุเคราะห์",
["cardinal adjectives"] = "คำคุณศัพท์เชิงการนับ",
}
function export.th_pos(pos)
return thai_pos[pos] or thai_pos[en_utilities.pluralize(pos)] or pos
end
function export.arabic_digit_to_thai(text)
if type(text) == "number" then
text = tostring(text) -- convert to string
end
if type(text) == "string" and find(text, "[0-9]") then
for n = 0, 9 do
text = gsub(text, tostring(n), thai_digits[n + 1])
end
end
return text
end
function export.thai_digit_to_arabic(text)
if type(text) == "string" and find(text, "[๐-๙]") then
for n = 0, 9 do
text = gsub(text, thai_digits[n + 1], tostring(n))
end
end
return text
end
function export.thai_number_sequence(text)
if type(text) == "number" then
text = tostring(text) -- convert to string
end
if type(text) == "string" then
text = export.thai_digit_to_arabic(text)
for n = 0, 9 do
text = gsub(text, tostring(n), thai_words[n + 1])
end
text = gsub(text, ".", thai_words2)
end
return text
end
--([\-+]?)([0-9,]*)((\.[0-9]+)?)
function export.thai_number_integer(text)
if type(text) == "number" then
text = tostring(text) -- convert to string
end
if type(text) == "string" and match(text, "^[-%+−]?[0-9๐-๙,]+$") then
text = export.thai_digit_to_arabic(text)
text = gsub(text, ",", "")
local len = text:len() -- now only Arabic digits
--TODO
end
return text
end
function export.thai_number_float(text)
if type(text) == "number" then
-- floating-point may be not accurate due to binary system
text = tostring(text) -- convert to string
end
if type(text) == "string" then
--TODO
end
return text
end
return export
