local u = require("Module:string utilities").char
local data = {}
data.phonetic_extraction = {
["th"] = "Module:th",
["km"] = "Module:km",
}
data.ignored_prefixes = {
["cat"] = true,
["category"] = true,
["file"] = true,
["image"] = true
}
data.pos_tags = {
["a"] = "形容詞",
["adv"] = "副詞",
["int"] = "感嘆詞",
["n"] = "名詞",
["pron"] = "代詞",
["v"] = "動詞",
["vi"] = "不及物動詞",
["vt"] = "及物動詞",
["vti"] = "及物和不及物動詞",
}
-- Scheme for using unsupported characters in titles.
data.unsupported_characters = {
["#"] = "`num`",
["%"] = "`percnt`", -- only escaped in percent encoding
["&"] = "`amp`", -- only escaped in HTML entities
["."] = "`period`", -- only escaped in dot-slash notation
["<"] = "`lt`",
[">"] = "`gt`",
["["] = "`lsqb`",
["]"] = "`rsqb`",
["_"] = "`lowbar`",
["`"] = "`grave`", -- used to enclose unsupported characters in the scheme, so a raw use in an unsupported title must be escaped to prevent interference
["{"] = "`lcub`",
["|"] = "`vert`",
["}"] = "`rcub`",
["~"] = "`tilde`", -- only escaped when 3 or more are consecutive
["\239\191\189"] = "`repl`" -- replacement character U+FFFD, which can't be typed directly here due to an abuse filter
}
-- Manually specified unsupported titles. Only put titles here if there is a different reason why they are unsupported, and not just because they contain one of the unsupported characters above.
data.unsupported_titles = {
[" "] = "Space",
["&"] = "`amp`amp;",
["λοπαδοτεμαχοσελαχογαλεοκρανιολειψανοδριμυποτριμματοσιλφιοκαραβομελιτοκατακεχυμενοκιχλεπικοσσυφοφαττοπεριστεραλεκτρυονοπτοκεφαλλιοκιγκλοπελειολαγῳοσιραιοβαφητραγανοπτερύγων"] = "Ancient Greek dish",
["กรุงเทพมหานคร อมรรัตนโกสินทร์ มหินทรายุธยา มหาดิลกภพ นพรัตนราชธานีบูรีรมย์ อุดมราชนิเวศน์มหาสถาน อมรพิมานอวตารสถิต สักกะทัตติยวิษณุกรรมประสิทธิ์"] = "Thai name of Bangkok",
[u(0x1680)] = "Ogham space",
[u(0x3000)] = "Ideographic space"
}
return data
