local U = require("Module:string/char")
local gmatch = mw.ustring.gmatch
local data = {
-- not in official X-SAMPA; from http://www.kneequickie.com/kq/Z-SAMPA
["b\\"] = { "ⱱ" },
["b_<"] = { "ɓ" },
["d`"] = { "ɖ", has_descender = true },
["d_<"] = { "ɗ" },
-- not in official X-SAMPA; Wikipedia-specific
["d`_<"] = { "ᶑ", has_descender = true },
["g"] = { "ɡ", has_descender = true },
["g_<"] = { "ɠ", has_descender = true },
["h\\"] = { "ɦ" },
["j\\"] = { "ʝ", has_descender = true },
["l`"] = { "ɭ", has_descender = true },
["l\\"] = { "ɺ" },
["n`"] = { "ɳ", has_descender = true },
["p\\"] = { "ɸ", has_descender = true },
["r`"] = { "ɽ", has_descender = true },
["r\\"] = { "ɹ" },
["r\\`"] = { "ɻ", has_descender = true },
["s`"] = { "ʂ", has_descender = true },
["s\\"] = { "ɕ" },
["t`"] = { "ʈ" },
["v\\"] = { "ʋ" },
["x\\"] = { "ɧ", has_descender = true },
["z`"] = { "ʐ", has_descender = true },
["z\\"] = { "ʑ" },
["A"] = { "ɑ" },
["B"] = { "β", has_descender = true },
["B\\"] = { "ʙ" },
["C"] = { "ç", has_descender = true },
["D"] = { "ð" },
["E"] = { "ɛ" },
["F"] = { "ɱ", has_descender = true },
["G"] = { "ɣ", has_descender = true },
["G\\"] = { "ɢ" },
["G\\_<"] = { "ʛ" },
["H"] = { "ɥ", has_descender = true },
["H\\"] = { "ʜ" },
["I"] = { "ɪ" },
["I\\"] = { "ɪ̈" },
["J"] = { "ɲ", has_descender = true },
["J\\"] = { "ɟ" },
["J\\_<"] = { "ʄ", has_descender = true },
["K"] = { "ɬ" },
["K\\"] = { "ɮ", has_descender = true },
["L"] = { "ʎ" },
["L\\"] = { "ʟ" },
["M"] = { "ɯ" },
["M\\"] = { "ɰ", has_descender = true },
["N"] = { "ŋ", has_descender = true },
["N\\"] = { "ɴ" },
["O"] = { "ɔ" },
["O\\"] = { "ʘ" },
["P"] = { "ʋ" },
["Q"] = { "ɒ" },
["R"] = { "ʁ" },
["R\\"] = { "ʀ" },
["S"] = { "ʃ", has_descender = true },
["T"] = { "θ" },
["U"] = { "ʊ" },
["U\\"] = { "ʊ̈" },
["V"] = { "ʌ" },
["W"] = { "ʍ" },
["X"] = { "χ", has_descender = true },
["X\\"] = { "ħ" },
["Y"] = { "ʏ" },
["Z"] = { "ʒ", has_descender = true },
["\""] = { "ˈ" },
["%"] = { "ˌ" },
-- not in official X-SAMPA; from http://www.kneequickie.com/kq/Z-SAMPA
["%\\"] = { "ᴙ" },
["'"] = { "ʲ", is_diacritic = true },
[":"] = { "ː", is_diacritic = true },
[":\\"] = { "ˑ", is_diacritic = true },
["@"] = { "ə" },
["@`"] = { "ɚ" },
["@\\"] = { "ɘ" },
["{"] = { "æ" },
["}"] = { "ʉ" },
["1"] = { "ɨ" },
["2"] = { "ø" },
["3"] = { "ɜ" },
["3`"] = { "ɝ" },
["3\\"] = { "ɞ" },
["4"] = { "ɾ" },
["5"] = { "ɫ" },
["6"] = { "ɐ" },
["7"] = { "ɤ" },
["8"] = { "ɵ" },
["9"] = { "œ" },
["&"] = { "ɶ" },
["?"] = { "ʔ" },
["?\\"] = { "ʕ" },
["<\\"] = { "ʢ" },
[">\\"] = { "ʡ" },
["^"] = { "ꜛ" },
["!"] = { "ꜜ" },
-- not in official X-SAMPA
["!!"] = { "‼" },
["!\\"] = { "ǃ" },
["|\\"] = { "ǀ", has_descender = true },
["||"] = { "‖", has_descender = true },
["|\\|\\"] = { "ǁ", has_descender = true },
["=\\"] = { "ǂ", has_descender = true },
-- linking mark, liaison
["-\\"] = { "‿", is_diacritic = true },
-- coarticulated; not in official X-SAMPA
["__"] = { U(0x361) },
-- fortis, strong articulation; not in official X-SAMPA
["_:"] = { U(0x348) },
["_\""] = { U(0x308), is_diacritic = true },
-- advanced
["_+"] = { U(0x31F), with_descender = "˖", is_diacritic = true },
-- retracted
["_-"] = { U(0x320), with_descender = "˗", is_diacritic = true },
-- rising tone
["_/"] = { U(0x30C), is_diacritic = true },
-- voiceless
["_0"] = { U(0x325), with_descender = U(0x30A), is_diacritic = true },
-- syllabic
["="] = { U(0x329), with_descender = U(0x30D), is_diacritic = true },
-- syllabic
["_="] = { U(0x329), with_descender = U(0x30D), is_diacritic = true },
-- strident: not in official X-SAMPA; from http://www.kneequickie.com/kq/Z-SAMPA
["_%\\"] = { U(0x1DFD) },
-- ejective
["_>"] = { "ʼ", is_diacritic = true },
-- pharyngealized
["_?\\"] = { "ˤ", is_diacritic = true },
-- falling tone
["_\\"] = { U(0x302), is_diacritic = true },
-- non-syllabic
["_^"] = { U(0x32F), is_diacritic = true },
-- no audible release
["_}"] = { U(0x31A), is_diacritic = true },
-- r-coloring (colouring), rhotacization
["`"] = { U(0x2DE), is_diacritic = true },
-- nasalization
["~"] = { U(0x303), is_diacritic = true },
-- advanced tongue root
["_A"] = { U(0x318), is_diacritic = true },
-- apical
["_a"] = { U(0x33A), is_diacritic = true },
-- extra-low tone
["_B"] = { U(0x30F), is_diacritic = true },
-- low rising tone
["_B_L"] = { U(0x1DC5), is_diacritic = true },
-- less rounded
["_c"] = { U(0x31C), is_diacritic = true },
-- dental
["_d"] = { U(0x32A), is_diacritic = true },
-- velarized or pharyngealized (dark)
["_e"] = { U(0x334), is_diacritic = true },
-- downstep
["<F>"] = { "↘" },
-- falling tone
["_F"] = { U(0x302), is_diacritic = true },
-- velarized
["_G"] = { "ˠ", is_diacritic = true },
-- high tone
["_H"] = { U(0x301), is_diacritic = true },
-- high rising tone
["_H_T"] = { U(0x1DC4), is_diacritic = true },
-- aspiration
["_h"] = { "ʰ", is_diacritic = true },
-- voiced aspiration (= breathy voice)
["_h\\"] = { "ʱ", is_diacritic = true },
-- palatalization
["_j"] = { "ʲ", is_diacritic = true },
-- creaky voice, laryngealization, vocal fry
["_k"] = { U(0x330), is_diacritic = true },
-- low tone
["_L"] = { U(0x300), is_diacritic = true },
-- lateral release
["_l"] = { "ˡ", is_diacritic = true },
-- mid tone
["_M"] = { U(0x304), is_diacritic = true },
-- laminal
["_m"] = { U(0x33B), is_diacritic = true },
-- linguolabial
["_N"] = { U(0x33C), is_diacritic = true },
-- nasal release
["_n"] = { "ⁿ", is_diacritic = true },
-- more rounded
["_O"] = { U(0x339), is_diacritic = true },
-- lowered
["_o"] = { U(0x31E), with_descender = "˕", is_diacritic = true },
-- retracted tongue root
["_q"] = { U(0x319), is_diacritic = true },
-- global rise
["<R>"] = { "↗" },
-- rising tone
["_R"] = { U(0x30C), is_diacritic = true },
-- rising falling tone
["_R_F"] = { U(0x1DC8), is_diacritic = true },
-- raised
["_r"] = { U(0x31D), is_diacritic = true },
-- extra-high tone
["_T"] = { U(0x30B), is_diacritic = true },
-- breathy voice, murmured voice, murmur, whispery voice
["_t"] = { U(0x324), is_diacritic = true },
-- voiced
["_v"] = { U(0x32C), is_diacritic = true },
-- labialized
["_w"] = { "ʷ", is_diacritic = true },
-- extra-short
["_X"] = { U(0x306), is_diacritic = true },
-- mid-centralized
["_x"] = { U(0x33D), is_diacritic = true },
["__T"] = { "˥" },
["__H"] = { "˦" },
["__M"] = { "˧" },
["__L"] = { "˨" },
["__B"] = { "˩" },
-- not X-SAMPA; for convenience
["0"] = { "◌" }, -- dotted circle
}
local identical = "acehklmnorstuvwxz"
for char in gmatch(identical, ".") do
data[char] = { char }
end
local identical_with_descender = "jpqy"
for char in gmatch(identical_with_descender, ".") do
data[char] = { char, has_descender = true }
end
return data
