48,406
edits
No edit summary |
No edit summary |
||
| Line 854: | Line 854: | ||
} | } | ||
]=] | ]=] | ||
local | local u = require("Module:string/char") | ||
data[1] = { | data[1] = { | ||
| Line 1,773: | Line 1,773: | ||
["k͡ʟ̝̊ʼ"] = {title = "velar lateral ejective affricate", link = "w:Velar lateral ejective affricate"}, | ["k͡ʟ̝̊ʼ"] = {title = "velar lateral ejective affricate", link = "w:Velar lateral ejective affricate"}, | ||
["ᶢʘ͡kxʼ"] = {title = "voiced labial linguo-glottalic affricate", link = "w:Ejective-contour clicks"}, | ["ᶢʘ͡kxʼ"] = {title = "voiced labial linguo-glottalic affricate", link = "w:Ejective-contour clicks"}, | ||
} | |||
data.separator_escapes = { | |||
["⁽"] = "(", ["⁾"] = ")", | |||
["₍"] = "(", ["₎"] = ")", | |||
["ˈ"] = "\1", ["ˌ"] = "\2", | |||
["ː"] = ":", ["ˑ"] = ";", | |||
} | } | ||
-- acute and grave tone marks | -- acute and grave tone marks | ||
local diacritics = u( | |||
-- grave, acute, circumflex, tilde, macron, breve | -- grave, acute, circumflex, tilde, macron, breve | ||
0x300, 0x301, 0x302, 0x303, 0x304, 0x306, | 0x300, 0x301, 0x302, 0x303, 0x304, 0x306, | ||
| Line 1,799: | Line 1,806: | ||
-- macron–acute, grave–macron, macron–grave, acute–macron, grave–acute–grave, acute–grave–acute | -- macron–acute, grave–macron, macron–grave, acute–macron, grave–acute–grave, acute–grave–acute | ||
0x1DC4, 0x1DC5, 0x1DC6, 0x1DC7, 0x1DC8, 0x1DC9) | 0x1DC4, 0x1DC5, 0x1DC6, 0x1DC7, 0x1DC8, 0x1DC9) | ||
data.diacritics = diacritics | |||
data.tones = | |||
data. | data.vowels = "iyɨʉɯuɪᵻʏʊᵿeøɘɵɤoəɚɛœɜɝɞʌɔæɐaɶɑɒäëïöüÿ" | ||
data.superscripts = | |||
data.valid = | local tones = "˥˦˧˨˩꜒꜓꜔꜕꜖꜈꜉꜊꜋꜌꜍꜎꜏꜐꜑¹²³⁴⁵⁶⁷⁸⁹⁰" | ||
data.tones = tones | |||
.. | |||
.. | local superscripts = u(0xA0) .. " ⁰¹²³⁴⁵⁶⁷⁸⁹ᵃ𐞃ᵄᵅᶛᵇ𐞄𐞅ᶜᶝᵈᶞ𐞋𐞌𐞍ᵉᵊᵋ𐞎ᶟᵌ𐞏𐞑ᶠᶢ𐞒𐞓𐞔ˠʰ𐞕𐞖ʱ𐞗ⁱᶦᶤʲᶨᶡ𐞘ᵏˡᶫꭞ𐞛ᶩ𐞞𐞠𐞡ᵐᶬⁿᶰᶮᶯᵑᵒ𐞢ꟹ𐞣ᵓᶱᵖᶲ𐞥ʳ𐞪ʴ𐞦𐞧ʵ𐞨𐞩ʶˢᶳᶴᵗ𐞯ᵘᶶᶣᵚᶭᶷᵛᶹ𐞰ᶺʷꭩˣʸ𐞲ᶻᶼᶽᶾˀˤ𐞳𐞴𐞶𐞷𐞸𐞹𐞵ᵝᶿᵡ˞⁻𐞁𐞂" | ||
data.superscripts = superscripts | |||
-- An array of patterns of valid character sequences. | |||
data.valid = { | |||
"⁽[" .. superscripts .. "]+⁾", | |||
"[ %(%)%%<>{|}%-→~⁓%.◌abcdefhijklmnopqrstuvwxyz¡àáâãāăēäæçèéêëĕěħìíîïĩīĭĺḿǹńňðòóôõöōŏőœøŕùúûüũūŭűýÿŷŋ" | |||
.. "ǀǁǂǃǎǐǒǔřǖǘǚǜǟǣǽǿȁȅȉȍȕȫȭȳɐɑɒɓɔɕɖɗɘəɚɛɜɝɞɟɠɡɢɣɤɥɦɧɨɪᵻɫɬɭɮɯɰɱɲɳɴɵɶɸɹɺ𝼈ɻɽɾʀʁʂʃʄʈʉʊᵿʋṽʌʍʎ𝼆ʏʐʑʒʔʕʘʞʙʛʜʝʟʡʢ𝼊ʬʭ" | |||
.. "ʼˈˌːˑˣ˔˕ˬ͗˭ˇ˖β͜θχᴙᶑ᷽ḁḛḭḯṍṏṳṵṹṻạẹẽịọụỳỵỹ‖․‥…‿↑↓↗↘ⱱꜛꜜꟸ𝆏𝆑˗ˋˊ–⸨⸩⁽⁾" .. diacritics .. tones .. superscripts .. "]+" | |||
} | |||
-- Character sequences which are valid only in a particular language. | |||
-- These can be either a single pattern (as a string), or an array of patterns (as a table). | |||
data.per_lang_valid = { | data.per_lang_valid = { | ||
["egy"] = "V", -- V for uncertain vowel | ["egy"] = "V+", -- V for uncertain vowel | ||
["okm"] = "[LHR!WT]+", -- irregular verb morphophonemes | |||
} | } | ||
| Line 1,946: | Line 1,965: | ||
["ᶐ"] = "ɑ˞", | ["ᶐ"] = "ɑ˞", | ||
["ᶒ"] = "e˞", | ["ᶒ"] = "e˞", | ||
["ə˞"] = "ɚ", | |||
["ᶕ"] = "ɚ", | ["ᶕ"] = "ɚ", | ||
["ᶓ"] = "ɛ˞", | ["ᶓ"] = "ɛ˞", | ||
["ɜ˞"] = "ɝ", | |||
["ᶔ"] = "ɝ", | ["ᶔ"] = "ɝ", | ||
["ᶖ"] = "i˞", | ["ᶖ"] = "i˞", | ||
| Line 2,004: | Line 2,025: | ||
["᫇"] = "ʷ", | ["᫇"] = "ʷ", | ||
["⸋"] = "̚", | ["⸋"] = "̚", | ||
["̱"] = "̠", -- COMBINING MACRON BELOW (U+0331) -> COMBINING MINUS SIGN BELOW (U+0320) | |||
-- Precomposed characters with deprecated or confusable diacritics; the left is a precomposed | |||
-- version of a lowercase letter with COMBINING MACRON BELOW and the right is the equivalent | |||
-- using COMBINING MINUS SIGN BELOW | |||
["ḇ"] = "b̠", | |||
["ḏ"] = "d̠", | |||
["ẖ"] = "h̠", | |||
["ḵ"] = "k̠", | |||
["ḻ"] = "l̠", | |||
["ṉ"] = "n̠", | |||
["ṟ"] = "r̠", | |||
["ṯ"] = "t̠", | |||
["ẕ"] = "z̠", | |||
} | } | ||
return data | return data | ||