模組:Sandbox/Al12si/zz/Date validation
模組解[開]| 你可能想去為呢個Scribunto module開一個解版。 編者可以響呢個模組嘅沙盤 (開 | 鏡)同埋試例 (開)版度試驗佢。 請加個類到個/doc嘅細版度。 呢個模組嘅細版。 |
-- vim: set sw=4 ts=4 ai sm :
---- 粵拼轉耶魯模組
----
---- Perl 原碼 2021年 原作者 [[User:Al12si]]
---- Lua 模組 2023年 翻譯 [[User:Al12si]]
----
---- 原程式唔會好小心咁解析粵拼，只係求其解析（用最少心機做到 project 就算，原碼只係做校對用嘅架生仔），
---- 所以模組解析粵拼都好求其，如果輸入唔係粵拼，輸出係 ｢未定義｣⸺即係可能係亂碼、垃圾、錯嘢等等
require ('strict');
local p = {};
local use_dotted_i_p = false;
local use_macrons_p = true;
if true then
local z = require('模組:書名');
p.cvs = z.cvs;
end
local function interpret_boolean( s )
return s:match('^%s*true%s*$')
or s:match('^%s*yes%s*$')
or s:match('^%s*0*1%s*$');
end
local function make_hangul_yam( s, adj )
if not adj then
adj = 0;
end
adj = adj + 0.2;
return '<span style="position:relative"><span style="position:absolute;display:inline-block;margin-top:' .. adj .. 'em">'
.. s .. '</span>';
end
local function make_hangul_yoeng( s, adj )
if not adj then
adj = 0;
end
adj = -1.2 - adj;
return '<span style="position:relative"><span style="position:absolute;display:inline-block;margin-top:' .. adj .. 'em">'
.. s .. '</span>';
end
local mappings;
local tone_mappings = {
['hangul'] = {
-- FIXME: can't understand the description, doing own thing based on description in PowerPoint
-- PowerPoint says originally, ˊsœŋ was represented by 2 dots (on left of hangul), ˉhœy by 1 dot
-- need way to distinguish between 2,3 and 5,6 so 2,3 will go below and 4,5,6 will go below
['prefix'] = {
'',
make_hangul_yam(' ̤'), -- two dots below (U+2004 [1/3 em space], U+324)
make_hangul_yam(' ̣'), -- one dot below (U+2004, U+323)
make_hangul_yoeng('｡', -0.2), -- ring above ("zero dots", like the Arabic system)
make_hangul_yoeng(' ̤'), -- two dots above
make_hangul_yoeng(' ̣'), -- one dot above
};
['suffix'] = {
'',
'</span>',
'</span>',
'</span>',
'</span>',
'</span>',
};
};
['ipa_phonemic'] = {
['prefix'] = { 'ˈ', 'ˇ', 'ˉ', 'ˌ', 'ˬ', 'ˍ' };
};
['ipa_phonetic'] = {
['suffix'] = { '˥', '˧˥', '˧', '˩', '˨˧', '˨' };
};
['pinyin_1960'] = {
['suffix'] = { '1', '2', '3', '4', '5', '6' };
};
['pinyin_1980'] = {
['suffix'] = { '1', '2', '3', '4', '5', '6' };
};
['zhuyin_1931'] = {
['suffix'] = { '', 'ˇ', 'ˋ', 'ˊ', '˘', 'ˆ', '˙', '', 'ʻ' };
};
['zhuyin_1932'] = {
['suffix'] = { '', 'ˇ', 'ˋ', 'ˊ', '˘', 'ˆ', '˙', '', 'ʻ' };
};
['zhuyin_1950'] = {
['suffix'] = { '', 'ˇ', 'ˋ', 'ˊ', '˘', 'ˆ', '˙', '', 'ʻ' };
};
};
tone_mappings.hangul_tswong = tone_mappings.hangul;
tone_mappings.hangul_sykim = tone_mappings.hangul;
tone_mappings.hangul_test = tone_mappings.hangul;
local schemes = {
['諺文'] = 'hangul';
['國際'] = 'ipa';
['萬國'] = 'ipa';
['拼音'] = 'pinyin';
['耶魯'] = 'yale';
['注音'] = 'zhuyin';
['黃錫凌'] = 'ipa_phonemic';
['黃錫凌式'] = 'ipa_phonemic';
['國際音標'] = 'ipa';
['萬國音標'] = 'ipa';
['粵語諺文'] = 'hangul';
['廣州拼音'] = 'pinyin';
['注音符號'] = 'zhuyin';
['粵語注音'] = 'zhuyin';
['廣州話拼音'] = 'pinyin';
['粵語注音符號'] = 'zhuyin';
['bopomofo'] = 'zhuyin';
['bpmf'] = 'zhuyin';
['hangeul'] = 'hangul';
['hangul'] = 'hangul';
['ipa'] = 'ipa';
['pinyin'] = 'pinyin';
['yale'] = 'yale';
['zhuyin'] = 'zhuyin';
};
local variants = {
['hangul'] = {
['金昔研'] = 'sykim';
['黃得森'] = 'tswong';
['sykim'] = 'sykim';
['test'] = 'test';
['tswong'] = 'tswong';
};
['ipa'] = {
['寛式'] = 'phonemic';
['寬式'] = 'phonemic';
['嚴式'] = 'phonetic';
['黃錫凌'] = 'phonemic';
['黃錫凌式'] = 'phonemic';
['phonemic'] = 'phonemic';
['phonetic'] = 'phonetic';
};
['pinyin'] = {
['1960'] = '1960';
['1980'] = '1980';
};
['zhuyin'] = {
['民國'] = '1932';
['中共'] = '1950';
['人民'] = '1950';
['趙雅庭'] = '1931';
['1931'] = '1931';
['1932'] = '1932';
['1950'] = '1950';
['1952'] = '1950'; -- source: [[廣州話拼音方案]]
};
};
local default_variants = {
['hangul'] = 'tswong';
['ipa'] = 'phonemic';
['pinyin'] = '1980';
['zhuyin'] = '1932';
};
local C1 = {
[''] = mw.ustring.char(0x110b);
['ʾ'] = mw.ustring.char(0x1159);
['bb'] = mw.ustring.char(0x1108);
['f'] = mw.ustring.char(0x1157); -- per [[:en:Hangul]], f is 112b or 1157, but not composable so unusable
['w'] = mw.ustring.char(0x111d); -- per [[:en:Hangul]]
['y'] = mw.ustring.char(0x1147); -- per [[:en:Hangul]]
};
local C2 = {
['l'] = mw.ustring.char(0x11af); -- think of ł = /w/
['m'] = mw.ustring.char(0x11b7);
['n'] = mw.ustring.char(0x11ab);
['ng'] = mw.ustring.char(0x11bc);
['b'] = mw.ustring.char(0x1107);
['d'] = mw.ustring.char(0x1103);
['g'] = mw.ustring.char(0x11a8); -- think of Ger g > Eng y... I'm out of ideas
['p'] = mw.ustring.char(0x11c1);
['t'] = mw.ustring.char(0x11c0);
['k'] = mw.ustring.char(0x11bf);
['j'] = mw.ustring.char(0x11bd);
['z'] = mw.ustring.char(0x11eb);
['lb'] = mw.ustring.char(0x11b2);
['lg'] = mw.ustring.char(0x11b0);
['lh'] = mw.ustring.char(0x11b6);
['ll'] = mw.ustring.char(0x11d0);
['lm'] = mw.ustring.char(0x11b1);
['ln'] = mw.ustring.char(0x11cd);
['lp'] = mw.ustring.char(0x11b5);
['lt'] = mw.ustring.char(0x11b4);
['nc'] = mw.ustring.char(0xd7cc);
['ngs'] = mw.ustring.char(0x11f1);
['nj'] = mw.ustring.char(0x11ac);
['ns'] = mw.ustring.char(0x11c7);
['s'] = mw.ustring.char(0x11ba);
['sk'] = mw.ustring.char(0x11e7);
['sm'] = mw.ustring.char(0xd7ea);
['sp'] = mw.ustring.char(0x11ea);
['st'] = mw.ustring.char(0x11e8);
};
local V = {
['aa'] = mw.ustring.char(0x1161);
['aai'] = mw.ustring.char(0x1162);
['ə'] = mw.ustring.char(0x119e);
['ae'] = mw.ustring.char(0x1162); -- per [[:en:Hangul]], this is /ɛ/
['e'] = mw.ustring.char(0x1166);
['əi'] = mw.ustring.char(0x11a1);
['ei'] = mw.ustring.char(0x1164); -- per [[:en:Hangul]], this is /e/
['eo'] = mw.ustring.char(0x1165);
['eo_u'] = mw.ustring.char(0x117b);
['eu'] = mw.ustring.char(0x1173);
['i'] = mw.ustring.char(0x1175);
['o'] = mw.ustring.char(0x1169);
['oi'] = mw.ustring.char(0x116c); -- called oe; per [[:en:Hangul]], this should be /œ/, which doesn't work
['u'] = mw.ustring.char(0x116e);
['waa'] = mw.ustring.char(0x116a);
['waai'] = mw.ustring.char(0x118A);
['wai'] = '(WAI)';
['wa'] = mw.ustring.char(0x118A);
['wae'] = mw.ustring.char(0x116b); -- per [[:en:Hangul]], this is /wɛ/
['we'] = mw.ustring.char(0x1170); -- per [[:en:Hangul]], this is /we/
['weo'] = mw.ustring.char(0x116f);
['weu'] = '(WEU)';
['wi'] = mw.ustring.char(0x1171); -- this is ui; per [[:en:Hangul]], this should be /y/, which doesn't work
['wo'] = mw.ustring.char(0x1182); -- XXX o + o
['woi'] = mw.ustring.char(0xd7b1); -- XXX o + o + i
['wu'] = mw.ustring.char(0x118d);
['wyu'] = '(WYU)';
['yaa'] = mw.ustring.char(0x1163);
['yaai'] = mw.ustring.char(0x1164);
['yə'] = mw.ustring.char(0x119d);
['yae'] = mw.ustring.char(0x1164); -- per [[:en:Hangul]], this is /jɛ/
['yeo'] = mw.ustring.char(0x1167);
['yeo_u'] = mw.ustring.char(0x117e);
['yo'] = mw.ustring.char(0x116d);
['yoi'] = mw.ustring.char(0x1188);
['ye'] = mw.ustring.char(0x1168); -- per [[:en:Hangul]], this is /je/
['yeu'] = mw.ustring.char(0x119c);
['yi'] = mw.ustring.char(0x1174);
['y_i'] = mw.ustring.char(0xd7c4);
['yu'] = mw.ustring.char(0x1172);
};
local function reconstruct_yale (initial_consonant, root, tone, punctuation, capped_p, all_caps_p)
local it = '';
if initial_consonant == nil then -- I hate Lua
initial_consonant = '';
end
if root == nil then -- I hate Lua
root = '';
end
if punctuation == nil then -- I hate Lua
punctuation = '';
end
local initial_vowel, other_vowels, final = mw.ustring.match(root, '^(ng)([aeiou]*)(.*)');
if not final then
initial_vowel, other_vowels, final = mw.ustring.match(root, '^(%a)([aeiou]*)(.*)');
end
if initial_vowel == nil then -- I hate Lua
initial_vowel = '';
end
if other_vowels == nil then -- I hate Lua
other_vowels = '';
end
if final == nil then -- I hate Lua
final = '';
end
local mod1, mod2;
if tone == 1 and use_macrons_p then
mod1 = '\204\132'; -- U+0304
elseif tone == 2 or tone == 5 then
mod1 = '\204\129'; -- U+0301
elseif tone == 1 or tone == 4 then
mod1 = '\204\128'; -- U+0300
else
mod1 = '';
end
if tone and tone > 3 then
mod2 = 'h';
else
mod2 = '';
end
if use_dotted_i_p and (not tone or tone == 3 or tone == 6) and all_caps_p then
initial_vowel = mw.ustring.gsub(initial_vowel, 'i', 'i̇'); -- append U+0307 I hate Lua
end
if not (initial_consonant == 'y' and initial_vowel:sub(1, 1) == 'y') then
it = it .. initial_consonant;
end
local part1, part2 = mw.ustring.match(initial_vowel, '^(%a)(%a*)$');
if part1 then
it = it .. part1 .. mod1 .. part2 .. other_vowels .. mod2 .. final .. punctuation;
end
if capped_p then
it = mw.ustring.upper(mw.ustring.sub(it, 1, 1)) .. mw.ustring.sub(it, 2);
elseif all_caps_p then
it = mw.ustring.upper(it);
end
return it;
end
local function reconstruct_ipa (initial_consonant, root, tone, punctuation, id)
local it = '';
local mapping = mappings[id];
local tone_mapping = tone_mappings[id];
if tone and tone_mapping.prefix and tone_mapping.prefix[tone] then
it = it .. tone_mapping.prefix[tone];
end
if initial_consonant then
it = it .. initial_consonant;
end
if root then
it = it .. root;
end
if tone and tone_mapping.suffix and tone_mapping.suffix[tone] then
it = it .. tone_mapping.suffix[tone];
end
if punctuation and not mapping.ignore_punctuation_p then
it = it .. punctuation;
end
return it;
end
local function reconstruct_ipa_phonemic (initial_consonant, root, tone, punctuation, capped_p, all_caps_p)
return reconstruct_ipa(initial_consonant, root, tone, punctuation, 'ipa_phonemic');
end
local function reconstruct_ipa_phonetic (initial_consonant, root, tone, punctuation, capped_p, all_caps_p)
return reconstruct_ipa(initial_consonant, root, tone, punctuation, 'ipa_phonetic');
end
local function reconstruct_pinyin (initial_consonant, root, tone, punctuation, id)
local it = reconstruct_ipa(initial_consonant, root, tone, punctuation, id);
it = mw.ustring.gsub(it, 'z([iü])', 'j%1');
it = mw.ustring.gsub(it, 'c([iü])', 'q%1');
it = mw.ustring.gsub(it, 's([iü])', 'x%1');
it = mw.ustring.gsub(it, '([jqx])ü', '%1u');
return it;
end
local function reconstruct_pinyin_1960 (initial_consonant, root, tone, punctuation, capped_p, all_caps_p)
return reconstruct_pinyin (initial_consonant, root, tone, punctuation, 'pinyin_1960');
end
local function reconstruct_pinyin_1980 (initial_consonant, root, tone, punctuation, capped_p, all_caps_p)
return reconstruct_pinyin (initial_consonant, root, tone, punctuation, 'pinyin_1980');
end
local function reconstruct_zhuyin (initial_consonant, root, tone, punctuation, id)
if root and tone and mw.ustring.match(root, '[ㄆㄊㄎ]') then -- XXX stupid hack
if tone == 1 then
tone = 7
elseif tone == 3 then
tone = 8
elseif tone == 6 then
tone = 9
end
end
return reconstruct_ipa(initial_consonant, root, tone, punctuation, id);
end
local function reconstruct_zhuyin_1931 (initial_consonant, root, tone, punctuation, capped_p, all_caps_p)
return reconstruct_zhuyin (initial_consonant, root, tone, punctuation, 'zhuyin_1931');
end
local function reconstruct_zhuyin_1932 (initial_consonant, root, tone, punctuation, capped_p, all_caps_p)
return reconstruct_zhuyin (initial_consonant, root, tone, punctuation, 'zhuyin_1932');
end
local function reconstruct_zhuyin_1950 (initial_consonant, root, tone, punctuation, capped_p, all_caps_p)
return reconstruct_zhuyin (initial_consonant, root, tone, punctuation, 'zhuyin_1950');
end
local function reconstruct_hangul (initial_consonant, root, tone, punctuation, id)
local onset, glide, n, s;
if type(initial_consonant) == 'table' then
onset = initial_consonant[1];
glide = initial_consonant[2];
else
onset = initial_consonant;
end
if type(root) == 'table' then
local i = glide;
if not i then
i = 1;
end
if root[i] then
if root[i][1] then
s = table.concat(root[i]);
else
error('Internal error: Unexpected value ' .. p.cvs(root[i]) .. ' for i=' .. p.cvs(i) .. ' (root=' .. p.cvs(root) .. ')');
end
else
s = 'ERROR(no root for i=' .. p.cvs(i) .. ')';
end
if onset and onset ~= '' then
s = onset .. s;
end
elseif (onset
and onset ~= ''
and onset ~= mappings[id].initials['']
and onset ~= C1['']
and onset ~= C1['ʾ']) or glide then
error('Internal error: ' .. root .. ': Not expecting onset but onset=' .. p.cvs(onset) .. ', glide=' .. p.cvs(glide));
else
s = root;
end
if n and not s then
s = mw.ustring.char(0xac00 + n);
end
return reconstruct_ipa(nil, s, tone, punctuation, 'hangul_tswong');
end
local function reconstruct_hangul_test (initial_consonant, root, tone, punctuation, id)
return reconstruct_hangul(initial_consonant, root, tone, punctuation, 'hangul_test');
end
local function reconstruct_hangul_tswong (initial_consonant, root, tone, punctuation, id)
return reconstruct_hangul(initial_consonant, root, tone, punctuation, 'hangul_tswong');
end
mappings = {
['hangul_test'] = {
['label'] = '諺文<sup>測試版</sup>';
['link'] = '粵語諺文';
['f'] = reconstruct_hangul_test;
['ignore_spaces_p'] = true,
['initials'] = {
[''] = 'ᅙ'; -- U+1159
['b'] = 'ᄇ'; -- U+1107
['p'] = 'ᄑ'; -- U+1111
['m'] = 'ᄆ'; -- U+1106
['f'] = C1.bb; -- U+112B per [[:en:Hangul]] but unusable because not supported at all
['d'] = 'ᄃ'; -- U+1103
['t'] = 'ᄐ'; -- U+1110
['n'] = 'ᄂ'; -- U+1102
['l'] = 'ᄅ'; -- U+1105
['g'] = 'ᄀ'; -- U+1100
['k'] = 'ᄏ'; -- U+110F
['ng'] = 'ᅌ'; -- U+114C
['h'] = 'ᄒ'; -- U+1112
['gw'] = { 'ᄀ', 'W' }; -- U+1100
['kw'] = { 'ᄏ', 'W' }; -- U+110F
['w'] = { C1[''], 'W' };
['z'] = 'ᄌ'; -- U+110C
['c'] = 'ᄎ'; -- U+110E
['s'] = 'ᄉ'; -- U+1109
['j'] = { C1[''], 'Y' };
};
['finals'] = { -- per [[:en:Hangul]], in principle œ = oi, y = ui, clearly unworkable unless -i can be a consonant letter
['aa'] = { { V.aa }; ['W'] = { V.waa }; ['Y'] = { V.yaa }; };
['aai'] = { { V.aa, C2.j }; ['W'] = { V.waa, C2.j }; ['Y'] = { V.yaa, C2.j }; };
['aau'] = { { V.aa, C2.l }; ['W'] = { V.waa, C2.l }; ['Y'] = { V.yaa, C2.l }; };
['aam'] = { { V.aa, C2.m }; ['W'] = { V.waa, C2.m }; ['Y'] = { V.yaa, C2.m }; };
['aan'] = { { V.aa, C2.n }; ['W'] = { V.waa, C2.n }; ['Y'] = { V.yaa, C2.n }; };
['aang'] = { { V.aa, C2.ng }; ['W'] = { V.waa, C2.ng }; ['Y'] = { V.yaa, C2.ng }; };
['aap'] = { { V.aa, C2.p }; ['W'] = { V.waa, C2.p }; ['Y'] = { V.yaa, C2.p }; };
['aat'] = { { V.aa, C2.t }; ['W'] = { V.waa, C2.t }; ['Y'] = { V.yaa, C2.t }; };
['aak'] = { { V.aa, C2.k }; ['W'] = { V.waa, C2.k }; ['Y'] = { V.yaa, C2.k }; };
['ai'] = { { V.eo, C2.j }; ['W'] = { V.weo, C2.j }; ['Y'] = { V.yeo, C2.j }; };
['au'] = { { V.eo, C2.l }; ['W'] = { V.weo, C2.l }; ['Y'] = { V.yeo, C2.l }; };
['am'] = { { V.eo, C2.m }; ['W'] = { V.weo, C2.m }; ['Y'] = { V.yeo, C2.m }; };
['an'] = { { V.eo, C2.n }; ['W'] = { V.weo, C2.n }; ['Y'] = { V.yeo, C2.n }; };
['ang'] = { { V.eo, C2.ng }; ['W'] = { V.weo, C2.ng }; ['Y'] = { V.yeo, C2.ng }; };
['ap'] = { { V.eo, C2.p }; ['W'] = { V.weo, C2.p }; ['Y'] = { V.yeo, C2.p }; };
['at'] = { { V.eo, C2.t }; ['W'] = { V.weo, C2.t }; ['Y'] = { V.yeo, C2.t }; };
['ak'] = { { V.eo, C2.k }; ['W'] = { V.weo, C2.k }; ['Y'] = { V.yeo, C2.k }; };
['e'] = { { V.ae }; ['W'] = { V.wae }; ['Y'] = { V.yae }; };
['ei'] = { { V.ae, C2.j }; ['W'] = { V.wae, C2.j }; ['Y'] = { V.yae, C2.j }; };
['eu'] = { { V.ae, C2.l }; ['W'] = { V.wae, C2.l }; ['Y'] = { V.yae, C2.l }; };
['em'] = { { V.ae, C2.m }; ['W'] = { V.wae, C2.m }; ['Y'] = { V.yae, C2.m }; };
['en'] = { { V.ae, C2.n }; ['W'] = { V.wae, C2.n }; ['Y'] = { V.yae, C2.n }; };
['eng'] = { { V.ae, C2.ng }; ['W'] = { V.wae, C2.ng }; ['Y'] = { V.yae, C2.ng }; };
['ep'] = { { V.ae, C2.p }; ['W'] = { V.wae, C2.p }; ['Y'] = { V.yae, C2.p }; };
['ek'] = { { V.ae, C2.k }; ['W'] = { V.wae, C2.k }; ['Y'] = { V.yae, C2.k }; };
['i'] = { { V.i }; ['W'] = { V.wi }; ['Y'] = { V.yi }; };
['iu'] = { { V.i, C2.l }; ['W'] = { V.wi, C2.l }; ['Y'] = { V.yi, C2.l }; };
['im'] = { { V.i, C2.m }; ['W'] = { V.wi, C2.m }; ['Y'] = { V.yi, C2.m }; };
['in'] = { { V.i, C2.n }; ['W'] = { V.wi, C2.n }; ['Y'] = { V.yi, C2.n }; };
['ing'] = { { V.i, C2.ng }; ['W'] = { V.wi, C2.ng }; ['Y'] = { V.yi, C2.ng }; };
['ip'] = { { V.i, C2.p }; ['W'] = { V.wi, C2.p }; ['Y'] = { V.yi, C2.p }; };
['it'] = { { V.i, C2.t }; ['W'] = { V.wi, C2.t }; ['Y'] = { V.yi, C2.t }; };
['ik'] = { { V.i, C2.k }; ['W'] = { V.wi, C2.k }; ['Y'] = { V.yi, C2.k }; };
['o'] = { { V.o }; ['W'] = { V.wo }; ['Y'] = { V.yo }; };
['oi'] = { { V.o, C2.j }; ['W'] = { V.wo, C2.j }; ['Y'] = { V.yo, C2.j }; };
['ou'] = { { V.o, C2.l }; ['W'] = { V.wo, C2.l }; ['Y'] = { V.yo, C2.l }; };
['on'] = { { V.o, C2.n }; ['W'] = { V.wo, C2.n }; ['Y'] = { V.yo, C2.n }; };
['ong'] = { { V.o, C2.ng }; ['W'] = { V.wo, C2.ng }; ['Y'] = { V.yo, C2.ng }; };
['op'] = { { V.o, C2.p }; ['W'] = { V.wo, C2.p }; ['Y'] = { V.yo, C2.p }; };
['ot'] = { { V.o, C2.t }; ['W'] = { V.wo, C2.t }; ['Y'] = { V.yo, C2.t }; };
['ok'] = { { V.o, C2.k }; ['W'] = { V.wo, C2.k }; ['Y'] = { V.yo, C2.k }; };
['u'] = { { V.u }; ['W'] = { V.wu }; ['Y'] = { C1.y, V.u }; };
['ui'] = { { V.u, C2.j }; ['W'] = { V.wu, C2.j }; ['Y'] = { C1.y, V.u, C2.j }; };
['un'] = { { V.u, C2.n }; ['W'] = { V.wu, C2.n }; ['Y'] = { C1.y, V.u, C2.n }; };
['ung'] = { { V.u, C2.ng }; ['W'] = { V.wu, C2.ng }; ['Y'] = { C1.y, V.u, C2.ng }; };
['up'] = { { V.u, C2.p }; ['W'] = { V.wu, C2.p }; ['Y'] = { C1.y, V.u, C2.p }; };
['ut'] = { { V.u, C2.t }; ['W'] = { V.wu, C2.t }; ['Y'] = { C1.y, V.u, C2.t }; };
['uk'] = { { V.u, C2.k }; ['W'] = { V.wu, C2.k }; ['Y'] = { C1.y, V.u, C2.k }; };
['oe'] = { { V.oi }; ['W'] = { C1.w, V.oi }; ['Y'] = { C1.y, V.oi }; };
['eoi'] = { { V.oi, C2.j }; ['W'] = { C1.w, V.oi, C2.j }; ['Y'] = { V.yoi, C2.j }; };
['eon'] = { { V.oi, C2.n }; ['W'] = { C1.w, V.oi, C2.n }; ['Y'] = { V.yoi, C2.n }; };
['oeng'] = { { V.oi, C2.ng }; ['W'] = { C1.w, V.oi, C2.ng }; ['Y'] = { V.yoi, C2.ng }; };
['eot'] = { { V.oi, C2.t }; ['W'] = { C1.w, V.oi, C2.t }; ['Y'] = { V.yoi, C2.t }; };
['oek'] = { { V.oi, C2.k }; ['W'] = { C1.w, V.oi, C2.k }; ['Y'] = { V.yoi, C2.k }; };
['yu'] = { { V.wi }; ['W'] = { C1.w, V.wi }; ['Y'] = { V.wi }; };
['yun'] = { { V.wi, C2.n }; ['W'] = { C1.w, V.wi, C2.n }; ['Y'] = { V.wi, C2.n }; };
['yut'] = { { V.wi, C2.t }; ['W'] = { C1.w, V.wi, C2.t }; ['Y'] = { V.wi, C2.t }; };
['m'] = 'ㅁ';
['ng'] = 'ㅇ'; -- or ㄲ
};
};
-- source: [[粵語諺文]]
-- any form of precomposing would not work, so we'll transform it into some kind of internal representation
-- then attempt to reconstruct the actual hangul in reconstruct_hangul_tswong
['hangul_tswong'] = {
['label'] = '諺文';
['link'] = '粵語諺文#黃得森方案';
['sublabel'] = '黃得森式';
['f'] = reconstruct_hangul_tswong;
['ignore_spaces_p'] = true,
['initials'] = {
[''] = '';--mw.ustring.char(0x110b);
['b'] = 'ᄇ'; -- U+1107
['p'] = 'ᄑ'; -- U+1111
['m'] = 'ᄆ'; -- U+1106
['f'] = mw.ustring.char(0x1108);
['d'] = 'ᄃ'; -- U+1103
['t'] = 'ᄐ'; -- U+1110
['n'] = 'ᄂ'; -- U+1102
['l'] = 'ᄅ'; -- U+1105
['g'] = 'ᄀ'; -- U+1100
['k'] = 'ᄏ'; -- U+110F
['ng'] = 'ᅌ'; -- U+114C
['h'] = 'ᄒ'; -- U+1112
['gw'] = { 'ᄀ', 'W' }; -- U+1100
['kw'] = { 'ᄏ', 'W' }; -- U+110F
['w'] = { 'ᄋ', 'W' }; -- U+110B
['z'] = 'ᄌ'; -- U+110C
['c'] = 'ᄎ'; -- U+110E
['s'] = 'ᄉ'; -- U+1109
['j'] = { 'ᄋ', 'Y' }; -- U+110B
};
['finals'] = {
['aa'] = { { V.aa }; ['W'] = { V.waa }; ['Y'] = { V.yaa }; };
['aai'] = { { V.ae }; ['W'] = { V.wae }; ['Y'] = { V.yae }; };
['aau'] = { { V.eo }; ['W'] = { V.weo }; ['Y'] = { V.yeo }; };
['aam'] = { { V.aa, C2.m }; ['W'] = { V.waa, C2.m }; ['Y'] = { V.yaa, C2.m }; };
['aan'] = { { V.aa, C2.n }; ['W'] = { V.waa, C2.n }; ['Y'] = { V.yaa, C2.n }; };
['aang'] = { { V.aa, C2.ng }; ['W'] = { V.waa, C2.ng }; ['Y'] = { V.yaa, C2.ng }; };
['aap'] = { { V.aa, C2.b }; ['W'] = { V.waa, C2.b }; ['Y'] = { V.yaa, C2.b }; };
['aat'] = { { V.aa, C2.d }; ['W'] = { V.waa, C2.d }; ['Y'] = { V.yaa, C2.d }; };
['aak'] = { { V.aa, C2.g }; ['W'] = { V.waa, C2.g }; ['Y'] = { V.yaa, C2.g }; };
['ai'] = { { V.ae, C2.s }; ['W'] = { V.wae, C2.s }; ['Y'] = { V.yae, C2.s }; };
['au'] = { { V.aa, C2.s }; ['W'] = { V.waa, C2.s }; ['Y'] = { V.yaa, C2.s }; };
['am'] = { { V.aa, C2.lm }; ['W'] = { V.waa, C2.lm }; ['Y'] = { V.yaa, C2.lm }; };
['an'] = { { V.aa, C2.nj }; ['W'] = { V.waa, C2.nj }; ['Y'] = { V.yaa, C2.nj }; };
['ang'] = { { V.aa, C2.ngs }; ['W'] = { V.waa, C2.ngs }; ['Y'] = { V.yaa, C2.ngs }; };
['ap'] = { { V.aa, C2.sp }; ['W'] = { V.waa, C2.sp }; ['Y'] = { V.yaa, C2.sp }; };
['at'] = { { V.aa, C2.st }; ['W'] = { V.waa, C2.st }; ['Y'] = { V.yaa, C2.st }; };
['ak'] = { { V.aa, C2.sk }; ['W'] = { V.waa, C2.sk }; ['Y'] = { V.yaa, C2.sk }; };
['e'] = { { V.e }; ['W'] = { V.we }; ['Y'] = { V.ye }; };
['ei'] = { { V.e, C2.s }; ['W'] = { V.we, C2.s }; ['Y'] = { V.ye, C2.s }; };
['eu'] = { { V.eo, C2.l }; ['W'] = { V.weo, C2.l }; ['Y'] = { V.yeo, C2.l }; };
['em'] = { { V.e, C2.m }; ['W'] = { V.we, C2.m }; ['Y'] = { V.ye, C2.m }; };
['en'] = { { V.e, C2.n }; ['W'] = { V.we, C2.n }; ['Y'] = { V.ye, C2.n }; };
['eng'] = { { V.e, C2.ng }; ['W'] = { V.we, C2.ng }; ['Y'] = { V.ye, C2.ng }; };
['ep'] = { { V.e, C2.b }; ['W'] = { V.we, C2.b }; ['Y'] = { V.ye, C2.b }; };
['ek'] = { { V.e, C2.g }; ['W'] = { V.we, C2.g }; ['Y'] = { V.ye, C2.g }; };
['i'] = { { V.i }; ['W'] = { V.wi }; ['Y'] = { V.yi }; };
['iu'] = { { V.yu }; ['W'] = { C1.w, V.yu }; ['Y'] = { C1.y, V.yu }; };
['im'] = { { V.i, C2.m }; ['W'] = { V.wi, C2.m }; ['Y'] = { V.yi, C2.m }; };
['in'] = { { V.i, C2.n }; ['W'] = { V.wi, C2.n }; ['Y'] = { V.yi, C2.n }; };
['ing'] = { { V.i, C2.ng }; ['W'] = { V.wi, C2.ng }; ['Y'] = { V.yi, C2.ng }; };
['ip'] = { { V.i, C2.b }; ['W'] = { V.wi, C2.b }; ['Y'] = { V.yi, C2.b }; };
['it'] = { { V.i, C2.d }; ['W'] = { V.wi, C2.d }; ['Y'] = { V.yi, C2.d }; };
['ik'] = { { V.i, C2.g }; ['W'] = { V.wi, C2.g }; ['Y'] = { V.yi, C2.g }; };
['o'] = { { V.o }; ['W'] = { V.wo }; ['Y'] = { V.yo }; };
['oi'] = { { V.oi }; ['W'] = { V.woi }; ['Y'] = { V.yoi }; };
['ou'] = { { V.o, C2.s }; ['W'] = { V.wo, C2.s }; ['Y'] = { V.yo, C2.s }; };
['on'] = { { V.o, C2.n }; ['W'] = { V.wo, C2.n }; ['Y'] = { V.yo, C2.n }; };
['ong'] = { { V.o, C2.ng }; ['W'] = { V.wo, C2.ng }; ['Y'] = { V.yo, C2.ng }; };
['op'] = { { V.o, C2.b }; ['W'] = { V.wo, C2.b }; ['Y'] = { V.yo, C2.b }; };
['ot'] = { { V.o, C2.d }; ['W'] = { V.wo, C2.d }; ['Y'] = { V.yo, C2.d }; };
['ok'] = { { V.o, C2.g }; ['W'] = { V.wo, C2.g }; ['Y'] = { V.yo, C2.g }; };
['u'] = { { V.u }; ['W'] = { V.wu }; ['Y'] = { C1.y, V.u }; };
['ui'] = { { V.wi }; ['W'] = { V.wi }; ['Y'] = { C1.y, V.wi }; };
['un'] = { { V.u, C2.n }; ['W'] = { V.wu, C2.n }; ['Y'] = { C1.y, V.u, C2.n }; };
['ung'] = { { V.u, C2.ng }; ['W'] = { V.wu, C2.ng }; ['Y'] = { C1.y, V.u, C2.ng }; };
['up'] = { { V.u, C2.b }; ['W'] = { V.wu, C2.b }; ['Y'] = { C1.y, V.u, C2.b }; };
['ut'] = { { V.u, C2.d }; ['W'] = { V.wu, C2.d }; ['Y'] = { C1.y, V.u, C2.d }; };
['uk'] = { { V.u, C2.g }; ['W'] = { V.wu, C2.g }; ['Y'] = { C1.y, V.u, C2.g }; };
['oe'] = { { V.eu }; ['W'] = { V.weu }; ['Y'] = { V.yoi }; };
['eoi'] = { { V.eu, C2.s }; ['W'] = { V.weu, C2.s }; ['Y'] = { V.yoi, C2.s }; };
['eon'] = { { V.eu, C2.ns }; ['W'] = { V.weu, C2.ns }; ['Y'] = { V.yoi, C2.ns }; };
['oeng'] = { { V.eu, C2.ngs }; ['W'] = { V.weu, C2.ngs }; ['Y'] = { V.yoi, C2.ngs }; };
['oet'] = { { V.eu, C2.t }; ['W'] = { V.weu, C2.t }; ['Y'] = { V.yoi, C2.t }; };
['oek'] = { { V.eu, C2.k }; ['W'] = { V.weu, C2.k }; ['Y'] = { V.yoi, C2.k }; };
['yu'] = { { V.yi }; ['W'] = { C1.w, V.yi }; ['Y'] = { V.yi }; };
['yun'] = { { V.yu, C2.n }; ['W'] = { C1.w, V.yi, C2.n }; ['Y'] = { V.yi, C2.n }; };
['yut'] = { { V.yu, C2.d }; ['W'] = { C1.w, V.yi, C2.d }; ['Y'] = { V.yi, C2.d }; };
['m'] = 'ㅁ';
['ng'] = 'ㅇ'; -- or ㄲ
};
};
['ipa_phonemic'] = {
['label'] = 'IPA';
['link'] = '黃錫凌式音標';
['f'] = reconstruct_ipa_phonemic;
['initials'] = {
[''] = '';
['b'] = 'b';
['p'] = 'p';
['m'] = 'm';
['f'] = 'f';
['d'] = 'd';
['t'] = 't';
['n'] = 'n';
['l'] = 'l';
['g'] = 'ɡ';
['k'] = 'k';
['ng'] = 'ŋ';
['h'] = 'h';
['gw'] = 'ɡw';
['kw'] = 'kw';
['w'] = 'w';
['z'] = 'dz';
['c'] = 'ts';
['s'] = 's';
['j'] = 'j';
};
['finals'] = {
['aa'] = 'a';
['aai'] = 'ai';
['aau'] = 'au';
['aam'] = 'am';
['aan'] = 'an';
['aang'] = 'aŋ';
['aap'] = 'ap';
['aat'] = 'at';
['aak'] = 'ak';
['ai'] = 'ɐi';
['au'] = 'ɐu';
['am'] = 'ɐm';
['an'] = 'ɐn';
['ang'] = 'ɐŋ';
['ap'] = 'ɐp';
['at'] = 'ɐt';
['ak'] = 'ɐk';
['e'] = 'ɛ';
['ei'] = 'ei';
['eng'] = 'ɛŋ';
['ek'] = 'ɛk';
['i'] = 'i';
['iu'] = 'iu';
['im'] = 'im';
['in'] = 'in';
['ing'] = 'iŋ';
['ip'] = 'ip';
['it'] = 'it';
['ik'] = 'ik';
['o'] = 'ɔ';
['oi'] = 'ɔi';
['ou'] = 'ou';
['on'] = 'ɔn';
['ong'] = 'ɔŋ';
['ot'] = 'ɔt';
['ok'] = 'ɔk';
['u'] = 'u';
['ui'] = 'ui';
['un'] = 'un';
['ung'] = 'uŋ';
['ut'] = 'ut';
['uk'] = 'uk';
['oe'] = 'œ';
['eoi'] = 'œy';
['eon'] = 'œn';
['oeng'] = 'œŋ';
['eot'] = 'œt';
['oek'] = 'œk';
['yu'] = 'y';
['yun'] = 'yn';
['yut'] = 'yt';
['m'] = 'm';
['ng'] = 'ŋ';
};
};
-- source: [[粵語注音符號]], with modifications
['ipa_phonetic'] = {
['label'] = 'IPA';
['link'] = '國際音標';
['sublabel'] = '嚴式';
['prefix'] = '[ '; -- U+200A hair space
['suffix'] = ' ]'; -- ditto
['f'] = reconstruct_ipa_phonetic;
['ignore_punctuation_p'] = true,
['initials'] = {
[''] = 'ˀ';
['b'] = 'p';
['p'] = 'pʰ';
['m'] = 'm';
['f'] = 'f';
['d'] = 't';
['t'] = 'tʰ';
['n'] = 'n';
['l'] = 'l';
['g'] = 'k';
['k'] = 'kʰ';
['ng'] = 'ŋ';
['h'] = 'h';
['gw'] = 'kʷ';
['kw'] = 'kʷʰ';
['w'] = 'w';
['z'] = 't͡s';
['c'] = 't͡sʰ';
['s'] = 's';
['j'] = 'j';
};
['finals'] = {
['aa'] = 'a';
['aai'] = 'a:i';
['aau'] = 'a:u';
['aam'] = 'a:m';
['aan'] = 'a:n';
['aang'] = 'a:ŋ';
['aap'] = 'a:p̚';
['aat'] = 'a:t̚';
['aak'] = 'a:k̚';
['ai'] = 'ɐi';
['au'] = 'ɐu';
['am'] = 'ɐm';
['an'] = 'ɐn';
['ang'] = 'ɐŋ';
['ap'] = 'ɐp̚';
['at'] = 'ɐt̚';
['ak'] = 'ɐk̚';
['e'] = 'ɛ:';
['ei'] = 'ei';
['eng'] = 'ɛ:ŋ';
['ek'] = 'ɛk̚';
['i'] = 'i:';
['iu'] = 'i:u';
['im'] = 'i:m';
['in'] = 'i:n';
['ing'] = 'ɪŋ';
['ip'] = 'i:p̚';
['it'] = 'i:t̚';
['ik'] = 'ɪk̚';
['o'] = 'ɔ';
['oi'] = 'ɔi';
['ou'] = 'ou';
['on'] = 'ɔn';
['ong'] = 'ɔŋ';
['ot'] = 'ɔt̚';
['ok'] = 'ɔk̚';
['u'] = 'u';
['ui'] = 'ui';
['un'] = 'un';
['ung'] = 'uŋ';
['ut'] = 'ut̚';
['uk'] = 'uk̚';
['oe'] = 'œ:';
['eoi'] = 'ɵy';
['eon'] = 'ɵn';
['oeng'] = 'œ:ŋ';
['eot'] = 'ɵt̚';
['oek'] = 'œ:k̚';
['yu'] = 'y:';
['yun'] = 'y:n';
['yut'] = 'yt̚';
['m'] = 'm̩';
['ng'] = 'ŋ̩';
};
};
-- source: [[廣州話拼音方案]]
['pinyin_1960'] = {
['label'] = '廣州話拼音';
['link'] = '廣州話拼音方案';
['sublabel'] = '1960年版';
['f'] = reconstruct_pinyin_1960;
['initials'] = {
[''] = '';
['b'] = 'b';
['p'] = 'p';
['m'] = 'm';
['f'] = 'f';
['d'] = 'd';
['t'] = 't';
['n'] = 'n';
['l'] = 'l';
['g'] = 'g';
['k'] = 'k';
['ng'] = 'ng';
['h'] = 'h';
['gw'] = 'gu';
['kw'] = 'ku';
['w'] = 'w';
['z'] = 'z';
['c'] = 'c';
['s'] = 's';
['j'] = 'y';
};
['finals'] = {
['aa'] = 'a';
['aai'] = 'ai';
['aau'] = 'ao';
['aam'] = 'am';
['aan'] = 'an';
['aang'] = 'ang';
['aap'] = 'ab';
['aat'] = 'ad';
['aak'] = 'ag';
['ai'] = 'ei';
['au'] = 'ou';
['am'] = 'em';
['an'] = 'en';
['ang'] = 'eng';
['ap'] = 'eb';
['at'] = 'ed';
['ak'] = 'eg';
['e'] = 'é';
['ei'] = 'éi';
['eng'] = 'éng';
['ek'] = 'ég';
['i'] = 'i';
['iu'] = 'iu';
['im'] = 'im';
['in'] = 'in';
['ing'] = 'ing';
['ip'] = 'ib';
['it'] = 'id';
['ik'] = 'ig';
['o'] = 'o';
['oi'] = 'oi';
['ou'] = 'ô';
['on'] = 'on';
['ong'] = 'ông';
['ot'] = 'od';
['ok'] = 'og';
['u'] = 'u';
['ui'] = 'ui';
['un'] = 'un';
['ung'] = 'ong';
['ut'] = 'ud';
['uk'] = 'ug';
['oe'] = 'ê';
['eoi'] = 'êu';
['eon'] = 'ên';
['oeng'] = 'êng';
['eot'] = 'êd';
['oek'] = 'êg';
['yu'] = 'ü';
['yun'] = 'ün';
['yut'] = 'üd';
['m'] = 'm’'; -- XXX not supported
['ng'] = 'ng’'; -- XXX not supported
};
};
-- source: [[廣州話拼音方案]]
['pinyin_1980'] = {
['label'] = '廣州話拼音';
['link'] = '廣州話拼音方案';
['f'] = reconstruct_pinyin_1980;
['initials'] = {
[''] = '';
['b'] = 'b';
['p'] = 'p';
['m'] = 'm';
['f'] = 'f';
['d'] = 'd';
['t'] = 't';
['n'] = 'n';
['l'] = 'l';
['g'] = 'g';
['k'] = 'k';
['ng'] = 'ng';
['h'] = 'h';
['gw'] = 'gu';
['kw'] = 'ku';
['w'] = 'w';
['z'] = 'z';
['c'] = 'c';
['s'] = 's';
['j'] = 'y';
};
['finals'] = {
['aa'] = 'a';
['aai'] = 'ai';
['aau'] = 'ao';
['aam'] = 'am';
['aan'] = 'an';
['aang'] = 'ang';
['aap'] = 'ab';
['aat'] = 'ad';
['aak'] = 'ag';
['ai'] = 'ei';
['au'] = 'eo';
['am'] = 'em';
['an'] = 'en';
['ang'] = 'eng';
['ap'] = 'eb';
['at'] = 'ed';
['ak'] = 'eg';
['e'] = 'é';
['ei'] = 'éi';
['eng'] = 'éng';
['ek'] = 'ég';
['i'] = 'i';
['iu'] = 'iu';
['im'] = 'im';
['in'] = 'in';
['ing'] = 'ing';
['ip'] = 'ib';
['it'] = 'id';
['ik'] = 'ig';
['o'] = 'o';
['oi'] = 'oi';
['ou'] = 'ou';
['on'] = 'on';
['ong'] = 'ong';
['ot'] = 'od';
['ok'] = 'og';
['u'] = 'u';
['ui'] = 'ui';
['un'] = 'un';
['ung'] = 'ung';
['ut'] = 'ud';
['uk'] = 'ug';
['oe'] = 'ê';
['eoi'] = 'êu';
['eon'] = 'ên';
['oeng'] = 'êng';
['eot'] = 'êd';
['oek'] = 'êg';
['yu'] = 'ü';
['yun'] = 'ün';
['yut'] = 'üd';
['m'] = 'm';
['ng'] = 'ng';
};
};
['yale'] = {
['label'] = '耶魯';
['link'] = '耶魯粵語拼音';
['f'] = reconstruct_yale;
['initials'] = {
[''] = '';
['b'] = 'b';
['p'] = 'p';
['m'] = 'm';
['f'] = 'f';
['d'] = 'd';
['t'] = 't';
['n'] = 'n';
['l'] = 'l';
['g'] = 'g';
['k'] = 'k';
['ng'] = 'ng';
['h'] = 'h';
['gw'] = 'gw';
['kw'] = 'kw';
['w'] = 'w';
['z'] = 'j';
['c'] = 'ch';
['s'] = 's';
['j'] = 'y';
};
['finals'] = {
['aa'] = 'a';
['aai'] = 'aai';
['aau'] = 'aau';
['aam'] = 'aam';
['aan'] = 'aan';
['aang'] = 'aang';
['aap'] = 'aap';
['aat'] = 'aat';
['aak'] = 'aak';
['ai'] = 'ai';
['au'] = 'au';
['am'] = 'am';
['an'] = 'an';
['ang'] = 'ang';
['ap'] = 'ap';
['at'] = 'at';
['ak'] = 'ak';
['e'] = 'e';
['ei'] = 'ei';
['eng'] = 'eng';
['ek'] = 'ek';
['i'] = 'i';
['iu'] = 'iu';
['im'] = 'im';
['in'] = 'in';
['ing'] = 'ing';
['ip'] = 'ip';
['it'] = 'it';
['ik'] = 'ik';
['o'] = 'o';
['oi'] = 'oi';
['ou'] = 'ou';
['on'] = 'on';
['ong'] = 'ong';
['ot'] = 'ot';
['ok'] = 'ok';
['u'] = 'u';
['ui'] = 'ui';
['un'] = 'un';
['ung'] = 'ung';
['ut'] = 'ut';
['uk'] = 'uk';
['oe'] = 'eu';
['eoi'] = 'eui';
['eon'] = 'eun';
['oeng'] = 'eung';
['eot'] = 'eut';
['oek'] = 'euk';
['yu'] = 'yu';
['yun'] = 'yun';
['yut'] = 'yut';
['m'] = 'm';
['ng'] = 'ng';
};
};
-- source: [[粵語注音符號]]
['zhuyin_1931'] = {
['label'] = '注音';
['link'] = '粵語注音符號#民國政府時期';
['sublabel'] = '原型';
['f'] = reconstruct_zhuyin_1931;
['initials'] = {
[''] = '';
['b'] = 'ㄅ';
['p'] = 'ㄆ';
['m'] = 'ㄇ';
['f'] = 'ㄈ';
['d'] = 'ㄉ';
['t'] = 'ㄊ';
['n'] = 'ㄋ';
['l'] = 'ㄌ';
['g'] = 'ㄍ';
['k'] = 'ㄎ';
['ng'] = 'ㄫ';
['h'] = 'ㄏ';
['gw'] = '[[File:Bpmf-gw.svg|16px]]';
['kw'] = '[[File:Bpmf-kw.svg|16px]]';
['w'] = 'ㄨ';
['z'] = 'ㄐ';
['c'] = 'ㄑ';
['s'] = 'ㄒ';
['j'] = 'ㄧ';
};
['finals'] = {
['aa'] = 'ㄚ';
['aai'] = 'ㄞ';
['aau'] = 'ㄠ';
['aam'] = 'ㄚㄇ';
['aan'] = 'ㄢ';
['aang'] = 'ㄤ';
['aap'] = 'ㄚㄆ';
['aat'] = 'ㄚㄊ';
['aak'] = 'ㄚㄎ';
['ai'] = 'ㄟ';
['au'] = 'ㄡ';
['am'] = 'ㄜㄇ';
['an'] = 'ㄣ';
['ang'] = 'ㄥ';
['ap'] = 'ㄜㄆ';
['at'] = 'ㄜㄊ';
['ak'] = 'ㄜㄎ';
['e'] = 'ㄝ';
['ei'] = 'ㄝㄧ';
['eu'] = 'ㄝㄨ';
['em'] = 'ㄝㄇ';
['en'] = 'ㄝㄋ';
['eng'] = 'ㄝㄫ';
['ep'] = 'ㄝㄆ';
['et'] = 'ㄝㄊ';
['ek'] = 'ㄝㄎ';
['i'] = 'ㄧ';
['iu'] = 'ㄧㄨ';
['im'] = 'ㄧㄇ';
['in'] = 'ㄧㄋ';
['ing'] = 'ㄧㄫ';
['ip'] = 'ㄧㄆ';
['it'] = 'ㄧㄊ';
['ik'] = 'ㄧㄎ';
['o'] = 'ㄛ';
['oi'] = 'ㄛㄧ';
['ou'] = 'ㄛㄨ';
['on'] = 'ㄛㄋ';
['ong'] = 'ㄛㄫ';
['ot'] = 'ㄛㄊ';
['ok'] = 'ㄛㄎ';
['u'] = 'ㄨ';
['ui'] = 'ㄨㄧ';
['un'] = 'ㄨㄋ';
['ung'] = 'ㄨㄫ';
['ut'] = 'ㄨㄊ';
['uk'] = 'ㄨㄎ';
['oe'] = '[[File:Bpmf-oe.svg|16px]]';
['eoi'] = '[[File:Bpmf-oe.svg|16px]]ㄧ';
['eon'] = '[[File:Bpmf-oe.svg|16px]]ㄋ';
['oeng'] = '[[File:Bpmf-oe.svg|16px]]ㄫ';
['eot'] = '[[File:Bpmf-oe.svg|16px]]ㄊ';
['oek'] = '[[File:Bpmf-oe.svg|16px]]ㄎ';
['yu'] = 'ㄩ';
['yun'] = 'ㄩㄋ';
['yut'] = 'ㄩㄊ';
['m'] = 'ㄇ';
['ng'] = 'ㄫ';
};
};
-- source: [[粵語注音符號]]
['zhuyin_1932'] = {
['label'] = '注音';
['link'] = '粵語注音符號#民國政府時期';
['sublabel'] = '1932年版';
['f'] = reconstruct_zhuyin_1932;
['initials'] = {
[''] = '';
['b'] = 'ㄅ';
['p'] = 'ㄆ';
['m'] = 'ㄇ';
['f'] = 'ㄈ';
['d'] = 'ㄉ';
['t'] = 'ㄊ';
['n'] = 'ㄋ';
['l'] = 'ㄌ';
['g'] = 'ㄍ';
['k'] = 'ㄎ';
['ng'] = 'ㄫ';
['h'] = 'ㄏ';
['gw'] = 'ㄍㄨ';
['kw'] = 'ㄎㄨ';
['w'] = 'ㄨ';
['z'] = '[[File:Bpmf-zi.svg|16px]]';
['c'] = '[[File:Bpmf-ci.svg|16px]]';
['s'] = '[[File:Bpmf-si.svg|16px]]';
['j'] = 'ㄧ';
};
['finals'] = {
['aa'] = 'ㄚ';
['aai'] = 'ㄞ';
['aau'] = 'ㄠ';
['aam'] = '[[File:Bpmf-aam.svg|16px]]';
['aan'] = 'ㄢ';
['aang'] = 'ㄤ';
['aap'] = 'ㄚ<sub>ㄆ</sub>';
['aat'] = 'ㄚ<sub>ㄊ</sub>';
['aak'] = 'ㄚ<sub>ㄎ</sub>';
['ai'] = '[[File:Bpmf-aq.svg|16px]]ㄧ';
['au'] = '[[File:Bpmf-aq.svg|16px]]ㄨ';
['am'] = '[[File:Bpmf-aq.svg|16px]]ㆬ';
['an'] = '[[File:Bpmf-aq.svg|16px]]ㄣ';
['ang'] = '[[File:Bpmf-aq.svg|16px]]ㄥ';
['ap'] = '[[File:Bpmf-aq.svg|16px]]<sub>ㄆ</sub>';
['at'] = '[[File:Bpmf-aq.svg|16px]]<sub>ㄊ</sub>';
['ak'] = '[[File:Bpmf-aq.svg|16px]]<sub>ㄎ</sub>';
['e'] = 'ㄝ';
['ei'] = 'ㄟ';
['eu'] = 'ㄝㄨ';
['em'] = 'ㄝㆬ';
['en'] = 'ㄝㄣ';
['eng'] = 'ㄝㄥ';
['ep'] = 'ㄝ<sub>ㄆ</sub>';
['et'] = 'ㄝ<sub>ㄊ</sub>';
['ek'] = 'ㄝ<sub>ㄎ</sub>';
['i'] = 'ㄧ';
['iu'] = 'ㄧㄨ';
['im'] = 'ㄧㆬ';
['in'] = 'ㄧㄣ';
['ing'] = 'ㄧㄥ';
['ip'] = 'ㄧ<sub>ㄆ</sub>';
['it'] = 'ㄧ<sub>ㄊ</sub>';
['ik'] = 'ㄧ<sub>ㄎ</sub>';
['o'] = 'ㄛ';
['oi'] = 'ㄛㄧ';
['ou'] = 'ㄡ';
['on'] = '[[File:Bpmf-on.svg|16px]]';
['ong'] = '[[File:Bpmf-aong.svg|16px]]';
['ot'] = 'ㄛ<sub>ㄊ</sub>';
['ok'] = 'ㄛ<sub>ㄎ</sub>';
['u'] = 'ㄨ';
['ui'] = 'ㄨㄧ';
['un'] = 'ㄨㄣ';
['ung'] = 'ㄨㄥ';
['ut'] = 'ㄨ<sub>ㄊ</sub>';
['uk'] = 'ㄨ<sub>ㄎ</sub>';
['oe'] = '[[File:Bpmf-eu.svg|16px]]';
['eoi'] = '[[File:Bpmf-eu.svg|16px]]ㄧ';
['eon'] = '[[File:Bpmf-eu.svg|16px]]ㄣ';
['oeng'] = '[[File:Bpmf-eu.svg|16px]]ㄥ';
['eot'] = '[[File:Bpmf-eu.svg|16px]]<sub>ㄊ</sub>';
['oek'] = '[[File:Bpmf-eu.svg|16px]]<sub>ㄎ</sub>';
['yu'] = 'ㄩ';
['yun'] = 'ㄩㄣ';
['yut'] = 'ㄩ<sub>ㄊ</sub>';
['m'] = 'ㆬ';
['ng'] = 'ㆭ';
};
};
-- source: [[粵語注音符號]]
['zhuyin_1950'] = {
['label'] = '注音';
['link'] = '粵語注音符號#人民政府時期';
['sublabel'] = '1950年版';
['f'] = reconstruct_zhuyin_1950;
['initials'] = {
[''] = '';
['b'] = 'ㄅ';
['p'] = 'ㄆ';
['m'] = 'ㄇ';
['f'] = 'ㄈ';
['d'] = 'ㄉ';
['t'] = 'ㄊ';
['n'] = 'ㄋ';
['l'] = 'ㄌ';
['g'] = 'ㄍ';
['k'] = 'ㄎ';
['ng'] = 'ㄫ';
['h'] = 'ㄏ';
['gw'] = '[[File:Bpmf-gw.svg|16px]]';
['kw'] = '[[File:Bpmf-kw.svg|16px]]';
['w'] = 'ㄨ';
['z'] = 'ㄐ';
['c'] = 'ㄑ';
['s'] = 'ㄒ';
['j'] = 'ㄧ';
};
['finals'] = {
['aa'] = 'ㄚ';
['aai'] = 'ㄞ';
['aau'] = 'ㄠ';
['aam'] = 'ㄚㄇ̣'; -- dot = U+323
['aan'] = 'ㄢ';
['aang'] = 'ㄤ';
['aap'] = 'ㄚㄆ̣';
['aat'] = 'ㄚㄊ̣';
['aak'] = 'ㄚㄎ̣';
['ai'] = 'ㄟ';
['au'] = 'ㄡ';
['am'] = '[[File:Bpmf-aq.svg|16px]]ㄇ̣';
['an'] = '[[File:Bpmf-aq.svg|16px]]ㄣ̣';
['ang'] = '[[File:Bpmf-aq.svg|16px]]ㄥ̣';
['ap'] = '[[File:Bpmf-aq.svg|16px]]ㄆ̣';
['at'] = '[[File:Bpmf-aq.svg|16px]]ㄊ̣';
['ak'] = '[[File:Bpmf-aq.svg|16px]]ㄎ̣';
['e'] = 'ㄝ';
['ei'] = 'ㄝㄧ';
['eu'] = 'ㄝㄨ';
['em'] = 'ㄝㄇ̣';
['en'] = 'ㄝㄋ̣';
['eng'] = 'ㄝㄫ̣';
['ep'] = 'ㄝㄆ̣';
['et'] = 'ㄝㄊ̣';
['ek'] = 'ㄝㄎ̣';
['i'] = 'ㄧ';
['iu'] = 'ㄧㄨ';
['im'] = 'ㄧㄇ̣';
['in'] = 'ㄧㄋ̣';
['ing'] = 'ㄧㄫ̣';
['ip'] = 'ㄧㄆ̣';
['it'] = 'ㄧㄊ̣';
['ik'] = 'ㄧㄎ̣';
['o'] = 'ㄛ';
['oi'] = 'ㄛㄧ';
['ou'] = 'ㄛㄨ';
['on'] = 'ㄛㄋ̣';
['ong'] = 'ㄛㄫ̣';
['ot'] = 'ㄛㄊ̣';
['ok'] = 'ㄛㄎ̣';
['u'] = 'ㄨ';
['ui'] = 'ㄨㄧ';
['un'] = 'ㄨㄋ̣';
['ung'] = 'ㄨㄫ̣';
['ut'] = 'ㄨㄊ̣';
['uk'] = 'ㄨㄎ̣';
['oe'] = '[[File:Bpmf-oe.svg|16px]]';
['eoi'] = '[[File:Bpmf-oe.svg|16px]]ㄧ';
['eon'] = '[[File:Bpmf-oe.svg|16px]]ㄋ̣';
['oeng'] = '[[File:Bpmf-oe.svg|16px]]ㄫ̣';
['eot'] = '[[File:Bpmf-oe.svg|16px]]ㄊ̣';
['oek'] = '[[File:Bpmf-oe.svg|16px]]ㄎ̣';
['yu'] = 'ㄩ';
['yun'] = 'ㄩㄋ̣';
['yut'] = 'ㄩㄊ̣';
['m'] = 'ㄇ';
['ng'] = 'ㄫ';
};
};
};
local function yalify_syllable (s, id)
local it;
local mapping = mappings[id];
local initials = mapping.initials;
local finals = mapping.finals;
local f = mapping.f;
if s then
local all_caps_p = s == mw.ustring.upper(s);
local capped_p = s == (mw.ustring.upper(mw.ustring.sub(s, 1, 1))
.. mw.ustring.lower(mw.ustring.sub(s, 2)));
local pat_avoid1 = '^ng%d'; -- I hate Lua
local pat_avoid2 = '^ng$';
local pat_part1 = '^([bcdfghjklmnpstwz]*)([a-z]+)';
local pat_part2 = '([^%a]*)$';
local initial, final, tone, punctuation;
local s1 = mw.ustring.lower(s);
for i, pat_tone in pairs({ '[1¹₁7⁷₇]', '[2²₂]', '[3³₃8⁸₈]',
'[4⁴₄]', '[5⁵₈]', '[6⁶₆9⁹₉]' }) do
if not mw.ustring.match(s, pat_avoid1)
and not mw.ustring.match(s, pat_avoid2) then
initial, final, punctuation = mw.ustring.match(s1,
pat_part1 .. pat_tone .. pat_part2);
if initial then
if initials[initial] then
initial = initials[initial];
end
if finals[final] then
final = finals[final];
end
tone = i;
end
if tone then break end;
end
end
if tone then
it = f(initial, final, tone, punctuation, capped_p, all_caps_p);
elseif not mapping.ignore_spaces_p or mw.ustring.match(s, '%S') then
it = s;
else
it = '';
end
end
it = it:gsub('(%[%[File:[^%[%]]+%]%])', '<span style="height:1em;vertical-align:text-bottom">%1</span>');
return it;
end
local function yalify (segments, id)
local it = '';
if not id then
id = 'yale';
end
local mapping = mappings[id];
if mapping.prefix then
it = it .. mapping.prefix;
end
for _, s in pairs(segments) do
it = it .. yalify_syllable(s, id);
end
if mapping.suffix then
it = it .. mapping.suffix;
end
return it;
end
local function break_into_segments (s) -- I hate Lua
local it = {};
local pat = '^([%a]+[1-9¹²³⁴⁵⁶⁷⁸⁹₁₂₃₄₅₆₇₈₉])';
while s and #s > 0 do
local pre = '';
while s and #s > 0 and not mw.ustring.match(s, pat) do
pre = pre .. mw.ustring.sub(s, 1, 1);
s = mw.ustring.sub(s, 2);
end
if #pre > 0 then
table.insert(it, pre);
end
local m, post = mw.ustring.match(s, pat .. '(.*)$');
if m then
table.insert(it, m);
end
s = post;
end
return it;
end
-- Entry point for template
p.yalify2 = function( frame )
return p.yalify(frame:getParent());
end
-- Entry point for direct #invoke
p.yalify = function (frame)
local parent = frame.args[1] or frame.args.version;
local s = '';
local scheme = 'yale';
local variant;
local label_p;
for k, v in pairs(frame.args) do
if type(k) == 'number' then
if #s > 0 then
s = s .. ' ';
end
s = s .. v;
elseif k == 'type' or k == '方案' then
scheme = v;
elseif k == 'variant' or k == '版本' then
variant = v;
elseif k == 'label' or k == '標題' then
label_p = interpret_boolean(v);
else
error('不明參數 ｢' .. k .. '｣');
end
end
if variant and not scheme then
scheme = 'yale';
end;
if scheme and not schemes[scheme] then
error('唔知 ｢' .. scheme .. '｣ 係乜方案');
end
if scheme and variant then
if not (variants[schemes[scheme]] and variants[schemes[scheme]][variant]) then
error('｢' .. scheme .. '｣ 方案冇版本叫 ｢' .. variant .. '｣');
end
variant = variants[schemes[scheme]][variant];
elseif scheme and default_variants[schemes[scheme]] then
variant = default_variants[schemes[scheme]];
end
if scheme then
scheme = schemes[scheme];
if variant then
scheme = scheme .. '_' .. variant;
end
if not mappings[scheme] then
error('Internal error: ' .. scheme .. ': No such scheme in mappings table');
end
end
local it = '';
if label_p and mappings[scheme].label then
local prefix, suffix;
if mappings[scheme].link then
prefix = '[[' .. mappings[scheme].link .. '|';
suffix = ']]';
end
it = it .. prefix .. mappings[scheme].label .. suffix;
if mappings[scheme].sublabel then
it = it .. '<sup>' .. mappings[scheme].sublabel .. '</sup>';
end
it = it .. '：';
end
it = it .. yalify(break_into_segments(s), scheme);
return it;
end
p.test = function ()
assert(yalify_syllable(nil) == nil); -- make sure it does not crash
assert(mw.ustring.toNFC(yalify_syllable_real('j', 'eu', 2, '', false, false)) == mw.ustring.toNFC('jéu'));
assert(mw.ustring.toNFC(yalify_syllable('zoe2')) == mw.ustring.toNFC('jéu'));
assert(z.cvs(break_into_segments('seoi1 zoe2')) == '[(seoi1) ( ) (zoe2)]');
assert(mw.ustring.toNFC(yalify({'seoi1', 'zoe2'})) == mw.ustring.toNFC('sēuijéu'));
assert(mw.ustring.toNFC(yalify({'seoi1', ' ', 'zoe2'})) == mw.ustring.toNFC('sēui jéu'));
error(p.cvs(yalify({'Seoi1', ' ', 'zoe2'})));
assert(mw.ustring.toNFC(yalify({'Seoi1', ' ', 'zoe2'})) == mw.ustring.toNFC('Sēui jéu'));
assert(mw.ustring.toNFC(yalify({'SEOI1', ' ', 'zoe2'})) == mw.ustring.toNFC('SĒUI jéu'));
end
return p;