https://linguifex.com/w/index.php?action=history&feed=atom&title=Module%3Api-translit Module:pi-translit - Revision history 2026-05-19T02:48:36Z Revision history for this page on the wiki MediaWiki 1.43.6 https://linguifex.com/w/index.php?title=Module:pi-translit&diff=495857&oldid=prev Sware: 1 revision imported 2026-04-21T12:45:04Z <p>1 revision imported</p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <tr class="diff-title" lang="en"> <td colspan="1" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="1" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 12:45, 21 April 2026</td> </tr><tr><td colspan="2" class="diff-notice" lang="en"><div class="mw-diff-empty">(No difference)</div> </td></tr></table> Sware https://linguifex.com/w/index.php?title=Module:pi-translit&diff=495856&oldid=prev wikt>SurjectionBot: Protected "Module:pi-translit": (bot) automatically protect highly visible templates/modules (reference score: 1963+ >= 1000) ([Edit=Allow only autoconfirmed users] (indefinite) [Move=Allow only autoconfirmed users] (indefinite)) 2024-04-27T09:36:06Z <p>Protected &quot;<a href="/wiki/Module:pi-translit" title="Module:pi-translit">Module:pi-translit</a>&quot;: (bot) automatically protect highly visible templates/modules (reference score: 1963+ &gt;= 1000) ([Edit=Allow only autoconfirmed users] (indefinite) [Move=Allow only autoconfirmed users] (indefinite))</p> <p><b>New page</b></p><div>local m_str_utils = require(&quot;Module:string utilities&quot;)<br /> <br /> local gsub = m_str_utils.gsub<br /> local match = m_str_utils.match<br /> local u = m_str_utils.char<br /> <br /> local export = {}<br /> <br /> function export.trwo(text, lang, sc, options)<br /> if (sc == &#039;Brah&#039;) then<br /> text = require(&#039;Module:Brah-translit&#039;).tr(text, lang, sc)<br /> elseif (sc == &#039;Deva&#039;) then<br /> text = require(&#039;Module:sa-translit&#039;).tr(text, lang, sc)<br /> elseif (sc == &#039;Sinh&#039;) then<br /> text = require(&#039;Module:si-translit&#039;).tr(text, lang, sc)<br /> elseif sc == &#039;Beng&#039; or sc == &#039;Mymr&#039; or sc == &#039;Lana&#039; or sc == &#039;Khmr&#039;<br /> or sc == &#039;Thai&#039; or sc == &#039;Laoo&#039;<br /> then<br /> local function dc(x) -- Use this to make marks legible. The name &#039;dc&#039; means &#039;drop carrier&#039;.<br /> return gsub(x, &quot;[𑀓कকකကกᨠកກ]&quot;, &quot;&quot;) -- These are the letter ka in the 9 supported Indic scripts.<br /> end<br /> local consonants = { -- And parts 1 of NFC-multipart independent vowels!<br /> -- Bengali<br /> [&#039;ক&#039;]=&#039;k&#039;, [&#039;খ&#039;]=&#039;kh&#039;, [&#039;গ&#039;]=&#039;g&#039;, [&#039;ঘ&#039;]=&#039;gh&#039;, [&#039;ঙ&#039;]=&#039;ṅ&#039;,<br /> [&#039;চ&#039;]=&#039;c&#039;, [&#039;ছ&#039;]=&#039;ch&#039;, [&#039;জ&#039;]=&#039;j&#039;, [&#039;ঝ&#039;]=&#039;jh&#039;, [&#039;ঞ&#039;]=&#039;ñ&#039;, <br /> [&#039;ট&#039;]=&#039;ṭ&#039;, [&#039;ঠ&#039;]=&#039;ṭh&#039;, [&#039;ড&#039;]=&#039;ḍ&#039;, [&#039;ঢ&#039;]=&#039;ḍh&#039;, [&#039;ণ&#039;]=&#039;ṇ&#039;, <br /> [&#039;ত&#039;]=&#039;t&#039;, [&#039;থ&#039;]=&#039;th&#039;, [&#039;দ&#039;]=&#039;d&#039;, [&#039;ধ&#039;]=&#039;dh&#039;, [&#039;ন&#039;]=&#039;n&#039;, <br /> [&#039;প&#039;]=&#039;p&#039;, [&#039;ফ&#039;]=&#039;ph&#039;, [&#039;ব&#039;]=&#039;b&#039;, [&#039;ভ&#039;]=&#039;bh&#039;, [&#039;ম&#039;]=&#039;m&#039;,<br /> [&#039;য&#039;]=&#039;y&#039;, [&#039;র&#039;]=&#039;r&#039;, [&#039;ল&#039;]=&#039;l&#039;, [&#039;ল়&#039;]=&#039;ḷ&#039;, -- xx[&#039;व&#039;]=&#039;v&#039;,<br /> [&#039;শ&#039;]=&#039;ś&#039;, [&#039;ষ&#039;]=&#039;ṣ&#039;, [&#039;স&#039;]=&#039;s&#039;, [&#039;হ&#039;]=&#039;h&#039;,<br /> [&#039;ৰ&#039;]=&#039;v&#039;, [&#039;ৰ&#039;..u(0x200d)]=&#039;v&#039;, [&#039;ৱ&#039;] = &#039;v&#039;,<br /> -- Myanmar<br /> [&#039;က&#039;]=&#039;k&#039;, [&#039;ခ&#039;]=&#039;kh&#039;, [&#039;ဂ&#039;]=&#039;g&#039;, [&#039;ဃ&#039;]=&#039;gh&#039;, [&#039;င&#039;]=&#039;ṅ&#039;,<br /> [&#039;စ&#039;]=&#039;c&#039;, [&#039;ဆ&#039;]=&#039;ch&#039;, [&#039;ဇ&#039;]=&#039;j&#039;, [&#039;ဈ&#039;]=&#039;jh&#039;, [&#039;ဉ&#039;]=&#039;ñ&#039;, <br /> [&#039;ဋ&#039;]=&#039;ṭ&#039;, [&#039;ဌ&#039;]=&#039;ṭh&#039;, [&#039;ဍ&#039;]=&#039;ḍ&#039;, [&#039;ဎ&#039;]=&#039;ḍh&#039;, [&#039;ဏ&#039;]=&#039;ṇ&#039;, <br /> [&#039;တ&#039;]=&#039;t&#039;, [&#039;ထ&#039;]=&#039;th&#039;, [&#039;ဒ&#039;]=&#039;d&#039;, [&#039;ဓ&#039;]=&#039;dh&#039;, [&#039;န&#039;]=&#039;n&#039;, <br /> [&#039;ပ&#039;]=&#039;p&#039;, [&#039;ဖ&#039;]=&#039;ph&#039;, [&#039;ဗ&#039;]=&#039;b&#039;, [&#039;ဘ&#039;]=&#039;bh&#039;, [&#039;မ&#039;]=&#039;m&#039;,<br /> [&#039;ယ&#039;]=&#039;y&#039;, [&#039;ရ&#039;]=&#039;r&#039;, [&#039;လ&#039;]=&#039;l&#039;, [&#039;ဝ&#039;]=&#039;v&#039;, [&#039;ဠ&#039;]=&#039;ḷ&#039;,<br /> [&#039;ၐ&#039;]=&#039;ś&#039;, [&#039;ၑ&#039;]=&#039;ṣ&#039;, [&#039;သ&#039;]=&#039;s&#039;, [&#039;ဟ&#039;]=&#039;h&#039;,<br /> [&#039;ည&#039;]=&#039;ññ&#039;, [&#039;ဿ&#039;]=&#039;ss&#039;, [&#039;အ&#039;] = &#039;ʼ&#039;,<br /> -- Subscript consonants: 103B..103E, 105E..1060<br /> [dc(&#039;ကျ&#039;)]=&#039;y&#039;, [dc(&#039;ကြ&#039;)]=&#039;r&#039;, [dc(&#039;ကွ&#039;)]=&#039;v&#039;, [dc(&#039;ကှ&#039;)]=&#039;h&#039;,<br /> [dc(&#039;ကၞ&#039;)]=&#039;n&#039;, [dc(&#039;ကၟ&#039;)]=&#039;m&#039;, [dc(&#039;ကၠ&#039;)]=&#039;l&#039;,<br /> -- Mon Pali consonants<br /> [&#039;ၚ&#039;]=&#039;ṅ&#039;, [&#039;ၛ&#039;]=&#039;jh&#039;,<br /> -- Shan (Pali) consonants - Excludes SHAN THA, MEDIAL WA, SIGN SHAW<br /> [&#039;ၵ&#039;]=&#039;k&#039;, [&#039;ၶ&#039;]=&#039;kh&#039;, [&#039;ၷ&#039;]=&#039;g&#039;, [&#039;ꧠ&#039;]=&#039;gh&#039;, -- [&#039;&#039;]=&#039;ṅ&#039;,<br /> [&#039;ၸ&#039;]=&#039;c&#039;, [&#039;ꧡ&#039;]=&#039;ch&#039;, [&#039;ၹ&#039;]=&#039;j&#039;, [&#039;ꧢ&#039;]=&#039;jh&#039;, [&#039;ၺ&#039;]=&#039;ñ&#039;, <br /> [&#039;ꩦ&#039;]=&#039;ṭ&#039;, [&#039;ꩧ&#039;]=&#039;ṭh&#039;, [&#039;ꩨ&#039;]=&#039;ḍ&#039;, [&#039;ꩩ&#039;]=&#039;ḍh&#039;, [&#039;ꧣ&#039;]=&#039;ṇ&#039;, <br /> -- [&#039;&#039;]=&#039;t&#039;, [&#039;&#039;]=&#039;th&#039;,<br /> [&#039;ၻ&#039;]=&#039;d&#039;, [&#039;ꩪ&#039;]=&#039;dh&#039;, [&#039;ၼ&#039;]=&#039;n&#039;, <br /> -- [&#039;&#039;]=&#039;p&#039;,<br /> [&#039;ၽ&#039;]=&#039;ph&#039;, [&#039;ၿ&#039;]=&#039;b&#039;, [&#039;ꧤ&#039;]=&#039;bh&#039;, -- [&#039;&#039;]=&#039;m&#039;,<br /> -- [&#039;&#039;]=&#039;y&#039;, [&#039;&#039;]=&#039;r&#039;, [&#039;&#039;]=&#039;l&#039;, [&#039;&#039;]=&#039;v&#039;,<br /> [&#039;ꩮ&#039;]=&#039;ḷ&#039;,<br /> -- [&#039;&#039;]=&#039;ś&#039;, [&#039;&#039;]=&#039;ṣ&#039;, [&#039;&#039;]=&#039;s&#039;,<br /> [&#039;ႁ&#039;]=&#039;h&#039;,<br /> -- [&#039;&#039;]=&#039;ññ&#039;, [&#039;&#039;]=&#039;ss&#039;,<br /> [&#039;ဢ&#039;] = &#039;ʼ&#039;,<br /> -- Other first parts of independent vowels.<br /> [&#039;ဣ&#039;]=&#039;i&#039;, [&#039;ဥ&#039;]=&#039;u&#039;,<br /> -- Lanna<br /> [&#039;ᨠ&#039;]=&#039;k&#039;, [&#039;ᨡ&#039;]=&#039;kh&#039;, [&#039;ᨣ&#039;]=&#039;g&#039;, [&#039;ᨥ&#039;]=&#039;gh&#039;, [&#039;ᨦ&#039;]=&#039;ṅ&#039;,<br /> [&#039;ᨧ&#039;]=&#039;c&#039;, [&#039;ᨨ&#039;]=&#039;ch&#039;, [&#039;ᨩ&#039;]=&#039;j&#039;, [&#039;ᨫ&#039;]=&#039;jh&#039;, [&#039;ᨬ&#039;]=&#039;ñ&#039;, <br /> [&#039;ᨭ&#039;]=&#039;ṭ&#039;, [&#039;ᨮ&#039;]=&#039;ṭh&#039;, [&#039;ᨯ&#039;]=&#039;ḍ&#039;, [&#039;ᨰ&#039;]=&#039;ḍh&#039;, [&#039;ᨱ&#039;]=&#039;ṇ&#039;, <br /> [&#039;ᨲ&#039;]=&#039;t&#039;, [&#039;ᨳ&#039;]=&#039;th&#039;, [&#039;ᨴ&#039;]=&#039;d&#039;, [&#039;ᨵ&#039;]=&#039;dh&#039;, [&#039;ᨶ&#039;]=&#039;n&#039;, <br /> [&#039;ᨷ&#039;]=&#039;p&#039;, [&#039;ᨸ&#039;]=&#039;p&#039;, [&#039;ᨹ&#039;]=&#039;ph&#039;, [&#039;ᨻ&#039;]=&#039;b&#039;, [&#039;ᨽ&#039;]=&#039;bh&#039;, [&#039;ᨾ&#039;]=&#039;m&#039;,<br /> [&#039;ᨿ&#039;]=&#039;y&#039;, [&#039;ᩁ&#039;]=&#039;r&#039;, [&#039;ᩃ&#039;]=&#039;l&#039;, [&#039;ᩅ&#039;]=&#039;v&#039;, [&#039;ᩊ&#039;]=&#039;ḷ&#039;,<br /> [&#039;ᩆ&#039;]=&#039;ś&#039;, [&#039;ᩇ&#039;]=&#039;ṣ&#039;, [&#039;ᩈ&#039;]=&#039;s&#039;, [&#039;ᩉ&#039;]=&#039;h&#039;,<br /> [&#039;ᩔ&#039;] = &#039;ss&#039;, [&#039;ᩋ&#039;] = &#039;ʼ&#039;, [&#039;ᩐ&#039;] = &#039;ū&#039;,<br /> -- Subscript consonants: 1A55, 1A56, 1A5B to 1A5E<br /> [dc(&#039;ᨠᩕ&#039;)]=&#039;r&#039;, [dc(&#039;ᨠᩖ&#039;)]=&#039;l&#039;, [dc(&#039;ᨠᩛ&#039;)]=&#039;ṭh&#039;, [dc(&#039;ᨠᩜ&#039;)]=&#039;m&#039;,<br /> [dc(&#039;ᨠᩝ&#039;)]=&#039;p&#039;, [dc(&#039;ᨠᩞ&#039;)]=&#039;s&#039;, <br /> -- Khmer<br /> [&#039;ក&#039;]=&#039;k&#039;, [&#039;ខ&#039;]=&#039;kh&#039;, [&#039;គ&#039;]=&#039;g&#039;, [&#039;ឃ&#039;]=&#039;gh&#039;, [&#039;ង&#039;]=&#039;ṅ&#039;,<br /> [&#039;ច&#039;]=&#039;c&#039;, [&#039;ឆ&#039;]=&#039;ch&#039;, [&#039;ជ&#039;]=&#039;j&#039;, [&#039;ឈ&#039;]=&#039;jh&#039;, [&#039;ញ&#039;]=&#039;ñ&#039;, <br /> [&#039;ដ&#039;]=&#039;ṭ&#039;, [&#039;ឋ&#039;]=&#039;ṭh&#039;, [&#039;ឌ&#039;]=&#039;ḍ&#039;, [&#039;ឍ&#039;]=&#039;ḍh&#039;, [&#039;ណ&#039;]=&#039;ṇ&#039;, <br /> [&#039;ត&#039;]=&#039;t&#039;, [&#039;ថ&#039;]=&#039;th&#039;, [&#039;ទ&#039;]=&#039;d&#039;, [&#039;ធ&#039;]=&#039;dh&#039;, [&#039;ន&#039;]=&#039;n&#039;, <br /> [&#039;ប&#039;]=&#039;p&#039;, [&#039;ផ&#039;]=&#039;ph&#039;, [&#039;ព&#039;]=&#039;b&#039;, [&#039;ភ&#039;]=&#039;bh&#039;, [&#039;ម&#039;]=&#039;m&#039;,<br /> [&#039;យ&#039;]=&#039;y&#039;, [&#039;រ&#039;]=&#039;r&#039;, [&#039;ល&#039;]=&#039;l&#039;, [&#039;វ&#039;]=&#039;v&#039;, [&#039;ឡ&#039;]=&#039;ḷ&#039;,<br /> [&#039;ឝ&#039;]=&#039;ś&#039;, [&#039;ឞ&#039;]=&#039;ṣ&#039;, [&#039;ស&#039;]=&#039;s&#039;, [&#039;ហ&#039;]=&#039;h&#039;, [&#039;អ&#039;] = &#039;ʼ&#039;,<br /> -- Thai<br /> [&#039;ก&#039;]=&#039;k&#039;, [&#039;ข&#039;]=&#039;kh&#039;, [&#039;ค&#039;]=&#039;g&#039;, [&#039;ฆ&#039;]=&#039;gh&#039;, [&#039;ง&#039;]=&#039;ṅ&#039;,<br /> [&#039;จ&#039;]=&#039;c&#039;, [&#039;ฉ&#039;]=&#039;ch&#039;, [&#039;ช&#039;]=&#039;j&#039;, [&#039;ฌ&#039;]=&#039;jh&#039;, [&#039;ญ&#039;]=&#039;ñ&#039;, <br /> [&#039;ฏ&#039;]=&#039;ṭ&#039;, [&#039;ฐ&#039;]=&#039;ṭh&#039;, [&#039;ฑ&#039;]=&#039;ḍ&#039;, [&#039;ฒ&#039;]=&#039;ḍh&#039;, [&#039;ณ&#039;]=&#039;ṇ&#039;, <br /> [&#039;ต&#039;]=&#039;t&#039;, [&#039;ถ&#039;]=&#039;th&#039;, [&#039;ท&#039;]=&#039;d&#039;, [&#039;ธ&#039;]=&#039;dh&#039;, [&#039;น&#039;]=&#039;n&#039;, <br /> [&#039;ป&#039;]=&#039;p&#039;, [&#039;ผ&#039;]=&#039;ph&#039;, [&#039;พ&#039;]=&#039;b&#039;, [&#039;ภ&#039;]=&#039;bh&#039;, [&#039;ม&#039;]=&#039;m&#039;,<br /> [&#039;ย&#039;]=&#039;y&#039;, [&#039;ร&#039;]=&#039;r&#039;, [&#039;ล&#039;]=&#039;l&#039;, [&#039;ว&#039;]=&#039;v&#039;, [&#039;ฬ&#039;]=&#039;ḷ&#039;,<br /> [&#039;ศ&#039;]=&#039;ś&#039;, [&#039;ษ&#039;]=&#039;ṣ&#039;, [&#039;ส&#039;]=&#039;s&#039;, [&#039;ห&#039;]=&#039;h&#039;, [&#039;อ&#039;] = &#039;&#039;, -- [&#039;อ&#039;] = &#039;ʼ&#039;,<br /> <br /> -- Lao<br /> [&#039;ກ&#039;]=&#039;k&#039;, [&#039;ຂ&#039;]=&#039;kh&#039;, [&#039;ຄ&#039;]=&#039;g&#039;, [&#039;ຆ&#039;]=&#039;gh&#039;, [&#039;ງ&#039;]=&#039;ṅ&#039;,<br /> [&#039;ຈ&#039;]=&#039;c&#039;, [&#039;ຉ&#039;]=&#039;ch&#039;, [&#039;ຊ&#039;]=&#039;j&#039;, [&#039;ຌ&#039;]=&#039;jh&#039;, [&#039;ຎ&#039;]=&#039;ñ&#039;, <br /> [&#039;ຏ&#039;]=&#039;ṭ&#039;, [&#039;ຐ&#039;]=&#039;ṭh&#039;, [&#039;ຑ&#039;]=&#039;ḍ&#039;, [&#039;ຒ&#039;]=&#039;ḍh&#039;, [&#039;ຓ&#039;]=&#039;ṇ&#039;, <br /> [&#039;ຕ&#039;]=&#039;t&#039;, [&#039;ຖ&#039;]=&#039;th&#039;, [&#039;ທ&#039;]=&#039;d&#039;, [&#039;ຘ&#039;]=&#039;dh&#039;, [&#039;ນ&#039;]=&#039;n&#039;, <br /> [&#039;ປ&#039;]=&#039;p&#039;, [&#039;ຜ&#039;]=&#039;ph&#039;, [&#039;ພ&#039;]=&#039;b&#039;, [&#039;ຠ&#039;]=&#039;bh&#039;, [&#039;ມ&#039;]=&#039;m&#039;,<br /> [&#039;ຍ&#039;]=&#039;y&#039;, [&#039;ຢ&#039;]=&#039;y&#039;, [&#039;ຣ&#039;]=&#039;r&#039;, [&#039;ລ&#039;]=&#039;l&#039;, [&#039;ວ&#039;]=&#039;v&#039;, [&#039;ຬ&#039;]=&#039;ḷ&#039;,<br /> [&#039;ຨ&#039;]=&#039;ś&#039;, [&#039;ຩ&#039;]=&#039;ṣ&#039;, [&#039;ສ&#039;]=&#039;s&#039;, [&#039;ຫ&#039;]=&#039;h&#039;, [&#039;ອ&#039;] = &#039;&#039;, -- [&#039;ອ&#039;] = &#039;ʼ&#039;,<br /> -- [&#039;ດ&#039;]=&#039;D&#039;, [&#039;ບ&#039;]=&#039;B&#039; -- Characters that appear but should be converted to others.<br /> }<br /> <br /> local diacritics = {<br /> -- Bengali - only NFC needed<br /> [dc(&#039;কা&#039;)]=&#039;ā&#039;, [dc(&#039;কি&#039;)]=&#039;i&#039;, [dc(&#039;কী&#039;)]=&#039;ī&#039;, [dc(&#039;কু&#039;)]=&#039;u&#039;, [dc(&#039;কূ&#039;)]=&#039;ū&#039;, [dc(&#039;কৃ&#039;)]=&#039;ṛ&#039;, [dc(&#039;কৄ&#039;)]=&#039;ṝ&#039;, <br /> [dc(&#039;কৢ&#039;)]=&#039;ḷ&#039;, [dc(&#039;কৣ&#039;)]=&#039;ḹ&#039;, [dc(&#039;কে&#039;)]=&#039;e&#039;, [dc(&#039;কৈ&#039;)]=&#039;ai&#039;, [dc(&#039;কো&#039;)]=&#039;o&#039;, [dc(&#039;কৌ&#039;)]=&#039;au&#039;, [dc(&#039;ক্&#039;)]=&#039;&#039;,<br /> -- Myanmar<br /> [dc(&#039;ကာ&#039;)]=&#039;ā&#039;, [dc(&#039;ကါ&#039;)]=&#039;ā&#039;, [dc(&#039;ကိ&#039;)]=&#039;i&#039;, [dc(&#039;ကီ&#039;)]=&#039;ī&#039;, [dc(&#039;ကု&#039;)]=&#039;u&#039;, [dc(&#039;ကူ&#039;)]=&#039;ū&#039;,<br /> [dc(&#039;ကၖ&#039;)]=&#039;ṛ&#039;, [dc(&#039;ကၗ&#039;)]=&#039;ṝ&#039;, [dc(&#039;ကၘ&#039;)]=&#039;ḷ&#039;, [dc(&#039;ကၙ&#039;)]=&#039;ḹ&#039;,<br /> [dc(&#039;ကေ&#039;)]=&#039;e&#039;, [dc(&#039;ကဲ&#039;)]=&#039;ai&#039;,<br /> -- The following are multicharacter!<br /> [dc(&#039;ကော&#039;)]=&#039;o&#039;, [dc(&#039;ကော်&#039;)]=&#039;au&#039;, [dc(&#039;က်က္&#039;)]=&#039;&#039;, [dc(&#039;ကေါ&#039;)]=&#039;o&#039;, [dc(&#039;ကေါ်&#039;)]=&#039;au&#039;,<br /> [dc(&#039;က္&#039;)]=&#039;&#039;, [dc(&#039;က်&#039;)]=&#039;&#039;,<br /> -- Mon - treatment of Sanskrit au is to be determined!<br /> [dc(&#039;ကဳ&#039;)]=&#039;ī&#039;,<br /> -- Shan<br /> [dc(&#039;ကႃ&#039;)]=&#039;ā&#039;, [dc(&#039;ကေႃ&#039;)]=&#039;o&#039;,<br /> -- Lanna<br /> [dc(&#039;ᨠᩣ&#039;)]=&#039;ā&#039;, [dc(&#039;ᨠᩤ&#039;)]=&#039;ā&#039;, [dc(&#039;ᨠᩥ&#039;)]=&#039;i&#039;, [dc(&#039;ᨠᩦ&#039;)]=&#039;ī&#039;, [dc(&#039;ᨠᩩ&#039;)]=&#039;u&#039;, [dc(&#039;ᨠᩪ&#039;)]=&#039;ū&#039;,<br /> [&#039;ᩂ&#039;]=&#039;ṛ&#039;, [&#039;ᩄ&#039;]=&#039;ḷ&#039;, -- Syllabic consonants may be very wrong!<br /> [dc(&#039;ᨠᩮ&#039;)]=&#039;e&#039;, [dc(&#039;ᨠᩱ&#039;)]=&#039;ai&#039;, [dc(&#039;ᨠᩰ&#039;)]=&#039;o&#039;,<br /> -- The next two rows are are multicharacter!<br /> [dc(&#039;ᨠᩮᩣ&#039;)]=&#039;o&#039;, [dc(&#039;ᨠᩮᩢᩣ&#039;)]=&#039;au&#039;, [dc(&#039;ᨠᩮᩫᩢᩣ&#039;)]=&#039;au&#039;, [dc(&#039;ᨠᩮᩫᩣ&#039;)] = &#039;au&#039;,<br /> [dc(&#039;ᨠᩮᩤ&#039;)]=&#039;o&#039;, [dc(&#039;ᨠᩮᩢᩤ&#039;)]=&#039;au&#039;, [dc(&#039;ᨠᩮᩫᩢᩤ&#039;)]=&#039;au&#039;, [dc(&#039;ᨠᩮᩫᩤ&#039;)] = &#039;au&#039;,<br /> [dc(&#039;ᨠ᩠&#039;)]=&#039;&#039;, [dc(&#039;ᨠ᩺&#039;)]=&#039;&#039;, [dc(&#039;ᨠ᩼&#039;)]=&#039;&#039;,<br /> -- Khmer<br /> [dc(&#039;កា&#039;)]=&#039;ā&#039;, [dc(&#039;កិ&#039;)]=&#039;i&#039;, [dc(&#039;កី&#039;)]=&#039;ī&#039;, [dc(&#039;កុ&#039;)]=&#039;u&#039;, [dc(&#039;កូ&#039;)]=&#039;ū&#039;,<br /> [dc(&#039;ក្ឫ&#039;)]=&#039;ṛ&#039;, [dc(&#039;ក្ឬ&#039;)]=&#039;ṝ&#039;, [dc(&#039;ក្ឭ&#039;)]=&#039;ḷ&#039;, [dc(&#039;ក្ឮ&#039;)]=&#039;ḹ&#039;, -- Multipart<br /> [dc(&#039;កេ&#039;)]=&#039;e&#039;, [dc(&#039;កៃ&#039;)]=&#039;ai&#039;, [dc(&#039;កោ&#039;)]=&#039;o&#039;, [dc(&#039;កៅ&#039;)]=&#039;au&#039;, [dc(&#039;ក្&#039;)]=&#039;&#039;, [dc(&#039;ក៑&#039;)]=&#039;&#039;,<br /> -- Thai<br /> [dc(&#039;กั&#039;)]=&#039;a&#039;, [&#039;า&#039;]=&#039;ā&#039;, [dc(&#039;กิ&#039;)]=&#039;i&#039;, [dc(&#039;กี&#039;)]=&#039;ī&#039;, [dc(&#039;กุ&#039;)]=&#039;u&#039;, [dc(&#039;กู&#039;)]=&#039;ū&#039;,<br /> [&#039;ฤ&#039;]=&#039;ṛ&#039;, [&#039;ฤๅ&#039;]=&#039;ṝ&#039;, [&#039;ฦ&#039;]=&#039;ḷ&#039;, [&#039;ฦๅ&#039;]=&#039;ḹ&#039;, -- Multipart<br /> [&#039;เ&#039;]=&#039;e&#039;, [&#039;ไ&#039;]=&#039;ai&#039;, [&#039;โ&#039;]=&#039;o&#039;, [&#039;เา&#039;]=&#039;au&#039;, [dc(&#039;กฺ&#039;)]=&#039;&#039;, [dc(&#039;ก์&#039;)]=&#039;&#039;, [&#039;ะ&#039;]=&#039;a&#039;,<br /> [dc(&#039;กึ&#039;)]=&#039;iṃ&#039;, -- Induced by jackbooted I/O<br /> -- Lao<br /> [dc(&#039;ກັ&#039;)]=&#039;a&#039;, [&#039;າ&#039;]=&#039;ā&#039;, [dc(&#039;ກິ&#039;)]=&#039;i&#039;, [dc(&#039;ກີ&#039;)]=&#039;ī&#039;, [dc(&#039;ກຸ&#039;)]=&#039;u&#039;, [dc(&#039;ກູ&#039;)]=&#039;ū&#039;,<br /> -- [&#039;ฤ&#039;]=&#039;ṛ&#039;, [&#039;ฤๅ&#039;)]=&#039;ṝ&#039;, [&#039;ฦ&#039;]=&#039;ḷ&#039;, [&#039;ฦๅ&#039;]=&#039;ḹ&#039;, -- Multipart<br /> [&#039;ເ&#039;]=&#039;e&#039;, [&#039;ໄ&#039;]=&#039;ai&#039;, [&#039;ໂ&#039;]=&#039;o&#039;, [dc(&#039;ເກົາ&#039;)]=&#039;au&#039;, [dc(&#039;ກ຺&#039;)]=&#039;&#039;, [dc(&#039;ກ໌&#039;)]=&#039;&#039;,<br /> [&#039;ະ&#039;]=&#039;a&#039;,<br /> [dc(&#039;ກຶ&#039;)]=&#039;iṃ&#039;, -- Induced by jackbooted I/O<br /> -- Results of subscripts - for 2nd level special subscripts.<br /> [&#039;ṭ&#039;]=&#039;ṭ&#039;, [&#039;n&#039;]=&#039;n&#039;, [&#039;p&#039;]=&#039;p&#039;, [&#039;m&#039;]=&#039;m&#039;, <br /> [&#039;y&#039;]=&#039;y&#039;, [&#039;r&#039;]=&#039;r&#039;, [&#039;l&#039;]=&#039;l&#039;, [&#039;w&#039;]=&#039;w&#039;, [&#039;s&#039;]=&#039;s&#039;, [&#039;h&#039;]=&#039;h&#039;,<br /> }<br /> <br /> local tt = {<br /> -- Bengali independent vowels<br /> [&#039;অ&#039;]=&#039;a&#039;, [&#039;আ&#039;]=&#039;ā&#039;, [&#039;ই&#039;]=&#039;i&#039;, [&#039;ঈ&#039;]=&#039;ī&#039;, [&#039;উ&#039;]=&#039;u&#039;, [&#039;ঊ&#039;]=&#039;ū&#039;, [&#039;ঋ&#039;]=&#039;ṛ&#039;, [&#039;ৠ&#039;]=&#039;ṝ&#039;,<br /> [&#039;ঌ&#039;]=&#039;ḷ&#039;, [&#039;ৡ&#039;]=&#039;ḹ&#039;, [&#039;এ&#039;]=&#039;e&#039;, [&#039;ঐ&#039;]=&#039;ai&#039;, [&#039;ও&#039;]=&#039;o&#039;, [&#039;ঔ&#039;]=&#039;au&#039;, <br /> -- chandrabindu, anusvara, visarga &amp; avagraha<br /> [dc(&#039;কঁ&#039;)]=&#039;m̐&#039;, [dc(&#039;কং&#039;)]=&#039;ṃ&#039;, [&#039;ঃ&#039;]=&#039;ḥ&#039;, [&#039;ঽ&#039;]=&#039;’&#039;,<br /> --numerals<br /> [&#039;০&#039;]=&#039;0&#039;, [&#039;১&#039;]=&#039;1&#039;, [&#039;২&#039;]=&#039;2&#039;, [&#039;৩&#039;]=&#039;3&#039;, [&#039;৪&#039;]=&#039;4&#039;, [&#039;৫&#039;]=&#039;5&#039;, [&#039;৬&#039;]=&#039;6&#039;, [&#039;৭&#039;]=&#039;7&#039;, [&#039;৮&#039;]=&#039;8&#039;, [&#039;৯&#039;]=&#039;9&#039;,<br /> -- Myanmar independent vowels<br /> [&#039;အ&#039;]=&#039;a&#039;, [&#039;အာ&#039;]=&#039;ā&#039;, [&#039;ဣ&#039;]=&#039;i&#039;, [&#039;ဤ&#039;]=&#039;ī&#039;, [&#039;ဥ&#039;]=&#039;u&#039;, [&#039;ဦ&#039;]=&#039;ū&#039;, [&#039;ၒ&#039;]=&#039;ṛ&#039;, [&#039;ၓ&#039;]=&#039;ṝ&#039;,<br /> [&#039;ၔ&#039;]=&#039;ḷ&#039;, [&#039;ၕ&#039;]=&#039;ḹ&#039;, [&#039;ဧ&#039;]=&#039;e&#039;, [&#039;အဲ&#039;]=&#039;ai&#039;, [&#039;ဩ&#039;]=&#039;o&#039;, [&#039;ဪ&#039;]=&#039;au&#039;, -- 2 of these are multi-character keys!<br /> -- Mon<br /> [&#039;ဣဳ&#039;] = &#039;ī&#039;, [&#039;ဥု&#039;] = &#039;ū&#039;, [&#039;ဨ&#039;] = &#039;e&#039;,<br /> -- Shan<br /> [&#039;ဢ&#039;] = &#039;a&#039;, [&#039;ဢႃ&#039;] = &#039;ā&#039;, [&#039;ဢိ&#039;] = &#039;i&#039;, [&#039;ဢီ&#039;] = &#039;ī&#039;, [&#039;ဢု&#039;] = &#039;u&#039;, [&#039;ဢူ&#039;] = &#039;ū&#039;,<br /> [&#039;ဢေ&#039;] = &#039;e&#039;, [&#039;ဢေႃ&#039;] = &#039;o&#039;, [&#039;ဢဲ&#039;] = &#039;ai&#039;, [&#039;ဢော်&#039;] = &#039;au&#039;,<br /> -- chandrabindu, anusvara, visarga &amp; avagraha<br /> -- [dc(&#039;က&#039;)]=&#039;m̐&#039;, <br /> [dc(&#039;ကံ&#039;)]=&#039;ṃ&#039;, [&#039;း&#039;]=&#039;ḥ&#039;,<br /> -- [&#039;&#039;]=&#039;’&#039;,<br /> --numerals<br /> [&#039;၀&#039;]=&#039;0&#039;, [&#039;၁&#039;]=&#039;1&#039;, [&#039;၂&#039;]=&#039;2&#039;, [&#039;၃&#039;]=&#039;3&#039;, [&#039;၄&#039;]=&#039;4&#039;, [&#039;၅&#039;]=&#039;5&#039;, [&#039;၆&#039;]=&#039;6&#039;, [&#039;၇&#039;]=&#039;7&#039;, [&#039;၈&#039;]=&#039;8&#039;, [&#039;၉&#039;]=&#039;9&#039;,<br /> -- Lanna independent vowels<br /> [&#039;ᩋ&#039;]=&#039;a&#039;, [&#039;ᩋᩣ&#039;]=&#039;ā&#039;, [&#039;ᩍ&#039;]=&#039;i&#039;, [&#039;ᩎ&#039;]=&#039;ī&#039;, [&#039;ᩏ&#039;]=&#039;u&#039;, [&#039;ᩐ&#039;]=&#039;ū&#039;, [&#039;ᩂ&#039;]=&#039;ṛ&#039;, -- [&#039;&#039;]=&#039;ṝ&#039;,<br /> [&#039;ᩄ&#039;]=&#039;ḷ&#039;,<br /> -- [&#039;&#039;]=&#039;ḹ&#039;,<br /> [&#039;ᩑ&#039;]=&#039;e&#039;, [&#039;ᩒ&#039;]=&#039;o&#039;, [&#039;ᩋᩰ&#039;] = &#039;o&#039;, [&#039;ᩋᩮᩣ&#039;]=&#039;o&#039;, [&#039;ᩐᩣ&#039;] = &#039;au&#039;, [&#039;ᩋᩱ&#039;] = &#039;ai&#039;,<br /> -- [&#039;&#039;]=&#039;ai&#039;, [&#039;&#039;]=&#039;au&#039;, <br /> -- chandrabindu, anusvara, visarga &amp; avagraha<br /> -- [dc(&#039;&#039;)]=&#039;m̐&#039;,<br /> [dc(&#039;ᨠᩴ&#039;)]=&#039;ṃ&#039;, [&#039;ᩡ&#039;]=&#039;ḥ&#039;, [dc(&#039;ᨠᩘ&#039;)]=&#039;ṅ&#039;,<br /> -- [&#039;&#039;]=&#039;’&#039;,<br /> --numerals<br /> [&#039;᪀&#039;]=&#039;0&#039;, [&#039;᪁&#039;]=&#039;1&#039;, [&#039;᪂&#039;]=&#039;2&#039;, [&#039;᪃&#039;]=&#039;3&#039;, [&#039;᪄&#039;]=&#039;4&#039;, [&#039;᪅&#039;]=&#039;5&#039;, [&#039;᪆&#039;]=&#039;6&#039;, [&#039;᪇&#039;]=&#039;7&#039;, [&#039;᪈&#039;]=&#039;8&#039;, [&#039;᪉&#039;]=&#039;9&#039;,<br /> [&#039;᪐&#039;]=&#039;0&#039;, [&#039;᪑&#039;]=&#039;1&#039;, [&#039;᪒&#039;]=&#039;2&#039;, [&#039;᪓&#039;]=&#039;3&#039;, [&#039;᪔&#039;]=&#039;4&#039;, [&#039;᪕&#039;]=&#039;5&#039;, [&#039;᪖&#039;]=&#039;6&#039;, [&#039;᪗&#039;]=&#039;7&#039;, [&#039;᪘&#039;]=&#039;8&#039;, [&#039;᪙&#039;]=&#039;9&#039;,<br /> -- Khmer independent vowels<br /> [&#039;អ&#039;]=&#039;a&#039;, [&#039;អា&#039;]=&#039;ā&#039;, [&#039;ឥ&#039;]=&#039;i&#039;, [&#039;ឦ&#039;]=&#039;ī&#039;, [&#039;ឧ&#039;]=&#039;u&#039;, [&#039;ឨ&#039;]=&#039;ū&#039;, [&#039;ឫ&#039;]=&#039;ṛ&#039;, [&#039;ឬ&#039;]=&#039;ṝ&#039;,<br /> [&#039;ឭ&#039;]=&#039;ḷ&#039;, [&#039;ឮ&#039;]=&#039;ḹ&#039;, [&#039;ឯ&#039;]=&#039;e&#039;, [&#039;ឰ&#039;]=&#039;ai&#039;, [&#039;ឱ&#039;]=&#039;o&#039;, [&#039;ឲ&#039;]=&#039;o&#039;, [&#039;ឳ&#039;]=&#039;au&#039;, <br /> -- chandrabindu, anusvara, visarga &amp; avagraha<br /> -- [dc(&#039;ក&#039;)]=&#039;m̐&#039;,<br /> [dc(&#039;កំ&#039;)]=&#039;ṃ&#039;, [&#039;ះ&#039;]=&#039;ḥ&#039;,<br /> -- [&#039;&#039;]=&#039;’&#039;,<br /> --numerals<br /> [&#039;០&#039;]=&#039;0&#039;, [&#039;១&#039;]=&#039;1&#039;, [&#039;២&#039;]=&#039;2&#039;, [&#039;៣&#039;]=&#039;3&#039;, [&#039;៤&#039;]=&#039;4&#039;, [&#039;៥&#039;]=&#039;5&#039;, [&#039;៦&#039;]=&#039;6&#039;, [&#039;៧&#039;]=&#039;7&#039;, [&#039;៨&#039;]=&#039;8&#039;, [&#039;៩&#039;]=&#039;9&#039;,<br /> [&#039;៰&#039;]=&#039;0&#039;, [&#039;៱&#039;]=&#039;1&#039;, [&#039;៲&#039;]=&#039;2&#039;, [&#039;៳&#039;]=&#039;3&#039;, [&#039;៴&#039;]=&#039;4&#039;, [&#039;៵&#039;]=&#039;5&#039;, [&#039;៶&#039;]=&#039;6&#039;, [&#039;៷&#039;]=&#039;7&#039;, [&#039;៸&#039;]=&#039;8&#039;, [&#039;៹&#039;]=&#039;9&#039;,<br /> -- Thai miscellanea<br /> -- independent vowels<br /> [&#039;ฤ&#039;]=&#039;ṛ&#039;, [&#039;ฤๅ&#039;]=&#039;ṝ&#039;, [&#039;ฦ&#039;]=&#039;ḷ&#039;, [&#039;ฦๅ&#039;]=&#039;ḹ&#039;,<br /> -- chandrabindu, anusvara, visarga &amp; avagraha<br /> -- [dc(&#039;ក&#039;)]=&#039;m̐&#039;,<br /> [dc(&#039;กํ&#039;)]=&#039;ṃ&#039;, [&#039;ะ&#039;]=&#039;ḥ&#039;,<br /> -- [&#039;&#039;]=&#039;’&#039;,<br /> --numerals<br /> [&#039;๐&#039;]=&#039;0&#039;, [&#039;๑&#039;]=&#039;1&#039;, [&#039;๒&#039;]=&#039;2&#039;, [&#039;๓&#039;]=&#039;3&#039;, [&#039;๔&#039;]=&#039;4&#039;, [&#039;๕&#039;]=&#039;5&#039;, [&#039;๖&#039;]=&#039;6&#039;, [&#039;๗&#039;]=&#039;7&#039;, [&#039;๘&#039;]=&#039;8&#039;, [&#039;๙&#039;]=&#039;9&#039;,<br /> -- Lao miscellanea<br /> -- chandrabindu, anusvara, visarga &amp; avagraha<br /> -- [dc(&#039;ក&#039;)]=&#039;m̐&#039;,<br /> [dc(&#039;ກໍ&#039;)]=&#039;ṃ&#039;, [&#039;ະ&#039;]=&#039;ḥ&#039;,<br /> -- [&#039;&#039;]=&#039;’&#039;,<br /> --numerals<br /> [&#039;໐&#039;]=&#039;0&#039;, [&#039;໑&#039;]=&#039;1&#039;, [&#039;໒&#039;]=&#039;2&#039;, [&#039;໓&#039;]=&#039;3&#039;, [&#039;໔&#039;]=&#039;4&#039;, [&#039;໕&#039;]=&#039;5&#039;, [&#039;໖&#039;]=&#039;6&#039;, [&#039;໗&#039;]=&#039;7&#039;, [&#039;໘&#039;]=&#039;8&#039;, [&#039;໙&#039;]=&#039;9&#039;,<br /> -- All scripts<br /> --punctuation <br /> [&#039;॥&#039;]=&#039;.&#039;, [&#039;။&#039;]=&#039;.&#039;, [&#039;᪩&#039;]=&#039;.&#039;, [&#039;᪫&#039;]=&#039;.&#039;, [&#039;៕&#039;]=&#039;.&#039;, [&#039;๚&#039;]=&#039;.&#039;, --double danda<br /> [&#039;।&#039;]=&#039;.&#039;, [&#039;၊&#039;]=&#039;.&#039;, [&#039;‌᪨&#039;]=&#039;.&#039;, [&#039;᪪&#039;]=&#039;.&#039;, [&#039;។&#039;]=&#039;.&#039;, [&#039;ฯ&#039;]=&#039;.&#039;, [&#039;ຯ&#039;]=&#039;.&#039;, --danda<br /> --Vedic extensions<br /> [&#039;ᳵ&#039;]=&#039;x&#039;, [&#039;ᳶ&#039;]=&#039;f&#039;,<br /> --Om<br /> -- [&#039;ॐ&#039;]=&#039;oṃ&#039;,<br /> --reconstructed<br /> [&#039;*&#039;] = &#039;&#039;,<br /> }<br /> -- Also handle subscript consonants encoded as marks.<br /> local S = dc(&#039;ကျကြကွကှကၞကၟကၠ&#039;).. -- Myanmar subscripts<br /> dc(&#039;ᨠᩕᨠᩖᨠᩛᨠᩜᨠᩝᨠᩞ&#039;) -- Lanna subscripts<br /> -- consonants and part 1 of NFC-multi-part independent vowels.<br /> local C = &#039;[কখগঘঙচছজঝঞটঠডঢণতথদধনপফবভমযরলवळশষসহৰৱ&#039;.. -- Bengali<br /> &#039;ကခဂဃငစဆဇဈဉဋဌဍဎဏတထဒဓနပဖဗဘမယရလဝဠၐၑသဟညဿအ&#039;.. -- Myanmar Part 1<br /> &#039;ၚၛၵၶၷꧠၸꧡၹꧢၺꩦꩧꩨꩩꧣၻꩪၼၽၿꧤꩮႁဢဣဥ&#039;.. -- Myanmar Part 2 (Mon and Shan)<br /> &#039;ᨠᨡᨣᨥᨦᨧᨨᨩᨫᨬᨭᨮᨯᨰᨱᨲᨳᨴᨵᨶᨷᨸᨹᨻᨽᨾᨿᩁᩃᩅᩊᩆᩇᩈᩉᩔᩋᩐ&#039;.. -- Lanna<br /> &#039;កខគឃងចឆជឈញដឋឌឍណតថទធនបផពភមយរលវឡឝសឞហអ&#039;.. -- Khmer<br /> &#039;กขคฆงจฉชฌญฏฐฑฒณตถทธนปผพภมยรลวศษสหฬอฤฦ&#039;.. -- Thai.<br /> &#039;ກຂຄຆງຈຉຊຌຎຏຐຑຒຓຕຖທຘນປຜພຠມຍຢຣລວຨຩສຫຬອ&#039;.. -- Lao<br /> &#039;ດບ&#039;.. -- Backstop for Lao<br /> S..&#039;][&#039;..u(0x09bc, 0x200d)..&#039;]?&#039; -- And allow Bengali nukta or necessary ZWJ.<br /> <br /> -- One character diacritics <br /> local dia = <br /> dc(&#039;[কাকিকীকুকূকৃকৄকৢকৣকেকৈকোকৌক্&#039;.. -- Bengali<br /> &#039;ကာကါကိကီကုကူကၖကၗကၘကၙကေကဲက္က်ကဳကႃ&#039;.. -- Myanmar<br /> &#039;ᨠᩣᨠᩤᨠᩥᨠᩦᨠᩩᨠᩪᩂᩄᨠᩮᨠᩱᨠᩰᨠ᩠ᨠ᩺ᨠ᩼&#039;.. -- Lanna<br /> &#039;ᨠᩫᩢ&#039;.. -- Lanna diacritics in second or third place.<br /> &#039;កាកិកីកុកូកេកៃកោកៅក្ក៑&#039;.. -- Khmer<br /> &#039;กักุิกูีเโไาๅฤฦกฺกึก์&#039;.. -- Thai<br /> &#039;ກັກຸິກູີເກົາໂໄກ຺ກຶກ໌&#039;.. -- Lao<br /> &#039;]&#039;)<br /> local diax = {}<br /> local ti = table.insert;<br /> ti(diax, &#039;(&#039;)<br /> ti(diax, dia) ti(diax, &#039;?&#039;)<br /> ti(diax, dia) ti(diax, &#039;?&#039;)<br /> ti(diax, dia) ti(diax, &#039;?&#039;)<br /> ti(diax, dia) ti(diax, &#039;?)&#039;)<br /> diax = table.concat(diax)<br /> local explicit = nil<br /> if options and options.impl then<br /> if options.impl == &#039;yes&#039; then<br /> explicit = false<br /> elseif options.impl == &#039;no&#039; then<br /> explicit = true<br /> end<br /> end<br /> if sc == &#039;Khmr&#039; then<br /> dep_liquid = &#039;(&#039;..C..dc(&#039;)(ក្)&#039;)..&#039;([ឫឬឭឮ])&#039;; -- Avoid gsub in gsub bug.<br /> text = gsub(<br /> text, dep_liquid,<br /> function(c, j, d) return consonants[c]..d end<br /> )<br /> -- Regularise robat<br /> robat_fix3 = &#039;(&#039;..C..dc(&#039;ក្&#039;)..C..dc(&#039;ក្&#039;)..C..&#039;)(&#039;..dc(&#039;ក៌)&#039;)<br /> robat_fix2 = &#039;(&#039;..C..dc(&#039;ក្&#039;)..C..&#039;)(&#039;..dc(&#039;ក៌)&#039;)<br /> robat_fix1 = &#039;(&#039;..C..&#039;)(&#039;..dc(&#039;ក៌)&#039;)<br /> derobatted = &#039;រ្&#039;..&#039;%1&#039;<br /> text = gsub(text, robat_fix3, derobatted)<br /> text = gsub(text, robat_fix2, derobatted)<br /> text = gsub(text, robat_fix1, derobatted)<br /> elseif sc == &#039;Thai&#039; or sc == &#039;Laoo&#039; then<br /> local v1 = dc(&#039;[กัກັ]&#039;)<br /> local v2 = dc(&#039;[กัะກັະ]&#039;)<br /> local va = dc(&#039;[กฺ]&#039;)<br /> if lang == &#039;sa&#039; then<br /> if match(text, v1) then explicit = true end -- SARA A is visarga!<br /> else<br /> if match(text, v2) then explicit = true end<br /> end<br /> local yLao, nuktaed<br /> if sc == &#039;Laoo&#039; then<br /> if options and options.y then<br /> if options.y == &#039;yaa&#039; or options.y == &#039;ຢ&#039; then<br /> yLao = &#039;yaa&#039;<br /> elseif options.y == &#039;yung&#039; or options.y == &#039;ຍ&#039; then<br /> yLao = &#039;yung&#039;<br /> end<br /> end<br /> if not yLao then<br /> if match(text, &#039;ຢ&#039;) then<br /> yLao = &#039;yaa&#039;<br /> else<br /> yLao = &#039;yung&#039;<br /> end<br /> end<br /> if explicit then<br /> nuktaed = match(text, u(0xeba))<br /> else<br /> local str<br /> if lang == &#039;sa&#039; then<br /> str = dc(&#039;ກ຺[ກັາກຸິກູີ]&#039;)<br /> else<br /> str = dc(&#039;ກ຺[ກັາກຸິກູີະ]&#039;)<br /> end<br /> nuktaed = match(text, str)<br /> end<br /> if nuktaed then -- Convert to extended alphabet<br /> rs = {<br /> [&quot;ຄ຺&quot;] = &quot;ຆ&quot;, [&quot;ສ຺&quot;] = &quot;ຉ&quot;, [&quot;ຊ຺&quot;] = &quot;ຌ&quot;, [&quot;ຍ຺&quot;] = &quot;ຎ&quot;,<br /> [&quot;ຕ຺&quot;] = &quot;ຏ&quot;, [&quot;ຖ຺&quot;] = &quot;ຐ&quot;, [&quot;ດ&quot;] = &quot;ຑ&quot;, [&quot;ນ຺&quot;] = &quot;ຓ&quot;,<br /> [&quot;ທ຺&quot;] = &quot;ຘ&quot;, [&quot;ພ຺&quot;] = &quot;ຠ&quot;, [&quot;ລ຺&quot;] = &quot;ຬ&quot;, [&quot;ງ຺&quot;] = dc(&quot;ໍກ&quot;),<br /> }<br /> text = gsub(text, &#039;[ຄສຊຍຕຖດນທພລງ]&#039;..u(0xeba)..&#039;?&#039;, rs)<br /> explicit = true<br /> end<br /> if yLao == &#039;yaa&#039; then text = gsub(text, &#039;ຍ&#039;, &#039;ຎ&#039;) end<br /> end<br /> if match(text, va) then explicit = false end<br /> if explicit == nil then<br /> -- It looks as though gsub (from dc()) and match interfere, so need local variables.<br /> local ngf1=dc(&#039;[กักิกุກັກິກຸ][งງ]$&#039;)<br /> local ngf2=dc(&#039;[กักิกุກັກິກຸ][งງ] &#039;)<br /> if (match(text, ngf1) or match(text, ngf2)) then explicit = true end<br /> end<br /> if not explicit then<br /> diax = gsub(diax, &#039;[ฤฦ]&#039;, &#039;า&#039;) -- Treat as ฤ and ฦ consonants.<br /> local search = &#039;([เโไເໂໄ])(&#039;..C..&#039;)([&#039;..u(0x0e3a, 0xeba)..&#039;])&#039;<br /> local longswap = function(p, c, v) return c..v..p end <br /> text = gsub(text, search, longswap)<br /> text = gsub(text, search, longswap)<br /> end<br /> if false and sc == &#039;Laoo&#039; then -- Keep around for future debugging<br /> local nr = &#039;F&#039;<br /> if nuktaed then nr = &#039;T&#039; end<br /> if yLao then<br /> nr = nr .. yLao<br /> else<br /> nr = nr .. &#039;y?&#039;<br /> end<br /> nr = nr .. &#039;-&#039;<br /> if not options or not options.impl then<br /> if explicit == nil then<br /> text = &#039;GN-&#039;..nr..text<br /> elseif explicit == false then<br /> text = &#039;GI-&#039;..nr..text<br /> else<br /> text = &#039;GE-&#039;..nr..text<br /> end<br /> elseif options.impl == &#039;both&#039; then<br /> if explicit == nil then<br /> text = &#039;N-&#039;..nr..text<br /> elseif explicit == false then<br /> text = &#039;I-&#039;..nr..text<br /> else<br /> text = &#039;E-&#039;..nr..text<br /> end<br /> elseif options.impl == &#039;yes&#039; then<br /> text = &#039;Y-&#039;..nr..text<br /> elseif options.impl == &#039;no&#039; then<br /> text = &#039;N-&#039;..nr..text<br /> elseif options.impl then<br /> text = options.impl .. nr .. text<br /> end<br /> end<br /> local pair = &#039;([เโไເໂໄ])(&#039;..C..&#039;)&#039;<br /> text = gsub(text, pair, &#039;%2%1&#039;)<br /> if explicit and lang ~= &#039;sa&#039; then -- SARA A is a vowel.<br /> diax = &#039;([ะະ&#039;..string.sub(diax,3)<br /> end<br /> if explicit and sc == &#039;Laoo&#039; then -- Clean up clusters<br /> ass = {<br /> [&quot;ກຄ&quot;] = &quot;ຄຄ&quot;, [&quot;ດຈ&quot;] = &quot;ຈຈ&quot;, [&quot;ດຊ&quot;] = &quot;ຊຊ&quot;, [&quot;ດມ&quot;] = &quot;ສມ&quot;,<br /> [&quot;ດຕ&quot;] = &quot;ຕຕ&quot;, [&quot;ດຖ&quot;] = &quot;ຕຖ&quot;, [&quot;ດທ&quot;] = &quot;ທທ&quot;, [&quot;ດສ&quot;] = &quot;ສສ&quot;,<br /> [&quot;ຍຈ&quot;] = &quot;ຎຈ&quot;, [&quot;ຍສ&quot;] = &quot;ຎຉ&quot;, [&quot;ຍຊ&quot;] = &quot;ຎຊ&quot;,<br /> [&quot;ນຈ&quot;] = &quot;ນຈ&quot;, [&quot;ນສ&quot;] = &quot;ຎຉ&quot;, [&quot;ນຊ&quot;] = &quot;ຎຊ&quot;, [&quot;ນຍ&quot;] = &quot;ຎຎ&quot;,<br /> [&quot;ບປ&quot;] = &quot;ປປ&quot;, [&quot;ບຜ&quot;] = &quot;ປຜ&quot;, [&quot;ບພ&quot;] = &quot;ພພ&quot;, [&quot;ບ&quot;] = &quot;ປ&quot;,<br /> }<br /> text = gsub(text, &#039;[ກດບຍນ][ຄຕຖທປຜພສລຈສຊຍມ]?&#039;, ass)<br /> end<br /> end<br /> if sc == &#039;Lana&#039; then<br /> -- Disambiguate lanna combining loop below.<br /> cl_search = dc(&#039;[ᨲᨻᨾ]ᨠᩛ&#039;)<br /> text = gsub(text, cl_search,<br /> {[&#039;ᨲᩛ&#039;]=&#039;ᨲ᩠ᨳ&#039;, [&#039;ᨻᩛ&#039;]=&#039;ᨻ᩠ᨻ&#039;, [&#039;ᨾᩛ&#039;]=&#039;ᨾ᩠ᨻ&#039;}) <br /> end<br /> if sc == &#039;Mymr&#039; or sc == &#039;Lana&#039; then<br /> local fn = function(c, d) return consonants[c]..d end<br /> local search = &#039;(&#039;..C..&#039;)([&#039;..S..&#039;])&#039;<br /> text = gsub(text, search, fn);<br /> text = gsub(text, search, fn); -- and again<br /> end<br /> if sc == &#039;Beng&#039; then<br /> -- Aberrant conversion:<br /> text = gsub(text, u(0x09b2, 0x9cd, 0x9bc, 0x9cd, 0x9b9), &#039;ḷহ&#039;) -- raw<br /> text = gsub(text, u(0x09b2, 0x9bc, 0x9cd, 0x9cd, 0x9b9), &#039;ḷহ&#039;) -- NFC<br /> -- Proper conversion:<br /> text = gsub(text, u(0x09b2, 0x9cd, 0x9bc, 0x9b9), &#039;ḷহ&#039;) -- not NFC<br /> -- text = gsub(text, u(0x09b2, 0x9bc, 0x9cd, 0x9b9), &#039;ḷহ&#039;) -- NFC<br /> end<br /> text = gsub(text, &#039;(&#039;..C..&#039;)&#039;..diax,<br /> function(c, d)<br /> local val = tt[c..d]<br /> if val then return val end<br /> local cn = consonants[c]<br /> if not cn then return &#039;X(&#039;..c..&#039;)&#039; end<br /> if d ~= &quot;&quot; then <br /> return cn .. (diacritics[d] or &#039;NIL(&#039;..d..&#039;)&#039;)<br /> elseif explicit then<br /> return cn<br /> else<br /> return cn .. &#039;a&#039;<br /> end<br /> end<br /> )<br /> text = gsub(text, &#039;.&#039;, tt)<br /> -- Bodge alphabetic Thai and Lao anusvara<br /> if explicit and text then<br /> text = gsub(text, &#039;ṅ$&#039;, &#039;ṃ&#039;)<br /> text = gsub(text, &#039;ṅ([^kg])&#039;, &#039;ṃ%1&#039;)<br /> end<br /> else <br /> text = nil -- Not ready for use yet!<br /> end<br /> return text<br /> end<br /> <br /> function export.tr(text, lang, sc)<br /> return export.trwo(text, lang, sc, {})<br /> end<br /> <br /> return export</div> wikt>SurjectionBot