https://linguifex.com/w/index.php?action=history&feed=atom&title=Module%3APolyt-stripdiacritics 2026-05-23T20:05:00Z Revision history for this page on the wiki MediaWiki 1.43.6 https://linguifex.com/w/index.php?title=Module:Polyt-stripdiacritics&diff=512660&oldid=prev 2026-05-07T14:25:37Z

<p>Created page with &quot;local export = {} local toNFC = mw.ustring.toNFC local toNFD = mw.ustring.toNFD local u = require(&quot;Module:string/char&quot;) local ugsub = mw.ustring.gsub local umatch = mw.ustring.match local grave = u(0x300) local acute = u(0x301) local smooth = u(0x313) local rough = u(0x314) local word_ch = &quot;[%w&quot; .. grave .. acute .. smooth .. rough .. u(0x308, 0x342, 0x345) .. &quot;]&quot; local following_word_pattern = &quot;^&quot; .. word_ch .. &quot;*%s+&quot; .. word_ch -- not punctuation local breathing_ch...&quot;</p> <p><b>New page</b></p><div>local export = {}<br /> <br /> local toNFC = mw.ustring.toNFC<br /> local toNFD = mw.ustring.toNFD<br /> local u = require(&quot;Module:string/char&quot;)<br /> local ugsub = mw.ustring.gsub<br /> local umatch = mw.ustring.match<br /> <br /> local grave = u(0x300)<br /> local acute = u(0x301)<br /> local smooth = u(0x313)<br /> local rough = u(0x314)<br /> <br /> local word_ch = &quot;[%w&quot; .. grave .. acute .. smooth .. rough .. u(0x308, 0x342, 0x345) .. &quot;]&quot;<br /> local following_word_pattern = &quot;^&quot; .. word_ch .. &quot;*%s+&quot; .. word_ch -- not punctuation<br /> <br /> local breathing_ch = &quot;[&quot; .. smooth .. rough .. &quot;]&quot;<br /> local rho_cap_smooth_sub = u(0x1FDC) -- temporary (unused) codepoint for Ρ̓, which has no atomic codepoint<br /> local rho = &quot;[ρῤῥΡ&quot; .. rho_cap_smooth_sub .. &quot;Ῥ]&quot;<br /> local two_or_more_rhos = rho .. rho .. &quot;+&quot;<br /> local expected_rho_breathings = &quot;^[ρῤΡ&quot; .. rho_cap_smooth_sub .. &quot;]+[ρῥΡῬ]$&quot;<br /> <br /> local Grek_stripDiacritics = require(&quot;Module:Grek-common&quot;).stripDiacritics<br /> <br /> function export.stripDiacritics(text, lang, sc)<br /> -- Do some substitutions done for all Greek text.<br /> text = Grek_stripDiacritics(text, lang, sc)<br /> -- Remove length marks and double undertie.<br /> text = toNFD(text):gsub(&quot;\204[\132\134]&quot;, &quot;&quot;):gsub(&quot;\205\156&quot;, &quot;&quot;)<br /> -- Convert grave to acute unless followed by another word.<br /> text = ugsub(text, grave .. &quot;()&quot;, function(pos)<br /> if not umatch(text, following_word_pattern, pos) then<br /> return acute<br /> end<br /> end)<br /> -- Convert &quot;ῤῥ&quot; to &quot;ρρ&quot;.<br /> text = ugsub(toNFC(text):gsub(&quot;Ρ̓&quot;, rho_cap_smooth_sub), two_or_more_rhos, function(rhos)<br /> if umatch(rhos, expected_rho_breathings) then<br /> return (toNFD(rhos:gsub(rho_cap_smooth_sub, &quot;Ρ̓&quot;)):gsub(breathing_ch, &quot;&quot;))<br /> end<br /> end):gsub(rho_cap_smooth_sub, &quot;Ρ̓&quot;)<br /> return toNFC(text)<br /> end<br /> <br /> return export</div>

Sware