Wikipedia:AutoEd/unicodehex.js
// Purpose: Changes hexcharacter codes in wikilinks to actual unicode characters
//
// History ->
// History
//
// Note: Contributed by CharlotteWeb
//
// Comments (CharlotteWeb):
// To keep things simple we'll ignore all image links. because some people prefer
// underscores in the file name and the caption can contain god-knows-what.
// one easy way is to flag them with a character which should never be used,
// but if it is already present we have a problem, so let's just quit.
//
function autoEdUnicodeHex(txt) { //MAIN FUNCTION describes list of fixes
if(txt.match(/\uE000/)) return(txt); // see Private Use Area
txt = txt.replace(/(\[\[[\:\s*]*(?:Image|File|Media)\s*\:)/gi, "$1\uE000");
if(m = txt.match(/\[\[[^\[\]\n\uE000]+\]\]/g)) {
for(var i = 0; i < m.length; i++) {
parts = m[i].split("|");
link = parts[0];
a = link.split("#")
title = a[0];
section = a[1];
try {
link = decodeURIComponent(title.replace(/\%(.[^0-9A-F]|[^0-9A-F].|$)/gi, "%25$1")
) + ( section ? ("#" + decodeURIComponent(section
// change "&#" to "%" when followed by valid hex
.replace(/&#([0-9A-F]{2})/gi, "%$1")
.replace(/\%(.[^0-9A-F]|[^0-9A-F].|$)/gi, "%25$1")
)
) : "" )
} catch(e) { } // just do no decoding
parts[0] = link;
txt = txt.replace(m[i], parts.join("|"));
}
}
return(txt.replace(/\uE000/g, ""));
}