X-Git-Url: http://git.roojs.org/?p=roojs1;a=blobdiff_plain;f=roojs-ui-debug.js;fp=roojs-ui-debug.js;h=699aabf81ab3a453bd83d9acc270c4b02183456d;hp=2b80d0bc529a02d8bec9e1207bee0932b709223a;hb=c2162fa64f4d6cb2a21a9296cdf9c79ab00ece5e;hpb=956622cdc1f0584adc4f530747c1cfcd1f26b1a7 diff --git a/roojs-ui-debug.js b/roojs-ui-debug.js index 2b80d0bc52..699aabf81a 100644 --- a/roojs-ui-debug.js +++ b/roojs-ui-debug.js @@ -20799,17 +20799,32 @@ Roo.extend(Roo.HtmlEditorCore, Roo.Component, { html = this.cleanHtml(html); // fix up the special chars.. normaly like back quotes in word... // however we do not want to do this with chinese.. - html = html.replace(/([\x80-\uffff])/g, function (a, b) { - var cc = b.charCodeAt(); - if ( + html = html.replace(/[\uD800-\uDBFF][\uDC00-\uDFFF]|[\u0080-\uFFFF]/g, function(match) { + + var cc = match.charCodeAt(); + + // Get the character value, handling surrogate pairs + if (match.length == 2) { + // It's a surrogate pair, calculate the Unicode code point + var high = match.charCodeAt(0) - 0xD800; + var low = match.charCodeAt(1) - 0xDC00; + cc = (high * 0x400) + low + 0x10000; + } else if ( (cc >= 0x4E00 && cc < 0xA000 ) || (cc >= 0x3400 && cc < 0x4E00 ) || (cc >= 0xf900 && cc < 0xfb00 ) ) { - return b; - } - return "&#"+cc+";" + return match; + } + + // No, use a numeric entity. Here we brazenly (and possibly mistakenly) + return "&#" + cc + ";"; + + }); + + + if(this.owner.fireEvent('beforesync', this, html) !== false){ this.el.dom.value = html; this.owner.fireEvent('sync', this, html);