var http = require('http'), sys = require('sys');
module.exports = {
cleanit: function (req, res) {
var r = {
// from http://tim.mackey.ie/CleanWordHTMLUsingRegularExpressions.aspx
msoTags: /<[\/]?(font|span|xml|del|ins|[ovwxp]:\w+)[^>]*?>/g,
msoAttributes: /<([^>]*)(?:class|lang|style|size|face|[ovwxp]:\w+)=(?:'[^']*'|""[^""]*""|[^\s>]+)([^>]*)>/,
msoParagraphs: /<([^>]*)(?:|[p]:\w+)=(?:'[^']*'|""[^""]*""|[^\s>]+)([^>]*)>/g,
crlf: /(\\r\\n)/g
};
var front = '\r\n \r\n \r\n \r\n Spellbinder - Chapter \r\n \r\n \r\n \r\n \r\n ';
var source = req.body.source;
// console.log(source);
var output = source.replace(r.msoTags, "");
output = output.replace(r.msoParagraphs, '');
output = output.replace(/(\r\n)/g, " ");
output = output.replace(/(\\r\\n)/g, " ");
output = output.replace(/<\/i>/g, "");
output = output.replace(/[“|”]/g, '"');
output = output.replace(/’/g, "'");
output = output.replace(/…/g, "…");
output = output.replace(/(.*?)<\/i>/g, "$1");
output = output.replace(/(.*?)<\/b>/g, "$1");
output = output.replace(/
\*\*\*<\/p>/g, "
* * *
");
output = output.replace(/CHAPTER\s(\d.?)<\/p>/, "
$1
");
output = output.replace(/( |\s|\s<\/em>)<\/p>/g, "");
output = output.replace(/ /g, " ");
output = output.replace(/\s<\/em><\/p>/g, "");
output = output.replace(/\s<\/p>/g, "");
output = output.replace(/\s+/g, " ");
output = output.replace(/<\/p>/g, "
\r\n");
// sys.puts(sys.inspect(output, false, null));
res.setHeader('Content-Type', 'application/html');
res.end(front + output + back);
}
};