public string DoTidy(string html)
{
Tidy.Core.Tidy document = new Tidy.Core.Tidy();
TidyMessageCollection messageCollection = new TidyMessageCollection();
document.Options.DocType = DocType.Omit;
document.Options.Xhtml = true;
document.Options.CharEncoding = CharEncoding.Utf8;
document.Options.LogicalEmphasis = true;
document.Options.MakeClean = false;
document.Options.QuoteNbsp = false;
document.Options.SmartIndent = false;
document.Options.IndentContent = false;
document.Options.TidyMark = false;
document.Options.DropFontTags = false;
document.Options.QuoteAmpersand = true;
document.Options.DropEmptyParas = true;
MemoryStream input = new MemoryStream();
MemoryStream output = new MemoryStream();
byte[] array = Encoding.UTF8.GetBytes(html);
input.Write(array, 0, array.Length);
input.Position = 0;
document.Parse(input, output, messageCollection);
string tidyXhtml = Encoding.UTF8.GetString(output.ToArray(), 0, output.ToArray().Length);
return(XElement.Parse(tidyXhtml).ToString());
}
public override void Write(byte[] buffer, int offset, int count)
{
var data = new byte[count];
Buffer.BlockCopy(buffer, offset, data, 0, count);
string html = Encoding.UTF8.GetString(buffer);
using (var input = new MemoryStream())
{
using (var output = new MemoryStream())
{
byte[] byteArray = Encoding.UTF8.GetBytes(html);
input.Write(byteArray, 0, byteArray.Length);
input.Position = 0;
_tidy.Parse(input, output, new TidyMessageCollection());
string result = Encoding.UTF8.GetString(output.ToArray());
byte[] outdata = Encoding.UTF8.GetBytes(result);
_stream.Write(outdata, 0, outdata.GetLength(0));
}
}
}
/// <summary>
/// Pretties the print.
/// </summary>
/// <param name="dirtyHtml">The dirty HTML.</param>
/// <param name="messages">The messages.</param>
/// <returns></returns>
public static string PrettyPrint(string dirtyHtml, out TidyMessageCollection messages)
{
const int spaces = 8;
var tidy = new Tidy.Core.Tidy();
tidy.Options.SmartIndent = true;
tidy.Options.IndentAttributes = false;
tidy.Options.WrapLen = 0;
tidy.Options.Spaces = spaces;
messages = new TidyMessageCollection();
using (var inStream = new MemoryStream(Encoding.Default.GetBytes(dirtyHtml)))
using (var outStream = new MemoryStream())
{
tidy.Parse(inStream, outStream, messages);
return(Encoding.Default.GetString(outStream.ToArray())
.Replace(new string(' ', spaces), '\t'.ToString()));
}
}
