HtmlToHtml Class

An HTML to HTML converter.

Definition

Namespace: MimeKit.Text
Assembly: MimeKit.Core (in MimeKit.Core.dll) Version: 5.0.0
C#
public class HtmlToHtml : TextConverter
Inheritance
Object    TextConverter    HtmlToHtml

Remarks

Used to convert HTML into HTML.

A tag that is truncated by the end of the input (e.g. <img src=x) is dropped rather than being written to the output.

Example

C#
                    /// <summary>
/// Visits a MimeMessage and generates HTML suitable to be rendered by a browser control.
/// </summary>
class HtmlPreviewVisitor : MimeVisitor
{
    List<MultipartRelated> stack = new List<MultipartRelated> ();
    List<MimeEntity> attachments = new List<MimeEntity> ();
    string body;

    /// <summary>
    /// Creates a new HtmlPreviewVisitor.
    /// </summary>
    public HtmlPreviewVisitor ()
    {
    }

    /// <summary>
    /// The list of attachments that were in the MimeMessage.
    /// </summary>
    public IList<MimeEntity> Attachments {
        get { return attachments; }
    }

    /// <summary>
    /// The HTML string that can be set on the BrowserControl.
    /// </summary>
    public string HtmlBody {
        get { return body ?? string.Empty; }
    }

    protected override void VisitMultipartAlternative (MultipartAlternative alternative)
    {
        // walk the multipart/alternative children backwards from greatest level of faithfulness to the least faithful
        for (int i = alternative.Count - 1; i >= 0 && body == null; i--)
            alternative[i].Accept (this);
    }

    protected override void VisitMultipartRelated (MultipartRelated related)
    {
        var root = related.Root;

        // push this multipart/related onto our stack
        stack.Add (related);

        // visit the root document
        root.Accept (this);

        // pop this multipart/related off our stack
        stack.RemoveAt (stack.Count - 1);
    }

    // look up the image based on the img src url within our multipart/related stack
    bool TryGetImage (string url, out MimePart image)
    {
        UriKind kind;
        int index;
        Uri uri;

        if (Uri.IsWellFormedUriString (url, UriKind.Absolute))
            kind = UriKind.Absolute;
        else if (Uri.IsWellFormedUriString (url, UriKind.Relative))
            kind = UriKind.Relative;
        else
            kind = UriKind.RelativeOrAbsolute;

        try {
            uri = new Uri (url, kind);
        } catch {
            image = null;
            return false;
        }

        for (int i = stack.Count - 1; i >= 0; i--) {
            if ((index = stack[i].IndexOf (uri)) == -1)
                continue;

            image = stack[i][index] as MimePart;
            return image != null;
        }

        image = null;

        return false;
    }

    /// <summary>
    /// Get a data: URI for the image attachment.
    /// </summary>
    /// <remarks>
    /// Encodes the image attachment into a string suitable for setting as a src= attribute value in
    /// an img tag.
    /// </remarks>
    /// <returns>The data: URI.</returns>
    /// <param name="image">The image attachment.</param>
    string GetDataUri (MimePart image)
    {
        using (var memory = new MemoryStream ()) {
            image.Content.DecodeTo (memory);
            var buffer = memory.GetBuffer ();
            var length = (int) memory.Length;
            var base64 = Convert.ToBase64String (buffer, 0, length);

            return string.Format ("data:{0};base64,{1}", image.ContentType.MimeType, base64);
        }
    }

    // Replaces <img src=...> urls that refer to images embedded within the message with
    // "file://" urls that the browser control will actually be able to load.
    void HtmlTagCallback (HtmlTagContext ctx, HtmlWriter htmlWriter)
    {
        if (ctx.TagId == HtmlTagId.Meta && !ctx.IsEndTag) {
            bool isContentType = false;

            ctx.WriteTag (htmlWriter, false);

            // replace charsets with "utf-8" since our output will be in utf-8 (and not whatever the original charset was)
            foreach (var attribute in ctx.Attributes) {
                if (attribute.Id == HtmlAttributeId.Charset) {
                    htmlWriter.WriteAttributeName (attribute.Name);
                    htmlWriter.WriteAttributeValue ("utf-8");
                } else if (isContentType && attribute.Id == HtmlAttributeId.Content) {
                    htmlWriter.WriteAttributeName (attribute.Name);
                    htmlWriter.WriteAttributeValue ("text/html; charset=utf-8");
                } else {
                    if (attribute.Id == HtmlAttributeId.HttpEquiv && attribute.Value != null
                        && attribute.Value.Equals ("Content-Type", StringComparison.OrdinalIgnoreCase))
                        isContentType = true;

                    htmlWriter.WriteAttribute (attribute);
                }
            }
        } else if (ctx.TagId == HtmlTagId.Image && !ctx.IsEndTag && stack.Count > 0) {
            ctx.WriteTag (htmlWriter, false);

            // replace the src attribute with a "data:" URL
            foreach (var attribute in ctx.Attributes) {
                if (attribute.Id == HtmlAttributeId.Src) {
                    if (!TryGetImage (attribute.Value, out var image)) {
                        htmlWriter.WriteAttribute (attribute);
                        continue;
                    }

                    var dataUri = GetDataUri (image);

                    htmlWriter.WriteAttributeName (attribute.Name);
                    htmlWriter.WriteAttributeValue (dataUri);
                } else {
                    htmlWriter.WriteAttribute (attribute);
                }
            }
        } else {
            // pass the tag through to the output
            ctx.WriteTag (htmlWriter, true);
        }
    }

    protected override void VisitTextPart (TextPart entity)
    {
        TextConverter converter;

        if (body != null) {
            // since we've already found the body, treat this as an attachment
            attachments.Add (entity);
            return;
        }

        if (entity.IsHtml) {
            converter = new HtmlToHtml {
                HtmlTagCallback = HtmlTagCallback
            };
        } else if (entity.IsFlowed) {
            var flowed = new FlowedToHtml ();
            string delsp;

            if (entity.ContentType.Parameters.TryGetValue ("delsp", out delsp))
                flowed.DeleteSpace = delsp.Equals ("yes", StringComparison.OrdinalIgnoreCase);

            converter = flowed;
        } else {
            converter = new TextToHtml ();
        }

        body = converter.Convert (entity.Text);
    }

    protected override void VisitTnefPart (TnefPart entity)
    {
        // extract any attachments in the MS-TNEF part
        using (var tnef = entity.LoadTnefMessage ()) {
            // the converted message (and its attachments) outlives the TnefMessage
            var result = tnef.ConvertToMime ();

            attachments.AddRange (result.Message.Attachments);
        }
    }

    protected override void VisitMessagePart (MessagePart entity)
    {
        // treat message/rfc822 parts as attachments
        attachments.Add (entity);
    }

    protected override void VisitMimePart (MimePart entity)
    {
        // realistically, if we've gotten this far, then we can treat this as an attachment
        // even if the IsAttachment property is false.
        attachments.Add (entity);
    }
}
                  

Constructors

HtmlToHtml Initialize a new instance of the HtmlToHtml class.

Properties

ComplianceLogger Get or set the logger to use for reporting HTML compliance violations.
ComplianceOptions Get or set the options that control how HTML compliance violations are reported.
DetectEncodingFromByteOrderMark Get or set whether the encoding of the input is detected from the byte order mark or determined by the InputEncoding property.
(Inherited from TextConverter)
FilterComments Get or set whether the converter should remove HTML comments from the output.
Footer Get or set the text that will be appended to the end of the output.
(Inherited from TextConverter)
FooterFormat Get or set the footer format.
Header Get or set text that will be prepended to the beginning of the output.
(Inherited from TextConverter)
HeaderFormat Get or set the header format.
HtmlTagCallback Get or set the HtmlTagCallback method to use for custom filtering of HTML tags and content.
InputEncoding Get or set the input encoding.
(Inherited from TextConverter)
InputFormat Get the input format.
(Overrides TextConverterInputFormat)
InputStreamBufferSize Get or set the size of the input stream buffer.
(Inherited from TextConverter)
MaxElementDepth Get or set the maximum element depth.
NoScriptHandling Get or set how <noscript> elements should be handled.
OutputEncoding Get or set the output encoding.
(Inherited from TextConverter)
OutputFormat Get the output format.
(Overrides TextConverterOutputFormat)
OutputHtmlFragment Get or set whether the converter should only output an HTML fragment.
OutputStreamBufferSize Get or set the size of the output stream buffer.
(Inherited from TextConverter)

Methods

Convert(String) Convert text from the InputFormat to the OutputFormat.
(Inherited from TextConverter)
Convert(Stream, Stream) Convert the contents of source from the InputFormat to the OutputFormat and writes the resulting text to destination.
(Inherited from TextConverter)
Convert(Stream, TextWriter) Convert the contents of source from the InputFormat to the OutputFormat and uses the writer to write the resulting text.
(Inherited from TextConverter)
Convert(TextReader, TextWriter) Convert the contents of reader from the InputFormat to the OutputFormat and uses the writer to write the resulting text.
(Overrides TextConverterConvert(TextReader, TextWriter))
Convert(TextReader, Stream) Convert the contents of reader from the InputFormat to the OutputFormat and writes the resulting text to destination.
(Inherited from TextConverter)
Equals Determines whether the specified object is equal to the current object.
(Inherited from Object)
Finalize Allows an object to try to free resources and perform other cleanup operations before it is reclaimed by garbage collection.
(Inherited from Object)
GetHashCode Serves as the default hash function.
(Inherited from Object)
GetType Gets the Type of the current instance.
(Inherited from Object)
MemberwiseClone Creates a shallow copy of the current Object.
(Inherited from Object)
ToString Returns a string that represents the current object.
(Inherited from Object)

See Also