/// <summary>
/// Gets the font attribute and combine with the style, size and family.
/// </summary>
public HtmlFont GetAsFont(String name)
{
HtmlFont font = HtmlFont.Parse(this[name]);
string attrValue = this[name + "-style"];
if (attrValue != null)
{
var style = Converter.ToFontStyle(attrValue);
if (style.HasValue)
{
font.Style = style.Value;
}
}
attrValue = this[name + "-variant"];
if (attrValue != null)
{
var variant = Converter.ToFontVariant(attrValue);
if (variant.HasValue)
{
font.Variant = variant.Value;
}
}
attrValue = this[name + "-weight"];
if (attrValue != null)
{
var weight = Converter.ToFontWeight(attrValue);
if (weight.HasValue)
{
font.Weight = weight.Value;
}
}
attrValue = this[name + "-family"];
if (attrValue != null)
{
font.Family = Converter.ToFontFamily(attrValue);
}
Unit unit = this.GetAsUnit(name + "-size");
if (unit.IsValid)
{
font.Size = unit;
}
return(font);
}
public static string Process(string html)
{
// Check for web parts - these cannot be migrated
HtmlHelper.FindWebParts(html);
// TODO: Check for references of /Documents folder - these files are not migrated
//Replace space characters
string result = html.Replace("\u200B", "").Replace(" ", " ");
result = result.Replace("size=\"+0\"", "");
result = result.Replace("<s>", "~~").Replace("</s>", "~~");
//Convert Span Highlights
result = HtmlSpan.Process(result);
//Convert embedded YouTube videos to markdown
result = Youtube.convertYoutubeVideos(result);
result = Greybox.Process(result);
//Remove unhandled tags
result = HtmlDescriptionList.Process(result);
result = HtmlDescriptionDetails.Process(result);
//Remove nodes, but keep the child nodes
result = HtmlHelper.RemoveNode(result, "dl", true);
result = HtmlHelper.RemoveNode(result, "dt", true);
result = HtmlHelper.RemoveNode(result, "dd", true);
result = HtmlHelper.ConvertTagsInPre(result);
result = HtmlFont.Process(result);
//Remove leading and trailing whitespace
result = TrimWhitespaceAroundBoldText(result);
result = HtmlHelper.RemoveNode(result, "dl", true);
return(result);
}
/// <summary>
/// Converts some common styling attributes to their OpenXml equivalence.
/// </summary>
/// <param name="en">The Html parser.</param>
/// <param name="styleAttributes">The collection of attributes where to store new discovered attributes.</param>
public void ProcessCommonAttributes(HtmlEnumerator en, IList <OpenXmlElement> styleAttributes)
{
if (en.Attributes.Count == 0)
{
return;
}
var colorValue = en.StyleAttributes.GetAsColor("color");
if (colorValue.IsEmpty)
{
colorValue = en.Attributes.GetAsColor("color");
}
if (!colorValue.IsEmpty)
{
styleAttributes.Add(new Color {
Val = colorValue.ToHexString()
});
}
colorValue = en.StyleAttributes.GetAsColor("background-color");
if (!colorValue.IsEmpty)
{
// change the way the background-color renders. It now uses Shading instead of Highlight.
// Changes brought by Wude on http://html2openxml.codeplex.com/discussions/277570
styleAttributes.Add(new Shading {
Val = ShadingPatternValues.Clear, Fill = colorValue.ToHexString()
});
}
var decorations = Converter.ToTextDecoration(en.StyleAttributes["text-decoration"]);
if ((decorations & TextDecoration.Underline) != 0)
{
styleAttributes.Add(new Underline {
Val = UnderlineValues.Single
});
}
if ((decorations & TextDecoration.LineThrough) != 0)
{
styleAttributes.Add(new Strike());
}
String[] classes = en.Attributes.GetAsClass();
if (classes != null)
{
for (int i = 0; i < classes.Length; i++)
{
string className = documentStyle.GetStyle(classes[i], StyleValues.Character, ignoreCase: true);
if (className != null) // only one Style can be applied in OpenXml and dealing with inheritance is out of scope
{
styleAttributes.Add(new RunStyle()
{
Val = className
});
break;
}
}
}
HtmlFont font = en.StyleAttributes.GetAsFont("font");
if (!font.IsEmpty)
{
if (font.Style == FontStyle.Italic)
{
styleAttributes.Add(new Italic());
}
if (font.Weight == FontWeight.Bold || font.Weight == FontWeight.Bolder)
{
styleAttributes.Add(new Bold());
}
if (font.Variant == FontVariant.SmallCaps)
{
styleAttributes.Add(new SmallCaps());
}
if (font.Family != null)
{
styleAttributes.Add(new RunFonts()
{
Ascii = font.Family, HighAnsi = font.Family
});
}
// size are half-point font size
if (font.Size.IsFixed)
{
styleAttributes.Add(new FontSize()
{
Val = (font.Size.ValueInPoint * 2).ToString(CultureInfo.InvariantCulture)
});
}
}
}