private static void ConvertContentTo(HtmlNode node, TextWriter outText, DomTextInfo textInfo,
PlainTextOptions options)
{
foreach (var subnode in node.ChildNodes)
{
ConvertTo(subnode, outText, textInfo, options);
}
}
private static void AddNewLineAtStartIfRequired(HtmlNode node, TextWriter outText, DomTextInfo textInfo)
{
// The new line before the paragraph, it it's the first child in the predefined nodes.
if (node.ParentNode != null &&
!SpecialNodeNames.Contains(node.ParentNode.Name) &&
node.PreviousSibling != null &&
!textInfo.IsNewLineAddedAtEnd)
{
outText.Write("\r\n");
}
}
private static void ConvertTo(HtmlNode node, TextWriter outText, DomTextInfo textInfo, PlainTextOptions options)
{
switch (node.NodeType)
{
case HtmlNodeType.Comment:
// don't output comments
break;
case HtmlNodeType.Document:
ConvertContentTo(node, outText, textInfo, options);
break;
case HtmlNodeType.Text:
// script and style must not be output
var parentName = node.ParentNode.Name;
if (parentName == "script" || parentName == "style")
{
break;
}
var html = ((HtmlTextNode)node).Text;
// is it in fact a special closing node output as text?
if (HtmlNode.IsOverlappedClosingElement(html))
{
break;
}
// check the text is meaningful and not a bunch of whitespaces
if (html.Length == 0)
{
break;
}
if (textInfo.PreserveFormatting)
{
// Entitize (decode) text if needed
if ((options & PlainTextOptions.Entitize) != 0)
{
html = DecodeHtml(html);
}
outText.Write(html);
break;
}
if (!textInfo.WritePrecedingWhiteSpace || textInfo.LastCharWasSpace)
{
html = html.TrimStart();
if (html.Length == 0)
{
break;
}
textInfo.WritePrecedingWhiteSpace = true;
}
// special case to get rid of "zero width space"
// Entitize (decode) text if needed
outText.Write(
(options & PlainTextOptions.Entitize) != 0
? Regex.Replace(DecodeHtml(html.TrimEnd()), @"\s{2,}", " ").Replace("\u200b", "")
: Regex.Replace(html.TrimEnd(), @"\s{2,}", " ").Replace(ZeroWidthSpace, ""));
textInfo.LastCharWasSpace = char.IsWhiteSpace(html[html.Length - 1]);
if (textInfo.LastCharWasSpace)
{
outText.Write(' ');
}
break;
case HtmlNodeType.Element:
string endElementString = null;
bool isInline;
var skip = false;
var listIndex = 0;
switch (node.Name)
{
case "nav":
skip = true;
isInline = false;
break;
case "body":
case "section":
case "article":
case "aside":
case "h1":
case "h2":
case "header":
case "footer":
case "address":
case "main":
case "div":
if ((options & PlainTextOptions.Paragraph) != 0)
{
endElementString = "\r\n";
textInfo.IsNewLineAddedAtEnd = true;
}
isInline = false;
break;
case "p":
if ((options & PlainTextOptions.Paragraph) != 0)
{
AddNewLineAtStartIfRequired(node, outText, textInfo);
if (!IsLastChildNodeInSpecialNodes(node))
{
endElementString = "\r\n";
textInfo.IsNewLineAddedAtEnd = true;
}
}
isInline = false;
break;
case "tr":
if ((options & PlainTextOptions.Table) != 0)
{
endElementString = "\r\n";
textInfo.IsNewLineAddedAtEnd = true;
}
isInline = false;
break;
case "th": // stylistic - adjust as you tend to use
case "td": // stylistic - adjust as you tend to use
if ((options & PlainTextOptions.Table) != 0)
{
endElementString = "\t";
}
isInline = false;
break;
case "br":
if ((options & PlainTextOptions.LineFeed) != 0)
{
outText.Write("\r\n");
textInfo.WritePrecedingWhiteSpace = false;
}
skip = true;
isInline = true;
break;
case "a":
if ((options & PlainTextOptions.Link) != 0)
{
if (node.Attributes.Contains("href"))
{
var href = node.Attributes["href"].Value.Trim();
if (node.InnerText.IndexOf(href, StringComparison.OrdinalIgnoreCase) == -1)
{
endElementString = "<" + href + ">";
}
}
}
isInline = true;
break;
case "li":
if ((options & PlainTextOptions.List) != 0)
{
if (textInfo.ListIndex > 0)
{
outText.Write("{0}.\t", textInfo.ListIndex++);
}
else
{
// using '•' as bullet char, with tab after, but whatever you want eg "\t->", if utf-8 0x2022
outText.Write("•\t");
}
if (node.ChildNodes != null && node.ChildNodes.Any() &&
node.ChildNodes.First().Name != "p")
{
endElementString = "\r\n";
}
}
isInline = false;
break;
case "ol":
listIndex = 1;
goto case "ul";
// not handling nested lists any differently at this stage - that is getting close to rendering problems
case "ul":
if ((options & PlainTextOptions.List) != 0)
{
AddNewLineAtStartIfRequired(node, outText, textInfo);
if (!IsLastChildNodeInSpecialNodes(node))
{
endElementString = "\r\n";
textInfo.IsNewLineAddedAtEnd = true;
}
}
isInline = false;
break;
case "img": // inline-block in reality
if ((options & PlainTextOptions.Image) != 0)
{
outText.Write("[Image]");
}
isInline = true;
break;
case "pre":
textInfo.PreserveFormatting = true;
isInline = true;
break;
default:
isInline = true;
break;
}
if (!skip && node.HasChildNodes)
{
var domTextInfo = isInline
? textInfo
: new DomTextInfo
{
ListIndex = listIndex,
IsNewLineAddedAtEnd = textInfo.IsNewLineAddedAtEnd
};
ConvertContentTo(node, outText, domTextInfo, options);
}
if (endElementString != null)
{
outText.Write(endElementString);
}
break;
default:
throw new ArgumentOutOfRangeException(nameof(node.NodeType));
}
}
