Release 3.1.0

CHANGELOG.md

@@ -5,12 +5,13 @@
 - Support MathMl
 - Support SVG
 
-## 3.0.1
+## 3.1.0
 
-- Ensure to count existing images from header and footer too #113
-- Preserve line break pre for OSX/Windows
-- Prevent a crash when the provided style is missing its type
-- Defensive code to avoid 2 rowSpan+colSpan with a cell in between to crash #59
+- Fix table Cell borders are wrongly applied on the run #156
+- Correctly handle RTL layout for text, list, table and document scope #86 #66
+- Support property line-height #52
+- Fallback to `background` style attribute as many users use this simplified attribute version
+- In `HtmlDomExpression.CreateFromHtmlNode`, use the correct casting to `IElement` rather than `IHtmlElement`, to prevent crash if `svg` node is encountered
 
 ## 3.0.0
 

README.md

@@ -68,5 +68,5 @@ Logo provided with the permission of [Enhanced Labs Design Studio](http://www.en
 
 ## Support
 
-This project is open source and I do my best to support it in my spare time. I'm always happy to receive Pull Request and grateful for the time you have taken
+This project is open source and I do my best to support it in my spare time. I'm always happy to receive Pull Request and grateful for the time you have taken. Please target branch `dev` only.
 If you have questions, don't hesitate to get in touch with me!

examples/Demo/Program.cs

@@ -17,15 +17,7 @@ static async Task Main(string[] args)
             const string filename = "test.docx";
             string html = ResourceHelper.GetString("Resources.CompleteRunTest.html");
             if (File.Exists(filename)) File.Delete(filename);
-const string preformattedText = @"
-              ^__^
-              (oo)\_______
-              (__)\       )\/\
-                  ||----w |
-                  ||     ||";
 
-            html = @$"<pre role='img' aria-label='ASCII COW'>
-{preformattedText}</pre>";
             using (MemoryStream generatedDocument = new MemoryStream())
             {
                 // Uncomment and comment the second using() to open an existing template document
@@ -53,7 +45,7 @@ static async Task Main(string[] args)
                     await converter.ParseHtml(html);
                     mainPart.Document.Save();
 
-                    //AssertThatOpenXmlDocumentIsValid(package);
+                    AssertThatOpenXmlDocumentIsValid(package);
                 }
 
                 File.WriteAllBytes(filename, generatedDocument.ToArray());

src/Html2OpenXml/Collections/HtmlAttributeCollection.cs

@@ -71,9 +71,9 @@ public HtmlColor GetColor(string name)
     /// Gets an attribute representing an unit: 120px, 10pt, 5em, 20%, ...
     /// </summary>
     /// <returns>If the attribute is misformed, the <see cref="Unit.IsValid"/> property is set to false.</returns>
-    public Unit GetUnit(string name)
+    public Unit GetUnit(string name, UnitMetric defaultMetric = UnitMetric.Unitless)
     {
-        return Unit.Parse(this[name]);
+        return Unit.Parse(this[name], defaultMetric);
     }
 
     /// <summary>
@@ -86,13 +86,13 @@ public Margin GetMargin(string name)
         Margin margin = Margin.Parse(this[name]);
         Unit u;
 
-        u = GetUnit(name + "-top");
+        u = GetUnit(name + "-top", UnitMetric.Pixel);
         if (u.IsValid) margin.Top = u;
-        u = GetUnit(name + "-right");
+        u = GetUnit(name + "-right", UnitMetric.Pixel);
         if (u.IsValid) margin.Right = u;
-        u = GetUnit(name + "-bottom");
+        u = GetUnit(name + "-bottom", UnitMetric.Pixel);
         if (u.IsValid) margin.Bottom = u;
-        u = GetUnit(name + "-left");
+        u = GetUnit(name + "-left", UnitMetric.Pixel);
         if (u.IsValid) margin.Left = u;
 
         return margin;

src/Html2OpenXml/Expressions/BlockElementExpression.cs

@@ -121,13 +121,11 @@ protected override void ComposeStyles (ParsingContext context)
         }
 
         // according to w3c, dir should be used in conjonction with lang. But whatever happens, we'll apply the RTL layout
-        if ("rtl".Equals(node.Direction, StringComparison.OrdinalIgnoreCase))
-        {
-            paraProperties.Justification = new() { Val = JustificationValues.Right };
-        }
-        else if ("ltr".Equals(node.Direction, StringComparison.OrdinalIgnoreCase))
-        {
-            paraProperties.Justification = new() { Val = JustificationValues.Left };
+        var dir = node.GetTextDirection();
+        if (dir.HasValue) {
+            paraProperties.BiDi = new() {
+                Val = OnOffValue.FromBoolean(dir == AngleSharp.Dom.DirectionMode.Rtl)
+            };
         }
 
         var attrValue = styleAttributes!["text-align"];
@@ -200,6 +198,44 @@ protected override void ComposeStyles (ParsingContext context)
 
             paraProperties.Indentation = indentation;
         }
+
+        var lineHeight = styleAttributes.GetUnit("line-height");
+        if (!lineHeight.IsValid 
+            && "normal".Equals(styleAttributes["line-height"], StringComparison.OrdinalIgnoreCase))
+        {
+            // if `normal` is specified, reset any values
+            lineHeight = new Unit(UnitMetric.Unitless, 1);
+        }
+
+        if (lineHeight.IsValid)
+        {
+            if (lineHeight.Type == UnitMetric.Unitless)
+            {
+                // auto should be considered as 240ths of a line
+                // https://learn.microsoft.com/en-us/dotnet/api/documentformat.openxml.wordprocessing.spacingbetweenlines.line?view=openxml-3.0.1
+                paraProperties.SpacingBetweenLines = new() {
+                    LineRule = LineSpacingRuleValues.Auto,
+                    Line = Math.Round(lineHeight.Value * 240).ToString(CultureInfo.InvariantCulture)
+                };
+            }
+            else if (lineHeight.Type == UnitMetric.Percent)
+            {
+                // percentage depends on the font size which is hard to determine here
+                // let's rely this to "auto" behaviour
+                paraProperties.SpacingBetweenLines = new() {
+                    LineRule = LineSpacingRuleValues.Auto,
+                    Line = Math.Round(lineHeight.Value / 100 * 240).ToString(CultureInfo.InvariantCulture)
+                };
+            }
+            else
+            {
+                // twentieths of a point
+                paraProperties.SpacingBetweenLines = new() {
+                    LineRule = LineSpacingRuleValues.Exact,
+                    Line = Math.Round(lineHeight.ValueInPoint * 20).ToString(CultureInfo.InvariantCulture)
+                };
+            }
+        }
     }
 
     /// <summary>

src/Html2OpenXml/Expressions/BodyExpression.cs

@@ -58,6 +58,17 @@ protected override void ComposeStyles(ParsingContext context)
                 }
             }
         }
+
+        if (paraProperties.BiDi is not null)
+        {
+            var sectionProperties = context.MainPart.Document.Body!.GetFirstChild<SectionProperties>();
+            if (sectionProperties == null || sectionProperties.GetFirstChild<PageSize>() == null)
+            {
+                context.MainPart.Document.Body.Append(sectionProperties = new());
+            }
+
+            sectionProperties.AddChild(paraProperties.BiDi.CloneNode(true));
+        }
     }
 
     /// <summary>

src/Html2OpenXml/Expressions/HorizontalLineExpression.cs

@@ -20,14 +20,8 @@ namespace HtmlToOpenXml.Expressions;
 /// Process the parsing of a <c>hr</c> element
 /// by inserting an horizontal line as it stands in many emails.
 /// </summary>
-sealed class HorizontalLineExpression(IHtmlElement node) : HtmlElementExpression(node)
+sealed class HorizontalLineExpression(IHtmlElement node) : HtmlDomExpression
 {
-    [System.Diagnostics.CodeAnalysis.ExcludeFromCodeCoverage]
-    public override void CascadeStyles(OpenXmlElement element)
-    {
-        throw new System.NotSupportedException();
-    }
-
     /// <inheritdoc/>
     public override IEnumerable<OpenXmlElement> Interpret (ParsingContext context)
     {

src/Html2OpenXml/Expressions/HtmlDomExpression.cs

@@ -24,53 +24,53 @@ namespace HtmlToOpenXml.Expressions;
 abstract class HtmlDomExpression
 {
     protected const string InternalNamespaceUri = "https://github.com/onizet/html2openxml";
-    static readonly Dictionary<string, Func<IHtmlElement, HtmlElementExpression>> knownTags = InitKnownTags();
+    static readonly Dictionary<string, Func<IElement, HtmlDomExpression>> knownTags = InitKnownTags();
     static readonly HashSet<string> ignoreTags = new(StringComparer.OrdinalIgnoreCase) {
         TagNames.Xml, TagNames.AnnotationXml, TagNames.Button, TagNames.Progress,
         TagNames.Select, TagNames.Input, TagNames.Textarea, TagNames.Meter };
 
-    private static Dictionary<string, Func<IHtmlElement, HtmlElementExpression>> InitKnownTags()
+    private static Dictionary<string, Func<IElement, HtmlDomExpression>> InitKnownTags()
     {
         // A complete list of HTML tags can be found here: http://www.w3schools.com/tags/default.asp
 
-        var knownTags = new Dictionary<string, Func<IHtmlElement, HtmlElementExpression>>(StringComparer.InvariantCultureIgnoreCase) {
-            { TagNames.A, el => new HyperlinkExpression(el) },
-            { TagNames.Abbr, el => new AbbreviationExpression(el) },
-            { "acronym", el => new AbbreviationExpression(el) },
-            { TagNames.B, el => new PhrasingElementExpression(el, new Bold()) },
-            { TagNames.BlockQuote, el => new BlockQuoteExpression(el) },
-            { TagNames.Br, el => new LineBreakExpression(el) },
-            { TagNames.Cite, el => new CiteElementExpression(el) },
-            { TagNames.Dd, el => new BlockElementExpression(el, new Indentation() { FirstLine = "708" }, new SpacingBetweenLines() { After = "0" }) },
-            { TagNames.Del, el => new PhrasingElementExpression(el, new Strike()) },
-            { TagNames.Dfn, el => new AbbreviationExpression(el) },
-            { TagNames.Em, el => new PhrasingElementExpression(el, new Italic()) },
-            { TagNames.Figcaption, el => new FigureCaptionExpression(el) },
-            { TagNames.Font, el => new FontElementExpression(el) },
-            { TagNames.H1, el => new HeadingElementExpression(el) },
-            { TagNames.H2, el => new HeadingElementExpression(el) },
-            { TagNames.H3, el => new HeadingElementExpression(el) },
-            { TagNames.H4, el => new HeadingElementExpression(el) },
-            { TagNames.H5, el => new HeadingElementExpression(el) },
-            { TagNames.H6, el => new HeadingElementExpression(el) },
-            { TagNames.I, el => new PhrasingElementExpression(el, new Italic()) },
-            { TagNames.Hr, el => new HorizontalLineExpression(el) },
-            { TagNames.Img, el => new ImageExpression(el) },
-            { TagNames.Ins, el => new PhrasingElementExpression(el, new Underline() { Val = UnderlineValues.Single }) },
-            { TagNames.Ol, el => new ListExpression(el) },
-            { TagNames.Pre, el => new PreElementExpression(el) },
-            { TagNames.Q, el => new QuoteElementExpression(el) },
-            { TagNames.Quote, el => new QuoteElementExpression(el) },
-            { TagNames.Span, el => new PhrasingElementExpression(el) },
-            { TagNames.S, el => new PhrasingElementExpression(el, new Strike()) },
-            { TagNames.Strike, el => new PhrasingElementExpression(el, new Strike()) },
-            { TagNames.Strong, el => new PhrasingElementExpression(el, new Bold()) },
-            { TagNames.Sub, el => new PhrasingElementExpression(el, new VerticalTextAlignment() { Val = VerticalPositionValues.Subscript }) },
-            { TagNames.Sup, el => new PhrasingElementExpression(el, new VerticalTextAlignment() { Val = VerticalPositionValues.Superscript }) },
-            { TagNames.Table, el => new TableExpression(el) },
-            { TagNames.Time, el => new PhrasingElementExpression(el) },
-            { TagNames.U, el => new PhrasingElementExpression(el, new Underline() { Val = UnderlineValues.Single }) },
-            { TagNames.Ul, el => new ListExpression(el) },
+        var knownTags = new Dictionary<string, Func<IElement, HtmlDomExpression>>(StringComparer.InvariantCultureIgnoreCase) {
+            { TagNames.A, el => new HyperlinkExpression((IHtmlAnchorElement) el) },
+            { TagNames.Abbr, el => new AbbreviationExpression((IHtmlElement) el) },
+            { "acronym", el => new AbbreviationExpression((IHtmlElement) el) },
+            { TagNames.B, el => new PhrasingElementExpression((IHtmlElement) el, new Bold()) },
+            { TagNames.BlockQuote, el => new BlockQuoteExpression((IHtmlElement) el) },
+            { TagNames.Br, _ => new LineBreakExpression() },
+            { TagNames.Cite, el => new CiteElementExpression((IHtmlElement) el) },
+            { TagNames.Dd, el => new BlockElementExpression((IHtmlElement) el, new Indentation() { FirstLine = "708" }, new SpacingBetweenLines() { After = "0" }) },
+            { TagNames.Del, el => new PhrasingElementExpression((IHtmlElement) el, new Strike()) },
+            { TagNames.Dfn, el => new AbbreviationExpression((IHtmlElement) el) },
+            { TagNames.Em, el => new PhrasingElementExpression((IHtmlElement) el, new Italic()) },
+            { TagNames.Figcaption, el => new FigureCaptionExpression((IHtmlElement) el) },
+            { TagNames.Font, el => new FontElementExpression((IHtmlElement) el) },
+            { TagNames.H1, el => new HeadingElementExpression((IHtmlElement) el) },
+            { TagNames.H2, el => new HeadingElementExpression((IHtmlElement) el) },
+            { TagNames.H3, el => new HeadingElementExpression((IHtmlElement) el) },
+            { TagNames.H4, el => new HeadingElementExpression((IHtmlElement) el) },
+            { TagNames.H5, el => new HeadingElementExpression((IHtmlElement) el) },
+            { TagNames.H6, el => new HeadingElementExpression((IHtmlElement) el) },
+            { TagNames.I, el => new PhrasingElementExpression((IHtmlElement) el, new Italic()) },
+            { TagNames.Hr, el => new HorizontalLineExpression((IHtmlElement) el) },
+            { TagNames.Img, el => new ImageExpression((IHtmlImageElement) el) },
+            { TagNames.Ins, el => new PhrasingElementExpression((IHtmlElement) el, new Underline() { Val = UnderlineValues.Single }) },
+            { TagNames.Ol, el => new ListExpression((IHtmlElement) el) },
+            { TagNames.Pre, el => new PreElementExpression((IHtmlElement) el) },
+            { TagNames.Q, el => new QuoteElementExpression((IHtmlElement) el) },
+            { TagNames.Quote, el => new QuoteElementExpression((IHtmlElement) el) },
+            { TagNames.Span, el => new PhrasingElementExpression((IHtmlElement) el) },
+            { TagNames.S, el => new PhrasingElementExpression((IHtmlElement) el, new Strike()) },
+            { TagNames.Strike, el => new PhrasingElementExpression((IHtmlElement) el, new Strike()) },
+            { TagNames.Strong, el => new PhrasingElementExpression((IHtmlElement) el, new Bold()) },
+            { TagNames.Sub, el => new PhrasingElementExpression((IHtmlElement) el, new VerticalTextAlignment() { Val = VerticalPositionValues.Subscript }) },
+            { TagNames.Sup, el => new PhrasingElementExpression((IHtmlElement) el, new VerticalTextAlignment() { Val = VerticalPositionValues.Superscript }) },
+            { TagNames.Table, el => new TableExpression((IHtmlTableElement) el) },
+            { TagNames.Time, el => new PhrasingElementExpression((IHtmlElement) el) },
+            { TagNames.U, el => new PhrasingElementExpression((IHtmlElement) el, new Underline() { Val = UnderlineValues.Single }) },
+            { TagNames.Ul, el => new ListExpression((IHtmlElement) el) },
         };
 
         return knownTags;
@@ -93,8 +93,8 @@ private static Dictionary<string, Func<IHtmlElement, HtmlElementExpression>> Ini
         else if (node.NodeType == NodeType.Element
             && !ignoreTags.Contains(node.NodeName))
         {
-            if (knownTags.TryGetValue(node.NodeName, out Func<IHtmlElement, HtmlElementExpression>? handler))
-                return handler((IHtmlElement) node);
+            if (knownTags.TryGetValue(node.NodeName, out Func<IElement, HtmlDomExpression>? handler))
+                return handler((IElement) node);
 
             // fallback on the flow element which will cover all the semantic Html5 tags
             return new BlockElementExpression((IHtmlElement) node);

src/Html2OpenXml/Expressions/HtmlElementExpression.cs

@@ -9,19 +9,15 @@
  * IMPLIED WARRANTIES OF MERCHANTABILITY AND/OR FITNESS FOR A
  * PARTICULAR PURPOSE.
  */
-using System;
-using AngleSharp.Html.Dom;
 using DocumentFormat.OpenXml;
 
 namespace HtmlToOpenXml.Expressions;
 
 /// <summary>
 /// Represents the base definition of the processor of an HTML tag.
 /// </summary>
-abstract class HtmlElementExpression(IHtmlElement node) : HtmlDomExpression
+abstract class HtmlElementExpression : HtmlDomExpression
 {
-    protected readonly IHtmlElement node = node ?? throw new ArgumentNullException(nameof(node));
-
     /// <summary>
     /// Apply the style properties on the provided element.
     /// </summary>

src/Html2OpenXml/Expressions/HyperlinkExpression.cs

@@ -24,16 +24,16 @@ namespace HtmlToOpenXml.Expressions;
 /// <summary>
 /// Process the parsing of a link element.
 /// </summary>
-sealed class HyperlinkExpression(IHtmlElement node) : PhrasingElementExpression(node)
+sealed class HyperlinkExpression(IHtmlAnchorElement node) : PhrasingElementExpression(node)
 {
-    private readonly IHtmlAnchorElement linkNode = (IHtmlAnchorElement) node;
+    private readonly IHtmlAnchorElement linkNode = node;
 
 
     /// <inheritdoc/>
     public override IEnumerable<OpenXmlElement> Interpret (ParsingContext context)
     {
         var h = CreateHyperlink(context);
-        var childElements = Interpret(context.CreateChild(this), node.ChildNodes);
+        var childElements = Interpret(context.CreateChild(this), linkNode.ChildNodes);
         if (h is null)
         {
             return childElements;
@@ -112,8 +112,8 @@ public override IEnumerable<OpenXmlElement> Interpret (ParsingContext context)
             return null;
         }
 
-        if (!string.IsNullOrEmpty(node.Title))
-            h.Tooltip = node.Title;
+        if (!string.IsNullOrEmpty(linkNode.Title))
+            h.Tooltip = linkNode.Title;
         return h;
     }
 }