Supports a feature to disable heading numbering #175

Author: onizet

src/Html2OpenXml/Expressions/HyperlinkExpression.cs

@@ -113,7 +113,7 @@ public override IEnumerable<OpenXmlElement> Interpret (ParsingContext context)
             h = new Hyperlink() { History = true, Anchor = "_top" };
         }
         // is it an anchor?
-        else if (!context.Converter.ExcludeLinkAnchor && linkNode.Hash.Length > 1 && linkNode.Hash[0] == '#')
+        else if (context.Converter.SupportsAnchorLinks && linkNode.Hash.Length > 1 && linkNode.Hash[0] == '#')
         {
             h = new Hyperlink(
                 ) { History = true, Anchor = linkNode.Hash.Substring(1) };

src/Html2OpenXml/Expressions/Numbering/HeadingElementExpression.cs

@@ -40,9 +40,9 @@ public override IEnumerable<OpenXmlElement> Interpret (ParsingContext context)
         paragraph.ParagraphProperties ??= new();
         paragraph.ParagraphProperties.ParagraphStyleId = 
             context.DocumentStyle.GetParagraphStyle(context.DocumentStyle.DefaultStyles.HeadingStyle + level);
-
+ 
         var runElement = childElements.FirstOrDefault();
-        if (runElement != null && IsNumbering(runElement))
+        if (runElement != null && context.Converter.SupportsHeadingNumbering && IsNumbering(runElement))
         {
             var abstractNumId = GetOrCreateListTemplate(context, HeadingNumberingName);
             var instanceId = GetListInstance(abstractNumId);

src/Html2OpenXml/HtmlConverter.cs

@@ -339,7 +339,8 @@ private TPart ResolveHeaderFooterPart<TRefType, TPart>(HeaderFooterValues? type)
     public AcronymPosition AcronymPosition { get; set; }
 
     /// <summary>
-    /// Gets or sets whether anchor links are included or not in the convertion.
+    /// Gets or sets whether anchor links are included or not in the conversion
+    /// (defaults <see langword="true" />).
     /// </summary>
     /// <remarks>An anchor is a term used to define a hyperlink destination inside a document.
     /// <see href="http://www.w3schools.com/HTML/html_links.asp"/>.
@@ -351,7 +352,23 @@ private TPart ResolveHeaderFooterPart<TRefType, TPart>(HeaderFooterValues? type)
     /// <see cref="DocumentFormat.OpenXml.Wordprocessing.BookmarkEnd"/> elements
     /// and set the value of href to <i><c>#name of your bookmark</c></i>.
     /// </remarks>
-    public bool ExcludeLinkAnchor { get; set; }
+    public bool SupportsAnchorLinks { get; set; } = true;
+
+    /// <summary>
+    /// Gets or sets whether anchor links are included or not in the conversion.
+    /// </summary>
+    /// <remarks>An anchor is a term used to define a hyperlink destination inside a document.
+    /// <see href="http://www.w3schools.com/HTML/html_links.asp"/>.
+    /// <br/>
+    /// It exists some predefined anchors used by Word such as _top to refer to the top of the document.
+    /// The anchor <i>#_top</i> is always accepted regardless this property value.
+    /// For others anchors like refering to your own bookmark or a title, add a 
+    /// <see cref="DocumentFormat.OpenXml.Wordprocessing.BookmarkStart"/> and 
+    /// <see cref="DocumentFormat.OpenXml.Wordprocessing.BookmarkEnd"/> elements
+    /// and set the value of href to <i><c>#name of your bookmark</c></i>.
+    /// </remarks>
+    [Obsolete("Use SupportsAnchorLink instead, if ExcludeLinkAnchor = true -> SupportsAnchorLink = false")]
+    public bool ExcludeLinkAnchor { get => !SupportsAnchorLinks; set => SupportsAnchorLinks = !value; }
 
     /// <summary>
     /// Gets the Html styles manager mapping to OpenXml style properties.
@@ -367,7 +384,7 @@ public WordDocumentStyle HtmlStyles
     public CaptionPositionValues TableCaptionPosition { get; set; }
 
     /// <summary>
-    /// Gets or sets whether the <c>pre</c> tag should be rendered as a table (default <see langword="false"/>).
+    /// Gets or sets whether the <c>pre</c> tag should be rendered as a table (defaults <see langword="false"/>).
     /// </summary>
     /// <remarks>The table will contains only one cell.</remarks>
     public bool RenderPreAsTable { get; set; }
@@ -378,6 +395,16 @@ public WordDocumentStyle HtmlStyles
     /// </summary>
     public bool ContinueNumbering { get; set; } = true;
 
+    /// <summary>
+    /// Defines whether any headings (<c>h1-h6</c>) could be considered as multi-level numbering, such as
+    /// top-level headings (Heading 1) are numbered 1, 2, 3, for example, and second-level headings (Heading 2) are numbered 1.1, 1.2, 1.3.
+    /// This feature is enabled by default.
+    /// </summary>
+    /// <remarks>The converter is detecting headings starting with a number (ie: <c>1.</c> or <c>1 </c>)
+    /// are considered as numbering.
+    /// </remarks>
+    public bool SupportsHeadingNumbering { get; set; } = true;
+
     /// <summary>
     /// Gets the mainDocumentPart of the destination OpenXml document.
     /// </summary>

test/HtmlToOpenXml.Tests/HeadingTests.cs

@@ -51,6 +51,32 @@ public void OrderedPattern_ReturnsNumberingHeading(string html)
             });
         }
 
+        [TestCase("<h1>1. Heading 1</h1><h2>1.1 Heading Normal Case</h1>")]
+        [TestCase("<h1>1. Heading 1</h1><h2>1.1  Heading Double Space</h2>", Description = "Double space after number")]
+        [TestCase("<h1>1. Heading 1</h1><h2>1.2&#09;Heading Tab</h2>", Description = "Tab after number")]
+        [TestCase("<h1>1. Heading 1</h1><h2>1.3Heading No Space</h2>", Description = "No space after number")]
+        public void OrderedPattern_DisableNumberingSupports_ReturnsSimpleHeading(string html)
+        {
+            converter.SupportsHeadingNumbering = false;
+            var elements = converter.Parse(html);
+
+            var absNum = mainPart.NumberingDefinitionsPart?.Numbering
+                .Elements<AbstractNum>()
+                .Where(abs => abs.AbstractNumDefinitionName?.Val == NumberingExpressionBase.HeadingNumberingName)
+                .SingleOrDefault();
+            Assert.That(absNum, Is.Null);
+
+            var paragraphs = elements.Cast<Paragraph>();
+            Assert.Multiple(() =>
+            {
+                Assert.That(paragraphs.Count(), Is.EqualTo(2));
+                Assert.That(paragraphs.First().InnerText, Is.EqualTo("1. Heading 1"));
+                Assert.That(paragraphs.First().ParagraphProperties?.NumberingProperties?.NumberingLevelReference?.Val,
+                    Is.Null,
+                    "First paragraph is not a numbering");
+            });
+        }
+
         [Test]
         public void MaxLevel_ShouldBeIgnored()
         {

test/HtmlToOpenXml.Tests/LinkTests.cs

@@ -82,7 +82,7 @@ public void Anchoring_WithUnknownTarget_ReturnsHyperlinkWithBookmark ()
         [Test]
         public void SetExcludeAnchoring_ReturnsSimpleRun ()
         {
-            converter.ExcludeLinkAnchor = true;
+            converter.SupportsAnchorLinks = false;
 
             // _top is always present and bypass the previous rule
             var elements = converter.Parse(@"<a href=""#_top"">Anchor2</a>");