Skip to content

Header and Footer support #163

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 8 commits into from
Sep 21, 2024
Merged

Header and Footer support #163

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
8f1b85e
New API to parse into the header and footer
onizet Sep 13, 2024
bf4db47
Amend unit test to cover these new API endpoints
onizet Sep 16, 2024
978dfaf
Clean code
onizet Sep 16, 2024
aa5b5dc
Register the header/footer relationship
onizet Sep 19, 2024
2e74a87
Unit test code to assert new header-footer are correctly registred
onizet Sep 20, 2024
e6907bc
Acronym and blocquote now default to simple run
onizet Sep 20, 2024
5ad14cb
Expose on which page(s) the header/footer will be displayed
onizet Sep 20, 2024
575ef1d
Use default paragraph styles
onizet Sep 21, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 7 additions & 2 deletions examples/Demo/Program.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ static class Program
static async Task Main(string[] args)
{
const string filename = "test.docx";
string html = ResourceHelper.GetString("Resources.CompleteRunTest.html");
string html = ResourceHelper.GetString("Resources.Document.html");
if (File.Exists(filename)) File.Delete(filename);

using (MemoryStream generatedDocument = new MemoryStream())
Expand All @@ -39,10 +39,15 @@ static async Task Main(string[] args)
}

HtmlConverter converter = new HtmlConverter(mainPart);
// HeaderPart headerPart = mainPart.AddNewPart<HeaderPart>();
//FooterPart footerPart = mainPart.AddNewPart<FooterPart>();
converter.RenderPreAsTable = true;
Body body = mainPart.Document.Body;

await converter.ParseHtml(html);
await converter.ParseHeader(@"<a href=""www.github.com"">
<img src=""data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAUAAAAFCAYAAACNbyblAAAAHElEQVQI12P4//8/w38GIAXDIBKE0DHxgljNBAAO9TXL0Y4OHwAAAABJRU5ErkJggg=="" alt=""Red dot"" /> Red Dot</a>");

await converter.ParseBody(html);
mainPart.Document.Save();

AssertThatOpenXmlDocumentIsValid(package);
Expand Down
3 changes: 2 additions & 1 deletion src/Html2OpenXml/Expressions/AbbreviationExpression.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,8 +32,9 @@ public override IEnumerable<OpenXmlElement> Interpret(ParsingContext context)
var childElements = base.Interpret(context);

// Transform the inline acronym/abbreviation to a reference to a foot note.
// Footnote or endnote are invalid inside header and footer
string? description = node.Title;
if (string.IsNullOrEmpty(description))
if (string.IsNullOrEmpty(description) || context.HostingPart is not MainDocumentPart)
return childElements;

string runStyle;
Expand Down
9 changes: 7 additions & 2 deletions src/Html2OpenXml/Expressions/BlockQuoteExpression.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@
using System.Linq;
using AngleSharp.Html.Dom;
using DocumentFormat.OpenXml;
using DocumentFormat.OpenXml.Packaging;
using DocumentFormat.OpenXml.Wordprocessing;

namespace HtmlToOpenXml.Expressions;
Expand All @@ -26,15 +27,19 @@ sealed class BlockQuoteExpression(IHtmlElement node) : BlockElementExpression(no
/// <inheritdoc/>
public override IEnumerable<OpenXmlElement> Interpret(ParsingContext context)
{
string? description = node.GetAttribute("cite");

var childElements = base.Interpret(context);
if (!childElements.Any())
return [];

// Footnote or endnote are invalid inside header and footer
if (context.HostingPart is not MainDocumentPart)
return childElements;

// Transform the inline acronym/abbreviation to a reference to a foot note.
if (childElements.First() is Paragraph paragraph)
{
string? description = node.GetAttribute("cite");

paragraph.ParagraphProperties ??= new();
if (paragraph.ParagraphProperties.ParagraphStyleId is null)
paragraph.ParagraphProperties.ParagraphStyleId =
Expand Down
11 changes: 7 additions & 4 deletions src/Html2OpenXml/Expressions/BodyExpression.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@
using AngleSharp.Dom;
using AngleSharp.Html.Dom;
using DocumentFormat.OpenXml;
using DocumentFormat.OpenXml.Packaging;
using DocumentFormat.OpenXml.Wordprocessing;

namespace HtmlToOpenXml.Expressions;
Expand All @@ -35,17 +36,19 @@ protected override void ComposeStyles(ParsingContext context)
{
base.ComposeStyles(context);

var mainPart = context.MainPart;

// Unsupported W3C attribute but claimed by users. Specified at <body> level, the page
// orientation is applied on the whole document
string? attr = styleAttributes!["page-orientation"];
if (attr != null)
{
PageOrientationValues orientation = Converter.ToPageOrientation(attr);

var sectionProperties = context.MainPart.Document.Body!.GetFirstChild<SectionProperties>();
var sectionProperties = mainPart.Document.Body!.GetFirstChild<SectionProperties>();
if (sectionProperties == null || sectionProperties.GetFirstChild<PageSize>() == null)
{
context.MainPart.Document.Body.Append(ChangePageOrientation(orientation));
mainPart.Document.Body.Append(ChangePageOrientation(orientation));
}
else
{
Expand All @@ -61,10 +64,10 @@ protected override void ComposeStyles(ParsingContext context)

if (paraProperties.BiDi is not null)
{
var sectionProperties = context.MainPart.Document.Body!.GetFirstChild<SectionProperties>();
var sectionProperties = mainPart.Document.Body!.GetFirstChild<SectionProperties>();
if (sectionProperties == null || sectionProperties.GetFirstChild<PageSize>() == null)
{
context.MainPart.Document.Body.Append(sectionProperties = new());
mainPart.Document.Body.Append(sectionProperties = new());
}

sectionProperties.AddChild(paraProperties.BiDi.CloneNode(true));
Expand Down
9 changes: 6 additions & 3 deletions src/Html2OpenXml/Expressions/HyperlinkExpression.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@
using System.Linq;
using AngleSharp.Html.Dom;
using DocumentFormat.OpenXml;
using DocumentFormat.OpenXml.Packaging;
using DocumentFormat.OpenXml.Wordprocessing;

namespace HtmlToOpenXml.Expressions;
Expand Down Expand Up @@ -42,8 +43,10 @@ public override IEnumerable<OpenXmlElement> Interpret (ParsingContext context)
// Let's see whether the link tag include an image inside its body.
// If so, the Hyperlink OpenXmlElement is lost and we'll keep only the images
// and applied a HyperlinkOnClick attribute.
var imagesInLink = childElements.Where(e => e.HasChild<Drawing>());
if (imagesInLink.Any())
IEnumerable<OpenXmlElement> imagesInLink;
// Clickable image is only supported in body but not in header/footer
if (context.HostingPart is MainDocumentPart &&
(imagesInLink = childElements.Where(e => e.HasChild<Drawing>())).Any())
{
foreach (var img in imagesInLink)
{
Expand Down Expand Up @@ -100,7 +103,7 @@ public override IEnumerable<OpenXmlElement> Interpret (ParsingContext context)
// ensure the links does not start with javascript:
else if (AngleSharpExtensions.TryParseUrl(att, UriKind.Absolute, out var uri))
{
var extLink = context.MainPart.AddHyperlinkRelationship(uri!, true);
var extLink = context.HostingPart.AddHyperlinkRelationship(uri!, true);

h = new Hyperlink(
) { History = true, Id = extLink.Id };
Expand Down
2 changes: 1 addition & 1 deletion src/Html2OpenXml/Expressions/Image/ImageExpression.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,7 +59,7 @@ class ImageExpression(IHtmlImageElement node) : ImageExpressionBase(node)

var (imageObjId, drawingObjId) = IncrementDrawingObjId(context);

HtmlImageInfo? iinfo = context.Converter.ImagePrefetcher.Download(src, CancellationToken.None)
HtmlImageInfo? iinfo = context.ImageLoader.Download(src, CancellationToken.None)
.ConfigureAwait(false).GetAwaiter().GetResult();

if (iinfo == null)
Expand Down
8 changes: 5 additions & 3 deletions src/Html2OpenXml/Expressions/Image/ImageExpressionBase.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@
using System.Collections.Generic;
using System.Linq;
using DocumentFormat.OpenXml;
using DocumentFormat.OpenXml.Packaging;
using DocumentFormat.OpenXml.Wordprocessing;

using a = DocumentFormat.OpenXml.Drawing;
Expand Down Expand Up @@ -85,10 +86,11 @@ internal static (uint imageObjId, uint drawingObjId) IncrementDrawingObjId(Parsi
drawingObjId ??= 1; // 1 is the minimum ID set by MS Office.
imageObjId ??= 1;

var mainPart = context.MainPart;
foreach (var part in new[] {
context.MainPart.Document.Body!.Descendants<Drawing>(),
context.MainPart.HeaderParts.Where(f => f.Header != null).SelectMany(f => f.Header.Descendants<Drawing>()),
context.MainPart.FooterParts.Where(f => f.Footer != null).SelectMany(f => f.Footer.Descendants<Drawing>())
mainPart.Document.Body!.Descendants<Drawing>(),
mainPart.HeaderParts.Where(f => f.Header != null).SelectMany(f => f.Header.Descendants<Drawing>()),
mainPart.FooterParts.Where(f => f.Footer != null).SelectMany(f => f.Footer.Descendants<Drawing>())
})
foreach (Drawing d in part)
{
Expand Down
Loading
Loading