lsm/PdfPig
1
0
Fork 0
mirror of https://github.com/UglyToad/PdfPig.git synced 2025-08-20 04:31:25 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

i merged a pr which broke the build, this updates the build to work

Browse Source 
move all arguments to add page to a setting object so it can be extended
in future in a non-breaking api change
This commit is contained in:
EliotJones 2025-07-20 11:24:21 -05:00 committed by BobLd
parent e636212ec8
commit efb8c2a803
3 changed files with 256 additions and 233 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/UglyToad.PdfPig.Tests/Writer/PdfDocumentBuilderTests.cs
View File

@ -139,7 +139,10 @@
using (var existing = PdfDocument.Open(contents, ParsingOptions.LenientParsingOff))
using (var output = new PdfDocumentBuilder())
{
output.AddPage(existing, 1, false);
output.AddPage(existing, 1, new PdfDocumentBuilder.AddPageOptions
{
KeepAnnotations = false
});
results = output.Build();
var pg = existing.GetPage(1);
var annots = pg.ExperimentalAccess.GetAnnotations().ToList();

32
src/UglyToad.PdfPig/Writer/PdfDocumentBuilder.cs
View File

@ -307,11 +307,11 @@ namespace UglyToad.PdfPig.Writer
/// </summary>
/// <param name="document">Source document.</param>
/// <param name="pageNumber">Page to copy.</param>
/// <param name="keepAnnotations">Flag to set whether annotation of page should be kept</param>
/// <param name="options">Control how copying for the page occurs.</param>
/// <returns>A builder for editing the page.</returns>
public PdfPageBuilder AddPage(PdfDocument document, int pageNumber, bool keepAnnotations = true)
public PdfPageBuilder AddPage(PdfDocument document, int pageNumber)
{
return AddPage(document, pageNumber, null);
return AddPage(document, pageNumber, new AddPageOptions());
}
/// <summary>
@ -319,9 +319,9 @@ namespace UglyToad.PdfPig.Writer
/// </summary>
/// <param name="document">Source document.</param>
/// <param name="pageNumber">Page to copy.</param>
/// <param name="copyLink">If set, links are copied based on the result of the delegate.</param>
/// <param name="options">Control how copying for the page occurs.</param>
/// <returns>A builder for editing the page.</returns>
public PdfPageBuilder AddPage(PdfDocument document, int pageNumber, Func<PdfAction, PdfAction?>? copyLink)
public PdfPageBuilder AddPage(PdfDocument document, int pageNumber, AddPageOptions options)
{
if (!existingCopies.TryGetValue(document.Structure.TokenScanner, out var refs))
{
@ -454,7 +454,7 @@ namespace UglyToad.PdfPig.Writer
if (kvp.Key == NameToken.Annots)
{
if (!keepAnnotations)
if (!options.KeepAnnotations)
{
continue;
}
@ -490,7 +490,7 @@ namespace UglyToad.PdfPig.Writer
if (tk.TryGet(NameToken.Subtype, out var st) && st is NameToken nm && nm == NameToken.Link)
{
if (copyLink is null)
if (options.CopyLinkFunc is null)
{
// ignore link if don't know how to copy
continue;
@ -503,7 +503,7 @@ namespace UglyToad.PdfPig.Writer
continue;
}
var copiedLink = copyLink(link);
var copiedLink = options.CopyLinkFunc(link);
if (copiedLink is null)
{
// ignore if caller wants to skip the link
@ -1248,5 +1248,21 @@ namespace UglyToad.PdfPig.Writer
context.Dispose();
}
/// <summary>
/// Options for how a page should be copied to the current builder when using AddPage.
/// </summary>
public class AddPageOptions
{
/// <summary>
/// Whether to preserve annotation objects in the copied page.
/// </summary>
public bool KeepAnnotations { get; set; } = true;
/// <summary>
/// Intercept how actions are copied from the source to destination page.
/// </summary>
public Func<PdfAction, PdfAction?>? CopyLinkFunc { get; set; }
}
}
}

452
src/UglyToad.PdfPig/Writer/PdfMerger.cs
View File

@ -1,236 +1,240 @@
namespace UglyToad.PdfPig.Writer
namespace UglyToad.PdfPig.Writer;
using System;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using Actions;
using Outline.Destinations;
/// <summary>
/// Merges PDF documents into each other.
/// </summary>
public static class PdfMerger
{
using System;
using System.Collections.Generic;
using System.IO;
using Filters;
using Logging;
using System.Linq;
using UglyToad.PdfPig.Actions;
using UglyToad.PdfPig.Outline.Destinations;
/// <summary>
/// Merge two PDF documents together with the pages from <paramref name="file1"/> followed by <paramref name="file2"/>.
/// </summary>
public static byte[] Merge(
string file1,
string file2,
IReadOnlyList<int>? file1Selection = null,
IReadOnlyList<int>? file2Selection = null,
PdfAStandard archiveStandard = PdfAStandard.None,
PdfDocumentBuilder.DocumentInformationBuilder? docInfoBuilder = null)
{
using (var output = new MemoryStream())
{
Merge(file1, file2, output, file1Selection, file2Selection, archiveStandard, docInfoBuilder);
return output.ToArray();
}
}
/// <summary>
/// Merges PDF documents into each other.
/// Merge two PDF documents together with the pages from <paramref name="file1"/> followed by <paramref name="file2"/> into the output stream.
/// </summary>
public static class PdfMerger
public static void Merge(
string file1,
string file2,
Stream output,
IReadOnlyList<int>? file1Selection = null,
IReadOnlyList<int>? file2Selection = null,
PdfAStandard archiveStandard = PdfAStandard.None,
PdfDocumentBuilder.DocumentInformationBuilder? docInfoBuilder = null)
{
private static readonly ILog Log = new NoOpLog();
_ = file1 ?? throw new ArgumentNullException(nameof(file1));
_ = file2 ?? throw new ArgumentNullException(nameof(file2));
private static readonly IFilterProvider FilterProvider = DefaultFilterProvider.Instance;
/// <summary>
/// Merge two PDF documents together with the pages from <paramref name="file1"/> followed by <paramref name="file2"/>.
/// </summary>
public static byte[] Merge(
string file1,
string file2,
IReadOnlyList<int>? file1Selection = null,
IReadOnlyList<int>? file2Selection = null,
PdfAStandard archiveStandard = PdfAStandard.None,
PdfDocumentBuilder.DocumentInformationBuilder? docInfoBuilder = null)
using (var stream1 = File.OpenRead(file1))
{
using (var output = new MemoryStream())
using (var stream2 = File.OpenRead(file2))
{
Merge(file1, file2, output, file1Selection, file2Selection, archiveStandard, docInfoBuilder);
return output.ToArray();
}
}
/// <summary>
/// Merge two PDF documents together with the pages from <paramref name="file1"/> followed by <paramref name="file2"/> into the output stream.
/// </summary>
public static void Merge(
string file1,
string file2,
Stream output,
IReadOnlyList<int>? file1Selection = null,
IReadOnlyList<int>? file2Selection = null,
PdfAStandard archiveStandard = PdfAStandard.None,
PdfDocumentBuilder.DocumentInformationBuilder? docInfoBuilder = null)
{
_ = file1 ?? throw new ArgumentNullException(nameof(file1));
_ = file2 ?? throw new ArgumentNullException(nameof(file2));
using (var stream1 = File.OpenRead(file1))
{
using (var stream2 = File.OpenRead(file2))
{
Merge(new[] { stream1, stream2 }, output, new[] { file1Selection, file2Selection }, archiveStandard, docInfoBuilder);
}
}
}
/// <summary>
/// Merge multiple PDF documents together with the pages in the order the file paths are provided.
/// </summary>
public static byte[] Merge(params string[] filePaths)
{
return Merge(PdfAStandard.None, null, filePaths);
}
/// <summary>
/// Merge multiple PDF documents together with the pages in the order the file paths are provided.
/// </summary>
public static byte[] Merge(PdfAStandard archiveStandard, PdfDocumentBuilder.DocumentInformationBuilder? docInfoBuilder, params string[] filePaths)
{
using (var output = new MemoryStream())
{
Merge(output, archiveStandard, docInfoBuilder, filePaths);
return output.ToArray();
}
}
/// <summary>
/// Merge multiple PDF documents together with the pages in the order the file paths are provided into the output stream
/// </summary>
public static void Merge(Stream output, params string[] filePaths)
{
Merge(output, PdfAStandard.None, null, filePaths);
}
/// <summary>
/// Merge multiple PDF documents together with the pages in the order the file paths are provided into the output stream
/// </summary>
public static void Merge(Stream output, PdfAStandard archiveStandard, PdfDocumentBuilder.DocumentInformationBuilder? docInfoBuilder, params string[] filePaths)
{
var streams = new List<Stream>(filePaths.Length);
try
{
for (var i = 0; i < filePaths.Length; i++)
{
var filePath = filePaths[i] ?? throw new ArgumentNullException(nameof(filePaths), $"Null filepath at index {i}.");
streams.Add(File.OpenRead(filePath));
}
Merge(streams, output, null, archiveStandard, docInfoBuilder);
}
finally
{
foreach (var stream in streams)
{
stream.Dispose();
}
}
}
/// <summary>
/// Merge the set of PDF documents.
/// </summary>
public static byte[] Merge(
IReadOnlyList<byte[]> files,
IReadOnlyList<IReadOnlyList<int>>? pagesBundle = null,
PdfAStandard archiveStandard = PdfAStandard.None,
PdfDocumentBuilder.DocumentInformationBuilder? docInfoBuilder = null)
{
_ = files ?? throw new ArgumentNullException(nameof(files));
using (var output = new MemoryStream())
{
Merge(files.Select(f => PdfDocument.Open(f)).ToArray(), output, pagesBundle, archiveStandard, docInfoBuilder);
return output.ToArray();
}
}
/// <summary>
/// Merge the set of PDF documents into the output stream
/// The caller must manage disposing the stream. The created PdfDocument will not dispose the stream.
/// <param name="streams">
/// A list of streams for the files contents, this must support reading and seeking.
/// </param>
/// <param name="output">Must be writable</param>
/// <param name="pagesBundle"></param>
/// <param name="archiveStandard"></param>
/// <param name="docInfoBuilder"></param>
/// </summary>
public static void Merge(
IReadOnlyList<Stream> streams,
Stream output,
IReadOnlyList<IReadOnlyList<int>?>? pagesBundle = null,
PdfAStandard archiveStandard = PdfAStandard.None,
PdfDocumentBuilder.DocumentInformationBuilder? docInfoBuilder = null)
{
_ = streams ?? throw new ArgumentNullException(nameof(streams));
_ = output ?? throw new ArgumentNullException(nameof(output));
Merge(streams.Select(f => PdfDocument.Open(f)).ToArray(), output, pagesBundle, archiveStandard, docInfoBuilder);
}
private static void Merge(
IReadOnlyList<PdfDocument> files,
Stream output,
IReadOnlyList<IReadOnlyList<int>?>? pagesBundle,
PdfAStandard archiveStandard = PdfAStandard.None,
PdfDocumentBuilder.DocumentInformationBuilder? docInfoBuilder = null)
{
var maxVersion = files.Select(x => x.Version).Max();
using (var document = new PdfDocumentBuilder(output, false, PdfWriterType.Default, maxVersion))
{
document.ArchiveStandard = archiveStandard;
if (docInfoBuilder != null)
{
document.IncludeDocumentInformation = true;
document.DocumentInformation = docInfoBuilder;
}
foreach (var fileIndex in Enumerable.Range(0, files.Count))
{
var existing = files[fileIndex];
IReadOnlyList<int>? pages = null;
if (pagesBundle != null && fileIndex < pagesBundle.Count)
{
pages = pagesBundle[fileIndex];
}
var basePageNumber = document.Pages.Count;
if (pages is null)
{
for (var i = 1; i <= existing.NumberOfPages; i++)
{
document.AddPage(existing, i, link => CopyLink(link, n => basePageNumber + n));
}
}
else
{
var pageNumbers = new Dictionary<int, int>();
for (var i = 0; i < pages.Count; i++)
{
pageNumbers[pages[i]] = basePageNumber + i + 1;
}
foreach (var i in pages)
{
document.AddPage(existing, i, link => CopyLink(
link, n => pageNumbers.TryGetValue(n, out var pageNumber) ? pageNumber : null));
}
}
}
}
PdfAction? CopyLink(PdfAction action, Func<int, int?> getPageNumber)
{
var link = action as AbstractGoToAction;
if (link is null)
{
// copy the link if it is not a link to PDF documents
return action;
}
var newPageNumber = getPageNumber(link.Destination.PageNumber);
if (newPageNumber is null)
{
// ignore the link if the target page does not exist in the PDF document
return null;
}
var newDestination = new ExplicitDestination(newPageNumber.Value, link.Destination.Type, link.Destination.Coordinates);
return action switch {
GoToAction goToAction => new GoToAction(newDestination),
GoToEAction goToEAction => new GoToEAction(newDestination, goToEAction.FileSpecification),
GoToRAction goToRAction => new GoToRAction(newDestination, goToRAction.Filename),
_ => action
};
Merge(new[] { stream1, stream2 }, output, new[] { file1Selection, file2Selection }, archiveStandard, docInfoBuilder);
}
}
}
/// <summary>
/// Merge multiple PDF documents together with the pages in the order the file paths are provided.
/// </summary>
public static byte[] Merge(params string[] filePaths)
{
return Merge(PdfAStandard.None, null, filePaths);
}
/// <summary>
/// Merge multiple PDF documents together with the pages in the order the file paths are provided.
/// </summary>
public static byte[] Merge(PdfAStandard archiveStandard, PdfDocumentBuilder.DocumentInformationBuilder? docInfoBuilder, params string[] filePaths)
{
using (var output = new MemoryStream())
{
Merge(output, archiveStandard, docInfoBuilder, filePaths);
return output.ToArray();
}
}
/// <summary>
/// Merge multiple PDF documents together with the pages in the order the file paths are provided into the output stream
/// </summary>
public static void Merge(Stream output, params string[] filePaths)
{
Merge(output, PdfAStandard.None, null, filePaths);
}
/// <summary>
/// Merge multiple PDF documents together with the pages in the order the file paths are provided into the output stream
/// </summary>
public static void Merge(Stream output, PdfAStandard archiveStandard, PdfDocumentBuilder.DocumentInformationBuilder? docInfoBuilder, params string[] filePaths)
{
var streams = new List<Stream>(filePaths.Length);
try
{
for (var i = 0; i < filePaths.Length; i++)
{
var filePath = filePaths[i] ?? throw new ArgumentNullException(nameof(filePaths), $"Null filepath at index {i}.");
streams.Add(File.OpenRead(filePath));
}
Merge(streams, output, null, archiveStandard, docInfoBuilder);
}
finally
{
foreach (var stream in streams)
{
stream.Dispose();
}
}
}
/// <summary>
/// Merge the set of PDF documents.
/// </summary>
public static byte[] Merge(
IReadOnlyList<byte[]> files,
IReadOnlyList<IReadOnlyList<int>>? pagesBundle = null,
PdfAStandard archiveStandard = PdfAStandard.None,
PdfDocumentBuilder.DocumentInformationBuilder? docInfoBuilder = null)
{
_ = files ?? throw new ArgumentNullException(nameof(files));
using (var output = new MemoryStream())
{
Merge(files.Select(f => PdfDocument.Open(f)).ToArray(), output, pagesBundle, archiveStandard, docInfoBuilder);
return output.ToArray();
}
}
/// <summary>
/// Merge the set of PDF documents into the output stream
/// The caller must manage disposing the stream. The created PdfDocument will not dispose the stream.
/// <param name="streams">
/// A list of streams for the files contents, this must support reading and seeking.
/// </param>
/// <param name="output">Must be writable</param>
/// <param name="pagesBundle"></param>
/// <param name="archiveStandard"></param>
/// <param name="docInfoBuilder"></param>
/// </summary>
public static void Merge(
IReadOnlyList<Stream> streams,
Stream output,
IReadOnlyList<IReadOnlyList<int>?>? pagesBundle = null,
PdfAStandard archiveStandard = PdfAStandard.None,
PdfDocumentBuilder.DocumentInformationBuilder? docInfoBuilder = null)
{
_ = streams ?? throw new ArgumentNullException(nameof(streams));
_ = output ?? throw new ArgumentNullException(nameof(output));
Merge(streams.Select(f => PdfDocument.Open(f)).ToArray(), output, pagesBundle, archiveStandard, docInfoBuilder);
}
private static void Merge(
IReadOnlyList<PdfDocument> files,
Stream output,
IReadOnlyList<IReadOnlyList<int>?>? pagesBundle,
PdfAStandard archiveStandard = PdfAStandard.None,
PdfDocumentBuilder.DocumentInformationBuilder? docInfoBuilder = null)
{
var maxVersion = files.Select(x => x.Version).Max();
using (var document = new PdfDocumentBuilder(output, false, PdfWriterType.Default, maxVersion))
{
document.ArchiveStandard = archiveStandard;
if (docInfoBuilder != null)
{
document.IncludeDocumentInformation = true;
document.DocumentInformation = docInfoBuilder;
}
foreach (var fileIndex in Enumerable.Range(0, files.Count))
{
var existing = files[fileIndex];
IReadOnlyList<int>? pages = null;
if (pagesBundle != null && fileIndex < pagesBundle.Count)
{
pages = pagesBundle[fileIndex];
}
var basePageNumber = document.Pages.Count;
if (pages is null)
{
for (var i = 1; i <= existing.NumberOfPages; i++)
{
document.AddPage(existing,
i,
new PdfDocumentBuilder.AddPageOptions
{
CopyLinkFunc = link => CopyLink(link, n => basePageNumber + n)
});
}
}
else
{
var pageNumbers = new Dictionary<int, int>();
for (var i = 0; i < pages.Count; i++)
{
pageNumbers[pages[i]] = basePageNumber + i + 1;
}
foreach (var i in pages)
{
document.AddPage(existing,
i,
new PdfDocumentBuilder.AddPageOptions
{
CopyLinkFunc = link => CopyLink(
link,
n => pageNumbers.TryGetValue(n, out var pageNumber) ? pageNumber : null)
});
}
}
}
}
PdfAction? CopyLink(PdfAction action, Func<int, int?> getPageNumber)
{
var link = action as AbstractGoToAction;
if (link is null)
{
// copy the link if it is not a link to PDF documents
return action;
}
var newPageNumber = getPageNumber(link.Destination.PageNumber);
if (newPageNumber is null)
{
// ignore the link if the target page does not exist in the PDF document
return null;
}
var newDestination = new ExplicitDestination(newPageNumber.Value, link.Destination.Type, link.Destination.Coordinates);
return action switch {
GoToAction => new GoToAction(newDestination),
GoToEAction goToEAction => new GoToEAction(newDestination, goToEAction.FileSpecification),
GoToRAction goToRAction => new GoToRAction(newDestination, goToRAction.Filename),
_ => action
};
}
}
}