From e12cc1677a48b0830d936b5f37c7ba719bc146fd Mon Sep 17 00:00:00 2001
From: Simon Cropp <simon.cropp@gmail.com>
Date: Thu, 22 Oct 2026 13:40:10 +1100
Subject: [PATCH] Morph.PDFium 1.4.3; convert pages in parallel

Convert rendered and read pages one at a time, loading each page twice
(once for its text, once inside RenderPage). It now goes through
PdfiumDocument.ProcessPages: each wanted page is loaded once, rendered
with page.Render and read, with the pages spread across cores; the
results come back in page order and are added to the conversion from
this thread, so PagedConversion need not be thread safe.

Morph.PDFium 1.4.3 also brings grayscale PNGs for text pages, pooled
render buffers and a per-image filter choice. Measured on a 149 page
text document, converting the whole document went from 1.28 s to 0.72 s
at 96 DPI and 3.35 s to 1.45 s at 200 DPI. The PNGs are different bytes
but compare equal under SSIM, so no snapshots change.
---
 src/Directory.Packages.props      |  2 +-
 src/Verify.PDFium/VerifyPDFium.cs | 40 ++++++++++++++++++++-----------
 2 files changed, 27 insertions(+), 15 deletions(-)

diff --git a/src/Directory.Packages.props b/src/Directory.Packages.props
index a7cf18d..aee0b6c 100644
--- a/src/Directory.Packages.props
+++ b/src/Directory.Packages.props
@@ -5,7 +5,7 @@
   </PropertyGroup>
   <ItemGroup>
     <PackageVersion Include="DeterministicPdf" Version="2.3.0" />
-    <PackageVersion Include="Morph.PDFium" Version="1.4.2" />
+    <PackageVersion Include="Morph.PDFium" Version="1.4.3" />
     <PackageVersion Include="MarkdownSnippets.MsBuild" Version="28.5.1" />
     <PackageVersion Include="ProjectDefaults" Version="1.0.184" />
     <PackageVersion Include="ProjectFiles" Version="1.6.0" />
diff --git a/src/Verify.PDFium/VerifyPDFium.cs b/src/Verify.PDFium/VerifyPDFium.cs
index 5a3220e..ebcecb0 100644
--- a/src/Verify.PDFium/VerifyPDFium.cs
+++ b/src/Verify.PDFium/VerifyPDFium.cs
@@ -104,27 +104,39 @@ static ConversionResult Convert(Stream stream, IReadOnlyDictionary<string, objec
         using (var document = PdfiumDocument.Load(bytes))
         {
             conversion.Info = PdfProperties.Normalize(document.GetProperties());
-            foreach (var number in conversion.Pages(document.PageCount))
-            {
-                var index = number - 1;
-                using var page = document.LoadPage(index);
-                var size = page.Size;
-
-                Stream? image = null;
-                if (includeImages)
+            // The pages are rendered and read in parallel: PDFium works on one at a time, but each
+            // page's PNG encoding overlaps the others' work. The results come back in page order, so
+            // they are added to the conversion in order from this thread.
+            var indices = conversion.Pages(document.PageCount).Select(_ => _ - 1);
+            var pages = document.ProcessPages(
+                indices,
+                _ =>
                 {
-                    image = new MemoryStream(document.RenderPage(index, dpi));
-                }
+                    byte[]? image = null;
+                    if (includeImages)
+                    {
+                        image = _.Render(dpi);
+                    }
 
-                string? text = null;
-                if (includeText)
+                    string? text = null;
+                    if (includeText)
+                    {
+                        text = _.GetText();
+                    }
+
+                    return (Number: _.Index + 1, _.Size, Image: image, Text: text);
+                });
+            foreach (var (number, size, image, text) in pages)
+            {
+                Stream? imageStream = null;
+                if (image != null)
                 {
-                    text = page.GetText();
+                    imageStream = new MemoryStream(image);
                 }
 
                 conversion.AddPage(
                     number,
-                    image,
+                    imageStream,
                     text,
                     new PageSize
                     {