From 9c857166cca051312ca6a47797b2d8a5732b6cc1 Mon Sep 17 00:00:00 2001
From: Jonas Jenwald <jonas.jenwald@gmail.com>
Date: Tue, 24 Mar 2026 22:36:51 +0100
Subject: [PATCH] Avoid downloading test PDFs multiple times

It's somewhat common for multiple test-cases to use the same PDF, for example tests for both `eq` and `text` with one PDF.
Currently the logic in `downloadManifestFiles` doesn't handle duplicate test PDFs, which leads to wasted time/resources by downloading the same PDF more than once. Naturally the effect of this is especially bad when downloading all linked PDFs.

Total number of test PDFs downloaded:
 - 507, with `master`.
 - 447, with this patch.
---
 test/downloadutils.mjs | 27 ++++++++++++++++++++-------
 1 file changed, 20 insertions(+), 7 deletions(-)

diff --git a/test/downloadutils.mjs b/test/downloadutils.mjs
index 63cb81473..9fdbe4780 100644
--- a/test/downloadutils.mjs
+++ b/test/downloadutils.mjs
@@ -40,14 +40,27 @@ async function downloadFile(file, url) {
 }
 
 async function downloadManifestFiles(manifest) {
-  const links = manifest
-    .filter(item => item.link && !fs.existsSync(item.file))
-    .map(item => {
-      const url = fs.readFileSync(`${item.file}.link`).toString().trimEnd();
-      return { file: item.file, url };
-    });
+  // Keep track of file identifiers to remove any duplicates,
+  // since multiple test-cases may use the same PDF.
+  const seenFiles = new Set();
 
-  for (const { file, url } of links) {
+  const links = new Map(
+    manifest
+      .filter(({ link, file }) => {
+        if (!link || seenFiles.has(file)) {
+          return false;
+        }
+        seenFiles.add(file);
+        return !fs.existsSync(file);
+      })
+      .map(({ file }) => {
+        const url = fs.readFileSync(`${file}.link`).toString().trimEnd();
+        return [file, url];
+      })
+  );
+  seenFiles.clear();
+
+  for (const [file, url] of links) {
     console.log(`Downloading ${url} to ${file}...`);
     try {
       await downloadFile(file, url);