From d3e65f24e3594c35dd23ad6378507a62f5e96710 Mon Sep 17 00:00:00 2001
From: Jonas Jenwald <jonas.jenwald@gmail.com>
Date: Sat, 6 Feb 2021 14:04:05 +0100
Subject: [PATCH] Request all data, rather than throwing, when encountering
 general errors in `ObjectLoader._walk` (issue 9462, PR 3289 follow-up)

*As far as I can tell, this has been broken ever since PR 3289 (back in 2013) without anyone noticing.*

For any non-`MissingDataException` errors encountered in `ObjectLoader._walk`, we're simply throwing immediately which thus has the potential to *completely* break rendering of an entire page.
In practice this is obviously only an issue for PDF documents which are in one way or another corrupt, since that's the only way that `XRef.fetch` will throw non-`MissingDataException` errors. To make matters worse these errors are *intermittent*, since they can only occur if the document is still loading when the `ObjectLoader`-code runs (note the early return in `ObjectLoader.load`).

Please note that we cannot simply catch the error and let "normal" parsing continue in `ObjectLoader._walk`, since that could lead to errors elsewhere given that resources "below" the current one (in the graph) might not be checked as intended then.
All-in-all, the only way to make absolutely sure that we won't cause *unexpected* `MissingDataException`s somewhere else in the code-base is to fallback to fetching the *entire* document in this edge-case.
---
 src/core/obj.js              | 6 +++++-
 test/pdfs/issue9462.pdf.link | 1 +
 test/test_manifest.json      | 9 +++++++++
 3 files changed, 15 insertions(+), 1 deletion(-)
 create mode 100644 test/pdfs/issue9462.pdf.link

diff --git a/src/core/obj.js b/src/core/obj.js
index 4061bb076..706d6d616 100644
--- a/src/core/obj.js
+++ b/src/core/obj.js
@@ -2556,7 +2556,11 @@ const ObjectLoader = (function () {
             currentNode = this.xref.fetch(currentNode);
           } catch (ex) {
             if (!(ex instanceof MissingDataException)) {
-              throw ex;
+              warn(`ObjectLoader._walk - requesting all data: "${ex}".`);
+              this.refSet = null;
+
+              const { manager } = this.xref.stream;
+              return manager.requestAllChunks();
             }
             nodesToRevisit.push(currentNode);
             pendingRequests.push({ begin: ex.begin, end: ex.end });
diff --git a/test/pdfs/issue9462.pdf.link b/test/pdfs/issue9462.pdf.link
new file mode 100644
index 000000000..673e2cca3
--- /dev/null
+++ b/test/pdfs/issue9462.pdf.link
@@ -0,0 +1 @@
+https://github.com/mozilla/pdf.js/files/1706865/cb7e7bd2362328f37fe97dc8dff151a3.pdf
diff --git a/test/test_manifest.json b/test/test_manifest.json
index 446068d36..4d9a8d51d 100644
--- a/test/test_manifest.json
+++ b/test/test_manifest.json
@@ -1127,6 +1127,15 @@
        "rounds": 1,
        "type": "load"
     },
+    {  "id": "issue9462",
+       "file": "pdfs/issue9462.pdf",
+       "md5": "0a2895b0aa8a8ef730a20b4116cd996c",
+       "rounds": 1,
+       "link": true,
+       "firstPage": 3,
+       "lastPage": 3,
+       "type": "eq"
+    },
     {  "id": "f1040",
        "file": "pdfs/f1040.pdf",
        "md5": "7323b50c6d28d959b8b4b92c469b2469",