Skip to content

Fix: brute-force xref scan loses stream position, missing recoverable trailers #1360

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
BobLd merged 1 commit into from
Jul 14, 2026
Merged

Fix: brute-force xref scan loses stream position, missing recoverable trailers #1360

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
19 changes: 18 additions & 1 deletion src/UglyToad.PdfPig/Parser/FileStructure/XrefBruteForcer.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
namespace UglyToad.PdfPig.Parser.FileStructure;
namespace UglyToad.PdfPig.Parser.FileStructure;

using Core;
using Logging;
Expand Down Expand Up @@ -135,6 +135,12 @@ void AddQueues(long num)

var potentialTableOffset = bytes.CurrentOffset - 4;

// TryReadTableAtOffset seeks the shared stream and does not restore
// position (including on failure). Snapshot so the scan resumes from
// here — otherwise a failed parse can skip past later keywords such
// as a recoverable 'trailer' dictionary.
var resumePosition = bytes.CurrentOffset;

if (xrefOffsetSeen.Contains(potentialTableOffset))
{
log.Debug($"Skipping circular xref reference at {potentialTableOffset}");
Expand All @@ -158,6 +164,8 @@ void AddQueues(long num)
log.Warn(
$"Found a table at {potentialTableOffset} but couldn't parse it.");
}

bytes.Seek(resumePosition);
}
else if (buffer.EndsWith("/XRef"))
{
Expand All @@ -176,6 +184,9 @@ void AddQueues(long num)
}
xrefOffsetSeen.Add(offset);

// Same position-preservation as the table branch above.
var resumePosition = bytes.CurrentOffset;

var stream = XrefStreamParser.TryReadStreamAtOffset(
new FileHeaderOffset(0),
offset,
Expand All @@ -187,11 +198,17 @@ void AddQueues(long num)
{
results.Add(stream);
}

bytes.Seek(resumePosition);
}
else if (buffer.EndsWith("trailer "))
{
ClearQueues();

// Ensure the scanner reads from the byte scan's current position —
// a preceding failed table/stream parse may have moved it elsewhere.
scanner.Seek(bytes.CurrentOffset);

// Grab the last trailer dictionary as backup in case we find no valid xrefs.
if (scanner.TryReadToken(out DictionaryToken trailerDict))
{
Expand Down
Loading