From 0fbd95938724ad2d72688d4112207c0590f0483f Mon Sep 17 00:00:00 2001
From: rampageservices <20424586+rampageservices@users.noreply.github.com>
Date: Sat, 21 Feb 2026 23:17:20 +0800
Subject: [PATCH] BUG: Prevent infinite loop from circular xref /Prev
 references

Malformed PDFs can contain circular /Prev references in the xref
chain (e.g., xref A -> /Prev -> xref B -> /Prev -> xref A).
This causes _read_xref_tables_and_trailers() to loop forever,
spamming "Overwriting cache for N M" warnings on every iteration
as the same objects are re-parsed and re-cached indefinitely.

Fix: Track visited xref offsets in a set. If a startxref value
has already been visited, log a warning and break the loop.

Closes #3654
---
 PyPDF2/_reader.py | 9 +++++++++
 1 file changed, 9 insertions(+)

Index: PyPDF2-2.11.1/PyPDF2/_reader.py
===================================================================
--- PyPDF2-2.11.1.orig/PyPDF2/_reader.py
+++ PyPDF2-2.11.1/PyPDF2/_reader.py
@@ -1564,7 +1564,16 @@ class PdfReader:
         self.xref_free_entry: Dict[int, Dict[Any, Any]] = {}
         self.xref_objStm: Dict[int, Tuple[Any, Any]] = {}
         self.trailer = DictionaryObject()
+        visited_xref_offsets: set[int] = set()
         while startxref is not None:
+            # Detect circular /Prev references in the xref chain
+            if startxref in visited_xref_offsets:
+                logger_warning(
+                    f"Circular xref chain detected at offset {startxref}, stopping",
+                    __name__,
+                )
+                break
+            visited_xref_offsets.add(startxref)
             # load the xref table
             stream.seek(startxref, 0)
             x = stream.read(1)