From 71c8140d5f7be9bb6302727cf22286a7389bc8b7 Mon Sep 17 00:00:00 2001
From: Alex Huszagh <ahuszagh@gmail.com>
Date: Mon, 23 Oct 2023 14:31:06 -0500
Subject: [PATCH] Fix an issue with infinite recursion.

Use a visited memo to check if the current object in the clone operation
has already been visited, and if so, do not add it to the list of
objects. This avoids infinite recursion in case there are links to
identical objects inside a PDF.
---
 pypdf/generic/_data_structures.py | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/pypdf/generic/_data_structures.py b/pypdf/generic/_data_structures.py
index 94f1f24257..e3120cc78a 100644
--- a/pypdf/generic/_data_structures.py
+++ b/pypdf/generic/_data_structures.py
@@ -40,6 +40,7 @@
     List,
     Optional,
     Sequence,
+    Set,
     Tuple,
     Union,
     cast,
@@ -187,6 +188,7 @@ def clone(
         except Exception:
             pass
 
+        visited = set()
         d__ = cast(
             "DictionaryObject",
             self._reference_clone(self.__class__(), pdf_dest, force_duplicate),
@@ -194,7 +196,7 @@ def clone(
         if ignore_fields is None:
             ignore_fields = []
         if len(d__.keys()) == 0:
-            d__._clone(self, pdf_dest, force_duplicate, ignore_fields)
+            d__._clone(self, pdf_dest, force_duplicate, ignore_fields, visited)
         return d__
 
     def _clone(
@@ -203,6 +205,7 @@ def _clone(
         pdf_dest: PdfWriterProtocol,
         force_duplicate: bool,
         ignore_fields: Optional[Sequence[Union[str, int]]],
+        visited: Set[Tuple[int, int]],
     ) -> None:
         """
         Update the object from src.
@@ -270,6 +273,13 @@ def _clone(
                                     cur_obj.__class__(), pdf_dest, force_duplicate
                                 ),
                             )
+                            # check to see if we've previously processed our item
+                            idnum = clon.indirect_reference.idnum
+                            generation = clon.indirect_reference.generation
+                            if (idnum, generation) in visited:
+                                cur_obj = None
+                                break
+                            visited.add((idnum, generation))
                             objs.append((cur_obj, clon))
                             assert prev_obj is not None
                             prev_obj[NameObject(k)] = clon.indirect_reference
@@ -282,7 +292,7 @@ def _clone(
                             except Exception:
                                 cur_obj = None
                         for s, c in objs:
-                            c._clone(s, pdf_dest, force_duplicate, ignore_fields)
+                            c._clone(s, pdf_dest, force_duplicate, ignore_fields, visited)
 
         for k, v in src.items():
             if k not in ignore_fields:
@@ -798,6 +808,7 @@ def _clone(
         pdf_dest: PdfWriterProtocol,
         force_duplicate: bool,
         ignore_fields: Optional[Sequence[Union[str, int]]],
+        visited: Set[Tuple[int, int]],
     ) -> None:
         """
         Update the object from src.
@@ -820,7 +831,7 @@ def _clone(
                 )
         except Exception:
             pass
-        super()._clone(src, pdf_dest, force_duplicate, ignore_fields)
+        super()._clone(src, pdf_dest, force_duplicate, ignore_fields, visited)
 
     def get_data(self) -> Union[bytes, str]:
         return self._data
@@ -1048,6 +1059,7 @@ def clone(
         except Exception:
             pass
 
+        visited = set()
         d__ = cast(
             "ContentStream",
             self._reference_clone(
@@ -1056,7 +1068,7 @@ def clone(
         )
         if ignore_fields is None:
             ignore_fields = []
-        d__._clone(self, pdf_dest, force_duplicate, ignore_fields)
+        d__._clone(self, pdf_dest, force_duplicate, ignore_fields, visited)
         return d__
 
     def _clone(
@@ -1065,6 +1077,7 @@ def _clone(
         pdf_dest: PdfWriterProtocol,
         force_duplicate: bool,
         ignore_fields: Optional[Sequence[Union[str, int]]],
+        visited: Set[Tuple[int, int]],
     ) -> None:
         """
         Update the object from src.
@@ -1081,7 +1094,7 @@ def _clone(
         self._operations = list(src_cs._operations)
         self.forced_encoding = src_cs.forced_encoding
         # no need to call DictionaryObjection or anything
-        # like super(DictionaryObject,self)._clone(src, pdf_dest, force_duplicate, ignore_fields)
+        # like super(DictionaryObject,self)._clone(src, pdf_dest, force_duplicate, ignore_fields, visited)
 
     def _parse_content_stream(self, stream: StreamType) -> None:
         # 7.8.2 Content Streams