ROB: Cope with xref not followed by separator (#2083)

Closes #2082
py-pdf · Aug 12, 2023 · 243fd9c · 243fd9c
1 parent f70dfad
commit 243fd9c
Show file tree

Hide file tree

Showing 2 changed files with 16 additions and 2 deletions.
diff --git a/pypdf/_reader.py b/pypdf/_reader.py
@@ -1634,8 +1634,8 @@ def _find_startxref_pos(self, stream: StreamType) -> int:
 
  def _read_standard_xref_table(self, stream: StreamType) -> None:
  # standard cross-reference table
- ref = stream.read(4)
- if ref[:3] != b"ref":
+ ref = stream.read(3)
+ if ref != b"ref":
  raise PdfReadError("xref table read error")
  read_non_whitespace(stream)
  stream.seek(-1, 1)

diff --git a/tests/test_reader.py b/tests/test_reader.py
@@ -1436,3 +1436,17 @@ def test_iss1825():
  reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
  page = reader.pages[0]
  page.extract_text()
+
+
+@pytest.mark.enable_socket()
+def test_iss2082():
+ url = "https://github.com/py-pdf/pypdf/files/12317939/test.pdf"
+ name = "iss2082.pdf"
+ b = get_data_from_url(url, name=name)
+ reader = PdfReader(BytesIO(b))
+ reader.pages[0].extract_text()
+
+ bb = bytearray(b)
+ bb[b.find(b"xref") + 2] = ord(b"E")
+ with pytest.raises(PdfReadError):
+ reader = PdfReader(BytesIO(bb))