ROB: Tolerate comments in arrays (#2856)

Closes #2843.

pypdf/_utils.py

@@ -206,6 +206,8 @@ def skip_over_comment(stream: StreamType) -> None:
     if tok == b"%":
         while tok not in (b"\n", b"\r"):
             tok = stream.read(1)
+            if tok == b"":
+                raise PdfStreamError("File ended unexpectedly.")
 
 
 def read_until_regex(stream: StreamType, regex: Pattern[bytes]) -> bytes:

pypdf/generic/_data_structures.py

@@ -232,6 +232,10 @@ def read_from_stream(
             tok = stream.read(1)
             while tok.isspace():
                 tok = stream.read(1)
+            if tok == b"%":
+                stream.seek(-1, 1)
+                skip_over_comment(stream)
+                continue
             stream.seek(-1, 1)
             # check for array ending
             peek_ahead = stream.read(1)
@@ -1341,12 +1345,7 @@ def read_object(
         return NullObject.read_from_stream(stream)
     elif tok == b"%":
         # comment
-        while tok not in (b"\r", b"\n"):
-            tok = stream.read(1)
-            # Prevents an infinite loop by raising an error if the stream is at
-            # the EOF
-            if len(tok) <= 0:
-                raise PdfStreamError("File ended unexpectedly.")
+        skip_over_comment(stream)
         tok = read_non_whitespace(stream)
         stream.seek(-1, 1)
         return read_object(stream, pdf, forced_encoding)

tests/test_reader.py

@@ -17,6 +17,7 @@
     EmptyFileError,
     FileNotDecryptedError,
     PdfReadError,
+    PdfStreamError,
     WrongPasswordError,
 )
 from pypdf.generic import (
@@ -1641,3 +1642,18 @@ def test_truncated_files(caplog):
     reader = PdfReader(BytesIO(b[:-6]))
     assert "CAUTION: startxref found while searching for %%EOF" in caplog.text
     assert reader._startxref < 100993
+
+
+@pytest.mark.enable_socket()
+def test_comments_in_array(caplog):
+    """Cf #2843: this deals with comments"""
+    url = "https://github.com/user-attachments/files/16992416/crash-2347912aa2a6f0fab5df4ebc8a424735d5d0d128.pdf"
+    name = "iss2843.pdf"  # reused
+    b = get_data_from_url(url, name=name)
+    reader = PdfReader(BytesIO(b))
+    reader.pages[0]
+    assert caplog.text == ""
+    reader = PdfReader(BytesIO(b))
+    reader.stream = BytesIO(b[:1149])
+    with pytest.raises(PdfStreamError):
+        reader.pages[0]