BUG: Prevent infinite loop when no character follows after a comment (#…

…1828)

Fixes #1825

pypdf/generic/_data_structures.py

@@ -1016,7 +1016,7 @@ def __parse_content_stream(self, stream: StreamType) -> None:
                 # encountering a comment -- but read_object assumes that
                 # following the comment must be the object we're trying to
                 # read.  In this case, it could be an operator instead.
-                while peek not in (b"\r", b"\n"):
+                while peek not in (b"\r", b"\n", b""):
                     peek = stream.read(1)
             else:
                 operands.append(read_object(stream, None, self.forced_encoding))

requirements/ci-3.11.txt

@@ -50,10 +50,13 @@ pytest==7.2.2
     #   -r requirements/ci.in
     #   pytest-benchmark
     #   pytest-socket
+    #   pytest-timeout
 pytest-benchmark==4.0.0
     # via -r requirements/ci.in
 pytest-socket==0.6.0
     # via -r requirements/ci.in
+pytest-timeout==2.1.0
+    # via -r requirements/ci.in
 ruff==0.0.259
     # via -r requirements/ci.in
 typeguard==3.0.2

requirements/ci.in

@@ -9,6 +9,7 @@ pycryptodome
 pytest
 pytest-benchmark
 pytest-socket
+pytest-timeout
 typeguard
 types-dataclasses
 types-Pillow

requirements/ci.txt

@@ -62,10 +62,13 @@ pytest==7.0.1
     #   -r requirements/ci.in
     #   pytest-benchmark
     #   pytest-socket
+    #   pytest-timeout
 pytest-benchmark==3.4.1
     # via -r requirements/ci.in
 pytest-socket==0.4.1
     # via -r requirements/ci.in
+pytest-timeout==2.1.0
+    # via -r requirements/ci.in
 six==1.16.0
     # via flake8-print
 tomli==1.2.3

tests/test_reader.py

@@ -1401,3 +1401,13 @@ def test_iss1756():
     in_pdf = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
     in_pdf.trailer["/ID"]
     # removed to cope with missing cryptodome during commit check : len(in_pdf.pages)
+
+
+@pytest.mark.enable_socket()
+@pytest.mark.timeout(30)
+def test_iss1825():
+    url = "https://github.com/py-pdf/pypdf/files/11367871/MiFO_LFO_FEIS_NOA_Published.3.pdf"
+    name = "iss1825.pdf"
+    reader = PdfReader(BytesIO(get_pdf_from_url(url, name=name)))
+    page = reader.pages[0]
+    page.extract_text()