community[minor]: 03 - Refactoring PyPDF parser (#29330)

This is one part of a larger Pull Request (PR) that is too large to be
submitted all at once.
This specific part focuses on updating the PyPDF parser.

For more details, see [PR
28970](https://github.com/langchain-ai/langchain/pull/28970).

libs/community/tests/unit_tests/document_loaders/parsers/test_pdf_parsers.py

@@ -12,7 +12,6 @@ from langchain_community.document_loaders.blob_loaders import Blob
 from langchain_community.document_loaders.parsers.pdf import (
     PDFMinerParser,
     PyPDFium2Parser,
-    PyPDFParser,
     _merge_text_and_extras,
 )
 
@@ -76,12 +75,6 @@ def _assert_with_parser(parser: BaseBlobParser, *, splits_by_page: bool = True)
         assert int(metadata["page"]) == 0
 
 
-@pytest.mark.requires("pypdf")
-def test_pypdf_parser() -> None:
-    """Test PyPDF parser."""
-    _assert_with_parser(PyPDFParser())
-
-
 @pytest.mark.requires("pdfminer")
 def test_pdfminer_parser() -> None:
     """Test PDFMiner parser."""
@@ -100,6 +93,7 @@ def test_pypdfium2_parser() -> None:
     "parser_factory,require,params",
     [
         ("PyMuPDFParser", "pymupdf", {}),
+        ("PyPDFParser", "pypdf", {}),
     ],
 )
 def test_parsers(

libs/community/tests/unit_tests/document_loaders/test_pdf.py

@@ -65,7 +65,8 @@ def test_pypdf_loader_with_layout() -> None:
     expected = path_to_layout_pdf_txt.read_text(encoding="utf-8")
     cleaned_first_page = re.sub(r"\x00", "", first_page)
     cleaned_expected = re.sub(r"\x00", "", expected)
-    assert cleaned_first_page == cleaned_expected
+
+    assert cleaned_first_page == cleaned_expected.strip()
 
 
 @pytest.mark.requires("pypdf")