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/integration_tests/document_loaders/parsers/test_pdf_parsers.py

@@ -14,7 +14,6 @@ from langchain_community.document_loaders.parsers import (
     PDFMinerParser,
     PDFPlumberParser,
     PyPDFium2Parser,
-    PyPDFParser,
 )
 
 if TYPE_CHECKING:
@@ -98,11 +97,6 @@ def _assert_with_duplicate_parser(parser: BaseBlobParser, dedupe: bool = False)
         assert "11000000 SSeerriieess" == docs[0].page_content.split("\n")[0]
 
 
-def test_pypdf_parser() -> None:
-    """Test PyPDF parser."""
-    _assert_with_parser(PyPDFParser())
-
-
 def test_pdfminer_parser() -> None:
     """Test PDFMiner parser."""
     # Does not follow defaults to split by page.
@@ -122,11 +116,6 @@ def test_pdfplumber_parser() -> None:
     _assert_with_duplicate_parser(PDFPlumberParser(dedupe=True), dedupe=True)
 
 
-def test_extract_images_text_from_pdf_pypdfparser() -> None:
-    """Test extract image from pdf and recognize text with rapid ocr - PyPDFParser"""
-    _assert_with_parser(PyPDFParser(extract_images=True))
-
-
 def test_extract_images_text_from_pdf_pdfminerparser() -> None:
     """Test extract image from pdf and recognize text with rapid ocr - PDFMinerParser"""
     _assert_with_parser(PDFMinerParser(extract_images=True))
@@ -150,6 +139,8 @@ class EmptyImageBlobParser(BaseImageBlobParser):
     "parser_factory,params",
     [
         ("PyMuPDFParser", {}),
+        ("PyPDFParser", {"extraction_mode": "plain"}),
+        ("PyPDFParser", {"extraction_mode": "layout"}),
     ],
 )
 @pytest.mark.requires("pillow")
@@ -176,6 +167,8 @@ def test_mode_and_extract_images_variations(
     "parser_factory,params",
     [
         ("PyMuPDFParser", {}),
+        ("PyPDFParser", {"extraction_mode": "plain"}),
+        ("PyPDFParser", {"extraction_mode": "layout"}),
     ],
 )
 @pytest.mark.requires("pillow")

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

@@ -212,6 +212,7 @@ def test_amazontextract_loader_failures() -> None:
     "parser_factory,params",
     [
         ("PyMuPDFLoader", {}),
+        ("PyPDFLoader", {}),
     ],
 )
 def test_standard_parameters(
@@ -229,12 +230,10 @@ def test_standard_parameters(
     loader = loader_class(
         file_path,
         mode="page",
-        page_delimiter="---",
+        pages_delimiter="---",
         images_parser=None,
         images_inner_format="text",
         password=None,
-        extract_tables=None,
-        extract_tables_settings=None,
     )
     docs = loader.load()
     assert len(docs) == 16

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")