community[minor]: 05 - Refactoring PyPDFium2 parser (#29625)

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
PyPDFium2 parser.

For more details, see
https://github.com/langchain-ai/langchain/pull/28970.

libs/community/tests/integration_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 import (
     BaseImageBlobParser,
     PDFPlumberParser,
-    PyPDFium2Parser,
 )
 
 if TYPE_CHECKING:
@@ -96,12 +95,6 @@ def _assert_with_duplicate_parser(parser: BaseBlobParser, dedupe: bool = False)
         assert "11000000 SSeerriieess" == docs[0].page_content.split("\n")[0]
 
 
-def test_pypdfium2_parser() -> None:
-    """Test PyPDFium2 parser."""
-    # Does not follow defaults to split by page.
-    _assert_with_parser(PyPDFium2Parser())
-
-
 def test_pdfplumber_parser() -> None:
     """Test PDFPlumber parser."""
     _assert_with_parser(PDFPlumberParser())
@@ -109,11 +102,6 @@ def test_pdfplumber_parser() -> None:
     _assert_with_duplicate_parser(PDFPlumberParser(dedupe=True), dedupe=True)
 
 
-def test_extract_images_text_from_pdf_pypdfium2parser() -> None:
-    """Test extract image from pdf and recognize text with rapid ocr - PyPDFium2Parser"""  # noqa: E501
-    _assert_with_parser(PyPDFium2Parser(extract_images=True))
-
-
 class EmptyImageBlobParser(BaseImageBlobParser):
     def _analyze_image(self, img: "Image") -> str:
         return "Hello world"
@@ -128,6 +116,7 @@ class EmptyImageBlobParser(BaseImageBlobParser):
     [
         ("PDFMinerParser", {}),
         ("PyMuPDFParser", {}),
+        ("PyPDFium2Parser", {}),
         ("PyPDFParser", {"extraction_mode": "plain"}),
         ("PyPDFParser", {"extraction_mode": "layout"}),
     ],
@@ -157,6 +146,7 @@ def test_mode_and_extract_images_variations(
     [
         ("PDFMinerParser", {}),
         ("PyMuPDFParser", {}),
+        ("PyPDFium2Parser", {}),
         ("PyPDFParser", {"extraction_mode": "plain"}),
         ("PyPDFParser", {"extraction_mode": "layout"}),
     ],

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

@@ -9,7 +9,6 @@ from langchain_community.document_loaders import (
     AmazonTextractPDFLoader,
     MathpixPDFLoader,
     PDFMinerPDFasHTMLLoader,
-    PyPDFium2Loader,
     UnstructuredPDFLoader,
 )
 
@@ -56,21 +55,6 @@ def test_pdfminer_pdf_as_html_loader() -> None:
     assert len(docs) == 1
 
 
-def test_pypdfium2_loader() -> None:
-    """Test PyPDFium2Loader."""
-    file_path = Path(__file__).parent.parent / "examples/hello.pdf"
-    loader = PyPDFium2Loader(file_path)
-    docs = loader.load()
-
-    assert len(docs) == 1
-
-    file_path = Path(__file__).parent.parent / "examples/layout-parser-paper.pdf"
-    loader = PyPDFium2Loader(file_path)
-
-    docs = loader.load()
-    assert len(docs) == 16
-
-
 @pytest.mark.skipif(
     not os.environ.get("MATHPIX_API_KEY"), reason="Mathpix API key not found"
 )
@@ -184,6 +168,7 @@ def test_amazontextract_loader_failures() -> None:
     [
         ("PDFMinerLoader", {}),
         ("PyMuPDFLoader", {}),
+        ("PyPDFium2Loader", {}),
         ("PyPDFLoader", {}),
     ],
 )
@@ -206,8 +191,6 @@ def test_standard_parameters(
         images_parser=None,
         images_inner_format="text",
         password=None,
-        extract_tables=None,
-        extract_tables_settings=None,
     )
     docs = loader.load()
     assert len(docs) == 16