community[minor]: 04 - Refactoring PDFMiner parser (#29526)

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 XXX
parser.

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

---------

Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>

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

@@ -11,7 +11,6 @@ from langchain_community.document_loaders.base import BaseBlobParser
 from langchain_community.document_loaders.blob_loaders import Blob
 from langchain_community.document_loaders.parsers import (
     BaseImageBlobParser,
-    PDFMinerParser,
     PDFPlumberParser,
     PyPDFium2Parser,
 )
@@ -97,12 +96,6 @@ def _assert_with_duplicate_parser(parser: BaseBlobParser, dedupe: bool = False)
         assert "11000000 SSeerriieess" == docs[0].page_content.split("\n")[0]
 
 
-def test_pdfminer_parser() -> None:
-    """Test PDFMiner parser."""
-    # Does not follow defaults to split by page.
-    _assert_with_parser(PDFMinerParser(), splits_by_page=False)
-
-
 def test_pypdfium2_parser() -> None:
     """Test PyPDFium2 parser."""
     # Does not follow defaults to split by page.
@@ -116,11 +109,6 @@ def test_pdfplumber_parser() -> None:
     _assert_with_duplicate_parser(PDFPlumberParser(dedupe=True), dedupe=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))
-
-
 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))
@@ -138,6 +126,7 @@ class EmptyImageBlobParser(BaseImageBlobParser):
 @pytest.mark.parametrize(
     "parser_factory,params",
     [
+        ("PDFMinerParser", {}),
         ("PyMuPDFParser", {}),
         ("PyPDFParser", {"extraction_mode": "plain"}),
         ("PyPDFParser", {"extraction_mode": "layout"}),
@@ -166,6 +155,7 @@ def test_mode_and_extract_images_variations(
 @pytest.mark.parametrize(
     "parser_factory,params",
     [
+        ("PDFMinerParser", {}),
         ("PyMuPDFParser", {}),
         ("PyPDFParser", {"extraction_mode": "plain"}),
         ("PyPDFParser", {"extraction_mode": "layout"}),

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

@@ -8,7 +8,6 @@ import langchain_community.document_loaders as pdf_loaders
 from langchain_community.document_loaders import (
     AmazonTextractPDFLoader,
     MathpixPDFLoader,
-    PDFMinerLoader,
     PDFMinerPDFasHTMLLoader,
     PyPDFium2Loader,
     UnstructuredPDFLoader,
@@ -42,34 +41,6 @@ def test_unstructured_pdf_loader_default_mode() -> None:
     assert len(docs) == 1
 
 
-def test_pdfminer_loader() -> None:
-    """Test PDFMiner loader."""
-    file_path = Path(__file__).parent.parent / "examples/hello.pdf"
-    loader = PDFMinerLoader(file_path)
-    docs = loader.load()
-
-    assert len(docs) == 1
-
-    file_path = Path(__file__).parent.parent / "examples/layout-parser-paper.pdf"
-    loader = PDFMinerLoader(file_path)
-
-    docs = loader.load()
-    assert len(docs) == 1
-
-    # Verify that concatenating pages parameter works
-    file_path = Path(__file__).parent.parent / "examples/hello.pdf"
-    loader = PDFMinerLoader(file_path, concatenate_pages=True)
-    docs = loader.load()
-
-    assert len(docs) == 1
-
-    file_path = Path(__file__).parent.parent / "examples/layout-parser-paper.pdf"
-    loader = PDFMinerLoader(file_path, concatenate_pages=False)
-
-    docs = loader.load()
-    assert len(docs) == 16
-
-
 def test_pdfminer_pdf_as_html_loader() -> None:
     """Test PDFMinerPDFasHTMLLoader."""
     file_path = Path(__file__).parent.parent / "examples/hello.pdf"
@@ -211,6 +182,7 @@ def test_amazontextract_loader_failures() -> None:
 @pytest.mark.parametrize(
     "parser_factory,params",
     [
+        ("PDFMinerLoader", {}),
         ("PyMuPDFLoader", {}),
         ("PyPDFLoader", {}),
     ],
@@ -234,6 +206,8 @@ 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

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

@@ -10,7 +10,6 @@ import langchain_community.document_loaders.parsers as pdf_parsers
 from langchain_community.document_loaders.base import BaseBlobParser
 from langchain_community.document_loaders.blob_loaders import Blob
 from langchain_community.document_loaders.parsers.pdf import (
-    PDFMinerParser,
     PyPDFium2Parser,
     _merge_text_and_extras,
 )
@@ -75,13 +74,6 @@ def _assert_with_parser(parser: BaseBlobParser, *, splits_by_page: bool = True)
         assert int(metadata["page"]) == 0
 
 
-@pytest.mark.requires("pdfminer")
-def test_pdfminer_parser() -> None:
-    """Test PDFMiner parser."""
-    # Does not follow defaults to split by page.
-    _assert_with_parser(PDFMinerParser(), splits_by_page=False)
-
-
 @pytest.mark.requires("pypdfium2")
 def test_pypdfium2_parser() -> None:
     """Test PyPDFium2 parser."""
@@ -92,6 +84,7 @@ def test_pypdfium2_parser() -> None:
 @pytest.mark.parametrize(
     "parser_factory,require,params",
     [
+        ("PDFMinerParser", "pdfminer", {"splits_by_page": False}),
         ("PyMuPDFParser", "pymupdf", {}),
         ("PyPDFParser", "pypdf", {}),
     ],