mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-27 04:24:45 +00:00
52 lines
1.4 KiB
Python
52 lines
1.4 KiB
Python
from pathlib import Path
|
|
|
|
from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
|
|
from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
|
|
from docling.datamodel.base_models import PdfPipelineOptions
|
|
from docling.datamodel.document import ConversionResult
|
|
from docling.pdf_document_converter import PdfDocumentConverter
|
|
|
|
from .verify_utils import verify_conversion_result
|
|
|
|
GENERATE = False
|
|
|
|
|
|
def get_pdf_paths():
|
|
|
|
# Define the directory you want to search
|
|
directory = Path("./tests/data")
|
|
|
|
# List all PDF files in the directory and its subdirectories
|
|
pdf_files = sorted(directory.rglob("*.pdf"))
|
|
return pdf_files
|
|
|
|
|
|
def get_converter():
|
|
|
|
pipeline_options = PdfPipelineOptions()
|
|
pipeline_options.do_ocr = False
|
|
pipeline_options.do_table_structure = True
|
|
pipeline_options.table_structure_options.do_cell_matching = True
|
|
|
|
converter = PdfDocumentConverter(
|
|
pipeline_options=pipeline_options,
|
|
pdf_backend=DoclingParseDocumentBackend,
|
|
)
|
|
|
|
return converter
|
|
|
|
|
|
def test_e2e_conversions():
|
|
|
|
pdf_paths = get_pdf_paths()
|
|
converter = get_converter()
|
|
|
|
for pdf_path in pdf_paths:
|
|
print(f"converting {pdf_path}")
|
|
|
|
doc_result: ConversionResult = converter.convert_single(pdf_path)
|
|
|
|
verify_conversion_result(
|
|
input_path=pdf_path, doc_result=doc_result, generate=GENERATE
|
|
)
|