
* Support tableformer model choice Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Update datamodel structure Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Update docs Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Cleanup Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Add test unit for table options Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Ensure import backwards-compatibility for PipelineOptions Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Update README Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Adjust parameters on custom_convert Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com> * Update Dockerfile Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com> --------- Signed-off-by: Christoph Auer <cau@zurich.ibm.com> Signed-off-by: Christoph Auer <60343111+cau-git@users.noreply.github.com>
51 lines
1.3 KiB
Python
51 lines
1.3 KiB
Python
from pathlib import Path
|
|
|
|
from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
|
|
from docling.datamodel.document import ConversionResult
|
|
from docling.datamodel.pipeline_options import PipelineOptions
|
|
from docling.document_converter import DocumentConverter
|
|
|
|
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 = PipelineOptions()
|
|
pipeline_options.do_ocr = False
|
|
pipeline_options.do_table_structure = True
|
|
pipeline_options.table_structure_options.do_cell_matching = True
|
|
|
|
converter = DocumentConverter(
|
|
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
|
|
)
|