docling/tests/test_e2e_conversion.py
Peter W. J. Staar f542460af3
fix: fix duplicate title and heading + add e2e tests for html and docx (#186)
* add real e2e tests for html and docx

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* updated the output of itxt

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* reformatted the text

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* fixed the tests

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* fixed the tests (2)

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* fixed the examples (1)

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* fixed the output of the test

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* updated the tests, moved the ground-truth

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* moved the ground-truth data

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* fixed the html tests

Signed-off-by: Peter Staar <taa@zurich.ibm.com>

* restructure title fix (#187)

Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>

---------

Signed-off-by: Peter Staar <taa@zurich.ibm.com>
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
Co-authored-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
2024-10-30 13:14:56 +01:00

63 lines
1.7 KiB
Python

from pathlib import Path
import yaml
from docling_core.types.doc import DoclingDocument
from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
from docling.datamodel.base_models import InputFormat
from docling.datamodel.document import ConversionResult
from docling.datamodel.pipeline_options import PdfPipelineOptions
from docling.document_converter import DocumentConverter, PdfFormatOption
from .verify_utils import verify_conversion_result_v1, verify_conversion_result_v2
GENERATE_V1 = False
GENERATE_V2 = 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 = DocumentConverter(
format_options={
InputFormat.PDF: PdfFormatOption(
pipeline_options=pipeline_options, backend=DoclingParseDocumentBackend
)
}
)
return converter
def test_e2e_pdfs_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(pdf_path)
verify_conversion_result_v1(
input_path=pdf_path, doc_result=doc_result, generate=GENERATE_V1
)
verify_conversion_result_v2(
input_path=pdf_path, doc_result=doc_result, generate=GENERATE_V2
)