
fix: Support for RTL programmatic documents fix(parser): detect and handle rotated pages fix(parser): fix bug causing duplicated text fix(formula): improve stopping criteria chore: update lock file fix: temporary constrain beautifulsoup * switch to code formula model v1.0.1 and new test pdf Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> * switch to code formula model v1.0.1 and new test pdf Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> * cleaned up the data folder in the tests Signed-off-by: Peter Staar <taa@zurich.ibm.com> * switch to code formula model v1.0.1 and new test pdf Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> * added three test-files for right-to-left Signed-off-by: Peter Staar <taa@zurich.ibm.com> * fix black Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> * added new gt for test_e2e_conversion Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> * added new gt for test_e2e_conversion Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> * Add code to expose text direction of cell Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * new test file Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> * update lock Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * fix mypy reports Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * fix example filepaths Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * add test data results Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * pin wheel of latest docling-parse release Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * use latest docling-core Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * remove debugging code Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * fix path to files in example Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> * Revert unwanted RTL additions Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fix test data paths in examples Signed-off-by: Christoph Auer <cau@zurich.ibm.com> --------- Signed-off-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> Signed-off-by: Peter Staar <taa@zurich.ibm.com> Signed-off-by: Christoph Auer <cau@zurich.ibm.com> Signed-off-by: Michele Dolfi <dol@zurich.ibm.com> Co-authored-by: Matteo-Omenetti <Matteo.Omenetti1@ibm.com> Co-authored-by: Peter Staar <taa@zurich.ibm.com> Co-authored-by: Christoph Auer <cau@zurich.ibm.com>
70 lines
1.9 KiB
Python
70 lines
1.9 KiB
Python
from io import BytesIO
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
|
|
from docling.datamodel.base_models import DocumentStream, InputFormat
|
|
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 = False
|
|
|
|
|
|
def get_pdf_path():
|
|
|
|
pdf_path = Path("./tests/data/pdf/2305.03393v1-pg9.pdf")
|
|
return pdf_path
|
|
|
|
|
|
@pytest.fixture
|
|
def 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_convert_path(converter: DocumentConverter):
|
|
|
|
pdf_path = get_pdf_path()
|
|
print(f"converting {pdf_path}")
|
|
|
|
doc_result = converter.convert(pdf_path)
|
|
verify_conversion_result_v1(
|
|
input_path=pdf_path, doc_result=doc_result, generate=GENERATE
|
|
)
|
|
verify_conversion_result_v2(
|
|
input_path=pdf_path, doc_result=doc_result, generate=GENERATE
|
|
)
|
|
|
|
|
|
def test_convert_stream(converter: DocumentConverter):
|
|
|
|
pdf_path = get_pdf_path()
|
|
print(f"converting {pdf_path}")
|
|
|
|
buf = BytesIO(pdf_path.open("rb").read())
|
|
stream = DocumentStream(name=pdf_path.name, stream=buf)
|
|
|
|
doc_result = converter.convert(stream)
|
|
verify_conversion_result_v1(
|
|
input_path=pdf_path, doc_result=doc_result, generate=GENERATE
|
|
)
|
|
verify_conversion_result_v2(
|
|
input_path=pdf_path, doc_result=doc_result, generate=GENERATE
|
|
)
|