mirror of
https://github.com/docling-project/docling.git
synced 2025-06-27 05:20:05 +00:00
34c7c79858
* fix: Fixes and tests for StopIteration on .convert() Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * fix: Remove unnecessary case handling Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * fix: Other test fixes Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * improve handling of unsupported types - Introduced new explicit exception types instead of `RuntimeError` - Introduced new `ConversionStatus` value for unsupported formats - Tidied up converter member typing & removed asserts Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com> * robustify & simplify format option resolution Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com> * rename new status, populate ConversionResult errors Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com> --------- Signed-off-by: Christoph Auer <cau@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>
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/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
|
|
)
|