mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 12:48:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat!: Docling v2 (#117)

Browse Source 
---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Maxim Lysak <mly@zurich.ibm.com>
Signed-off-by: Michele Dolfi <dol@zurich.ibm.com>
Signed-off-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
Co-authored-by: Maxim Lysak <mly@zurich.ibm.com>
Co-authored-by: Michele Dolfi <dol@zurich.ibm.com>
Co-authored-by: Panos Vagenas <35837085+vagenas@users.noreply.github.com>
This commit is contained in:
Christoph Auer
2024-10-16 21:02:03 +02:00
committed by GitHub
parent d504432c1e
commit 7d3be0edeb
144 changed files with 15180 additions and 3828 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
tests/test_options.py
View File

@@ -3,12 +3,10 @@ from pathlib import Path
import pytest
from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
from docling.datamodel.base_models import ConversionStatus
from docling.datamodel.base_models import ConversionStatus, InputFormat
from docling.datamodel.document import ConversionResult
from docling.datamodel.pipeline_options import PipelineOptions, TableFormerMode
from docling.document_converter import DocumentConverter
from .verify_utils import verify_conversion_result
from docling.datamodel.pipeline_options import PdfPipelineOptions, TableFormerMode
from docling.document_converter import DocumentConverter, PdfFormatOption
@pytest.fixture
@@ -19,15 +17,19 @@ def test_doc_path():
def get_converters_with_table_options():
for cell_matching in [True, False]:
for mode in [TableFormerMode.FAST, TableFormerMode.ACCURATE]:
pipeline_options = PipelineOptions()
pipeline_options = PdfPipelineOptions()
pipeline_options.do_ocr = False
pipeline_options.do_table_structure = True
pipeline_options.table_structure_options.do_cell_matching = cell_matching
pipeline_options.table_structure_options.mode = mode
converter = DocumentConverter(
pipeline_options=pipeline_options,
pdf_backend=DoclingParseDocumentBackend,
format_options={
InputFormat.PDF: PdfFormatOption(
pipeline_options=pipeline_options,
backend=DoclingParseDocumentBackend,
)
}
)
yield converter
@@ -37,6 +39,6 @@ def test_e2e_conversions(test_doc_path):
for converter in get_converters_with_table_options():
print(f"converting {test_doc_path}")
doc_result: ConversionResult = converter.convert_single(test_doc_path)
doc_result: ConversionResult = converter.convert(test_doc_path)
assert doc_result.status == ConversionStatus.SUCCESS