mirror of
https://github.com/docling-project/docling.git
synced 2025-06-27 05:20:05 +00:00

* Add DoclingParseV3 backend implementation Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Use docling-core with docling-parse types Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fixes and test updates Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fix streams Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fix streams Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Reset tests Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * update test cases Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * update test units Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Add back DoclingParse v1 backend, pipeline options Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Update locks Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * fix: update docling-core to 2.22.0 Update dependency library docling-core to latest release 2.22.0 Fix regression tests and ground truth files Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> * Ground-truth files updated Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Update tests, use TextCell.from_ocr property Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Text fixes, new test data Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Rename docling backend to v4 Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Test all backends, fixes Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Reset all tests to use docling-parse v1 for now Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * Fixes for DPv4 backend init, better test coverage Signed-off-by: Christoph Auer <cau@zurich.ibm.com> * test_input_doc use default backend Signed-off-by: Christoph Auer <cau@zurich.ibm.com> --------- Signed-off-by: Christoph Auer <cau@zurich.ibm.com> Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com> Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
58 lines
1.6 KiB
Python
58 lines
1.6 KiB
Python
import json
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
|
|
from docling.backend.docling_parse_v4_backend import DoclingParseV4DocumentBackend
|
|
from docling.datamodel.base_models import InputFormat
|
|
from docling.datamodel.pipeline_options import PdfPipelineOptions
|
|
from docling.document_converter import DocumentConverter, PdfFormatOption
|
|
|
|
|
|
@pytest.fixture
|
|
def test_doc_paths():
|
|
return [
|
|
Path("tests/data/html/wiki_duck.html"),
|
|
Path("tests/data/docx/word_sample.docx"),
|
|
Path("tests/data/docx/lorem_ipsum.docx"),
|
|
Path("tests/data/pptx/powerpoint_sample.pptx"),
|
|
Path("tests/data/2305.03393v1-pg9-img.png"),
|
|
Path("tests/data/pdf/2206.01062.pdf"),
|
|
]
|
|
|
|
|
|
def get_converter():
|
|
|
|
pipeline_options = PdfPipelineOptions()
|
|
pipeline_options.do_ocr = False
|
|
|
|
converter = DocumentConverter(
|
|
format_options={
|
|
InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options),
|
|
InputFormat.IMAGE: PdfFormatOption(
|
|
pipeline_options=pipeline_options,
|
|
),
|
|
}
|
|
)
|
|
|
|
return converter
|
|
|
|
|
|
def test_compare_legacy_output(test_doc_paths):
|
|
converter = get_converter()
|
|
|
|
res = converter.convert_all(test_doc_paths, raises_on_error=True)
|
|
|
|
for conv_res in res:
|
|
print(f"Results for {conv_res.input.file}")
|
|
print(
|
|
json.dumps(
|
|
conv_res.legacy_document.model_dump(
|
|
mode="json", by_alias=True, exclude_none=True
|
|
)
|
|
)
|
|
)
|
|
|
|
# assert res.legacy_output == res.legacy_output_transformed
|