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>
63 lines
1.9 KiB
Python
63 lines
1.9 KiB
Python
import os
|
|
from io import BytesIO
|
|
from pathlib import Path
|
|
|
|
from docling_core.types.doc import DoclingDocument
|
|
|
|
from docling.datamodel.base_models import DocumentStream, InputFormat
|
|
from docling.datamodel.document import ConversionResult
|
|
from docling.document_converter import DocumentConverter
|
|
|
|
from .test_data_gen_flag import GEN_TEST_DATA
|
|
from .verify_utils import verify_document, verify_export
|
|
|
|
GENERATE = GEN_TEST_DATA
|
|
|
|
|
|
def get_pubmed_paths():
|
|
directory = Path(os.path.dirname(__file__) + f"/data/pubmed/")
|
|
xml_files = sorted(directory.rglob("*.xml"))
|
|
return xml_files
|
|
|
|
|
|
def get_converter():
|
|
converter = DocumentConverter(allowed_formats=[InputFormat.XML_JATS])
|
|
return converter
|
|
|
|
|
|
def test_e2e_pubmed_conversions(use_stream=False):
|
|
pubmed_paths = get_pubmed_paths()
|
|
converter = get_converter()
|
|
|
|
for pubmed_path in pubmed_paths:
|
|
gt_path = (
|
|
pubmed_path.parent.parent / "groundtruth" / "docling_v2" / pubmed_path.name
|
|
)
|
|
if use_stream:
|
|
buf = BytesIO(pubmed_path.open("rb").read())
|
|
stream = DocumentStream(name=pubmed_path.name, stream=buf)
|
|
conv_result: ConversionResult = converter.convert(stream)
|
|
else:
|
|
conv_result: ConversionResult = converter.convert(pubmed_path)
|
|
doc: DoclingDocument = conv_result.document
|
|
|
|
pred_md: str = doc.export_to_markdown()
|
|
assert verify_export(pred_md, str(gt_path) + ".md"), "export to md"
|
|
|
|
pred_itxt: str = doc._export_to_indented_text(
|
|
max_text_len=70, explicit_tables=False
|
|
)
|
|
assert verify_export(
|
|
pred_itxt, str(gt_path) + ".itxt"
|
|
), "export to indented-text"
|
|
|
|
assert verify_document(doc, str(gt_path) + ".json", GENERATE), "export to json"
|
|
|
|
|
|
def test_e2e_pubmed_conversions_stream():
|
|
test_e2e_pubmed_conversions(use_stream=True)
|
|
|
|
|
|
def test_e2e_pubmed_conversions_no_stream():
|
|
test_e2e_pubmed_conversions(use_stream=False)
|