docling/tests/test_backend_jats.py
Christoph Auer 3960b199d6
feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905)
* 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>
2025-03-18 10:38:19 +01:00

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)