mirrors/docling
1
0
Fork 0
mirror of https://github.com/DS4SD/docling.git synced 2025-12-08 20:58:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: fix HTML table parser and JATS backend bugs (#1948)

Browse Source 
Fix a bug in parsing HTML tables in HTML backend.
Fix a bug in test file that prevented JATS backend tests.
Ensure that the JATS backend creates headings with the right level.
Remove unnecessary data files for testing JATS backend.

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
This commit is contained in:
Cesar Berrospi Ramis
2025-07-16 10:49:24 +02:00
committed by GitHub
parent d6d2dbe2f9
commit e1e3053695
27 changed files with 29206 additions and 14362 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
tests/test_backend_jats.py
View File

@@ -14,9 +14,9 @@ from .verify_utils import verify_document, verify_export
GENERATE = GEN_TEST_DATA
def get_pubmed_paths():
directory = Path(os.path.dirname(__file__) + "/data/pubmed/")
xml_files = sorted(directory.rglob("*.xml"))
def get_jats_paths():
directory = Path(os.path.dirname(__file__) + "/data/jats/")
xml_files = sorted(directory.rglob("*.nxml"))
return xml_files
@@ -25,20 +25,20 @@ def get_converter():
return converter
def test_e2e_pubmed_conversions(use_stream=False):
pubmed_paths = get_pubmed_paths()
def test_e2e_jats_conversions(use_stream=False):
jats_paths = get_jats_paths()
converter = get_converter()
for pubmed_path in pubmed_paths:
for jats_path in jats_paths:
gt_path = (
pubmed_path.parent.parent / "groundtruth" / "docling_v2" / pubmed_path.name
jats_path.parent.parent / "groundtruth" / "docling_v2" / jats_path.name
)
if use_stream:
buf = BytesIO(pubmed_path.open("rb").read())
stream = DocumentStream(name=pubmed_path.name, stream=buf)
buf = BytesIO(jats_path.open("rb").read())
stream = DocumentStream(name=jats_path.name, stream=buf)
conv_result: ConversionResult = converter.convert(stream)
else:
conv_result: ConversionResult = converter.convert(pubmed_path)
conv_result: ConversionResult = converter.convert(jats_path)
doc: DoclingDocument = conv_result.document
pred_md: str = doc.export_to_markdown()
@@ -54,9 +54,9 @@ def test_e2e_pubmed_conversions(use_stream=False):
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_jats_conversions_stream():
test_e2e_jats_conversions(use_stream=True)
def test_e2e_pubmed_conversions_no_stream():
test_e2e_pubmed_conversions(use_stream=False)
def test_e2e_jats_conversions_no_stream():
test_e2e_jats_conversions(use_stream=False)