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

fix(html): fix HTML parsed heading level (#1244)

Browse Source 
Signed-off-by: Panos Vagenas <pva@zurich.ibm.com>
This commit is contained in:
Panos Vagenas
2025-03-26 10:30:23 +01:00
committed by GitHub
parent 9eb1686f93
commit 85c4df887b
13 changed files with 68 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
tests/test_backend_html.py
View File

@@ -32,16 +32,16 @@ def test_heading_levels():
)
doc = backend.convert()
found_lvl_2 = found_lvl_3 = False
found_lvl_1 = found_lvl_2 = False
for item, _ in doc.iterate_items():
if isinstance(item, SectionHeaderItem):
if item.text == "Etymology":
found_lvl_1 = True
assert item.level == 1
elif item.text == "Feeding":
found_lvl_2 = True
assert item.level == 2
elif item.text == "Feeding":
found_lvl_3 = True
assert item.level == 3
assert found_lvl_2 and found_lvl_3
assert found_lvl_1 and found_lvl_2
@pytest.mark.skip(