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: support escaped characters in markdown backend (#2304)

Browse Source 
fix: improve markdown backend to support input documents with escaped characters

Signed-off-by: Lucas Morin <lucas.morin222@gmail.com>
This commit is contained in:
Lucas Morin
2025-09-23 18:00:16 +02:00
committed by GitHub
parent d599177547
commit 9d67bb9ed6
7 changed files with 772 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
tests/test_backend_markdown.py
View File

@@ -26,10 +26,12 @@ def test_convert_valid():
assert len(relevant_paths) > 0
yaml_filter = ["inline_and_formatting", "mixed_without_h1"]
json_filter = ["escaped_characters"]
for in_path in relevant_paths:
md_gt_path = root_path / "groundtruth" / "docling_v2" / f"{in_path.name}.md"
yaml_gt_path = root_path / "groundtruth" / "docling_v2" / f"{in_path.name}.yaml"
json_gt_path = root_path / "groundtruth" / "docling_v2" / f"{in_path.name}.json"
in_doc = InputDocument(
path_or_stream=in_path,
@@ -45,6 +47,9 @@ def test_convert_valid():
act_doc = backend.convert()
act_data = act_doc.export_to_markdown()
if in_path.stem in json_filter:
assert verify_document(act_doc, json_gt_path, GENERATE), "export to json"
if GEN_TEST_DATA:
with open(md_gt_path, mode="w", encoding="utf-8") as f:
f.write(f"{act_data}\n")