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: skip temporary docx files (#2413)

Browse Source 
fix: CLI detects docx temporary files and breaks

Signed-off-by: Victor Moreli <victormoreli64@gmail.com>
This commit is contained in:
Victor Moreli
2025-10-10 04:39:26 -03:00
committed by GitHub
parent b5f7fef29b
commit ee5501320e
1 changed files with 18 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
docling/cli/main.py
View File

@@ -547,13 +547,25 @@ def convert( # noqa: C901
if local_path.exists() and local_path.is_dir():
for fmt in from_formats:
for ext in FormatToExtensions[fmt]:
input_doc_paths.extend(
list(local_path.glob(f"**/*.{ext}"))
for path in local_path.glob(f"**/*.{ext}"):
if path.name.startswith("~$") and ext == "docx":
_log.info(
f"Ignoring temporary Word file: {path}"
)
input_doc_paths.extend(
list(local_path.glob(f"**/*.{ext.upper()}"))
continue
input_doc_paths.append(path)
for path in local_path.glob(f"**/*.{ext.upper()}"):
if path.name.startswith("~$") and ext == "docx":
_log.info(
f"Ignoring temporary Word file: {path}"
)
continue
input_doc_paths.append(path)
elif local_path.exists():
if not local_path.name.startswith("~$") and ext == "docx":
_log.info(f"Ignoring temporary Word file: {path}")
continue
input_doc_paths.append(local_path)
else:
err_console.print(