[Community][minor]: Updating source path, and file path for SharePoint loader in PebbloSafeLoader (#25592)

- **Description:** Updating source path and file path in Pebblo safe
loader for SharePoint apps during loading
- **Issue:** NA
- **Dependencies:** NA
- **Tests:** NA
- **Docs** NA

---------

Co-authored-by: dristy.cd <dristy@clouddefense.io>
This commit is contained in:
Dristy Srivastava
2024-08-26 18:08:40 +05:30
committed by GitHub
parent 745d1c2b8d
commit fbb4761199
2 changed files with 33 additions and 12 deletions

View File

@@ -252,11 +252,16 @@ class PebbloSafeLoader(BaseLoader):
"""Add Pebblo specific metadata to documents."""
for doc in self.docs_with_id:
doc_metadata = doc.metadata
doc_metadata["full_path"] = get_full_path(
doc_metadata.get(
"full_path", doc_metadata.get("source", self.source_path)
if self.loader.__class__.__name__ == "SharePointLoader":
doc_metadata["full_path"] = get_full_path(
doc_metadata.get("source", self.source_path)
)
else:
doc_metadata["full_path"] = get_full_path(
doc_metadata.get(
"full_path", doc_metadata.get("source", self.source_path)
)
)
)
doc_metadata["pb_checksum"] = classified_docs.get(doc.pb_id, {}).get(
"pb_checksum", None
)