Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Change Data Loader Namespace #6568

Merged
merged 1 commit into from
Jun 22, 2023
Merged

Change Data Loader Namespace #6568

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions langchain/document_loaders/docugami.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -243,7 +243,7 @@ def _metadata_for_project(self, project: Dict) -> Dict:
artifact_url = artifact.get("url")
artifact_doc = artifact.get("document")

if artifact_name == f"{project_id}.xml" and artifact_url and artifact_doc:
if artifact_name == "report-values.xml" and artifact_url and artifact_doc:
doc_id = artifact_doc["id"]
metadata: Dict = {}

Expand All @@ -266,11 +266,11 @@ def _metadata_for_project(self, project: Dict) -> Dict:
artifact_tree = etree.parse(io.BytesIO(response.content))
artifact_root = artifact_tree.getroot()
ns = artifact_root.nsmap
entries = artifact_root.xpath("//wp:Entry", namespaces=ns)
entries = artifact_root.xpath("//pr:Entry", namespaces=ns)
for entry in entries:
heading = entry.xpath("./wp:Heading", namespaces=ns)[0].text
heading = entry.xpath("./pr:Heading", namespaces=ns)[0].text
value = " ".join(
entry.xpath("./wp:Value", namespaces=ns)[0].itertext()
entry.xpath("./pr:Value", namespaces=ns)[0].itertext()
).strip()
metadata[heading] = value
per_file_metadata[doc_id] = metadata
Expand Down