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

Jump to bottom

fixed label filter #2978

Merged
merged 4 commits into from
Oct 29, 2024
Merged

fixed label filter #2978

Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
8467c21
added old error handling to comment fetching
hagen-danswer Oct 28, 2024
52a2a8f
Not
hagen-danswer Oct 29, 2024
ee47b95
properly escaped cql labels
hagen-danswer Oct 29, 2024
6ee602c
reverted changes
hagen-danswer Oct 29, 2024
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
35 changes: 23 additions & 12 deletions backend/danswer/connectors/confluence/connector.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,6 +50,10 @@
"restrictions.read.restrictions.group",
]

_NO_PARENT_OR_NO_PERMISSIONS_ERROR_STR = (
"No parent or not permitted to view content with id"
)


class ConfluenceConnector(LoadConnector, PollConnector, SlimConnector):
def __init__(
Expand Down Expand Up @@ -91,12 +95,13 @@ def __init__(
cql_page_query += f" and id='{page_id}'"

self.cql_page_query = cql_page_query
self.cql_label_filter = ""
self.cql_time_filter = ""

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

added proper escaping for label filtering

self.cql_label_filter = ""
if labels_to_skip:
labels_to_skip = list(set(labels_to_skip))
comma_separated_labels = ",".join(labels_to_skip)
self.cql_label_filter = f"&label not in ({comma_separated_labels})"
comma_separated_labels = ",".join(f"'{label}'" for label in labels_to_skip)
self.cql_label_filter = f" and label not in ({comma_separated_labels})"

def load_credentials(self, credentials: dict[str, Any]) -> dict[str, Any] | None:
# see https://github.com/atlassian-api/atlassian-python-api/blob/master/atlassian/rest_client.py
Expand All @@ -118,15 +123,21 @@ def _get_comment_string_for_page_id(self, page_id: str) -> str:
comment_cql += self.cql_label_filter

expand = ",".join(_COMMENT_EXPANSION_FIELDS)
for comments in self.confluence_client.paginated_cql_page_retrieval(
cql=comment_cql,
expand=expand,
):
for comment in comments:
comment_string += "\nComment:\n"
comment_string += extract_text_from_confluence_html(
confluence_client=self.confluence_client, confluence_object=comment
)
try:
for comments in self.confluence_client.paginated_cql_page_retrieval(
cql=comment_cql,
expand=expand,
):
for comment in comments:
comment_string += "\nComment:\n"
comment_string += extract_text_from_confluence_html(
confluence_client=self.confluence_client,
confluence_object=comment,
)
except Exception as e:
logger.exception("error fetching comments: \n")
if _NO_PARENT_OR_NO_PERMISSIONS_ERROR_STR not in str(e):
raise

return comment_string

Expand Down
Loading