Skip to content

Commit a161462

Browse files
authored
Indexing bug (#888)
1 parent ad5b5df commit a161462

File tree

2 files changed

+7
-0
lines changed

2 files changed

+7
-0
lines changed

backend/python/app/services/messaging/kafka/handlers/record.py

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -24,6 +24,7 @@
2424
# from app.connectors.sources.google.common.arango_service import ArangoService
2525
from app.services.scheduler.interface.scheduler import Scheduler
2626
from app.services.scheduler.scheduler_factory import SchedulerFactory
27+
from app.utils.mimetype_to_extension import get_extension_from_mimetype
2728
from app.utils.redis_util import build_redis_url
2829

2930

@@ -162,6 +163,11 @@ async def process_event(self, event_type: str, payload: dict) -> bool:
162163
if record_name and "." in record_name:
163164
extension = payload["recordName"].split(".")[-1]
164165

166+
if (extension is None or extension == "unknown") and mime_type is not None and mime_type != "unknown":
167+
derived_extension = get_extension_from_mimetype(mime_type)
168+
if derived_extension:
169+
extension = derived_extension
170+
165171
self.logger.info("🚀 Checking for mime_type")
166172
self.logger.info("🚀 mime_type: %s", mime_type)
167173
self.logger.info("🚀 extension: %s", extension)

backend/python/app/utils/mimetype_to_extension.py

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -44,6 +44,7 @@
4444
"application/csv": "csv",
4545
"text/markdown": "md",
4646
"text/mdx": "mdx",
47+
"text/gmail_content": "html",
4748
}
4849

4950

0 commit comments

Comments
 (0)