Page Menu
Home
Software Heritage
Search
Configure Global Search
Log In
Files
F9696658
D6753.id24529.diff
No One
Temporary
Actions
View File
Edit File
Delete File
View Transforms
Subscribe
Mute Notifications
Award Token
Flag For Later
Size
1 KB
Subscribers
None
D6753.id24529.diff
View Options
diff --git a/swh/scheduler/backend.py b/swh/scheduler/backend.py
--- a/swh/scheduler/backend.py
+++ b/swh/scheduler/backend.py
@@ -261,6 +261,11 @@
select_cols = ListedOrigin.select_columns()
insert_cols, insert_meta = ListedOrigin.insert_columns_and_metavars()
+ deduplicated_origins = {
+ tuple(getattr(origin, k) for k in pk_cols): origin
+ for origin in listed_origins
+ }
+
upsert_cols = [col for col in insert_cols if col not in pk_cols]
upsert_set = ", ".join(f"{col} = EXCLUDED.{col}" for col in upsert_cols)
@@ -274,7 +279,7 @@
ret = psycopg2.extras.execute_values(
cur=cur,
sql=query,
- argslist=(attr.asdict(origin) for origin in listed_origins),
+ argslist=(attr.asdict(origin) for origin in deduplicated_origins.values()),
template=f"({', '.join(insert_meta)})",
page_size=1000,
fetch=True,
diff --git a/swh/scheduler/tests/test_scheduler.py b/swh/scheduler/tests/test_scheduler.py
--- a/swh/scheduler/tests/test_scheduler.py
+++ b/swh/scheduler/tests/test_scheduler.py
@@ -686,6 +686,15 @@
assert all(origin.first_seen == origin.last_seen for origin in ret)
+ def test_record_listed_origins_with_duplicate(self, swh_scheduler, listed_origins):
+ # the duplicates must be in the same page to raise the "on conflict error"
+ listed_origins.insert(0, listed_origins[0])
+
+ ret = swh_scheduler.record_listed_origins(listed_origins)
+
+ # without the duplicate
+ assert len(ret) == len(listed_origins) - 1
+
def test_record_listed_origins_upsert(self, swh_scheduler, listed_origins):
# First, insert `cutoff` origins
cutoff = 100
File Metadata
Details
Attached
Mime Type
text/plain
Expires
Sun, Aug 17, 8:54 PM (17 h, 38 m ago)
Storage Engine
blob
Storage Format
Raw Data
Storage Handle
3221433
Attached To
D6753: Ensure there is no duplicated origins in the insertion batches
Event Timeline
Log In to Comment