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

fix(inc984): scrub the correct bucket for sentry.user.ip #6692

Merged
merged 1 commit into from
Dec 19, 2024
Merged

fix(inc984): scrub the correct bucket for sentry.user.ip #6692

Show file tree
Hide file tree
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
2 changes: 1 addition & 1 deletion snuba/manual_jobs/scrub_ips_from_eap_spans.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ def _get_query(self, cluster_name: str | None) -> str:
on_cluster = f"ON CLUSTER '{cluster_name}'" if cluster_name else ""
return f"""ALTER TABLE eap_spans_2_local
{on_cluster}
UPDATE `attr_str_1` = mapApply((k, v) -> (k, if(k = 'user.ip', 'scrubbed', v)), `attr_str_1`)
UPDATE `attr_str_14` = mapApply((k, v) -> (k, if(k = 'sentry.user.ip', 'scrubbed', v)), `attr_str_14`)
WHERE organization_id IN [{organization_ids}]
AND _sort_timestamp >= toDateTime('{start_datetime}')
AND _sort_timestamp < toDateTime('{end_datetime}')"""
Expand Down
14 changes: 9 additions & 5 deletions tests/manual_jobs/test_scrub_ips_from_eap_spans.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,7 +111,7 @@ def test_generate_query() -> None:
job._get_query(None)
== """ALTER TABLE eap_spans_2_local

UPDATE `attr_str_1` = mapApply((k, v) -> (k, if(k = 'user.ip', 'scrubbed', v)), `attr_str_1`)
UPDATE `attr_str_14` = mapApply((k, v) -> (k, if(k = 'sentry.user.ip', 'scrubbed', v)), `attr_str_14`)
WHERE organization_id IN [1,3,5,6]
AND _sort_timestamp >= toDateTime('2024-12-01T00:00:00')
AND _sort_timestamp < toDateTime('2024-12-10T00:00:00')"""
Expand Down Expand Up @@ -175,6 +175,7 @@ def _gen_message(
"transaction.method": "POST",
"transaction.op": "http.server",
"user": "ip:127.0.0.1",
"user.ip": _USER_IP,
},
"span_id": "123456781234567D",
"tags": {
Expand All @@ -185,7 +186,6 @@ def _gen_message(
"relay_protocol_version": "3",
"relay_use_post_or_schedule": "True",
"relay_use_post_or_schedule_rejected": "version",
"user.ip": _USER_IP,
"spans_over_limit": "False",
"server_name": "blah",
"color": random.choice(["red", "green", "blue"]),
Expand Down Expand Up @@ -219,12 +219,16 @@ def _generate_request(
)
),
columns=[
Column(key=AttributeKey(type=AttributeKey.TYPE_STRING, name="user.ip"))
Column(
key=AttributeKey(type=AttributeKey.TYPE_STRING, name="sentry.user.ip")
)
],
order_by=[
TraceItemTableRequest.OrderBy(
column=Column(
key=AttributeKey(type=AttributeKey.TYPE_STRING, name="user.ip")
key=AttributeKey(
type=AttributeKey.TYPE_STRING, name="sentry.user.ip"
)
)
)
],
Expand All @@ -235,7 +239,7 @@ def _generate_expected_response(ip: str) -> TraceItemTableResponse:
return TraceItemTableResponse(
column_values=[
TraceItemColumnValues(
attribute_name="user.ip",
attribute_name="sentry.user.ip",
results=[AttributeValue(val_str=ip) for _ in range(20)],
)
],
Expand Down
Loading