Skip to content

[PULP-2474] Optimize Maven repository metrics counts #541

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

Merged
dkliban merged 1 commit into from
Oct 14, 2026
Merged

[PULP-2474] Optimize Maven repository metrics counts #541

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
40 changes: 28 additions & 12 deletions pulp_maven/app/catalog.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,17 @@

from collections import defaultdict

from django.db.models import CharField, FilteredRelation, Func, Max, OuterRef, Q, Subquery, Value
from django.db.models import (
Aggregate,
CharField,
FilteredRelation,
Func,
Max,
OuterRef,
Q,
Subquery,
Value,
)
from django.db.models.functions import Coalesce, Collate

from pulpcore.plugin.models import RepositoryContent
Expand Down Expand Up @@ -328,6 +338,13 @@ def assemble_package_index(content_qs, ga_rows, repository_version):
return result


class CountDistinctTuple(Aggregate):
"""Count distinct tuples using PostgreSQL's row-valued DISTINCT syntax."""

function = "COUNT"
template = "%(function)s(DISTINCT (%(expressions)s))"


def repository_metrics(content_qs):
"""Distinct package / logical-version / build counts for MavenPackage.

Expand All @@ -338,14 +355,13 @@ def repository_metrics(content_qs):
after rebuild-suffix strip
* ``build_count``: distinct ``(group_id, artifact_id, version)`` (full GAV)
"""
content_qs = content_qs.order_by()
return {
"package_count": content_qs.values("group_id", "artifact_id").distinct().count(),
"version_count": (
content_qs.annotate(_base_version=base_version_annotation())
.values("group_id", "artifact_id", "_base_version")
.distinct()
.count()
),
"build_count": content_qs.values("group_id", "artifact_id", "version").distinct().count(),
}
counts = (
content_qs.order_by()
.annotate(_base_version=base_version_annotation())
.aggregate(
package_count=CountDistinctTuple("group_id", "artifact_id"),
version_count=CountDistinctTuple("group_id", "artifact_id", "_base_version"),
build_count=CountDistinctTuple("group_id", "artifact_id", "version"),
)
)
return counts
Loading