Skip to content

[ENG-11883] bad file counts #11846

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

Draft
aaxelb wants to merge 1 commit into
base: develop
Choose a base branch
from
+43 −11
Draft

[ENG-11883] bad file counts #11846

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
54 changes: 43 additions & 11 deletions osf/metrics/reporters/osfstorage_file_count.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,11 @@
from django.db.models import Q
import logging

from osf.models import AbstractNode, Preprint
from osf.models import (
AbstractNode,
Preprint,
SpamStatus,
)
from osf.metrics.daily_reports import DailyOsfstorageFileCountReport
from osf.metrics.utils import cycle_coverage_date
from ._base import DailyReporter
Expand All @@ -13,32 +17,60 @@

class OsfstorageFileCountReporter(DailyReporter):

def report(self, date):
def report(self, report_date):
from addons.osfstorage.models import OsfStorageFile

file_qs = OsfStorageFile.objects
file_qs = (
OsfStorageFile.objects
.filter(created__date__lte=report_date)
.exclude(deleted__date__lte=report_date)
)
abstract_node_content_type = ContentType.objects.get_for_model(AbstractNode)
preprint_content_type = ContentType.objects.get_for_model(Preprint)
node_ids = (
AbstractNode.objects
.exclude(spam_status=SpamStatus.SPAM)
.values('id')
)
preprint_ids = (
Preprint.objects
.exclude(spam_status=SpamStatus.SPAM)
.values('id')
)

total_query = Q(
target_object_id__in=node_ids,
target_content_type=abstract_node_content_type,
) | Q(
target_object_id__in=preprint_ids,
target_content_type=preprint_content_type,
)

public_query = Q(
target_object_id__in=AbstractNode.objects.filter(is_public=True).values('id'),
target_content_type__in=[abstract_node_content_type, preprint_content_type],
target_object_id__in=node_ids.filter(is_public=True),
target_content_type=abstract_node_content_type,
) | Q(
target_object_id__in=preprint_ids.filter(is_public=True),
target_content_type=preprint_content_type,
)

private_query = Q(
target_object_id__in=AbstractNode.objects.filter(is_public=False).values('id'),
target_content_type__in=[abstract_node_content_type, preprint_content_type],
target_object_id__in=node_ids.filter(is_public=False),
target_content_type=abstract_node_content_type,
) | Q(
target_object_id__in=preprint_ids.filter(is_public=False),
target_content_type=preprint_content_type,
)

daily_query = Q(created__date=date)
daily_query = Q(created__date=report_date)

yield DailyOsfstorageFileCountReport(
cycle_coverage=cycle_coverage_date(date),
cycle_coverage=cycle_coverage_date(report_date),
files=dict(
total=file_qs.count(),
total=file_qs.filter(total_query).count(),
public=file_qs.filter(public_query).count(),
private=file_qs.filter(private_query).count(),
total_daily=file_qs.filter(daily_query).count(),
total_daily=file_qs.filter(total_query & daily_query).count(),
public_daily=file_qs.filter(public_query & daily_query).count(),
private_daily=file_qs.filter(private_query & daily_query).count(),
),
Expand Down