mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2026-07-29 15:24:54 +00:00
stumpylogandClaude Sonnet 5
0506dcad05
Adds two new functions to harness.py: - _current_git_ref(): Gets the current git short SHA - append_profiling_history(): Appends JSON line to profiling/results/history.jsonl This enables profiling numbers to persist across sessions/dates, with every run appended to an immutable timeline rather than overwriting per-stage snapshots. Also adds corresponding test to verify the function writes valid JSON lines. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
75 lines
2.3 KiB
Python
75 lines
2.3 KiB
Python
# profiling/test_harness_self_check.py
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from profiling.harness import append_profiling_history
|
|
from profiling.harness import require_postgres
|
|
from profiling.harness import run_profile
|
|
from profiling.seed import seed_permission_dataset
|
|
|
|
|
|
@pytest.mark.profiling
|
|
@pytest.mark.django_db
|
|
def test_seed_medium_scale_produces_expected_counts() -> None:
|
|
require_postgres()
|
|
data = seed_permission_dataset(scale="medium")
|
|
assert len(data.documents) == 20_000
|
|
assert len(data.tags) == 100
|
|
assert len(data.correspondents) == 300
|
|
assert len(data.document_types) == 50
|
|
assert len(data.storage_paths) == 20
|
|
|
|
from guardian.models import GroupObjectPermission
|
|
from guardian.models import UserObjectPermission
|
|
|
|
user_perm_count = UserObjectPermission.objects.count()
|
|
group_perm_count = GroupObjectPermission.objects.count()
|
|
# within 5% of the ratio-derived target -- exact counts depend on random
|
|
# sampling without replacement, see seed.py
|
|
assert 2_242 <= user_perm_count <= 2_478
|
|
assert 43_111 <= group_perm_count <= 47_649
|
|
|
|
|
|
@pytest.mark.profiling
|
|
@pytest.mark.django_db
|
|
def test_run_profile_reports_query_count_and_timing() -> None:
|
|
require_postgres()
|
|
|
|
def trivial() -> list[int]:
|
|
from documents.models import Document
|
|
|
|
return list(Document.objects.values_list("id", flat=True)[:1])
|
|
|
|
result = run_profile(trivial, repeat=3)
|
|
assert result.best_seconds >= 0
|
|
assert len(result.all_seconds) == 3
|
|
assert result.query_count >= 1
|
|
|
|
|
|
def test_append_profiling_history_writes_a_valid_json_line() -> None:
|
|
history_path = Path(__file__).parent / "results" / "history.jsonl"
|
|
before_lines = (
|
|
history_path.read_text().splitlines() if history_path.exists() else []
|
|
)
|
|
|
|
append_profiling_history(
|
|
stage="self-check",
|
|
scenario="test_append_profiling_history_writes_a_valid_json_line",
|
|
best_seconds=0.001,
|
|
query_count=0,
|
|
scale="medium",
|
|
code_ref="test-run",
|
|
)
|
|
|
|
after_lines = history_path.read_text().splitlines()
|
|
assert len(after_lines) == len(before_lines) + 1
|
|
entry = json.loads(after_lines[-1])
|
|
assert entry["stage"] == "self-check"
|
|
assert entry["code_ref"] == "test-run"
|
|
assert entry["scale"] == "medium"
|
|
assert "timestamp" in entry
|