Топология подтверждена перед удалением (docker-compose.prod.yml): tradein-backend (uvicorn app.main:app) — SCHEDULER_ENABLE=false; tradein-scraper (python -m app.scheduler_main) — SCHEDULER_ENABLE=true + USE_KIT_SCHEDULER=true. Kit-путь (_run_kit_scheduler → scraper_kit.orchestration.scheduler + product_handlers) самодостаточен: не импортирует ничего из app.services.scheduler.scheduler_loop или app.services.scrape_pipeline. Все НЕ-sweep джобы, которые kit-scheduler диспетчерит через build_product_handlers, идут напрямую в app.tasks.*/ app.services.* (либо lazy-импортят import_rosreestr_dkp/_execute_cian_backfill из scheduler.py) — мимо удаляемой legacy-машинерии. app/services/scheduler.py: 2098 → 418 строк. Удалено: scheduler_loop, get_due_schedules, reap_zombies, _claim_run, _defer_next_run_at, _spawn_tracked/ _drain_inflight/_inflight_tasks, все 27 trigger_*_run-функций, импорт app.services.scrape_pipeline, константы SCHEDULER_TICK_SEC/ZOMBIE_THRESHOLD_HOURS (достижимы были только через удалённый scheduler_loop-путь). Оставлено (живые импортёры вне удалённого): compute_next_run_at + has_running_run (admin.py), import_rosreestr_dkp + _execute_cian_backfill (lazy-импорты в product_handlers.py — job-тела kit-handler'ов). main.py: убран `from app.services.scheduler import scheduler_loop` + lifespan-блок запуска (`if settings.scheduler_enable: asyncio.create_task(scheduler_loop())`); прод-backend всегда шёл с SCHEDULER_ENABLE=false, так что это был мёртвый код. scheduler_main.py: убрана ship-dark развилка #2192 (USE_KIT_SCHEDULER=false → legacy scheduler_loop fallback) — _run_kit_scheduler() теперь безусловный путь. Поле settings.use_kit_scheduler оставлено в конфиге (Settings extra="ignore" защищает от startup-краха на leftover env var), но на ветвление не влияет. app.services.scrape_pipeline: 0 runtime-импортёров в app/+scripts/+packages/ после этого PR (только тесты, которые Part E удалит вместе с самим файлом) — подтверждено grep. scrape_pipeline.py не тронут (Part E). Тесты: удалены test_house_imv_backfill_scheduler.py (100% legacy-триггер, backfill_house_imv сервис покрыт в test_house_imv_backfill_browser_flag.py / test_backfill_wave2.py) и test_kit_registry_completeness.py (parity-инвариант против удалённого dispatch, дублирует test_scraper_kit_scheduler_parity.py). Точечно вырезаны "Scheduler wiring" секции (trigger_fn_exists/dispatch_branch_ wired/runs_in_executor) из ~10 файлов, тестирующих сами task-функции — сами task-тесты (SQL-shape, миграции, fake-db поведение) оставлены нетронутыми. test_scheduler.py: 825 → ~90 строк (остались только compute_next_run_at-тесты). test_scraper_kit_scheduler_parity.py: убрана golden-parity секция против удалённого scheduler_loop (SOURCE_TO_OLD_TRIGGER/_drive_old_one_tick/ test_routing_parity_per_source), остальное (claim/reap_zombies/dispatch/ registry-shape тесты kit-модуля) сохранено — источник этих инвариантов не app.services.scheduler, а сам scraper_kit.orchestration.scheduler. test_scheduler_main.py: 2 теста, патчившие app.services.scheduler.scheduler_loop, переведены на монкипатч sm._run_kit_scheduler (единственный путь после этого PR). test_sweep_imv_phase.py:171-371 (6 прямых импортов run_avito_city_sweep из scrape_pipeline) намеренно НЕ тронуты — Part E. Verify: полный pytest 3179 passed / 6 skipped / 1 known-unrelated fail (test_search_cache_hit, #2208, не связан с этим PR); ruff 0.7.4 чист на всех изменённых файлах; `python -c "import app.main; import app.scheduler_main"` OK.
285 lines
11 KiB
Python
285 lines
11 KiB
Python
"""Tests for the stale avito listing deactivation task (#759).
|
|
|
|
Static assertions (SQL shape, psycopg-v3 cast discipline) mirror the pattern established
|
|
in test_listing_source_snapshot.py. One behavioural test drives the counter logic via a
|
|
fake db without a live database.
|
|
"""
|
|
|
|
import inspect
|
|
import os
|
|
import re
|
|
from pathlib import Path
|
|
from typing import Any
|
|
|
|
import pytest
|
|
|
|
# Stub DATABASE_URL before any app import (same guard as test_listing_source_snapshot.py —
|
|
# these tests are static/fake-db, no live DB).
|
|
os.environ.setdefault("DATABASE_URL", "postgresql+psycopg://test:test@localhost:5432/test")
|
|
|
|
from app.tasks import deactivate_stale_avito as task_mod
|
|
|
|
_SQL_DIR = Path(__file__).resolve().parents[1] / "data" / "sql"
|
|
_MIGRATION_090 = _SQL_DIR / "090_scrape_schedules_seed_deactivate_stale_avito.sql"
|
|
|
|
_DEACTIVATE_SQL = str(task_mod._DEACTIVATE_SQL.text)
|
|
_TASK_SRC = inspect.getsource(task_mod.deactivate_stale_avito_listings)
|
|
_GENERIC_TASK_SRC = inspect.getsource(task_mod.deactivate_stale_listings)
|
|
|
|
|
|
# ── SQL shape ─────────────────────────────────────────────────────────────────
|
|
|
|
|
|
def test_sql_targets_only_avito_source() -> None:
|
|
"""Compat wrapper enforces source='avito' via listing_source param — cian/yandex not touched."""
|
|
# _DEACTIVATE_SQL is now the generic all-segments SQL using :listing_source bind param.
|
|
assert ":listing_source" in _DEACTIVATE_SQL
|
|
# The avito constraint is enforced by the compat wrapper passing listing_source="avito".
|
|
assert 'listing_source="avito"' in _TASK_SRC
|
|
|
|
|
|
def test_sql_only_deactivates_not_deletes() -> None:
|
|
"""Rows must be marked is_active=false, never DELETEd (history needed for #667)."""
|
|
assert "SET is_active = false" in _DEACTIVATE_SQL
|
|
assert "DELETE" not in _DEACTIVATE_SQL.upper()
|
|
|
|
|
|
def test_sql_guards_already_inactive_rows() -> None:
|
|
"""Filter AND is_active=true avoids redundant updates on rows already deactivated."""
|
|
assert "is_active = true" in _DEACTIVATE_SQL
|
|
|
|
|
|
def test_sql_uses_last_seen_at_threshold() -> None:
|
|
"""Threshold is last_seen_at < NOW() - interval, not any other column."""
|
|
assert "last_seen_at" in _DEACTIVATE_SQL
|
|
assert "NOW()" in _DEACTIVATE_SQL
|
|
|
|
|
|
def test_sql_uses_cast_interval_not_double_colon() -> None:
|
|
"""psycopg v3: bind param via CAST(:ttl_days || ' days' AS interval), never ::interval."""
|
|
assert "CAST(:ttl_days || ' days' AS interval)" in _DEACTIVATE_SQL
|
|
# No bind-param (:name) followed by ::type anywhere.
|
|
assert not re.search(r":\w+::", _DEACTIVATE_SQL)
|
|
|
|
|
|
def test_sql_ttl_param_named_ttl_days() -> None:
|
|
"""Bind param must be :ttl_days (wired from settings.avito_stale_ttl_days)."""
|
|
assert ":ttl_days" in _DEACTIVATE_SQL
|
|
|
|
|
|
# ── Settings wiring ───────────────────────────────────────────────────────────
|
|
|
|
|
|
def test_settings_has_avito_stale_ttl_days() -> None:
|
|
from app.core.config import settings
|
|
|
|
assert hasattr(settings, "avito_stale_ttl_days")
|
|
assert settings.avito_stale_ttl_days == 10 # default
|
|
|
|
|
|
def test_task_reads_ttl_from_settings() -> None:
|
|
"""Task must use settings.avito_stale_ttl_days, not a hardcoded literal."""
|
|
assert "settings.avito_stale_ttl_days" in _TASK_SRC
|
|
|
|
|
|
# ── Task function contract ────────────────────────────────────────────────────
|
|
|
|
|
|
def test_task_returns_deactivated_counter() -> None:
|
|
# counter logic lives in the generic deactivate_stale_listings function
|
|
assert '"deactivated"' in _GENERIC_TASK_SRC or "'deactivated'" in _GENERIC_TASK_SRC
|
|
|
|
|
|
def test_task_finalises_run() -> None:
|
|
# mark_done/mark_failed live in the generic deactivate_stale_listings function
|
|
assert "mark_done" in _GENERIC_TASK_SRC
|
|
assert "mark_failed" in _GENERIC_TASK_SRC
|
|
|
|
|
|
def test_task_commits_and_rollbacks_on_error() -> None:
|
|
# commit/rollback live in the generic deactivate_stale_listings function
|
|
assert "db.commit()" in _GENERIC_TASK_SRC
|
|
assert "db.rollback()" in _GENERIC_TASK_SRC
|
|
|
|
|
|
# ── Migration 090 ─────────────────────────────────────────────────────────────
|
|
|
|
|
|
def test_migration_090_exists() -> None:
|
|
assert _MIGRATION_090.is_file(), f"missing migration: {_MIGRATION_090}"
|
|
|
|
|
|
def test_migration_090_seeds_correct_source_and_window() -> None:
|
|
sql = _MIGRATION_090.read_text("utf-8")
|
|
assert "'deactivate_stale_avito'" in sql
|
|
# Window 06:00-07:00 UTC — after avito sweep (02:00-05:00).
|
|
assert re.search(r"\b6\b", sql), "window_start_hour 6 missing"
|
|
assert re.search(r"\b7\b", sql), "window_end_hour 7 missing"
|
|
|
|
|
|
def test_migration_090_is_idempotent() -> None:
|
|
sql = _MIGRATION_090.read_text("utf-8")
|
|
assert "ON CONFLICT (source) DO NOTHING" in sql
|
|
|
|
|
|
def test_migration_090_enabled_true() -> None:
|
|
sql = _MIGRATION_090.read_text("utf-8")
|
|
insert_block = sql.split("INSERT INTO scrape_schedules")[1]
|
|
# enabled=true (SAFE — pure internal DB UPDATE).
|
|
assert "true," in insert_block
|
|
|
|
|
|
def test_migration_090_is_transactional() -> None:
|
|
sql = _MIGRATION_090.read_text("utf-8")
|
|
assert "BEGIN;" in sql
|
|
assert "COMMIT;" in sql
|
|
|
|
|
|
def test_migration_090_no_psycopg_trap() -> None:
|
|
"""Migration is plain DDL/DML seed (no bind params), guard :x::type trap anyway."""
|
|
sql = _MIGRATION_090.read_text("utf-8")
|
|
assert not re.search(r":\w+::", sql)
|
|
|
|
|
|
# ── Behavioural test: counter logic via fake db ───────────────────────────────
|
|
|
|
|
|
class _FakeResult:
|
|
def __init__(self, rowcount: int) -> None:
|
|
self.rowcount = rowcount
|
|
|
|
|
|
class _FakeDB:
|
|
"""Minimal stand-in for SQLAlchemy Session."""
|
|
|
|
def __init__(self, rowcount: int) -> None:
|
|
self._rowcount = rowcount
|
|
self.executed: list[Any] = []
|
|
self.committed = False
|
|
self.rolled_back = False
|
|
|
|
def execute(self, stmt: Any, params: dict[str, Any] | None = None) -> _FakeResult:
|
|
self.executed.append((stmt, params))
|
|
return _FakeResult(self._rowcount)
|
|
|
|
def commit(self) -> None:
|
|
self.committed = True
|
|
|
|
def rollback(self) -> None:
|
|
self.rolled_back = True
|
|
|
|
|
|
def test_counter_logic_with_fake_db(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
"""deactivate_stale_avito_listings maps execute() rowcount → counters + marks done."""
|
|
marked: dict[str, Any] = {}
|
|
monkeypatch.setattr(
|
|
task_mod.runs_mod,
|
|
"mark_done",
|
|
lambda _db, run_id, counters: marked.update(run_id=run_id, counters=dict(counters)),
|
|
)
|
|
monkeypatch.setattr(task_mod.runs_mod, "mark_failed", lambda *a, **k: None)
|
|
|
|
db = _FakeDB(rowcount=137)
|
|
out = task_mod.deactivate_stale_avito_listings(db, run_id=42) # type: ignore[arg-type]
|
|
|
|
assert out == {"deactivated": 137}
|
|
assert db.committed is True
|
|
assert len(db.executed) == 1
|
|
# Bind params must contain ttl_days wired from settings.
|
|
_stmt, params = db.executed[0]
|
|
assert params is not None
|
|
assert "ttl_days" in params
|
|
assert params["ttl_days"] == 10 # default from settings
|
|
# run_id finalised via mark_done.
|
|
assert marked["run_id"] == 42
|
|
assert marked["counters"] == {"deactivated": 137}
|
|
|
|
|
|
def test_counter_logic_zero_rows(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
"""rowcount=0 → deactivated=0, still commits and marks done."""
|
|
marked: dict[str, Any] = {}
|
|
monkeypatch.setattr(
|
|
task_mod.runs_mod,
|
|
"mark_done",
|
|
lambda _db, run_id, counters: marked.update(run_id=run_id, counters=dict(counters)),
|
|
)
|
|
monkeypatch.setattr(task_mod.runs_mod, "mark_failed", lambda *a, **k: None)
|
|
|
|
db = _FakeDB(rowcount=0)
|
|
out = task_mod.deactivate_stale_avito_listings(db, run_id=1) # type: ignore[arg-type]
|
|
|
|
assert out == {"deactivated": 0}
|
|
assert db.committed is True
|
|
assert marked["counters"] == {"deactivated": 0}
|
|
|
|
|
|
def test_failure_path_rollback_and_mark_failed(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
"""On execute error: rollback + mark_failed + re-raise (no silent swallow)."""
|
|
failed: dict[str, Any] = {}
|
|
monkeypatch.setattr(task_mod.runs_mod, "mark_done", lambda *a, **k: None)
|
|
monkeypatch.setattr(
|
|
task_mod.runs_mod,
|
|
"mark_failed",
|
|
lambda _db, run_id, err, counters: failed.update(run_id=run_id, err=err),
|
|
)
|
|
|
|
class _BoomDB(_FakeDB):
|
|
def execute(self, stmt: Any, params: dict[str, Any] | None = None) -> _FakeResult:
|
|
raise RuntimeError("db exploded")
|
|
|
|
db = _BoomDB(rowcount=0)
|
|
with pytest.raises(RuntimeError, match="db exploded"):
|
|
task_mod.deactivate_stale_avito_listings(db, run_id=7) # type: ignore[arg-type]
|
|
|
|
assert db.rolled_back is True
|
|
assert failed["run_id"] == 7
|
|
|
|
|
|
# ── Migration 100: prod hot-fix — flip enabled=false → true ──────────────────
|
|
|
|
_MIGRATION_100 = _SQL_DIR / "100_enable_deactivate_stale_avito.sql"
|
|
|
|
|
|
def test_migration_100_exists() -> None:
|
|
"""Prod hot-fix migration must be present so deploy auto-applies it."""
|
|
assert _MIGRATION_100.is_file(), f"missing migration: {_MIGRATION_100}"
|
|
|
|
|
|
def test_migration_100_updates_correct_source() -> None:
|
|
sql = _MIGRATION_100.read_text("utf-8")
|
|
assert "'deactivate_stale_avito'" in sql
|
|
|
|
|
|
def test_migration_100_sets_enabled_true() -> None:
|
|
sql = _MIGRATION_100.read_text("utf-8")
|
|
# UPDATE … SET enabled = true
|
|
assert re.search(
|
|
r"enabled\s*=\s*true", sql, re.IGNORECASE
|
|
), "migration 100 must SET enabled = true"
|
|
|
|
|
|
def test_migration_100_is_idempotent() -> None:
|
|
"""WHERE enabled = false ensures re-running after fix → 0 rows matched."""
|
|
sql = _MIGRATION_100.read_text("utf-8")
|
|
assert re.search(
|
|
r"enabled\s*=\s*false", sql, re.IGNORECASE
|
|
), "migration 100 must guard with AND enabled = false for idempotency"
|
|
|
|
|
|
def test_migration_100_is_transactional() -> None:
|
|
sql = _MIGRATION_100.read_text("utf-8")
|
|
assert "BEGIN;" in sql
|
|
assert "COMMIT;" in sql
|
|
|
|
|
|
def test_migration_100_no_psycopg_trap() -> None:
|
|
"""Plain DML — no bind params — guard :x::type trap anyway."""
|
|
sql = _MIGRATION_100.read_text("utf-8")
|
|
assert not re.search(r":\w+::", sql)
|
|
|
|
|
|
def test_migration_100_also_resets_next_run_at() -> None:
|
|
"""next_run_at = NOW() ensures the scheduler fires on the next tick."""
|
|
sql = _MIGRATION_100.read_text("utf-8")
|
|
assert "next_run_at" in sql
|
|
assert "NOW()" in sql
|