from datetime import timedelta from django.utils import timezone from tracker.models import Site, Visitor, VisitSession, Event from tracker.services.geo import resolver as _geo from tracker.services.ingest import ingest_batch NOW = timezone.now() def _batch(events, vid="v1", sid="s1"): return {"visitor_id": vid, "session_id": sid, "context": { "referrer_domain": "google.com", "utm": {"utm_source": "google"}, "path": "/landing", "device_type": "PC", "os": "Windows", "browser": "Chrome", "language": "en-US", "screen": "1920x1080"}, "events": events} def _ev(i, name="page_view", **kw): d = dict(event_id=f"e{i}", event_name=name, occurred_at=NOW, path="/p", title="T", properties={}) d.update(kw) return d # 1. 首批建档 def test_first_batch_creates_visitor_session_events(db): site = Site.objects.create(name="s", domains=["a.com"]) r = ingest_batch(site, _batch([_ev(1), _ev(2)]), ip="114.114.114.114") assert (r["accepted"], r["duplicated"], r["rejected"]) == (2, 0, []) v = Visitor.objects.get(site=site, visitor_id="v1") assert v.first_referrer_domain == "google.com" and v.visit_count == 1 assert v.active_days == 1 and v.last_ip == "114.114.114.114" if _geo._searcher: # 地理断言仅在有真实 xdb 时执行，CI/fresh clone 不因缺库变红 assert v.country == "中国" and v.city == "南京市" # 114 DNS（江苏南京） assert Event.objects.filter(site=site).count() == 2 # 2. 重放幂等 + 不抬高会话聚合 def test_duplicate_events_never_inflate_aggregates(db): site = Site.objects.create(name="s", domains=["a.com"]) ingest_batch(site, _batch([_ev(1), _ev(2, "page_stay", properties={"active_ms": 3000, "path": "/p"})])) r = ingest_batch(site, _batch([_ev(1)])) # 重放 assert r["duplicated"] == 1 and Event.objects.count() == 2 sess = VisitSession.objects.get() assert sess.event_count == 2 and sess.stay_ms == 3000 # 重放没有重复加分 # 3. 新会话递增 visit_count（F 表达式） def test_new_session_increments_visit_count(db): site = Site.objects.create(name="s", domains=["a.com"]) ingest_batch(site, _batch([_ev(1)], sid="s1")) ingest_batch(site, _batch([_ev(2)], sid="s2")) v = Visitor.objects.get(visitor_id="v1") assert v.visit_count == 2 and VisitSession.objects.count() == 2 # 4. 服务端 30 分钟兜底切分（同 sid 间隔>30min 切出 s1#2，且同批后续事件复用同段） def test_server_backstop_splits_idle_gap(db): site = Site.objects.create(name="s", domains=["a.com"]) ingest_batch(site, _batch([_ev(1, occurred_at=NOW - timedelta(minutes=90))])) r = ingest_batch(site, _batch([_ev(2), _ev(3)])) # 两条同批 assert VisitSession.objects.count() == 2 # s1 与 s1#2，不会切成 3 段 assert r["accepted"] == 2 # 5. 拒绝事件带原因上报 def test_rejected_events_reported_with_reason(db): site = Site.objects.create(name="s", domains=["a.com"]) r = ingest_batch(site, _batch([_ev(1, event_name="bad"), _ev(2)])) assert r["accepted"] == 1 and r["rejected"][0]["reason"] == "event_name_not_allowed" # 6. page_stay 的 active_ms 累计进 stay_ms def test_stay_ms_accumulates(db): site = Site.objects.create(name="s", domains=["a.com"]) ingest_batch(site, _batch([ _ev(1), _ev(2, "page_stay", properties={"active_ms": 5000, "path": "/p"})])) ingest_batch(site, _batch([ _ev(3, occurred_at=NOW + timedelta(minutes=1)), _ev(4, "page_stay", properties={"active_ms": 7000, "path": "/p"}, occurred_at=NOW + timedelta(minutes=1))])) assert VisitSession.objects.get().stay_ms == 12000 # 7. 爬虫 UA 标记（访客+事件） def test_bot_ua_marked(db): site = Site.objects.create(name="s", domains=["a.com"]) ingest_batch(site, _batch([_ev(1)]), ip="66.249.66.1", ua="Mozilla/5.0 (compatible; Googlebot/2.1)") assert Visitor.objects.get().is_bot is True assert Event.objects.get().is_bot is True # 8. 超批拒绝 def test_batch_size_invalid(db): site = Site.objects.create(name="s", domains=["a.com"]) r = ingest_batch(site, _batch([_ev(i) for i in range(60)])) assert r["rejected"] == [{"reason": "batch_size_invalid"}] # 9. 同批重复 event_id：去重后只入一份，聚合不灌倍 def test_intra_batch_duplicate_event_id_deduped(db): site = Site.objects.create(name="s", domains=["a.com"]) evs = [_ev(1, "page_stay", properties={"active_ms": 1000, "path": "/p"}) for _ in range(3)] # 3 份同 id r = ingest_batch(site, _batch(evs)) assert (r["accepted"], r["duplicated"]) == (1, 2) sess = VisitSession.objects.get() assert sess.event_count == 1 and sess.stay_ms == 1000 # 10. 切分后同 sid 小间隔连发：空闲比较取会话族最大 ended_at，不再每批新开段 def test_split_then_small_gap_reuses_segment(db): site = Site.objects.create(name="s", domains=["a.com"]) ingest_batch(site, _batch([_ev(1, occurred_at=NOW - timedelta(minutes=90))])) ingest_batch(site, _batch([_ev(2)])) # 90min 间隔 → 切出 s1#2 ingest_batch(site, _batch([_ev(3, occurred_at=NOW + timedelta(minutes=1))])) ingest_batch(site, _batch([_ev(4, occurred_at=NOW + timedelta(minutes=2))])) assert VisitSession.objects.count() == 2 # 保持 s1 与 s1#2，不切 s1#3/s1#4 assert Visitor.objects.get(visitor_id="v1").visit_count == 2 # 11. invariant 4：乱序批次（后入更早发生）ended_at 不回退 def test_ended_at_never_regresses_on_out_of_order_batch(db): site = Site.objects.create(name="s", domains=["a.com"]) ingest_batch(site, _batch([_ev(1, occurred_at=NOW + timedelta(minutes=1))])) ingest_batch(site, _batch([_ev(2, occurred_at=NOW)])) sess = VisitSession.objects.get() assert abs((sess.ended_at - (NOW + timedelta(minutes=1))).total_seconds()) < 1 # 12. 首触持久：第二批换 referrer 不改首触字段 def test_first_touch_immutable_across_batches(db): site = Site.objects.create(name="s", domains=["a.com"]) ingest_batch(site, _batch([_ev(1)])) b = _batch([_ev(2)]) b["context"]["referrer_domain"] = "bing.com" ingest_batch(site, b) v = Visitor.objects.get(visitor_id="v1") assert v.first_referrer_domain == "google.com" assert v.first_utm == {"utm_source": "google"} # 13. payload 缺 visitor_id/session_id 提前拒绝 def test_missing_payload_fields_rejected(db): site = Site.objects.create(name="s", domains=["a.com"]) p = _batch([_ev(1)]) del p["visitor_id"] assert ingest_batch(site, p)["rejected"] == [{"reason": "invalid_payload"}] p = _batch([_ev(1)]) del p["session_id"] assert ingest_batch(site, p)["rejected"] == [{"reason": "invalid_payload"}] # 14. SDK context 的 timezone 落库 Visitor.timezone_name（Task16 联调发现：键名映射缺口） def test_context_timezone_persisted_to_visitor(db): site = Site.objects.create(name="s", domains=["a.com"]) b = _batch([_ev(1)]) b["context"]["timezone"] = "Asia/Shanghai" ingest_batch(site, b) assert Visitor.objects.get(visitor_id="v1").timezone_name == "Asia/Shanghai" # 15. 归因分类 best-effort：引擎抛异常不影响采集入库（first_touch/session_entry 双路） def test_attribution_failure_never_breaks_ingest(db, monkeypatch): from tracker.services import ingest as ingest_mod site = Site.objects.create(name="s", domains=["a.com"]) monkeypatch.setattr(ingest_mod, "classify", lambda **kw: (_ for _ in ()).throw(RuntimeError("boom"))) r = ingest_batch(site, _batch([_ev(1)])) assert r["accepted"] == 1 and Event.objects.count() == 1 assert Visitor.objects.count() == 1 and VisitSession.objects.count() == 1 # 16. 首触分类用本批第一条 page_view 的完整 referrer（搜索词可恢复），非 ctx 裸域名 def test_first_touch_classification_uses_full_pageview_referrer(db): from tracker.models import SourceClassification site = Site.objects.create(name="s", domains=["a.com"]) b = _batch([_ev(1, properties={"referrer": "https://m.baidu.com/s?wd=挖掘机"})]) b["context"]["utm"] = {} # 默认 fixture 带 utm_source=google，与百度矛盾 → conflict ingest_batch(site, b) ft = SourceClassification.objects.get(scope="first_touch") assert ft.channel == "natural_search" and ft.platform == "百度" assert ft.search_term == "挖掘机" and ft.resolution == "resolved" # 17. 扩展环境键快照：device_model 独立列 + env_extra 白名单（白名单外不入库） def test_extended_env_snapshot_persisted(db): site = Site.objects.create(name="s", domains=["a.com"]) b = _batch([_ev(1)]) b["context"].update({ "device_model": "Pixel 7", "device_pixel_ratio": 2.625, "viewport": "393x851", "orientation": "portrait-primary", "max_touch_points": 5, "device_memory": 8, "languages": "zh-CN,en", "color_scheme": "dark", "standalone": "0", "network_downlink": 10, "network_rtt": 50, "save_data": "0", "wechat_version": "8.0.49", "platform_version": "13.0.0", "architecture": "arm", "bitness": "64", "evil_key": "