浅念
137 lines
6.7 KiB
Python
137 lines
6.7 KiB
Python
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"}]
|