fangke/server/tracker/tests/test_attribution.py

"""来源归因规则引擎（tracker/services/attribution.classify）。

纯函数用例（无 DB）+ 重算命令/入库集成为带 db 标记的独立用例。
诚实状态语义：resolved=观察到 referrer 证据；label_only=仅 UTM 自述；
conflict=两证据矛盾并列；unknown=直接访问不猜测。
"""
import pytest
from django.core.management import call_command
from django.utils import timezone

from tracker.models import Site, SourceClassification, VisitSession, Visitor
from tracker.services.attribution import classify

NOW = timezone.now()


# ---------------------------------------------------------------- 引擎纯函数
def test_bing_search_term_extracted():
    r = classify(referrer_url="https://www.bing.com/search?q=%E6%8C%96%E6%8E%98%E6%9C%BA&m=1",
                 landing_path="/pricing")
    assert r["channel"] == "natural_search"
    assert r["platform"] == "Bing"
    assert r["search_term"] == "挖掘机"
    assert r["evidence_kind"] == "observed_referrer"
    assert r["resolution"] == "resolved"


def test_google_never_fabricates_search_term():
    r = classify(referrer_url="https://www.google.com/search?q=cats")
    assert r["channel"] == "natural_search" and r["platform"] == "Google"
    assert r["search_term"] == ""            # Google 不在 SEARCH_TERM_PARAMS 表 = 恒空，绝不虚构
    assert r["variant"] == ""                # google.com → TLD "com" 不显示


def test_google_country_tld_as_variant():
    r = classify(referrer_url="https://www.google.co.ru/search?q=x")
    assert r["platform"] == "Google" and r["variant"] == "ru"


def test_baidu_wd_chinese_term_and_word_fallback():
    r = classify(referrer_url="https://www.baidu.com/s?wd=挖掘机价格")
    assert r["platform"] == "百度" and r["search_term"] == "挖掘机价格"
    r2 = classify(referrer_url="https://m.baidu.com/s?word=租赁")   # 子域 + word 参数兜底
    assert r2["platform"] == "百度" and r2["search_term"] == "租赁"


def test_chatgpt_referral():
    r = classify(referrer_url="https://chatgpt.com/c/abc")
    assert r["channel"] == "ai_referral" and r["platform"] == "ChatGPT"
    assert r["resolution"] == "resolved"
    r2 = classify(referrer_url="https://chat.chatgpt.com/")   # 子域同样命中
    assert r2["channel"] == "ai_referral" and r2["platform"] == "ChatGPT"


def test_social_twitter_short_link():
    r = classify(referrer_url="https://t.co/AbCdEf")
    assert r["channel"] == "social" and r["platform"] == "Twitter/X"


def test_generic_referral_keeps_host_as_platform():
    r = classify(referrer_url="https://blog.example.com/post/1")
    assert r["channel"] == "referral" and r["platform"] == "blog.example.com"
    assert r["evidence_kind"] == "observed_referrer" and r["resolution"] == "resolved"


def test_paid_click_param_wins_over_natural_search():
    r = classify(referrer_url="https://www.bing.com/search?q=x",
                 landing_path="/offer?gclid=EAIaIQ")
    assert r["channel"] == "paid_search" and r["platform"] == "Google Ads"   # 付费优先于自然
    assert r["detail"].get("click_param") == "gclid"
    r2 = classify(landing_path="/?fbclid=IwAR0")                            # 仅落地页带点击参数
    assert r2["channel"] == "paid_search" and r2["platform"] == "Meta Ads"


def test_paid_param_in_referrer_url():
    r = classify(referrer_url="https://example.com/ad?msclkid=xyz", landing_path="/")
    assert r["channel"] == "paid_search" and r["platform"] == "Bing Ads"


def test_micromessenger_ua_without_referrer_is_in_app():
    r = classify(ua="Mozilla/5.0 (Linux; Android 14) MicroMessenger/8.0.47")
    assert r["channel"] == "in_app" and r["platform"] == "微信"
    assert r["resolution"] == "resolved"


def test_in_app_marker_overlays_existing_source_in_detail():
    r = classify(referrer_url="https://www.bing.com/search?q=x",
                 ua="Mozilla/5.0 ... MicroMessenger/8.0.47")
    assert r["channel"] == "natural_search"          # 来源结论不被 UA 覆盖
    assert r["detail"].get("in_app") == "微信"         # 应用内浏览器作为 surface 叠加进 detail


def test_internal_referrer_treated_as_no_signal():
    r = classify(referrer_url="https://www.a.com/other-page", internal_domains=["a.com"])
    assert r["channel"] == "direct" and r["resolution"] == "unknown"
    r2 = classify(referrer_url="https://sub.a.com/x", utm={"utm_source": "newsletter"},
                  internal_domains=["a.com"])        # 本站跳转后仍带 UTM → 仅剩标签证据
    assert r2["resolution"] == "label_only" and r2["platform"] == "newsletter"


def test_utm_matching_referrer_upgrades_to_combined():
    r = classify(referrer_url="https://www.bing.com/search?q=x", utm={"utm_source": "bing"})
    assert r["channel"] == "natural_search" and r["evidence_kind"] == "combined"


def test_utm_contradicting_referrer_is_conflict_with_both_evidences():
    r = classify(referrer_url="https://facebook.com/l/abc", utm={"utm_source": "google"})
    assert r["channel"] == "social" and r["platform"] == "Facebook"   # 观察证据优先于自述标签
    assert r["resolution"] == "conflict"
    assert r["evidence_kind"] == "observed_referrer"
    ref_ev, utm_ev = r["detail"]["referrer_evidence"], r["detail"]["utm_evidence"]
    assert ref_ev["platform"] == "Facebook" and ref_ev["channel"] == "social"
    assert utm_ev["platform"] == "google" and utm_ev["evidence_kind"] == "utm_label"


def test_utm_only_is_label_only():
    r = classify(utm={"utm_source": "newsletter"})
    assert r["channel"] == "referral"               # 未知标签 → 有名 referral，但状态诚实标注
    assert r["platform"] == "newsletter"
    assert r["resolution"] == "label_only" and r["evidence_kind"] == "utm_label"
    r2 = classify(utm={"utm_source": "baidu"})      # 已知引擎标签 → 归入对应渠道（仍 label_only）
    assert r2["channel"] == "natural_search" and r2["platform"] == "baidu"
    assert r2["resolution"] == "label_only"


def test_empty_everything_is_direct_unknown():
    r = classify()
    assert r == {"channel": "direct", "platform": "", "variant": "",
                 "search_term": "", "evidence_kind": "", "resolution": "unknown",
                 "detail": {}}


def test_search_term_cleaned_and_truncated():
    long = "词" * 150
    r = classify(referrer_url=f"https://www.bing.com/search?q=%20%20{long}%20")
    assert r["search_term"] == "词" * 100           # strip + 截 100
    r2 = classify(referrer_url="https://www.bing.com/search?q=a%00b%01c")  # 控制字符剔除
    assert r2["search_term"] == "abc"


def test_garbage_referrer_url_does_not_crash():
    r = classify(referrer_url="http://[invalid", landing_path="/x")
    assert r["channel"] in ("referral", "direct")   # 不崩，落到兜底分支即可


# ------------------------------------------------------- 入库 + 重算集成
@pytest.mark.django_db
def test_ingest_writes_first_touch_and_session_entry():
    from tracker.services.ingest import ingest_batch
    site = Site.objects.create(name="s", domains=["a.com"])
    payload = {"visitor_id": "v1", "session_id": "s1", "context": {
        "referrer_domain": "www.bing.com", "utm": {}, "path": "/landing"},
        "events": [{"event_id": "e1", "event_name": "page_view", "occurred_at": NOW,
                    "path": "/landing", "title": "T",
                    "properties": {"referrer": "https://www.bing.com/search?q=%E6%8C%96%E6%8E%98%E6%9C%BA"}}]}
    ingest_batch(site, payload, ip="114.114.114.114", ua="Mozilla/5.0")
    ft = SourceClassification.objects.get(site=site, visitor__visitor_id="v1", scope="first_touch")
    assert ft.session is None
    assert ft.channel == "natural_search" and ft.platform == "Bing"
    assert ft.search_term == "挖掘机" and ft.rule_version == "v1"
    se = SourceClassification.objects.get(site=site, scope="session_entry")
    assert se.session.session_id == "s1"
    assert se.channel == "natural_search" and se.platform == "Bing"


@pytest.mark.django_db
def test_recompute_attribution_idempotent():
    from tracker.services.ingest import ingest_batch
    site = Site.objects.create(name="s", domains=["a.com"])
    payload = {"visitor_id": "v1", "session_id": "s1", "context": {
        "referrer_domain": "www.bing.com", "utm": {}, "path": "/landing"},
        "events": [{"event_id": "e1", "event_name": "page_view", "occurred_at": NOW,
                    "path": "/landing", "title": "T",
                    "properties": {"referrer": "https://www.bing.com/search?q=ok"}}]}
    ingest_batch(site, payload, ip="114.114.114.114", ua="Mozilla/5.0")
    SourceClassification.objects.all().delete()      # 清掉增量写入，验证重算可全量重建
    call_command("recompute_attribution", stdout=None)
    n1 = SourceClassification.objects.count()
    assert n1 == 2                                   # first_touch + session_entry 各一
    ft = SourceClassification.objects.get(scope="first_touch")
    assert ft.channel == "natural_search" and ft.search_term == "ok"
    call_command("recompute_attribution", stdout=None)   # 第二遍：upsert 不重复不漂移
    assert SourceClassification.objects.count() == n1