382 lines
16 KiB
Python
382 lines
16 KiB
Python
|
from app.engine.services.contact_pipeline import (
|
||
|
|
merge_contacts, normalize_contacts, split_validate,
|
||
|
|
)
|
||
|
|
|
||
|
|
|
||
|
|
def test_normalize_chinese_and_english_keys():
|
||
|
|
raw = {"手机": "+8613800138000", "邮箱": "a@b.com", "微信": "wxid_1",
|
||
|
|
"WhatsApp号码": "+254712345678", "空": ""}
|
||
|
|
out = normalize_contacts(raw)
|
||
|
|
assert out == {
|
||
|
|
"phone": "+8613800138000", "email": "a@b.com",
|
||
|
|
"wechat": "wxid_1", "whatsapp": "+254712345678",
|
||
|
|
}
|
||
|
|
|
||
|
|
|
||
|
|
def test_normalize_later_alias_wins_on_same_key():
|
||
|
|
# 同 key 别名冲突时后写者覆盖（上游 extractor 单轮内一般不会同时给 手机 与 tel，
|
||
|
|
# 但语义必须被钉死并被测试）
|
||
|
|
assert normalize_contacts({"手机": "1111111", "tel": "2222222"}) == {"phone": "2222222"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_normalize_coerces_bare_string_extractor_output():
|
||
|
|
# Task 11 真人验收实测: 真实 GLM extractor 偶发把联系方式压成裸字符串
|
||
|
|
# (mock 测不出)——唯一事实源处兜形,不崩溃不丢号:
|
||
|
|
# 含 @ → email;裸号码 → phone;列表逐项;其他非 dict 按空
|
||
|
|
assert normalize_contacts("+966 50 123 4567") == {"phone": "+966 50 123 4567"}
|
||
|
|
assert normalize_contacts("buyer@example.com") == {"email": "buyer@example.com"}
|
||
|
|
assert normalize_contacts(["+966501234567", "a@b.com"]) == {
|
||
|
|
"phone": "+966501234567", "email": "a@b.com"}
|
||
|
|
assert normalize_contacts(" ") == {}
|
||
|
|
assert normalize_contacts(12345) == {}
|
||
|
|
# merge_contacts 两侧裸串同样不崩、正常深合并
|
||
|
|
assert merge_contacts("+966501234567", {"whatsapp": "+966509876543"}) == {
|
||
|
|
"phone": "+966501234567", "whatsapp": "+966509876543"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_merge_new_value_wins_same_key():
|
||
|
|
old = {"phone": "+254700000000"}
|
||
|
|
new = {"手机": "+254711111111"} # 客户改号
|
||
|
|
assert merge_contacts(old, new) == {"phone": "+254711111111"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_merge_empty_new_keeps_old():
|
||
|
|
# T1 场景: extractor 某轮返回空联系方式,不得抹掉已有值
|
||
|
|
old = {"phone": "+254700000000"}
|
||
|
|
assert merge_contacts(old, {}) == {"phone": "+254700000000"}
|
||
|
|
assert merge_contacts(old, None) == {"phone": "+254700000000"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_split_validate_confirmed_and_suspect():
|
||
|
|
confirmed, suspect = split_validate({
|
||
|
|
"email": "a@b.com", # 合法邮箱
|
||
|
|
"phone": "+254 712 345 678", # 数字 12 位 → confirmed
|
||
|
|
"whatsapp": "12345", # 数字 5 位 → suspect
|
||
|
|
})
|
||
|
|
assert confirmed == {"email": "a@b.com", "phone": "+254 712 345 678"}
|
||
|
|
assert suspect == {"whatsapp": "12345"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_split_validate_bad_email_is_suspect():
|
||
|
|
confirmed, suspect = split_validate({"email": "not-an-email"})
|
||
|
|
assert confirmed == {} and suspect == {"email": "not-an-email"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_split_validate_wechat_id_is_confirmed():
|
||
|
|
# 微信号无数字格式(wxid_x 等),非空≥4字符即 confirmed——否则只留微信的
|
||
|
|
# 客户永远无法触发邮件
|
||
|
|
confirmed, suspect = split_validate({"wechat": "wxid_1"})
|
||
|
|
assert confirmed == {"wechat": "wxid_1"} and suspect == {}
|
||
|
|
|
||
|
|
|
||
|
|
def test_split_validate_wechat_short_is_suspect():
|
||
|
|
confirmed, suspect = split_validate({"wechat": "abc"})
|
||
|
|
assert confirmed == {} and suspect == {"wechat": "abc"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_normalize_coerces_int_values():
|
||
|
|
# extractor 偶尔会把号码输出成 int,不得崩溃且要能归一化
|
||
|
|
assert normalize_contacts({"手机": 254712345678}) == {"phone": "254712345678"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_merge_none_old_keeps_new():
|
||
|
|
assert merge_contacts(None, {"email": "a@b.com"}) == {"email": "a@b.com"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_normalize_phone_alias_variants():
|
||
|
|
# 审查补充: 电话号码 / phone number 等带空格、中文长名变体必须命中 phone
|
||
|
|
assert normalize_contacts({"电话号码": "13800138000"}) == {"phone": "13800138000"}
|
||
|
|
assert normalize_contacts({"phone number": "+12345678901"}) == {"phone": "+12345678901"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_normalize_fuzzy_key_variants():
|
||
|
|
# extractor 常见即兴 key(精确别名表外)不得静默丢值
|
||
|
|
assert normalize_contacts({"联系电话": "13800138000"}) == {"phone": "13800138000"}
|
||
|
|
assert normalize_contacts({"手机号": "13800138000"}) == {"phone": "13800138000"}
|
||
|
|
assert normalize_contacts({"WhatsApp账号": "+254712345678"}) == {
|
||
|
|
"whatsapp": "+254712345678"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_normalize_unknown_key_still_dropped():
|
||
|
|
# 完全不含渠道词的 key 仍然丢弃(如 "备注")
|
||
|
|
assert normalize_contacts({"备注": "13800138000"}) == {}
|
||
|
|
|
||
|
|
|
||
|
|
def test_normalize_slash_combined_key_deterministic():
|
||
|
|
# "电话/WhatsApp" 双渠道复合 key: 按 KEY_ALIASES 声明序取第一个命中(phone 先于 whatsapp)
|
||
|
|
assert normalize_contacts({"电话/WhatsApp": "13800138000"}) == {
|
||
|
|
"phone": "13800138000"}
|
||
|
|
|
||
|
|
|
||
|
|
from app.engine.services.contact_pipeline import scan_user_messages
|
||
|
|
|
||
|
|
|
||
|
|
def m(*texts):
|
||
|
|
return [{"role": "user", "content": t} for t in texts] + [
|
||
|
|
{"role": "assistant", "content": "call me at +999111222333"}]
|
||
|
|
|
||
|
|
|
||
|
|
def test_scan_email():
|
||
|
|
found = scan_user_messages(m("my email is john.doe@x.co send quotes"))
|
||
|
|
assert found == {"email": "john.doe@x.co"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_scan_intl_phone():
|
||
|
|
found = scan_user_messages(m("you can reach me +254712345678"))
|
||
|
|
assert found == {"phone": "+254712345678"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_scan_whatsapp_context_word():
|
||
|
|
found = scan_user_messages(m("whatsapp: 0712 345 678"))
|
||
|
|
assert found.get("whatsapp") == "0712 345 678"
|
||
|
|
|
||
|
|
|
||
|
|
def test_scan_wa_me_link():
|
||
|
|
found = scan_user_messages(m("chat https://wa.me/254712345678"))
|
||
|
|
assert found == {"whatsapp": "254712345678"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_scan_ignores_prices_years_and_ai_messages():
|
||
|
|
texts = m(
|
||
|
|
"budget $25,000 for 2024 PE100 pipes", # 价格+年份
|
||
|
|
"50,000 km mileage", # 里程
|
||
|
|
"I want 5 units", # 数量
|
||
|
|
)
|
||
|
|
# 上一条含 assistant 消息,确保只扫 user
|
||
|
|
found = scan_user_messages(texts)
|
||
|
|
assert found == {}
|
||
|
|
|
||
|
|
|
||
|
|
def test_scan_full_history_not_only_last():
|
||
|
|
# S4: 扫全量历史,早轮的联系方式也要能捞到
|
||
|
|
msgs = [
|
||
|
|
{"role": "user", "content": "hi"},
|
||
|
|
{"role": "assistant", "content": "hey"},
|
||
|
|
{"role": "user", "content": "mail me a@b.com"},
|
||
|
|
{"role": "assistant", "content": "got it"},
|
||
|
|
{"role": "user", "content": "how much is pvc"},
|
||
|
|
]
|
||
|
|
assert scan_user_messages(msgs) == {"email": "a@b.com"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_scan_context_word_does_not_grab_unrelated_numbers():
|
||
|
|
# S1: 上下文词必须与数字邻接(同一匹配内),消息任意位置的7位数字不得被抓
|
||
|
|
assert scan_user_messages(m("call me on delivery, order 1234567")) == {}
|
||
|
|
assert scan_user_messages(m("车架号码是 LFV3A23C8K3123456 吗")) == {}
|
||
|
|
assert scan_user_messages(m("engine number 2ZRFE1234567?")) == {}
|
||
|
|
assert scan_user_messages(m("我手机坏了 budget 1500000 ksh")) == {}
|
||
|
|
|
||
|
|
|
||
|
|
def test_scan_adjacent_context_phone():
|
||
|
|
assert scan_user_messages(m("my phone number is 0712 345 678")) == {
|
||
|
|
"phone": "0712 345 678"}
|
||
|
|
assert scan_user_messages(m("call me at +86 138 0013 8000")) == {
|
||
|
|
"phone": "+86 138 0013 8000"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_canon_normalizes_for_dedup():
|
||
|
|
from app.engine.services.contact_pipeline import canon
|
||
|
|
assert canon("A@B.COM") == "a@b.com"
|
||
|
|
assert canon("+254 712-345 678") == "254712345678"
|
||
|
|
|
||
|
|
|
||
|
|
from app.engine.services.contact_pipeline import latest_stated_contacts
|
||
|
|
|
||
|
|
|
||
|
|
def test_latest_stated_correction_context():
|
||
|
|
msgs = m("my phone is +8613800138000", "wrong number, use +8613999999999")
|
||
|
|
assert latest_stated_contacts(msgs) == {"phone": "+8613999999999"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_latest_stated_new_number_no_correction_words():
|
||
|
|
msgs = m("my number is +254712345678", "my new number is +254700111222")
|
||
|
|
assert latest_stated_contacts(msgs) == {"phone": "+254700111222"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_latest_stated_bare_number_has_no_authority():
|
||
|
|
# 更正语境缺席时,裸 +号 无覆盖权(价格/单号防误翻新)
|
||
|
|
msgs = m("my number is +254712345678", "total is +254700111222 usd wait no")
|
||
|
|
assert latest_stated_contacts(msgs) == {"phone": "+254712345678"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_latest_stated_same_value_no_conflict():
|
||
|
|
msgs = m("my number is +254712345678", "my number is +254712345678")
|
||
|
|
assert latest_stated_contacts(msgs) == {"phone": "+254712345678"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_scan_my_phone_is_local_number():
|
||
|
|
# 评审恢复项: "my phone is <无+本地号>" 曾从门控模式掉落(extractor 漏时彻底失联)
|
||
|
|
found = scan_user_messages(m("my phone is 07123456789"))
|
||
|
|
assert found == {"phone": "07123456789"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_latest_stated_my_phone_is_form():
|
||
|
|
msgs = m("hi", "my phone is 07123456789")
|
||
|
|
assert latest_stated_contacts(msgs) == {"phone": "07123456789"}
|
||
|
|
|
||
|
|
|
||
|
|
from app.engine.services.contact_pipeline import resolve_by_recency
|
||
|
|
|
||
|
|
|
||
|
|
def _u(*texts):
|
||
|
|
return [{"role": "user", "content": t} for t in texts]
|
||
|
|
|
||
|
|
|
||
|
|
def test_recency_mirror_lag_newest_wins():
|
||
|
|
# Task 12b 场景: extractor 只翻新 phone,镜像 whatsapp 滞后 → 最新提及统一
|
||
|
|
before = {"phone": "+8613800138000", "whatsapp": "+8613800138000"}
|
||
|
|
after = {"phone": "+8613999999999", "whatsapp": "+8613800138000"}
|
||
|
|
msgs = _u("my phone is +8613800138000", "wrong number, use +8613999999999")
|
||
|
|
assert resolve_by_recency(before, after, msgs) == {
|
||
|
|
"phone": "+8613999999999", "whatsapp": "+8613999999999"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_recency_kills_extractor_oscillation():
|
||
|
|
# 实测bug场景: extractor 翻回更早消息里的旧号 → 裁决回最新的 ...004
|
||
|
|
before = {"phone": "+8613800138004", "whatsapp": "+8613800138004"}
|
||
|
|
after = {"phone": "+8613800138000", "whatsapp": "+8613800138004"} # extractor 振荡
|
||
|
|
msgs = _u("my whatsapp is +8613800138000", "my whatsapp is +8613800138004",
|
||
|
|
"any pipe talk")
|
||
|
|
assert resolve_by_recency(before, after, msgs) == before # 无变化→不触发更正
|
||
|
|
|
||
|
|
|
||
|
|
def test_recency_suppresses_hallucinated_value():
|
||
|
|
# 幻觉值从未出现在消息里(last_idx=-1) → 真实陈述胜
|
||
|
|
before = {"phone": "+8613800138004", "whatsapp": "+8613800138004"}
|
||
|
|
after = {"phone": "+8613999999999", "whatsapp": "+8613800138004"}
|
||
|
|
msgs = _u("my whatsapp is +8613800138004")
|
||
|
|
assert resolve_by_recency(before, after, msgs) == before
|
||
|
|
|
||
|
|
|
||
|
|
def test_recency_bare_newest_number_wins():
|
||
|
|
# 用户实测终局: 最晚消息里的裸新号(extractor 抓到)胜过更早的陈述
|
||
|
|
before = {"phone": "+8613800138004", "whatsapp": "+8613800138004"}
|
||
|
|
after = {"phone": "18325698745", "whatsapp": "+8613800138004"}
|
||
|
|
msgs = _u("my whatsapp is +8613800138004", "chat", "18325698745")
|
||
|
|
assert resolve_by_recency(before, after, msgs) == {
|
||
|
|
"phone": "18325698745", "whatsapp": "18325698745"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_recency_genuinely_different_untouched():
|
||
|
|
before = {"phone": "+8613800138000", "whatsapp": "+254712345678"}
|
||
|
|
after = {"phone": "+8613999999999", "whatsapp": "+254712345678"}
|
||
|
|
msgs = _u("my phone is +8613800138000", "my whatsapp is +254712345678",
|
||
|
|
"wrong number, use +8613999999999")
|
||
|
|
assert resolve_by_recency(before, after, msgs) == after # 不同组不动
|
||
|
|
|
||
|
|
|
||
|
|
from app.engine.services.contact_pipeline import standalone_number
|
||
|
|
|
||
|
|
|
||
|
|
def test_standalone_number_captures_cn_and_ke_mobiles():
|
||
|
|
assert standalone_number("15236541128") == "15236541128"
|
||
|
|
assert standalone_number("0712345678") == "0712345678"
|
||
|
|
assert standalone_number("+86 138 0013 8000") == "+86 138 0013 8000"
|
||
|
|
|
||
|
|
|
||
|
|
def test_standalone_number_rejects_prices_years_and_prose():
|
||
|
|
assert standalone_number("2024") is None # 年份
|
||
|
|
assert standalone_number("25000") is None # 美元价
|
||
|
|
assert standalone_number("1500000") is None # 先令价(7位)
|
||
|
|
assert standalone_number("50,000 km") is None # 含字母逗号
|
||
|
|
assert standalone_number("I want 5 units") is None
|
||
|
|
|
||
|
|
|
||
|
|
def test_latest_stated_standalone_overrides():
|
||
|
|
msgs = m("my number is +254712345678", "chat", "15236541128")
|
||
|
|
assert latest_stated_contacts(msgs) == {"phone": "15236541128"}
|
||
|
|
|
||
|
|
|
||
|
|
# ---- P0 捕获缺口扩充: 号码在前/无is/msg me/wa冒号 ----
|
||
|
|
# 全部经 scan_user_messages 断言,不直接 import 新正则符号
|
||
|
|
|
||
|
|
|
||
|
|
def test_scan_number_before_whatsapp():
|
||
|
|
# 倒装: "0712 345 678 is my whatsapp"
|
||
|
|
assert scan_user_messages(m("0712 345 678 is my whatsapp")) == {
|
||
|
|
"whatsapp": "0712 345 678"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_scan_number_before_wechat_cn():
|
||
|
|
# 中文倒装(我的后无空格——正则必须用 \s* 而非 \s+,实证 \s+ 永不命中)
|
||
|
|
assert scan_user_messages(m("13800138000 我的微信")) == {
|
||
|
|
"wechat": "13800138000"}
|
||
|
|
assert scan_user_messages(m("13800138000 这是我的微信")) == {
|
||
|
|
"wechat": "13800138000"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_scan_my_number_without_is():
|
||
|
|
# "my number 0712345678"(无 is/冒号)
|
||
|
|
assert scan_user_messages(m("my number 0712345678")) == {
|
||
|
|
"phone": "0712345678"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_scan_text_me_forms():
|
||
|
|
assert scan_user_messages(m("text me at 07123456789")) == {
|
||
|
|
"phone": "07123456789"}
|
||
|
|
assert scan_user_messages(m("msg me 07123456789")) == {
|
||
|
|
"phone": "07123456789"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_scan_wa_colon_local_number():
|
||
|
|
assert scan_user_messages(m("wa: 07123456789")) == {
|
||
|
|
"whatsapp": "07123456789"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_scan_new_forms_do_not_grab_prices():
|
||
|
|
# 误报防护: 价格/单号即使与 whatsapp 词同现也不得捕获(无 my 指称/无邻接)
|
||
|
|
assert scan_user_messages(m("paid 2500000 via whatsapp transfer")) == {}
|
||
|
|
assert scan_user_messages(m("my budget 25000 number one priority")) == {}
|
||
|
|
assert scan_user_messages(m("order 1234567 is my order number")) == {}
|
||
|
|
# 排位表述(实证: 若倒装正则收 number/phone,"2500000 is my number" 被误捕,
|
||
|
|
# 且 latest_stated_contacts 覆盖权会把真实号码翻新成价格)——倒装只收显式渠道词
|
||
|
|
assert scan_user_messages(m("2500000 is my number one choice")) == {}
|
||
|
|
# wa 词界守卫: "my watch/way" 的 wa 后无词边界,不得命中
|
||
|
|
assert scan_user_messages(m("0712345678 my watch")) == {}
|
||
|
|
assert scan_user_messages(m("0712345678 my way home")) == {}
|
||
|
|
|
||
|
|
|
||
|
|
def test_bare_my_number_has_no_latest_authority():
|
||
|
|
# 回归钉死: 裸 "my number X"(无 is/冒号)只进扫描辅源,不得进
|
||
|
|
# latest_stated_contacts 获覆盖权——否则首轮旧值长期压制 extractor
|
||
|
|
# 后续改号(实证: test_correction_up_to_three 两封更正邮件全灭)。
|
||
|
|
# 预期 {} 依赖 "wrong,"(逗号后无 number/phone)不命中 CORRECTION_CTX_RE。
|
||
|
|
msgs = m("my number +8613800138000", "wrong, use +8613800139999",
|
||
|
|
"again +8613800122222")
|
||
|
|
assert latest_stated_contacts(msgs) == {}
|
||
|
|
|
||
|
|
|
||
|
|
def test_number_first_whatsapp_whitespace_variants():
|
||
|
|
# 回归(评审): whats\s*app 捕获的任意空白变体(双空格/NBSP)不得让
|
||
|
|
# _NUMBER_FIRST_CHANNEL 查表 KeyError——scan 在每条用户消息的热路径上
|
||
|
|
# 运行(conversation.py 无 try/except),崩溃即断流整轮对话。
|
||
|
|
assert scan_user_messages(m("0712345678 is my whats app")) == {
|
||
|
|
"whatsapp": "0712345678"}
|
||
|
|
assert scan_user_messages(m("0712345678 is my whats\xa0app")) == {
|
||
|
|
"whatsapp": "0712345678"}
|
||
|
|
# 两个接线位(scan + latest)都要走空白归一,任一崩都算回归
|
||
|
|
assert latest_stated_contacts(m("0712345678 is my whats app")) == {
|
||
|
|
"whatsapp": "0712345678"}
|
||
|
|
|
||
|
|
|
||
|
|
# ---- 阿语/波斯语数字归一化(中东买家): 存库与比对全链 ASCII ----
|
||
|
|
|
||
|
|
|
||
|
|
def test_arabic_digits_normalized():
|
||
|
|
# 阿语数字(中东买家)提取后应转 ASCII,CRM 可直接拨
|
||
|
|
confirmed, _ = split_validate({"whatsapp": "+٩٦٦٥٠١٢٣٤٥٦٧"})
|
||
|
|
assert confirmed["whatsapp"] == "+966501234567"
|
||
|
|
|
||
|
|
|
||
|
|
def test_arabic_digits_scan_latest_translated():
|
||
|
|
# 捕获源头即转 ASCII: 用户消息里的阿语号码,scan/latest 的落库形态
|
||
|
|
# 直接可拨;canon 比对也与 ASCII 形态同口径(不触发假性"改号"更正邮件)
|
||
|
|
msgs = [{"role": "user", "content": "whatsapp: ٩٦٦٥٠١٢٣٤٥٦٧"}]
|
||
|
|
assert scan_user_messages(msgs) == {"whatsapp": "966501234567"}
|
||
|
|
assert latest_stated_contacts(msgs) == {"whatsapp": "966501234567"}
|
||
|
|
|
||
|
|
|
||
|
|
def test_arabic_digits_canon_equals_ascii_form():
|
||
|
|
from app.engine.services.contact_pipeline import canon
|
||
|
|
assert canon("+٩٦٦ ٥٠١ ٢٣٤ ٥٦٧") == canon("+966 501 234 567")
|