浅念
265 lines
11 KiB
Python
265 lines
11 KiB
Python
"""统一联系方式管道：联系方式检测的唯一事实源。
|
||
|
||
三个动作：
|
||
- 归一化：中英文 key 别名统一为 phone/whatsapp/email/wechat
|
||
- 深合并：同 key 新值覆盖旧值（客户改号场景），空值不覆盖
|
||
- 校验分级：confirmed（格式通过，可触发邮件/结束）/ suspect（疑似，
|
||
仅用于提醒 AI 礼貌确认，防止重复索要——D6/S1）
|
||
|
||
上游约定：raw_info 中 "_" 前缀 key 为内部状态，禁止进入提示词渲染。
|
||
"""
|
||
import re
|
||
|
||
KEY_ALIASES = {
|
||
"phone": "phone", "手机": "phone", "电话": "phone", "电话号码": "phone",
|
||
"联系电话": "phone", "手机号": "phone", "手机号码": "phone",
|
||
"tel": "phone", "telephone": "phone", "phone_number": "phone",
|
||
"phone number": "phone", "mobile": "phone", "mobile_number": "phone",
|
||
"mobile number": "phone",
|
||
"whatsapp": "whatsapp", "wa": "whatsapp", "wsp": "whatsapp",
|
||
"whats app": "whatsapp", "whatsapp账号": "whatsapp",
|
||
"whatsapp号码": "whatsapp", "whatsapp number": "whatsapp",
|
||
"email": "email", "邮箱": "email", "e-mail": "email", "mail": "email",
|
||
"电子邮件": "email",
|
||
"wechat": "wechat", "微信": "wechat", "wx": "wechat", "weixin": "wechat",
|
||
}
|
||
|
||
|
||
def normalize_contacts(raw: dict | None) -> dict:
|
||
"""key 归一化 + 去空值。精确别名优先;未命中再做 contains 兜底
|
||
(extractor 即兴变体 key 不静默丢值)。contains 按 KEY_ALIASES 声明序
|
||
取第一个命中——复合 key(电话/WhatsApp)结果确定。"""
|
||
out: dict[str, str] = {}
|
||
for k, v in (raw or {}).items():
|
||
key = str(k).strip().lower()
|
||
alias = KEY_ALIASES.get(key)
|
||
if alias is None:
|
||
for name, target in KEY_ALIASES.items():
|
||
if name in key:
|
||
alias = target
|
||
break
|
||
val = str(v or "").strip()
|
||
if alias and val:
|
||
out[alias] = val
|
||
return out
|
||
|
||
|
||
def merge_contacts(old: dict | None, new: dict | None) -> dict:
|
||
"""同 key 新值覆盖旧值；空/缺省不覆盖（堵浅合并抹数据 bug）。"""
|
||
return {**normalize_contacts(old), **normalize_contacts(new)}
|
||
|
||
|
||
def digits_only(s: str) -> str:
|
||
"""提取纯数字（split_validate 位数判断与后续 canon 复用）。"""
|
||
return re.sub(r"\D", "", s)
|
||
|
||
|
||
def split_validate(contacts: dict) -> tuple[dict, dict]:
|
||
"""返回 (confirmed, suspect)。电话/WhatsApp 取数字 7-15 位为合格；微信取非空 ≥4 字符。"""
|
||
confirmed: dict[str, str] = {}
|
||
suspect: dict[str, str] = {}
|
||
for k, v in normalize_contacts(contacts).items():
|
||
if k == "email":
|
||
ok = re.fullmatch(r"[^@\s]+@[^@\s]+\.[^@\s]+", v) is not None
|
||
elif k == "wechat":
|
||
ok = len(v.strip()) >= 4 # 微信号无数字格式,非空短串即可
|
||
else:
|
||
ok = 7 <= len(digits_only(v)) <= 15
|
||
(confirmed if ok else suspect)[k] = v
|
||
return confirmed, suspect
|
||
|
||
|
||
EMAIL_RE = re.compile(r"[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}")
|
||
INTL_PHONE_RE = re.compile(r"\+\d{6,15}")
|
||
# 邻接绑定：上下文词与数字必须在同一匹配内（仅空白衔接）——禁止"消息任意位置
|
||
# 有上下文词 + 任意位置有 7 位数字"的消息级误绑（S1：车架号/订单号/先令价格）
|
||
WHATSAPP_CTX_RE = re.compile(
|
||
r"(?:whats\s*app|wa\.?me|(?:^|\b)wa\s*[:：])\D{0,12}(\+?\d[\d\s\-().]{5,17}\d)",
|
||
re.IGNORECASE,
|
||
)
|
||
PHONE_CTX_RE = re.compile(
|
||
r"(?:my\s+(?:(?:new|other|another)\s+)?(?:phone\s+)?number\s+is|"
|
||
r"my\s+(?:(?:new|other|another)\s+)?phone\s+is|"
|
||
r"(?:msg|message|text|ping)\s+me\s+(?:at|on)?\s*|"
|
||
r"call\s+me\s+(?:at|on)|reach\s+me\s+(?:at|on)|"
|
||
r"phone\s*[:：]|number\s*[:：]|号码\s*[:：]|手机号?\s*[:：]|电话\s*[:：])\s*"
|
||
r"(\+?\d[\d\s\-().]{5,17}\d)",
|
||
re.IGNORECASE,
|
||
)
|
||
# 仅 scan_user_messages 使用的裸邻接形态: "my number 0712345678"(无 is/冒号)。
|
||
# ⚠️ 不得进 latest_stated_contacts——裸邻接无自述确定性,授覆盖权会让首轮旧值
|
||
# 长期压制 extractor 后续改号(实证: test_correction_up_to_three 更正邮件全灭)。
|
||
# 已知覆盖边界: "my phone 0712345678"(phone 变体,无 is)不在本形态内。
|
||
PHONE_ADJACENCY_SCAN_RE = re.compile(
|
||
r"my\s+(?:(?:new|other|another)\s+)?number\s+(\+?\d[\d\s\-().]{5,17}\d)",
|
||
re.IGNORECASE,
|
||
)
|
||
# 倒装自述: "0712 345 678 is my whatsapp / 13800138000 我的微信"
|
||
# ⚠️ 只收显式渠道词(whatsapp/wa/wechat/微信),不收 number/phone/号码——
|
||
# 自查实证: "2500000 is my number one choice" 这类排位表述会把价格误绑成
|
||
# 号码,且本正则进入 latest_stated_contacts 即获覆盖权,误捕获会翻新掉
|
||
# 已存真实号码(正是 S1 系测试在防的事故类)。倒装电话表述罕见,不值得
|
||
# 为其承担该风险;电话主通路由 PHONE_CTX_RE 前缀形态/standalone/INTL 覆盖。
|
||
# (?:my|我的)后用 \s* 而非 \s+: 中文"我的微信"连写无空白,\s+ 永不命中(实证)。
|
||
NUMBER_FIRST_RE = re.compile(
|
||
r"(\+?\d[\d\s\-().]{5,17}\d)\s*(?:is|这是)?\s*"
|
||
r"(?:my|我的)\s*(whats\s*app|wa\b|wechat|微信)",
|
||
re.IGNORECASE,
|
||
)
|
||
|
||
_NUMBER_FIRST_CHANNEL = {
|
||
"whatsapp": "whatsapp", "whats app": "whatsapp", "wa": "whatsapp",
|
||
"wechat": "wechat", "微信": "wechat",
|
||
}
|
||
|
||
|
||
def _number_first_channel(hit: re.Match) -> str:
|
||
# whats\s*app 可捕到任意空白变体(双空格/NBSP/换行),查表前先归一成
|
||
# 单空格——否则 KeyError 会沿着 scan 的每消息热路径直接断流整轮对话。
|
||
return _NUMBER_FIRST_CHANNEL[" ".join(hit.group(2).lower().split())]
|
||
|
||
|
||
# 更正语境(与裸国际号同消息出现时才授予覆盖权)
|
||
CORRECTION_CTX_RE = re.compile(
|
||
r"wrong\s+(?:number|phone)|typo|打错|写错|输错|错了|换成了?|改为|"
|
||
r"use\s+(?:this|new|the\s+new)|instead|correct\s+(?:number|phone|it)",
|
||
re.IGNORECASE,
|
||
)
|
||
|
||
|
||
def scan_user_messages(messages: list[dict]) -> dict:
|
||
"""S4: 扫描全部客户消息,返回高置信捕获(email / +国际号 / whatsapp·wa.me /
|
||
显式电话上下文邻接数字)。裸数字(价格/年份/里程/车架号)一律不收。"""
|
||
found: dict[str, str] = {}
|
||
for msg in messages:
|
||
if msg.get("role") != "user":
|
||
continue
|
||
text = msg.get("content", "")
|
||
if "email" not in found:
|
||
hit = EMAIL_RE.search(text)
|
||
if hit:
|
||
found["email"] = hit.group(0)
|
||
if "phone" not in found:
|
||
sn = standalone_number(text)
|
||
if sn:
|
||
found["phone"] = sn
|
||
if "phone" not in found:
|
||
hit = INTL_PHONE_RE.search(text)
|
||
if hit:
|
||
found["phone"] = hit.group(0)
|
||
if "whatsapp" not in found:
|
||
hit = WHATSAPP_CTX_RE.search(text)
|
||
if hit:
|
||
found["whatsapp"] = hit.group(1)
|
||
if "phone" not in found:
|
||
hit = PHONE_CTX_RE.search(text)
|
||
if hit:
|
||
found["phone"] = hit.group(1)
|
||
if "phone" not in found:
|
||
hit = PHONE_ADJACENCY_SCAN_RE.search(text)
|
||
if hit:
|
||
found["phone"] = hit.group(1)
|
||
# 倒装属最低置信层: whatsapp/phone 任一已被更高置信源捕获即跳过,
|
||
# 不与之竞争(跨 key 门控故含 phone)。
|
||
if "whatsapp" not in found and "phone" not in found:
|
||
hit = NUMBER_FIRST_RE.search(text)
|
||
if hit:
|
||
ch = _number_first_channel(hit)
|
||
found[ch] = hit.group(1)
|
||
return found
|
||
|
||
|
||
def canon(value: str) -> str:
|
||
"""去重比对用的规范形：邮箱小写，其余取纯数字（S3/R3 best-effort）。"""
|
||
value = str(value or "").strip()
|
||
if "@" in value:
|
||
return value.lower()
|
||
return digits_only(value)
|
||
|
||
|
||
def standalone_number(text: str) -> str | None:
|
||
"""整条消息仅为一个号码(Task 12d): 客户"直接甩号"的最显式表达,授予覆盖权。
|
||
≥9 位下限把年份(4)/美元价(5)/先令价(5-7)全部排除在外;
|
||
允许 +/-/空格/横线/点/括号包裹,其余任何字符(字母/逗号)即非独立号码条。"""
|
||
t = (text or "").strip()
|
||
if not re.fullmatch(r"\+?[\d\s\-().·]{9,25}", t):
|
||
return None
|
||
return t if 9 <= len(digits_only(t)) <= 15 else None
|
||
|
||
|
||
def latest_stated_contacts(messages: list[dict]) -> dict:
|
||
"""最新显式自述(唯一可覆盖 extractor 回传的来源,Task 12):
|
||
|
||
同 key 取全历史最后一次显式自述。覆盖权仅授予:
|
||
- 上下文门控捕获(whatsapp/wa.me/wa:、my (new/other) number is、msg/text/ping me、colon 形式、email)
|
||
- 倒装渠道自述(NUMBER_FIRST_RE: "0712 345 678 is my whatsapp"、
|
||
"13800138000 我的微信"——只认显式渠道词)
|
||
- "更正语境 ∧ 同消息裸国际号"(wrong number, use +86...)
|
||
纯裸数字无覆盖权(S1): 防价格/年份/订单号误翻新。
|
||
例外(Task 12d): 整条消息仅为一个号码(≥9位) = 最显式自述,授予覆盖权。
|
||
通则(权威契约): 正则接进本循环即授覆盖权——新增低精度形态时只进
|
||
扫描辅源 scan_user_messages,不进这里(先例: PHONE_ADJACENCY_SCAN_RE,
|
||
裸 my number 邻接曾致更正邮件全灭)。
|
||
"""
|
||
latest: dict[str, str] = {}
|
||
for msg in messages:
|
||
if msg.get("role") != "user":
|
||
continue
|
||
text = msg.get("content") or ""
|
||
hit = EMAIL_RE.search(text)
|
||
if hit:
|
||
latest["email"] = hit.group(0)
|
||
hit = WHATSAPP_CTX_RE.search(text)
|
||
if hit:
|
||
latest["whatsapp"] = hit.group(1)
|
||
sn = standalone_number(text)
|
||
if sn:
|
||
latest["phone"] = sn
|
||
hit = PHONE_CTX_RE.search(text)
|
||
if hit:
|
||
latest["phone"] = hit.group(1)
|
||
elif CORRECTION_CTX_RE.search(text):
|
||
hit = INTL_PHONE_RE.search(text)
|
||
if hit:
|
||
latest["phone"] = hit.group(0)
|
||
hit = NUMBER_FIRST_RE.search(text)
|
||
if hit:
|
||
ch = _number_first_channel(hit)
|
||
latest[ch] = hit.group(1)
|
||
return latest
|
||
|
||
|
||
def resolve_by_recency(before: dict, after: dict, messages: list[dict]) -> dict:
|
||
"""最近提及裁决(Task 12c): before 中同 canon 的非 email key 构成一个镜像身份组。
|
||
组内分歧时,取"出现在最晚客户消息里"的 canon 代表值——
|
||
- 杀掉 extractor 在历史号码间的振荡(旧号总在更早的消息里,天然落败)
|
||
- 压制幻觉值(从未出现在任何消息里,last_idx=-1)
|
||
- 客户最新消息里的新号(extractor 抓到的裸号)天然胜出
|
||
组内一致或不同组(本就不同的号)时原样返回。"""
|
||
out = dict(after)
|
||
groups: dict[str, set[str]] = {}
|
||
for k, v in (before or {}).items():
|
||
if k != "email" and v:
|
||
groups.setdefault(canon(str(v)), set()).add(k)
|
||
user_digits = [
|
||
digits_only(m.get("content") or "") for m in messages
|
||
if m.get("role") == "user"
|
||
]
|
||
|
||
def last_idx(c: str) -> int:
|
||
for i in range(len(user_digits) - 1, -1, -1):
|
||
if c and c in user_digits[i]:
|
||
return i
|
||
return -1
|
||
|
||
for keys in groups.values():
|
||
vals = {k: out[k] for k in keys if out.get(k)}
|
||
distinct = {canon(str(v)) for v in vals.values()}
|
||
if len(distinct) > 1:
|
||
best = max(distinct, key=last_idx)
|
||
if last_idx(best) >= 0:
|
||
rep = next(v for v in vals.values() if canon(str(v)) == best)
|
||
for k in keys:
|
||
out[k] = rep
|
||
return out
|