33 lines
1.6 KiB
Python
33 lines
1.6 KiB
Python
|
"""客服会话落库前的敏感凭据最小化处理。
|
|||
|
|
|
|||
|
|
来源：同事 `ZSY_develop` 分支（`app/core/conversation_privacy.py`），整文件移植，未改语义。
|
|||
|
|
纯正则、无外部依赖，供记忆投影（`MilvusProfileProjection`）在写入向量前做最后一道脱敏。
|
|||
|
|
|
|||
|
|
为什么要单独抽一层：记忆内容最终会进入 Milvus 与 Neo4j，一旦写入就脱离了会话事务的
|
|||
|
|
管控范围。把脱敏放在**写入适配器内部**（而不是依赖调用方记得做），是为了让"未经脱敏的
|
|||
|
|
文本不得落外部存储"成为代码保证，而不是流程约定。
|
|||
|
|
"""
|
|||
|
|
|
|||
|
|
import re
|
|||
|
|
|
|||
|
|
# 替换顺序从带业务语义的凭据开始，避免通用数字规则先破坏上下文。
|
|||
|
|
_SENSITIVE_PATTERNS: tuple[tuple[re.Pattern[str], str], ...] = (
|
|||
|
|
(
|
|||
|
|
re.compile(r"(?i)((?:登录|交易)?密码)\s*(?:[:：=]|是)\s*[^\s，。；,;]{1,64}"),
|
|||
|
|
r"\1[已隐藏]",
|
|||
|
|
),
|
|||
|
|
(re.compile(r"(?i)((?:登录|交易)?密码)\s*\d{4,32}"), r"\1[已隐藏]"),
|
|||
|
|
(re.compile(r"(?i)(验证码|短信码|校验码)\s*(?:[:：=]|是)?\s*\d{4,8}"), r"\1[已隐藏]"),
|
|||
|
|
(re.compile(r"(?<!\d)\d{17}[\dXx](?!\d)"), "[证件号已隐藏]"),
|
|||
|
|
(re.compile(r"(?<!\d)(?:\d[ -]?){15,18}\d(?!\d)"), "[银行卡号已隐藏]"),
|
|||
|
|
(re.compile(r"(?<!\d)1[3-9]\d{9}(?!\d)"), "[手机号已隐藏]"),
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
|
|||
|
|
def sanitize_customer_service_message(message: str) -> str:
|
|||
|
|
"""保留风险关键词，移除不应进入会话、Outbox 或后续 Redis 的凭据值。"""
|
|||
|
|
sanitized = message
|
|||
|
|
for pattern, replacement in _SENSITIVE_PATTERNS:
|
|||
|
|
sanitized = pattern.sub(replacement, sanitized)
|
|||
|
|
return sanitized
|