"""公司知识库模块 — 公司匹配和证据排序。"""
import re
from typing import Optional


def _normalize_loose(input_str: str) -> str:
    """模糊标准化：小写 + 去除括号/分隔符。"""
    s = input_str.lower()
    s = re.sub(r"[\s\-_·.（）()\[\]{}]", "", s)
    s = s.replace("x", "")
    return s


def _score_profile(input_str: str, aliases: list[str], tags: list[str]) -> int:
    """评分公司匹配度。"""
    normalized = _normalize_loose(input_str)
    score = 0
    for alias in aliases:
        if _normalize_loose(alias) in normalized or normalized in _normalize_loose(alias):
            score += 4
    for tag in tags:
        if _normalize_loose(tag) in normalized:
            score += 2
    return score


def match_company_knowledge(
    product_name: Optional[str] = None,
    company_hint: Optional[str] = None,
    forced_company_id: Optional[str] = None,
    companies: list[dict] = None,
    products: list[dict] = None,
) -> dict:
    """匹配公司知识库。

    Args:
        product_name: 产品名称
        company_hint: 公司名称提示
        forced_company_id: 强制指定公司 ID
        companies: 公司配置列表
        products: 产品配置列表

    Returns:
        CompanyKnowledgeMatch dict
    """
    companies = companies or []
    products = products or []

    # 1. 强制指定
    if forced_company_id:
        company = next((c for c in companies if c.get("id") == forced_company_id), None)
        if company:
            return {
                "companyId": company["id"],
                "companyName": company.get("displayName", ""),
                "evidenceFiles": [],
                "confidence": 1.0,
                "matchedBy": "company_forced",
            }

    # 2. 产品目录匹配
    if product_name:
        normalized = product_name.lower()
        for prod in products:
            aliases = prod.get("aliases", [])
            if any(_normalize_loose(a) in normalized for a in aliases):
                company_id = prod.get("companyId")
                company = next((c for c in companies if c.get("id") == company_id), None)
                if company:
                    return {
                        "companyId": company["id"],
                        "companyName": company.get("displayName", ""),
                        "evidenceFiles": [],
                        "confidence": 1.0,
                        "matchedBy": "product_catalog",
                    }

    # 3. 别名/标签模糊匹配
    best_match = None
    best_score = 0
    search_text = f"{product_name or ''} {company_hint or ''}"

    for company in companies:
        aliases = company.get("aliases", [])
        tags = company.get("aliases", [])  # 用别名作为标签
        score = _score_profile(search_text, aliases, tags)
        if score > best_score:
            best_score = score
            best_match = company

    if best_match and best_score > 0:
        confidence = min(0.95, 0.45 + best_score / 20)
        return {
            "companyId": best_match["id"],
            "companyName": best_match.get("displayName", ""),
            "evidenceFiles": [],
            "confidence": confidence,
            "matchedBy": "company_alias",
        }

    return {
        "companyId": "",
        "companyName": "",
        "evidenceFiles": [],
        "confidence": 0,
        "matchedBy": "unknown",
    }


def expected_company_id_for_product(
    product_name: Optional[str],
    products: list[dict] = None,
) -> Optional[str]:
    """通过产品名查找对应公司 ID。"""
    if not product_name:
        return None
    products = products or []
    normalized = product_name.lower()
    for prod in products:
        aliases = prod.get("aliases", [])
        if any(_normalize_loose(a) in normalized for a in aliases):
            return prod.get("companyId")
    return None