"""L2 训练营知识库工具 — 按需加载 + 语义搜索

本文件包含知识库查询工具的实现。修改主提示词时请勿改动此文件。
"""

from __future__ import annotations

import re
from pathlib import Path
from typing import List

from common.knowledge_loader import list_knowledge_files, load_knowledge_file

# ───────────────────────────── 配置 ─────────────────────────────
_KB_DIR = Path(__file__).parent / "knowledge_base"

# 知识库元数据（与文件名一一对应）
_KB_METADATA: dict[str, dict] = {
    "01_课程层次与问题判断.md": {
        "title": "课程层次与问题判断",
        "description": "帮助判断学员问题属于299启蒙课还是1280训练营层次，以及问题卡在哪个阶段",
        "keywords": [
            "课程层次", "299", "1280", "启蒙课", "训练营", "问题判断",
            "阶段", "层次", "基础", "进阶", "学员水平", "课程区别",
        ],
    },
    "02_即时回复表达原则.md": {
        "title": "即时回复表达原则",
        "description": "辅导老师回复学员时的表达风格、语气、措辞原则和禁忌",
        "keywords": [
            "表达", "回复", "语气", "措辞", "风格", "原则", "禁忌",
            "怎么说", "话术", "沟通", "表达技巧", "回复模板",
        ],
    },
    "03_常见学员问题回应素材.md": {
        "title": "常见学员问题回应素材",
        "description": "学员常见问题的分类、回应策略和具体话术示例",
        "keywords": [
            "常见问题", "学员问题", "回应", "话术", "示例", "策略",
            "情绪", "愤怒", "委屈", "焦虑", "失望", "质疑", "抱怨",
            "婚姻", "孩子", "工作", "健康", "家庭", "关系",
        ],
    },
    "04_功课与练习反馈边界.md": {
        "title": "功课与练习反馈边界",
        "description": "学员功课、练习、打卡的反馈原则和边界，什么该说什么不该说",
        "keywords": [
            "功课", "练习", "打卡", "反馈", "边界", "作业",
            "释放法", "万能释放法", "数息法", "身体感知", "情绪觉察",
            "练习指导", "功课点评", "训练",
        ],
    },
    "05_安全边界与现实风险.md": {
        "title": "安全边界与现实风险",
        "description": "学员安全风险识别、危机干预边界、何时必须上报",
        "keywords": [
            "安全", "风险", "危机", "自杀", "自残", "伤害", "暴力",
            "报警", "上报", "边界", "现实风险", "法律保护", "隐私",
            "紧急情况", "危险", "保护",
        ],
    },
    "06_1280核心术语词典.md": {
        "title": "1280核心术语词典",
        "description": "1280训练营核心术语的标准解释和使用场景",
        "keywords": [
            "术语", "词典", "概念", "定义", "解释",
            "看见自己", "回到自己", "万能释放法", "情绪心钥", "抗拒心钥",
            "原生数据", "潜意识数据", "数息法", "身体感知", "情绪觉察",
            "内在模式", "释放", "觉察", "感知",
        ],
    },
    "07_大本营承接与成交话术.md": {
        "title": "大本营承接与成交话术",
        "description": "大本营课程承接判断、成交话术、异议处理策略",
        "keywords": [
            "大本营", "承接", "成交", "异议", "销售", "推课",
            "后续课程", "持续训练", "课程信心", "报名", "价格", "权益",
            "没时间", "没钱", "怕没效果", "家人不同意", "不想继续",
        ],
    },
}

# ───────────────────────────── 工具函数 ─────────────────────────────

def _tokenize(text: str) -> set[str]:
    """中文分词（使用jieba）"""
    try:
        import jieba

        return set(jieba.cut(text))
    except ImportError:
        # 降级：按字拆分
        return set(text)


def _calc_relevance(query: str, content: str) -> float:
    """计算查询与内容的相关度（0-1）"""
    query_tokens = _tokenize(query.lower())
    content_tokens = _tokenize(content.lower())

    if not query_tokens:
        return 0.0

    overlap = query_tokens & content_tokens
    return len(overlap) / len(query_tokens)


def _extract_relevant_sections(content: str, query: str, max_sections: int = 3) -> list[str]:
    """从知识库内容中提取与查询最相关的章节"""
    # 按二级标题分割
    sections = re.split(r"\n(?=##\s+)", content)

    scored = []
    for section in sections:
        if not section.strip():
            continue
        score = _calc_relevance(query, section)
        scored.append((score, section))

    scored.sort(key=lambda x: x[0], reverse=True)
    return [s for _, s in scored[:max_sections]]


# ───────────────────────────── 公开工具 ─────────────────────────────

def list_kb() -> str:
    """列出所有可用的知识库文件

    当你不确定该查哪个知识库文件时，先调用此工具查看列表。
    """
    lines = ["# 可用知识库文件\n"]
    for fname, meta in _KB_METADATA.items():
        lines.append(f"## {meta['title']}")
        lines.append(f"- 文件名: `{fname}`")
        lines.append(f"- 描述: {meta['description']}")
        lines.append(f"- 关键词: {', '.join(meta['keywords'][:5])}...\n")

    return "\n".join(lines)


def load_kb(filename: str) -> str:
    """加载指定知识库文件的完整内容

    Args:
        filename: 知识库文件名（如 "01_课程层次与问题判断.md"）

    当你已确定需要哪个文件的内容时，调用此工具加载完整内容。
    """
    if filename not in _KB_METADATA:
        available = ", ".join(_KB_METADATA.keys())
        return f"错误: 文件 '{filename}' 不存在。可用文件: {available}"

    content = load_knowledge_file(_KB_DIR, filename)
    if not content:
        return f"错误: 无法读取文件 '{filename}'"

    return content


def search_kb(query: str, top_k: int = 3) -> str:
    """根据关键词搜索所有知识库文件，返回最相关的片段

    Args:
        query: 搜索关键词（中文）
        top_k: 返回结果数量（默认3条）

    当你不确定具体文件，但知道要查什么内容时，调用此工具。
    """
    all_files = list_knowledge_files(_KB_DIR)
    results: list[tuple[float, str, str]] = []

    for fname in all_files:
        content = load_knowledge_file(_KB_DIR, fname)
        if not content:
            continue

        # 计算文件级相关度
        file_score = _calc_relevance(query, content)

        # 提取最相关的章节
        sections = _extract_relevant_sections(content, query, max_sections=2)

        for section in sections:
            section_score = _calc_relevance(query, section)
            # 综合得分：文件级 + 章节级
            final_score = (file_score + section_score) / 2
            results.append((final_score, fname, section))

    # 排序并取 top_k
    results.sort(key=lambda x: x[0], reverse=True)
    top_results = results[:top_k]

    if not top_results:
        return f"未找到与 '{query}' 相关的知识库内容。"

    lines = [f"# 知识库搜索结果: '{query}'\n"]
    for i, (score, fname, section) in enumerate(top_results, 1):
        meta = _KB_METADATA.get(fname, {})
        title = meta.get("title", fname)
        lines.append(f"## 结果 {i}（相关度: {score:.2f}）")
        lines.append(f"**来源**: {title} (`{fname}`)")
        lines.append(f"**内容**:\n{section[:800]}...\n")

    return "\n".join(lines)