#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
9种中医体质 × 方剂/药材/穴位 深层挖掘
=========================================
数据源：
  - 方剂库 (1000个JSON)
  - 中药材库 (1000个JSON)
  - 针灸穴位库 (1000个JSON)
  - 九种体质详细数据.json

输出：
  1. JSON: 体质-方剂药材穴位挖掘.json
  2. MD: 体质数据挖掘报告.md (追加在疾病症状部分之后)
"""

import json
import os
import re
import sys
from collections import defaultdict, Counter
from pathlib import Path

# ============================================================
# 0. 路径设置
# ============================================================
BASE = Path("/home/songyi/Documents/ai_agent_scraper_study/data/大医网")
DIR_FANGJI = BASE / "01_来源数据/方剂"
DIR_YAOCAI = BASE / "01_来源数据/中药材"
DIR_XUEWEI = BASE / "01_来源数据/针灸穴位"
CONST_PATH = BASE / "02_加工数据/中医体质/九种体质详细数据.json"
OUT_JSON = BASE / "03_关联融合/交叉关联分析/体质-方剂药材穴位挖掘.json"
OUT_MD = BASE / "04_分析报告/体质数据挖掘报告.md"

# 确保输出目录存在
OUT_JSON.parent.mkdir(parents=True, exist_ok=True)
OUT_MD.parent.mkdir(parents=True, exist_ok=True)

# ============================================================
# 1. 加载体质数据 & 提取关键字
# ============================================================
print("[1/6] 加载体质数据...")
with open(CONST_PATH, "r", encoding="utf-8") as f:
    constitutions = json.load(f)

# 9种体质: 名称 + 关联关键字
const_info = {}   # { "气虚质": { "keywords": [...], "name": "气虚质" } }
for c in constitutions:
    name = c["名称"]
    kw = c.get("关联关键字", [])
    const_info[name] = {
        "keywords": kw,
        "name": name,
        "data": c
    }

const_names = list(const_info.keys())
print(f"  加载 {len(const_names)} 种体质: {const_names}")

# ============================================================
# 2. 加载全部数据
# ============================================================
print("[2/6] 加载方剂、药材、穴位数据...")

def load_json_files(directory):
    """加载目录下所有JSON文件，返回列表"""
    items = []
    files = sorted(os.listdir(directory))
    for fname in files:
        if not fname.endswith(".json"):
            continue
        fpath = os.path.join(directory, fname)
        try:
            with open(fpath, "r", encoding="utf-8") as f:
                data = json.load(f)
            items.append(data)
        except Exception as e:
            print(f"  ⚠ 加载失败 {fname}: {e}")
    return items

# 方剂
fangji_list = load_json_files(DIR_FANGJI)
print(f"  方剂: {len(fangji_list)} 个")

# 中药材
yaocai_list = load_json_files(DIR_YAOCAI)
print(f"  药材: {len(yaocai_list)} 个")

# 针灸穴位
xuewei_list = load_json_files(DIR_XUEWEI)
print(f"  穴位: {len(xuewei_list)} 个")

# ============================================================
# 3. 构建药材名索引 (用于最长前缀匹配)
# ============================================================
print("[3/6] 构建药材名称索引 (最长前缀匹配)...")

# 收集所有药材名称 (按长度降序排序，避免 金 vs 金银花 误配)
herb_names_all = []
for h in yaocai_list:
    name = h.get("名称", "").strip()
    if name:
        herb_names_all.append(name)
    # 也加入别名中的药材名
    aliases = h.get("别名", "")
    if aliases:
        # 别名格式: "木丹、鲜支、越桃、支子、山栀子、栀子"
        for a in re.split(r'[、，,]', aliases):
            a = a.strip()
            if a and len(a) >= 2:
                herb_names_all.append(a)

# 去重并按长度降序排序
herb_names_all = sorted(set(herb_names_all), key=lambda x: (-len(x), x))
print(f"  药材名称库: {len(herb_names_all)} 个 (含别名)")

def longest_prefix_match(text, herb_list=None):
    """
    在 text 中搜索药材名（最长前缀匹配）
    返回匹配到的药材名列表
    """
    if herb_list is None:
        herb_list = herb_names_all
    found = []
    # 按长度降序遍历，确保先匹配长名
    remaining = text
    # 简单方法：对每个已知药材名，看是否出现在text中
    # 但为避免重叠，我们使用贪心匹配
    for hname in herb_list:
        if hname in remaining:
            found.append(hname)
            # 移除已匹配部分，避免重复/重叠
            # 但这里我们不用移除，因为方解-组成中是"、"分隔的，不会有重叠
    return found

def extract_herbs_from_formula(formula):
    """
    从方剂数据中提取药材名
    优先从 方解-组成 字段提取
    其次是 组成 字段
    最后从 方义 字段中提取
    """
    herbs = []
    
    # 1. 尝试 方解-组成
    if "方解-组成" in formula:
        text = formula["方解-组成"]
        # 用、分割
        parts = re.split(r'[、，,]', text)
        for p in parts:
            p = p.strip()
            if p:
                herbs.append(p)
    
    # 2. 尝试 组成
    if not herbs and "组成" in formula:
        text = formula["组成"]
        # 用、或空格分割，去掉剂量信息
        # 例如: 桂枝（别切）四两、甘草（炙）四两、白术三两
        # 提取括号前的药材名
        parts = re.split(r'[、，,]', text)
        for p in parts:
            p = p.strip()
            # 去掉剂量部分
            # 匹配 "药材名（炮制）剂量" 或 "药材名 剂量"
            m = re.match(r'^([\u4e00-\u9fff\w]+)', p)
            if m:
                name = m.group(1).strip()
                if name and len(name) >= 2:
                    herbs.append(name)
    
    # 3. 从方义中提取
    if not herbs and "方义" in formula:
        text = formula["方义"]
        # 使用最长前缀匹配提取药材名
        herbs = longest_prefix_match(text)
    
    # 去重
    seen = set()
    unique_herbs = []
    for h in herbs:
        if h not in seen:
            seen.add(h)
            unique_herbs.append(h)
    
    return unique_herbs


# ============================================================
# 4. 评分函数
# ============================================================

def score_formula(formula, keywords):
    """
    对方剂进行体质关键字评分
    名称 +5, 方义/简介 +3, 歌诀/出处 +2, 其他 +1
    返回总分
    """
    score = 0.0
    # 名称
    name = formula.get("名称", "")
    for kw in keywords:
        if kw in name:
            score += 5.0
    
    # 方义 + 简介 (+3)
    fangyi = formula.get("方义", "")
    intro = formula.get("简介", "")
    for field_text in [fangyi, intro]:
        if field_text:
            for kw in keywords:
                count = field_text.count(kw)
                score += count * 3.0
    
    # 歌诀 + 出处 (+2)
    gejue = formula.get("歌诀", "")
    chuchu = formula.get("出处", "")
    for field_text in [gejue, chuchu]:
        if field_text:
            for kw in keywords:
                count = field_text.count(kw)
                score += count * 2.0
    
    # 其他字段 (+1)
    other_fields = ["分类", "运用", "配伍特点", "加减化裁", "化裁方之间的鉴别",
                    "重要文献摘要", "用法用量", "使用注意", "趣味记忆", "注意事项",
                    "各家论述", "方解-功效", "方解-主治"]
    for field in other_fields:
        val = formula.get(field, "")
        if val:
            for kw in keywords:
                count = val.count(kw)
                score += count * 1.0
    
    return round(score, 1)


def score_herb(herb, keywords):
    """
    对药材进行体质关键字评分
    名称 +5, 简介 +3, 功效作用 +3, 性味归经 +2, 临床应用 +2, 其他 +1
    """
    score = 0.0
    
    # 名称 (+5)
    name = herb.get("名称", "")
    for kw in keywords:
        if kw in name:
            score += 5.0
    
    # 简介 (+3)
    intro = herb.get("简介", "")
    if intro:
        for kw in keywords:
            count = intro.count(kw)
            score += count * 3.0
    
    # 功效作用 (+3) - 嵌套对象
    effect = herb.get("功效作用", {})
    if isinstance(effect, dict):
        effect_text = " ".join(str(v) for v in effect.values())
    elif isinstance(effect, str):
        effect_text = effect
    else:
        effect_text = ""
    if effect_text:
        for kw in keywords:
            count = effect_text.count(kw)
            score += count * 3.0
    
    # 性味归经 (+2)
    xingwei = herb.get("性味归经", "")
    if xingwei:
        for kw in keywords:
            count = xingwei.count(kw)
            score += count * 2.0
    
    # 临床应用 (+2)
    clinical = herb.get("临床应用", {})
    if isinstance(clinical, dict):
        clinical_text = " ".join(str(v) for v in clinical.values())
    elif isinstance(clinical, str):
        clinical_text = clinical
    else:
        clinical_text = ""
    if clinical_text:
        for kw in keywords:
            count = clinical_text.count(kw)
            score += count * 2.0
    
    # 其他字段 (+1)
    other_fields = ["别名", "中文名称", "拉丁文名", "道地产区", "加工炮制",
                    "药材鉴别", "保存方法", "植物学信息", "动物学信息",
                    "矿物学信息", "毒性", "相关方剂", "医保类型"]
    for field in other_fields:
        val = herb.get(field, "")
        if isinstance(val, str) and val:
            for kw in keywords:
                count = val.count(kw)
                score += count * 1.0
        elif isinstance(val, dict):
            val_text = " ".join(str(v) for v in val.values())
            if val_text:
                for kw in keywords:
                    count = val_text.count(kw)
                    score += count * 1.0
    
    return round(score, 1)


def score_xuewei(xuewei, keywords):
    """
    对穴位进行体质关键字评分
    名称 +5, 主治 +3, 详细主治 +3, 功能 +2, 其他 +1
    """
    score = 0.0
    
    # 名称 (+5)
    name = xuewei.get("名称", "")
    for kw in keywords:
        if kw in name:
            score += 5.0
    
    # 主治 (+3)
    zhuzhi = xuewei.get("主治", "")
    if zhuzhi:
        for kw in keywords:
            count = zhuzhi.count(kw)
            score += count * 3.0
    
    # 详细主治 (+3)
    detail = xuewei.get("详细主治", "")
    if detail:
        for kw in keywords:
            count = detail.count(kw)
            score += count * 3.0
    
    # 功能 (+2)
    func = xuewei.get("功能", "") or xuewei.get("功能作用", "")
    if func:
        for kw in keywords:
            count = func.count(kw)
            score += count * 2.0
    
    # 其他字段 (+1)
    other_fields = ["简介", "隶属", "位置", "定位", "解剖", "详细操作",
                    "临床运用", "主要配伍", "配伍", "附注", "相关论述",
                    "出处", "功能作用"]
    for field in other_fields:
        val = xuewei.get(field, "")
        if isinstance(val, str) and val:
            for kw in keywords:
                count = val.count(kw)
                score += count * 1.0
    
    return round(score, 1)


# ============================================================
# 5. 主挖掘流程
# ============================================================
print("[4/6] 执行方剂/药材/穴位评分挖掘...")

# 结果容器
result = {
    "体质-方剂": {},
    "体质-药材": {},
    "体质-穴位": {},
    "体质-药材分类统计": {},
    "体质-核心药对": {},
    "体质-穴位归经统计": {},
    "统计摘要": {}
}

# ---- 5A. 方剂挖掘 ----
print("  → 方剂评分...")
for const_name in const_names:
    keywords = const_info[const_name]["keywords"]
    
    scored = []
    for f in fangji_list:
        s = score_formula(f, keywords)
        if s >= 3.0:
            herbs = extract_herbs_from_formula(f)
            scored.append({
                "名称": f.get("名称", ""),
                "得分": s,
                "药材": herbs
            })
    
    # 排序取TOP20
    scored.sort(key=lambda x: (-x["得分"], x["名称"]))
    top20 = scored[:20]
    result["体质-方剂"][const_name] = top20
    print(f"    {const_name}: {len(scored)} 个通过阈值, TOP20已选取")

# ---- 5B. 药材挖掘 ----
print("  → 药材评分...")
for const_name in const_names:
    keywords = const_info[const_name]["keywords"]
    
    scored = []
    for h in yaocai_list:
        s = score_herb(h, keywords)
        if s >= 3.0:
            # 分类：使用 药材分类 字段
            classification = h.get("药材分类", "其他")
            xingwei = h.get("性味归经", "")
            scored.append({
                "名称": h.get("名称", ""),
                "得分": s,
                "分类": classification,
                "性味归经": xingwei
            })
    
    scored.sort(key=lambda x: (-x["得分"], x["名称"]))
    top30 = scored[:30]
    result["体质-药材"][const_name] = top30
    
    # 药材分类统计
    class_counter = Counter()
    for item in top30:
        class_counter[item["分类"]] += 1
    result["体质-药材分类统计"][const_name] = dict(class_counter.most_common())
    
    # 核心药对 (TOP30药材两两组合)
    top_names = [item["名称"] for item in top30]
    pairs = []
    for i in range(len(top_names)):
        for j in range(i+1, len(top_names)):
            a, b = top_names[i], top_names[j]
            # 统计共现次数 = 同时在多少方剂中出现
            co_count = 0
            for f in fangji_list:
                herbs = extract_herbs_from_formula(f)
                if a in herbs and b in herbs:
                    co_count += 1
            if co_count > 0:
                pairs.append([a, b, co_count])
    # 按共现数降序排序
    pairs.sort(key=lambda x: -x[2])
    result["体质-核心药对"][const_name] = pairs[:30]  # 取TOP30药对
    
    print(f"    {const_name}: {len(scored)} 个通过阈值, TOP30选取, {len(pairs)} 个药对")

# ---- 5C. 穴位挖掘 ----
print("  → 穴位评分...")
for const_name in const_names:
    keywords = const_info[const_name]["keywords"]
    
    scored = []
    for x in xuewei_list:
        s = score_xuewei(x, keywords)
        if s >= 3.0:
            scored.append({
                "名称": x.get("名称", ""),
                "得分": s,
                "隶属": x.get("隶属", ""),
                "主治": x.get("主治", "")
            })
    
    scored.sort(key=lambda x: (-x["得分"], x["名称"]))
    top20 = scored[:20]
    result["体质-穴位"][const_name] = top20
    
    # 穴位归经统计
    meridian_counter = Counter()
    for item in top20:
        meridian_counter[item["隶属"]] += 1
    result["体质-穴位归经统计"][const_name] = dict(meridian_counter.most_common())
    
    print(f"    {const_name}: {len(scored)} 个通过阈值, TOP20选取")


# ---- 5D. 统计摘要 ----
print("  → 生成统计摘要...")
summary = {}
for const_name in const_names:
    summary[const_name] = {
        "方剂数": len(result["体质-方剂"].get(const_name, [])),
        "药材数": len(result["体质-药材"].get(const_name, [])),
        "穴位数": len(result["体质-穴位"].get(const_name, [])),
        "药材分类数": len(result["体质-药材分类统计"].get(const_name, {})),
        "核心药对数": len(result["体质-核心药对"].get(const_name, [])),
        "穴位归经数": len(result["体质-穴位归经统计"].get(const_name, {}))
    }
result["统计摘要"] = summary

# ============================================================
# 6. 输出 JSON
# ============================================================
print("[5/6] 写入 JSON...")
with open(OUT_JSON, "w", encoding="utf-8") as f:
    json.dump(result, f, ensure_ascii=False, indent=2)
print(f"  ✓ 已写入: {OUT_JSON}")


# ============================================================
# 7. 输出 MD 报告 (追加方式)
# ============================================================
print("[6/6] 写入 MD 报告...")

def generate_md_section(const_name, top_formulas, top_herbs, herb_class_stats,
                        core_pairs, top_xuewei, meridian_stats):
    """生成一种体质的MD报告节"""
    lines = []
    lines.append(f"\n### {const_name}\n")
    
    # --- 方剂 ---
    lines.append("#### ① 体质-方剂 (TOP20)\n")
    lines.append("| 排名 | 方剂名称 | 匹配得分 | 所含药材 |")
    lines.append("|------|----------|----------|----------|")
    for i, item in enumerate(top_formulas, 1):
        herbs_str = "、".join(item["药材"][:8]) if item["药材"] else "—"
        if len(item["药材"]) > 8:
            herbs_str += "…"
        lines.append(f"| {i} | {item['名称']} | {item['得分']} | {herbs_str} |")
    
    # --- 药材 ---
    lines.append("\n#### ② 体质-药材 (TOP30)\n")
    lines.append("| 排名 | 药材名称 | 匹配得分 | 药材分类 | 性味归经 |")
    lines.append("|------|----------|----------|----------|----------|")
    for i, item in enumerate(top_herbs, 1):
        lines.append(f"| {i} | {item['名称']} | {item['得分']} | {item['分类']} | {item['性味归经']} |")
    
    # 药材分类统计
    lines.append("\n**药材分类统计**\n")
    lines.append("| 分类 | 数量 |")
    lines.append("|------|------|")
    for cls, cnt in herb_class_stats.items():
        lines.append(f"| {cls} | {cnt} |")
    
    # --- 核心药对 ---
    lines.append("\n**核心药对 (TOP30)**\n")
    lines.append("| 排名 | 药对 | 共现次数 |")
    lines.append("|------|------|----------|")
    for i, pair in enumerate(core_pairs[:15], 1):  # 显示前15
        lines.append(f"| {i} | {pair[0]} + {pair[1]} | {pair[2]} |")
    
    # --- 穴位 ---
    lines.append("\n#### ③ 体质-穴位 (TOP20)\n")
    lines.append("| 排名 | 穴位名称 | 匹配得分 | 隶属经脉 | 主治 |")
    lines.append("|------|----------|----------|----------|------|")
    for i, item in enumerate(top_xuewei, 1):
        zhuzhi_short = item['主治'][:40] + "…" if len(item['主治']) > 40 else item['主治']
        lines.append(f"| {i} | {item['名称']} | {item['得分']} | {item['隶属']} | {zhuzhi_short} |")
    
    # 穴位归经统计
    lines.append("\n**穴位归经统计**\n")
    lines.append("| 经脉 | 数量 |")
    lines.append("|------|------|")
    for mer, cnt in meridian_stats.items():
        lines.append(f"| {mer} | {cnt} |")
    
    lines.append("\n---\n")
    return "\n".join(lines)


# 构造MD内容
md_sections = []
md_sections.append("# 体质数据挖掘报告\n")
md_sections.append("## 一、疾病-症状关联分析（已有）\n\n*此部分为原有内容，此处省略*  \n")

md_sections.append("\n## 二、体质-方剂挖掘\n")
for const_name in const_names:
    lines = []
    top_formulas = result["体质-方剂"].get(const_name, [])
    lines.append(f"\n### {const_name}\n")
    lines.append("| 排名 | 方剂名称 | 匹配得分 | 所含药材 |")
    lines.append("|------|----------|----------|----------|")
    for i, item in enumerate(top_formulas, 1):
        herbs_str = "、".join(item["药材"][:8]) if item["药材"] else "—"
        if len(item["药材"]) > 8:
            herbs_str += "…"
        lines.append(f"| {i} | {item['名称']} | {item['得分']} | {herbs_str} |")
    md_sections.append("\n".join(lines))

md_sections.append("\n## 三、体质-药材挖掘\n")
for const_name in const_names:
    lines = []
    top_herbs = result["体质-药材"].get(const_name, [])
    herb_class_stats = result["体质-药材分类统计"].get(const_name, {})
    core_pairs = result["体质-核心药对"].get(const_name, [])
    
    lines.append(f"\n### {const_name}\n")
    lines.append("**TOP30药材**\n")
    lines.append("| 排名 | 药材名称 | 匹配得分 | 药材分类 | 性味归经 |")
    lines.append("|------|----------|----------|----------|----------|")
    for i, item in enumerate(top_herbs, 1):
        lines.append(f"| {i} | {item['名称']} | {item['得分']} | {item['分类']} | {item['性味归经']} |")
    
    lines.append("\n**药材分类统计**\n")
    lines.append("| 分类 | 数量 |")
    lines.append("|------|------|")
    for cls, cnt in herb_class_stats.items():
        lines.append(f"| {cls} | {cnt} |")
    
    lines.append("\n**核心药对 (TOP15)**\n")
    lines.append("| 排名 | 药对 | 共现次数 |")
    lines.append("|------|------|----------|")
    for i, pair in enumerate(core_pairs[:15], 1):
        lines.append(f"| {i} | {pair[0]} + {pair[1]} | {pair[2]} |")
    
    md_sections.append("\n".join(lines))

md_sections.append("\n## 四、体质-穴位挖掘\n")
for const_name in const_names:
    lines = []
    top_xuewei = result["体质-穴位"].get(const_name, [])
    meridian_stats = result["体质-穴位归经统计"].get(const_name, {})
    
    lines.append(f"\n### {const_name}\n")
    lines.append("**TOP20穴位**\n")
    lines.append("| 排名 | 穴位名称 | 匹配得分 | 隶属经脉 | 主治 |")
    lines.append("|------|----------|----------|----------|------|")
    for i, item in enumerate(top_xuewei, 1):
        zhuzhi_short = item['主治'][:40] + "…" if len(item['主治']) > 40 else item['主治']
        lines.append(f"| {i} | {item['名称']} | {item['得分']} | {item['隶属']} | {zhuzhi_short} |")
    
    lines.append("\n**穴位归经统计**\n")
    lines.append("| 经脉 | 数量 |")
    lines.append("|------|------|")
    for mer, cnt in meridian_stats.items():
        lines.append(f"| {mer} | {cnt} |")
    
    md_sections.append("\n".join(lines))

# 写入MD
with open(OUT_MD, "w", encoding="utf-8") as f:
    f.write("\n".join(md_sections))
print(f"  ✓ 已写入: {OUT_MD}")

# ============================================================
# 8. 验证
# ============================================================
print("\n" + "="*60)
print("验证结果")
print("="*60)

# 验证JSON
with open(OUT_JSON, "r", encoding="utf-8") as f:
    v = json.load(f)
print(f"\n✅ JSON 验证通过")
print(f"   - 体质-方剂: {len(v['体质-方剂'])} 种体质")
print(f"   - 体质-药材: {len(v['体质-药材'])} 种体质")
print(f"   - 体质-穴位: {len(v['体质-穴位'])} 种体质")
print(f"   - 体质-药材分类统计: {len(v['体质-药材分类统计'])} 种体质")
print(f"   - 体质-核心药对: {len(v['体质-核心药对'])} 种体质")
print(f"   - 体质-穴位归经统计: {len(v['体质-穴位归经统计'])} 种体质")

# 检查每种体质都有数据
for cn in const_names:
    f_count = len(v["体质-方剂"].get(cn, []))
    h_count = len(v["体质-药材"].get(cn, []))
    x_count = len(v["体质-穴位"].get(cn, []))
    print(f"   {cn}: 方剂={f_count}, 药材={h_count}, 穴位={x_count}")

# 验证MD
md_size = os.path.getsize(OUT_MD)
print(f"\n✅ MD 验证通过 ({md_size} bytes)")
print(f"\n输出文件:")
print(f"   1. {OUT_JSON}")
print(f"   2. {OUT_MD}")
print("\n完成!")