#!/usr/bin/env python3
"""
体质-药膳推荐体系构建脚本
多因子评分模型 + 功效分类统计 + 来源分析 + 共享分析
"""

import json
import os
import glob
import re
from collections import defaultdict, Counter

# ===== 1. 加载数据 =====
BASE_DIR = "/home/songyi/Documents/ai_agent_scraper_study/data/大医网"

# 加载9种体质详细数据
with open(os.path.join(BASE_DIR, "02_加工数据/中医体质/九种体质详细数据.json"), "r", encoding="utf-8") as f:
    constitutions_data = json.load(f)

# 构建体质字典
constitutions = {}
for c in constitutions_data:
    name = c["名称"]
    constitutions[name] = c

print(f"加载体质数据: {len(constitutions)} 种")
for name in constitutions:
    c = constitutions[name]
    print(f"  {name}: 推荐药膳={c.get('推荐药膳', [])}")

# 加载所有药膳文件
diet_dir = os.path.join(BASE_DIR, "01_来源数据/药膳食疗")
diet_files = glob.glob(os.path.join(diet_dir, "*.json"))
print(f"\n药膳食疗文件数: {len(diet_files)}")

dietary_list = []
for fpath in sorted(diet_files):
    try:
        with open(fpath, "r", encoding="utf-8") as f:
            item = json.load(f)
        dietary_list.append(item)
    except Exception as e:
        print(f"  加载失败: {os.path.basename(fpath)}: {e}")

print(f"成功加载药膳食疗: {len(dietary_list)} 条")

# 加载已有交叉关联
cross_assoc_path = os.path.join(BASE_DIR, "02_加工数据/中医体质/体质-大医网交叉关联.json")
if os.path.exists(cross_assoc_path):
    with open(cross_assoc_path, "r", encoding="utf-8") as f:
        cross_data = json.load(f)
    print(f"加载已有交叉关联, keys: {list(cross_data.keys())}")
else:
    cross_data = {}
    print("未找到已有交叉关联文件")

# ===== 2. 定义体质相关配置 =====

# 经典文献列表（来源字段含以下文献名视为经典文献）
CLASSIC_LITERATURE = [
    "伤寒论", "金匮要略", "黄帝内经", "本草纲目", "食疗本草",
    "饮膳正要", "食医心鉴", "太平圣惠方", "圣济总录",
    "中国药膳大辞典", "中国药膳学", "中医药膳学", "药膳宝典",
    "药膳学", "千金要方", "千金翼方", "外台秘要",
    "肘后备急方", "普济方", "中医食疗学",
    "季节养生药膳指南"
]

# 九种体质的配置（关联关键字、推荐食材、推荐药膳、调理关键词）
CONSTITUTION_CONFIG = {
    "气虚质": {
        "keywords": ["气虚", "气短", "乏力", "自汗", "懒言", "神疲", "补气", "益气", "培元", "固本"],
        "ingredients": ["山药", "大枣", "红枣", "黄芪", "党参", "人参", "白术", "茯苓", "糯米", 
                       "粳米", "小米", "土豆", "香菇", "鸡肉", "牛肉", "鳝鱼", "泥鳅", "蜂蜜",
                       "黄豆", "扁豆", "豇豆", "南瓜", "胡萝卜", "桂圆", "龙眼"],
        "efficacy_keywords": ["补气", "益气", "健脾", "培元", "固本", "补中益气"],
        "type_name": "气虚"
    },
    "阳虚质": {
        "keywords": ["阳虚", "畏寒", "怕冷", "四肢不温", "寒凝", "温阳", "散寒", "壮阳", "肾阳", "脾阳"],
        "ingredients": ["羊肉", "牛肉", "韭菜", "生姜", "肉桂", "核桃", "栗子", "荔枝", "龙眼",
                       "茴香", "丁香", "花椒", "小茴香", "干姜", "当归", "附子", "狗肉"],
        "efficacy_keywords": ["温阳", "散寒", "壮阳", "温中", "暖胃", "温补脾肾", "补肾壮阳"],
        "type_name": "阳虚"
    },
    "阴虚质": {
        "keywords": ["阴虚", "口干", "咽干", "手足心热", "潮热", "盗汗", "滋阴", "降火", "生津", "润燥"],
        "ingredients": ["百合", "银耳", "莲子", "枸杞", "黑芝麻", "鸭肉", "甲鱼", "龟肉", "海参",
                       "牡蛎", "蜂蜜", "梨", "甘蔗", "枇杷", "桑葚", "黑木耳", "沙参", "玉竹",
                       "麦冬", "生地", "生地黄"],
        "efficacy_keywords": ["滋阴", "降火", "生津", "润燥", "养阴", "清热", "滋补肝肾"],
        "type_name": "阴虚"
    },
    "痰湿质": {
        "keywords": ["痰湿", "肥胖", "痰多", "胸闷", "苔腻", "健脾", "祛湿", "化痰", "降浊", "利水"],
        "ingredients": ["薏苡仁", "冬瓜", "白萝卜", "赤小豆", "茯苓", "荷叶", "山楂", "陈皮",
                       "燕麦", "荞麦", "海带", "紫菜", "生姜", "莱菔子"],
        "efficacy_keywords": ["祛湿", "化痰", "健脾", "利水", "降浊", "消食", "导滞", "除湿"],
        "type_name": "痰湿"
    },
    "湿热质": {
        "keywords": ["湿热", "口苦", "苔黄腻", "痤疮", "湿疹", "清热", "利湿", "解毒", "化浊", "泻火"],
        "ingredients": ["绿豆", "赤小豆", "薏苡仁", "冬瓜", "苦瓜", "黄瓜", "芹菜", "蒲公英",
                       "马齿苋", "菊花", "金银花", "莲藕", "茭白", "栀子"],
        "efficacy_keywords": ["清热", "利湿", "解毒", "化浊", "泻火", "凉血", "祛湿"],
        "type_name": "湿热"
    },
    "血瘀质": {
        "keywords": ["血瘀", "瘀血", "面色晦暗", "瘀斑", "刺痛", "活血", "化瘀", "行气", "通络", "消癥"],
        "ingredients": ["山楂", "黑豆", "黑木耳", "醋", "玫瑰花", "红糖", "桃仁", "油菜", "茄子",
                       "藕", "香菇", "海带", "川芎", "红花", "当归"],
        "efficacy_keywords": ["活血", "化瘀", "行气", "通络", "散瘀", "消癥", "止痛"],
        "type_name": "血瘀"
    },
    "气郁质": {
        "keywords": ["气郁", "抑郁", "焦虑", "胸闷", "胁痛", "疏肝", "解郁", "理气", "调中", "安神"],
        "ingredients": ["柑橘", "佛手", "玫瑰花", "小麦", "大麦", "荞麦", "香橼", "橙子", "柚",
                       "洋葱", "大蒜", "萝卜", "茴香", "柴胡", "薄荷", "合欢花", "陈皮", "柠檬"],
        "efficacy_keywords": ["疏肝", "解郁", "理气", "安神", "调中", "行气", "开郁"],
        "type_name": "气郁"
    },
    "特禀质": {
        "keywords": ["过敏", "哮喘", "荨麻疹", "鼻炎", "风团", "益气", "固表", "祛风", "抗敏", "特禀"],
        "ingredients": ["黄芪", "白术", "防风", "红枣", "蜂蜜", "山药", "人参", "灵芝", "薏苡仁",
                       "莲子", "糯米", "花生", "党参", "紫苏", "生姜"],
        "efficacy_keywords": ["益气", "固表", "祛风", "抗敏", "扶正", "补肺", "健脾"],
        "type_name": "特禀"
    },
    "平和质": {
        "keywords": ["平和", "平衡", "调和", "保健", "养生", "预防"],
        "ingredients": ["五谷杂粮", "蔬菜", "水果", "鱼肉", "蛋奶", "豆制品", "坚果", "绿茶",
                       "山药", "红枣", "枸杞", "茯苓"],
        "efficacy_keywords": ["平和", "调和", "保健", "养生", "平衡", "滋补"],
        "type_name": "平和"
    }
}

print("\n体质配置加载完成")

# ===== 3. 多因子评分模型 =====

def is_classic_literature(source):
    """判断是否来自经典文献"""
    if not source:
        return False
    for lit in CLASSIC_LITERATURE:
        if lit in source:
            return True
    return False

def text_contains_keywords(text, keywords):
    """检查文本是否包含任意关键字"""
    if not text:
        return False
    text_lower = text.lower()
    for kw in keywords:
        if kw in text:
            return True
    return False

def count_keyword_matches(text, keywords):
    """统计文本中匹配的关键字数量"""
    if not text:
        return 0
    count = 0
    for kw in keywords:
        if kw in text:
            count += 1
    return count

def score_dietary_for_constitution(diet_item, constitution_name):
    """
    多因子评分模型
    返回：(总分, 各因子详细得分)
    """
    cfg = CONSTITUTION_CONFIG[constitution_name]
    keywords = cfg["keywords"]
    ingredients = cfg["ingredients"]
    
    # 获取各字段
    efficacy = diet_item.get("功效", "") or ""
    intro = diet_item.get("简介", "") or ""
    name = diet_item.get("名称", "") or ""
    recipe = diet_item.get("配方", "") or ""  # HTML可能包含食材
    suitable_pop = diet_item.get("适宜人群", "") or ""
    source = diet_item.get("来源", "") or ""
    related = diet_item.get("相关配伍", "") or ""
    
    # 移除HTML标签
    recipe_clean = re.sub(r'<[^>]+>', '', recipe)
    suitable_clean = re.sub(r'<[^>]+>', '', suitable_pop)
    related_clean = re.sub(r'<[^>]+>', '', related)
    intro_clean = re.sub(r'<[^>]+>', '', intro)
    
    scores = {}
    
    # A) 功效字段含体质关键字 +4（高权重）
    score_efficacy = 0
    for kw in keywords:
        if kw in efficacy:
            score_efficacy += 4
    # 同时检查功效关键词
    for kw in cfg["efficacy_keywords"]:
        if kw in efficacy:
            score_efficacy += 4
    scores["功效匹配"] = score_efficacy
    
    # B) 简介/名称字段含体质关键字 +3
    score_intro_name = 0
    combined_intro_name = intro_clean + " " + name
    for kw in keywords:
        if kw in combined_intro_name:
            score_intro_name += 3
    for kw in cfg["efficacy_keywords"]:
        if kw in combined_intro_name:
            score_intro_name += 3
    scores["简介/名称匹配"] = score_intro_name
    
    # C) 配方字段含体质推荐食材 +2
    score_recipe = 0
    for ing in ingredients:
        if ing in recipe_clean:
            score_recipe += 2
    # 也检查相关配伍字段
    for ing in ingredients:
        if ing in related_clean:
            score_recipe += 1  # 配伍中匹配权重略低
    scores["配方食材匹配"] = score_recipe
    
    # D) 适宜人群字段含体质关键字 +3
    score_suitable = 0
    for kw in keywords:
        if kw in suitable_clean:
            score_suitable += 3
    for kw in cfg["efficacy_keywords"]:
        if kw in suitable_clean:
            score_suitable += 3
    scores["适宜人群匹配"] = score_suitable
    
    # E) 来源字段含经典文献 +1
    score_source = 1 if is_classic_literature(source) else 0
    scores["经典文献加分"] = score_source
    
    total = sum(scores.values())
    return total, scores


# ===== 4. 对每种体质评分 =====
print("\n开始多因子评分...")

constitution_order = ["气虚质", "阳虚质", "阴虚质", "痰湿质", "湿热质", "血瘀质", "气郁质", "特禀质", "平和质"]

# 存储结果
dietary_recommendations = {}
dietary_efficacy_stats = {}
all_shared_dietary = {}  # name -> list of constitution types

THRESHOLD = 4.0

for cname in constitution_order:
    scored_items = []
    for item in dietary_list:
        total, scores = score_dietary_for_constitution(item, cname)
        if total >= THRESHOLD:
            scored_items.append({
                "名称": item.get("名称", ""),
                "来源": item.get("来源", ""),
                "功效": item.get("功效", ""),
                "简介": item.get("简介", ""),
                "得分": total,
                "各因子得分": scores,
                "配方": item.get("配方", ""),
                "适宜人群": item.get("适宜人群", ""),
                "相关配伍": item.get("相关配伍", "")
            })
    
    # 按得分降序排列，取TOP30
    scored_items.sort(key=lambda x: (-x["得分"], x["名称"]))
    top_items = scored_items[:30]
    
    print(f"{cname}: 得分≥{THRESHOLD}的药膳数={len(scored_items)}, TOP3={[t['名称'] for t in top_items[:3]]}")
    
    # 记录共享信息
    for item in top_items:
        name = item["名称"]
        if name not in all_shared_dietary:
            all_shared_dietary[name] = {"体质": [], "功效": item["功效"], "来源": item["来源"]}
        all_shared_dietary[name]["体质"].append(cname)
    
    # 构建推荐列表（含共享标记）
    recommendations = []
    for item in top_items:
        name = item["名称"]
        total = item["得分"]
        source = item["来源"]
        efficacy = item["功效"]
        recommendations.append({
            "名称": name,
            "来源": source,
            "功效": efficacy,
            "得分": total,
            "是否共享": False,  # 后面更新
            "共享体质": []
        })
    
    dietary_recommendations[cname] = recommendations

# ===== 5. 更新共享信息 =====
# 找出跨体质药膳
shared_count = 0
cross_constitution_items = []
for name, info in all_shared_dietary.items():
    if len(info["体质"]) >= 2:
        shared_count += 1
        cross_constitution_items.append({
            "名称": name,
            "适用体质": info["体质"],
            "功效": info["功效"],
            "来源": info["来源"]
        })

# 更新推荐列表中的共享标记
for cname in constitution_order:
    for rec in dietary_recommendations[cname]:
        name = rec["名称"]
        if name in all_shared_dietary and len(all_shared_dietary[name]["体质"]) >= 2:
            rec["是否共享"] = True
            rec["共享体质"] = [t for t in all_shared_dietary[name]["体质"] if t != cname]

print(f"\n跨体质药膳数: {shared_count}")
for item in cross_constitution_items[:5]:
    print(f"  {item['名称']}: {item['适用体质']}")

# ===== 6. 功效分类统计 =====
print("\n开始功效分类统计...")

EFFICACY_KEYWORDS_MAP = {
    "补气": ["补气", "益气", "补中益气"],
    "健脾": ["健脾", "补脾", "益脾", "温脾"],
    "养血": ["养血", "补血", "活血养血"],
    "滋阴": ["滋阴", "养阴", "育阴"],
    "温阳": ["温阳", "壮阳", "补阳"],
    "散寒": ["散寒", "温中", "暖胃", "祛寒"],
    "清热": ["清热", "解毒", "泻火", "凉血"],
    "祛湿": ["祛湿", "利湿", "除湿", "化湿", "渗湿"],
    "化痰": ["化痰", "祛痰", "消痰"],
    "疏肝": ["疏肝", "解郁", "理气", "行气"],
    "安神": ["安神", "宁心", "养心"],
    "补肾": ["补肾", "益肾", "滋肾", "温肾"],
    "润肺": ["润肺", "补肺", "养肺"],
    "消食": ["消食", "导滞", "开胃", "健胃"],
    "生津": ["生津", "止渴", "润燥"],
    "活血": ["活血", "化瘀", "散瘀", "通络"],
    "固表": ["固表", "固涩", "止汗", "收敛"],
    "祛风": ["祛风", "疏风", "散风"],
    "利水": ["利水", "消肿", "利尿"],
    "补虚": ["补虚", "补益", "滋补", "扶正"]
}

for cname in constitution_order:
    top_items = dietary_recommendations[cname][:30]
    efficacy_stats = defaultdict(int)
    
    for item in top_items:
        efficacy_text = item["功效"]
        if not efficacy_text:
            continue
        # 统计功效关键词
        for category, keywords in EFFICACY_KEYWORDS_MAP.items():
            for kw in keywords:
                if kw in efficacy_text:
                    efficacy_stats[category] += 1
                    break  # 每个药膳每个分类只计1次
    
    dietary_efficacy_stats[cname] = dict(sorted(efficacy_stats.items(), key=lambda x: -x[1]))
    top_cats = list(dietary_efficacy_stats[cname].keys())[:5]
    print(f"{cname}: {dict(top_cats)}...")

# ===== 7. 来源分析 =====
print("\n开始来源分析...")
source_stats = defaultdict(int)
for cname in constitution_order:
    for rec in dietary_recommendations[cname]:
        source = rec["来源"]
        if source:
            # 简化来源名
            simple_source = source.strip()
            source_stats[simple_source] += 1

top_sources = sorted(source_stats.items(), key=lambda x: -x[1])[:20]
print("TOP来源:")
for s, c in top_sources:
    print(f"  {s}: {c}次")

# ===== 8. 构建完整JSON输出 =====
print("\n构建JSON输出...")

# 统计摘要
total_recommendations = sum(len(v) for v in dietary_recommendations.values())
total_unique = len(all_shared_dietary)

summary_stats = {
    "总药膳数": len(dietary_list),
    "体质类型数": len(constitution_order),
    "各体质推荐药膳数": {c: len(dietary_recommendations[c]) for c in constitution_order},
    "总推荐人次": total_recommendations,
    "去重推荐药膳数": total_unique,
    "跨体质共享药膳数": shared_count,
    "评分阈值": THRESHOLD,
    "评分模型因子": {
        "功效字段含体质关键字": "+4",
        "简介/名称字段含体质关键字": "+3",
        "配方字段含体质推荐食材": "+2",
        "适宜人群字段含体质关键字": "+3",
        "来源字段含经典文献": "+1"
    }
}

output_json = {
    "体质-药膳推荐": dietary_recommendations,
    "体质-药膳功效统计": dietary_efficacy_stats,
    "体质-药膳来源统计": dict(top_sources),
    "体质-药膳共享分析": {
        "数量": shared_count,
        "跨体质药膳": cross_constitution_items
    },
    "统计摘要": summary_stats
}

# 保存JSON
output_dir = os.path.join(BASE_DIR, "03_关联融合/交叉关联分析")
os.makedirs(output_dir, exist_ok=True)
output_path = os.path.join(output_dir, "体质-药膳推荐体系.json")
with open(output_path, "w", encoding="utf-8") as f:
    json.dump(output_json, f, ensure_ascii=False, indent=2)

print(f"\nJSON已保存: {output_path}")
print(f"文件大小: {os.path.getsize(output_path) / 1024:.1f} KB")

# ===== 9. 验证JSON完整性 =====
with open(output_path, "r", encoding="utf-8") as f:
    verify = json.load(f)
print(f"\n验证JSON:")
print(f"  体质-药膳推荐: {len(verify['体质-药膳推荐'])} 种体质")
for c in constitution_order:
    print(f"    {c}: {len(verify['体质-药膳推荐'][c])} 条推荐")
print(f"  体质-药膳功效统计: {len(verify['体质-药膳功效统计'])} 种")
print(f"  体质-药膳共享分析: {verify['体质-药膳共享分析']['数量']} 条共享")
print(f"  统计摘要: 总推荐={verify['统计摘要']['总推荐人次']}人次")

print("\n===== 药膳推荐体系构建完成 =====")