how/build_note_to_all_index.py

"""
构建帖子ID到点和分类的完整映射

从人设.json和what解构结果中提取每个帖子的：
1. 所属的灵感分类、目的分类、关键点分类（来自人设.json）
2. 具体的灵感点、目的点、关键点（来自what解构结果）
3. 帖子详情

使用方式:
    python build_note_to_all_index.py --persona-dir data/阿里多多酱/out/人设_1110
"""
import os
import json
import argparse
from typing import Dict, List, Any
from glob import glob
from script.detail import get_xiaohongshu_detail


def build_category_mapping(persona_data: Dict[str, Any]) -> Dict[str, List[str]]:
    """构建帖子ID到分类的映射

    Args:
        persona_data: 人设数据

    Returns:
        {note_id: [分类名称列表]}
    """
    note_to_categories = {}

    # 遍历所有视角
    for perspective in persona_data.get("灵感点列表", []):
        perspective_name = perspective.get("视角名称", "")

        # 遍历一级分类
        for category_l1 in perspective.get("模式列表", []):
            category_l1_name = category_l1.get("分类名称", "")

            # 遍历二级分类
            for category_l2 in category_l1.get("二级细分", []):
                category_l2_name = category_l2.get("分类名称", "")
                category_l2_def = category_l2.get("分类定义", "")
                note_ids = category_l2.get("帖子ID列表", [])

                # 去重帖子ID
                unique_note_ids = list(dict.fromkeys(note_ids))

                # 为每个帖子添加分类信息
                for note_id in unique_note_ids:
                    if note_id not in note_to_categories:
                        note_to_categories[note_id] = []

                    note_to_categories[note_id].append({
                        "分类类型": "灵感分类",
                        "视角名称": perspective_name,
                        "一级分类": category_l1_name,
                        "二级分类": category_l2_name,
                        "分类定义": category_l2_def
                    })

    return note_to_categories


def extract_points_from_what(what_dir: str) -> Dict[str, Dict[str, Any]]:
    """从what解构结果提取所有点

    Args:
        what_dir: what解构结果目录

    Returns:
        {note_id: {灵感点列表, 目的点列表, 关键点列表}}
    """
    note_to_points = {}

    # 读取所有what解构文件
    what_files = glob(os.path.join(what_dir, "*_with_history_*.json"))

    for what_file in what_files:
        # 从文件名提取note_id
        filename = os.path.basename(what_file)
        note_id = filename.split("_with_history_")[0]

        with open(what_file, 'r', encoding='utf-8') as f:
            data = json.load(f)

        three_points = data.get("三点解构", {})

        # 提取灵感点
        inspiration_points = []
        inspiration_data = three_points.get("灵感点", {})

        for field in ["全新内容", "共性差异", "共性内容"]:
            items = inspiration_data.get(field, [])
            for item in items:
                point = item.get("灵感点", "")
                if point:
                    inspiration_points.append({
                        "灵感点": point,
                        "来源字段": field,
                        "维度": item.get("维度", ""),
                        "描述": item.get("描述", "")
                    })

        # 提取目的点
        purpose_points = []
        purpose_data = three_points.get("目的点", {})

        # 主目的
        main_purpose = purpose_data.get("main_purpose", {})
        if main_purpose:
            point = main_purpose.get("目的点", "")
            if point:
                purpose_points.append({
                    "目的点": point,
                    "类型": "主目的",
                    "维度": main_purpose.get("维度", ""),
                    "描述": main_purpose.get("描述", "")
                })

        # 次要目的
        secondary_purposes = purpose_data.get("secondary_purposes", [])
        for sec_purpose in secondary_purposes:
            point = sec_purpose.get("目的点", "")
            if point:
                purpose_points.append({
                    "目的点": point,
                    "类型": "次要目的",
                    "维度": sec_purpose.get("维度", ""),
                    "描述": sec_purpose.get("描述", "")
                })

        # 提取关键点
        key_points = []
        keypoint_data = three_points.get("关键点", {})
        kp_list = keypoint_data.get("key_points", [])

        for kp in kp_list:
            point = kp.get("关键点", "")
            if point:
                key_points.append({
                    "关键点": point,
                    "维度大类": kp.get("维度大类", ""),
                    "维度细分": kp.get("维度细分", ""),
                    "描述": kp.get("描述", "")
                })

        note_to_points[note_id] = {
            "灵感点列表": inspiration_points,
            "目的点列表": purpose_points,
            "关键点列表": key_points
        }

    return note_to_points


def build_note_to_all_index(
    persona_dir: str,
    fetch_details: bool = True
) -> Dict[str, Any]:
    """构建帖子ID到点和分类的完整映射

    Args:
        persona_dir: 人设目录路径
        fetch_details: 是否获取帖子详情

    Returns:
        完整的映射索引
    """
    persona_file = os.path.join(persona_dir, "人设.json")
    what_dir = os.path.join(persona_dir, "what解构结果")

    print(f"{'=' * 80}")
    print(f"构建帖子ID到点和分类的完整映射")
    print(f"{'=' * 80}")
    print(f"人设文件: {persona_file}")
    print(f"解构目录: {what_dir}\n")

    # 读取人设数据
    with open(persona_file, 'r', encoding='utf-8') as f:
        persona_data = json.load(f)

    # 构建分类映射
    print(f"{'─' * 80}")
    print(f"1. 提取分类信息（来自人设.json）")
    print(f"{'─' * 80}\n")
    note_to_categories = build_category_mapping(persona_data)
    print(f"✓ 从人设.json中提取了 {len(note_to_categories)} 个帖子的分类信息\n")

    # 提取点信息
    print(f"{'─' * 80}")
    print(f"2. 提取点信息（来自what解构结果）")
    print(f"{'─' * 80}\n")
    note_to_points = extract_points_from_what(what_dir)
    print(f"✓ 从what解构结果中提取了 {len(note_to_points)} 个帖子的点信息\n")

    # 合并所有帖子ID
    all_note_ids = set(note_to_categories.keys()) | set(note_to_points.keys())
    print(f"✓ 共有 {len(all_note_ids)} 个唯一帖子\n")

    # 构建完整映射
    note_index = {}

    for note_id in all_note_ids:
        note_index[note_id] = {
            "帖子ID": note_id,
            "所属分类": note_to_categories.get(note_id, []),
            "灵感点列表": note_to_points.get(note_id, {}).get("灵感点列表", []),
            "目的点列表": note_to_points.get(note_id, {}).get("目的点列表", []),
            "关键点列表": note_to_points.get(note_id, {}).get("关键点列表", [])
        }

    # 获取帖子详情
    if fetch_details:
        print(f"{'=' * 80}")
        print(f"开始获取帖子详情...")
        print(f"{'=' * 80}\n")

        for i, note_id in enumerate(sorted(all_note_ids), 1):
            try:
                print(f"[{i}/{len(all_note_ids)}] 获取详情: {note_id}")
                detail = get_xiaohongshu_detail(note_id)
                note_index[note_id]["帖子详情"] = detail
            except Exception as e:
                print(f"  ⚠️  获取失败: {e}")
                note_index[note_id]["帖子详情"] = {
                    "channel_content_id": note_id,
                    "error": str(e)
                }

        print(f"\n✓ 帖子详情获取完成\n")

    return note_index


def save_index(index_data: Dict[str, Any], output_file: str):
    """保存索引到文件

    Args:
        index_data: 索引数据
        output_file: 输出文件路径
    """
    output_dir = os.path.dirname(output_file)
    if output_dir:
        os.makedirs(output_dir, exist_ok=True)

    with open(output_file, 'w', encoding='utf-8') as f:
        json.dump(index_data, f, ensure_ascii=False, indent=2)

    print(f"✓ 索引已保存: {output_file}")


def print_statistics(index_data: Dict[str, Any]):
    """打印统计信息

    Args:
        index_data: 完整的索引数据
    """
    print(f"\n{'=' * 80}")
    print(f"索引统计信息")
    print(f"{'=' * 80}\n")

    total_notes = len(index_data)
    print(f"帖子总数: {total_notes}")

    # 统计有分类的帖子
    notes_with_categories = sum(1 for v in index_data.values() if v.get("所属分类"))
    print(f"有分类信息的帖子: {notes_with_categories}")

    # 统计有点信息的帖子
    notes_with_inspiration = sum(1 for v in index_data.values() if v.get("灵感点列表"))
    notes_with_purpose = sum(1 for v in index_data.values() if v.get("目的点列表"))
    notes_with_keypoint = sum(1 for v in index_data.values() if v.get("关键点列表"))

    print(f"有灵感点信息的帖子: {notes_with_inspiration}")
    print(f"有目的点信息的帖子: {notes_with_purpose}")
    print(f"有关键点信息的帖子: {notes_with_keypoint}")

    # 统计平均数量
    total_categories = sum(len(v.get("所属分类", [])) for v in index_data.values())
    total_inspiration = sum(len(v.get("灵感点列表", [])) for v in index_data.values())
    total_purpose = sum(len(v.get("目的点列表", [])) for v in index_data.values())
    total_keypoint = sum(len(v.get("关键点列表", [])) for v in index_data.values())

    if total_notes > 0:
        print(f"\n平均每个帖子:")
        print(f"  分类数: {total_categories / total_notes:.1f}")
        print(f"  灵感点数: {total_inspiration / total_notes:.1f}")
        print(f"  目的点数: {total_purpose / total_notes:.1f}")
        print(f"  关键点数: {total_keypoint / total_notes:.1f}")


def main():
    """主函数"""
    parser = argparse.ArgumentParser(
        description="构建帖子ID到点和分类的完整映射",
        formatter_class=argparse.RawDescriptionHelpFormatter,
        epilog="""
使用示例:
  # 基本使用
  python build_note_to_all_index.py --persona-dir data/阿里多多酱/out/人设_1110

  # 只构建索引，不获取帖子详情
  python build_note_to_all_index.py --persona-dir data/阿里多多酱/out/人设_1110 --no-details

  # 自定义输出文件
  python build_note_to_all_index.py --persona-dir data/阿里多多酱/out/人设_1110 --output custom.json
        """
    )

    parser.add_argument(
        "--persona-dir",
        required=True,
        help="人设目录路径（包含人设.json和what解构结果/的目录）"
    )

    parser.add_argument(
        "--output",
        default=None,
        help="输出文件路径（默认: {persona_dir}/帖子到分类和点映射.json）"
    )

    parser.add_argument(
        "--no-details",
        action="store_true",
        help="不获取帖子详情（只构建索引结构）"
    )

    args = parser.parse_args()

    persona_dir = args.persona_dir
    fetch_details = not args.no_details

    # 检查必要文件
    persona_file = os.path.join(persona_dir, "人设.json")
    what_dir = os.path.join(persona_dir, "what解构结果")

    if not os.path.exists(persona_file):
        print(f"❌ 错误: 找不到人设文件: {persona_file}")
        return

    if not os.path.exists(what_dir):
        print(f"❌ 错误: 找不到what解构目录: {what_dir}")
        return

    # 构建索引
    index_data = build_note_to_all_index(persona_dir, fetch_details=fetch_details)

    # 确定输出文件路径
    if args.output:
        output_file = args.output
    else:
        output_file = os.path.join(persona_dir, "帖子到分类和点映射.json")

    # 保存索引
    save_index(index_data, output_file)

    # 打印统计信息
    print_statistics(index_data)


if __name__ == "__main__":
    main()