cfc/docs/参考资料/dan_reports/update_materials.py

# -*- coding: utf-8 -*-
"""
自动化更新脚本 - 素材库全量更新流水线

功能: 从原始PDF报告更新素材库的三个核心数据文件
流程:
  1. 分类重命名报告 (process_all_pdfs.py)
  2. 全类型数据提取 (extract_all_types.py)
  3. 全类型学生合并 (merge_all_types.py)
  4. 删除重复A1报告 (delete_duplicate_a1.py)

用法:
  python scripts/reports/update_materials.py          # 从 scripts 目录运行
  cd 项目根目录 && python scripts/reports/update_materials.py  # 从根目录运行
"""
import os
import sys
import subprocess

# 脚本所在目录 = scripts/reports/
SCRIPTS_DIR = os.path.dirname(os.path.abspath(__file__))
PROJECT_DIR = os.path.dirname(os.path.dirname(SCRIPTS_DIR))


def run_script(script_name, label):
    """运行 scripts/reports/ 中的脚本"""
    script_path = os.path.join(SCRIPTS_DIR, script_name)
    print(f"\n{'=' * 50}")
    print(f"[{label}] 运行: {script_name}")
    print(f"{'=' * 50}")

    result = subprocess.run(
        [sys.executable, script_path],
        cwd=PROJECT_DIR,
        capture_output=False
    )

    if result.returncode != 0:
        print(f"  [FAIL] [{label}] 失败 (exit code={result.returncode})")
        return False
    print(f"  [OK] [{label}] 完成")
    return True


def main():
    print("=" * 60)
    print("  素材库全量更新流水线")
    print("=" * 60)
    print(f"  项目根目录: {PROJECT_DIR}")
    print(f"  脚本目录:   {SCRIPTS_DIR}")

    steps = [
        ("process_all_pdfs.py",       "1/4 报告分类重命名"),
        ("extract_all_types.py",      "2/4 全类型数据提取"),
        ("merge_all_types.py",        "3/4 全类型学生合并"),
        ("delete_duplicate_a1.py",    "4/4 清理重复A1报告"),
    ]

    for script, label in steps:
        if not run_script(script, label):
            print(f"\n  ❌ 流水线在 [{label}] 中断")
            sys.exit(1)

    print(f"\n{'=' * 60}")
    print("  [OK] 素材库更新完成!")
    print(f"{'=' * 60}")
    print("\n生成的文件:")
    print("  - 素材库/测评数据_优化提取.csv")
    print("  - 素材库/学生汇总数据.csv")
    print("\n提示: 案例库.md 需要手动根据新增数据更新案例")


if __name__ == "__main__":
    main()