cfc/docs/参考资料/dan_reports/delete_duplicate_a1.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
检查报告中所有A1_开头的文件，如果同目录中有内容完全相同的文件，则删掉这个A1_开头的文件
"""

import os
import hashlib
from pathlib import Path

def file_hash(filepath):
    """计算文件 SHA256 哈希"""
    h = hashlib.sha256()
    with open(filepath, 'rb') as f:
        for chunk in iter(lambda: f.read(65536), b''):
            h.update(chunk)
    return h.hexdigest()

def main():
    # 自动计算项目根目录 (scripts/reports/ → 项目根)
    report_dir = Path(__file__).parent.parent.parent / "报告"
    
    # 找出所有 A1_ 开头的文件
    a1_files = list(report_dir.glob("A1_*.pdf"))
    print(f"找到 {len(a1_files)} 个 A1_ 开头的文件")
    
    # 计算所有文件的哈希
    all_files = list(report_dir.glob("*.pdf"))
    hash_map = {}
    
    for f in all_files:
        h = file_hash(str(f))
        if h not in hash_map:
            hash_map[h] = []
        hash_map[h].append(f)
    
    # 找出重复的文件
    deleted_count = 0
    for h, files in hash_map.items():
        if len(files) > 1:
            a1_dups = [f for f in files if f.name.startswith("A1_")]
            non_a1 = [f for f in files if not f.name.startswith("A1_")]
            
            if a1_dups and non_a1:
                for f in a1_dups:
                    try:
                        f.unlink()
                        print(f"[DELETED] {f.name} (与 {non_a1[0].name} 内容相同)")
                        deleted_count += 1
                    except Exception as e:
                        print(f"[FAIL] {f.name}: {e}")
            elif len(a1_dups) > 1:
                keep = a1_dups[0]
                for f in a1_dups[1:]:
                    try:
                        f.unlink()
                        print(f"[DELETED] {f.name} (与 {keep.name} 内容相同)")
                        deleted_count += 1
                    except Exception as e:
                        print(f"[FAIL] {f.name}: {e}")
    print(f"\n总共删除了 {deleted_count} 个重复的 A1_ 文件")

if __name__ == "__main__":
    main()