利用AI生成批量导出内核源码的脚本

最近用AI实现了一个脚本，用于将内核源码全部导出为txt文件，路径全部平坦化，而且支持过滤，下面是跟AI的对话：

https://yuanbao.tencent.com/bot/app/share/chat/GjdXiqdQaoVn

下面是最终生成的脚本，非常不错：

kernel_flatten.py

#!/usr/bin/env python3
"""
Linux内核源码导出工具（带分组功能）
支持按编号分组存储文件，解决大数量文件管理问题
"""

import os
import shutil
import argparse
import re
import sys
import math
from collections import OrderedDict

def sanitize_filename(path):
    """路径安全化：替换特殊字符为下划线"""
    return re.sub(r'[^\w\-_.]', '_', path)

class FilterRule:
    """过滤规则处理器"""
    def __init__(self, pattern, is_include, is_suffix=False):
        self.pattern = pattern
        self.is_include = is_include
        self.is_suffix = is_suffix
    
    def match(self, rel_path, is_dir=False):
        """匹配目录或后缀规则"""
        if self.is_suffix:
            # 后缀匹配（大小写不敏感）
            return rel_path.lower().endswith(self.pattern.lower())
        else:
            # 目录匹配（支持子目录递归）
            pattern = self.pattern.replace('\\', '/')
            target_path = rel_path.replace('\\', '/')
            return (target_path == pattern or 
                    target_path.startswith(pattern + '/')) if is_dir else pattern in target_path

def parse_filter_args(filter_args, exclude_args):
    """解析命令行过滤参数，生成优先级规则链"""
    rule_chain = OrderedDict()
    sequence = []
    
    # 处理包含规则(-f)
    if filter_args:
        for item in filter_args.split(','):
            item = item.strip()
            if not item: continue
            is_suffix = item.startswith('.')
            rule = FilterRule(item, True, is_suffix)
            key = f"include_{item}"
            rule_chain[key] = rule
            sequence.append(key)
    
    # 处理排除规则(-n)
    if exclude_args:
        for item in exclude_args.split(','):
            item = item.strip()
            if not item: continue
            is_suffix = item.startswith('.')
            rule = FilterRule(item, False, is_suffix)
            key = f"exclude_{item}"
            rule_chain[key] = rule  # 后出现规则覆盖先出现规则
            sequence.append(key)
    
    return [rule_chain[key] for key in sequence]

def should_include_file(rel_path, rules):
    """根据规则链决策是否包含文件"""
    dir_part = os.path.dirname(rel_path)
    file_name = os.path.basename(rel_path)
    
    if not rules:
        return True  # 无规则时默认包含
    
    # 逆序应用规则（后出现优先级更高）
    for rule in reversed(rules):
        if not rule.is_suffix and rule.match(dir_part, is_dir=True):
            return rule.is_include
        if rule.is_suffix and rule.match(file_name):
            return rule.is_include
    
    return not any(rule.is_include for rule in rules)  # 无匹配时的默认策略

def process_source_tree(source_dir, output_dir, prefix="", rules=None, digits=0, num_groups=0):
    """处理文件并分组存储"""
    safe_prefix = sanitize_filename(prefix).rstrip('_') if prefix else ""
    files_to_export = []  # 存储需要导出的文件路径
    
    # 第一次遍历：收集需要导出的文件
    total_count = 0
    for root, _, files in os.walk(source_dir):
        for filename in files:
            total_count += 1
            src_path = os.path.join(root, filename)
            rel_path = os.path.relpath(src_path, source_dir)
            
            if should_include_file(rel_path, rules):
                files_to_export.append(rel_path)
    
    included_count = len(files_to_export)
    if included_count == 0:
        print("没有需要导出的文件")
        return total_count, 0, 0
    
    # 计算分组参数
    group_size = 0
    group_dirs = []
    if num_groups > 0:
        group_size = math.ceil(included_count / num_groups)  # 每组文件数（向上取整）
        # 创建分组目录
        for i in range(1, num_groups + 1):
            group_dir = os.path.join(output_dir, f"group_{i}")
            os.makedirs(group_dir, exist_ok=True)
            group_dirs.append(group_dir)
        print(f"创建 {num_groups} 个分组目录，每组最多 {group_size} 个文件")
    
    # 第二次遍历：处理文件并分组
    current_index = 0
    for rel_path in files_to_export:
        current_index += 1
        src_path = os.path.join(source_dir, rel_path)
        
        # 确定目标目录
        if num_groups > 0:
            group_index = (current_index - 1) // group_size  # 计算分组索引
            target_dir = group_dirs[group_index]
        else:
            target_dir = output_dir
        
        # 生成带编号的文件名
        counter_str = f"{current_index:0{digits}d}_" if digits > 0 else ""
        base_name = sanitize_filename(rel_path)
        
        # 智能后缀处理
        _, ext = os.path.splitext(os.path.basename(rel_path))
        if ext.lower() == '.txt':
            encoded_name = base_name
        else:
            encoded_name = base_name + ".txt"
        
        # 组合最终文件名
        if safe_prefix:
            final_name = f"{counter_str}{safe_prefix}_{encoded_name}"
        else:
            final_name = f"{counter_str}{encoded_name}"
        
        dest_path = os.path.join(target_dir, final_name)
        
        # 复制文件
        shutil.copy2(src_path, dest_path)
        
        # 打印处理信息
        if num_groups > 0:
            group_info = f" → group_{group_index+1}/{final_name}"
        else:
            group_info = f" → {final_name}"
        
        print(f"Processed [{current_index}/{included_count}]: {rel_path}{group_info}")
    
    return total_count, included_count, current_index

def main():
    parser = argparse.ArgumentParser(
        description="Linux内核源码导出工具（分组存储版）",
        formatter_class=argparse.ArgumentDefaultsHelpFormatter
    )
    parser.add_argument("-s", "--source", required=True, help="内核源码根目录路径")
    parser.add_argument("-o", "--output", required=True, help="输出目录路径")
    parser.add_argument("-p", "--prefix", default="", 
                        help="文件名前缀（下划线分隔）")
    parser.add_argument("-f", "--filter", default="", 
                        help="包含规则（逗号分隔，如 'kernel,.c'）")
    parser.add_argument("-n", "--exclude", default="", 
                        help="排除规则（逗号分隔，如 'docs,.txt'）")
    parser.add_argument("-d", "--digits", type=int, default=5,
                        help="编号位数（0=禁用，建议≥4）")
    parser.add_argument("-t", "--groups", type=int, default=0,
                        help="分组数量（0=不分组）")
    
    args = parser.parse_args()
    
    # 路径验证
    if not os.path.isdir(args.source):
        print(f"错误：源目录不存在 {args.source}")
        sys.exit(1)
        
    # 创建输出目录
    os.makedirs(args.output, exist_ok=True)
    
    # 解析过滤规则
    rules = parse_filter_args(args.filter, args.exclude)
    
    # 打印参数摘要
    print(f"源码目录: {args.source}")
    print(f"输出目录: {args.output}")
    print(f"文件名前缀: '{args.prefix}'" if args.prefix else "未指定前缀")
    print(f"编号设置: {args.digits}位数字" if args.digits > 0 else "编号功能已禁用")
    print(f"分组设置: {args.groups}组" if args.groups > 0 else "不启用分组")
    if args.filter: print(f"包含规则: {args.filter}")
    if args.exclude: print(f"排除规则: {args.exclude}")
    
    if rules:
        print("\n激活规则（优先级降序）:")
        for i, rule in enumerate(reversed(rules), 1):
            rule_type = "包含" if rule.is_include else "排除"
            rule_target = "后缀" if rule.is_suffix else "目录"
            print(f"  {i}. [{rule_type}] {rule_target} '{rule.pattern}'")
    
    print("\n" + "=" * 60)
    
    # 执行文件处理
    total, included, seq_count = process_source_tree(
        args.source, 
        args.output, 
        args.prefix,
        rules,
        args.digits,
        args.groups
    )
    
    print("=" * 60)
    print(f"处理完成！扫描文件: {total}, 导出文件: {included}")
    if args.digits > 0:
        print(f"文件编号范围: 1 - {seq_count} (位数:{args.digits})")
        if seq_count >= (10 ** args.digits):
            print(f"⚠️ 警告: 文件数超过编号容量，请增加 --digits 参数值")

if __name__ == "__main__":
    main()