import os
import datetime

# ================= 配置区域 =================
# 输出文件名包含版本号（时间戳）
TIMESTAMP = datetime.datetime.now().strftime("%Y%m%d_%H%M")
OUTPUT_FILE = f"project_code_v{TIMESTAMP}.txt"

# 需要包含的文件后缀 (根据你的截图，主要是 Java, XML, Yaml, Dockerfile, Shell)
INCLUDE_EXTENSIONS = {'.java', '.xml', '.yml', '.yaml', '.properties', '.sql', '.sh', 'Dockerfile', '.md'}

# 需要完全匹配的文件名 (无后缀的文件，如 Dockerfile)
INCLUDE_FILENAMES = {'Dockerfile', 'Makefile', 'Jenkinsfile'}

# 需要忽略的目录
IGNORE_DIRS = {
    'target', '.idea', '.git', '.mvn', 'wrapper', 'build',
    'arthas-output', 'knowledge-base-server-log', 'test' # 如果不需要测试代码，可以加上 'test'
}
# ===========================================

def generate_tree(startpath):
    """生成项目目录树结构字符串"""
    tree_str = "【项目目录结构】:\n"
    for root, dirs, files in os.walk(startpath):
        dirs[:] = [d for d in dirs if d not in IGNORE_DIRS]
        level = root.replace(startpath, '').count(os.sep)
        indent = ' ' * 4 * (level)
        tree_str += '{}{}/\n'.format(indent, os.path.basename(root))
        subindent = ' ' * 4 * (level + 1)
        for f in files:
            # 简单过滤显示在树中的文件
            if any(f.endswith(ext) for ext in INCLUDE_EXTENSIONS) or f in INCLUDE_FILENAMES:
                tree_str += '{}{}\n'.format(subindent, f)
    return tree_str + "\n" + "="*50 + "\n\n"

def is_target_file(filename):
    """判断是否为目标文件"""
    if filename in INCLUDE_FILENAMES:
        return True
    _, ext = os.path.splitext(filename)
    return ext in INCLUDE_EXTENSIONS

def merge_files():
    root_dir = os.getcwd() # 获取当前脚本所在目录

    with open(OUTPUT_FILE, 'w', encoding='utf-8') as outfile:
        # 1. 写入目录树
        print("正在生成目录结构...")
        outfile.write(generate_tree(root_dir))

        # 2. 遍历并写入文件内容
        print("正在合并代码文件...")
        for root, dirs, files in os.walk(root_dir):
            # 移除忽略的目录
            dirs[:] = [d for d in dirs if d not in IGNORE_DIRS]

            for file in files:
                if is_target_file(file):
                    file_path = os.path.join(root, file)
                    rel_path = os.path.relpath(file_path, root_dir)

                    # 写入文件头分割线
                    header = f"\n\n{'='*20}\nFile Path: {rel_path}\n{'='*20}\n"
                    outfile.write(header)

                    try:
                        with open(file_path, 'r', encoding='utf-8') as infile:
                            outfile.write(infile.read())
                    except Exception as e:
                        outfile.write(f"\n[Error reading file: {e}]\n")
                        print(f"Error reading {rel_path}: {e}")

    print(f"✅ 完成！文件已保存为: {OUTPUT_FILE}")

if __name__ == '__main__':
    merge_files()