#!/usr/bin/env python3
"""
列合并/拆分模板
将多列合并为一列，或将一列拆分为多列
"""

import pandas as pd
import sys
from pathlib import Path

def main():
    # 参数配置
    file_path = "{file}"
    output_path = "{output}"
    operation = "{operation}"  # 操作类型: merge/split
    
    # 合并参数
    merge_columns = "{merge_columns}"  # 要合并的列（逗号分隔）
    merge_separator = "{merge_separator}"  # 分隔符
    result_column = "{result_column}"  # 结果列名
    
    # 拆分参数
    split_column = "{split_column}"  # 要拆分的列
    split_separator = "{split_separator}"  # 分隔符
    new_columns = "{new_columns}"  # 新列名（逗号分隔）
    
    # 读取文件
    df = pd.read_excel(file_path)
    
    print(f"原始数据: {{len(df)}} 行, {{len(df.columns)}} 列")
    
    if operation == "merge":
        # 合并列
        columns = [col.strip() for col in merge_columns.split(",")]
        
        # 检查列是否存在
        missing_cols = [col for col in columns if col not in df.columns]
        if missing_cols:
            print(f"错误: 列不存在: {{missing_cols}}")
            sys.exit(1)
        
        # 合并列
        df[result_column] = df[columns].astype(str).agg(merge_separator.join, axis=1)
        
        print(f"合并列: {{columns}}")
        print(f"分隔符: '{{merge_separator}}'")
        print(f"结果列: {{result_column}}")
    
    elif operation == "split":
        # 拆分列
        if split_column not in df.columns:
            print(f"错误: 列 '{split_column}' 不存在")
            sys.exit(1)
        
        # 拆分列
        split_df = df[split_column].str.split(split_separator, expand=True)
        
        # 设置新列名
        new_col_names = [col.strip() for col in new_columns.split(",")]
        for i, name in enumerate(new_col_names):
            if i < split_df.shape[1]:
                df[name] = split_df[i]
        
        print(f"拆分列: {{split_column}}")
        print(f"分隔符: '{{split_separator}}'")
        print(f"新列: {{new_col_names}}")
    
    # 保存结果
    df.to_excel(output_path, index=False)
    
    print(f"\n操作完成")
    print(f"输出文件: {{output_path}}")
    print(f"最终数据: {{len(df)}} 行, {{len(df.columns)}} 列")
    
    # 显示前几行
    print(f"\n预览:")
    print(df.head(5).to_string(index=False))

if __name__ == "__main__":
    main()