复杂orc文件转txt文件

import pyarrow.orc as orc
import pyarrow as pa

# 指定 .snappy.orc 文件的路径
orc_file_path = 'a.snappy.orc'

# 读取 ORC 文件内容为 PyArrow 表
orc_file = orc.ORCFile(orc_file_path)
table = orc_file.read()

# 获取表的列名
columns = table.schema.names

# 创建一个字典存储列数据
data_dict = {column: table.column(column).to_pylist() for column in columns}

# 定义输出文件路径
txt_file_path = 'data/output_file.txt'

# 打开文件进行写入
with open(txt_file_path, 'w', encoding='utf-8') as file:
    # 写入表头
    file.write('\t'.join(columns) + '\n')
    
    # 获取行数
    num_rows = len(data_dict[columns[0]])
    
    # 逐行写入数据
    for i in range(num_rows):
        row_data = []
        for column in columns:
            # 获取当前列的数据
            value = data_dict[column][i]
            
            # 将复杂数据类型转换为字符串（如列表、字典等）
            if isinstance(value, (list, dict, np.ndarray)):
                value = str(value)
            
            # 将数据转换为字符串
            row_data.append(str(value))
        
        # 写入当前行到文件中
        file.write('\t'.join(row_data) + '\n')

print(f"数据已成功写入到 {txt_file_path}")