get memory consumption of data from an apache ORC format file

get_orc_size.py

import pyorc
import sys

# 打开要读取的orc文件
with open("./output.orc", "rb") as data:
    # 创建一个读取器对象
    reader = pyorc.Reader(data)
    # 初始化一个变量来存储总大小
    total_size = 0
    # 遍历文件中的每一行记录
    for row in reader:
        # 计算当前行记录在内存中的大小，并累加到总大小中
        total_size += sys.getsizeof(row)
    # 打印总大小
    print(f"The total size of the orc file content in memory is {total_size} bytes.")