Created
April 7, 2021 07:07
-
-
Save seirl/3313921c4f86782fd54cd2570d2cc281 to your computer and use it in GitHub Desktop.
Concatenate small ORC files into a single output using PyORC
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
# Copyright (c) 2021 Antoine Pietri <antoine.pietri1@gmail.com> | |
# SPDX-License-Identifier: GPL-3.0 | |
import pyorc | |
import argparse | |
def main(): | |
parser = argparse.ArgumentParser() | |
parser.add_argument('-o', '--output', type=argparse.FileType(mode='wb')) | |
parser.add_argument('files', type=argparse.FileType(mode='rb'), nargs='+') | |
args = parser.parse_args() | |
schema = str(pyorc.Reader(args.files[0]).schema) | |
with pyorc.Writer(args.output, schema) as writer: | |
for i, f in enumerate(args.files): | |
reader = pyorc.Reader(f) | |
if str(reader.schema) != schema: | |
raise RuntimeError( | |
"Inconsistent ORC schemas.\n" | |
"\tFirst file schema: {}\n" | |
"\tFile #{} schema: {}" | |
.format(schema, i, str(reader.schema)) | |
) | |
for line in reader: | |
writer.write(line) | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment