Created
January 7, 2019 22:01
-
-
Save jonstefansson/51fb939e227b3344f40f3932fc992a68 to your computer and use it in GitHub Desktop.
Flatten BigQuery JSON schema
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
import click | |
import json | |
@click.command() | |
@click.argument("input_source", type=click.File("rt")) | |
def flatten(input_source): | |
""" | |
Creates a flattened representation of a BigQuery JSON schema. | |
\b | |
:param input_source: A JSON schema file or STDIN | |
:return: Streams flattened data to STDOUT | |
""" | |
schema = json.load(input_source) | |
_process_array(schema) | |
def _process_array(ary, parent=None): | |
for element in ary: | |
name = '.'.join([i for i in [parent, element["name"]] if i is not None]) | |
print("{0:<65s} {1:<12s} {2:s}".format(name, element["type"], element["mode"])) | |
if element["type"] == "RECORD": | |
_process_array(element["fields"], parent=name) | |
if __name__ == "__main__": | |
flatten() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment