Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add option to preserve the original ordering of columns #75

Merged
merged 2 commits into from
Nov 11, 2021
Merged

Add option to preserve the original ordering of columns #75

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c64d8ee
Add option to preserve the original ordering of columns
kdeggelman Nov 10, 2021
cb73385
Update option name and fix line lengths
kdeggelman Nov 11, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
14 changes: 13 additions & 1 deletion bigquery_schema_generator/generate_schema.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,6 +86,7 @@ def __init__(
debugging_map=False,
sanitize_names=False,
ignore_invalid_lines=False,
preserve_input_sort_order=False,
):
self.input_format = input_format
self.infer_mode = infer_mode
Expand Down Expand Up @@ -113,7 +114,10 @@ def __init__(
# If CSV, preserve the original ordering because 'bq load` matches the
# CSV column with the respective schema entry using the position of the
# column in the schema.
self.sorted_schema = (input_format in {'json', 'dict'})
self.sorted_schema = (
(input_format in {'json', 'dict'})
and not preserve_input_sort_order
)

self.line_number = 0
self.error_logs = []
Expand Down Expand Up @@ -1042,6 +1046,13 @@ def main():
' This can be fetched with:'
' `bq show --schema <project_id>:<dataset>:<table_name>',
default=None)
parser.add_argument(
'--preserve_input_sort_order',
help='Preserve the original ordering of columns from input instead of'
' sorting alphabetically.'
' This only impacts `input_format` of json or dict',
action='store_true'
)
args = parser.parse_args()

# Configure logging.
Expand All @@ -1056,6 +1067,7 @@ def main():
debugging_map=args.debugging_map,
sanitize_names=args.sanitize_names,
ignore_invalid_lines=args.ignore_invalid_lines,
preserve_input_sort_order=args.preserve_input_sort_order
)
existing_schema_map = read_existing_schema_from_file(
args.existing_schema_path)
Expand Down