robdiciuccio commented on a change in pull request #14449:
URL: https://github.com/apache/superset/pull/14449#discussion_r636508662
##########
File path: superset/views/database/views.py
##########
@@ -128,6 +128,32 @@ def form_get(self, form: CsvToDatabaseForm) -> None:
def form_post(self, form: CsvToDatabaseForm) -> Response:
database = form.con.data
csv_table = Table(table=form.name.data, schema=form.schema.data)
+ file_type = form.csv_file.data.filename.split(".")[-1]
+ if file_type == "parquet":
+ read = pd.read_parquet
+ kwargs = {
+ "columns": form.usecols.data,
+ }
+ else:
+ read = pd.read_csv
+ kwargs = {
+ "chunksize": 1000,
+ "encoding": "utf-8",
+ "header": form.header.data if form.header.data else 0,
+ "index_col": form.index_col.data,
+ "infer_datetime_format": form.infer_datetime_format.data,
+ "iterator": True,
+ "keep_default_na": not form.null_values.data,
+ "mangle_dupe_cols": form.mangle_dupe_cols.data,
+ "usecols": form.usecols.data,
Review comment:
This appears to change the behavior of the existing CSV upload
functionality by specifying columns. Can you add some tests around this?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
