Skip to content

CREATE TABLE AS support for BigQuery #2487

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

Open
wants to merge 3 commits into
base: v4
Choose a base branch
from
+22 −5
Open

CREATE TABLE AS support for BigQuery #2487

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b2ef343
Add CREATE TABLE AS compatibility for BigQuery data source
Niels-b Nov 21, 2025
5289e6b
Fix issue with tabulate when result contains non-ascii characters
Niels-b Nov 21, 2025
2d9e812
Fix formatting of string for tabulate
Niels-b Nov 21, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions soda-bigquery/src/soda_bigquery/common/data_sources/bigquery_data_source.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@
COLUMN,
CONCAT_WS,
COUNT,
CREATE_TABLE_AS_SELECT,
DISTINCT,
LITERAL,
REGEX_LIKE,
Expand Down Expand Up @@ -242,3 +243,13 @@ def get_preferred_number_of_rows_for_insert(self) -> int:
def _build_concat_ws_sql(self, concat_ws: CONCAT_WS) -> str:
elements: str = f", '{concat_ws.separator}', ".join(self.build_expression_sql(e) for e in concat_ws.expressions)
return f"CONCAT({elements})"

# Exact copy from Postgres. So we can refactor this once more data sources support this.
def build_create_table_as_select_sql(
self, create_table_as_select: CREATE_TABLE_AS_SELECT, add_semicolon: bool = True
) -> str:
result_sql: str = f"CREATE TABLE {create_table_as_select.fully_qualified_table_name} AS "
result_sql += f"(\n{self.build_select_sql(create_table_as_select.select_elements, add_semicolon=False)})" + (
";" if add_semicolon else ""
)
return result_sql
16 changes: 11 additions & 5 deletions soda-core/src/soda_core/common/data_source_connection.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,11 +84,17 @@ def execute_query(self, sql: str, log_query: bool = True) -> QueryResult:
formatted_rows = self.format_rows(rows)
truncated_rows = self.truncate_rows(formatted_rows)
headers = [self._execute_query_get_result_row_column_name(c) for c in cursor.description]
table_text: str = tabulate(
truncated_rows,
headers=headers,
tablefmt="github",
)
# The tabulate can crash if the rows contain non-ASCII characters.
# This is purely for debugging/logging purposes, so we can try/catch this.
try:
table_text: str = tabulate(
truncated_rows,
headers=headers,
tablefmt="github",
)
except UnicodeDecodeError as e:
logger.debug(f"Error formatting rows. These may contain non-ASCII characters. {e}")
table_text = "Error formatting rows. These may contain non-ASCII characters."

logger.debug(
f"SQL query result (max {self.MAX_ROWS} rows, {self.MAX_CHARS_PER_STRING} chars per string):\n{table_text}"
Expand Down