def get(self, data_source_id, database_name, table_name):
data_source = _get_databricks_data_source(
data_source_id, user=self.current_user, org=self.current_org
)
job = get_databricks_table_columns.delay(data_source.id, database_name, table_name)
return serialize_job(job)
def run_query(query, parameters, data_source, query_id, max_age=0):
if data_source.paused:
if data_source.pause_reason:
message = "{} is paused ({}). Please try later.".format(
data_source.name, data_source.pause_reason)
else:
message = "{} is paused. Please try later.".format(
data_source.name)
return error_response(message)
try:
query.apply(parameters)
except (InvalidParameterError, QueryDetachedFromDataSourceError) as e:
abort(400, message=str(e))
if query.missing_params:
return error_response("Missing parameter value for: {}".format(
", ".join(query.missing_params)))
if max_age == 0:
query_result = None
else:
query_result = models.QueryResult.get_latest(data_source, query.text,
max_age)
record_event(
current_user.org,
current_user,
{
"action": "execute_query",
"cache": "hit" if query_result else "miss",
"object_id": data_source.id,
"object_type": "data_source",
"query": query.text,
"query_id": query_id,
"parameters": parameters,
},
)
if query_result:
return {
"query_result":
serialize_query_result(query_result, current_user.is_api_user())
}
else:
job = enqueue_query(
query.text,
data_source,
current_user.id,
current_user.is_api_user(),
metadata={
"Username":
repr(current_user)
if current_user.is_api_user() else current_user.email,
"Query ID":
query_id,
},
)
return serialize_job(job)
def get(self, data_source_id):
data_source = get_object_or_404(models.DataSource.get_by_id_and_org,
data_source_id, self.current_org)
require_access(data_source, self.current_user, view_only)
refresh = request.args.get("refresh") is not None
job = get_schema.delay(data_source.id, refresh)
return serialize_job(job)
def get(self, data_source_id, database_name):
data_source = _get_databricks_data_source(
data_source_id, user=self.current_user, org=self.current_org
)
refresh = request.args.get("refresh") is not None
if not refresh:
cached_tables = _get_tables_from_cache(data_source_id, database_name)
if cached_tables is not None:
return {"schema": cached_tables, "has_columns": True}
job = get_databricks_tables.delay(data_source.id, database_name)
return serialize_job(job)
job = get_database_tables_with_columns.delay(
data_source.id, database_name, redis_key=_tables_key(data_source_id, database_name)
)
return serialize_job(job)
def get(self, data_source_id, database_name):
data_source = get_object_or_404(
models.DataSource.get_by_id_and_org, data_source_id, self.current_org
)
require_access(data_source, self.current_user, view_only)
if not data_source.type == "databricks":
abort(
400, message="Resource only available for the Databricks query runner."
)
job = get_databricks_schema.delay(data_source.id, database_name)
return serialize_job(job)
def get(self, data_source_id):
data_source = _get_databricks_data_source(
data_source_id, user=self.current_user, org=self.current_org
)
refresh = request.args.get("refresh") is not None
if not refresh:
cached_databases = _get_databases_from_cache(data_source_id)
if cached_databases is not None:
return cached_databases
job = get_databricks_databases.delay(
data_source.id, redis_key=_databases_key(data_source_id)
)
return serialize_job(job)
def get(self, job_id, query_id=None):
"""
Retrieve info about a running query job.
"""
job = Job.fetch(job_id)
return serialize_job(job)
