def run_sql()

in use-cases/ec2-redshift-access/scripts/redshift-data.py [0:0]

• 24 lines of code
• 8 McCabe index (conditional complexity)

def run_sql(sql_text):
    client = boto3.client("redshift-data")
    res = client.execute_statement(Database=REDSHIFT_CLUSTER_ENDPOINT.split('/')[1], DbUser=REDSHIFT_USER_NAME, Sql=sql_text,
                                   ClusterIdentifier=REDSHIFT_CLUSTER_ENDPOINT.split('.')[0])
    query_id = res["Id"]
    done = False
    while not done:
        time.sleep(1)
        status_description = client.describe_statement(Id=query_id)
        status = status_description["Status"]
        if status == "FAILED":
            raise Exception('SQL query failed:' + query_id + ": " + status_description["Error"])
        elif status == "FINISHED":
            if status_description['ResultSize']>0:
                results = client.get_statement_result(Id=query_id)
                column_labels = []
                for i in range(len(results["ColumnMetadata"])): column_labels.append(results["ColumnMetadata"][i]['label'])
                records = []
                for record in results.get('Records'):
                    records.append([list(rec.values())[0] for rec in record])
                df = pd.DataFrame(np.array(records), columns=column_labels)
                return df
            else:
                return query_id