dpgaspar commented on a change in pull request #11711: URL: https://github.com/apache/incubator-superset/pull/11711#discussion_r527570486
########## File path: superset/reports/commands/alert.py ########## @@ -0,0 +1,83 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. +import json +import logging +from operator import eq, ge, gt, le, lt, ne +from typing import Optional + +import numpy as np + +from superset import jinja_context +from superset.commands.base import BaseCommand +from superset.models.reports import ReportSchedule, ReportScheduleValidatorType +from superset.reports.commands.exceptions import ( + AlertQueryInvalidTypeError, + AlertQueryMultipleColumnsError, + AlertQueryMultipleRowsError, +) + +logger = logging.getLogger(__name__) + + +OPERATOR_FUNCTIONS = {">=": ge, ">": gt, "<=": le, "<": lt, "==": eq, "!=": ne} + + +class AlertCommand(BaseCommand): + def __init__(self, report_schedule: ReportSchedule): + self._report_schedule = report_schedule + self._result: Optional[float] = None + + def run(self) -> bool: + self.validate() + + if self._report_schedule.validator_type == ReportScheduleValidatorType.NOT_NULL: + self._report_schedule.last_value_row_json = self._result + return self._result not in (0, None, np.nan) + self._report_schedule.last_value = self._result + operator = json.loads(self._report_schedule.validator_config_json)["op"] + threshold = json.loads(self._report_schedule.validator_config_json)["threshold"] + return OPERATOR_FUNCTIONS[operator](self._result, threshold) + + def validate(self) -> None: + """ + Validate the query result as a Pandas DataFrame + """ + sql_template = jinja_context.get_template_processor( + database=self._report_schedule.database + ) + rendered_sql = sql_template.process_template(self._report_schedule.sql) + df = self._report_schedule.database.get_df(rendered_sql) + + if df.empty: + return + rows = df.to_records() + if self._report_schedule.validator_type == ReportScheduleValidatorType.NOT_NULL: + self._result = rows[0][1] + return + # check if query return more then one row + if len(rows) > 1: Review comment: What do you think about surfacing the number of returned rows? Would be nice to try to wrap all the rows in a string, but need to be careful and truncate it to a certain point, think about a user mistake with millions of rows? ---------------------------------------------------------------- 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]
