[GitHub] [airflow] jmcarp commented on a change in pull request #5407: [AIRFLOW-4741] Include Sentry into core Airflow

[GitBox <gi...@apache.org>]

jmcarp commented on a change in pull request #5407: [AIRFLOW-4741] Include Sentry into core Airflow
URL: https://github.com/apache/airflow/pull/5407#discussion_r305588847
 
 

 ##########
 File path: airflow/sentry.py
 ##########
 @@ -0,0 +1,203 @@
+# -*- coding: utf-8 -*-
+#
+# 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.
+
+"""Sentry Integration"""
+
+
+from typing import Any
+from functools import wraps
+
+from airflow import configuration as conf
+from airflow.utils.db import provide_session
+from airflow.utils.log.logging_mixin import LoggingMixin
+from airflow.utils.state import State
+
+
+log = LoggingMixin().log
+
+
+class DummySentry:
+    """
+    Blank class for Sentry.
+    """
+
+    @classmethod
+    def add_tagging(cls, task_instance):
+        """
+        Blank function for tagging.
+        """
+
+    @classmethod
+    def add_breadcrumbs(cls, session=None):
+        """
+        Blank function for breadcrumbs.
+        """
+
+    @classmethod
+    def format_run_task(cls, run):
+        """
+        Blank function for formatting a TaskInstance._run_raw_task.
+        """
+        return run
+
+
+@provide_session
+def get_task_instances(dag_id, task_ids, execution_date, session=None):
+    """
+    Retrieves task instance based on dag_id and execution_date.
+    """
+    from airflow.models.taskinstance import TaskInstance  # Avoid circular import
+
+    if session is None or not task_ids:
+        return []
+
+    TI = TaskInstance
+    ti = (
+        session.query(TI)
+        .filter(
+            TI.dag_id == dag_id,
+            TI.task_id.in_(task_ids),
+            TI.execution_date == execution_date,
+        )
+        .all()
+    )
+    return ti
+
+
+class ConfiguredSentry:
+    """
+    Configure Sentry SDK.
+    """
+
+    SCOPE_TAGS = frozenset(("task_id", "dag_id", "execution_date", "operator"))
+    SCOPE_CRUMBS = frozenset(
+        ("dag_id", "task_id", "execution_date", "state", "operator", "duration")
+    )
+
+    def __init__(self):
+        """
+        Initialize the Sentry SDK.
+        """
+        ignore_logger("airflow.task")
+        ignore_logger("airflow.jobs.backfill_job.BackfillJob")
+        executor_name = conf.get("core", "EXECUTOR")
+
+        sentry_flask = FlaskIntegration()
+
+        # LoggingIntegration is set by default.
+        integrations = [sentry_flask]
+
+        if executor_name == "CeleryExecutor":
+            from sentry_sdk.integrations.celery import CeleryIntegration
+            from sentry_sdk.integrations.tornado import TornadoIntegration
+
+            sentry_celery = CeleryIntegration()
+            sentry_tornado = TornadoIntegration()
+            integrations += [sentry_celery, sentry_tornado]
+
+        self.task = None
 
 Review comment:
   Do we need to store these attributes on the instance? Maybe I'm missing something, but it seems like it would be simpler to pass `task_instance` to both `add_tagging` and `add_breadcrumbs` and not keep state on the instance at all.

----------------------------------------------------------------
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:
users@infra.apache.org


With regards,
Apache Git Services