This is an automated email from the ASF dual-hosted git repository.

ephraimanierobi pushed a commit to branch v2-9-test
in repository https://gitbox.apache.org/repos/asf/airflow.git

commit ebb74b28dec1c855895337746cccc413597bf26f
Author: Andrey Anshin <[email protected]>
AuthorDate: Thu May 30 13:00:09 2024 +0400

    Improve visibility of links / variables / other configs in Configuration 
Reference (#39916)
    
    * Improve visibility of links / variables / other configs in Configuration 
Reference
    
    * Fixup config test cases
    
    (cherry picked from commit eba6406053eef5dd87619f86a1c82ca38971ec10)
---
 airflow/config_templates/config.yml       | 358 ++++++++++++++++++------------
 tests/cli/commands/test_config_command.py |  12 +-
 2 files changed, 217 insertions(+), 153 deletions(-)

diff --git a/airflow/config_templates/config.yml 
b/airflow/config_templates/config.yml
index 28e86a9e16..74e9bcdb09 100644
--- a/airflow/config_templates/config.yml
+++ b/airflow/config_templates/config.yml
@@ -33,8 +33,9 @@ core:
         Hostname by providing a path to a callable, which will resolve the 
hostname.
         The format is "package.function".
 
-        For example, default value "airflow.utils.net.getfqdn" means that 
result from patched
-        version of socket.getfqdn() - see 
https://github.com/python/cpython/issues/49254.
+        For example, default value ``airflow.utils.net.getfqdn`` means that 
result from patched
+        version of `socket.getfqdn() 
<https://docs.python.org/3/library/socket.html#socket.getfqdn>`__,
+        see related `CPython Issue 
<https://github.com/python/cpython/issues/49254>`__.
 
         No argument should be required in the function specified.
         If using IP address as hostname is preferred, use value 
``airflow.utils.net.get_host_ip_address``
@@ -44,10 +45,15 @@ core:
       default: "airflow.utils.net.getfqdn"
     might_contain_dag_callable:
       description: |
-        A callable to check if a python file has airflow dags defined or not
-        with argument as: `(file_path: str, zip_file: zipfile.ZipFile | None = 
None)`
-        return True if it has dags otherwise False
+        A callable to check if a python file has airflow dags defined or not 
and should
+        return ``True`` if it has dags otherwise ``False``.
         If this is not provided, Airflow uses its own heuristic rules.
+
+        The function should have the following signature
+
+        .. code-block:: python
+
+            def func_name(file_path: str, zip_file: zipfile.ZipFile | None = 
None) -> bool: ...
       version_added: 2.6.0
       type: string
       example: ~
@@ -55,7 +61,8 @@ core:
     default_timezone:
       description: |
         Default timezone in case supplied date times are naive
-        can be utc (default), system, or any IANA timezone string (e.g. 
Europe/Amsterdam)
+        can be `UTC` (default), `system`, or any `IANA 
<https://www.iana.org/time-zones>`
+        timezone string (e.g. Europe/Amsterdam)
       version_added: ~
       type: string
       example: ~
@@ -92,7 +99,7 @@ core:
         The maximum number of task instances allowed to run concurrently in 
each DAG. To calculate
         the number of tasks that is running concurrently for a DAG, add up the 
number of running
         tasks for all DAG runs of the DAG. This is configurable at the DAG 
level with ``max_active_tasks``,
-        which is defaulted as ``max_active_tasks_per_dag``.
+        which is defaulted as ``[core] max_active_tasks_per_dag``.
 
         An example scenario when this would be useful is when you want to stop 
a new dag with an early
         start date from stealing all the executor slots in a cluster.
@@ -111,7 +118,7 @@ core:
       description: |
         The maximum number of active DAG runs per DAG. The scheduler will not 
create more DAG runs
         if it reaches the limit. This is configurable at the DAG level with 
``max_active_runs``,
-        which is defaulted as ``max_active_runs_per_dag``.
+        which is defaulted as ``[core] max_active_runs_per_dag``.
       version_added: ~
       type: string
       example: ~
@@ -120,7 +127,7 @@ core:
       description: |
         (experimental) The maximum number of consecutive DAG failures before 
DAG is automatically paused.
         This is also configurable per DAG level with 
``max_consecutive_failed_dag_runs``,
-        which is defaulted as ``max_consecutive_failed_dag_runs_per_dag``.
+        which is defaulted as ``[core] 
max_consecutive_failed_dag_runs_per_dag``.
         If not specified, then the value is considered as 0,
         meaning that the dags are never paused out by default.
       version_added: 2.9.0
@@ -131,9 +138,10 @@ core:
       description: |
         The name of the method used in order to start Python processes via the 
multiprocessing module.
         This corresponds directly with the options available in the Python 
docs:
-        
https://docs.python.org/3/library/multiprocessing.html#multiprocessing.set_start_method.
-        Must be one of the values returned by:
-        
https://docs.python.org/3/library/multiprocessing.html#multiprocessing.get_all_start_methods.
+        `multiprocessing.set_start_method
+        
<https://docs.python.org/3/library/multiprocessing.html#multiprocessing.set_start_method>`__
+        must be one of the values returned by 
`multiprocessing.get_all_start_methods()
+        
<https://docs.python.org/3/library/multiprocessing.html#multiprocessing.get_all_start_methods>`__.
       version_added: "2.0.0"
       type: string
       default: ~
@@ -156,9 +164,11 @@ core:
       default: "{AIRFLOW_HOME}/plugins"
     execute_tasks_new_python_interpreter:
       description: |
-        Should tasks be executed via forking of the parent process ("False",
-        the speedier option) or by spawning a new python process ("True" slow,
-        but means plugin changes picked up by tasks straight away)
+        Should tasks be executed via forking of the parent process
+
+        * ``False``: Execute via forking of the parent process
+        * ``True``: Spawning a new python process, slower than fork, but means 
plugin changes picked
+          up by tasks straight away
       default: "False"
       example: ~
       version_added: 2.0.0
@@ -262,7 +272,7 @@ core:
       description: |
         What classes can be imported during deserialization. This is a multi 
line value.
         The individual items will be parsed as regexp patterns.
-        This is a secondary option to ``allowed_deserialization_classes``.
+        This is a secondary option to ``[core] 
allowed_deserialization_classes``.
       version_added: 2.8.2
       type: string
       default: ''
@@ -293,8 +303,10 @@ core:
       default: "True"
     dag_ignore_file_syntax:
       description: |
-        The pattern syntax used in the ".airflowignore" files in the DAG 
directories. Valid values are
-        ``regexp`` or ``glob``.
+        The pattern syntax used in the
+        `.airflowignore
+        
<https://airflow.apache.org/docs/apache-airflow/stable/core-concepts/dags.html#airflowignore>`__
+        files in the DAG directories. Valid values are ``regexp`` or ``glob``.
       version_added: 2.3.0
       type: string
       example: ~
@@ -347,8 +359,11 @@ core:
       default: "30"
     compress_serialized_dags:
       description: |
-        If True, serialized DAGs are compressed before writing to DB.
-        Note: this will disable the DAG dependencies view
+        If ``True``, serialized DAGs are compressed before writing to DB.
+
+        .. note::
+
+            This will disable the DAG dependencies view
       version_added: 2.3.0
       type: string
       example: ~
@@ -397,7 +412,7 @@ core:
     lazy_discover_providers:
       description: |
         By default Airflow providers are lazily-discovered (discovery and 
imports happen only when required).
-        Set it to False, if you want to discover providers whenever 'airflow' 
is invoked via cli or
+        Set it to ``False``, if you want to discover providers whenever 
'airflow' is invoked via cli or
         loaded from module.
       version_added: 2.0.0
       type: boolean
@@ -405,9 +420,12 @@ core:
       default: "True"
     hide_sensitive_var_conn_fields:
       description: |
-        Hide sensitive Variables or Connection extra json keys from UI and 
task logs when set to True
+        Hide sensitive **Variables** or **Connection extra json keys** from UI
+        and task logs when set to ``True``
+
+        .. note::
 
-        (Connection passwords are always hidden in logs)
+            Connection passwords are always hidden in logs
       version_added: 2.1.0
       type: boolean
       example: ~
@@ -481,7 +499,8 @@ core:
       default: "False"
     internal_api_url:
       description: |
-        (experimental) Airflow Internal API url. Only used if [core] 
database_access_isolation is True.
+        (experimental) Airflow Internal API url.
+        Only used if ``[core] database_access_isolation`` is ``True``.
       version_added: 2.6.0
       type: string
       default: ~
@@ -489,14 +508,16 @@ core:
     test_connection:
       description: |
         The ability to allow testing connections across Airflow UI, API and 
CLI.
-        Supported options: Disabled, Enabled, Hidden. Default: Disabled
+        Supported options: ``Disabled``, ``Enabled``, ``Hidden``. Default: 
Disabled
         Disabled - Disables the test connection functionality and disables the 
Test Connection button in UI.
         Enabled - Enables the test connection functionality and shows the Test 
Connection button in UI.
         Hidden - Disables the test connection functionality and hides the Test 
Connection button in UI.
         Before setting this to Enabled, make sure that you review the users 
who are able to add/edit
         connections and ensure they are trusted. Connection testing can be 
done maliciously leading to
-        undesired and insecure outcomes. For more information on capabilities 
of users, see the documentation:
-        
https://airflow.apache.org/docs/apache-airflow/stable/security/security_model.html#capabilities-of-authenticated-ui-users
+        undesired and insecure outcomes.
+        See `Airflow Security Model: Capabilities of authenticated UI users
+        
<https://airflow.apache.org/docs/apache-airflow/stable/security/security_model.html#capabilities-of-authenticated-ui-users>`__
+        for more details.
       version_added: 2.7.0
       type: string
       example: ~
@@ -522,10 +543,11 @@ database:
       default: "alembic.ini"
     sql_alchemy_conn:
       description: |
-        The SqlAlchemy connection string to the metadata database.
-        SqlAlchemy supports many different database engines.
-        More information here:
-        
http://airflow.apache.org/docs/apache-airflow/stable/howto/set-up-database.html#database-uri
+        The SQLAlchemy connection string to the metadata database.
+        SQLAlchemy supports many different database engines.
+        See: `Set up a Database Backend: Database URI
+        
<https://airflow.apache.org/docs/apache-airflow/stable/howto/set-up-database.html#database-uri>`__
+        for more details.
       version_added: 2.3.0
       type: string
       sensitive: true
@@ -552,22 +574,23 @@ database:
         in case they have different encoding.
         By default this collation is the same as the database collation, 
however for ``mysql`` and ``mariadb``
         the default is ``utf8mb3_bin`` so that the index sizes of our index 
keys will not exceed
-        the maximum size of allowed index when collation is set to ``utf8mb4`` 
variant
-        (see 
https://github.com/apache/airflow/pull/17603#issuecomment-901121618).
+        the maximum size of allowed index when collation is set to ``utf8mb4`` 
variant, see
+        `GitHub Issue Comment 
<https://github.com/apache/airflow/pull/17603#issuecomment-901121618>`__
+        for more details.
       version_added: 2.3.0
       type: string
       example: ~
       default: ~
     sql_alchemy_pool_enabled:
       description: |
-        If SqlAlchemy should pool database connections.
+        If SQLAlchemy should pool database connections.
       version_added: 2.3.0
       type: string
       example: ~
       default: "True"
     sql_alchemy_pool_size:
       description: |
-        The SqlAlchemy pool size is the maximum number of database connections
+        The SQLAlchemy pool size is the maximum number of database connections
         in the pool. 0 indicates no limit.
       version_added: 2.3.0
       type: string
@@ -580,7 +603,7 @@ database:
         additional connections will be returned up to this limit.
         When those additional connections are returned to the pool, they are 
disconnected and discarded.
         It follows then that the total number of simultaneous connections the 
pool will allow
-        is pool_size + max_overflow,
+        is **pool_size** + **max_overflow**,
         and the total number of "sleeping" connections the pool will allow is 
pool_size.
         max_overflow can be set to ``-1`` to indicate no overflow limit;
         no limit will be placed on the total number of concurrent connections. 
Defaults to ``10``.
@@ -590,7 +613,7 @@ database:
       default: "10"
     sql_alchemy_pool_recycle:
       description: |
-        The SqlAlchemy pool recycle is the number of seconds a connection
+        The SQLAlchemy pool recycle is the number of seconds a connection
         can be idle in the pool before it is invalidated. This config does
         not apply to sqlite. If the number of DB connections is ever exceeded,
         a lower config value will allow the system to recover faster.
@@ -602,8 +625,9 @@ database:
       description: |
         Check connection at the start of each connection pool checkout.
         Typically, this is a simple statement like "SELECT 1".
-        More information here:
-        
https://docs.sqlalchemy.org/en/14/core/pooling.html#disconnect-handling-pessimistic
+        See `SQLAlchemy Pooling: Disconnect Handling - Pessimistic
+        
<https://docs.sqlalchemy.org/en/14/core/pooling.html#disconnect-handling-pessimistic>`__
+        for more details.
       version_added: 2.3.0
       type: string
       example: ~
@@ -611,20 +635,20 @@ database:
     sql_alchemy_schema:
       description: |
         The schema to use for the metadata database.
-        SqlAlchemy supports databases with the concept of multiple schemas.
+        SQLAlchemy supports databases with the concept of multiple schemas.
       version_added: 2.3.0
       type: string
       example: ~
       default: ""
     sql_alchemy_connect_args:
       description: |
-        Import path for connect args in SqlAlchemy. Defaults to an empty dict.
-        This is useful when you want to configure db engine args that 
SqlAlchemy won't parse
+        Import path for connect args in SQLAlchemy. Defaults to an empty dict.
+        This is useful when you want to configure db engine args that 
SQLAlchemy won't parse
         in connection string. This can be set by passing a dictionary 
containing the create engine parameters.
-        For more details about passing create engine parameters(keepalives 
variables, timeout etc)
-        in postgres db connection see
-        
https://airflow.apache.org/docs/apache-airflow/stable/howto/set-up-database.html#setting-up-a-postgresql-database
-        e.g connect_args={"timeout":30} can be defined in 
airflow_local_settings.py and
+        For more details about passing create engine parameters (keepalives 
variables, timeout etc)
+        in Postgres DB Backend see `Setting up a PostgreSQL Database
+        
<https://airflow.apache.org/docs/apache-airflow/stable/howto/set-up-database.html#setting-up-a-postgresql-database>`__
+        e.g ``connect_args={"timeout":30}`` can be defined in 
``airflow_local_settings.py`` and
         can be imported as shown below
       version_added: 2.3.0
       type: string
@@ -659,7 +683,7 @@ database:
       description: |
         Whether to run alembic migrations during Airflow start up. Sometimes 
this operation can be expensive,
         and the users can assert the correct version through other means (e.g. 
through a Helm chart).
-        Accepts "True" or "False".
+        Accepts ``True`` or ``False``.
       version_added: 2.6.0
       type: string
       example: ~
@@ -672,8 +696,9 @@ logging:
         The folder where airflow should store its log files.
         This path must be absolute.
         There are a few existing configurations that assume this is set to the 
default.
-        If you choose to override this you may need to update the 
dag_processor_manager_log_location and
-        child_process_log_directory settings as well.
+        If you choose to override this you may need to update the
+        ``[logging] dag_processor_manager_log_location`` and
+        ``[logging] child_process_log_directory settings`` as well.
       version_added: 2.0.0
       type: string
       example: ~
@@ -681,7 +706,7 @@ logging:
     remote_logging:
       description: |
         Airflow can store logs remotely in AWS S3, Google Cloud Storage or 
Elastic Search.
-        Set this to True if you want to enable remote logging.
+        Set this to ``True`` if you want to enable remote logging.
       version_added: 2.0.0
       type: string
       example: ~
@@ -707,7 +732,7 @@ logging:
       description: |
         Path to Google Credential JSON file. If omitted, authorization based 
on `the Application Default
         Credentials
-        
<https://cloud.google.com/docs/authentication/production#finding_credentials_automatically>`__
 will
+        
<https://cloud.google.com/docs/authentication/application-default-credentials>`__
 will
         be used.
       version_added: 2.0.0
       type: string
@@ -716,20 +741,20 @@ logging:
     remote_base_log_folder:
       description: |
         Storage bucket URL for remote logging
-        S3 buckets should start with "s3://"
-        Cloudwatch log groups should start with "cloudwatch://"
-        GCS buckets should start with "gs://"
-        WASB buckets should start with "wasb" just to help Airflow select 
correct handler
-        Stackdriver logs should start with "stackdriver://"
+        S3 buckets should start with **s3://**
+        Cloudwatch log groups should start with **cloudwatch://**
+        GCS buckets should start with **gs://**
+        WASB buckets should start with **wasb** just to help Airflow select 
correct handler
+        Stackdriver logs should start with **stackdriver://**
       version_added: 2.0.0
       type: string
       example: ~
       default: ""
     remote_task_handler_kwargs:
       description: |
-        The remote_task_handler_kwargs param is loaded into a dictionary and 
passed to __init__ of remote
-        task handler and it overrides the values provided by Airflow config. 
For example if you set
-        `delete_local_logs=False` and you provide ``{"delete_local_copy": 
true}``, then the local
+        The remote_task_handler_kwargs param is loaded into a dictionary and 
passed to the ``__init__``
+        of remote task handler and it overrides the values provided by Airflow 
config. For example if you set
+        ``delete_local_logs=False`` and you provide ``{"delete_local_copy": 
true}``, then the local
         log files will be deleted after they are uploaded to remote location.
       version_added: 2.6.0
       type: string
@@ -844,7 +869,7 @@ logging:
     secret_mask_adapter:
       description: |
         An import path to a function to add adaptations of each secret added 
with
-        `airflow.utils.log.secrets_masker.mask_secret` to be masked in log 
messages. The given function
+        ``airflow.utils.log.secrets_masker.mask_secret`` to be masked in log 
messages. The given function
         is expected to require a single parameter: the secret to be adapted. 
It may return a
         single adaptation of the secret or an iterable of adaptations to each 
be masked as secrets.
         The original secret will be masked as well as any adaptations returned.
@@ -854,7 +879,7 @@ logging:
       example: "urllib.parse.quote"
     task_log_prefix_template:
       description: |
-        Specify prefix pattern like mentioned below with stream handler 
TaskHandlerWithCustomFormatter
+        Specify prefix pattern like mentioned below with stream handler 
``TaskHandlerWithCustomFormatter``
       version_added: 2.0.0
       type: string
       example: 
"{{ti.dag_id}}-{{ti.task_id}}-{{execution_date}}-{{ti.try_number}}"
@@ -910,7 +935,7 @@ logging:
       default: ""
     worker_log_server_port:
       description: |
-        When you start an airflow worker, airflow starts a tiny web server
+        When you start an Airflow worker, Airflow starts a tiny web server
         subprocess to serve the workers local log files to the airflow main
         web server, who then builds pages and sends them to users. This defines
         the port on which the logs are served. It needs to be unused, and open
@@ -921,8 +946,8 @@ logging:
       default: "8793"
     trigger_log_server_port:
       description: |
-        Port to serve logs from for triggerer.  See worker_log_server_port 
description
-        for more info.
+        Port to serve logs from for triggerer.
+        See ``[logging] worker_log_server_port`` description for more info.
       version_added: 2.6.0
       type: string
       example: ~
@@ -943,10 +968,10 @@ logging:
         when you use impersonation, when logs are written by a different user 
than airflow. The most secure
         way of configuring it in this case is to add both users to the same 
group and make it the default
         group of both users. Group-writeable logs are default in airflow, but 
you might decide that you are
-        OK with having the logs other-writeable, in which case you should set 
it to `0o777`. You might
-        decide to add more security if you do not use impersonation and change 
it to `0o755` to make it
-        only owner-writeable. You can also make it just readable only for 
owner by changing it to `0o700` if
-        all the access (read/write) for your logs happens from the same user.
+        OK with having the logs other-writeable, in which case you should set 
it to ``0o777``. You might
+        decide to add more security if you do not use impersonation and change 
it to ``0o755`` to make it
+        only owner-writeable. You can also make it just readable only for 
owner by changing it to ``0o700``
+        if all the access (read/write) for your logs happens from the same 
user.
       version_added: 2.6.0
       type: string
       example: "0o775"
@@ -957,10 +982,10 @@ logging:
         when you use impersonation, when logs are written by a different user 
than airflow. The most secure
         way of configuring it in this case is to add both users to the same 
group and make it the default
         group of both users. Group-writeable logs are default in airflow, but 
you might decide that you are
-        OK with having the logs other-writeable, in which case you should set 
it to `0o666`. You might
-        decide to add more security if you do not use impersonation and change 
it to `0o644` to make it
-        only owner-writeable. You can also make it just readable only for 
owner by changing it to `0o600` if
-        all the access (read/write) for your logs happens from the same user.
+        OK with having the logs other-writeable, in which case you should set 
it to ``0o666``. You might
+        decide to add more security if you do not use impersonation and change 
it to ``0o644`` to make it
+        only owner-writeable. You can also make it just readable only for 
owner by changing it to ``0o600``
+        if all the access (read/write) for your logs happens from the same 
user.
       version_added: 2.6.0
       type: string
       example: "0o664"
@@ -982,7 +1007,7 @@ logging:
         the scheduler, executor, or callback execution context. This can help 
in circumstances such as
         when there's something blocking the execution of the task and 
ordinarily there may be no task
         logs at all.
-        This is set to True by default. If you encounter issues with this 
feature
+        This is set to ``True`` by default. If you encounter issues with this 
feature
         (e.g. scheduler performance issues) it can be disabled.
       version_added: 2.8.0
       type: boolean
@@ -990,12 +1015,13 @@ logging:
       default: "True"
 metrics:
   description: |
-    StatsD (https://github.com/etsy/statsd) integration settings.
+    `StatsD <https://github.com/statsd/statsd>`__ integration settings.
   options:
     metrics_use_pattern_match:
       description: |
-        If true, metrics_allow_list and metrics_block_list will use regex 
pattern matching
-        anywhere within the metric name instead of only prefix matching at the 
start of the name.
+        If true, ``[metrics] metrics_allow_list`` and ``[metrics] 
metrics_block_list`` will use
+        regex pattern matching anywhere within the metric name instead of only 
prefix matching
+        at the start of the name.
       version_added: 2.9.0
       type: boolean
       example: ~
@@ -1003,8 +1029,8 @@ metrics:
     metrics_allow_list:
       description: |
         Configure an allow list (comma separated string) to send only certain 
metrics.
-        If metrics_use_pattern_match is false, match only the exact metric 
name prefix.
-        If metrics_use_pattern_match is true, provide regex patterns to match.
+        If ``[metrics] metrics_use_pattern_match`` is ``false``, match only 
the exact metric name prefix.
+        If ``[metrics] metrics_use_pattern_match`` is ``true``, provide regex 
patterns to match.
       version_added: 2.6.0
       type: string
       example: "\"scheduler,executor,dagrun\" or 
\"^scheduler,^executor,heartbeat|timeout\""
@@ -1012,9 +1038,12 @@ metrics:
     metrics_block_list:
       description: |
         Configure a block list (comma separated string) to block certain 
metrics from being emitted.
-        If metrics_allow_list and metrics_block_list are both configured, 
metrics_block_list is ignored.
-        If metrics_use_pattern_match is false, match only the exact metric 
name prefix.
-        If metrics_use_pattern_match is true, provide regex patterns to match.
+        If ``[metrics] metrics_allow_list`` and ``[metrics] 
metrics_block_list`` are both configured,
+        ``[metrics] metrics_block_list`` is ignored.
+
+        If ``[metrics] metrics_use_pattern_match`` is ``false``, match only 
the exact metric name prefix.
+
+        If ``[metrics] metrics_use_pattern_match`` is ``true``, provide regex 
patterns to match.
       version_added: 2.6.0
       type: string
       example: "\"scheduler,executor,dagrun\" or 
\"^scheduler,^executor,heartbeat|timeout\""
@@ -1052,8 +1081,11 @@ metrics:
         A function that validate the StatsD stat name, apply changes to the 
stat name if necessary and return
         the transformed stat name.
 
-        The function should have the following signature:
-        def func_name(stat_name: str) -> str:
+        The function should have the following signature
+
+        .. code-block:: python
+
+            def func_name(stat_name: str) -> str: ...
       version_added: 2.0.0
       type: string
       example: ~
@@ -1067,14 +1099,14 @@ metrics:
       default: "False"
     statsd_datadog_tags:
       description: |
-        List of datadog tags attached to all metrics(e.g: 
key1:value1,key2:value2)
+        List of datadog tags attached to all metrics(e.g: 
``key1:value1,key2:value2``)
       version_added: 2.0.0
       type: string
       example: ~
       default: ""
     statsd_datadog_metrics_tags:
       description: |
-        Set to False to disable metadata tags for some of the emitted metrics
+        Set to ``False`` to disable metadata tags for some of the emitted 
metrics
       version_added: 2.6.0
       type: boolean
       example: ~
@@ -1083,7 +1115,9 @@ metrics:
       description: |
         If you want to utilise your own custom StatsD client set the relevant
         module path below.
-        Note: The module path must exist on your PYTHONPATH for Airflow to 
pick it up
+        Note: The module path must exist on your
+        `PYTHONPATH 
<https://docs.python.org/3/using/cmdline.html#envvar-PYTHONPATH>`
+        for Airflow to pick it up
       version_added: 2.0.0
       type: string
       example: ~
@@ -1092,7 +1126,7 @@ metrics:
       description: |
         If you want to avoid sending all the available metrics tags to StatsD,
         you can configure a block list of prefixes (comma separated) to filter 
out metric tags
-        that start with the elements of the list (e.g: "job_id,run_id")
+        that start with the elements of the list (e.g: ``job_id,run_id``)
       version_added: 2.6.0
       type: string
       example: job_id,run_id,dag_id,task_id
@@ -1143,17 +1177,17 @@ metrics:
       default: "60000"
     otel_debugging_on:
       description: |
-        If True, all metrics are also emitted to the console. Defaults to 
False.
+        If ``True``, all metrics are also emitted to the console. Defaults to 
``False``.
       version_added: 2.7.0
       type: string
       example: ~
       default: "False"
     otel_ssl_active:
       description: |
-        If True, SSL will be enabled.  Defaults to False.
+        If ``True``, SSL will be enabled. Defaults to ``False``.
         To establish an HTTPS connection to the OpenTelemetry collector,
         you need to configure the SSL certificate and key within the 
OpenTelemetry collector's
-        config.yml file.
+        ``config.yml`` file.
       version_added: 2.7.0
       type: string
       example: ~
@@ -1170,8 +1204,10 @@ secrets:
       default: ""
     backend_kwargs:
       description: |
-        The backend_kwargs param is loaded into a dictionary and passed to 
__init__ of secrets backend class.
-        See documentation for the secrets backend you are using. JSON is 
expected.
+        The backend_kwargs param is loaded into a dictionary and passed to 
``__init__``
+        of secrets backend class. See documentation for the secrets backend 
you are using.
+        JSON is expected.
+
         Example for AWS Systems Manager ParameterStore:
         ``{"connections_prefix": "/airflow/connections", "profile_name": 
"default"}``
       version_added: 1.10.10
@@ -1246,9 +1282,11 @@ api:
 
         .. warning::
 
-          This `Experimental REST API 
<https://airflow.readthedocs.io/en/latest/rest-api-ref.html>`__ is
+          This `Experimental REST API
+          
<https://airflow.apache.org/docs/apache-airflow/stable/deprecated-rest-api-ref.html>`__
 is
           deprecated since version 2.0. Please consider using
-          `the Stable REST API 
<https://airflow.readthedocs.io/en/latest/stable-rest-api-ref.html>`__.
+          `the Stable REST API
+          
<https://airflow.apache.org/docs/apache-airflow/stable/stable-rest-api-ref.html>`__.
           For more information on migration, see
           `RELEASE_NOTES.rst 
<https://github.com/apache/airflow/blob/main/RELEASE_NOTES.rst>`_
       version_added: 2.0.0
@@ -1258,7 +1296,8 @@ api:
     auth_backends:
       description: |
         Comma separated list of auth backends to authenticate users of the 
API. See
-        
https://airflow.apache.org/docs/apache-airflow/stable/security/api.html for 
possible values.
+        `Security: API
+        
<https://airflow.apache.org/docs/apache-airflow/stable/security/api.html>`__ 
for possible values.
         ("airflow.api.auth.backend.default" allows all requests for historic 
reasons)
       version_added: 2.3.0
       type: string
@@ -1327,8 +1366,8 @@ api:
       default: ""
     enable_xcom_deserialize_support:
       description: |
-        Indicates whether the *xcomEntries* endpoint supports the *deserialize*
-        flag. If set to False, setting this flag in a request would result in a
+        Indicates whether the **xcomEntries** endpoint supports the 
**deserialize**
+        flag. If set to ``False``, setting this flag in a request would result 
in a
         400 Bad Request error.
       type: boolean
       version_added: 2.7.0
@@ -1404,7 +1443,8 @@ operators:
     allow_illegal_arguments:
       description: |
         Is allowed to pass additional/unused arguments (args, kwargs) to the 
BaseOperator operator.
-        If set to False, an exception will be thrown, otherwise only the 
console message will be displayed.
+        If set to ``False``, an exception will be thrown,
+        otherwise only the console message will be displayed.
       version_added: 2.0.0
       type: string
       example: ~
@@ -1438,7 +1478,7 @@ webserver:
     default_ui_timezone:
       description: |
         Default timezone to display all dates in the UI, can be UTC, system, or
-        any IANA timezone string (e.g. Europe/Amsterdam). If left empty the
+        any IANA timezone string (e.g. **Europe/Amsterdam**). If left empty the
         default value of core/default_timezone will be used
       version_added: 1.10.10
       type: string
@@ -1477,17 +1517,17 @@ webserver:
       default: ""
     session_backend:
       description: |
-        The type of backend used to store web session data, can be `database` 
or `securecookie`. For the
-        `database` backend, sessions are store in the database (in `session` 
table) and they can be
+        The type of backend used to store web session data, can be 
``database`` or ``securecookie``. For the
+        ``database`` backend, sessions are store in the database and they can 
be
         managed there (for example when you reset password of the user, all 
sessions for that user are
-        deleted). For the `securecookie` backend, sessions are stored in 
encrypted cookies on the client
-        side. The `securecookie` mechanism is 'lighter' than database backend, 
but sessions are not deleted
+        deleted). For the ``securecookie`` backend, sessions are stored in 
encrypted cookies on the client
+        side. The ``securecookie`` mechanism is 'lighter' than database 
backend, but sessions are not deleted
         when you reset password of the user, which means that other than 
waiting for expiry time, the only
         way to invalidate all sessions for a user is to change secret_key and 
restart webserver (which
         also invalidates and logs out all other user's sessions).
 
-        When you are using `database` backend, make sure to keep your database 
session table small
-        by periodically running `airflow db clean --table session` command, 
especially if you have
+        When you are using ``database`` backend, make sure to keep your 
database session table small
+        by periodically running ``airflow db clean --table session`` command, 
especially if you have
         automated API calls that will create a new session for each call 
rather than reuse the sessions
         stored in browser cookies.
       version_added: 2.2.4
@@ -1526,9 +1566,9 @@ webserver:
       default: "6000"
     reload_on_plugin_change:
       description: |
-        If set to True, Airflow will track files in plugins_folder directory. 
When it detects changes,
-        then reload the gunicorn. If set to True, gunicorn starts without 
preloading, which is slower, uses
-        more memory, and may cause race conditions. Avoid setting this to True 
in production.
+        If set to ``True``, Airflow will track files in plugins_folder 
directory. When it detects changes,
+        then reload the gunicorn. If set to ``True``, gunicorn starts without 
preloading, which is slower,
+        uses more memory, and may cause race conditions. Avoid setting this to 
``True`` in production.
       version_added: 1.10.11
       type: boolean
       example: ~
@@ -1557,9 +1597,19 @@ webserver:
     worker_class:
       description: |
         The worker class gunicorn should use. Choices include
-        sync (default), eventlet, gevent. Note when using gevent you might 
also want to set the
-        "_AIRFLOW_PATCH_GEVENT" environment variable to "1" to make sure 
gevent patching is done as
-        early as possible.
+        ``sync`` (default), ``eventlet``, ``gevent``.
+
+        .. warning::
+
+            When using ``gevent`` you might also want to set the 
``_AIRFLOW_PATCH_GEVENT``
+            environment variable to ``"1"`` to make sure gevent patching is 
done as early as possible.
+
+            See related Issues / PRs for more details:
+
+            * https://github.com/benoitc/gunicorn/issues/2796
+            * https://github.com/apache/airflow/issues/8212
+            * https://github.com/apache/airflow/pull/28283
+
       version_added: ~
       type: string
       example: ~
@@ -1581,16 +1631,17 @@ webserver:
     access_logformat:
       description: |
         Access log format for gunicorn webserver.
-        default format is %%(h)s %%(l)s %%(u)s %%(t)s "%%(r)s" %%(s)s %%(b)s 
"%%(f)s" "%%(a)s"
-        documentation - 
https://docs.gunicorn.org/en/stable/settings.html#access-log-format
+        default format is ``%%(h)s %%(l)s %%(u)s %%(t)s "%%(r)s" %%(s)s %%(b)s 
"%%(f)s" "%%(a)s"``
+        See `Gunicorn Settings: 'access_log_format' Reference
+        
<https://docs.gunicorn.org/en/stable/settings.html#access-log-format>`__ for 
more details
       version_added: 2.0.0
       type: string
       example: ~
       default: ""
     expose_config:
       description: |
-        Expose the configuration file in the web server. Set to 
"non-sensitive-only" to show all values
-        except those that have security implications. "True" shows all values. 
"False" hides the
+        Expose the configuration file in the web server. Set to 
``non-sensitive-only`` to show all values
+        except those that have security implications. ``True`` shows all 
values. ``False`` hides the
         configuration completely.
       version_added: ~
       type: string
@@ -1728,35 +1779,44 @@ webserver:
     proxy_fix_x_for:
       description: |
         Number of values to trust for ``X-Forwarded-For``.
-        More info: 
https://werkzeug.palletsprojects.com/en/0.16.x/middleware/proxy_fix/
+        See `Werkzeug: X-Forwarded-For Proxy Fix
+        
<https://werkzeug.palletsprojects.com/en/2.3.x/middleware/proxy_fix/>`__ for 
more details.
       version_added: 1.10.7
       type: integer
       example: ~
       default: "1"
     proxy_fix_x_proto:
       description: |
-        Number of values to trust for ``X-Forwarded-Proto``
+        Number of values to trust for ``X-Forwarded-Proto``.
+        See `Werkzeug: X-Forwarded-For Proxy Fix
+        
<https://werkzeug.palletsprojects.com/en/2.3.x/middleware/proxy_fix/>`__ for 
more details.
       version_added: 1.10.7
       type: integer
       example: ~
       default: "1"
     proxy_fix_x_host:
       description: |
-        Number of values to trust for ``X-Forwarded-Host``
+        Number of values to trust for ``X-Forwarded-Host``.
+        See `Werkzeug: X-Forwarded-For Proxy Fix
+        
<https://werkzeug.palletsprojects.com/en/2.3.x/middleware/proxy_fix/>`__ for 
more details.
       version_added: 1.10.7
       type: integer
       example: ~
       default: "1"
     proxy_fix_x_port:
       description: |
-        Number of values to trust for ``X-Forwarded-Port``
+        Number of values to trust for ``X-Forwarded-Port``.
+        See `Werkzeug: X-Forwarded-For Proxy Fix
+        
<https://werkzeug.palletsprojects.com/en/2.3.x/middleware/proxy_fix/>`__ for 
more details.
       version_added: 1.10.7
       type: integer
       example: ~
       default: "1"
     proxy_fix_x_prefix:
       description: |
-        Number of values to trust for ``X-Forwarded-Prefix``
+        Number of values to trust for ``X-Forwarded-Prefix``.
+        See `Werkzeug: X-Forwarded-For Proxy Fix
+        
<https://werkzeug.palletsprojects.com/en/2.3.x/middleware/proxy_fix/>`__ for 
more details.
       version_added: 1.10.7
       type: integer
       example: ~
@@ -1792,7 +1852,7 @@ webserver:
     analytics_tool:
       description: |
         Send anonymous user activity to your analytics tool
-        choose from google_analytics, segment, metarouter, or matomo
+        choose from ``google_analytics``, ``segment``, ``metarouter``, or 
``matomo``
       version_added: ~
       type: string
       example: ~
@@ -1831,7 +1891,7 @@ webserver:
     session_lifetime_minutes:
       description: |
         The UI cookie lifetime in minutes. User will be logged out from UI 
after
-        ``session_lifetime_minutes`` of non-activity
+        ``[webserver] session_lifetime_minutes`` of non-activity
       version_added: 1.10.13
       type: integer
       example: ~
@@ -1924,8 +1984,8 @@ webserver:
       default: "md5"
     show_trigger_form_if_no_params:
       description: |
-        Behavior of the trigger DAG run button for DAGs without params. False 
to skip and trigger
-        without displaying a form to add a dag_run.conf, True to always 
display the form.
+        Behavior of the trigger DAG run button for DAGs without params. 
``False`` to skip and trigger
+        without displaying a form to add a **dag_run.conf**, ``True`` to 
always display the form.
         The form is displayed always if parameters are defined.
       version_added: 2.7.0
       type: boolean
@@ -1945,7 +2005,7 @@ webserver:
         Displaying the DAG or trigger form in web UI provides the DAG author 
the potential to
         inject malicious code into clients browsers. To ensure the web UI is 
safe by default,
         raw HTML is disabled by default. If you trust your DAG authors, you 
can enable HTML
-        support in markdown by setting this option to True.
+        support in markdown by setting this option to ``True``.
 
         This parameter also enables the deprecated fields ``description_html`` 
and
         ``custom_html_form`` in DAG params until the feature is removed in a 
future version.
@@ -1964,7 +2024,8 @@ webserver:
       description: |
         Require confirmation when changing a DAG in the web UI. This is to 
prevent accidental changes
         to a DAG that may be running on sensitive environments like production.
-        When set to True, confirmation dialog will be shown when a user tries 
to Pause/Unpause, Trigger a DAG
+        When set to ``True``, confirmation dialog will be shown when a user 
tries to Pause/Unpause,
+        Trigger a DAG
       version_added: 2.9.0
       type: boolean
       example: ~
@@ -2093,7 +2154,7 @@ smtp:
       default: "25"
     smtp_mail_from:
       description: |
-        Specifies the default "from" email address used when Airflow sends 
email notifications.
+        Specifies the default **from** email address used when Airflow sends 
email notifications.
       version_added: ~
       type: string
       example: ~
@@ -2115,9 +2176,10 @@ smtp:
       default: "5"
 sentry:
   description: |
-    Sentry (https://docs.sentry.io) integration. Here you can supply
-    additional configuration options based on the Python platform. See:
-    https://docs.sentry.io/error-reporting/configuration/?platform=python.
+    `Sentry <https://docs.sentry.io>`__ integration. Here you can supply
+    additional configuration options based on the Python platform.
+    See `Python / Configuration / Basic Options
+    <https://docs.sentry.io/platforms/python/configuration/options/>`__ for 
more details.
     Unsupported options: ``integrations``, ``in_app_include``, 
``in_app_exclude``,
     ``ignore_errors``, ``before_breadcrumb``, ``transport``.
   options:
@@ -2165,7 +2227,7 @@ scheduler:
       description: |
         The frequency (in seconds) at which the LocalTaskJob should send 
heartbeat signals to the
         scheduler to notify it's still alive. If this value is set to 0, the 
heartbeat interval will default
-        to the value of scheduler_zombie_task_threshold.
+        to the value of ``[scheduler] scheduler_zombie_task_threshold``.
       version_added: 2.7.0
       type: integer
       example: ~
@@ -2190,7 +2252,7 @@ scheduler:
     min_file_process_interval:
       description: |
         Number of seconds after which a DAG file is parsed. The DAG file is 
parsed every
-        ``min_file_process_interval`` number of seconds. Updates to DAGs are 
reflected after
+        ``[scheduler] min_file_process_interval`` number of seconds. Updates 
to DAGs are reflected after
         this interval. Keeping this number low will increase CPU usage.
       version_added: ~
       type: integer
@@ -2210,7 +2272,7 @@ scheduler:
         How long (in seconds) to wait after we have re-parsed a DAG file 
before deactivating stale
         DAGs (DAGs which are no longer present in the expected files). The 
reason why we need
         this threshold is to account for the time between when the file is 
parsed and when the
-        DAG is loaded. The absolute maximum that this could take is 
`dag_file_processor_timeout`,
+        DAG is loaded. The absolute maximum that this could take is ``[core] 
dag_file_processor_timeout``,
         but when you have a long timeout configured, it results in a 
significant delay in the
         deactivation of stale dags.
       version_added: 2.6.0
@@ -2240,9 +2302,9 @@ scheduler:
       default: "5.0"
     scheduler_health_check_threshold:
       description: |
-        If the last scheduler heartbeat happened more than 
scheduler_health_check_threshold
+        If the last scheduler heartbeat happened more than ``[scheduler] 
scheduler_health_check_threshold``
         ago (in seconds), scheduler is considered unhealthy.
-        This is used by the health check in the "/health" endpoint and in 
`airflow jobs check` CLI
+        This is used by the health check in the **/health** endpoint and in 
``airflow jobs check`` CLI
         for SchedulerJob.
       version_added: 1.10.2
       type: integer
@@ -2251,7 +2313,7 @@ scheduler:
     enable_health_check:
       description: |
         When you start a scheduler, airflow starts a tiny web server
-        subprocess to serve a health check if this is set to True
+        subprocess to serve a health check if this is set to ``True``
       version_added: 2.4.0
       type: boolean
       example: ~
@@ -2316,7 +2378,7 @@ scheduler:
       default: "True"
     ignore_first_depends_on_past_by_default:
       description: |
-        Setting this to True will make first task instance of a task
+        Setting this to ``True`` will make first task instance of a task
         ignore depends_on_past setting. A task instance will be considered
         as the first task instance of a task when there is no task instance
         in the DB with an execution_date earlier than it., i.e. no manual 
marking
@@ -2328,11 +2390,11 @@ scheduler:
     max_tis_per_query:
       description: |
         This changes the batch size of queries in the scheduling main loop.
-        This should not be greater than ``core.parallelism``.
+        This should not be greater than ``[core] parallelism``.
         If this is too high, SQL query performance may be impacted by
         complexity of query predicate, and/or excessive locking.
         Additionally, you may hit the maximum allowable query length for your 
db.
-        Set this to 0 to use the value of ``core.parallelism``
+        Set this to 0 to use the value of ``[core] parallelism``
       version_added: ~
       type: integer
       example: ~
@@ -2340,7 +2402,7 @@ scheduler:
     use_row_level_locking:
       description: |
         Should the scheduler issue ``SELECT ... FOR UPDATE`` in relevant 
queries.
-        If this is set to False then you should not run more than a single
+        If this is set to ``False`` then you should not run more than a single
         scheduler at once
       version_added: 2.0.0
       type: boolean
@@ -2376,8 +2438,8 @@ scheduler:
       description: |
         The scheduler reads dag files to extract the airflow modules that are 
going to be used,
         and imports them ahead of time to avoid having to re-do it for each 
parsing process.
-        This flag can be set to False to disable this behavior in case an 
airflow module needs to be freshly
-        imported each time (at the cost of increased DAG parsing time).
+        This flag can be set to ``False`` to disable this behavior in case an 
airflow module needs
+        to be freshly imported each time (at the cost of increased DAG parsing 
time).
       version_added: 2.6.0
       type: boolean
       example: ~
@@ -2415,7 +2477,7 @@ scheduler:
       default: "False"
     max_callbacks_per_loop:
       description: |
-        Only applicable if `[scheduler]standalone_dag_processor` is true and  
callbacks are stored
+        Only applicable if ``[scheduler] standalone_dag_processor`` is true 
and  callbacks are stored
         in database. Contains maximum number of callbacks that are fetched 
during a single loop.
       version_added: 2.3.0
       type: integer
@@ -2423,7 +2485,7 @@ scheduler:
       default: "20"
     dag_stale_not_seen_duration:
       description: |
-        Only applicable if `[scheduler]standalone_dag_processor` is true.
+        Only applicable if ``[scheduler] standalone_dag_processor`` is true.
         Time in seconds after which dags, which were not updated by Dag 
Processor are deactivated.
       version_added: 2.4.0
       type: integer
@@ -2431,7 +2493,7 @@ scheduler:
       default: "600"
     use_job_schedule:
       description: |
-        Turn off scheduler use of cron intervals by setting this to False.
+        Turn off scheduler use of cron intervals by setting this to ``False``.
         DAGs submitted manually in the web UI or with trigger_dag will still 
run.
       version_added: 1.10.2
       type: boolean
@@ -2462,7 +2524,7 @@ scheduler:
     task_queued_timeout_check_interval:
       description: |
         How often to check for tasks that have been in the queued state for
-        longer than `[scheduler] task_queued_timeout`.
+        longer than ``[scheduler] task_queued_timeout``.
       version_added: 2.6.0
       type: float
       example: ~
@@ -2513,9 +2575,9 @@ triggerer:
       default: "5"
     triggerer_health_check_threshold:
       description: |
-        If the last triggerer heartbeat happened more than 
triggerer_health_check_threshold
+        If the last triggerer heartbeat happened more than ``[triggerer] 
triggerer_health_check_threshold``
         ago (in seconds), triggerer is considered unhealthy.
-        This is used by the health check in the "/health" endpoint and in 
`airflow jobs check` CLI
+        This is used by the health check in the **/health** endpoint and in 
``airflow jobs check`` CLI
         for TriggererJob.
       version_added: 2.7.0
       type: float
diff --git a/tests/cli/commands/test_config_command.py 
b/tests/cli/commands/test_config_command.py
index a4705eaa1a..9a22e1c09f 100644
--- a/tests/cli/commands/test_config_command.py
+++ b/tests/cli/commands/test_config_command.py
@@ -26,6 +26,8 @@ from airflow.cli import cli_parser
 from airflow.cli.commands import config_command
 from tests.test_utils.config import conf_vars
 
+STATSD_CONFIG_BEGIN_WITH = "# `StatsD <https://github.com/statsd/statsd>`"
+
 
 class TestCliConfigList:
     @classmethod
@@ -90,7 +92,7 @@ class TestCliConfigList:
         lines = output.splitlines()
         # comes from metrics description
         assert all(not line.startswith("# Source: ") for line in lines if line)
-        assert any(line.startswith("# StatsD") for line in lines if line)
+        assert any(line.startswith(STATSD_CONFIG_BEGIN_WITH) for line in lines 
if line)
         assert all(not line.startswith("# Example:") for line in lines if line)
         assert all(not line.startswith("# Variable:") for line in lines if 
line)
 
@@ -102,7 +104,7 @@ class TestCliConfigList:
         output = temp_stdout.getvalue()
         lines = output.splitlines()
         assert all(not line.startswith("# Source: ") for line in lines if line)
-        assert all(not line.startswith("# StatsD") for line in lines if line)
+        assert all(not line.startswith(STATSD_CONFIG_BEGIN_WITH) for line in 
lines if line)
         assert any(line.startswith("# Example:") for line in lines if line)
         assert all(not line.startswith("# Variable:") for line in lines if 
line)
 
@@ -114,7 +116,7 @@ class TestCliConfigList:
         output = temp_stdout.getvalue()
         lines = output.splitlines()
         assert all(not line.startswith("# Source: ") for line in lines if line)
-        assert all(not line.startswith("# StatsD") for line in lines if line)
+        assert all(not line.startswith(STATSD_CONFIG_BEGIN_WITH) for line in 
lines if line)
         assert all(not line.startswith("# Example:") for line in lines if line)
         assert any(line.startswith("# Variable:") for line in lines if line)
 
@@ -126,7 +128,7 @@ class TestCliConfigList:
         output = temp_stdout.getvalue()
         lines = output.splitlines()
         assert any(line.startswith("# Source: ") for line in lines if line)
-        assert all(not line.startswith("# StatsD") for line in lines if line)
+        assert all(not line.startswith(STATSD_CONFIG_BEGIN_WITH) for line in 
lines if line)
         assert all(not line.startswith("# Example:") for line in lines if line)
         assert all(not line.startswith("# Variable:") for line in lines if 
line)
 
@@ -138,7 +140,7 @@ class TestCliConfigList:
         output = temp_stdout.getvalue()
         lines = output.splitlines()
         assert all(not line.startswith("# Source: ") for line in lines if line)
-        assert any(line.startswith("# StatsD") for line in lines if line)
+        assert any(line.startswith(STATSD_CONFIG_BEGIN_WITH) for line in lines 
if line)
         assert any(not line.startswith("# Example:") for line in lines if line)
         assert any(not line.startswith("# Example:") for line in lines if line)
         assert any(line.startswith("# Variable:") for line in lines if line)

Reply via email to