This is an automated email from the ASF dual-hosted git repository.
ephraimanierobi pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/airflow.git
The following commit(s) were added to refs/heads/main by this push:
new 1571f80 Add pre-commit hook for common misspelling check in files
(#18964)
1571f80 is described below
commit 1571f80546853688778c2a3ec5194e5c8be0edbd
Author: Ephraim Anierobi <[email protected]>
AuthorDate: Thu Oct 14 19:37:08 2021 +0100
Add pre-commit hook for common misspelling check in files (#18964)
This PR adds codespell to the pre-commit hooks. This will specifically help
us a bit in resolving sphinx errors.
From the project page:
It does not check for word membership in a complete dictionary, but instead
looks for a set of common misspellings.
Therefore it should catch errors like "adn", but it will not catch
"adnasdfasdf".
This also means it shouldn't generate false-positives when you use a niche
term it doesn't know about.
This means the sphinx errors are not solved completely.
---
.github/workflows/build-images.yml | 4 ++--
.pre-commit-config.yaml | 12 ++++++++++++
BREEZE.rst | 2 +-
STATIC_CODE_CHECKS.rst | 2 ++
UPDATING.md | 2 +-
airflow/_vendor/connexion/__init__.py | 2 +-
airflow/example_dags/plugins/workday.py | 2 +-
airflow/providers/cncf/kubernetes/utils/pod_launcher.py | 2 +-
airflow/providers/google/cloud/hooks/bigquery.py | 2 +-
.../providers/microsoft/azure/operators/wasb_delete_blob.py | 2 +-
airflow/providers/microsoft/azure/sensors/wasb.py | 2 +-
airflow/providers/ssh/hooks/ssh.py | 8 ++++----
airflow/settings.py | 2 +-
airflow/templates.py | 2 +-
airflow/utils/db.py | 2 +-
airflow/www/fab_security/manager.py | 6 +++---
airflow/www/static/js/graph.js | 2 +-
airflow/www/static/js/tree.js | 2 +-
breeze | 2 +-
breeze-complete | 1 +
chart/README.md | 2 +-
chart/tests/helm_template_generator.py | 2 +-
dev/README_RELEASE_PROVIDER_PACKAGES.md | 2 +-
dev/import_all_classes.py | 2 +-
.../secrets-backends/aws-secrets-manager.rst | 2 +-
docs/apache-airflow-providers-ssh/connections/ssh.rst | 2 +-
docs/apache-airflow/howto/set-up-database.rst | 4 ++--
docs/apache-airflow/modules_management.rst | 2 +-
docs/apache-airflow/pipeline_example.csv | 4 ++--
docs/apache-airflow/security/kerberos.rst | 2 +-
docs/apache-airflow/security/webserver.rst | 2 +-
docs/helm-chart/index.rst | 2 +-
docs/helm-chart/production-guide.rst | 4 ++--
docs/spelling_wordlist.txt | 7 +++++++
scripts/ci/libraries/_initialization.sh | 2 +-
scripts/ci/pre_commit/pre_commit_yaml_to_cfg.py | 2 +-
scripts/in_container/prod/entrypoint_prod.sh | 2 +-
tests/dag_processing/test_manager.py | 2 +-
tests/models/test_taskinstance.py | 2 +-
tests/providers/ssh/hooks/test_ssh.py | 2 +-
tests/sensors/test_external_task_sensor.py | 2 +-
tests/task/task_runner/test_base_task_runner.py | 2 +-
42 files changed, 69 insertions(+), 47 deletions(-)
diff --git a/.github/workflows/build-images.yml
b/.github/workflows/build-images.yml
index 612ffb5..3f7c51a 100644
--- a/.github/workflows/build-images.yml
+++ b/.github/workflows/build-images.yml
@@ -307,12 +307,12 @@ jobs:
- name: "Build PROD images ${{ matrix.python-version }}:${{
env.GITHUB_REGISTRY_PUSH_IMAGE_TAG }}"
run: ./scripts/ci/images/ci_prepare_prod_image_on_ci.sh
env:
- # GITHUB_REGISTRY_PULL_IMAGE_TAG is overriden to latest in order to
build PROD image using "latest"
+ # GITHUB_REGISTRY_PULL_IMAGE_TAG is overridden to latest in order to
build PROD image using "latest"
GITHUB_REGISTRY_PULL_IMAGE_TAG: "latest"
- name: "Push PROD images ${{ matrix.python-version }}:${{
env.GITHUB_REGISTRY_PUSH_IMAGE_TAG }}"
run: ./scripts/ci/images/ci_push_production_images.sh
env:
- # GITHUB_REGISTRY_PULL_IMAGE_TAG is overriden to latest in order to
build PROD image using "latest"
+ # GITHUB_REGISTRY_PULL_IMAGE_TAG is overridden to latest in order to
build PROD image using "latest"
GITHUB_REGISTRY_PULL_IMAGE_TAG: "latest"
cancel-on-ci-build:
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index 0003071..896f9d3 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -258,6 +258,18 @@ repos:
exclude: |
(?x)
^airflow/_vendor/
+ - repo: https://github.com/codespell-project/codespell
+ rev: v2.1.0
+ hooks:
+ - id: codespell
+ name: Run codespell to check for common misspellings in files
+ entry: codespell
+ language: python
+ types: [text]
+ exclude:
^airflow/_vendor/|^CHANGELOG.txt|^airflow/www/static/css/material-icons.css
+ args:
+ - --ignore-words=docs/spelling_wordlist.txt
+ -
--skip=docs/*/commits.rst,airflow/providers/*/*.rst,*.lock,INTHEWILD.md,*.min.js
- repo: local
hooks:
- id: lint-openapi
diff --git a/BREEZE.rst b/BREEZE.rst
index 711da47..e4a1ca0 100644
--- a/BREEZE.rst
+++ b/BREEZE.rst
@@ -2191,7 +2191,7 @@ This is the current syntax for `./breeze <./breeze>`_:
check-executables-have-shebangs check-extras-order
check-hooks-apply
check-integrations check-merge-conflict check-xml
daysago-import-check
debug-statements detect-private-key doctoc
dont-use-safe-filter end-of-file-fixer
- fix-encoding-pragma flake8 flynt forbid-tabs helm-lint
identity
+ fix-encoding-pragma flake8 flynt codespell forbid-tabs
helm-lint identity
incorrect-use-of-LoggingMixin insert-license isort
json-schema language-matters
lint-dockerfile lint-openapi markdownlint mermaid
mixed-line-ending mypy mypy-helm
no-providers-in-core-examples no-relative-imports
pre-commit-descriptions
diff --git a/STATIC_CODE_CHECKS.rst b/STATIC_CODE_CHECKS.rst
index 81bc6de..51391a5 100644
--- a/STATIC_CODE_CHECKS.rst
+++ b/STATIC_CODE_CHECKS.rst
@@ -188,6 +188,8 @@ require Breeze Docker images to be installed locally.
------------------------------------
---------------------------------------------------------------- ------------
``flynt`` Runs flynt
------------------------------------
---------------------------------------------------------------- ------------
+``codespell`` Checks for common misspellings in files.
+------------------------------------
---------------------------------------------------------------- ------------
``forbid-tabs`` Fails if tabs are used in the project
------------------------------------
---------------------------------------------------------------- ------------
``helm-lint`` Verifies if helm lint passes for the
chart
diff --git a/UPDATING.md b/UPDATING.md
index 8ffd87d..cef97e1 100644
--- a/UPDATING.md
+++ b/UPDATING.md
@@ -283,7 +283,7 @@ No breaking changes.
### `activate_dag_runs` argument of the function `clear_task_instances` is
replaced with `dag_run_state`
-To achieve the previous default behaviour of `clear_task_instances` with
`activate_dag_runs=True`, no change is needed. To achieve the previous
behaviour of `activate_dag_runs=False`, pass `dag_run_state=False` instead.
(The previous paramater is still accepted, but is deprecated)
+To achieve the previous default behaviour of `clear_task_instances` with
`activate_dag_runs=True`, no change is needed. To achieve the previous
behaviour of `activate_dag_runs=False`, pass `dag_run_state=False` instead.
(The previous parameter is still accepted, but is deprecated)
### `dag.set_dag_runs_state` is deprecated
diff --git a/airflow/_vendor/connexion/__init__.py
b/airflow/_vendor/connexion/__init__.py
index 8286d6c..7852d49 100755
--- a/airflow/_vendor/connexion/__init__.py
+++ b/airflow/_vendor/connexion/__init__.py
@@ -6,7 +6,7 @@ from .apis import AbstractAPI # NOQA
from .apps import AbstractApp # NOQA
from .decorators.produces import NoContent # NOQA
from .exceptions import ProblemException # NOQA
-# add operation for backwards compatability
+# add operation for backwards compatibility
from .operations import compat
from .problem import problem # NOQA
from .resolver import Resolution, Resolver, RestyResolver # NOQA
diff --git a/airflow/example_dags/plugins/workday.py
b/airflow/example_dags/plugins/workday.py
index 84a5ff8c..f856739 100644
--- a/airflow/example_dags/plugins/workday.py
+++ b/airflow/example_dags/plugins/workday.py
@@ -16,7 +16,7 @@
# specific language governing permissions and limitations
# under the License.
-"""Plugin to demostrate timetable registration and accomdate example DAGs."""
+"""Plugin to demonstrate timetable registration and accommodate example
DAGs."""
# [START howto_timetable]
from datetime import timedelta
diff --git a/airflow/providers/cncf/kubernetes/utils/pod_launcher.py
b/airflow/providers/cncf/kubernetes/utils/pod_launcher.py
index 671d260..1eda041 100644
--- a/airflow/providers/cncf/kubernetes/utils/pod_launcher.py
+++ b/airflow/providers/cncf/kubernetes/utils/pod_launcher.py
@@ -263,7 +263,7 @@ class PodLauncher(LoggingMixin):
)
except BaseHTTPError:
self.log.exception('There was an error reading the kubernetes
API.')
- # Reraise to be catched by self.monitor_pod.
+ # Reraise to be caught by self.monitor_pod.
raise
@tenacity.retry(stop=tenacity.stop_after_attempt(3),
wait=tenacity.wait_exponential(), reraise=True)
diff --git a/airflow/providers/google/cloud/hooks/bigquery.py
b/airflow/providers/google/cloud/hooks/bigquery.py
index ba2ae50..1aa95ed 100644
--- a/airflow/providers/google/cloud/hooks/bigquery.py
+++ b/airflow/providers/google/cloud/hooks/bigquery.py
@@ -1422,7 +1422,7 @@ class BigQueryHook(GoogleBaseHook, DbApiHook):
# Turn schema_field_updates into a dict keyed on field names
schema_fields_updates = {field["name"]: field for field in
deepcopy(schema_fields_updates)}
- # Create a new dict for storing the new schema, initated based on
the current_schema
+ # Create a new dict for storing the new schema, initiated based on
the current_schema
# as of Python 3.6, dicts retain order.
new_schema = {field["name"]: field for field in
deepcopy(current_schema)}
diff --git a/airflow/providers/microsoft/azure/operators/wasb_delete_blob.py
b/airflow/providers/microsoft/azure/operators/wasb_delete_blob.py
index 3e8c1c5..8cc0849 100644
--- a/airflow/providers/microsoft/azure/operators/wasb_delete_blob.py
+++ b/airflow/providers/microsoft/azure/operators/wasb_delete_blob.py
@@ -65,7 +65,7 @@ class WasbDeleteBlobOperator(BaseOperator):
self.ignore_if_missing = ignore_if_missing
def execute(self, context: dict) -> None:
- self.log.info('Deleting blob: %s\nin wasb://%s', self.blob_name,
self.container_name)
+ self.log.info('Deleting blob: %s\n in wasb://%s', self.blob_name,
self.container_name)
hook = WasbHook(wasb_conn_id=self.wasb_conn_id)
hook.delete_file(
diff --git a/airflow/providers/microsoft/azure/sensors/wasb.py
b/airflow/providers/microsoft/azure/sensors/wasb.py
index 8a345bf..e78ec1d 100644
--- a/airflow/providers/microsoft/azure/sensors/wasb.py
+++ b/airflow/providers/microsoft/azure/sensors/wasb.py
@@ -57,7 +57,7 @@ class WasbBlobSensor(BaseSensorOperator):
self.check_options = check_options
def poke(self, context: dict):
- self.log.info('Poking for blob: %s\nin wasb://%s', self.blob_name,
self.container_name)
+ self.log.info('Poking for blob: %s\n in wasb://%s', self.blob_name,
self.container_name)
hook = WasbHook(wasb_conn_id=self.wasb_conn_id)
return hook.check_for_blob(self.container_name, self.blob_name,
**self.check_options)
diff --git a/airflow/providers/ssh/hooks/ssh.py
b/airflow/providers/ssh/hooks/ssh.py
index e0c5c96..cc4ef1c 100644
--- a/airflow/providers/ssh/hooks/ssh.py
+++ b/airflow/providers/ssh/hooks/ssh.py
@@ -261,13 +261,13 @@ class SSHHook(BaseHook):
if not self.allow_host_key_change:
self.log.warning(
- 'Remote Identification Change is not verified. '
- 'This wont protect against Man-In-The-Middle attacks'
+ "Remote Identification Change is not verified. "
+ "This won't protect against Man-In-The-Middle attacks"
)
client.load_system_host_keys()
if self.no_host_key_check:
- self.log.warning('No Host Key Verification. This wont protect
against Man-In-The-Middle attacks')
+ self.log.warning("No Host Key Verification. This won't protect
against Man-In-The-Middle attacks")
# Default is RejectPolicy
client.set_missing_host_key_policy(paramiko.AutoAddPolicy())
else:
@@ -400,7 +400,7 @@ class SSHHook(BaseHook):
for pkey_class in self._pkey_loaders:
try:
key = pkey_class.from_private_key(StringIO(private_key),
password=passphrase)
- # Test it acutally works. If Paramiko loads an openssh
generated key, sometimes it will
+ # Test it actually works. If Paramiko loads an openssh
generated key, sometimes it will
# happily load it as the wrong type, only to fail when
actually used.
key.sign_ssh_data(b'')
return key
diff --git a/airflow/settings.py b/airflow/settings.py
index 9a456ba..3df8248 100644
--- a/airflow/settings.py
+++ b/airflow/settings.py
@@ -550,7 +550,7 @@ MASK_SECRETS_IN_LOGS = False
# Display alerts on the dashboard
# Useful for warning about setup issues or announcing changes to end users
-# List of UIAlerts, which allows for specifiying the message, category, and
roles the
+# List of UIAlerts, which allows for specifying the message, category, and
roles the
# message should be shown to. For example:
# from airflow.www.utils import UIAlert
#
diff --git a/airflow/templates.py b/airflow/templates.py
index 7cbd556..690951e 100644
--- a/airflow/templates.py
+++ b/airflow/templates.py
@@ -32,7 +32,7 @@ class
SandboxedEnvironment(jinja2.sandbox.SandboxedEnvironment):
Allow access to ``_`` prefix vars (but not ``__``).
Unlike the stock SandboxedEnvironment, we allow access to "private"
attributes (ones starting with
- ``_``) whilst still blocking internal or truely private attributes
(``__`` prefixed ones).
+ ``_``) whilst still blocking internal or truly private attributes
(``__`` prefixed ones).
"""
return not jinja2.sandbox.is_internal_attribute(obj, attr)
diff --git a/airflow/utils/db.py b/airflow/utils/db.py
index 17522d3..fc0dc44 100644
--- a/airflow/utils/db.py
+++ b/airflow/utils/db.py
@@ -771,7 +771,7 @@ def check_task_tables_without_matching_dagruns(session) ->
Iterable[str]:
try:
metadata.reflect(only=[model.__tablename__])
except exc.InvalidRequestError:
- # Table doesn't exist, but try the other ones incase the user is
upgrading from an _old_ DB
+ # Table doesn't exist, but try the other ones in case the user is
upgrading from an _old_ DB
# version
pass
diff --git a/airflow/www/fab_security/manager.py
b/airflow/www/fab_security/manager.py
index 85341e9..997d70b 100644
--- a/airflow/www/fab_security/manager.py
+++ b/airflow/www/fab_security/manager.py
@@ -857,7 +857,7 @@ class BaseSecurityManager:
if len(self.auth_roles_mapping) > 0:
request_fields.append(self.auth_ldap_group_field)
- # preform the LDAP search
+ # perform the LDAP search
log.debug(
"LDAP search for '%s' with fields %s in scope '%s'"
% (filter_str, request_fields, self.auth_ldap_search)
@@ -1017,7 +1017,7 @@ class BaseSecurityManager:
user_attributes = {}
# Flow 1 - (Indirect Search Bind):
- # - in this flow, special bind credentials are used to preform the
+ # - in this flow, special bind credentials are used to perform the
# LDAP search
# - in this flow, AUTH_LDAP_SEARCH must be set
if self.auth_ldap_bind_user:
@@ -1051,7 +1051,7 @@ class BaseSecurityManager:
# Flow 2 - (Direct Search Bind):
# - in this flow, the credentials provided by the end-user are
used
- # to preform the LDAP search
+ # to perform the LDAP search
# - in this flow, we only search LDAP if AUTH_LDAP_SEARCH is set
# - features like AUTH_USER_REGISTRATION &
AUTH_ROLES_SYNC_AT_LOGIN
# will only work if AUTH_LDAP_SEARCH is set
diff --git a/airflow/www/static/js/graph.js b/airflow/www/static/js/graph.js
index 097c861..6671eae 100644
--- a/airflow/www/static/js/graph.js
+++ b/airflow/www/static/js/graph.js
@@ -400,7 +400,7 @@ function startOrStopRefresh() {
$('#auto_refresh').change(() => {
if ($('#auto_refresh').is(':checked')) {
- // Run an initial refesh before starting interval if manually turned on
+ // Run an initial refresh before starting interval if manually turned on
handleRefresh();
localStorage.removeItem('disableAutoRefresh');
} else {
diff --git a/airflow/www/static/js/tree.js b/airflow/www/static/js/tree.js
index 741224d..de79cb3 100644
--- a/airflow/www/static/js/tree.js
+++ b/airflow/www/static/js/tree.js
@@ -473,7 +473,7 @@ document.addEventListener('DOMContentLoaded', () => {
$('#auto_refresh').change(() => {
if ($('#auto_refresh').is(':checked')) {
- // Run an initial refesh before starting interval if manually turned on
+ // Run an initial refresh before starting interval if manually turned on
handleRefresh();
localStorage.removeItem('disableAutoRefresh');
diff --git a/breeze b/breeze
index 4a2c80d..2dd7fab 100755
--- a/breeze
+++ b/breeze
@@ -149,7 +149,7 @@ function breeze::setup_default_breeze_constants() {
AIRFLOW_SOURCES_TO=${AIRFLOW_SOURCES_TO:="/opt/airflow"}
export AIRFLOW_SOURCES_TO
- # Unlike in CI scripts, in breeze by default production image ist
installed from sources
+ # Unlike in CI scripts, in breeze by default production image is installed
from sources
export AIRFLOW_INSTALLATION_METHOD="."
# If it set is set to specified version, then the source version of Airflow
diff --git a/breeze-complete b/breeze-complete
index 0b7e8ab..1e1eb99 100644
--- a/breeze-complete
+++ b/breeze-complete
@@ -102,6 +102,7 @@ end-of-file-fixer
fix-encoding-pragma
flake8
flynt
+codespell
forbid-tabs
helm-lint
identity
diff --git a/chart/README.md b/chart/README.md
index db2ffc5..b4e38b4 100644
--- a/chart/README.md
+++ b/chart/README.md
@@ -40,7 +40,7 @@ cluster using the [Helm](https://helm.sh) package manager.
* Supported Airflow version: ``1.10+``, ``2.0+``
* Supported database backend: ``PostgresSQL``, ``MySQL``
* Autoscaling for ``CeleryExecutor`` provided by KEDA
-* PostgresSQL and PgBouncer with a battle-tested configuration
+* PostgreSQL and PgBouncer with a battle-tested configuration
* Monitoring:
* StatsD/Prometheus metrics for Airflow
* Prometheus metrics for PgBouncer
diff --git a/chart/tests/helm_template_generator.py
b/chart/tests/helm_template_generator.py
index 8c9aff5..af4d1ba 100644
--- a/chart/tests/helm_template_generator.py
+++ b/chart/tests/helm_template_generator.py
@@ -80,7 +80,7 @@ def create_validator(api_version, kind, kubernetes_version):
def validate_k8s_object(instance, kubernetes_version):
- # Skip PostgresSQL chart
+ # Skip PostgreSQL chart
labels = jmespath.search("metadata.labels", instance)
if "helm.sh/chart" in labels:
chart = labels["helm.sh/chart"]
diff --git a/dev/README_RELEASE_PROVIDER_PACKAGES.md
b/dev/README_RELEASE_PROVIDER_PACKAGES.md
index 3edb68e..f5df6f8 100644
--- a/dev/README_RELEASE_PROVIDER_PACKAGES.md
+++ b/dev/README_RELEASE_PROVIDER_PACKAGES.md
@@ -212,7 +212,7 @@ rm -rf ${AIRFLOW_REPO_ROOT}/dist/*
./breeze prepare-provider-packages --version-suffix-for-pypi rc1
--package-format both
```
-if you ony build few packages, run:
+if you only build few packages, run:
```shell script
./breeze prepare-provider-packages --version-suffix-for-pypi rc1
--package-format both \
diff --git a/dev/import_all_classes.py b/dev/import_all_classes.py
index 67a76c8..54cd747 100755
--- a/dev/import_all_classes.py
+++ b/dev/import_all_classes.py
@@ -45,7 +45,7 @@ def import_all_classes(
:param provider_ids - provider ids that should be loaded.
:param print_imports - if imported class should also be printed in output
:param print_skips - if skipped classes should also be printed in output
- :return: tupple of list of all imported classes and all warnings generated
+ :return: tuple of list of all imported classes and all warnings generated
"""
imported_classes = []
tracebacks = []
diff --git
a/docs/apache-airflow-providers-amazon/secrets-backends/aws-secrets-manager.rst
b/docs/apache-airflow-providers-amazon/secrets-backends/aws-secrets-manager.rst
index 692b77c..5ceaa39 100644
---
a/docs/apache-airflow-providers-amazon/secrets-backends/aws-secrets-manager.rst
+++
b/docs/apache-airflow-providers-amazon/secrets-backends/aws-secrets-manager.rst
@@ -104,7 +104,7 @@ For example, if you want to set parameter
``connections_prefix`` to ``"airflow/c
backend =
airflow.providers.amazon.aws.secrets.secrets_manager.SecretsManagerBackend
backend_kwargs = {"connections_prefix": "airflow/connections",
"variables_prefix": null, "profile_name": "default"}
-Example of storing Google Secrets in AWS Secrets Manger
+Example of storing Google Secrets in AWS Secrets Manager
""""""""""""""""""""""""""""""""""""""""""""""""""""""""
For connecting to a google cloud conn, all the fields must be in the extra
field, and their names follow the pattern
``extra_google_cloud_platform__value``. For example:
diff --git a/docs/apache-airflow-providers-ssh/connections/ssh.rst
b/docs/apache-airflow-providers-ssh/connections/ssh.rst
index c9c109a..3cb0e0d 100644
--- a/docs/apache-airflow-providers-ssh/connections/ssh.rst
+++ b/docs/apache-airflow-providers-ssh/connections/ssh.rst
@@ -51,7 +51,7 @@ Extra (optional)
* ``timeout`` - Deprecated - use conn_timeout instead.
* ``compress`` - ``true`` to ask the remote client/server to compress
traffic; ``false`` to refuse compression. Default is ``true``.
* ``no_host_key_check`` - Set to ``false`` to restrict connecting to hosts
with no entries in ``~/.ssh/known_hosts`` (Hosts file). This provides maximum
protection against trojan horse attacks, but can be troublesome when the
``/etc/ssh/ssh_known_hosts`` file is poorly maintained or connections to new
hosts are frequently made. This option forces the user to manually add all new
hosts. Default is ``true``, ssh will automatically add new host keys to the
user known hosts files.
- * ``allow_host_key_change`` - Set to ``true`` if you want to allow
connecting to hosts that has host key changed or when you get 'REMOTE HOST
IDENTIFICATION HAS CHANGED' error. This wont protect against Man-In-The-Middle
attacks. Other possible solution is to remove the host entry from
``~/.ssh/known_hosts`` file. Default is ``false``.
+ * ``allow_host_key_change`` - Set to ``true`` if you want to allow
connecting to hosts that has host key changed or when you get 'REMOTE HOST
IDENTIFICATION HAS CHANGED' error. This won't protect against
Man-In-The-Middle attacks. Other possible solution is to remove the host entry
from ``~/.ssh/known_hosts`` file. Default is ``false``.
* ``look_for_keys`` - Set to ``false`` if you want to disable searching
for discoverable private key files in ``~/.ssh/``
* ``host_key`` - The base64 encoded ssh-rsa public key of the host or
"ssh-<key type> <key data>" (as you would find in the ``known_hosts`` file).
Specifying this allows making the connection if and only if the public key of
the endpoint matches this value.
diff --git a/docs/apache-airflow/howto/set-up-database.rst
b/docs/apache-airflow/howto/set-up-database.rst
index 932f15a..0c2a61e 100644
--- a/docs/apache-airflow/howto/set-up-database.rst
+++ b/docs/apache-airflow/howto/set-up-database.rst
@@ -27,7 +27,7 @@ The document below describes the database engine
configurations, the necessary c
Choosing database backend
-------------------------
-If you want to take a real test drive of Airflow, you should consider setting
up a database backend to **MySQL**, **PostgresSQL** , **MsSQL**.
+If you want to take a real test drive of Airflow, you should consider setting
up a database backend to **MySQL**, **PostgreSQL** , **MsSQL**.
By default, Airflow uses **SQLite**, which is intended for development
purposes only.
Airflow supports the following database engine versions, so make sure which
version you have. Old versions may not support all SQL statements.
@@ -230,7 +230,7 @@ If you use a current Postgres user with custom search_path,
search_path can be c
ALTER USER airflow_user SET search_path = public;
-For more information regarding setup of the PostgresSQL connection, see
`PostgreSQL dialect
<https://docs.sqlalchemy.org/en/13/dialects/postgresql.html>`__ in SQLAlchemy
documentation.
+For more information regarding setup of the PostgreSQL connection, see
`PostgreSQL dialect
<https://docs.sqlalchemy.org/en/13/dialects/postgresql.html>`__ in SQLAlchemy
documentation.
.. note::
diff --git a/docs/apache-airflow/modules_management.rst
b/docs/apache-airflow/modules_management.rst
index 8488a58..4e61d27 100644
--- a/docs/apache-airflow/modules_management.rst
+++ b/docs/apache-airflow/modules_management.rst
@@ -112,7 +112,7 @@ In the case above, there are the ways you could import the
python files:
.. code-block:: python
from my_company.common_package.common_module import SomeClass
- from my_company.common_package.subpackge.subpackaged_util_module import
AnotherClass
+ from my_company.common_package.subpackage.subpackaged_util_module import
AnotherClass
from my_company.my_custom_dags.base_dag import BaseDag
You can see the ``.airflowignore`` file at the root of your folder. This is a
file that you can put in your
diff --git a/docs/apache-airflow/pipeline_example.csv
b/docs/apache-airflow/pipeline_example.csv
index a1b9f2d..16df952 100644
--- a/docs/apache-airflow/pipeline_example.csv
+++ b/docs/apache-airflow/pipeline_example.csv
@@ -68,7 +68,7 @@ Serial Number,Company Name,Employee Markme,Description,Leave
9.78174E+12,COLLABORATION IN LEARNING,MAL LEE AND LORRAE WARD,ACER PRESS,0
9.78086E+12,RE-IMAGINING EDUCATIMarkL LEADERSHIP,BRIAN J.CALDWELL,ACER PRESS,0
9.78086E+12,TOWARDS A MOVING SCHOOL,FLEMING & KLEINHENZ,ACER PRESS,0
-9.78086E+12,DESINGNING A THINKING A CURRICULAM,SUSAN WILKS,ACER PRESS,0
+9.78086E+12,DESIGNING A THINKING A CURRICULAM,SUSAN WILKS,ACER PRESS,0
9.78086E+12,LEADING A DIGITAL SCHOOL,MAL LEE AND MICHEAL GAFFNEY,ACER PRESS,0
9.78086E+12,NUMERACY,WESTWOOD,ACER PRESS,0
9.78086E+12,TEACHING ORAL LANGUAGE,JOHN MUNRO,ACER PRESS,0
@@ -87,7 +87,7 @@ Serial Number,Company Name,Employee Markme,Description,Leave
9.78818E+12,TULSIDAS ' RAMAYAMark,Mark,ACK,0
9.78818E+12,TALES OF HANUMAN,-,ACK,0
9.78818E+12,VALMIKI'S RAMAYAMark,A C K,ACK,1
-9.78818E+12,THE BEST OF INIDAN WIT AND WISDOM,Mark,ACK,0
+9.78818E+12,THE BEST OF INIDAN WITH AND WISDOM,Mark,ACK,0
9.78818E+12,MORE TALES FROM THE PANCHTANTRA,AMarkNT PAL,ACK,0
9.78818E+12,THE GREAT MUGHALS {5-IN-1},AMarkNT.,ACK,0
9.78818E+12,FAMOUS SCIENTISTS,Mark,ACK,0
diff --git a/docs/apache-airflow/security/kerberos.rst
b/docs/apache-airflow/security/kerberos.rst
index 190c2f1..1832645 100644
--- a/docs/apache-airflow/security/kerberos.rst
+++ b/docs/apache-airflow/security/kerberos.rst
@@ -78,7 +78,7 @@ If you need more granular options for your kerberos ticket
the following options
forwardable = True
# Allow to include or remove local IP from kerberos token.
- # This is particulary useful if you use Airflow inside a VM NATted behind
host system IP.
+ # This is particularly useful if you use Airflow inside a VM NATted behind
host system IP.
include_ip = True
Keep in mind that Kerberos ticket are generated via ``kinit`` and will your
use your local ``krb5.conf`` by default.
diff --git a/docs/apache-airflow/security/webserver.rst
b/docs/apache-airflow/security/webserver.rst
index 283d5aa..f168faa 100644
--- a/docs/apache-airflow/security/webserver.rst
+++ b/docs/apache-airflow/security/webserver.rst
@@ -220,7 +220,7 @@ webserver_config.py itself if you wish.
) -> Dict[str, Union[str, List[str]]]:
# Creates the user info payload from Github.
- # The user previously allowed your app to act on thier behalf,
+ # The user previously allowed your app to act on their behalf,
# so now we can query the user and teams endpoints for their
data.
# Username and team membership are added to the payload and
returned to FAB.
diff --git a/docs/helm-chart/index.rst b/docs/helm-chart/index.rst
index 6910a73..ad4dd88 100644
--- a/docs/helm-chart/index.rst
+++ b/docs/helm-chart/index.rst
@@ -67,7 +67,7 @@ Features
* Supported Airflow version: ``1.10+``, ``2.0+``
* Supported database backend: ``PostgresSQL``, ``MySQL``
* Autoscaling for ``CeleryExecutor`` provided by KEDA
-* PostgresSQL and PgBouncer with a battle-tested configuration
+* PostgreSQL and PgBouncer with a battle-tested configuration
* Monitoring:
* StatsD/Prometheus metrics for Airflow
diff --git a/docs/helm-chart/production-guide.rst
b/docs/helm-chart/production-guide.rst
index 4d3c3a3..a1250f2 100644
--- a/docs/helm-chart/production-guide.rst
+++ b/docs/helm-chart/production-guide.rst
@@ -24,7 +24,7 @@ Database
--------
You will want to use an external database instead of the one deployed with the
chart by default.
-Both **PostgresSQL** and **MySQL** are supported. Supported versions can be
+Both **PostgreSQL** and **MySQL** are supported. Supported versions can be
found on the :doc:`Set up a Database Backend
<apache-airflow:howto/set-up-database>` page.
.. code-block:: yaml
@@ -48,7 +48,7 @@ found on the :doc:`Set up a Database Backend
<apache-airflow:howto/set-up-databa
PgBouncer
---------
-If you are using PostgresSQL as your database, you will likely want to enable
`PgBouncer <https://www.pgbouncer.org/>`_ as well.
+If you are using PostgreSQL as your database, you will likely want to enable
`PgBouncer <https://www.pgbouncer.org/>`_ as well.
Airflow can open a lot of database connections due to its distributed nature
and using a connection pooler can significantly
reduce the number of open connections on the database.
diff --git a/docs/spelling_wordlist.txt b/docs/spelling_wordlist.txt
index 39b88c7..998d203 100644
--- a/docs/spelling_wordlist.txt
+++ b/docs/spelling_wordlist.txt
@@ -400,6 +400,7 @@ Zsh
Zymergen
abc
accessor
+aci
ack
ackIds
acknowledgement
@@ -407,6 +408,7 @@ actionCard
acyclic
adhoc
adls
+afterall
airbnb
airbyte
airflowignore
@@ -527,6 +529,7 @@ changelog
charset
checklicence
checksums
+childs
chmod
chown
ci
@@ -570,6 +573,7 @@ configs
conftest
conn
connectTimeoutMS
+connexion
containerConfiguration
contentUrl
contextmgr
@@ -873,6 +877,7 @@ ish
isn
iterable
iteratively
+iterm
itertools
izip
javascript
@@ -1109,6 +1114,7 @@ psrp
psycopg
pty
pubsub
+pullrequest
py
pyMongo
pyarrow
@@ -1214,6 +1220,7 @@ sharded
shellcheck
shellcmd
shm
+sie
sigv
skipable
sku
diff --git a/scripts/ci/libraries/_initialization.sh
b/scripts/ci/libraries/_initialization.sh
index 65c8f3b..cad80ff 100644
--- a/scripts/ci/libraries/_initialization.sh
+++ b/scripts/ci/libraries/_initialization.sh
@@ -938,7 +938,7 @@ function initialization::check_docker_version() {
docker_version=$(docker version --format '{{.Client.Version}}' | sed
's/\+.*$//' || true)
if [ "${docker_version}" == "" ]; then
echo
- echo "${COLOR_YELLOW}Your version of docker is unknown. If the scripts
faill, please make sure to install docker at least: ${min_docker_version}
version.${COLOR_RESET}"
+ echo "${COLOR_YELLOW}Your version of docker is unknown. If the scripts
fail, please make sure to install docker at least: ${min_docker_version}
version.${COLOR_RESET}"
echo
return
fi
diff --git a/scripts/ci/pre_commit/pre_commit_yaml_to_cfg.py
b/scripts/ci/pre_commit/pre_commit_yaml_to_cfg.py
index 600c5de..5a66d6c 100755
--- a/scripts/ci/pre_commit/pre_commit_yaml_to_cfg.py
+++ b/scripts/ci/pre_commit/pre_commit_yaml_to_cfg.py
@@ -17,7 +17,7 @@
# specific language governing permissions and limitations
# under the License.
"""
-Module to covert Airflow configs in config.yml to default_airflow.cfg file
+Module to convert Airflow configs in config.yml to default_airflow.cfg file
"""
import os
diff --git a/scripts/in_container/prod/entrypoint_prod.sh
b/scripts/in_container/prod/entrypoint_prod.sh
index 2e57773..a7623b6 100755
--- a/scripts/in_container/prod/entrypoint_prod.sh
+++ b/scripts/in_container/prod/entrypoint_prod.sh
@@ -281,7 +281,7 @@ if [[ -n "${_PIP_ADDITIONAL_REQUIREMENTS=}" ]] ; then
>&2 echo
>&2 echo "!!!!! Installing additional requirements:
'${_PIP_ADDITIONAL_REQUIREMENTS}' !!!!!!!!!!!!"
>&2 echo
- >&2 echo "WARNING: This is a developpment/test feature only. NEVER use it
in production!"
+ >&2 echo "WARNING: This is a development/test feature only. NEVER use it
in production!"
>&2 echo " Instead, build a custom image as described in"
>&2 echo
>&2 echo " https://airflow.apache.org/docs/docker-stack/build.html";
diff --git a/tests/dag_processing/test_manager.py
b/tests/dag_processing/test_manager.py
index 2db282e..1dbd1c9 100644
--- a/tests/dag_processing/test_manager.py
+++ b/tests/dag_processing/test_manager.py
@@ -774,7 +774,7 @@ class TestDagFileProcessorManager:
manager._refresh_dag_dir()
# Assert dag not deleted in SDM
assert SerializedDagModel.has_dag('test_zip_dag')
- # assert code not delted
+ # assert code not deleted
assert DagCode.has_dag(dag.fileloc)
diff --git a/tests/models/test_taskinstance.py
b/tests/models/test_taskinstance.py
index 4f7d3f9..e705207 100644
--- a/tests/models/test_taskinstance.py
+++ b/tests/models/test_taskinstance.py
@@ -1916,7 +1916,7 @@ class TestTaskInstance:
rtif_get_k8s_pod_yaml.assert_called_once_with(ti, session=session)
render_k8s_pod_yaml.assert_not_called()
- # Now test that when we _dont_ find it in the DB, it calles
render_k8s_pod_yaml
+ # Now test that when we _dont_ find it in the DB, it calls
render_k8s_pod_yaml
rtif_get_k8s_pod_yaml.return_value = None
render_k8s_pod_yaml.return_value = fake_spec
diff --git a/tests/providers/ssh/hooks/test_ssh.py
b/tests/providers/ssh/hooks/test_ssh.py
index 89068fd..2351c4e 100644
--- a/tests/providers/ssh/hooks/test_ssh.py
+++ b/tests/providers/ssh/hooks/test_ssh.py
@@ -691,7 +691,7 @@ class TestSSHHook(unittest.TestCase):
def test_openssh_private_key(self):
# Paramiko behaves differently with OpenSSH generated keys to paramiko
# generated keys, so we need a test one.
- # This has been gernerated specifically to put here, it is not
otherwise in use
+ # This has been generated specifically to put here, it is not
otherwise in use
TEST_OPENSSH_PRIVATE_KEY = "-----BEGIN OPENSSH " + textwrap.dedent(
"""\
PRIVATE KEY-----
diff --git a/tests/sensors/test_external_task_sensor.py
b/tests/sensors/test_external_task_sensor.py
index e507c7c..9580dc3 100644
--- a/tests/sensors/test_external_task_sensor.py
+++ b/tests/sensors/test_external_task_sensor.py
@@ -750,7 +750,7 @@ def dag_bag_cyclic():
)
task_a >> task_b
- # Create the last dag wich loops back
+ # Create the last dag which loops back
with DAG(f"dag_{depth}", start_date=DEFAULT_DATE,
schedule_interval=None) as dag:
dags.append(dag)
task_a = ExternalTaskSensor(
diff --git a/tests/task/task_runner/test_base_task_runner.py
b/tests/task/task_runner/test_base_task_runner.py
index 499bba7..96fd9f5 100644
--- a/tests/task/task_runner/test_base_task_runner.py
+++ b/tests/task/task_runner/test_base_task_runner.py
@@ -37,7 +37,7 @@ def test_config_copy_mode(tmp_configuration_copy, chown,
subprocess_call, dag_ma
ti = dr.task_instances[0]
job = LocalTaskJob(ti)
runner = BaseTaskRunner(job)
- # So we don't try to delete it -- cos the file wont exist
+ # So we don't try to delete it -- cos the file won't exist
del runner._cfg_path
includes = bool(impersonation)
