Fix spellings (#14483)

apache · Feb 27, 2021 · 50a1504 · 50a1504
1 parent afb3432
commit 50a1504
Show file tree

Hide file tree

Showing 55 changed files with 100 additions and 100 deletions.
diff --git a/BREEZE.rst b/BREEZE.rst
@@ -333,7 +333,7 @@ Managing CI environment:
  * Generate constraints with ``breeze generate-constraints``
  * Execute arbitrary command in the test environment with ``breeze shell`` command
  * Execute arbitrary docker-compose command with ``breeze docker-compose`` command
- * Push docker images with ``breeze push-image`` command (require committer's rights to push images)
+ * Push docker images with ``breeze push-image`` command (require committers rights to push images)
 
 You can optionally reset the Airflow metada database if specified as extra ``--db-reset`` flag and for CI image
 you can also start integrations (separate Docker images) if specified as extra ``--integration`` flags. You can also
@@ -356,7 +356,7 @@ Managing Prod environment (with ``--production-image`` flag):
  * Restart running interactive environment with ``breeze restart`` command
  * Execute arbitrary command in the test environment with ``breeze shell`` command
  * Execute arbitrary docker-compose command with ``breeze docker-compose`` command
- * Push docker images with ``breeze push-image`` command (require committer's rights to push images)
+ * Push docker images with ``breeze push-image`` command (require committers rights to push images)
 
 You can optionally reset database if specified as extra ``--db-reset`` flag. You can also
 chose which backend database should be used with ``--backend`` flag and python version with ``--python`` flag.

diff --git a/CONTRIBUTING.rst b/CONTRIBUTING.rst
@@ -983,7 +983,7 @@ If this function is designed to be called by "end-users" (i.e. DAG authors) then
  ...
  # You SHOULD not commit the session here. The wrapper will take care of commit()/rollback() if exception
 
-Don't use time() for duration calcuations
+Don't use time() for duration calculations
 -----------------------------------------
 
 If you wish to compute the time difference between two events with in the same process, use

diff --git a/Dockerfile b/Dockerfile
@@ -256,7 +256,7 @@ ENV AIRFLOW_INSTALLATION_METHOD=${AIRFLOW_INSTALLATION_METHOD}
 ARG AIRFLOW_VERSION_SPECIFICATION=""
 ENV AIRFLOW_VERSION_SPECIFICATION=${AIRFLOW_VERSION_SPECIFICATION}
 
-# We can seet this value to true in case we want to install .whl .tar.gz packages placed in the
+# We can set this value to true in case we want to install .whl .tar.gz packages placed in the
 # docker-context-files folder. This can be done for both - additional packages you want to install
 # and for airflow as well (you have to set INSTALL_FROM_PYPI to false in this case)
 ARG INSTALL_FROM_DOCKER_CONTEXT_FILES=""

diff --git a/IMAGES.rst b/IMAGES.rst
@@ -228,7 +228,7 @@ Choosing image registry
 =======================
 
 By default images are pulled and pushed from and to DockerHub registry when you use Breeze's push-image
-or build commands. But as described in `CI Documentaton <CI.rst>`_, you can choose different image
+or build commands. But as described in `CI Documentation <CI.rst>`_, you can choose different image
 registry by setting ``GITHUB_REGISTRY`` to ``docker.pkg.github.com`` for Github Package Registry or
 ``ghcr.io`` for GitHub Container Registry.
 

diff --git a/UPDATING.md b/UPDATING.md
@@ -780,7 +780,7 @@ In previous versions, the `LatestOnlyOperator` forcefully skipped all (direct an
 
 No change is needed if only the default trigger rule `all_success` is being used.
 
-If the DAG relies on tasks with other trigger rules (i.e. `all_done`) being skipped by the `LatestOnlyOperator`, adjustments to the DAG need to be made to commodate the change in behaviour, i.e. with additional edges from the `LatestOnlyOperator`.
+If the DAG relies on tasks with other trigger rules (i.e. `all_done`) being skipped by the `LatestOnlyOperator`, adjustments to the DAG need to be made to accommodate the change in behaviour, i.e. with additional edges from the `LatestOnlyOperator`.
 
 The goal of this change is to achieve a more consistent and configurale cascading behaviour based on the `BaseBranchOperator` (see [AIRFLOW-2923](https://jira.apache.org/jira/browse/AIRFLOW-2923) and [AIRFLOW-1784](https://jira.apache.org/jira/browse/AIRFLOW-1784)).
 
@@ -1662,7 +1662,7 @@ ImapHook:
 #### `airflow.providers.http.hooks.http.HttpHook`
 
 The HTTPHook is now secured by default: `verify=True` (before: `verify=False`)
-This can be overwriten by using the extra_options param as `{'verify': False}`.
+This can be overwritten by using the extra_options param as `{'verify': False}`.
 
 #### `airflow.providers.cloudant.hooks.cloudant.CloudantHook`
 

diff --git a/airflow/cli/commands/webserver_command.py b/airflow/cli/commands/webserver_command.py
@@ -188,7 +188,7 @@ def _kill_old_workers(self, count: int) -> None:
 
  def _reload_gunicorn(self) -> None:
  """
- Send signal to reload the gunciron configuration. When gunciorn receive signals, it reload the
+ Send signal to reload the gunicorn configuration. When gunicorn receive signals, it reload the
  configuration, start the new worker processes with a new configuration and gracefully
  shutdown older workers.
  """

diff --git a/airflow/executors/celery_executor.py b/airflow/executors/celery_executor.py
@@ -363,7 +363,7 @@ def _check_for_stalled_adopted_tasks(self):
  # If the task gets updated to STARTED (which Celery does) or has
  # already finished, then it will be removed from this list -- so
  # the only time it's still in this list is when it a) never made it
- # to celery in the first place (i.e. race condition somehwere in
+ # to celery in the first place (i.e. race condition somewhere in
  # the dying executor) or b) a really long celery queue and it just
  # hasn't started yet -- better cancel it and let the scheduler
  # re-queue rather than have this task risk stalling for ever

diff --git a/airflow/models/dag.py b/airflow/models/dag.py
@@ -1400,7 +1400,7 @@ def clear_dags(
  return count
 
  def __deepcopy__(self, memo):
- # Swiwtcharoo to go around deepcopying objects coming through the
+ # Switcharoo to go around deepcopying objects coming through the
  # backdoor
  cls = self.__class__
  result = cls.__new__(cls)

diff --git a/airflow/models/dagbag.py b/airflow/models/dagbag.py
@@ -525,7 +525,7 @@ def sync_to_db(self, session: Optional[Session] = None):
  from airflow.models.dag import DAG
  from airflow.models.serialized_dag import SerializedDagModel
 
- def _serialze_dag_capturing_errors(dag, session):
+ def _serialize_dag_capturing_errors(dag, session):
  """
  Try to serialize the dag to the DB, but make a note of any errors.
 
@@ -561,7 +561,7 @@ def _serialze_dag_capturing_errors(dag, session):
  try:
  # Write Serialized DAGs to DB, capturing errors
  for dag in self.dags.values():
- serialize_errors.extend(_serialze_dag_capturing_errors(dag, session))
+ serialize_errors.extend(_serialize_dag_capturing_errors(dag, session))
 
  DAG.bulk_write_to_db(self.dags.values(), session=session)
  except OperationalError:

diff --git a/airflow/models/dagrun.py b/airflow/models/dagrun.py
@@ -440,7 +440,7 @@ def update_state(
  msg='task_failure',
  )
 
- # if all leafs succeeded and no unfinished tasks, the run succeeded
+ # if all leaves succeeded and no unfinished tasks, the run succeeded
  elif not unfinished_tasks and all(leaf_ti.state in State.success_states for leaf_ti in leaf_tis):
  self.log.info('Marking run %s successful', self)
  self.set_state(State.SUCCESS)
@@ -592,7 +592,7 @@ def _emit_true_scheduling_delay_stats_for_finished_state(self, finished_tis):
  dag = self.get_dag()
 
  if not self.dag.schedule_interval or self.dag.schedule_interval == "@once":
- # We can't emit this metric if there is no following schedule to cacluate from!
+ # We can't emit this metric if there is no following schedule to calculate from!
  return
 
  ordered_tis_by_start_date = [ti for ti in finished_tis if ti.start_date]

diff --git a/airflow/providers/google/cloud/example_dags/example_life_sciences.py b/airflow/providers/google/cloud/example_dags/example_life_sciences.py
@@ -29,7 +29,7 @@
 
 
 # [START howto_configure_simple_action_pipeline]
-SIMPLE_ACTION_PIEPELINE = {
+SIMPLE_ACTION_PIPELINE = {
  "pipeline": {
  "actions": [
  {"imageUri": "bash", "commands": ["-c", "echo Hello, world"]},
@@ -83,7 +83,7 @@
  # [START howto_run_pipeline]
  simple_life_science_action_pipeline = LifeSciencesRunPipelineOperator(
  task_id='simple-action-pipeline',
- body=SIMPLE_ACTION_PIEPELINE,
+ body=SIMPLE_ACTION_PIPELINE,
  project_id=PROJECT_ID,
  location=LOCATION,
  )

diff --git a/airflow/providers/google/cloud/operators/compute.py b/airflow/providers/google/cloud/operators/compute.py
@@ -355,7 +355,7 @@ def execute(self, context) -> None:
  dict(name="onHostMaintenance", optional=True),
  dict(name="automaticRestart", optional=True),
  dict(name="preemptible", optional=True),
- dict(name="nodeAffinitites", optional=True), # not validating deeper
+ dict(name="nodeAffinities", optional=True), # not validating deeper
  ],
  ),
  dict(name="labels", optional=True),

diff --git a/airflow/providers/google/cloud/transfers/sql_to_gcs.py b/airflow/providers/google/cloud/transfers/sql_to_gcs.py
@@ -263,7 +263,7 @@ def _configure_parquet_file(self, file_handle, parquet_schema):
 
  def _convert_parquet_schema(self, cursor):
  type_map = {
- 'INTERGER': pa.int64(),
+ 'INTEGER': pa.int64(),
  'FLOAT': pa.float64(),
  'NUMERIC': pa.float64(),
  'BIGNUMERIC': pa.float64(),

diff --git a/airflow/providers/google/common/utils/id_token_credentials.py b/airflow/providers/google/common/utils/id_token_credentials.py
@@ -205,8 +205,8 @@ def get_default_id_token_credentials(
 if __name__ == "__main__":
  from google.auth.transport import requests
 
- request_adaapter = requests.Request()
+ request_adapter = requests.Request()
 
  creds = get_default_id_token_credentials(target_audience=None)
- creds.refresh(request=request_adaapter)
+ creds.refresh(request=request_adapter)
  print(creds.token)
diff --git a/airflow/settings.py b/airflow/settings.py
@@ -435,7 +435,7 @@ def initialize():
  configure_orm()
  configure_action_logging()
 
- # Ensure we close DB connections at scheduler and gunicon worker terminations
+ # Ensure we close DB connections at scheduler and gunicorn worker terminations
  atexit.register(dispose_orm)
 
 

diff --git a/airflow/utils/db.py b/airflow/utils/db.py
@@ -256,7 +256,7 @@ def create_default_connections(session=None):
  conn_id="facebook_default",
  conn_type="facebook_social",
  extra="""
- { "account_id": "<AD_ACCOUNNT_ID>",
+ { "account_id": "<AD_ACCOUNT_ID>",
  "app_id": "<FACEBOOK_APP_ID>",
  "app_secret": "<FACEBOOK_APP_SECRET>",
  "access_token": "<FACEBOOK_AD_ACCESS_TOKEN>"

diff --git a/airflow/www/static/js/datetime_utils.js b/airflow/www/static/js/datetime_utils.js
@@ -76,7 +76,7 @@ export function updateAllDateTimes() {
  const dt = moment($el.attr('datetime'));
  $el.text(dt.format(defaultFormat));
  if ($el.attr('title') !== undefined) {
- // If displayed date is not UTC, have the UTC date in a title attriubte
+ // If displayed date is not UTC, have the UTC date in a title attribute
  $el.attr('title', dt.isUTC() ? '' : `UTC: ${dt.clone().utc().format()}`);
  }
  });

diff --git a/airflow/www/static/js/gantt_chart_d3v2.js b/airflow/www/static/js/gantt_chart_d3v2.js
@@ -119,7 +119,7 @@ d3.gantt = function() {
  return "translate(" + (x(d.start_date.valueOf()) + yAxisLeftOffset) + "," + y(d.task_id) + ")";
  };
 
- function tickFormater(d) {
+ function tickFormatter(d) {
  // We can't use d3.time.format as that uses local time, so instead we use
  // moment as that handles our "global" timezone.
  return moment(d).strftime(tickFormat);
@@ -129,7 +129,7 @@ d3.gantt = function() {
 
  var y = d3.scale.ordinal().domain(taskTypes).rangeRoundBands([ 0, height - margin.top - margin.bottom ], .1);
 
- var xAxis = d3.svg.axis().scale(x).orient("bottom").tickFormat(tickFormater).tickSubdivide(true)
+ var xAxis = d3.svg.axis().scale(x).orient("bottom").tickFormat(tickFormatter).tickSubdivide(true)
  .tickSize(8).tickPadding(8);
 
  var yAxis = d3.svg.axis().scale(y).orient("left").tickSize(0);
@@ -157,7 +157,7 @@ d3.gantt = function() {
  var initAxis = function() {
  x = d3.time.scale().domain([ timeDomainStart, timeDomainEnd ]).range([ 0, width-yAxisLeftOffset ]).clamp(true);
  y = d3.scale.ordinal().domain(taskTypes).rangeRoundBands([ 0, height - margin.top - margin.bottom ], .1);
- xAxis = d3.svg.axis().scale(x).orient("bottom").tickFormat(tickFormater).tickSubdivide(true)
+ xAxis = d3.svg.axis().scale(x).orient("bottom").tickFormat(tickFormatter).tickSubdivide(true)
  .tickSize(8).tickPadding(8);
 
  yAxis = d3.svg.axis().scale(y).orient("left").tickSize(0);

diff --git a/breeze b/breeze
@@ -1024,7 +1024,7 @@ function breeze::parse_arguments() {
  echo "Additional apt dev dependencies: ${ADDITIONAL_DEV_APT_DEPS}"
  shift 2
  ;;
- --dev-apt-commad)
+ --dev-apt-command)
  export DEV_APT_COMMAND="${2}"
  echo "Apt dev command: ${DEV_APT_COMMAND}"
  shift 2
@@ -1049,7 +1049,7 @@ function breeze::parse_arguments() {
  echo "Additional apt runtime dependencies: ${ADDITIONAL_RUNTIME_APT_DEPS}"
  shift 2
  ;;
- --runtime-apt-commad)
+ --runtime-apt-command)
  export RUNTIME_APT_COMMAND="${2}"
  echo "Apt runtime command: ${RUNTIME_APT_COMMAND}"
  shift 2

diff --git a/...secrets-backends/aws-secrets-manaager.rst → .../secrets-backends/aws-secrets-manager.rst b/...secrets-backends/aws-secrets-manaager.rst → .../secrets-backends/aws-secrets-manager.rst
diff --git a/docs/exts/docs_build/docs_builder.py b/docs/exts/docs_build/docs_builder.py
@@ -150,8 +150,8 @@ def check_spelling(self, verbose):
  )
  warning_text = ""
  for filepath in glob(f"{tmp_dir}/**/*.spelling", recursive=True):
- with open(filepath) as speeling_file:
- warning_text += speeling_file.read()
+ with open(filepath) as spelling_file:
+ warning_text += spelling_file.read()
 
  spelling_errors.extend(parse_spelling_warnings(warning_text, self._src_dir))
  return spelling_errors

diff --git a/docs/exts/docs_build/github_action_utils.py b/docs/exts/docs_build/github_action_utils.py
@@ -23,7 +23,7 @@
 def with_group(title):
  """
  If used in GitHub Action, creates an expandable group in the GitHub Action log.
- Otherwise, dispaly simple text groups.
+ Otherwise, display simple text groups.
 
  For more information, see:
  https://docs.github.com/en/free-pro-team@latest/actions/reference/workflow-commands-for-github-actions#grouping-log-lines

diff --git a/scripts/ci/libraries/_push_pull_remove_images.sh b/scripts/ci/libraries/_push_pull_remove_images.sh
@@ -104,7 +104,7 @@ function push_pull_remove_images::pull_image_github_dockerhub() {
  set -e
 }
 
-# Pulls the base Python image. This image is used as base for CI and PROD imaages, depending on the parameters used:
+# Pulls the base Python image. This image is used as base for CI and PROD images, depending on the parameters used:
 #
 # * if UPGRADE_TO_NEWER_DEPENDENCIES is noy false, then it pulls the latest Python image available first and
 # adds `org.opencontainers.image.source` label to it, so that it is linked to Airflow repository when

diff --git a/tests/api/common/experimental/test_mark_tasks.py b/tests/api/common/experimental/test_mark_tasks.py
@@ -592,7 +592,7 @@ def test_set_state_without_commit(self):
 
  will_be_altered = set_dag_run_state_to_failed(self.dag1, date, commit=False)
 
- # Only the running task shouldbe altered.
+ # Only the running task should be altered.
  expected = self._get_num_tasks_with_starting_state(State.RUNNING, inclusion=True)
  assert len(will_be_altered) == expected
  self._verify_dag_run_state(self.dag1, date, State.RUNNING)

diff --git a/tests/api_connexion/test_error_handling.py b/tests/api_connexion/test_error_handling.py
@@ -39,7 +39,7 @@ def test_incorrect_endpoint_should_return_json(self):
 
  assert 404 == resp_json["status"]
 
- # When we are hitting non-api incorrect enpoint
+ # When we are hitting non-api incorrect endpoint
 
  resp_json = self.client.get("/incorrect_endpoint").json
 

diff --git a/tests/cli/commands/test_task_command.py b/tests/cli/commands/test_task_command.py
@@ -237,10 +237,10 @@ def test_task_states_for_dag_run(self):
 
  dag2 = DagBag().dags['example_python_operator']
  task2 = dag2.get_task(task_id='print_the_context')
- defaut_date2 = timezone.make_aware(datetime(2016, 1, 9))
+ default_date2 = timezone.make_aware(datetime(2016, 1, 9))
  dag2.clear()
 
- ti2 = TaskInstance(task2, defaut_date2)
+ ti2 = TaskInstance(task2, default_date2)
 
  ti2.set_state(State.SUCCESS)
  ti_start = ti2.start_date
@@ -253,7 +253,7 @@ def test_task_states_for_dag_run(self):
  'tasks',
  'states-for-dag-run',
  'example_python_operator',
- defaut_date2.isoformat(),
+ default_date2.isoformat(),
  '--output',
  "json",
  ]
@@ -352,7 +352,7 @@ def tearDown(self) -> None:
  def assert_log_line(self, text, logs_list, expect_from_logging_mixin=False):
  """
  Get Log Line and assert only 1 Entry exists with the given text. Also check that
- "logging_mixin" line does not appear in that log line to avoid duplicate loggigng as below:
+ "logging_mixin" line does not appear in that log line to avoid duplicate logging as below:
 
  [2020-06-24 16:47:23,537] {logging_mixin.py:91} INFO - [2020-06-24 16:47:23,536] {python.py:135}
  """

diff --git a/tests/jobs/test_local_task_job.py b/tests/jobs/test_local_task_job.py
@@ -355,7 +355,7 @@ def task_function(ti):
  job1 = LocalTaskJob(task_instance=ti, ignore_ti_state=True, executor=SequentialExecutor())
  with timeout(30):
  # This should be _much_ shorter to run.
- # If you change this limit, make the timeout in the callbable above bigger
+ # If you change this limit, make the timeout in the callable above bigger
  job1.run()
 
  ti.refresh_from_db()
@@ -422,7 +422,7 @@ def dummy_return_code(*args, **kwargs):
 
  with timeout(10):
  # This should be _much_ shorter to run.
- # If you change this limit, make the timeout in the callbable above bigger
+ # If you change this limit, make the timeout in the callable above bigger
  job1.run()
 
  ti.refresh_from_db()
@@ -431,7 +431,7 @@ def dummy_return_code(*args, **kwargs):
 
  def test_mark_success_on_success_callback(self):
  """
- Test that ensures that where a task is marked suceess in the UI
+ Test that ensures that where a task is marked success in the UI
  on_success_callback gets executed
  """
  # use shared memory value so we can properly track value change even if

diff --git a/tests/jobs/test_scheduler_job.py b/tests/jobs/test_scheduler_job.py
@@ -2359,7 +2359,7 @@ def test_dagrun_root_fail_unfinished(self):
  dag.run(start_date=dr.execution_date, end_date=dr.execution_date, executor=self.null_exec)
 
  # Mark the successful task as never having run since we want to see if the
- # dagrun will be in a running state despite haveing an unfinished task.
+ # dagrun will be in a running state despite having an unfinished task.
  with create_session() as session:
  ti = dr.get_task_instance('test_dagrun_unfinished', session=session)
  ti.state = State.NONE

diff --git a/tests/kubernetes/test_pod_generator.py b/tests/kubernetes/test_pod_generator.py
@@ -293,7 +293,7 @@ def test_from_obj(self):
  }
  assert (
  result_from_pod == expected_from_pod
- ), "There was a discrepency between KubernetesExecutor and pod_override"
+ ), "There was a discrepancy between KubernetesExecutor and pod_override"
 
  assert {
  'apiVersion': 'v1',

diff --git a/tests/models/test_dag.py b/tests/models/test_dag.py
@@ -717,7 +717,7 @@ def test_bulk_write_to_db_max_active_runs(self):
 
  model = session.query(DagModel).get((dag.dag_id,))
  assert model.next_dagrun == period_end
- # We signle "at max active runs" by saying this run is never eligible to be created
+ # We signal "at max active runs" by saying this run is never eligible to be created
  assert model.next_dagrun_create_after is None
 
  def test_sync_to_db(self):
@@ -1042,7 +1042,7 @@ def test_dag_handle_callback_crash(self, mock_stats):
  dag.add_task(BaseOperator(task_id="faketastic", owner='Also fake', start_date=when))
 
  dag_run = dag.create_dagrun(State.RUNNING, when, run_type=DagRunType.MANUAL)
- # should not rause any exception
+ # should not raise any exception
  dag.handle_callback(dag_run, success=False)
  dag.handle_callback(dag_run, success=True)
 

diff --git a/tests/models/test_dagcode.py b/tests/models/test_dagcode.py
@@ -128,7 +128,7 @@ def _compare_example_dags(self, example_dags):
  def test_code_can_be_read_when_no_access_to_file(self):
  """
  Test that code can be retrieved from DB when you do not have access to Code file.
- Source Code should atleast exist in one of DB or File.
+ Source Code should at least exist in one of DB or File.
  """
  example_dag = make_example_dags(example_dags_module).get('example_bash_operator')
  example_dag.sync_to_db()