Enable Sphinx spellcheck for doc generation (#10280)

.rat-excludes

@@ -49,6 +49,9 @@ _images/*
 searchindex.js
 _api/*
 
+# the word list for checking spellings
+spelling_wordlist.txt
+
 # Apache Rat does not detect BSD-2 clause properly
 # it is compatible according to http://www.apache.org/legal/resolved.html#category-a
 kerberos_auth.py

Dockerfile.ci

@@ -76,6 +76,7 @@ RUN curl --fail --location https://deb.nodesource.com/setup_10.x | bash - \
            libsasl2-dev \
            libsasl2-modules \
            libssl-dev \
+           libenchant-dev \
            locales  \
            netcat \
            nodejs \

UPDATING.md

@@ -644,7 +644,7 @@ The `chain` method and `cross_downstream` method both use BaseOperator. If any o
 any classes or functions from helpers module, then it automatically has an
 implicit dependency to BaseOperator. That can often lead to cyclic dependencies.
 
-More information in [AIFLOW-6392](https://issues.apache.org/jira/browse/AIRFLOW-6392)
+More information in [Airflow-6392](https://issues.apache.org/jira/browse/AIRFLOW-6392)
 
 In Airflow <2.0 you imported those two methods like this:
 
@@ -1443,7 +1443,7 @@ you should write `@GoogleBaseHook.provide_gcp_credential_file`
 It is highly recommended to have 1TB+ disk size for Dataproc to have sufficient throughput:
 https://cloud.google.com/compute/docs/disks/performance
 
-Hence, the default value for `master_disk_size` in DataprocCreateClusterOperator has beeen changes from 500GB to 1TB.
+Hence, the default value for `master_disk_size` in DataprocCreateClusterOperator has been changes from 500GB to 1TB.
 
 #### `<airflow class="providers google c"></airflow>loud.operators.bigquery.BigQueryGetDatasetTablesOperator`
 
@@ -1610,7 +1610,7 @@ See the [docs](https://python-cloudant.readthedocs.io/en/latest/) for more infor
 
 #### `airflow.providers.snowflake`
 
-When initializing a Snowflake hook or operator, the value used for `snowflake_conn_id` was always `snowflake_conn_id`, regardless of whether or not you specified a value for it. The default `snowflake_conn_id` value is now switched to `snowflake_default` for consistency and will be properly overriden when specified.
+When initializing a Snowflake hook or operator, the value used for `snowflake_conn_id` was always `snowflake_conn_id`, regardless of whether or not you specified a value for it. The default `snowflake_conn_id` value is now switched to `snowflake_default` for consistency and will be properly overridden when specified.
 
 ### Other changes
 

airflow/config_templates/config.yml

@@ -404,7 +404,7 @@
       default: ""
     - name: stackdriver_key_path
       description: |
-        Path to GCP Credential JSON file. If ommited, authorization based on `the Application Default
+        Path to GCP Credential JSON file. If omitted, authorization based on `the Application Default
         Credentials
         <https://cloud.google.com/docs/authentication/production#finding_credentials_automatically>`__ will
         be used.
@@ -623,7 +623,7 @@
       default: ""
     - name: google_key_path
       description: |
-        Path to GCP Credential JSON file. If ommited, authorization based on `the Application Default
+        Path to GCP Credential JSON file. If omitted, authorization based on `the Application Default
         Credentials
         <https://cloud.google.com/docs/authentication/production#finding_credentials_automatically>`__ will
         be used.
@@ -1164,7 +1164,7 @@
     ``ignore_errors``, ``before_breadcrumb``, ``before_send``, ``transport``.
   options:
     - name: sentry_on
-      description: Enable error repoting to Sentry
+      description: Enable error reporting to Sentry
       version_added: ~
       type: string
       example: ~

airflow/config_templates/default_airflow.cfg

@@ -230,7 +230,7 @@ remote_logging = False
 # location.
 remote_log_conn_id =
 
-# Path to GCP Credential JSON file. If ommited, authorization based on `the Application Default
+# Path to GCP Credential JSON file. If omitted, authorization based on `the Application Default
 # Credentials
 # <https://cloud.google.com/docs/authentication/production#finding_credentials_automatically>`__ will
 # be used.
@@ -339,7 +339,7 @@ fallback_page_limit = 100
 # Example: google_oauth2_audience = project-id-random-value.apps.googleusercontent.com
 google_oauth2_audience =
 
-# Path to GCP Credential JSON file. If ommited, authorization based on `the Application Default
+# Path to GCP Credential JSON file. If omitted, authorization based on `the Application Default
 # Credentials
 # <https://cloud.google.com/docs/authentication/production#finding_credentials_automatically>`__ will
 # be used.
@@ -573,7 +573,7 @@ smtp_mail_from = [email protected]
 # https://docs.sentry.io/error-reporting/configuration/?platform=python.
 # Unsupported options: ``integrations``, ``in_app_include``, ``in_app_exclude``,
 # ``ignore_errors``, ``before_breadcrumb``, ``before_send``, ``transport``.
-# Enable error repoting to Sentry
+# Enable error reporting to Sentry
 sentry_on = false
 sentry_dsn =
 

airflow/executors/base_executor.py

@@ -267,6 +267,6 @@ def terminate(self):
 
     @staticmethod
     def validate_command(command: List[str]) -> None:
-        """Check if the command to execute is airflow comnand"""
+        """Check if the command to execute is airflow command"""
         if command[0:3] != ["airflow", "tasks", "run"]:
             raise ValueError('The command must start with ["airflow", "tasks", "run"].')

airflow/macros/hive.py

@@ -94,7 +94,7 @@ def closest_ds_partition(
     :type before: bool or None
     :param schema: table schema
     :type schema: str
-    :param metastore_conn_id: which matastore connection to use
+    :param metastore_conn_id: which metastore connection to use
     :type metastore_conn_id: str
     :returns: The closest date
     :rtype: str or None

airflow/models/dag.py

@@ -987,7 +987,7 @@ def clear(
 
         :param start_date: The minimum execution_date to clear
         :type start_date: datetime.datetime or None
-        :param end_date: The maximum exeuction_date to clear
+        :param end_date: The maximum execution_date to clear
         :type end_date: datetime.datetime or None
         :param only_failed: Only clear failed tasks
         :type only_failed: bool

airflow/operators/sql.py

@@ -391,7 +391,7 @@ def get_db_hook(self):
 
 class SQLThresholdCheckOperator(BaseOperator):
     """
-    Performs a value check using sql code against a mininmum threshold
+    Performs a value check using sql code against a minimum threshold
     and a maximum threshold. Thresholds can be in the form of a numeric
     value OR a sql statement that results a numeric.
 

airflow/providers/amazon/aws/operators/datasync.py

@@ -88,7 +88,7 @@ class AWSDataSyncOperator(BaseOperator):
     :raises AirflowException: If ``task_arn`` was not specified, or if
         either ``source_location_uri`` or ``destination_location_uri`` were
         not specified.
-    :raises AirflowException: If source or destination Location weren't found
+    :raises AirflowException: If source or destination Location were not found
         and could not be created.
     :raises AirflowException: If ``choose_task`` or ``choose_location`` fails.
     :raises AirflowException: If Task creation, update, execution or delete fails.

airflow/providers/apache/kylin/hooks/kylin.py

@@ -28,7 +28,7 @@ class KylinHook(BaseHook):
     """
     :param kylin_conn_id: The connection id as configured in Airflow administration.
     :type kylin_conn_id: str
-    :param project: porject name
+    :param project: project name
     :type project: Optional[str]
     :param dsn: dsn
     :type dsn: Optional[str]

airflow/providers/apache/kylin/operators/kylin_cube.py

@@ -39,7 +39,7 @@ class KylinCubeOperator(BaseOperator):
 
     :param kylin_conn_id: The connection id as configured in Airflow administration.
     :type kylin_conn_id: str
-    :param project: kylin porject name, this param will overwrite the project in kylin_conn_id:
+    :param project: kylin project name, this param will overwrite the project in kylin_conn_id:
     :type project: str
     :param cube: kylin cube name
     :type cube: str
@@ -57,7 +57,7 @@ class KylinCubeOperator(BaseOperator):
         and you should give offset_start and offset_end
         refresh_streaming - use build2 rest api,and buildType is ‘REFRESH’
         merge_streaming - use build2 rest api,and buildType is ‘MERGE’
-        delete - delete segment, and you shoulf give segment_name value
+        delete - delete segment, and you should give segment_name value
         disable - disable cube
         enable - enable cube
         purge - purge cube

airflow/providers/google/cloud/hooks/automl.py

@@ -524,7 +524,7 @@ def deploy_model(
     ) -> Operation:
         """
         Deploys a model. If a model is already deployed, deploying it with the same parameters
-        has no effect. Deploying with different parametrs (as e.g. changing node_number) will
+        has no effect. Deploying with different parameters (as e.g. changing node_number) will
         reset the deployment state without pausing the model_id’s availability.
 
         Only applicable for Text Classification, Image Object Detection and Tables; all other

airflow/providers/google/cloud/hooks/bigquery.py

@@ -548,7 +548,7 @@ def create_external_table(self,  # pylint: disable=too-many-locals,too-many-argu
             The missing values are treated as nulls. If false, records with missing
             trailing columns are treated as bad records, and if there are too many bad
             records, an invalid error is returned in the job result. Only applicable when
-            soure_format is CSV.
+            source_format is CSV.
         :type allow_jagged_rows: bool
         :param encoding: The character encoding of the data. See:
 
@@ -709,7 +709,7 @@ def patch_table(self,  # pylint: disable=too-many-arguments
                     encryption_configuration: Optional[Dict] = None) -> None:
         """
         Patch information in an existing table.
-        It only updates fileds that are provided in the request object.
+        It only updates fields that are provided in the request object.
 
         Reference: https://cloud.google.com/bigquery/docs/reference/rest/v2/tables/patch
 
@@ -1590,7 +1590,7 @@ def run_load(self,  # pylint: disable=too-many-locals,too-many-arguments,invalid
             The missing values are treated as nulls. If false, records with missing
             trailing columns are treated as bad records, and if there are too many bad
             records, an invalid error is returned in the job result. Only applicable when
-            soure_format is CSV.
+            source_format is CSV.
         :type allow_jagged_rows: bool
         :param encoding: The character encoding of the data.
 

airflow/providers/google/cloud/hooks/datacatalog.py

@@ -889,7 +889,7 @@ def search_catalog(
         Searches Data Catalog for multiple resources like entries, tags that match a query.
 
         This does not return the complete resource, only the resource identifier and high level fields.
-        Clients can subsequentally call ``Get`` methods.
+        Clients can subsequently call ``Get`` methods.
 
         Note that searches do not have full recall. There may be results that match your query but are not
         returned, even in subsequent pages of results. These missing results may vary across repeated calls to