apache-airflow-providers-amazon 8.23.0rc1__py3-none-any.whl → 8.24.0__py3-none-any.whl

airflow/providers/amazon/aws/sensors/glue.py

@@ -18,10 +18,18 @@
 from __future__ import annotations
 
 from functools import cached_property
-from typing import TYPE_CHECKING, Sequence
+from typing import TYPE_CHECKING, Any, Sequence
 
+from airflow.configuration import conf
 from airflow.exceptions import AirflowException, AirflowSkipException
-from airflow.providers.amazon.aws.hooks.glue import GlueJobHook
+from airflow.providers.amazon.aws.hooks.glue import GlueDataQualityHook, GlueJobHook
+from airflow.providers.amazon.aws.sensors.base_aws import AwsBaseSensor
+from airflow.providers.amazon.aws.triggers.glue import (
+    GlueDataQualityRuleRecommendationRunCompleteTrigger,
+    GlueDataQualityRuleSetEvaluationRunCompleteTrigger,
+)
+from airflow.providers.amazon.aws.utils import validate_execute_complete_event
+from airflow.providers.amazon.aws.utils.mixins import aws_template_fields
 from airflow.sensors.base import BaseSensorOperator
 
 if TYPE_CHECKING:
@@ -91,3 +99,253 @@ class GlueJobSensor(BaseSensorOperator):
                     run_id=self.run_id,
                     continuation_tokens=self.next_log_tokens,
                 )
+
+
+class GlueDataQualityRuleSetEvaluationRunSensor(AwsBaseSensor[GlueDataQualityHook]):
+    """
+    Waits for an AWS Glue data quality ruleset evaluation run to reach any of the status below.
+
+    'FAILED', 'STOPPED', 'STOPPING', 'TIMEOUT', 'SUCCEEDED'
+
+    .. seealso::
+        For more information on how to use this sensor, take a look at the guide:
+        :ref:`howto/sensor:GlueDataQualityRuleSetEvaluationRunSensor`
+
+    :param evaluation_run_id: The AWS Glue data quality ruleset evaluation run identifier.
+    :param verify_result_status: Validate all the ruleset rules evaluation run results,
+        If any of the rule status is Fail or Error then an exception is thrown. (default: True)
+    :param show_results: Displays all the ruleset rules evaluation run results. (default: True)
+    :param deferrable: If True, the sensor will operate in deferrable mode. This mode requires aiobotocore
+        module to be installed.
+        (default: False, but can be overridden in config file by setting default_deferrable to True)
+    :param poke_interval: Polling period in seconds to check for the status of the job. (default: 120)
+    :param max_retries: Number of times before returning the current state. (default: 60)
+
+    :param aws_conn_id: The Airflow connection used for AWS credentials.
+        If this is ``None`` or empty then the default boto3 behaviour is used. If
+        running Airflow in a distributed manner and aws_conn_id is None or
+        empty, then default boto3 configuration would be used (and must be
+        maintained on each worker node).
+    :param region_name: AWS region_name. If not specified then the default boto3 behaviour is used.
+    :param verify: Whether to verify SSL certificates. See:
+        https://boto3.amazonaws.com/v1/documentation/api/latest/reference/core/session.html
+    :param botocore_config: Configuration dictionary (key-values) for botocore client. See:
+        https://botocore.amazonaws.com/v1/documentation/api/latest/reference/config.html
+    """
+
+    SUCCESS_STATES = ("SUCCEEDED",)
+
+    FAILURE_STATES = ("FAILED", "STOPPED", "STOPPING", "TIMEOUT")
+
+    aws_hook_class = GlueDataQualityHook
+    template_fields: Sequence[str] = aws_template_fields("evaluation_run_id")
+
+    def __init__(
+        self,
+        *,
+        evaluation_run_id: str,
+        show_results: bool = True,
+        verify_result_status: bool = True,
+        deferrable: bool = conf.getboolean("operators", "default_deferrable", fallback=False),
+        poke_interval: int = 120,
+        max_retries: int = 60,
+        aws_conn_id: str | None = "aws_default",
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+        self.evaluation_run_id = evaluation_run_id
+        self.show_results = show_results
+        self.verify_result_status = verify_result_status
+        self.aws_conn_id = aws_conn_id
+        self.max_retries = max_retries
+        self.poke_interval = poke_interval
+        self.deferrable = deferrable
+
+    def execute(self, context: Context) -> Any:
+        if self.deferrable:
+            self.defer(
+                trigger=GlueDataQualityRuleSetEvaluationRunCompleteTrigger(
+                    evaluation_run_id=self.evaluation_run_id,
+                    waiter_delay=int(self.poke_interval),
+                    waiter_max_attempts=self.max_retries,
+                    aws_conn_id=self.aws_conn_id,
+                ),
+                method_name="execute_complete",
+            )
+        else:
+            super().execute(context=context)
+
+    def execute_complete(self, context: Context, event: dict[str, Any] | None = None) -> None:
+        event = validate_execute_complete_event(event)
+
+        if event["status"] != "success":
+            message = f"Error: AWS Glue data quality ruleset evaluation run: {event}"
+            if self.soft_fail:
+                raise AirflowSkipException(message)
+            raise AirflowException(message)
+
+        self.hook.validate_evaluation_run_results(
+            evaluation_run_id=event["evaluation_run_id"],
+            show_results=self.show_results,
+            verify_result_status=self.verify_result_status,
+        )
+
+        self.log.info("AWS Glue data quality ruleset evaluation run completed.")
+
+    def poke(self, context: Context):
+        self.log.info(
+            "Poking for AWS Glue data quality ruleset evaluation run RunId: %s", self.evaluation_run_id
+        )
+
+        response = self.hook.conn.get_data_quality_ruleset_evaluation_run(RunId=self.evaluation_run_id)
+
+        status = response.get("Status")
+
+        if status in self.SUCCESS_STATES:
+            self.hook.validate_evaluation_run_results(
+                evaluation_run_id=self.evaluation_run_id,
+                show_results=self.show_results,
+                verify_result_status=self.verify_result_status,
+            )
+
+            self.log.info(
+                "AWS Glue data quality ruleset evaluation run completed RunId: %s Run State: %s",
+                self.evaluation_run_id,
+                response["Status"],
+            )
+
+            return True
+
+        elif status in self.FAILURE_STATES:
+            job_error_message = (
+                f"Error: AWS Glue data quality ruleset evaluation run RunId: {self.evaluation_run_id} Run "
+                f"Status: {status}"
+                f": {response.get('ErrorString')}"
+            )
+            self.log.info(job_error_message)
+            # TODO: remove this if block when min_airflow_version is set to higher than 2.7.1
+            if self.soft_fail:
+                raise AirflowSkipException(job_error_message)
+            raise AirflowException(job_error_message)
+        else:
+            return False
+
+
+class GlueDataQualityRuleRecommendationRunSensor(AwsBaseSensor[GlueDataQualityHook]):
+    """
+    Waits for an AWS Glue data quality recommendation run to reach any of the status below.
+
+    'FAILED', 'STOPPED', 'STOPPING', 'TIMEOUT', 'SUCCEEDED'
+
+    .. seealso::
+        For more information on how to use this sensor, take a look at the guide:
+        :ref:`howto/sensor:GlueDataQualityRuleRecommendationRunSensor`
+
+    :param recommendation_run_id: The AWS Glue data quality rule recommendation run identifier.
+    :param show_results: Displays the recommended ruleset (a set of rules), when recommendation run completes. (default: True)
+    :param deferrable: If True, the sensor will operate in deferrable mode. This mode requires aiobotocore
+        module to be installed.
+        (default: False, but can be overridden in config file by setting default_deferrable to True)
+    :param poke_interval: Polling period in seconds to check for the status of the job. (default: 120)
+    :param max_retries: Number of times before returning the current state. (default: 60)
+
+    :param aws_conn_id: The Airflow connection used for AWS credentials.
+        If this is ``None`` or empty then the default boto3 behaviour is used. If
+        running Airflow in a distributed manner and aws_conn_id is None or
+        empty, then default boto3 configuration would be used (and must be
+        maintained on each worker node).
+    :param region_name: AWS region_name. If not specified then the default boto3 behaviour is used.
+    :param verify: Whether to verify SSL certificates. See:
+        https://boto3.amazonaws.com/v1/documentation/api/latest/reference/core/session.html
+    :param botocore_config: Configuration dictionary (key-values) for botocore client. See:
+        https://botocore.amazonaws.com/v1/documentation/api/latest/reference/config.html
+    """
+
+    SUCCESS_STATES = ("SUCCEEDED",)
+
+    FAILURE_STATES = ("FAILED", "STOPPED", "STOPPING", "TIMEOUT")
+
+    aws_hook_class = GlueDataQualityHook
+    template_fields: Sequence[str] = aws_template_fields("recommendation_run_id")
+
+    def __init__(
+        self,
+        *,
+        recommendation_run_id: str,
+        show_results: bool = True,
+        deferrable: bool = conf.getboolean("operators", "default_deferrable", fallback=False),
+        poke_interval: int = 120,
+        max_retries: int = 60,
+        aws_conn_id: str | None = "aws_default",
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+        self.recommendation_run_id = recommendation_run_id
+        self.show_results = show_results
+        self.deferrable = deferrable
+        self.poke_interval = poke_interval
+        self.max_retries = max_retries
+        self.aws_conn_id = aws_conn_id
+
+    def execute(self, context: Context) -> Any:
+        if self.deferrable:
+            self.defer(
+                trigger=GlueDataQualityRuleRecommendationRunCompleteTrigger(
+                    recommendation_run_id=self.recommendation_run_id,
+                    waiter_delay=int(self.poke_interval),
+                    waiter_max_attempts=self.max_retries,
+                    aws_conn_id=self.aws_conn_id,
+                ),
+                method_name="execute_complete",
+            )
+        else:
+            super().execute(context=context)
+
+    def execute_complete(self, context: Context, event: dict[str, Any] | None = None) -> None:
+        event = validate_execute_complete_event(event)
+
+        if event["status"] != "success":
+            message = f"Error: AWS Glue data quality recommendation run: {event}"
+            if self.soft_fail:
+                raise AirflowSkipException(message)
+            raise AirflowException(message)
+
+        if self.show_results:
+            self.hook.log_recommendation_results(run_id=self.recommendation_run_id)
+
+        self.log.info("AWS Glue data quality recommendation run completed.")
+
+    def poke(self, context: Context) -> bool:
+        self.log.info(
+            "Poking for AWS Glue data quality recommendation run RunId: %s", self.recommendation_run_id
+        )
+
+        response = self.hook.conn.get_data_quality_rule_recommendation_run(RunId=self.recommendation_run_id)
+
+        status = response.get("Status")
+
+        if status in self.SUCCESS_STATES:
+            if self.show_results:
+                self.hook.log_recommendation_results(run_id=self.recommendation_run_id)
+
+            self.log.info(
+                "AWS Glue data quality recommendation run completed RunId: %s Run State: %s",
+                self.recommendation_run_id,
+                response["Status"],
+            )
+
+            return True
+
+        elif status in self.FAILURE_STATES:
+            job_error_message = (
+                f"Error: AWS Glue data quality recommendation run RunId: {self.recommendation_run_id} Run "
+                f"Status: {status}"
+                f": {response.get('ErrorString')}"
+            )
+            self.log.info(job_error_message)
+            # TODO: remove this if block when min_airflow_version is set to higher than 2.7.1
+            if self.soft_fail:
+                raise AirflowSkipException(job_error_message)
+            raise AirflowException(job_error_message)
+        else:
+            return False

airflow/providers/amazon/aws/sensors/s3.py

@@ -78,6 +78,11 @@ class S3KeySensor(BaseSensorOperator):
                  CA cert bundle than the one used by botocore.
     :param deferrable: Run operator in the deferrable mode
     :param use_regex: whether to use regex to check bucket
+    :param metadata_keys: List of head_object attributes to gather and send to ``check_fn``.
+        Acceptable values: Any top level attribute returned by s3.head_object. Specify * to return
+        all available attributes.
+        Default value: "Size".
+        If the requested attribute is not found, the key is still included and the value is None.
     """
 
     template_fields: Sequence[str] = ("bucket_key", "bucket_name")
@@ -93,6 +98,7 @@ class S3KeySensor(BaseSensorOperator):
         verify: str | bool | None = None,
         deferrable: bool = conf.getboolean("operators", "default_deferrable", fallback=False),
         use_regex: bool = False,
+        metadata_keys: list[str] | None = None,
         **kwargs,
     ):
         super().__init__(**kwargs)
@@ -104,14 +110,14 @@ class S3KeySensor(BaseSensorOperator):
         self.verify = verify
         self.deferrable = deferrable
         self.use_regex = use_regex
+        self.metadata_keys = metadata_keys if metadata_keys else ["Size"]
 
     def _check_key(self, key):
         bucket_name, key = S3Hook.get_s3_bucket_key(self.bucket_name, key, "bucket_name", "bucket_key")
         self.log.info("Poking for key : s3://%s/%s", bucket_name, key)
 
         """
-        Set variable `files` which contains a list of dict which contains only the size
-        If needed we might want to add other attributes later
+        Set variable `files` which contains a list of dict which contains attributes defined by the user
         Format: [{
             'Size': int
         }]
@@ -123,8 +129,21 @@ class S3KeySensor(BaseSensorOperator):
             if not key_matches:
                 return False
 
-            # Reduce the set of metadata to size only
-            files = [{"Size": f["Size"]} for f in key_matches]
+            # Reduce the set of metadata to requested attributes
+            files = []
+            for f in key_matches:
+                metadata = {}
+                if "*" in self.metadata_keys:
+                    metadata = self.hook.head_object(f["Key"], bucket_name)
+                else:
+                    for key in self.metadata_keys:
+                        try:
+                            metadata[key] = f[key]
+                        except KeyError:
+                            # supplied key might be from head_object response
+                            self.log.info("Key %s not found in response, performing head_object", key)
+                            metadata[key] = self.hook.head_object(f["Key"], bucket_name).get(key, None)
+                files.append(metadata)
         elif self.use_regex:
             keys = self.hook.get_file_metadata("", bucket_name)
             key_matches = [k for k in keys if re.match(pattern=key, string=k["Key"])]
@@ -134,7 +153,18 @@ class S3KeySensor(BaseSensorOperator):
             obj = self.hook.head_object(key, bucket_name)
             if obj is None:
                 return False
-            files = [{"Size": obj["ContentLength"]}]
+            metadata = {}
+            if "*" in self.metadata_keys:
+                metadata = self.hook.head_object(key, bucket_name)
+
+            else:
+                for key in self.metadata_keys:
+                    # backwards compatibility with original implementation
+                    if key == "Size":
+                        metadata[key] = obj.get("ContentLength")
+                    else:
+                        metadata[key] = obj.get(key, None)
+            files = [metadata]
 
         if self.check_fn is not None:
             return self.check_fn(files)

airflow/providers/amazon/aws/transfers/dynamodb_to_s3.py

@@ -105,7 +105,6 @@ class DynamoDBToS3Operator(AwsToAwsBaseOperator):
         "file_size",
         "dynamodb_scan_kwargs",
         "s3_key_prefix",
-        "process_func",
         "export_time",
         "export_format",
         "check_interval",

airflow/providers/amazon/aws/transfers/s3_to_dynamodb.py

@@ -0,0 +1,257 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Any, Literal, Sequence, TypedDict
+
+from botocore.exceptions import ClientError, WaiterError
+
+from airflow.exceptions import AirflowException
+from airflow.models import BaseOperator
+from airflow.providers.amazon.aws.hooks.dynamodb import DynamoDBHook
+
+if TYPE_CHECKING:
+    from airflow.utils.context import Context
+
+
+class AttributeDefinition(TypedDict):
+    """Attribute Definition Type."""
+
+    AttributeName: str
+    AttributeType: Literal["S", "N", "B"]
+
+
+class KeySchema(TypedDict):
+    """Key Schema Type."""
+
+    AttributeName: str
+    KeyType: Literal["HASH", "RANGE"]
+
+
+class S3ToDynamoDBOperator(BaseOperator):
+    """Load Data from S3 into a DynamoDB.
+
+    Data stored in S3 can be uploaded to a new or existing DynamoDB. Supported file formats CSV, DynamoDB JSON and
+    Amazon ION.
+
+
+    :param s3_bucket: The S3 bucket that is imported
+    :param s3_key: Key prefix that imports single or multiple objects from S3
+    :param dynamodb_table_name: Name of the table that shall be created
+    :param dynamodb_key_schema: Primary key and sort key. Each element represents one primary key
+        attribute. AttributeName is the name of the attribute. KeyType is the role for the attribute. Valid values
+        HASH or RANGE
+    :param dynamodb_attributes: Name of the attributes of a table. AttributeName is the name for the attribute
+        AttributeType is the data type for the attribute. Valid values for AttributeType are
+        S - attribute is of type String
+        N - attribute is of type Number
+        B - attribute is of type Binary
+    :param dynamodb_tmp_table_prefix: Prefix for the temporary DynamoDB table
+    :param delete_on_error: If set, the new DynamoDB table will be deleted in case of import errors
+    :param use_existing_table: Whether to import to an existing non new DynamoDB table. If set to
+        true data is loaded first into a temporary DynamoDB table (using the AWS ImportTable Service),
+        then retrieved as chunks into memory and loaded into the target table. If set to false, a new
+        DynamoDB table will be created and S3 data is bulk loaded by the AWS ImportTable Service.
+    :param input_format: The format for the imported data. Valid values for InputFormat are CSV, DYNAMODB_JSON
+        or ION
+    :param billing_mode: Billing mode for the table. Valid values are PROVISIONED or PAY_PER_REQUEST
+    :param on_demand_throughput: Extra options for maximum number of read and write units
+    :param import_table_kwargs: Any additional optional import table parameters to pass, such as ClientToken,
+        InputCompressionType, or InputFormatOptions. See:
+        https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/dynamodb/client/import_table.html
+    :param import_table_creation_kwargs: Any additional optional import table creation parameters to pass, such as
+        ProvisionedThroughput, SSESpecification, or GlobalSecondaryIndexes. See:
+        https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/dynamodb/client/import_table.html
+    :param wait_for_completion: Whether to wait for cluster to stop
+    :param check_interval: Time in seconds to wait between status checks
+    :param max_attempts: Maximum number of attempts to check for job completion
+    :param aws_conn_id: The reference to the AWS connection details
+    """
+
+    template_fields: Sequence[str] = (
+        "s3_bucket",
+        "s3_key",
+        "dynamodb_table_name",
+        "dynamodb_key_schema",
+        "dynamodb_attributes",
+        "dynamodb_tmp_table_prefix",
+        "delete_on_error",
+        "use_existing_table",
+        "input_format",
+        "billing_mode",
+        "import_table_kwargs",
+        "import_table_creation_kwargs",
+    )
+    ui_color = "#e2e8f0"
+
+    def __init__(
+        self,
+        *,
+        s3_bucket: str,
+        s3_key: str,
+        dynamodb_table_name: str,
+        dynamodb_key_schema: list[KeySchema],
+        dynamodb_attributes: list[AttributeDefinition] | None = None,
+        dynamodb_tmp_table_prefix: str = "tmp",
+        delete_on_error: bool = False,
+        use_existing_table: bool = False,
+        input_format: Literal["CSV", "DYNAMODB_JSON", "ION"] = "DYNAMODB_JSON",
+        billing_mode: Literal["PROVISIONED", "PAY_PER_REQUEST"] = "PAY_PER_REQUEST",
+        import_table_kwargs: dict[str, Any] | None = None,
+        import_table_creation_kwargs: dict[str, Any] | None = None,
+        wait_for_completion: bool = True,
+        check_interval: int = 30,
+        max_attempts: int = 240,
+        aws_conn_id: str | None = "aws_default",
+        **kwargs,
+    ) -> None:
+        super().__init__(**kwargs)
+        self.s3_bucket = s3_bucket
+        self.s3_key = s3_key
+        self.dynamodb_table_name = dynamodb_table_name
+        self.dynamodb_attributes = dynamodb_attributes
+        self.dynamodb_tmp_table_prefix = dynamodb_tmp_table_prefix
+        self.delete_on_error = delete_on_error
+        self.use_existing_table = use_existing_table
+        self.dynamodb_key_schema = dynamodb_key_schema
+        self.input_format = input_format
+        self.billing_mode = billing_mode
+        self.import_table_kwargs = import_table_kwargs
+        self.import_table_creation_kwargs = import_table_creation_kwargs
+        self.wait_for_completion = wait_for_completion
+        self.check_interval = check_interval
+        self.max_attempts = max_attempts
+        self.aws_conn_id = aws_conn_id
+
+    @property
+    def tmp_table_name(self):
+        """Temporary table name."""
+        return f"{self.dynamodb_tmp_table_prefix}_{self.dynamodb_table_name}"
+
+    def _load_into_new_table(self, table_name: str, delete_on_error: bool) -> str:
+        """
+        Import S3 key or keys into a new DynamoDB table.
+
+        :param table_name: Name of the table that shall be created
+        :param delete_on_error: If set, the new DynamoDB table will be deleted in case of import errors
+        :return: The Amazon resource number (ARN)
+        """
+        dynamodb_hook = DynamoDBHook(aws_conn_id=self.aws_conn_id)
+        client = dynamodb_hook.client
+
+        import_table_config = self.import_table_kwargs or {}
+        import_table_creation_config = self.import_table_creation_kwargs or {}
+
+        try:
+            response = client.import_table(
+                S3BucketSource={
+                    "S3Bucket": self.s3_bucket,
+                    "S3KeyPrefix": self.s3_key,
+                },
+                InputFormat=self.input_format,
+                TableCreationParameters={
+                    "TableName": table_name,
+                    "AttributeDefinitions": self.dynamodb_attributes,
+                    "KeySchema": self.dynamodb_key_schema,
+                    "BillingMode": self.billing_mode,
+                    **import_table_creation_config,
+                },
+                **import_table_config,
+            )
+        except ClientError as e:
+            self.log.error("Error: failed to load from S3 into DynamoDB table. Error: %s", str(e))
+            raise AirflowException(f"S3 load into DynamoDB table failed with error: {e}")
+
+        if response["ImportTableDescription"]["ImportStatus"] == "FAILED":
+            raise AirflowException(
+                "S3 into Dynamodb job creation failed. Code: "
+                f"{response['ImportTableDescription']['FailureCode']}. "
+                f"Failure: {response['ImportTableDescription']['FailureMessage']}"
+            )
+
+        if self.wait_for_completion:
+            self.log.info("Waiting for S3 into Dynamodb job to complete")
+            waiter = dynamodb_hook.get_waiter("import_table")
+            try:
+                waiter.wait(
+                    ImportArn=response["ImportTableDescription"]["ImportArn"],
+                    WaiterConfig={"Delay": self.check_interval, "MaxAttempts": self.max_attempts},
+                )
+            except WaiterError:
+                status, error_code, error_msg = dynamodb_hook.get_import_status(
+                    response["ImportTableDescription"]["ImportArn"]
+                )
+                if delete_on_error:
+                    client.delete_table(TableName=table_name)
+                raise AirflowException(
+                    f"S3 import into Dynamodb job failed: Status: {status}. Error: {error_code}. Error message: {error_msg}"
+                )
+        return response["ImportTableDescription"]["ImportArn"]
+
+    def _load_into_existing_table(self) -> str:
+        """
+        Import S3 key or keys in an existing DynamoDB table.
+
+        :return:The Amazon resource number (ARN)
+        """
+        if not self.wait_for_completion:
+            raise ValueError("wait_for_completion must be set to True when loading into an existing table")
+        table_keys = [key["AttributeName"] for key in self.dynamodb_key_schema]
+
+        dynamodb_hook = DynamoDBHook(
+            aws_conn_id=self.aws_conn_id, table_name=self.dynamodb_table_name, table_keys=table_keys
+        )
+        client = dynamodb_hook.client
+
+        self.log.info("Loading from S3 into a tmp DynamoDB table %s", self.tmp_table_name)
+        self._load_into_new_table(table_name=self.tmp_table_name, delete_on_error=self.delete_on_error)
+        total_items = 0
+        try:
+            paginator = client.get_paginator("scan")
+            paginate = paginator.paginate(
+                TableName=self.tmp_table_name,
+                Select="ALL_ATTRIBUTES",
+                ReturnConsumedCapacity="NONE",
+                ConsistentRead=True,
+            )
+            self.log.info(
+                "Loading data from %s to %s DynamoDB table", self.tmp_table_name, self.dynamodb_table_name
+            )
+            for page in paginate:
+                total_items += page.get("Count", 0)
+                dynamodb_hook.write_batch_data(items=page["Items"])
+            self.log.info("Number of items loaded: %s", total_items)
+        finally:
+            self.log.info("Delete tmp DynamoDB table %s", self.tmp_table_name)
+            client.delete_table(TableName=self.tmp_table_name)
+            return dynamodb_hook.get_conn().Table(self.dynamodb_table_name).table_arn
+
+    def execute(self, context: Context) -> str:
+        """
+        Execute S3 to DynamoDB Job from Airflow.
+
+        :param context: The current context of the task instance
+        :return: The Amazon resource number (ARN)
+        """
+        if self.use_existing_table:
+            self.log.info("Loading from S3 into new DynamoDB table %s", self.dynamodb_table_name)
+            return self._load_into_existing_table()
+        self.log.info("Loading from S3 into existing DynamoDB table %s", self.dynamodb_table_name)
+        return self._load_into_new_table(
+            table_name=self.dynamodb_table_name, delete_on_error=self.delete_on_error
+        )