com.amazonaws.services.kinesisfirehose.AmazonKinesisFirehose Maven / Gradle / Ivy
Show all versions of aws-java-sdk-kinesis Show documentation
/*
* Copyright 2012-2017 Amazon.com, Inc. or its affiliates. All Rights Reserved.
*
* Licensed under the Apache License, Version 2.0 (the "License"). You may not use this file except in compliance with
* the License. A copy of the License is located at
*
* http://aws.amazon.com/apache2.0
*
* or in the "license" file accompanying this file. This file 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.
*/
package com.amazonaws.services.kinesisfirehose;
import javax.annotation.Generated;
import com.amazonaws.*;
import com.amazonaws.regions.*;
import com.amazonaws.services.kinesisfirehose.model.*;
/**
* Interface for accessing Firehose.
*
* Note: Do not directly implement this interface, new methods are added to it regularly. Extend from
* {@link com.amazonaws.services.kinesisfirehose.AbstractAmazonKinesisFirehose} instead.
*
*
* Amazon Kinesis Firehose API Reference
*
* Amazon Kinesis Firehose is a fully-managed service that delivers real-time streaming data to destinations such as
* Amazon Simple Storage Service (Amazon S3), Amazon Elasticsearch Service (Amazon ES), and Amazon Redshift.
*
*/
@Generated("com.amazonaws:aws-java-sdk-code-generator")
public interface AmazonKinesisFirehose {
/**
* The region metadata service name for computing region endpoints. You can use this value to retrieve metadata
* (such as supported regions) of the service.
*
* @see RegionUtils#getRegionsForService(String)
*/
String ENDPOINT_PREFIX = "firehose";
/**
* Overrides the default endpoint for this client ("https://firehose.us-east-1.amazonaws.com"). Callers can use this
* method to control which AWS region they want to work with.
*
* Callers can pass in just the endpoint (ex: "firehose.us-east-1.amazonaws.com") or a full URL, including the
* protocol (ex: "https://firehose.us-east-1.amazonaws.com"). If the protocol is not specified here, the default
* protocol from this client's {@link ClientConfiguration} will be used, which by default is HTTPS.
*
* For more information on using AWS regions with the AWS SDK for Java, and a complete list of all available
* endpoints for all AWS services, see:
* http://developer.amazonwebservices.com/connect/entry.jspa?externalID=3912
*
* This method is not threadsafe. An endpoint should be configured when the client is created and before any
* service requests are made. Changing it afterwards creates inevitable race conditions for any service requests in
* transit or retrying.
*
* @param endpoint
* The endpoint (ex: "firehose.us-east-1.amazonaws.com") or a full URL, including the protocol (ex:
* "https://firehose.us-east-1.amazonaws.com") of the region specific AWS endpoint this client will
* communicate with.
* @deprecated use {@link AwsClientBuilder#setEndpointConfiguration(AwsClientBuilder.EndpointConfiguration)} for
* example:
* {@code builder.setEndpointConfiguration(new EndpointConfiguration(endpoint, signingRegion));}
*/
@Deprecated
void setEndpoint(String endpoint);
/**
* An alternative to {@link AmazonKinesisFirehose#setEndpoint(String)}, sets the regional endpoint for this client's
* service calls. Callers can use this method to control which AWS region they want to work with.
*
* By default, all service endpoints in all regions use the https protocol. To use http instead, specify it in the
* {@link ClientConfiguration} supplied at construction.
*
* This method is not threadsafe. A region should be configured when the client is created and before any service
* requests are made. Changing it afterwards creates inevitable race conditions for any service requests in transit
* or retrying.
*
* @param region
* The region this client will communicate with. See {@link Region#getRegion(com.amazonaws.regions.Regions)}
* for accessing a given region. Must not be null and must be a region where the service is available.
*
* @see Region#getRegion(com.amazonaws.regions.Regions)
* @see Region#createClient(Class, com.amazonaws.auth.AWSCredentialsProvider, ClientConfiguration)
* @see Region#isServiceSupported(String)
* @deprecated use {@link AwsClientBuilder#setRegion(String)}
*/
@Deprecated
void setRegion(Region region);
/**
*
* Creates a delivery stream.
*
*
* By default, you can create up to 20 delivery streams per region.
*
*
* This is an asynchronous operation that immediately returns. The initial status of the delivery stream is
* CREATING. After the delivery stream is created, its status is ACTIVE and it now accepts
* data. Attempts to send data to a delivery stream that is not in the ACTIVE state cause an exception.
* To check the state of a delivery stream, use DescribeDeliveryStream.
*
*
* A delivery stream is configured with a single destination: Amazon S3, Amazon Elasticsearch Service, or Amazon
* Redshift. You must specify only one of the following destination configuration parameters:
* ExtendedS3DestinationConfiguration, S3DestinationConfiguration,
* ElasticsearchDestinationConfiguration, or RedshiftDestinationConfiguration.
*
*
* When you specify S3DestinationConfiguration, you can also provide the following optional values:
* BufferingHints, EncryptionConfiguration, and CompressionFormat. By default, if no
* BufferingHints value is provided, Firehose buffers data up to 5 MB or for 5 minutes, whichever condition
* is satisfied first. Note that BufferingHints is a hint, so there are some cases where the service cannot
* adhere to these conditions strictly; for example, record boundaries are such that the size is a little over or
* under the configured buffering size. By default, no encryption is performed. We strongly recommend that you
* enable encryption to ensure secure data storage in Amazon S3.
*
*
* A few notes about Amazon Redshift as a destination:
*
*
* -
*
* An Amazon Redshift destination requires an S3 bucket as intermediate location, as Firehose first delivers data to
* S3 and then uses COPY syntax to load data into an Amazon Redshift table. This is specified in the
* RedshiftDestinationConfiguration.S3Configuration parameter.
*
*
* -
*
* The compression formats SNAPPY or ZIP cannot be specified in
* RedshiftDestinationConfiguration.S3Configuration because the Amazon Redshift COPY operation
* that reads from the S3 bucket doesn't support these compression formats.
*
*
* -
*
* We strongly recommend that you use the user name and password you provide exclusively with Firehose, and that the
* permissions for the account are restricted for Amazon Redshift INSERT permissions.
*
*
*
*
* Firehose assumes the IAM role that is configured as part of the destination. The role should allow the Firehose
* principal to assume the role, and the role should have permissions that allows the service to deliver the data.
* For more information, see Amazon S3 Bucket
* Access in the Amazon Kinesis Firehose Developer Guide.
*
*
* @param createDeliveryStreamRequest
* @return Result of the CreateDeliveryStream operation returned by the service.
* @throws InvalidArgumentException
* The specified input parameter has an value that is not valid.
* @throws LimitExceededException
* You have already reached the limit for a requested resource.
* @throws ResourceInUseException
* The resource is already in use and not available for this operation.
* @sample AmazonKinesisFirehose.CreateDeliveryStream
* @see AWS
* API Documentation
*/
CreateDeliveryStreamResult createDeliveryStream(CreateDeliveryStreamRequest createDeliveryStreamRequest);
/**
*
* Deletes a delivery stream and its data.
*
*
* You can delete a delivery stream only if it is in ACTIVE or DELETING state, and not in
* the CREATING state. While the deletion request is in process, the delivery stream is in the
* DELETING state.
*
*
* To check the state of a delivery stream, use DescribeDeliveryStream.
*
*
* While the delivery stream is DELETING state, the service may continue to accept the records, but the
* service doesn't make any guarantees with respect to delivering the data. Therefore, as a best practice, you
* should first stop any applications that are sending records before deleting a delivery stream.
*
*
* @param deleteDeliveryStreamRequest
* @return Result of the DeleteDeliveryStream operation returned by the service.
* @throws ResourceInUseException
* The resource is already in use and not available for this operation.
* @throws ResourceNotFoundException
* The specified resource could not be found.
* @sample AmazonKinesisFirehose.DeleteDeliveryStream
* @see AWS
* API Documentation
*/
DeleteDeliveryStreamResult deleteDeliveryStream(DeleteDeliveryStreamRequest deleteDeliveryStreamRequest);
/**
*
* Describes the specified delivery stream and gets the status. For example, after your delivery stream is created,
* call DescribeDeliveryStream to see if the delivery stream is ACTIVE and therefore ready for
* data to be sent to it.
*
*
* @param describeDeliveryStreamRequest
* @return Result of the DescribeDeliveryStream operation returned by the service.
* @throws ResourceNotFoundException
* The specified resource could not be found.
* @sample AmazonKinesisFirehose.DescribeDeliveryStream
* @see AWS API Documentation
*/
DescribeDeliveryStreamResult describeDeliveryStream(DescribeDeliveryStreamRequest describeDeliveryStreamRequest);
/**
*
* Lists your delivery streams.
*
*
* The number of delivery streams might be too large to return using a single call to ListDeliveryStreams.
* You can limit the number of delivery streams returned, using the Limit parameter. To determine whether
* there are more delivery streams to list, check the value of HasMoreDeliveryStreams in the output. If there
* are more delivery streams to list, you can request them by specifying the name of the last delivery stream
* returned in the call in the ExclusiveStartDeliveryStreamName parameter of a subsequent call.
*
*
* @param listDeliveryStreamsRequest
* @return Result of the ListDeliveryStreams operation returned by the service.
* @sample AmazonKinesisFirehose.ListDeliveryStreams
* @see AWS
* API Documentation
*/
ListDeliveryStreamsResult listDeliveryStreams(ListDeliveryStreamsRequest listDeliveryStreamsRequest);
/**
*
* Writes a single data record into an Amazon Kinesis Firehose delivery stream. To write multiple data records into
* a delivery stream, use PutRecordBatch. Applications using these operations are referred to as producers.
*
*
* By default, each delivery stream can take in up to 2,000 transactions per second, 5,000 records per second, or 5
* MB per second. Note that if you use PutRecord and PutRecordBatch, the limits are an aggregate
* across these two operations for each delivery stream. For more information about limits and how to request an
* increase, see Amazon Kinesis Firehose
* Limits.
*
*
* You must specify the name of the delivery stream and the data record when using PutRecord. The data record
* consists of a data blob that can be up to 1,000 KB in size, and any kind of data, for example, a segment from a
* log file, geographic location data, web site clickstream data, etc.
*
*
* Firehose buffers records before delivering them to the destination. To disambiguate the data blobs at the
* destination, a common solution is to use delimiters in the data, such as a newline (\n) or some
* other character unique within the data. This allows the consumer application(s) to parse individual data items
* when reading the data from the destination.
*
*
* The PutRecord operation returns a RecordId, which is a unique string assigned to each record.
* Producer applications can use this ID for purposes such as auditability and investigation.
*
*
* If the PutRecord operation throws a ServiceUnavailableException, back off and retry. If the
* exception persists, it is possible that the throughput limits have been exceeded for the delivery stream.
*
*
* Data records sent to Firehose are stored for 24 hours from the time they are added to a delivery stream as it
* attempts to send the records to the destination. If the destination is unreachable for more than 24 hours, the
* data is no longer available.
*
*
* @param putRecordRequest
* @return Result of the PutRecord operation returned by the service.
* @throws ResourceNotFoundException
* The specified resource could not be found.
* @throws InvalidArgumentException
* The specified input parameter has an value that is not valid.
* @throws ServiceUnavailableException
* The service is unavailable, back off and retry the operation. If you continue to see the exception,
* throughput limits for the delivery stream may have been exceeded. For more information about limits and
* how to request an increase, see Amazon Kinesis Firehose Limits.
* @sample AmazonKinesisFirehose.PutRecord
* @see AWS API
* Documentation
*/
PutRecordResult putRecord(PutRecordRequest putRecordRequest);
/**
*
* Writes multiple data records into a delivery stream in a single call, which can achieve higher throughput per
* producer than when writing single records. To write single data records into a delivery stream, use
* PutRecord. Applications using these operations are referred to as producers.
*
*
* By default, each delivery stream can take in up to 2,000 transactions per second, 5,000 records per second, or 5
* MB per second. Note that if you use PutRecord and PutRecordBatch, the limits are an aggregate
* across these two operations for each delivery stream. For more information about limits, see Amazon Kinesis Firehose Limits.
*
*
* Each PutRecordBatch request supports up to 500 records. Each record in the request can be as large as
* 1,000 KB (before 64-bit encoding), up to a limit of 4 MB for the entire request. These limits cannot be changed.
*
*
* You must specify the name of the delivery stream and the data record when using PutRecord. The data record
* consists of a data blob that can be up to 1,000 KB in size, and any kind of data, for example, a segment from a
* log file, geographic location data, web site clickstream data, and so on.
*
*
* Firehose buffers records before delivering them to the destination. To disambiguate the data blobs at the
* destination, a common solution is to use delimiters in the data, such as a newline (\n) or some
* other character unique within the data. This allows the consumer application(s) to parse individual data items
* when reading the data from the destination.
*
*
* The PutRecordBatch response includes a count of failed records, FailedPutCount, and an array of
* responses, RequestResponses. Each entry in the RequestResponses array provides additional
* information about the processed record, and directly correlates with a record in the request array using the same
* ordering, from the top to the bottom. The response array always includes the same number of records as the
* request array. RequestResponses includes both successfully and unsuccessfully processed records. Firehose
* attempts to process all records in each PutRecordBatch request. A single record failure does not stop the
* processing of subsequent records.
*
*
* A successfully processed record includes a RecordId value, which is unique for the record. An
* unsuccessfully processed record includes ErrorCode and ErrorMessage values. ErrorCode
* reflects the type of error, and is one of the following values: ServiceUnavailable or
* InternalFailure. ErrorMessage provides more detailed information about the error.
*
*
* If there is an internal server error or a timeout, the write might have completed or it might have failed. If
* FailedPutCount is greater than 0, retry the request, resending only those records that might have failed
* processing. This minimizes the possible duplicate records and also reduces the total bytes sent (and
* corresponding charges). We recommend that you handle any duplicates at the destination.
*
*
* If PutRecordBatch throws ServiceUnavailableException, back off and retry. If the exception
* persists, it is possible that the throughput limits have been exceeded for the delivery stream.
*
*
* Data records sent to Firehose are stored for 24 hours from the time they are added to a delivery stream as it
* attempts to send the records to the destination. If the destination is unreachable for more than 24 hours, the
* data is no longer available.
*
*
* @param putRecordBatchRequest
* @return Result of the PutRecordBatch operation returned by the service.
* @throws ResourceNotFoundException
* The specified resource could not be found.
* @throws InvalidArgumentException
* The specified input parameter has an value that is not valid.
* @throws ServiceUnavailableException
* The service is unavailable, back off and retry the operation. If you continue to see the exception,
* throughput limits for the delivery stream may have been exceeded. For more information about limits and
* how to request an increase, see Amazon Kinesis Firehose Limits.
* @sample AmazonKinesisFirehose.PutRecordBatch
* @see AWS API
* Documentation
*/
PutRecordBatchResult putRecordBatch(PutRecordBatchRequest putRecordBatchRequest);
/**
*
* Updates the specified destination of the specified delivery stream.
*
*
* You can use this operation to change the destination type (for example, to replace the Amazon S3 destination with
* Amazon Redshift) or change the parameters associated with a destination (for example, to change the bucket name
* of the Amazon S3 destination). The update might not occur immediately. The target delivery stream remains active
* while the configurations are updated, so data writes to the delivery stream can continue during this process. The
* updated configurations are usually effective within a few minutes.
*
*
* Note that switching between Amazon ES and other services is not supported. For an Amazon ES destination, you can
* only update to another Amazon ES destination.
*
*
* If the destination type is the same, Firehose merges the configuration parameters specified with the destination
* configuration that already exists on the delivery stream. If any of the parameters are not specified in the call,
* the existing values are retained. For example, in the Amazon S3 destination, if EncryptionConfiguration is
* not specified then the existing EncryptionConfiguration is maintained on the destination.
*
*
* If the destination type is not the same, for example, changing the destination from Amazon S3 to Amazon Redshift,
* Firehose does not merge any parameters. In this case, all parameters must be specified.
*
*
* Firehose uses CurrentDeliveryStreamVersionId to avoid race conditions and conflicting merges. This is a
* required field, and the service updates the configuration only if the existing configuration has a version ID
* that matches. After the update is applied successfully, the version ID is updated, and can be retrieved using
* DescribeDeliveryStream. You should use the new version ID to set CurrentDeliveryStreamVersionId in
* the next call.
*
*
* @param updateDestinationRequest
* @return Result of the UpdateDestination operation returned by the service.
* @throws InvalidArgumentException
* The specified input parameter has an value that is not valid.
* @throws ResourceInUseException
* The resource is already in use and not available for this operation.
* @throws ResourceNotFoundException
* The specified resource could not be found.
* @throws ConcurrentModificationException
* Another modification has already happened. Fetch VersionId again and use it to update the
* destination.
* @sample AmazonKinesisFirehose.UpdateDestination
* @see AWS API
* Documentation
*/
UpdateDestinationResult updateDestination(UpdateDestinationRequest updateDestinationRequest);
/**
* Shuts down this client object, releasing any resources that might be held open. This is an optional method, and
* callers are not expected to call it, but can if they want to explicitly release any open resources. Once a client
* has been shutdown, it should not be used to make any more requests.
*/
void shutdown();
/**
* Returns additional metadata for a previously executed successful request, typically used for debugging issues
* where a service isn't acting as expected. This data isn't considered part of the result data returned by an
* operation, so it's available through this separate, diagnostic interface.
*
* Response metadata is only cached for a limited period of time, so if you need to access this extra diagnostic
* information for an executed request, you should use this method to retrieve it as soon as possible after
* executing a request.
*
* @param request
* The originally executed request.
*
* @return The response metadata for the specified request, or null if none is available.
*/
ResponseMetadata getCachedResponseMetadata(AmazonWebServiceRequest request);
}