Beispiel #1
0
  def __init__(
      self,
      stream_name,
      aws_access_key,
      aws_secret_key,
      region,
      partition_key,
      service_endpoint=None,
      verify_certificate=None,
      producer_properties=None,
      expansion_service=None,
  ):
    """
    Initializes a write operation to Kinesis.

    :param stream_name: Kinesis stream name.
    :param aws_access_key: Kinesis access key.
    :param aws_secret_key: Kinesis access key secret.
    :param region: AWS region. Example: 'us-east-1'.
    :param service_endpoint: Kinesis service endpoint
    :param verify_certificate: Enable or disable certificate verification.
        Never set to False on production. True by default.
    :param partition_key: Specify default partition key.
    :param producer_properties: Specify the configuration properties for Kinesis
        Producer Library (KPL) as dictionary.
        Example: {'CollectionMaxCount': '1000', 'ConnectTimeout': '10000'}
    :param expansion_service: The address (host:port) of the ExpansionService.
    """
    super().__init__(
        self.URN,
        NamedTupleBasedPayloadBuilder(
            WriteToKinesisSchema(
                stream_name=stream_name,
                aws_access_key=aws_access_key,
                aws_secret_key=aws_secret_key,
                region=region,
                partition_key=partition_key,
                service_endpoint=service_endpoint,
                verify_certificate=verify_certificate,
                producer_properties=producer_properties,
            )),
        expansion_service or default_io_expansion_service(),
    )
Beispiel #2
0
  def __init__(
      self,
      stream_name,
      aws_access_key,
      aws_secret_key,
      region,
      service_endpoint=None,
      verify_certificate=None,
      max_num_records=None,
      max_read_time=None,
      initial_position_in_stream=None,
      initial_timestamp_in_stream=None,
      request_records_limit=None,
      up_to_date_threshold=None,
      max_capacity_per_shard=None,
      watermark_policy=None,
      watermark_idle_duration_threshold=None,
      rate_limit=None,
      expansion_service=None,
  ):
    """
    Initializes a read operation from Kinesis.

    :param stream_name: Kinesis stream name.
    :param aws_access_key: Kinesis access key.
    :param aws_secret_key: Kinesis access key secret.
    :param region: AWS region. Example: 'us-east-1'.
    :param service_endpoint: Kinesis service endpoint
    :param verify_certificate: Enable or disable certificate verification.
        Never set to False on production. True by default.
    :param max_num_records: Specifies to read at most a given number of records.
        Must be greater than 0.
    :param max_read_time: Specifies to read records during x milliseconds.
    :param initial_timestamp_in_stream: Specify reading beginning at the given
        timestamp in milliseconds. Must be in the past.
    :param initial_position_in_stream: Specify reading from some initial
        position in stream. Possible values:
        LATEST - Start after the most recent data record (fetch new data).
        TRIM_HORIZON - Start from the oldest available data record.
        AT_TIMESTAMP - Start from the record at or after the specified
        server-side timestamp.
    :param request_records_limit: Specifies the maximum number of records in
        GetRecordsResult returned by GetRecords call which is limited by 10K
        records. If should be adjusted according to average size of data record
        to prevent shard overloading. More at:
        docs.aws.amazon.com/kinesis/latest/APIReference/API_GetRecords.html
    :param up_to_date_threshold: Specifies how late in milliseconds records
        consumed by this source can be to still be considered on time. Defaults
        to zero.
    :param max_capacity_per_shard: Specifies the maximum number of messages per
        one shard. Defaults to 10'000.
    :param watermark_policy: Specifies the watermark policy. Possible values:
        PROCESSING_TYPE, ARRIVAL_TIME. Defaults to ARRIVAL_TIME.
    :param watermark_idle_duration_threshold: Use only when watermark policy is
        ARRIVAL_TIME. Denotes the duration for which the watermark can be idle.
        Passed in milliseconds.
    :param rate_limit: Sets fixed rate policy for given milliseconds value. By
        default there is no rate limit.
    :param expansion_service: The address (host:port) of the ExpansionService.
    """
    WatermarkPolicy.validate_param(watermark_policy)
    InitialPositionInStream.validate_param(initial_position_in_stream)

    if watermark_idle_duration_threshold:
      assert WatermarkPolicy.ARRIVAL_TIME == watermark_policy

    if request_records_limit:
      assert 0 < request_records_limit <= 10000

    initial_timestamp_in_stream = int(
        initial_timestamp_in_stream) if initial_timestamp_in_stream else None

    if initial_timestamp_in_stream and initial_timestamp_in_stream < time.time(
    ):
      logging.warning('Provided timestamp emplaced not in the past.')

    super().__init__(
        self.URN,
        NamedTupleBasedPayloadBuilder(
            ReadFromKinesisSchema(
                stream_name=stream_name,
                aws_access_key=aws_access_key,
                aws_secret_key=aws_secret_key,
                region=region,
                service_endpoint=service_endpoint,
                verify_certificate=verify_certificate,
                max_num_records=max_num_records,
                max_read_time=max_read_time,
                initial_position_in_stream=initial_position_in_stream,
                initial_timestamp_in_stream=initial_timestamp_in_stream,
                request_records_limit=request_records_limit,
                up_to_date_threshold=up_to_date_threshold,
                max_capacity_per_shard=max_capacity_per_shard,
                watermark_policy=watermark_policy,
                watermark_idle_duration_threshold=
                watermark_idle_duration_threshold,
                rate_limit=rate_limit,
            )),
        expansion_service or default_io_expansion_service(),
    )
Beispiel #3
0
 def __init__(self, tag, expansion_service):
     # type: (str, JavaJarExpansionService) -> None
     super(Print, self).__init__(
         self.URN, NamedTupleBasedPayloadBuilder(PrintSchema(tag=tag)),
         expansion_service)