Source code for apache_beam.transforms.xlang.io

#
# 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.
#

# NOTE: This file contains autogenerated external transform(s)
# and should not be edited by hand.
# Refer to gen_xlang_wrappers.py for more info.

"""Cross-language transforms in this module can be imported from the
:py:mod:`apache_beam.io` package."""

# pylint:disable=line-too-long

from apache_beam.transforms.external import BeamJarExpansionService
from apache_beam.transforms.external_transform_provider import ExternalTransform


[docs] class DatadogWrite(ExternalTransform): identifier = "beam:schematransform:org.apache.beam:datadog_write:v1" def __init__( self, api_key, url, batch_count=None, error_handling=None, max_buffer_size=None, min_batch_count=None, parallelism=None, expansion_service=None): """ :param api_key: (str) The Datadog API key. :param url: (str) The Datadog API URL. :param batch_count: (int32) The number of events to batch together for each write. :param error_handling: (Row(output=<class 'str'>)) Specifies how to handle errors. :param max_buffer_size: (int64) The maximum buffer size in bytes. :param min_batch_count: (int32) The minimum number of events to batch together for each write. :param parallelism: (int32) The degree of parallelism for writing. """ self.default_expansion_service = BeamJarExpansionService( "sdks:java:io:expansion-service:shadowJar") super().__init__( api_key=api_key, url=url, batch_count=batch_count, error_handling=error_handling, max_buffer_size=max_buffer_size, min_batch_count=min_batch_count, parallelism=parallelism, expansion_service=expansion_service)
[docs] class GenerateSequence(ExternalTransform): """ Outputs a PCollection of Beam Rows, each containing a single INT64 number called "value". The count is produced from the given "start" value and either up to the given "end" or until 2^63 - 1. To produce an unbounded PCollection, simply do not specify an "end" value. Unbounded sequences can specify a "rate" for output elements. In all cases, the sequence of numbers is generated in parallel, so there is no inherent ordering between the generated values """ identifier = "beam:schematransform:org.apache.beam:generate_sequence:v1" def __init__(self, start, end=None, rate=None, expansion_service=None): """ :param start: (int64) The minimum number to generate (inclusive). :param end: (int64) The maximum number to generate (exclusive). Will be an unbounded sequence if left unspecified. :param rate: (Row(elements=<class 'int64'>, seconds=typing.Optional[int64])) Specifies the rate to generate a given number of elements per a given number of seconds. Applicable only to unbounded sequences. """ self.default_expansion_service = BeamJarExpansionService( "sdks:java:io:expansion-service:shadowJar") super().__init__( start=start, end=end, rate=rate, expansion_service=expansion_service)
[docs] class MongodbWrite(ExternalTransform): identifier = "beam:schematransform:org.apache.beam:mongodb_write:v1" def __init__( self, collection, database, uri, batch_size=None, error_handling=None, expansion_service=None): """ :param collection: (str) The MongoDB collection to write to. :param database: (str) The MongoDB database to write to. :param uri: (str) The connection URI for the MongoDB server. :param batch_size: (int64) The number of documents to include in each batch write. :param error_handling: (Row(output=<class 'str'>)) This option specifies whether and where to output unwritable rows. Note: Error handling is currently limited to data conversion failures before sending to the MongoDB driver, as the underlying MongoDbIO does not yet support dead-letter queues for write failures. """ self.default_expansion_service = BeamJarExpansionService( "sdks:java:io:expansion-service:shadowJar") super().__init__( collection=collection, database=database, uri=uri, batch_size=batch_size, error_handling=error_handling, expansion_service=expansion_service)
[docs] class TfrecordRead(ExternalTransform): identifier = "beam:schematransform:org.apache.beam:tfrecord_read:v1" def __init__( self, compression, file_pattern, validate, error_handling=None, expansion_service=None): """ :param compression: (str) Decompression type to use when reading input files. :param file_pattern: (str) Filename or file pattern used to find input files. :param validate: (boolean) Validate file pattern. :param error_handling: (Row(output=<class 'str'>)) This option specifies whether and where to output unwritable rows. """ self.default_expansion_service = BeamJarExpansionService( "sdks:java:io:expansion-service:shadowJar") super().__init__( compression=compression, file_pattern=file_pattern, validate=validate, error_handling=error_handling, expansion_service=expansion_service)
[docs] class TfrecordWrite(ExternalTransform): identifier = "beam:schematransform:org.apache.beam:tfrecord_write:v1" def __init__( self, compression, num_shards, output_prefix, error_handling=None, filename_suffix=None, max_num_writers_per_bundle=None, no_spilling=None, shard_template=None, expansion_service=None): """ :param compression: (str) Option to indicate the output sink's compression type. Default is NONE. :param num_shards: (int32) The number of shards to use, or 0 for automatic. :param output_prefix: (str) The directory to which files will be written. :param error_handling: (Row(output=<class 'str'>)) This option specifies whether and where to output unwritable rows. :param filename_suffix: (str) The suffix of each file written, combined with prefix and shardTemplate. :param max_num_writers_per_bundle: (int32) Maximum number of writers created in a bundle before spilling to shuffle. :param no_spilling: (boolean) Whether to skip the spilling of data caused by having maxNumWritersPerBundle. :param shard_template: (str) The shard template of each file written, combined with prefix and suffix. """ self.default_expansion_service = BeamJarExpansionService( "sdks:java:io:expansion-service:shadowJar") super().__init__( compression=compression, num_shards=num_shards, output_prefix=output_prefix, error_handling=error_handling, filename_suffix=filename_suffix, max_num_writers_per_bundle=max_num_writers_per_bundle, no_spilling=no_spilling, shard_template=shard_template, expansion_service=expansion_service)
[docs] class ReadFromMqtt(ExternalTransform): """ Reads messages from an MQTT broker and outputs each payload as a single `bytes` field. By default the read is unbounded (streaming): it keeps consuming messages from the subscribed topic until the pipeline is stopped. Setting `maxNumRecords` and/or `maxReadTimeSeconds` bounds the read, producing a bounded (batch) PCollection. Note: streaming reads require a runner that supports portable streaming (e.g. Prism, Flink, or Dataflow). The legacy local Python DirectRunner does not execute portable streaming cross-language reads. """ identifier = "beam:schematransform:org.apache.beam:mqtt_read:v1" def __init__( self, connection_configuration, max_num_records=None, max_read_time_seconds=None, expansion_service=None): """ :param connection_configuration: (Row(client_id=typing.Optional[str], password=typing.Optional[str], server_uri=<class 'str'>, topic=typing.Optional[str], username=typing.Optional[str])) Configuration options to set up the MQTT connection. :param max_num_records: (int64) The max number of records to receive. Setting this will result in a bounded PCollection. :param max_read_time_seconds: (int64) The maximum time for this source to read messages. Setting this will result in a bounded PCollection. """ self.default_expansion_service = BeamJarExpansionService( "sdks:java:io:messaging-expansion-service:shadowJar") super().__init__( connection_configuration=connection_configuration, max_num_records=max_num_records, max_read_time_seconds=max_read_time_seconds, expansion_service=expansion_service)
[docs] class WriteToMqtt(ExternalTransform): """ Publishes messages to an MQTT broker. Expects an input PCollection of rows with a single `bytes` field, each of which is published as one MQTT message. Works with both bounded (batch) and unbounded (streaming) input PCollections. """ identifier = "beam:schematransform:org.apache.beam:mqtt_write:v1" def __init__( self, connection_configuration, retained=None, expansion_service=None): """ :param connection_configuration: (Row(client_id=typing.Optional[str], password=typing.Optional[str], server_uri=<class 'str'>, topic=typing.Optional[str], username=typing.Optional[str])) Configuration options to set up the MQTT connection. :param retained: (boolean) Whether or not the publish message should be retained by the messaging engine. When a subscriber connects, it gets the latest retained message. Defaults to `False`, which will clear the retained message from the server. """ self.default_expansion_service = BeamJarExpansionService( "sdks:java:io:messaging-expansion-service:shadowJar") super().__init__( connection_configuration=connection_configuration, retained=retained, expansion_service=expansion_service)