sdks/standard_external_transforms.yaml

#
# 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 is autogenerated and should not be edited by hand.
# Configs are generated based on the expansion service
# configuration in /sdks/standard_expansion_services.yaml.
# Refer to gen_xlang_wrappers.py for more info.
#
# Last updated on: 2025-06-05

- default_service: sdks:java:io:expansion-service:shadowJar
  description: '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'
  destinations:
    python: apache_beam/io
  fields:
  - description: The maximum number to generate (exclusive). Will be an unbounded
      sequence if left unspecified.
    name: end
    nullable: true
    type: int64
  - description: Specifies the rate to generate a given number of elements per a given
      number of seconds. Applicable only to unbounded sequences.
    name: rate
    nullable: true
    type: Row(elements=<class 'int64'>, seconds=typing.Optional[int64])
  - description: The minimum number to generate (inclusive).
    name: start
    nullable: false
    type: int64
  identifier: beam:schematransform:org.apache.beam:generate_sequence:v1
  name: GenerateSequence
- default_service: sdks:java:io:expansion-service:shadowJar
  description: ''
  destinations:
    python: apache_beam/io
  fields:
  - description: Decompression type to use when reading input files.
    name: compression
    nullable: false
    type: str
  - description: This option specifies whether and where to output unwritable rows.
    name: error_handling
    nullable: true
    type: Row(output=<class 'str'>)
  - description: Filename or file pattern used to find input files.
    name: file_pattern
    nullable: false
    type: str
  - description: Validate file pattern.
    name: validate
    nullable: false
    type: boolean
  identifier: beam:schematransform:org.apache.beam:tfrecord_read:v1
  name: TfrecordRead
- default_service: sdks:java:io:expansion-service:shadowJar
  description: ''
  destinations:
    python: apache_beam/io
  fields:
  - description: Option to indicate the output sink's compression type. Default is
      NONE.
    name: compression
    nullable: false
    type: str
  - description: This option specifies whether and where to output unwritable rows.
    name: error_handling
    nullable: true
    type: Row(output=<class 'str'>)
  - description: The suffix of each file written, combined with prefix and shardTemplate.
    name: filename_suffix
    nullable: true
    type: str
  - description: Maximum number of writers created in a bundle before spilling to
      shuffle.
    name: max_num_writers_per_bundle
    nullable: true
    type: int32
  - description: Whether to skip the spilling of data caused by having maxNumWritersPerBundle.
    name: no_spilling
    nullable: true
    type: boolean
  - description: The number of shards to use, or 0 for automatic.
    name: num_shards
    nullable: false
    type: int32
  - description: The directory to which files will be written.
    name: output_prefix
    nullable: false
    type: str
  - description: The shard template of each file written, combined with prefix and
      suffix.
    name: shard_template
    nullable: true
    type: str
  identifier: beam:schematransform:org.apache.beam:tfrecord_write:v1
  name: TfrecordWrite