Google Git
Sign in
apache / beam / d8d876144ea74335ebfd2b47030cc3c4f26e4416 / . / sdks / python / apache_beam / runners / dataflow / internal / clients / dataflow / dataflow_v1b3_messages.py
blob: 021f394088a3642f8f0eb17aef4f418c7949d59c [file] [log] [blame]
#
# 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.
#
"""Generated message classes for dataflow version v1b3.
Manages Google Cloud Dataflow projects on Google Cloud Platform.
"""
# NOTE: This file is autogenerated and should not be edited by hand.
from __future__ import absolute_import
from apitools.base.protorpclite import messages as _messages
from apitools.base.py import encoding
from apitools.base.py import extra_types
package = 'dataflow'
class ApproximateProgress(_messages.Message):
r"""Obsolete in favor of ApproximateReportedProgress and
ApproximateSplitRequest.
Fields:
percentComplete: Obsolete.
position: Obsolete.
remainingTime: Obsolete.
"""
percentComplete = _messages.FloatField(1, variant=_messages.Variant.FLOAT)
position = _messages.MessageField('Position', 2)
remainingTime = _messages.StringField(3)
class ApproximateReportedProgress(_messages.Message):
r"""A progress measurement of a WorkItem by a worker.
Fields:
consumedParallelism: Total amount of parallelism in the portion of input
of this task that has already been consumed and is no longer active. In
the first two examples above (see remaining_parallelism), the value
should be 29 or 2 respectively. The sum of remaining_parallelism and
consumed_parallelism should equal the total amount of parallelism in
this work item. If specified, must be finite.
fractionConsumed: Completion as fraction of the input consumed, from 0.0
(beginning, nothing consumed), to 1.0 (end of the input, entire input
consumed).
position: A Position within the work to represent a progress.
remainingParallelism: Total amount of parallelism in the input of this
task that remains, (i.e. can be delegated to this task and any new tasks
via dynamic splitting). Always at least 1 for non-finished work items
and 0 for finished. "Amount of parallelism" refers to how many non-
empty parts of the input can be read in parallel. This does not
necessarily equal number of records. An input that can be read in
parallel down to the individual records is called "perfectly
splittable". An example of non-perfectly parallelizable input is a
block-compressed file format where a block of records has to be read as
a whole, but different blocks can be read in parallel. Examples: * If
we are processing record #30 (starting at 1) out of 50 in a perfectly
splittable 50-record input, this value should be 21 (20 remaining + 1
current). * If we are reading through block 3 in a block-compressed file
consisting of 5 blocks, this value should be 3 (since blocks 4 and 5
can be processed in parallel by new tasks via dynamic splitting and
the current task remains processing block 3). * If we are reading
through the last block in a block-compressed file, or reading or
processing the last record in a perfectly splittable input, this value
should be 1, because apart from the current task, no additional
remainder can be split off.
"""
consumedParallelism = _messages.MessageField('ReportedParallelism', 1)
fractionConsumed = _messages.FloatField(2)
position = _messages.MessageField('Position', 3)
remainingParallelism = _messages.MessageField('ReportedParallelism', 4)
class ApproximateSplitRequest(_messages.Message):
r"""A suggestion by the service to the worker to dynamically split the
WorkItem.
Fields:
fractionConsumed: A fraction at which to split the work item, from 0.0
(beginning of the input) to 1.0 (end of the input).
fractionOfRemainder: The fraction of the remainder of work to split the
work item at, from 0.0 (split at the current position) to 1.0 (end of
the input).
position: A Position at which to split the work item.
"""
fractionConsumed = _messages.FloatField(1)
fractionOfRemainder = _messages.FloatField(2)
position = _messages.MessageField('Position', 3)
class AutoscalingEvent(_messages.Message):
r"""A structured message reporting an autoscaling decision made by the
Dataflow service.
Enums:
EventTypeValueValuesEnum: The type of autoscaling event to report.
Fields:
currentNumWorkers: The current number of workers the job has.
description: A message describing why the system decided to adjust the
current number of workers, why it failed, or why the system decided to
not make any changes to the number of workers.
eventType: The type of autoscaling event to report.
targetNumWorkers: The target number of workers the worker pool wants to
resize to use.
time: The time this event was emitted to indicate a new target or current
num_workers value.
workerPool: A short and friendly name for the worker pool this event
refers to, populated from the value of
PoolStageRelation::user_pool_name.
"""
class EventTypeValueValuesEnum(_messages.Enum):
r"""The type of autoscaling event to report.
Values:
TYPE_UNKNOWN: Default type for the enum. Value should never be
returned.
TARGET_NUM_WORKERS_CHANGED: The TARGET_NUM_WORKERS_CHANGED type should
be used when the target worker pool size has changed at the start of
an actuation. An event should always be specified as
TARGET_NUM_WORKERS_CHANGED if it reflects a change in the
target_num_workers.
CURRENT_NUM_WORKERS_CHANGED: The CURRENT_NUM_WORKERS_CHANGED type should
be used when actual worker pool size has been changed, but the
target_num_workers has not changed.
ACTUATION_FAILURE: The ACTUATION_FAILURE type should be used when we
want to report an error to the user indicating why the current number
of workers in the pool could not be changed. Displayed in the current
status and history widgets.
NO_CHANGE: Used when we want to report to the user a reason why we are
not currently adjusting the number of workers. Should specify both
target_num_workers, current_num_workers and a decision_message.
"""
TYPE_UNKNOWN = 0
TARGET_NUM_WORKERS_CHANGED = 1
CURRENT_NUM_WORKERS_CHANGED = 2
ACTUATION_FAILURE = 3
NO_CHANGE = 4
currentNumWorkers = _messages.IntegerField(1)
description = _messages.MessageField('StructuredMessage', 2)
eventType = _messages.EnumField('EventTypeValueValuesEnum', 3)
targetNumWorkers = _messages.IntegerField(4)
time = _messages.StringField(5)
workerPool = _messages.StringField(6)
class AutoscalingSettings(_messages.Message):
r"""Settings for WorkerPool autoscaling.
Enums:
AlgorithmValueValuesEnum: The algorithm to use for autoscaling.
Fields:
algorithm: The algorithm to use for autoscaling.
maxNumWorkers: The maximum number of workers to cap scaling at.
"""
class AlgorithmValueValuesEnum(_messages.Enum):
r"""The algorithm to use for autoscaling.
Values:
AUTOSCALING_ALGORITHM_UNKNOWN: The algorithm is unknown, or unspecified.
AUTOSCALING_ALGORITHM_NONE: Disable autoscaling.
AUTOSCALING_ALGORITHM_BASIC: Increase worker count over time to reduce
job execution time.
"""
AUTOSCALING_ALGORITHM_UNKNOWN = 0
AUTOSCALING_ALGORITHM_NONE = 1
AUTOSCALING_ALGORITHM_BASIC = 2
algorithm = _messages.EnumField('AlgorithmValueValuesEnum', 1)
maxNumWorkers = _messages.IntegerField(2, variant=_messages.Variant.INT32)
class BigQueryIODetails(_messages.Message):
r"""Metadata for a BigQuery connector used by the job.
Fields:
dataset: Dataset accessed in the connection.
projectId: Project accessed in the connection.
query: Query used to access data in the connection.
table: Table accessed in the connection.
"""
dataset = _messages.StringField(1)
projectId = _messages.StringField(2)
query = _messages.StringField(3)
table = _messages.StringField(4)
class BigTableIODetails(_messages.Message):
r"""Metadata for a BigTable connector used by the job.
Fields:
instanceId: InstanceId accessed in the connection.
projectId: ProjectId accessed in the connection.
tableId: TableId accessed in the connection.
"""
instanceId = _messages.StringField(1)
projectId = _messages.StringField(2)
tableId = _messages.StringField(3)
class CPUTime(_messages.Message):
r"""Modeled after information exposed by /proc/stat.
Fields:
rate: Average CPU utilization rate (% non-idle cpu / second) since
previous sample.
timestamp: Timestamp of the measurement.
totalMs: Total active CPU time across all cores (ie., non-idle) in
milliseconds since start-up.
"""
rate = _messages.FloatField(1)
timestamp = _messages.StringField(2)
totalMs = _messages.IntegerField(3, variant=_messages.Variant.UINT64)
class ComponentSource(_messages.Message):
r"""Description of an interstitial value between transforms in an execution
stage.
Fields:
name: Dataflow service generated name for this source.
originalTransformOrCollection: User name for the original user transform
or collection with which this source is most closely associated.
userName: Human-readable name for this transform; may be user or system
generated.
"""
name = _messages.StringField(1)
originalTransformOrCollection = _messages.StringField(2)
userName = _messages.StringField(3)
class ComponentTransform(_messages.Message):
r"""Description of a transform executed as part of an execution stage.
Fields:
name: Dataflow service generated name for this source.
originalTransform: User name for the original user transform with which
this transform is most closely associated.
userName: Human-readable name for this transform; may be user or system
generated.
"""
name = _messages.StringField(1)
originalTransform = _messages.StringField(2)
userName = _messages.StringField(3)
class ComputationTopology(_messages.Message):
r"""All configuration data for a particular Computation.
Fields:
computationId: The ID of the computation.
inputs: The inputs to the computation.
keyRanges: The key ranges processed by the computation.
outputs: The outputs from the computation.
stateFamilies: The state family values.
systemStageName: The system stage name.
"""
computationId = _messages.StringField(1)
inputs = _messages.MessageField('StreamLocation', 2, repeated=True)
keyRanges = _messages.MessageField('KeyRangeLocation', 3, repeated=True)
outputs = _messages.MessageField('StreamLocation', 4, repeated=True)
stateFamilies = _messages.MessageField('StateFamilyConfig', 5, repeated=True)
systemStageName = _messages.StringField(6)
class ConcatPosition(_messages.Message):
r"""A position that encapsulates an inner position and an index for the
inner position. A ConcatPosition can be used by a reader of a source that
encapsulates a set of other sources.
Fields:
index: Index of the inner source.
position: Position within the inner source.
"""
index = _messages.IntegerField(1, variant=_messages.Variant.INT32)
position = _messages.MessageField('Position', 2)
class CounterMetadata(_messages.Message):
r"""CounterMetadata includes all static non-name non-value counter
attributes.
Enums:
KindValueValuesEnum: Counter aggregation kind.
StandardUnitsValueValuesEnum: System defined Units, see above enum.
Fields:
description: Human-readable description of the counter semantics.
kind: Counter aggregation kind.
otherUnits: A string referring to the unit type.
standardUnits: System defined Units, see above enum.
"""
class KindValueValuesEnum(_messages.Enum):
r"""Counter aggregation kind.
Values:
INVALID: Counter aggregation kind was not set.
SUM: Aggregated value is the sum of all contributed values.
MAX: Aggregated value is the max of all contributed values.
MIN: Aggregated value is the min of all contributed values.
MEAN: Aggregated value is the mean of all contributed values.
OR: Aggregated value represents the logical 'or' of all contributed
values.
AND: Aggregated value represents the logical 'and' of all contributed
values.
SET: Aggregated value is a set of unique contributed values.
DISTRIBUTION: Aggregated value captures statistics about a distribution.
LATEST_VALUE: Aggregated value tracks the latest value of a variable.
"""
INVALID = 0
SUM = 1
MAX = 2
MIN = 3
MEAN = 4
OR = 5
AND = 6
SET = 7
DISTRIBUTION = 8
LATEST_VALUE = 9
class StandardUnitsValueValuesEnum(_messages.Enum):
r"""System defined Units, see above enum.
Values:
BYTES: Counter returns a value in bytes.
BYTES_PER_SEC: Counter returns a value in bytes per second.
MILLISECONDS: Counter returns a value in milliseconds.
MICROSECONDS: Counter returns a value in microseconds.
NANOSECONDS: Counter returns a value in nanoseconds.
TIMESTAMP_MSEC: Counter returns a timestamp in milliseconds.
TIMESTAMP_USEC: Counter returns a timestamp in microseconds.
TIMESTAMP_NSEC: Counter returns a timestamp in nanoseconds.
"""
BYTES = 0
BYTES_PER_SEC = 1
MILLISECONDS = 2
MICROSECONDS = 3
NANOSECONDS = 4
TIMESTAMP_MSEC = 5
TIMESTAMP_USEC = 6
TIMESTAMP_NSEC = 7
description = _messages.StringField(1)
kind = _messages.EnumField('KindValueValuesEnum', 2)
otherUnits = _messages.StringField(3)
standardUnits = _messages.EnumField('StandardUnitsValueValuesEnum', 4)
class CounterStructuredName(_messages.Message):
r"""Identifies a counter within a per-job namespace. Counters whose
structured names are the same get merged into a single value for the job.
Enums:
OriginValueValuesEnum: One of the standard Origins defined above.
PortionValueValuesEnum: Portion of this counter, either key or value.
Fields:
componentStepName: Name of the optimized step being executed by the
workers.
executionStepName: Name of the stage. An execution step contains multiple
component steps.
inputIndex: Index of an input collection that's being read from/written to
as a side input. The index identifies a step's side inputs starting by 1
(e.g. the first side input has input_index 1, the third has input_index
3). Side inputs are identified by a pair of (original_step_name,
input_index). This field helps uniquely identify them.
name: Counter name. Not necessarily globally-unique, but unique within the
context of the other fields. Required.
origin: One of the standard Origins defined above.
originNamespace: A string containing a more specific namespace of the
counter's origin.
originalRequestingStepName: The step name requesting an operation, such as
GBK. I.e. the ParDo causing a read/write from shuffle to occur, or a
read from side inputs.
originalStepName: System generated name of the original step in the user's
graph, before optimization.
portion: Portion of this counter, either key or value.
workerId: ID of a particular worker.
"""
class OriginValueValuesEnum(_messages.Enum):
r"""One of the standard Origins defined above.
Values:
SYSTEM: Counter was created by the Dataflow system.
USER: Counter was created by the user.
"""
SYSTEM = 0
USER = 1
class PortionValueValuesEnum(_messages.Enum):
r"""Portion of this counter, either key or value.
Values:
ALL: Counter portion has not been set.
KEY: Counter reports a key.
VALUE: Counter reports a value.
"""
ALL = 0
KEY = 1
VALUE = 2
componentStepName = _messages.StringField(1)
executionStepName = _messages.StringField(2)
inputIndex = _messages.IntegerField(3, variant=_messages.Variant.INT32)
name = _messages.StringField(4)
origin = _messages.EnumField('OriginValueValuesEnum', 5)
originNamespace = _messages.StringField(6)
originalRequestingStepName = _messages.StringField(7)
originalStepName = _messages.StringField(8)
portion = _messages.EnumField('PortionValueValuesEnum', 9)
workerId = _messages.StringField(10)
class CounterStructuredNameAndMetadata(_messages.Message):
r"""A single message which encapsulates structured name and metadata for a
given counter.
Fields:
metadata: Metadata associated with a counter
name: Structured name of the counter.
"""
metadata = _messages.MessageField('CounterMetadata', 1)
name = _messages.MessageField('CounterStructuredName', 2)
class CounterUpdate(_messages.Message):
r"""An update to a Counter sent from a worker.
Fields:
boolean: Boolean value for And, Or.
cumulative: True if this counter is reported as the total cumulative
aggregate value accumulated since the worker started working on this
WorkItem. By default this is false, indicating that this counter is
reported as a delta.
distribution: Distribution data
floatingPoint: Floating point value for Sum, Max, Min.
floatingPointList: List of floating point numbers, for Set.
floatingPointMean: Floating point mean aggregation value for Mean.
integer: Integer value for Sum, Max, Min.
integerGauge: Gauge data
integerList: List of integers, for Set.
integerMean: Integer mean aggregation value for Mean.
internal: Value for internally-defined counters used by the Dataflow
service.
nameAndKind: Counter name and aggregation type.
shortId: The service-generated short identifier for this counter. The
short_id -> (name, metadata) mapping is constant for the lifetime of a
job.
stringList: List of strings, for Set.
structuredNameAndMetadata: Counter structured name and metadata.
"""
boolean = _messages.BooleanField(1)
cumulative = _messages.BooleanField(2)
distribution = _messages.MessageField('DistributionUpdate', 3)
floatingPoint = _messages.FloatField(4)
floatingPointList = _messages.MessageField('FloatingPointList', 5)
floatingPointMean = _messages.MessageField('FloatingPointMean', 6)
integer = _messages.MessageField('SplitInt64', 7)
integerGauge = _messages.MessageField('IntegerGauge', 8)
integerList = _messages.MessageField('IntegerList', 9)
integerMean = _messages.MessageField('IntegerMean', 10)
internal = _messages.MessageField('extra_types.JsonValue', 11)
nameAndKind = _messages.MessageField('NameAndKind', 12)
shortId = _messages.IntegerField(13)
stringList = _messages.MessageField('StringList', 14)
structuredNameAndMetadata = _messages.MessageField('CounterStructuredNameAndMetadata', 15)
class CreateJobFromTemplateRequest(_messages.Message):
r"""A request to create a Cloud Dataflow job from a template.
Messages:
ParametersValue: The runtime parameters to pass to the job.
Fields:
environment: The runtime environment for the job.
gcsPath: Required. A Cloud Storage path to the template from which to
create the job. Must be a valid Cloud Storage URL, beginning with
`gs://`.
jobName: Required. The job name to use for the created job.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) to
which to direct the request.
parameters: The runtime parameters to pass to the job.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class ParametersValue(_messages.Message):
r"""The runtime parameters to pass to the job.
Messages:
AdditionalProperty: An additional property for a ParametersValue object.
Fields:
additionalProperties: Additional properties of type ParametersValue
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a ParametersValue object.
Fields:
key: Name of the additional property.
value: A string attribute.
"""
key = _messages.StringField(1)
value = _messages.StringField(2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
environment = _messages.MessageField('RuntimeEnvironment', 1)
gcsPath = _messages.StringField(2)
jobName = _messages.StringField(3)
location = _messages.StringField(4)
parameters = _messages.MessageField('ParametersValue', 5)
class CustomSourceLocation(_messages.Message):
r"""Identifies the location of a custom souce.
Fields:
stateful: Whether this source is stateful.
"""
stateful = _messages.BooleanField(1)
class DataDiskAssignment(_messages.Message):
r"""Data disk assignment for a given VM instance.
Fields:
dataDisks: Mounted data disks. The order is important a data disk's
0-based index in this list defines which persistent directory the disk
is mounted to, for example the list of {
"myproject-1014-104817-4c2-harness-0-disk-0" }, {
"myproject-1014-104817-4c2-harness-0-disk-1" }.
vmInstance: VM instance name the data disks mounted to, for example
"myproject-1014-104817-4c2-harness-0".
"""
dataDisks = _messages.StringField(1, repeated=True)
vmInstance = _messages.StringField(2)
class DataflowProjectsDeleteSnapshotsRequest(_messages.Message):
r"""A DataflowProjectsDeleteSnapshotsRequest object.
Fields:
location: The location that contains this snapshot.
projectId: The ID of the Cloud Platform project that the snapshot belongs
to.
snapshotId: The ID of the snapshot.
"""
location = _messages.StringField(1)
projectId = _messages.StringField(2, required=True)
snapshotId = _messages.StringField(3)
class DataflowProjectsJobsAggregatedRequest(_messages.Message):
r"""A DataflowProjectsJobsAggregatedRequest object.
Enums:
FilterValueValuesEnum: The kind of filter to use.
ViewValueValuesEnum: Level of information requested in response. Default
is `JOB_VIEW_SUMMARY`.
Fields:
filter: The kind of filter to use.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains this job.
pageSize: If there are many jobs, limit response to at most this many. The
actual number of jobs returned will be the lesser of max_responses and
an unspecified server-defined limit.
pageToken: Set this to the 'next_page_token' field of a previous response
to request additional results in a long list.
projectId: The project which owns the jobs.
view: Level of information requested in response. Default is
`JOB_VIEW_SUMMARY`.
"""
class FilterValueValuesEnum(_messages.Enum):
r"""The kind of filter to use.
Values:
UNKNOWN: <no description>
ALL: <no description>
TERMINATED: <no description>
ACTIVE: <no description>
"""
UNKNOWN = 0
ALL = 1
TERMINATED = 2
ACTIVE = 3
class ViewValueValuesEnum(_messages.Enum):
r"""Level of information requested in response. Default is
`JOB_VIEW_SUMMARY`.
Values:
JOB_VIEW_UNKNOWN: <no description>
JOB_VIEW_SUMMARY: <no description>
JOB_VIEW_ALL: <no description>
JOB_VIEW_DESCRIPTION: <no description>
"""
JOB_VIEW_UNKNOWN = 0
JOB_VIEW_SUMMARY = 1
JOB_VIEW_ALL = 2
JOB_VIEW_DESCRIPTION = 3
filter = _messages.EnumField('FilterValueValuesEnum', 1)
location = _messages.StringField(2)
pageSize = _messages.IntegerField(3, variant=_messages.Variant.INT32)
pageToken = _messages.StringField(4)
projectId = _messages.StringField(5, required=True)
view = _messages.EnumField('ViewValueValuesEnum', 6)
class DataflowProjectsJobsCreateRequest(_messages.Message):
r"""A DataflowProjectsJobsCreateRequest object.
Enums:
ViewValueValuesEnum: The level of information requested in response.
Fields:
job: A Job resource to be passed as the request body.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains this job.
projectId: The ID of the Cloud Platform project that the job belongs to.
replaceJobId: Deprecated. This field is now in the Job message.
view: The level of information requested in response.
"""
class ViewValueValuesEnum(_messages.Enum):
r"""The level of information requested in response.
Values:
JOB_VIEW_UNKNOWN: <no description>
JOB_VIEW_SUMMARY: <no description>
JOB_VIEW_ALL: <no description>
JOB_VIEW_DESCRIPTION: <no description>
"""
JOB_VIEW_UNKNOWN = 0
JOB_VIEW_SUMMARY = 1
JOB_VIEW_ALL = 2
JOB_VIEW_DESCRIPTION = 3
job = _messages.MessageField('Job', 1)
location = _messages.StringField(2)
projectId = _messages.StringField(3, required=True)
replaceJobId = _messages.StringField(4)
view = _messages.EnumField('ViewValueValuesEnum', 5)
class DataflowProjectsJobsDebugGetConfigRequest(_messages.Message):
r"""A DataflowProjectsJobsDebugGetConfigRequest object.
Fields:
getDebugConfigRequest: A GetDebugConfigRequest resource to be passed as
the request body.
jobId: The job id.
projectId: The project id.
"""
getDebugConfigRequest = _messages.MessageField('GetDebugConfigRequest', 1)
jobId = _messages.StringField(2, required=True)
projectId = _messages.StringField(3, required=True)
class DataflowProjectsJobsDebugSendCaptureRequest(_messages.Message):
r"""A DataflowProjectsJobsDebugSendCaptureRequest object.
Fields:
jobId: The job id.
projectId: The project id.
sendDebugCaptureRequest: A SendDebugCaptureRequest resource to be passed
as the request body.
"""
jobId = _messages.StringField(1, required=True)
projectId = _messages.StringField(2, required=True)
sendDebugCaptureRequest = _messages.MessageField('SendDebugCaptureRequest', 3)
class DataflowProjectsJobsGetMetricsRequest(_messages.Message):
r"""A DataflowProjectsJobsGetMetricsRequest object.
Fields:
jobId: The job to get messages for.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains the job specified by job_id.
projectId: A project id.
startTime: Return only metric data that has changed since this time.
Default is to return all information about all metrics for the job.
"""
jobId = _messages.StringField(1, required=True)
location = _messages.StringField(2)
projectId = _messages.StringField(3, required=True)
startTime = _messages.StringField(4)
class DataflowProjectsJobsGetRequest(_messages.Message):
r"""A DataflowProjectsJobsGetRequest object.
Enums:
ViewValueValuesEnum: The level of information requested in response.
Fields:
jobId: The job ID.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains this job.
projectId: The ID of the Cloud Platform project that the job belongs to.
view: The level of information requested in response.
"""
class ViewValueValuesEnum(_messages.Enum):
r"""The level of information requested in response.
Values:
JOB_VIEW_UNKNOWN: <no description>
JOB_VIEW_SUMMARY: <no description>
JOB_VIEW_ALL: <no description>
JOB_VIEW_DESCRIPTION: <no description>
"""
JOB_VIEW_UNKNOWN = 0
JOB_VIEW_SUMMARY = 1
JOB_VIEW_ALL = 2
JOB_VIEW_DESCRIPTION = 3
jobId = _messages.StringField(1, required=True)
location = _messages.StringField(2)
projectId = _messages.StringField(3, required=True)
view = _messages.EnumField('ViewValueValuesEnum', 4)
class DataflowProjectsJobsListRequest(_messages.Message):
r"""A DataflowProjectsJobsListRequest object.
Enums:
FilterValueValuesEnum: The kind of filter to use.
ViewValueValuesEnum: Level of information requested in response. Default
is `JOB_VIEW_SUMMARY`.
Fields:
filter: The kind of filter to use.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains this job.
pageSize: If there are many jobs, limit response to at most this many. The
actual number of jobs returned will be the lesser of max_responses and
an unspecified server-defined limit.
pageToken: Set this to the 'next_page_token' field of a previous response
to request additional results in a long list.
projectId: The project which owns the jobs.
view: Level of information requested in response. Default is
`JOB_VIEW_SUMMARY`.
"""
class FilterValueValuesEnum(_messages.Enum):
r"""The kind of filter to use.
Values:
UNKNOWN: <no description>
ALL: <no description>
TERMINATED: <no description>
ACTIVE: <no description>
"""
UNKNOWN = 0
ALL = 1
TERMINATED = 2
ACTIVE = 3
class ViewValueValuesEnum(_messages.Enum):
r"""Level of information requested in response. Default is
`JOB_VIEW_SUMMARY`.
Values:
JOB_VIEW_UNKNOWN: <no description>
JOB_VIEW_SUMMARY: <no description>
JOB_VIEW_ALL: <no description>
JOB_VIEW_DESCRIPTION: <no description>
"""
JOB_VIEW_UNKNOWN = 0
JOB_VIEW_SUMMARY = 1
JOB_VIEW_ALL = 2
JOB_VIEW_DESCRIPTION = 3
filter = _messages.EnumField('FilterValueValuesEnum', 1)
location = _messages.StringField(2)
pageSize = _messages.IntegerField(3, variant=_messages.Variant.INT32)
pageToken = _messages.StringField(4)
projectId = _messages.StringField(5, required=True)
view = _messages.EnumField('ViewValueValuesEnum', 6)
class DataflowProjectsJobsMessagesListRequest(_messages.Message):
r"""A DataflowProjectsJobsMessagesListRequest object.
Enums:
MinimumImportanceValueValuesEnum: Filter to only get messages with
importance >= level
Fields:
endTime: Return only messages with timestamps < end_time. The default is
now (i.e. return up to the latest messages available).
jobId: The job to get messages about.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains the job specified by job_id.
minimumImportance: Filter to only get messages with importance >= level
pageSize: If specified, determines the maximum number of messages to
return. If unspecified, the service may choose an appropriate default,
or may return an arbitrarily large number of results.
pageToken: If supplied, this should be the value of next_page_token
returned by an earlier call. This will cause the next page of results to
be returned.
projectId: A project id.
startTime: If specified, return only messages with timestamps >=
start_time. The default is the job creation time (i.e. beginning of
messages).
"""
class MinimumImportanceValueValuesEnum(_messages.Enum):
r"""Filter to only get messages with importance >= level
Values:
JOB_MESSAGE_IMPORTANCE_UNKNOWN: <no description>
JOB_MESSAGE_DEBUG: <no description>
JOB_MESSAGE_DETAILED: <no description>
JOB_MESSAGE_BASIC: <no description>
JOB_MESSAGE_WARNING: <no description>
JOB_MESSAGE_ERROR: <no description>
"""
JOB_MESSAGE_IMPORTANCE_UNKNOWN = 0
JOB_MESSAGE_DEBUG = 1
JOB_MESSAGE_DETAILED = 2
JOB_MESSAGE_BASIC = 3
JOB_MESSAGE_WARNING = 4
JOB_MESSAGE_ERROR = 5
endTime = _messages.StringField(1)
jobId = _messages.StringField(2, required=True)
location = _messages.StringField(3)
minimumImportance = _messages.EnumField('MinimumImportanceValueValuesEnum', 4)
pageSize = _messages.IntegerField(5, variant=_messages.Variant.INT32)
pageToken = _messages.StringField(6)
projectId = _messages.StringField(7, required=True)
startTime = _messages.StringField(8)
class DataflowProjectsJobsSnapshotRequest(_messages.Message):
r"""A DataflowProjectsJobsSnapshotRequest object.
Fields:
jobId: The job to be snapshotted.
projectId: The project which owns the job to be snapshotted.
snapshotJobRequest: A SnapshotJobRequest resource to be passed as the
request body.
"""
jobId = _messages.StringField(1, required=True)
projectId = _messages.StringField(2, required=True)
snapshotJobRequest = _messages.MessageField('SnapshotJobRequest', 3)
class DataflowProjectsJobsUpdateRequest(_messages.Message):
r"""A DataflowProjectsJobsUpdateRequest object.
Fields:
job: A Job resource to be passed as the request body.
jobId: The job ID.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains this job.
projectId: The ID of the Cloud Platform project that the job belongs to.
"""
job = _messages.MessageField('Job', 1)
jobId = _messages.StringField(2, required=True)
location = _messages.StringField(3)
projectId = _messages.StringField(4, required=True)
class DataflowProjectsJobsWorkItemsLeaseRequest(_messages.Message):
r"""A DataflowProjectsJobsWorkItemsLeaseRequest object.
Fields:
jobId: Identifies the workflow job this worker belongs to.
leaseWorkItemRequest: A LeaseWorkItemRequest resource to be passed as the
request body.
projectId: Identifies the project this worker belongs to.
"""
jobId = _messages.StringField(1, required=True)
leaseWorkItemRequest = _messages.MessageField('LeaseWorkItemRequest', 2)
projectId = _messages.StringField(3, required=True)
class DataflowProjectsJobsWorkItemsReportStatusRequest(_messages.Message):
r"""A DataflowProjectsJobsWorkItemsReportStatusRequest object.
Fields:
jobId: The job which the WorkItem is part of.
projectId: The project which owns the WorkItem's job.
reportWorkItemStatusRequest: A ReportWorkItemStatusRequest resource to be
passed as the request body.
"""
jobId = _messages.StringField(1, required=True)
projectId = _messages.StringField(2, required=True)
reportWorkItemStatusRequest = _messages.MessageField('ReportWorkItemStatusRequest', 3)
class DataflowProjectsLocationsJobsCreateRequest(_messages.Message):
r"""A DataflowProjectsLocationsJobsCreateRequest object.
Enums:
ViewValueValuesEnum: The level of information requested in response.
Fields:
job: A Job resource to be passed as the request body.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains this job.
projectId: The ID of the Cloud Platform project that the job belongs to.
replaceJobId: Deprecated. This field is now in the Job message.
view: The level of information requested in response.
"""
class ViewValueValuesEnum(_messages.Enum):
r"""The level of information requested in response.
Values:
JOB_VIEW_UNKNOWN: <no description>
JOB_VIEW_SUMMARY: <no description>
JOB_VIEW_ALL: <no description>
JOB_VIEW_DESCRIPTION: <no description>
"""
JOB_VIEW_UNKNOWN = 0
JOB_VIEW_SUMMARY = 1
JOB_VIEW_ALL = 2
JOB_VIEW_DESCRIPTION = 3
job = _messages.MessageField('Job', 1)
location = _messages.StringField(2, required=True)
projectId = _messages.StringField(3, required=True)
replaceJobId = _messages.StringField(4)
view = _messages.EnumField('ViewValueValuesEnum', 5)
class DataflowProjectsLocationsJobsDebugGetConfigRequest(_messages.Message):
r"""A DataflowProjectsLocationsJobsDebugGetConfigRequest object.
Fields:
getDebugConfigRequest: A GetDebugConfigRequest resource to be passed as
the request body.
jobId: The job id.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains the job specified by job_id.
projectId: The project id.
"""
getDebugConfigRequest = _messages.MessageField('GetDebugConfigRequest', 1)
jobId = _messages.StringField(2, required=True)
location = _messages.StringField(3, required=True)
projectId = _messages.StringField(4, required=True)
class DataflowProjectsLocationsJobsDebugSendCaptureRequest(_messages.Message):
r"""A DataflowProjectsLocationsJobsDebugSendCaptureRequest object.
Fields:
jobId: The job id.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains the job specified by job_id.
projectId: The project id.
sendDebugCaptureRequest: A SendDebugCaptureRequest resource to be passed
as the request body.
"""
jobId = _messages.StringField(1, required=True)
location = _messages.StringField(2, required=True)
projectId = _messages.StringField(3, required=True)
sendDebugCaptureRequest = _messages.MessageField('SendDebugCaptureRequest', 4)
class DataflowProjectsLocationsJobsGetMetricsRequest(_messages.Message):
r"""A DataflowProjectsLocationsJobsGetMetricsRequest object.
Fields:
jobId: The job to get messages for.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains the job specified by job_id.
projectId: A project id.
startTime: Return only metric data that has changed since this time.
Default is to return all information about all metrics for the job.
"""
jobId = _messages.StringField(1, required=True)
location = _messages.StringField(2, required=True)
projectId = _messages.StringField(3, required=True)
startTime = _messages.StringField(4)
class DataflowProjectsLocationsJobsGetRequest(_messages.Message):
r"""A DataflowProjectsLocationsJobsGetRequest object.
Enums:
ViewValueValuesEnum: The level of information requested in response.
Fields:
jobId: The job ID.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains this job.
projectId: The ID of the Cloud Platform project that the job belongs to.
view: The level of information requested in response.
"""
class ViewValueValuesEnum(_messages.Enum):
r"""The level of information requested in response.
Values:
JOB_VIEW_UNKNOWN: <no description>
JOB_VIEW_SUMMARY: <no description>
JOB_VIEW_ALL: <no description>
JOB_VIEW_DESCRIPTION: <no description>
"""
JOB_VIEW_UNKNOWN = 0
JOB_VIEW_SUMMARY = 1
JOB_VIEW_ALL = 2
JOB_VIEW_DESCRIPTION = 3
jobId = _messages.StringField(1, required=True)
location = _messages.StringField(2, required=True)
projectId = _messages.StringField(3, required=True)
view = _messages.EnumField('ViewValueValuesEnum', 4)
class DataflowProjectsLocationsJobsListRequest(_messages.Message):
r"""A DataflowProjectsLocationsJobsListRequest object.
Enums:
FilterValueValuesEnum: The kind of filter to use.
ViewValueValuesEnum: Level of information requested in response. Default
is `JOB_VIEW_SUMMARY`.
Fields:
filter: The kind of filter to use.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains this job.
pageSize: If there are many jobs, limit response to at most this many. The
actual number of jobs returned will be the lesser of max_responses and
an unspecified server-defined limit.
pageToken: Set this to the 'next_page_token' field of a previous response
to request additional results in a long list.
projectId: The project which owns the jobs.
view: Level of information requested in response. Default is
`JOB_VIEW_SUMMARY`.
"""
class FilterValueValuesEnum(_messages.Enum):
r"""The kind of filter to use.
Values:
UNKNOWN: <no description>
ALL: <no description>
TERMINATED: <no description>
ACTIVE: <no description>
"""
UNKNOWN = 0
ALL = 1
TERMINATED = 2
ACTIVE = 3
class ViewValueValuesEnum(_messages.Enum):
r"""Level of information requested in response. Default is
`JOB_VIEW_SUMMARY`.
Values:
JOB_VIEW_UNKNOWN: <no description>
JOB_VIEW_SUMMARY: <no description>
JOB_VIEW_ALL: <no description>
JOB_VIEW_DESCRIPTION: <no description>
"""
JOB_VIEW_UNKNOWN = 0
JOB_VIEW_SUMMARY = 1
JOB_VIEW_ALL = 2
JOB_VIEW_DESCRIPTION = 3
filter = _messages.EnumField('FilterValueValuesEnum', 1)
location = _messages.StringField(2, required=True)
pageSize = _messages.IntegerField(3, variant=_messages.Variant.INT32)
pageToken = _messages.StringField(4)
projectId = _messages.StringField(5, required=True)
view = _messages.EnumField('ViewValueValuesEnum', 6)
class DataflowProjectsLocationsJobsMessagesListRequest(_messages.Message):
r"""A DataflowProjectsLocationsJobsMessagesListRequest object.
Enums:
MinimumImportanceValueValuesEnum: Filter to only get messages with
importance >= level
Fields:
endTime: Return only messages with timestamps < end_time. The default is
now (i.e. return up to the latest messages available).
jobId: The job to get messages about.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains the job specified by job_id.
minimumImportance: Filter to only get messages with importance >= level
pageSize: If specified, determines the maximum number of messages to
return. If unspecified, the service may choose an appropriate default,
or may return an arbitrarily large number of results.
pageToken: If supplied, this should be the value of next_page_token
returned by an earlier call. This will cause the next page of results to
be returned.
projectId: A project id.
startTime: If specified, return only messages with timestamps >=
start_time. The default is the job creation time (i.e. beginning of
messages).
"""
class MinimumImportanceValueValuesEnum(_messages.Enum):
r"""Filter to only get messages with importance >= level
Values:
JOB_MESSAGE_IMPORTANCE_UNKNOWN: <no description>
JOB_MESSAGE_DEBUG: <no description>
JOB_MESSAGE_DETAILED: <no description>
JOB_MESSAGE_BASIC: <no description>
JOB_MESSAGE_WARNING: <no description>
JOB_MESSAGE_ERROR: <no description>
"""
JOB_MESSAGE_IMPORTANCE_UNKNOWN = 0
JOB_MESSAGE_DEBUG = 1
JOB_MESSAGE_DETAILED = 2
JOB_MESSAGE_BASIC = 3
JOB_MESSAGE_WARNING = 4
JOB_MESSAGE_ERROR = 5
endTime = _messages.StringField(1)
jobId = _messages.StringField(2, required=True)
location = _messages.StringField(3, required=True)
minimumImportance = _messages.EnumField('MinimumImportanceValueValuesEnum', 4)
pageSize = _messages.IntegerField(5, variant=_messages.Variant.INT32)
pageToken = _messages.StringField(6)
projectId = _messages.StringField(7, required=True)
startTime = _messages.StringField(8)
class DataflowProjectsLocationsJobsSnapshotRequest(_messages.Message):
r"""A DataflowProjectsLocationsJobsSnapshotRequest object.
Fields:
jobId: The job to be snapshotted.
location: The location that contains this job.
projectId: The project which owns the job to be snapshotted.
snapshotJobRequest: A SnapshotJobRequest resource to be passed as the
request body.
"""
jobId = _messages.StringField(1, required=True)
location = _messages.StringField(2, required=True)
projectId = _messages.StringField(3, required=True)
snapshotJobRequest = _messages.MessageField('SnapshotJobRequest', 4)
class DataflowProjectsLocationsJobsUpdateRequest(_messages.Message):
r"""A DataflowProjectsLocationsJobsUpdateRequest object.
Fields:
job: A Job resource to be passed as the request body.
jobId: The job ID.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains this job.
projectId: The ID of the Cloud Platform project that the job belongs to.
"""
job = _messages.MessageField('Job', 1)
jobId = _messages.StringField(2, required=True)
location = _messages.StringField(3, required=True)
projectId = _messages.StringField(4, required=True)
class DataflowProjectsLocationsJobsWorkItemsLeaseRequest(_messages.Message):
r"""A DataflowProjectsLocationsJobsWorkItemsLeaseRequest object.
Fields:
jobId: Identifies the workflow job this worker belongs to.
leaseWorkItemRequest: A LeaseWorkItemRequest resource to be passed as the
request body.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains the WorkItem's job.
projectId: Identifies the project this worker belongs to.
"""
jobId = _messages.StringField(1, required=True)
leaseWorkItemRequest = _messages.MessageField('LeaseWorkItemRequest', 2)
location = _messages.StringField(3, required=True)
projectId = _messages.StringField(4, required=True)
class DataflowProjectsLocationsJobsWorkItemsReportStatusRequest(_messages.Message):
r"""A DataflowProjectsLocationsJobsWorkItemsReportStatusRequest object.
Fields:
jobId: The job which the WorkItem is part of.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains the WorkItem's job.
projectId: The project which owns the WorkItem's job.
reportWorkItemStatusRequest: A ReportWorkItemStatusRequest resource to be
passed as the request body.
"""
jobId = _messages.StringField(1, required=True)
location = _messages.StringField(2, required=True)
projectId = _messages.StringField(3, required=True)
reportWorkItemStatusRequest = _messages.MessageField('ReportWorkItemStatusRequest', 4)
class DataflowProjectsLocationsSnapshotsDeleteRequest(_messages.Message):
r"""A DataflowProjectsLocationsSnapshotsDeleteRequest object.
Fields:
location: The location that contains this snapshot.
projectId: The ID of the Cloud Platform project that the snapshot belongs
to.
snapshotId: The ID of the snapshot.
"""
location = _messages.StringField(1, required=True)
projectId = _messages.StringField(2, required=True)
snapshotId = _messages.StringField(3, required=True)
class DataflowProjectsLocationsSnapshotsGetRequest(_messages.Message):
r"""A DataflowProjectsLocationsSnapshotsGetRequest object.
Fields:
location: The location that contains this snapshot.
projectId: The ID of the Cloud Platform project that the snapshot belongs
to.
snapshotId: The ID of the snapshot.
"""
location = _messages.StringField(1, required=True)
projectId = _messages.StringField(2, required=True)
snapshotId = _messages.StringField(3, required=True)
class DataflowProjectsLocationsSnapshotsListRequest(_messages.Message):
r"""A DataflowProjectsLocationsSnapshotsListRequest object.
Fields:
location: The location to list snapshots in.
projectId: The project ID to list snapshots for.
"""
location = _messages.StringField(1, required=True)
projectId = _messages.StringField(2, required=True)
class DataflowProjectsLocationsSqlValidateRequest(_messages.Message):
r"""A DataflowProjectsLocationsSqlValidateRequest object.
Fields:
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) to
which to direct the request.
projectId: Required. The ID of the Cloud Platform project that the job
belongs to.
query: The sql query to validate.
"""
location = _messages.StringField(1, required=True)
projectId = _messages.StringField(2, required=True)
query = _messages.StringField(3)
class DataflowProjectsLocationsTemplatesCreateRequest(_messages.Message):
r"""A DataflowProjectsLocationsTemplatesCreateRequest object.
Fields:
createJobFromTemplateRequest: A CreateJobFromTemplateRequest resource to
be passed as the request body.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) to
which to direct the request.
projectId: Required. The ID of the Cloud Platform project that the job
belongs to.
"""
createJobFromTemplateRequest = _messages.MessageField('CreateJobFromTemplateRequest', 1)
location = _messages.StringField(2, required=True)
projectId = _messages.StringField(3, required=True)
class DataflowProjectsLocationsTemplatesGetRequest(_messages.Message):
r"""A DataflowProjectsLocationsTemplatesGetRequest object.
Enums:
ViewValueValuesEnum: The view to retrieve. Defaults to METADATA_ONLY.
Fields:
gcsPath: Required. A Cloud Storage path to the template from which to
create the job. Must be valid Cloud Storage URL, beginning with 'gs://'.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) to
which to direct the request.
projectId: Required. The ID of the Cloud Platform project that the job
belongs to.
view: The view to retrieve. Defaults to METADATA_ONLY.
"""
class ViewValueValuesEnum(_messages.Enum):
r"""The view to retrieve. Defaults to METADATA_ONLY.
Values:
METADATA_ONLY: <no description>
"""
METADATA_ONLY = 0
gcsPath = _messages.StringField(1)
location = _messages.StringField(2, required=True)
projectId = _messages.StringField(3, required=True)
view = _messages.EnumField('ViewValueValuesEnum', 4)
class DataflowProjectsLocationsTemplatesLaunchRequest(_messages.Message):
r"""A DataflowProjectsLocationsTemplatesLaunchRequest object.
Fields:
dynamicTemplate_gcsPath: Path to dynamic template spec file on GCS. The
file must be a Json serialized DynamicTemplateFieSpec object.
dynamicTemplate_stagingLocation: Cloud Storage path for staging
dependencies. Must be a valid Cloud Storage URL, beginning with `gs://`.
gcsPath: A Cloud Storage path to the template from which to create the
job. Must be valid Cloud Storage URL, beginning with 'gs://'.
launchTemplateParameters: A LaunchTemplateParameters resource to be passed
as the request body.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) to
which to direct the request.
projectId: Required. The ID of the Cloud Platform project that the job
belongs to.
validateOnly: If true, the request is validated but not actually executed.
Defaults to false.
"""
dynamicTemplate_gcsPath = _messages.StringField(1)
dynamicTemplate_stagingLocation = _messages.StringField(2)
gcsPath = _messages.StringField(3)
launchTemplateParameters = _messages.MessageField('LaunchTemplateParameters', 4)
location = _messages.StringField(5, required=True)
projectId = _messages.StringField(6, required=True)
validateOnly = _messages.BooleanField(7)
class DataflowProjectsLocationsWorkerMessagesRequest(_messages.Message):
r"""A DataflowProjectsLocationsWorkerMessagesRequest object.
Fields:
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains the job.
projectId: The project to send the WorkerMessages to.
sendWorkerMessagesRequest: A SendWorkerMessagesRequest resource to be
passed as the request body.
"""
location = _messages.StringField(1, required=True)
projectId = _messages.StringField(2, required=True)
sendWorkerMessagesRequest = _messages.MessageField('SendWorkerMessagesRequest', 3)
class DataflowProjectsSnapshotsGetRequest(_messages.Message):
r"""A DataflowProjectsSnapshotsGetRequest object.
Fields:
location: The location that contains this snapshot.
projectId: The ID of the Cloud Platform project that the snapshot belongs
to.
snapshotId: The ID of the snapshot.
"""
location = _messages.StringField(1)
projectId = _messages.StringField(2, required=True)
snapshotId = _messages.StringField(3, required=True)
class DataflowProjectsSnapshotsListRequest(_messages.Message):
r"""A DataflowProjectsSnapshotsListRequest object.
Fields:
location: The location to list snapshots in.
projectId: The project ID to list snapshots for.
"""
location = _messages.StringField(1)
projectId = _messages.StringField(2, required=True)
class DataflowProjectsTemplatesCreateRequest(_messages.Message):
r"""A DataflowProjectsTemplatesCreateRequest object.
Fields:
createJobFromTemplateRequest: A CreateJobFromTemplateRequest resource to
be passed as the request body.
projectId: Required. The ID of the Cloud Platform project that the job
belongs to.
"""
createJobFromTemplateRequest = _messages.MessageField('CreateJobFromTemplateRequest', 1)
projectId = _messages.StringField(2, required=True)
class DataflowProjectsTemplatesGetRequest(_messages.Message):
r"""A DataflowProjectsTemplatesGetRequest object.
Enums:
ViewValueValuesEnum: The view to retrieve. Defaults to METADATA_ONLY.
Fields:
gcsPath: Required. A Cloud Storage path to the template from which to
create the job. Must be valid Cloud Storage URL, beginning with 'gs://'.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) to
which to direct the request.
projectId: Required. The ID of the Cloud Platform project that the job
belongs to.
view: The view to retrieve. Defaults to METADATA_ONLY.
"""
class ViewValueValuesEnum(_messages.Enum):
r"""The view to retrieve. Defaults to METADATA_ONLY.
Values:
METADATA_ONLY: <no description>
"""
METADATA_ONLY = 0
gcsPath = _messages.StringField(1)
location = _messages.StringField(2)
projectId = _messages.StringField(3, required=True)
view = _messages.EnumField('ViewValueValuesEnum', 4)
class DataflowProjectsTemplatesLaunchRequest(_messages.Message):
r"""A DataflowProjectsTemplatesLaunchRequest object.
Fields:
dynamicTemplate_gcsPath: Path to dynamic template spec file on GCS. The
file must be a Json serialized DynamicTemplateFieSpec object.
dynamicTemplate_stagingLocation: Cloud Storage path for staging
dependencies. Must be a valid Cloud Storage URL, beginning with `gs://`.
gcsPath: A Cloud Storage path to the template from which to create the
job. Must be valid Cloud Storage URL, beginning with 'gs://'.
launchTemplateParameters: A LaunchTemplateParameters resource to be passed
as the request body.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) to
which to direct the request.
projectId: Required. The ID of the Cloud Platform project that the job
belongs to.
validateOnly: If true, the request is validated but not actually executed.
Defaults to false.
"""
dynamicTemplate_gcsPath = _messages.StringField(1)
dynamicTemplate_stagingLocation = _messages.StringField(2)
gcsPath = _messages.StringField(3)
launchTemplateParameters = _messages.MessageField('LaunchTemplateParameters', 4)
location = _messages.StringField(5)
projectId = _messages.StringField(6, required=True)
validateOnly = _messages.BooleanField(7)
class DataflowProjectsWorkerMessagesRequest(_messages.Message):
r"""A DataflowProjectsWorkerMessagesRequest object.
Fields:
projectId: The project to send the WorkerMessages to.
sendWorkerMessagesRequest: A SendWorkerMessagesRequest resource to be
passed as the request body.
"""
projectId = _messages.StringField(1, required=True)
sendWorkerMessagesRequest = _messages.MessageField('SendWorkerMessagesRequest', 2)
class DatastoreIODetails(_messages.Message):
r"""Metadata for a Datastore connector used by the job.
Fields:
namespace: Namespace used in the connection.
projectId: ProjectId accessed in the connection.
"""
namespace = _messages.StringField(1)
projectId = _messages.StringField(2)
class DeleteSnapshotResponse(_messages.Message):
r"""Response from deleting a snapshot."""
class DerivedSource(_messages.Message):
r"""Specification of one of the bundles produced as a result of splitting a
Source (e.g. when executing a SourceSplitRequest, or when splitting an
active task using WorkItemStatus.dynamic_source_split), relative to the
source being split.
Enums:
DerivationModeValueValuesEnum: What source to base the produced source on
(if any).
Fields:
derivationMode: What source to base the produced source on (if any).
source: Specification of the source.
"""
class DerivationModeValueValuesEnum(_messages.Enum):
r"""What source to base the produced source on (if any).
Values:
SOURCE_DERIVATION_MODE_UNKNOWN: The source derivation is unknown, or
unspecified.
SOURCE_DERIVATION_MODE_INDEPENDENT: Produce a completely independent
Source with no base.
SOURCE_DERIVATION_MODE_CHILD_OF_CURRENT: Produce a Source based on the
Source being split.
SOURCE_DERIVATION_MODE_SIBLING_OF_CURRENT: Produce a Source based on the
base of the Source being split.
"""
SOURCE_DERIVATION_MODE_UNKNOWN = 0
SOURCE_DERIVATION_MODE_INDEPENDENT = 1
SOURCE_DERIVATION_MODE_CHILD_OF_CURRENT = 2
SOURCE_DERIVATION_MODE_SIBLING_OF_CURRENT = 3
derivationMode = _messages.EnumField('DerivationModeValueValuesEnum', 1)
source = _messages.MessageField('Source', 2)
class Disk(_messages.Message):
r"""Describes the data disk used by a workflow job.
Fields:
diskType: Disk storage type, as defined by Google Compute Engine. This
must be a disk type appropriate to the project and zone in which the
workers will run. If unknown or unspecified, the service will attempt
to choose a reasonable default. For example, the standard persistent
disk type is a resource name typically ending in "pd-standard". If SSD
persistent disks are available, the resource name typically ends with
"pd-ssd". The actual valid values are defined the Google Compute Engine
API, not by the Cloud Dataflow API; consult the Google Compute Engine
documentation for more information about determining the set of
available disk types for a particular project and zone. Google Compute
Engine Disk types are local to a particular project in a particular
zone, and so the resource name will typically look something like this:
compute.googleapis.com/projects/project-id/zones/zone/diskTypes/pd-
standard
mountPoint: Directory in a VM where disk is mounted.
sizeGb: Size of disk in GB. If zero or unspecified, the service will
attempt to choose a reasonable default.
"""
diskType = _messages.StringField(1)
mountPoint = _messages.StringField(2)
sizeGb = _messages.IntegerField(3, variant=_messages.Variant.INT32)
class DisplayData(_messages.Message):
r"""Data provided with a pipeline or transform to provide descriptive info.
Fields:
boolValue: Contains value if the data is of a boolean type.
durationValue: Contains value if the data is of duration type.
floatValue: Contains value if the data is of float type.
int64Value: Contains value if the data is of int64 type.
javaClassValue: Contains value if the data is of java class type.
key: The key identifying the display data. This is intended to be used as
a label for the display data when viewed in a dax monitoring system.
label: An optional label to display in a dax UI for the element.
namespace: The namespace for the key. This is usually a class name or
programming language namespace (i.e. python module) which defines the
display data. This allows a dax monitoring system to specially handle
the data and perform custom rendering.
shortStrValue: A possible additional shorter value to display. For example
a java_class_name_value of com.mypackage.MyDoFn will be stored with
MyDoFn as the short_str_value and com.mypackage.MyDoFn as the
java_class_name value. short_str_value can be displayed and
java_class_name_value will be displayed as a tooltip.
strValue: Contains value if the data is of string type.
timestampValue: Contains value if the data is of timestamp type.
url: An optional full URL.
"""
boolValue = _messages.BooleanField(1)
durationValue = _messages.StringField(2)
floatValue = _messages.FloatField(3, variant=_messages.Variant.FLOAT)
int64Value = _messages.IntegerField(4)
javaClassValue = _messages.StringField(5)
key = _messages.StringField(6)
label = _messages.StringField(7)
namespace = _messages.StringField(8)
shortStrValue = _messages.StringField(9)
strValue = _messages.StringField(10)
timestampValue = _messages.StringField(11)
url = _messages.StringField(12)
class DistributionUpdate(_messages.Message):
r"""A metric value representing a distribution.
Fields:
count: The count of the number of elements present in the distribution.
histogram: (Optional) Histogram of value counts for the distribution.
max: The maximum value present in the distribution.
min: The minimum value present in the distribution.
sum: Use an int64 since we'd prefer the added precision. If overflow is a
common problem we can detect it and use an additional int64 or a double.
sumOfSquares: Use a double since the sum of squares is likely to overflow
int64.
"""
count = _messages.MessageField('SplitInt64', 1)
histogram = _messages.MessageField('Histogram', 2)
max = _messages.MessageField('SplitInt64', 3)
min = _messages.MessageField('SplitInt64', 4)
sum = _messages.MessageField('SplitInt64', 5)
sumOfSquares = _messages.FloatField(6)
class DynamicSourceSplit(_messages.Message):
r"""When a task splits using WorkItemStatus.dynamic_source_split, this
message describes the two parts of the split relative to the description of
the current task's input.
Fields:
primary: Primary part (continued to be processed by worker). Specified
relative to the previously-current source. Becomes current.
residual: Residual part (returned to the pool of work). Specified relative
to the previously-current source.
"""
primary = _messages.MessageField('DerivedSource', 1)
residual = _messages.MessageField('DerivedSource', 2)
class Environment(_messages.Message):
r"""Describes the environment in which a Dataflow Job runs.
Enums:
FlexResourceSchedulingGoalValueValuesEnum: Which Flexible Resource
Scheduling mode to run in.
Messages:
InternalExperimentsValue: Experimental settings.
SdkPipelineOptionsValue: The Cloud Dataflow SDK pipeline options specified
by the user. These options are passed through the service and are used
to recreate the SDK pipeline options on the worker in a language
agnostic and platform independent way.
UserAgentValue: A description of the process that generated the request.
VersionValue: A structure describing which components and their versions
of the service are required in order to run the job.
Fields:
clusterManagerApiService: The type of cluster manager API to use. If
unknown or unspecified, the service will attempt to choose a reasonable
default. This should be in the form of the API service name, e.g.
"compute.googleapis.com".
dataset: The dataset for the current project where various workflow
related tables are stored. The supported resource type is: Google
BigQuery: bigquery.googleapis.com/{dataset}
experiments: The list of experiments to enable.
flexResourceSchedulingGoal: Which Flexible Resource Scheduling mode to run
in.
internalExperiments: Experimental settings.
sdkPipelineOptions: The Cloud Dataflow SDK pipeline options specified by
the user. These options are passed through the service and are used to
recreate the SDK pipeline options on the worker in a language agnostic
and platform independent way.
serviceAccountEmail: Identity to run virtual machines as. Defaults to the
default account.
serviceKmsKeyName: If set, contains the Cloud KMS key identifier used to
encrypt data at rest, AKA a Customer Managed Encryption Key (CMEK).
Format:
projects/PROJECT_ID/locations/LOCATION/keyRings/KEY_RING/cryptoKeys/KEY
tempStoragePrefix: The prefix of the resources the system should use for
temporary storage. The system will append the suffix "/temp-{JOBNAME}
to this resource prefix, where {JOBNAME} is the value of the job_name
field. The resulting bucket and object prefix is used as the prefix of
the resources used to store temporary data needed during the job
execution. NOTE: This will override the value in taskrunner_settings.
The supported resource type is: Google Cloud Storage:
storage.googleapis.com/{bucket}/{object}
bucket.storage.googleapis.com/{object}
userAgent: A description of the process that generated the request.
version: A structure describing which components and their versions of the
service are required in order to run the job.
workerPools: The worker pools. At least one "harness" worker pool must be
specified in order for the job to have workers.
"""
class FlexResourceSchedulingGoalValueValuesEnum(_messages.Enum):
r"""Which Flexible Resource Scheduling mode to run in.
Values:
FLEXRS_UNSPECIFIED: Run in the default mode.
FLEXRS_SPEED_OPTIMIZED: Optimize for lower execution time.
FLEXRS_COST_OPTIMIZED: Optimize for lower cost.
"""
FLEXRS_UNSPECIFIED = 0
FLEXRS_SPEED_OPTIMIZED = 1
FLEXRS_COST_OPTIMIZED = 2
@encoding.MapUnrecognizedFields('additionalProperties')
class InternalExperimentsValue(_messages.Message):
r"""Experimental settings.
Messages:
AdditionalProperty: An additional property for a
InternalExperimentsValue object.
Fields:
additionalProperties: Properties of the object. Contains field @type
with type URL.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a InternalExperimentsValue object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
@encoding.MapUnrecognizedFields('additionalProperties')
class SdkPipelineOptionsValue(_messages.Message):
r"""The Cloud Dataflow SDK pipeline options specified by the user. These
options are passed through the service and are used to recreate the SDK
pipeline options on the worker in a language agnostic and platform
independent way.
Messages:
AdditionalProperty: An additional property for a SdkPipelineOptionsValue
object.
Fields:
additionalProperties: Properties of the object.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a SdkPipelineOptionsValue object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
@encoding.MapUnrecognizedFields('additionalProperties')
class UserAgentValue(_messages.Message):
r"""A description of the process that generated the request.
Messages:
AdditionalProperty: An additional property for a UserAgentValue object.
Fields:
additionalProperties: Properties of the object.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a UserAgentValue object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
@encoding.MapUnrecognizedFields('additionalProperties')
class VersionValue(_messages.Message):
r"""A structure describing which components and their versions of the
service are required in order to run the job.
Messages:
AdditionalProperty: An additional property for a VersionValue object.
Fields:
additionalProperties: Properties of the object.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a VersionValue object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
clusterManagerApiService = _messages.StringField(1)
dataset = _messages.StringField(2)
experiments = _messages.StringField(3, repeated=True)
flexResourceSchedulingGoal = _messages.EnumField('FlexResourceSchedulingGoalValueValuesEnum', 4)
internalExperiments = _messages.MessageField('InternalExperimentsValue', 5)
sdkPipelineOptions = _messages.MessageField('SdkPipelineOptionsValue', 6)
serviceAccountEmail = _messages.StringField(7)
serviceKmsKeyName = _messages.StringField(8)
tempStoragePrefix = _messages.StringField(9)
userAgent = _messages.MessageField('UserAgentValue', 10)
version = _messages.MessageField('VersionValue', 11)
workerPools = _messages.MessageField('WorkerPool', 12, repeated=True)
class ExecutionStageState(_messages.Message):
r"""A message describing the state of a particular execution stage.
Enums:
ExecutionStageStateValueValuesEnum: Executions stage states allow the same
set of values as JobState.
Fields:
currentStateTime: The time at which the stage transitioned to this state.
executionStageName: The name of the execution stage.
executionStageState: Executions stage states allow the same set of values
as JobState.
"""
class ExecutionStageStateValueValuesEnum(_messages.Enum):
r"""Executions stage states allow the same set of values as JobState.
Values:
JOB_STATE_UNKNOWN: The job's run state isn't specified.
JOB_STATE_STOPPED: `JOB_STATE_STOPPED` indicates that the job has not
yet started to run.
JOB_STATE_RUNNING: `JOB_STATE_RUNNING` indicates that the job is
currently running.
JOB_STATE_DONE: `JOB_STATE_DONE` indicates that the job has successfully
completed. This is a terminal job state. This state may be set by the
Cloud Dataflow service, as a transition from `JOB_STATE_RUNNING`. It
may also be set via a Cloud Dataflow `UpdateJob` call, if the job has
not yet reached a terminal state.
JOB_STATE_FAILED: `JOB_STATE_FAILED` indicates that the job has failed.
This is a terminal job state. This state may only be set by the Cloud
Dataflow service, and only as a transition from `JOB_STATE_RUNNING`.
JOB_STATE_CANCELLED: `JOB_STATE_CANCELLED` indicates that the job has
been explicitly cancelled. This is a terminal job state. This state
may only be set via a Cloud Dataflow `UpdateJob` call, and only if the
job has not yet reached another terminal state.
JOB_STATE_UPDATED: `JOB_STATE_UPDATED` indicates that the job was
successfully updated, meaning that this job was stopped and another
job was started, inheriting state from this one. This is a terminal
job state. This state may only be set by the Cloud Dataflow service,
and only as a transition from `JOB_STATE_RUNNING`.
JOB_STATE_DRAINING: `JOB_STATE_DRAINING` indicates that the job is in
the process of draining. A draining job has stopped pulling from its
input sources and is processing any data that remains in-flight. This
state may be set via a Cloud Dataflow `UpdateJob` call, but only as a
transition from `JOB_STATE_RUNNING`. Jobs that are draining may only
transition to `JOB_STATE_DRAINED`, `JOB_STATE_CANCELLED`, or
`JOB_STATE_FAILED`.
JOB_STATE_DRAINED: `JOB_STATE_DRAINED` indicates that the job has been
drained. A drained job terminated by stopping pulling from its input
sources and processing any data that remained in-flight when draining
was requested. This state is a terminal state, may only be set by the
Cloud Dataflow service, and only as a transition from
`JOB_STATE_DRAINING`.
JOB_STATE_PENDING: `JOB_STATE_PENDING` indicates that the job has been
created but is not yet running. Jobs that are pending may only
transition to `JOB_STATE_RUNNING`, or `JOB_STATE_FAILED`.
JOB_STATE_CANCELLING: `JOB_STATE_CANCELLING` indicates that the job has
been explicitly cancelled and is in the process of stopping. Jobs
that are cancelling may only transition to `JOB_STATE_CANCELLED` or
`JOB_STATE_FAILED`.
JOB_STATE_QUEUED: `JOB_STATE_QUEUED` indicates that the job has been
created but is being delayed until launch. Jobs that are queued may
only transition to `JOB_STATE_PENDING` or `JOB_STATE_CANCELLED`.
"""
JOB_STATE_UNKNOWN = 0
JOB_STATE_STOPPED = 1
JOB_STATE_RUNNING = 2
JOB_STATE_DONE = 3
JOB_STATE_FAILED = 4
JOB_STATE_CANCELLED = 5
JOB_STATE_UPDATED = 6
JOB_STATE_DRAINING = 7
JOB_STATE_DRAINED = 8
JOB_STATE_PENDING = 9
JOB_STATE_CANCELLING = 10
JOB_STATE_QUEUED = 11
currentStateTime = _messages.StringField(1)
executionStageName = _messages.StringField(2)
executionStageState = _messages.EnumField('ExecutionStageStateValueValuesEnum', 3)
class ExecutionStageSummary(_messages.Message):
r"""Description of the composing transforms, names/ids, and input/outputs of
a stage of execution. Some composing transforms and sources may have been
generated by the Dataflow service during execution planning.
Enums:
KindValueValuesEnum: Type of tranform this stage is executing.
Fields:
componentSource: Collections produced and consumed by component transforms
of this stage.
componentTransform: Transforms that comprise this execution stage.
id: Dataflow service generated id for this stage.
inputSource: Input sources for this stage.
kind: Type of tranform this stage is executing.
name: Dataflow service generated name for this stage.
outputSource: Output sources for this stage.
"""
class KindValueValuesEnum(_messages.Enum):
r"""Type of tranform this stage is executing.
Values:
UNKNOWN_KIND: Unrecognized transform type.
PAR_DO_KIND: ParDo transform.
GROUP_BY_KEY_KIND: Group By Key transform.
FLATTEN_KIND: Flatten transform.
READ_KIND: Read transform.
WRITE_KIND: Write transform.
CONSTANT_KIND: Constructs from a constant value, such as with Create.of.
SINGLETON_KIND: Creates a Singleton view of a collection.
SHUFFLE_KIND: Opening or closing a shuffle session, often as part of a
GroupByKey.
"""
UNKNOWN_KIND = 0
PAR_DO_KIND = 1
GROUP_BY_KEY_KIND = 2
FLATTEN_KIND = 3
READ_KIND = 4
WRITE_KIND = 5
CONSTANT_KIND = 6
SINGLETON_KIND = 7
SHUFFLE_KIND = 8
componentSource = _messages.MessageField('ComponentSource', 1, repeated=True)
componentTransform = _messages.MessageField('ComponentTransform', 2, repeated=True)
id = _messages.StringField(3)
inputSource = _messages.MessageField('StageSource', 4, repeated=True)
kind = _messages.EnumField('KindValueValuesEnum', 5)
name = _messages.StringField(6)
outputSource = _messages.MessageField('StageSource', 7, repeated=True)
class FailedLocation(_messages.Message):
r"""Indicates which [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) failed
to respond to a request for data.
Fields:
name: The name of the [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that failed to respond.
"""
name = _messages.StringField(1)
class FileIODetails(_messages.Message):
r"""Metadata for a File connector used by the job.
Fields:
filePattern: File Pattern used to access files by the connector.
"""
filePattern = _messages.StringField(1)
class FlattenInstruction(_messages.Message):
r"""An instruction that copies its inputs (zero or more) to its (single)
output.
Fields:
inputs: Describes the inputs to the flatten instruction.
"""
inputs = _messages.MessageField('InstructionInput', 1, repeated=True)
class FloatingPointList(_messages.Message):
r"""A metric value representing a list of floating point numbers.
Fields:
elements: Elements of the list.
"""
elements = _messages.FloatField(1, repeated=True)
class FloatingPointMean(_messages.Message):
r"""A representation of a floating point mean metric contribution.
Fields:
count: The number of values being aggregated.
sum: The sum of all values being aggregated.
"""
count = _messages.MessageField('SplitInt64', 1)
sum = _messages.FloatField(2)
class GetDebugConfigRequest(_messages.Message):
r"""Request to get updated debug configuration for component.
Fields:
componentId: The internal component id for which debug configuration is
requested.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains the job specified by job_id.
workerId: The worker id, i.e., VM hostname.
"""
componentId = _messages.StringField(1)
location = _messages.StringField(2)
workerId = _messages.StringField(3)
class GetDebugConfigResponse(_messages.Message):
r"""Response to a get debug configuration request.
Fields:
config: The encoded debug configuration for the requested component.
"""
config = _messages.StringField(1)
class GetTemplateResponse(_messages.Message):
r"""The response to a GetTemplate request.
Fields:
metadata: The template metadata describing the template name, available
parameters, etc.
status: The status of the get template request. Any problems with the
request will be indicated in the error_details.
"""
metadata = _messages.MessageField('TemplateMetadata', 1)
status = _messages.MessageField('Status', 2)
class Histogram(_messages.Message):
r"""Histogram of value counts for a distribution. Buckets have an inclusive
lower bound and exclusive upper bound and use "1,2,5 bucketing": The first
bucket range is from [0,1) and all subsequent bucket boundaries are powers
of ten multiplied by 1, 2, or 5. Thus, bucket boundaries are 0, 1, 2, 5, 10,
20, 50, 100, 200, 500, 1000, ... Negative values are not supported.
Fields:
bucketCounts: Counts of values in each bucket. For efficiency, prefix and
trailing buckets with count = 0 are elided. Buckets can store the full
range of values of an unsigned long, with ULLONG_MAX falling into the
59th bucket with range [1e19, 2e19).
firstBucketOffset: Starting index of first stored bucket. The non-
inclusive upper-bound of the ith bucket is given by:
pow(10,(i-first_bucket_offset)/3) * (1,2,5)[(i-first_bucket_offset)%3]
"""
bucketCounts = _messages.IntegerField(1, repeated=True)
firstBucketOffset = _messages.IntegerField(2, variant=_messages.Variant.INT32)
class InstructionInput(_messages.Message):
r"""An input of an instruction, as a reference to an output of a producer
instruction.
Fields:
outputNum: The output index (origin zero) within the producer.
producerInstructionIndex: The index (origin zero) of the parallel
instruction that produces the output to be consumed by this input. This
index is relative to the list of instructions in this input's
instruction's containing MapTask.
"""
outputNum = _messages.IntegerField(1, variant=_messages.Variant.INT32)
producerInstructionIndex = _messages.IntegerField(2, variant=_messages.Variant.INT32)
class InstructionOutput(_messages.Message):
r"""An output of an instruction.
Messages:
CodecValue: The codec to use to encode data being written via this output.
Fields:
codec: The codec to use to encode data being written via this output.
name: The user-provided name of this output.
onlyCountKeyBytes: For system-generated byte and mean byte metrics,
certain instructions should only report the key size.
onlyCountValueBytes: For system-generated byte and mean byte metrics,
certain instructions should only report the value size.
originalName: System-defined name for this output in the original workflow
graph. Outputs that do not contribute to an original instruction do not
set this.
systemName: System-defined name of this output. Unique across the
workflow.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class CodecValue(_messages.Message):
r"""The codec to use to encode data being written via this output.
Messages:
AdditionalProperty: An additional property for a CodecValue object.
Fields:
additionalProperties: Properties of the object.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a CodecValue object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
codec = _messages.MessageField('CodecValue', 1)
name = _messages.StringField(2)
onlyCountKeyBytes = _messages.BooleanField(3)
onlyCountValueBytes = _messages.BooleanField(4)
originalName = _messages.StringField(5)
systemName = _messages.StringField(6)
class IntegerGauge(_messages.Message):
r"""A metric value representing temporal values of a variable.
Fields:
timestamp: The time at which this value was measured. Measured as msecs
from epoch.
value: The value of the variable represented by this gauge.
"""
timestamp = _messages.StringField(1)
value = _messages.MessageField('SplitInt64', 2)
class IntegerList(_messages.Message):
r"""A metric value representing a list of integers.
Fields:
elements: Elements of the list.
"""
elements = _messages.MessageField('SplitInt64', 1, repeated=True)
class IntegerMean(_messages.Message):
r"""A representation of an integer mean metric contribution.
Fields:
count: The number of values being aggregated.
sum: The sum of all values being aggregated.
"""
count = _messages.MessageField('SplitInt64', 1)
sum = _messages.MessageField('SplitInt64', 2)
class Job(_messages.Message):
r"""Defines a job to be run by the Cloud Dataflow service.
Enums:
CurrentStateValueValuesEnum: The current state of the job. Jobs are
created in the `JOB_STATE_STOPPED` state unless otherwise specified. A
job in the `JOB_STATE_RUNNING` state may asynchronously enter a terminal
state. After a job has reached a terminal state, no further state
updates may be made. This field may be mutated by the Cloud Dataflow
service; callers cannot mutate it.
RequestedStateValueValuesEnum: The job's requested state. `UpdateJob` may
be used to switch between the `JOB_STATE_STOPPED` and
`JOB_STATE_RUNNING` states, by setting requested_state. `UpdateJob` may
also be used to directly set a job's requested state to
`JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably terminating the
job if it has not already reached a terminal state.
TypeValueValuesEnum: The type of Cloud Dataflow job.
Messages:
LabelsValue: User-defined labels for this job. The labels map can contain
no more than 64 entries. Entries of the labels map are UTF8 strings
that comply with the following restrictions: * Keys must conform to
regexp: \p{Ll}\p{Lo}{0,62} * Values must conform to regexp:
[\p{Ll}\p{Lo}\p{N}_-]{0,63} * Both keys and values are additionally
constrained to be <= 128 bytes in size.
TransformNameMappingValue: The map of transform name prefixes of the job
to be replaced to the corresponding name prefixes of the new job.
Fields:
clientRequestId: The client's unique identifier of the job, re-used across
retried attempts. If this field is set, the service will ensure its
uniqueness. The request to create a job will fail if the service has
knowledge of a previously submitted job with the same client's ID and
job name. The caller may use this field to ensure idempotence of job
creation across retried attempts to create a job. By default, the field
is empty and, in that case, the service ignores it.
createTime: The timestamp when the job was initially created. Immutable
and set by the Cloud Dataflow service.
createdFromSnapshotId: If this is specified, the job's initial state is
populated from the given snapshot.
currentState: The current state of the job. Jobs are created in the
`JOB_STATE_STOPPED` state unless otherwise specified. A job in the
`JOB_STATE_RUNNING` state may asynchronously enter a terminal state.
After a job has reached a terminal state, no further state updates may
be made. This field may be mutated by the Cloud Dataflow service;
callers cannot mutate it.
currentStateTime: The timestamp associated with the current state.
environment: The environment for the job.
executionInfo: Deprecated.
id: The unique ID of this job. This field is set by the Cloud Dataflow
service when the Job is created, and is immutable for the life of the
job.
jobMetadata: This field is populated by the Dataflow service to support
filtering jobs by the metadata values provided here. Populated for
ListJobs and all GetJob views SUMMARY and higher.
labels: User-defined labels for this job. The labels map can contain no
more than 64 entries. Entries of the labels map are UTF8 strings that
comply with the following restrictions: * Keys must conform to regexp:
\p{Ll}\p{Lo}{0,62} * Values must conform to regexp:
[\p{Ll}\p{Lo}\p{N}_-]{0,63} * Both keys and values are additionally
constrained to be <= 128 bytes in size.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains this job.
name: The user-specified Cloud Dataflow job name. Only one Job with a
given name may exist in a project at any given time. If a caller
attempts to create a Job with the same name as an already-existing Job,
the attempt returns the existing Job. The name must match the regular
expression `[a-z]([-a-z0-9]{0,38}[a-z0-9])?`
pipelineDescription: Preliminary field: The format of this data may change
at any time. A description of the user pipeline and stages through which
it is executed. Created by Cloud Dataflow service. Only retrieved with
JOB_VIEW_DESCRIPTION or JOB_VIEW_ALL.
projectId: The ID of the Cloud Platform project that the job belongs to.
replaceJobId: If this job is an update of an existing job, this field is
the job ID of the job it replaced. When sending a `CreateJobRequest`,
you can update a job by specifying it here. The job named here is
stopped, and its intermediate state is transferred to this job.
replacedByJobId: If another job is an update of this job (and thus, this
job is in `JOB_STATE_UPDATED`), this field contains the ID of that job.
requestedState: The job's requested state. `UpdateJob` may be used to
switch between the `JOB_STATE_STOPPED` and `JOB_STATE_RUNNING` states,
by setting requested_state. `UpdateJob` may also be used to directly
set a job's requested state to `JOB_STATE_CANCELLED` or
`JOB_STATE_DONE`, irrevocably terminating the job if it has not already
reached a terminal state.
stageStates: This field may be mutated by the Cloud Dataflow service;
callers cannot mutate it.
startTime: The timestamp when the job was started (transitioned to
JOB_STATE_PENDING). Flexible resource scheduling jobs are started with
some delay after job creation, so start_time is unset before start and
is updated when the job is started by the Cloud Dataflow service. For
other jobs, start_time always equals to create_time and is immutable and
set by the Cloud Dataflow service.
steps: Exactly one of step or steps_location should be specified. The
top-level steps that constitute the entire job.
stepsLocation: The GCS location where the steps are stored.
tempFiles: A set of files the system should be aware of that are used for
temporary storage. These temporary files will be removed on job
completion. No duplicates are allowed. No file patterns are supported.
The supported files are: Google Cloud Storage:
storage.googleapis.com/{bucket}/{object}
bucket.storage.googleapis.com/{object}
transformNameMapping: The map of transform name prefixes of the job to be
replaced to the corresponding name prefixes of the new job.
type: The type of Cloud Dataflow job.
"""
class CurrentStateValueValuesEnum(_messages.Enum):
r"""The current state of the job. Jobs are created in the
`JOB_STATE_STOPPED` state unless otherwise specified. A job in the
`JOB_STATE_RUNNING` state may asynchronously enter a terminal state. After
a job has reached a terminal state, no further state updates may be made.
This field may be mutated by the Cloud Dataflow service; callers cannot
mutate it.
Values:
JOB_STATE_UNKNOWN: The job's run state isn't specified.
JOB_STATE_STOPPED: `JOB_STATE_STOPPED` indicates that the job has not
yet started to run.
JOB_STATE_RUNNING: `JOB_STATE_RUNNING` indicates that the job is
currently running.
JOB_STATE_DONE: `JOB_STATE_DONE` indicates that the job has successfully
completed. This is a terminal job state. This state may be set by the
Cloud Dataflow service, as a transition from `JOB_STATE_RUNNING`. It
may also be set via a Cloud Dataflow `UpdateJob` call, if the job has
not yet reached a terminal state.
JOB_STATE_FAILED: `JOB_STATE_FAILED` indicates that the job has failed.
This is a terminal job state. This state may only be set by the Cloud
Dataflow service, and only as a transition from `JOB_STATE_RUNNING`.
JOB_STATE_CANCELLED: `JOB_STATE_CANCELLED` indicates that the job has
been explicitly cancelled. This is a terminal job state. This state
may only be set via a Cloud Dataflow `UpdateJob` call, and only if the
job has not yet reached another terminal state.
JOB_STATE_UPDATED: `JOB_STATE_UPDATED` indicates that the job was
successfully updated, meaning that this job was stopped and another
job was started, inheriting state from this one. This is a terminal
job state. This state may only be set by the Cloud Dataflow service,
and only as a transition from `JOB_STATE_RUNNING`.
JOB_STATE_DRAINING: `JOB_STATE_DRAINING` indicates that the job is in
the process of draining. A draining job has stopped pulling from its
input sources and is processing any data that remains in-flight. This
state may be set via a Cloud Dataflow `UpdateJob` call, but only as a
transition from `JOB_STATE_RUNNING`. Jobs that are draining may only
transition to `JOB_STATE_DRAINED`, `JOB_STATE_CANCELLED`, or
`JOB_STATE_FAILED`.
JOB_STATE_DRAINED: `JOB_STATE_DRAINED` indicates that the job has been
drained. A drained job terminated by stopping pulling from its input
sources and processing any data that remained in-flight when draining
was requested. This state is a terminal state, may only be set by the
Cloud Dataflow service, and only as a transition from
`JOB_STATE_DRAINING`.
JOB_STATE_PENDING: `JOB_STATE_PENDING` indicates that the job has been
created but is not yet running. Jobs that are pending may only
transition to `JOB_STATE_RUNNING`, or `JOB_STATE_FAILED`.
JOB_STATE_CANCELLING: `JOB_STATE_CANCELLING` indicates that the job has
been explicitly cancelled and is in the process of stopping. Jobs
that are cancelling may only transition to `JOB_STATE_CANCELLED` or
`JOB_STATE_FAILED`.
JOB_STATE_QUEUED: `JOB_STATE_QUEUED` indicates that the job has been
created but is being delayed until launch. Jobs that are queued may
only transition to `JOB_STATE_PENDING` or `JOB_STATE_CANCELLED`.
"""
JOB_STATE_UNKNOWN = 0
JOB_STATE_STOPPED = 1
JOB_STATE_RUNNING = 2
JOB_STATE_DONE = 3
JOB_STATE_FAILED = 4
JOB_STATE_CANCELLED = 5
JOB_STATE_UPDATED = 6
JOB_STATE_DRAINING = 7
JOB_STATE_DRAINED = 8
JOB_STATE_PENDING = 9
JOB_STATE_CANCELLING = 10
JOB_STATE_QUEUED = 11
class RequestedStateValueValuesEnum(_messages.Enum):
r"""The job's requested state. `UpdateJob` may be used to switch between
the `JOB_STATE_STOPPED` and `JOB_STATE_RUNNING` states, by setting
requested_state. `UpdateJob` may also be used to directly set a job's
requested state to `JOB_STATE_CANCELLED` or `JOB_STATE_DONE`, irrevocably
terminating the job if it has not already reached a terminal state.
Values:
JOB_STATE_UNKNOWN: The job's run state isn't specified.
JOB_STATE_STOPPED: `JOB_STATE_STOPPED` indicates that the job has not
yet started to run.
JOB_STATE_RUNNING: `JOB_STATE_RUNNING` indicates that the job is
currently running.
JOB_STATE_DONE: `JOB_STATE_DONE` indicates that the job has successfully
completed. This is a terminal job state. This state may be set by the
Cloud Dataflow service, as a transition from `JOB_STATE_RUNNING`. It
may also be set via a Cloud Dataflow `UpdateJob` call, if the job has
not yet reached a terminal state.
JOB_STATE_FAILED: `JOB_STATE_FAILED` indicates that the job has failed.
This is a terminal job state. This state may only be set by the Cloud
Dataflow service, and only as a transition from `JOB_STATE_RUNNING`.
JOB_STATE_CANCELLED: `JOB_STATE_CANCELLED` indicates that the job has
been explicitly cancelled. This is a terminal job state. This state
may only be set via a Cloud Dataflow `UpdateJob` call, and only if the
job has not yet reached another terminal state.
JOB_STATE_UPDATED: `JOB_STATE_UPDATED` indicates that the job was
successfully updated, meaning that this job was stopped and another
job was started, inheriting state from this one. This is a terminal
job state. This state may only be set by the Cloud Dataflow service,
and only as a transition from `JOB_STATE_RUNNING`.
JOB_STATE_DRAINING: `JOB_STATE_DRAINING` indicates that the job is in
the process of draining. A draining job has stopped pulling from its
input sources and is processing any data that remains in-flight. This
state may be set via a Cloud Dataflow `UpdateJob` call, but only as a
transition from `JOB_STATE_RUNNING`. Jobs that are draining may only
transition to `JOB_STATE_DRAINED`, `JOB_STATE_CANCELLED`, or
`JOB_STATE_FAILED`.
JOB_STATE_DRAINED: `JOB_STATE_DRAINED` indicates that the job has been
drained. A drained job terminated by stopping pulling from its input
sources and processing any data that remained in-flight when draining
was requested. This state is a terminal state, may only be set by the
Cloud Dataflow service, and only as a transition from
`JOB_STATE_DRAINING`.
JOB_STATE_PENDING: `JOB_STATE_PENDING` indicates that the job has been
created but is not yet running. Jobs that are pending may only
transition to `JOB_STATE_RUNNING`, or `JOB_STATE_FAILED`.
JOB_STATE_CANCELLING: `JOB_STATE_CANCELLING` indicates that the job has
been explicitly cancelled and is in the process of stopping. Jobs
that are cancelling may only transition to `JOB_STATE_CANCELLED` or
`JOB_STATE_FAILED`.
JOB_STATE_QUEUED: `JOB_STATE_QUEUED` indicates that the job has been
created but is being delayed until launch. Jobs that are queued may
only transition to `JOB_STATE_PENDING` or `JOB_STATE_CANCELLED`.
"""
JOB_STATE_UNKNOWN = 0
JOB_STATE_STOPPED = 1
JOB_STATE_RUNNING = 2
JOB_STATE_DONE = 3
JOB_STATE_FAILED = 4
JOB_STATE_CANCELLED = 5
JOB_STATE_UPDATED = 6
JOB_STATE_DRAINING = 7
JOB_STATE_DRAINED = 8
JOB_STATE_PENDING = 9
JOB_STATE_CANCELLING = 10
JOB_STATE_QUEUED = 11
class TypeValueValuesEnum(_messages.Enum):
r"""The type of Cloud Dataflow job.
Values:
JOB_TYPE_UNKNOWN: The type of the job is unspecified, or unknown.
JOB_TYPE_BATCH: A batch job with a well-defined end point: data is read,
data is processed, data is written, and the job is done.
JOB_TYPE_STREAMING: A continuously streaming job with no end: data is
read, processed, and written continuously.
"""
JOB_TYPE_UNKNOWN = 0
JOB_TYPE_BATCH = 1
JOB_TYPE_STREAMING = 2
@encoding.MapUnrecognizedFields('additionalProperties')
class LabelsValue(_messages.Message):
r"""User-defined labels for this job. The labels map can contain no more
than 64 entries. Entries of the labels map are UTF8 strings that comply
with the following restrictions: * Keys must conform to regexp:
\p{Ll}\p{Lo}{0,62} * Values must conform to regexp:
[\p{Ll}\p{Lo}\p{N}_-]{0,63} * Both keys and values are additionally
constrained to be <= 128 bytes in size.
Messages:
AdditionalProperty: An additional property for a LabelsValue object.
Fields:
additionalProperties: Additional properties of type LabelsValue
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a LabelsValue object.
Fields:
key: Name of the additional property.
value: A string attribute.
"""
key = _messages.StringField(1)
value = _messages.StringField(2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
@encoding.MapUnrecognizedFields('additionalProperties')
class TransformNameMappingValue(_messages.Message):
r"""The map of transform name prefixes of the job to be replaced to the
corresponding name prefixes of the new job.
Messages:
AdditionalProperty: An additional property for a
TransformNameMappingValue object.
Fields:
additionalProperties: Additional properties of type
TransformNameMappingValue
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a TransformNameMappingValue object.
Fields:
key: Name of the additional property.
value: A string attribute.
"""
key = _messages.StringField(1)
value = _messages.StringField(2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
clientRequestId = _messages.StringField(1)
createTime = _messages.StringField(2)
createdFromSnapshotId = _messages.StringField(3)
currentState = _messages.EnumField('CurrentStateValueValuesEnum', 4)
currentStateTime = _messages.StringField(5)
environment = _messages.MessageField('Environment', 6)
executionInfo = _messages.MessageField('JobExecutionInfo', 7)
id = _messages.StringField(8)
jobMetadata = _messages.MessageField('JobMetadata', 9)
labels = _messages.MessageField('LabelsValue', 10)
location = _messages.StringField(11)
name = _messages.StringField(12)
pipelineDescription = _messages.MessageField('PipelineDescription', 13)
projectId = _messages.StringField(14)
replaceJobId = _messages.StringField(15)
replacedByJobId = _messages.StringField(16)
requestedState = _messages.EnumField('RequestedStateValueValuesEnum', 17)
stageStates = _messages.MessageField('ExecutionStageState', 18, repeated=True)
startTime = _messages.StringField(19)
steps = _messages.MessageField('Step', 20, repeated=True)
stepsLocation = _messages.StringField(21)
tempFiles = _messages.StringField(22, repeated=True)
transformNameMapping = _messages.MessageField('TransformNameMappingValue', 23)
type = _messages.EnumField('TypeValueValuesEnum', 24)
class JobExecutionInfo(_messages.Message):
r"""Additional information about how a Cloud Dataflow job will be executed
that isn't contained in the submitted job.
Messages:
StagesValue: A mapping from each stage to the information about that
stage.
Fields:
stages: A mapping from each stage to the information about that stage.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class StagesValue(_messages.Message):
r"""A mapping from each stage to the information about that stage.
Messages:
AdditionalProperty: An additional property for a StagesValue object.
Fields:
additionalProperties: Additional properties of type StagesValue
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a StagesValue object.
Fields:
key: Name of the additional property.
value: A JobExecutionStageInfo attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('JobExecutionStageInfo', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
stages = _messages.MessageField('StagesValue', 1)
class JobExecutionStageInfo(_messages.Message):
r"""Contains information about how a particular google.dataflow.v1beta3.Step
will be executed.
Fields:
stepName: The steps associated with the execution stage. Note that stages
may have several steps, and that a given step might be run by more than
one stage.
"""
stepName = _messages.StringField(1, repeated=True)
class JobMessage(_messages.Message):
r"""A particular message pertaining to a Dataflow job.
Enums:
MessageImportanceValueValuesEnum: Importance level of the message.
Fields:
id: Deprecated.
messageImportance: Importance level of the message.
messageText: The text of the message.
time: The timestamp of the message.
"""
class MessageImportanceValueValuesEnum(_messages.Enum):
r"""Importance level of the message.
Values:
JOB_MESSAGE_IMPORTANCE_UNKNOWN: The message importance isn't specified,
or is unknown.
JOB_MESSAGE_DEBUG: The message is at the 'debug' level: typically only
useful for software engineers working on the code the job is running.
Typically, Dataflow pipeline runners do not display log messages at
this level by default.
JOB_MESSAGE_DETAILED: The message is at the 'detailed' level: somewhat
verbose, but potentially useful to users. Typically, Dataflow
pipeline runners do not display log messages at this level by default.
These messages are displayed by default in the Dataflow monitoring UI.
JOB_MESSAGE_BASIC: The message is at the 'basic' level: useful for
keeping track of the execution of a Dataflow pipeline. Typically,
Dataflow pipeline runners display log messages at this level by
default, and these messages are displayed by default in the Dataflow
monitoring UI.
JOB_MESSAGE_WARNING: The message is at the 'warning' level: indicating a
condition pertaining to a job which may require human intervention.
Typically, Dataflow pipeline runners display log messages at this
level by default, and these messages are displayed by default in the
Dataflow monitoring UI.
JOB_MESSAGE_ERROR: The message is at the 'error' level: indicating a
condition preventing a job from succeeding. Typically, Dataflow
pipeline runners display log messages at this level by default, and
these messages are displayed by default in the Dataflow monitoring UI.
"""
JOB_MESSAGE_IMPORTANCE_UNKNOWN = 0
JOB_MESSAGE_DEBUG = 1
JOB_MESSAGE_DETAILED = 2
JOB_MESSAGE_BASIC = 3
JOB_MESSAGE_WARNING = 4
JOB_MESSAGE_ERROR = 5
id = _messages.StringField(1)
messageImportance = _messages.EnumField('MessageImportanceValueValuesEnum', 2)
messageText = _messages.StringField(3)
time = _messages.StringField(4)
class JobMetadata(_messages.Message):
r"""Metadata available primarily for filtering jobs. Will be included in the
ListJob response and Job SUMMARY view.
Fields:
bigTableDetails: Identification of a BigTable source used in the Dataflow
job.
bigqueryDetails: Identification of a BigQuery source used in the Dataflow
job.
datastoreDetails: Identification of a Datastore source used in the
Dataflow job.
fileDetails: Identification of a File source used in the Dataflow job.
pubsubDetails: Identification of a PubSub source used in the Dataflow job.
sdkVersion: The SDK version used to run the job.
spannerDetails: Identification of a Spanner source used in the Dataflow
job.
"""
bigTableDetails = _messages.MessageField('BigTableIODetails', 1, repeated=True)
bigqueryDetails = _messages.MessageField('BigQueryIODetails', 2, repeated=True)
datastoreDetails = _messages.MessageField('DatastoreIODetails', 3, repeated=True)
fileDetails = _messages.MessageField('FileIODetails', 4, repeated=True)
pubsubDetails = _messages.MessageField('PubSubIODetails', 5, repeated=True)
sdkVersion = _messages.MessageField('SdkVersion', 6)
spannerDetails = _messages.MessageField('SpannerIODetails', 7, repeated=True)
class JobMetrics(_messages.Message):
r"""JobMetrics contains a collection of metrics describing the detailed
progress of a Dataflow job. Metrics correspond to user-defined and system-
defined metrics in the job. This resource captures only the most recent
values of each metric; time-series data can be queried for them (under the
same metric names) from Cloud Monitoring.
Fields:
metricTime: Timestamp as of which metric values are current.
metrics: All metrics for this job.
"""
metricTime = _messages.StringField(1)
metrics = _messages.MessageField('MetricUpdate', 2, repeated=True)
class KeyRangeDataDiskAssignment(_messages.Message):
r"""Data disk assignment information for a specific key-range of a sharded
computation. Currently we only support UTF-8 character splits to simplify
encoding into JSON.
Fields:
dataDisk: The name of the data disk where data for this range is stored.
This name is local to the Google Cloud Platform project and uniquely
identifies the disk within that project, for example
"myproject-1014-104817-4c2-harness-0-disk-1".
end: The end (exclusive) of the key range.
start: The start (inclusive) of the key range.
"""
dataDisk = _messages.StringField(1)
end = _messages.StringField(2)
start = _messages.StringField(3)
class KeyRangeLocation(_messages.Message):
r"""Location information for a specific key-range of a sharded computation.
Currently we only support UTF-8 character splits to simplify encoding into
JSON.
Fields:
dataDisk: The name of the data disk where data for this range is stored.
This name is local to the Google Cloud Platform project and uniquely
identifies the disk within that project, for example
"myproject-1014-104817-4c2-harness-0-disk-1".
deliveryEndpoint: The physical location of this range assignment to be
used for streaming computation cross-worker message delivery.
deprecatedPersistentDirectory: DEPRECATED. The location of the persistent
state for this range, as a persistent directory in the worker local
filesystem.
end: The end (exclusive) of the key range.
start: The start (inclusive) of the key range.
"""
dataDisk = _messages.StringField(1)
deliveryEndpoint = _messages.StringField(2)
deprecatedPersistentDirectory = _messages.StringField(3)
end = _messages.StringField(4)
start = _messages.StringField(5)
class LaunchTemplateParameters(_messages.Message):
r"""Parameters to provide to the template being launched.
Messages:
ParametersValue: The runtime parameters to pass to the job.
Fields:
environment: The runtime environment for the job.
jobName: Required. The job name to use for the created job.
parameters: The runtime parameters to pass to the job.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class ParametersValue(_messages.Message):
r"""The runtime parameters to pass to the job.
Messages:
AdditionalProperty: An additional property for a ParametersValue object.
Fields:
additionalProperties: Additional properties of type ParametersValue
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a ParametersValue object.
Fields:
key: Name of the additional property.
value: A string attribute.
"""
key = _messages.StringField(1)
value = _messages.StringField(2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
environment = _messages.MessageField('RuntimeEnvironment', 1)
jobName = _messages.StringField(2)
parameters = _messages.MessageField('ParametersValue', 3)
class LaunchTemplateResponse(_messages.Message):
r"""Response to the request to launch a template.
Fields:
job: The job that was launched, if the request was not a dry run and the
job was successfully launched.
"""
job = _messages.MessageField('Job', 1)
class LeaseWorkItemRequest(_messages.Message):
r"""Request to lease WorkItems.
Messages:
UnifiedWorkerRequestValue: Untranslated bag-of-bytes WorkRequest from
UnifiedWorker.
Fields:
currentWorkerTime: The current timestamp at the worker.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains the WorkItem's job.
requestedLeaseDuration: The initial lease period.
unifiedWorkerRequest: Untranslated bag-of-bytes WorkRequest from
UnifiedWorker.
workItemTypes: Filter for WorkItem type.
workerCapabilities: Worker capabilities. WorkItems might be limited to
workers with specific capabilities.
workerId: Identifies the worker leasing work -- typically the ID of the
virtual machine running the worker.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class UnifiedWorkerRequestValue(_messages.Message):
r"""Untranslated bag-of-bytes WorkRequest from UnifiedWorker.
Messages:
AdditionalProperty: An additional property for a
UnifiedWorkerRequestValue object.
Fields:
additionalProperties: Properties of the object. Contains field @type
with type URL.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a UnifiedWorkerRequestValue object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
currentWorkerTime = _messages.StringField(1)
location = _messages.StringField(2)
requestedLeaseDuration = _messages.StringField(3)
unifiedWorkerRequest = _messages.MessageField('UnifiedWorkerRequestValue', 4)
workItemTypes = _messages.StringField(5, repeated=True)
workerCapabilities = _messages.StringField(6, repeated=True)
workerId = _messages.StringField(7)
class LeaseWorkItemResponse(_messages.Message):
r"""Response to a request to lease WorkItems.
Messages:
UnifiedWorkerResponseValue: Untranslated bag-of-bytes WorkResponse for
UnifiedWorker.
Fields:
unifiedWorkerResponse: Untranslated bag-of-bytes WorkResponse for
UnifiedWorker.
workItems: A list of the leased WorkItems.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class UnifiedWorkerResponseValue(_messages.Message):
r"""Untranslated bag-of-bytes WorkResponse for UnifiedWorker.
Messages:
AdditionalProperty: An additional property for a
UnifiedWorkerResponseValue object.
Fields:
additionalProperties: Properties of the object. Contains field @type
with type URL.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a UnifiedWorkerResponseValue object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
unifiedWorkerResponse = _messages.MessageField('UnifiedWorkerResponseValue', 1)
workItems = _messages.MessageField('WorkItem', 2, repeated=True)
class ListJobMessagesResponse(_messages.Message):
r"""Response to a request to list job messages.
Fields:
autoscalingEvents: Autoscaling events in ascending timestamp order.
jobMessages: Messages in ascending timestamp order.
nextPageToken: The token to obtain the next page of results if there are
more.
"""
autoscalingEvents = _messages.MessageField('AutoscalingEvent', 1, repeated=True)
jobMessages = _messages.MessageField('JobMessage', 2, repeated=True)
nextPageToken = _messages.StringField(3)
class ListJobsResponse(_messages.Message):
r"""Response to a request to list Cloud Dataflow jobs. This may be a
partial response, depending on the page size in the ListJobsRequest.
Fields:
failedLocation: Zero or more messages describing the [regional endpoints]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that failed to respond.
jobs: A subset of the requested job information.
nextPageToken: Set if there may be more results than fit in this response.
"""
failedLocation = _messages.MessageField('FailedLocation', 1, repeated=True)
jobs = _messages.MessageField('Job', 2, repeated=True)
nextPageToken = _messages.StringField(3)
class ListSnapshotsResponse(_messages.Message):
r"""List of snapshots.
Fields:
snapshots: Returned snapshots.
"""
snapshots = _messages.MessageField('Snapshot', 1, repeated=True)
class MapTask(_messages.Message):
r"""MapTask consists of an ordered set of instructions, each of which
describes one particular low-level operation for the worker to perform in
order to accomplish the MapTask's WorkItem. Each instruction must appear in
the list before any instructions which depends on its output.
Fields:
counterPrefix: Counter prefix that can be used to prefix counters. Not
currently used in Dataflow.
instructions: The instructions in the MapTask.
stageName: System-defined name of the stage containing this MapTask.
Unique across the workflow.
systemName: System-defined name of this MapTask. Unique across the
workflow.
"""
counterPrefix = _messages.StringField(1)
instructions = _messages.MessageField('ParallelInstruction', 2, repeated=True)
stageName = _messages.StringField(3)
systemName = _messages.StringField(4)
class MetricShortId(_messages.Message):
r"""The metric short id is returned to the user alongside an offset into
ReportWorkItemStatusRequest
Fields:
metricIndex: The index of the corresponding metric in the
ReportWorkItemStatusRequest. Required.
shortId: The service-generated short identifier for the metric.
"""
metricIndex = _messages.IntegerField(1, variant=_messages.Variant.INT32)
shortId = _messages.IntegerField(2)
class MetricStructuredName(_messages.Message):
r"""Identifies a metric, by describing the source which generated the
metric.
Messages:
ContextValue: Zero or more labeled fields which identify the part of the
job this metric is associated with, such as the name of a step or
collection. For example, built-in counters associated with steps will
have context['step'] = <step-name>. Counters associated with
PCollections in the SDK will have context['pcollection'] = <pcollection-
name>.
Fields:
context: Zero or more labeled fields which identify the part of the job
this metric is associated with, such as the name of a step or
collection. For example, built-in counters associated with steps will
have context['step'] = <step-name>. Counters associated with
PCollections in the SDK will have context['pcollection'] = <pcollection-
name>.
name: Worker-defined metric name.
origin: Origin (namespace) of metric name. May be blank for user-define
metrics; will be "dataflow" for metrics defined by the Dataflow service
or SDK.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class ContextValue(_messages.Message):
r"""Zero or more labeled fields which identify the part of the job this
metric is associated with, such as the name of a step or collection. For
example, built-in counters associated with steps will have context['step']
= <step-name>. Counters associated with PCollections in the SDK will have
context['pcollection'] = <pcollection-name>.
Messages:
AdditionalProperty: An additional property for a ContextValue object.
Fields:
additionalProperties: Additional properties of type ContextValue
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a ContextValue object.
Fields:
key: Name of the additional property.
value: A string attribute.
"""
key = _messages.StringField(1)
value = _messages.StringField(2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
context = _messages.MessageField('ContextValue', 1)
name = _messages.StringField(2)
origin = _messages.StringField(3)
class MetricUpdate(_messages.Message):
r"""Describes the state of a metric.
Fields:
cumulative: True if this metric is reported as the total cumulative
aggregate value accumulated since the worker started working on this
WorkItem. By default this is false, indicating that this metric is
reported as a delta that is not associated with any WorkItem.
distribution: A struct value describing properties of a distribution of
numeric values.
gauge: A struct value describing properties of a Gauge. Metrics of gauge
type show the value of a metric across time, and is aggregated based on
the newest value.
internal: Worker-computed aggregate value for internal use by the Dataflow
service.
kind: Metric aggregation kind. The possible metric aggregation kinds are
"Sum", "Max", "Min", "Mean", "Set", "And", "Or", and "Distribution". The
specified aggregation kind is case-insensitive. If omitted, this is not
an aggregated value but instead a single metric sample value.
meanCount: Worker-computed aggregate value for the "Mean" aggregation
kind. This holds the count of the aggregated values and is used in
combination with mean_sum above to obtain the actual mean aggregate
value. The only possible value type is Long.
meanSum: Worker-computed aggregate value for the "Mean" aggregation kind.
This holds the sum of the aggregated values and is used in combination
with mean_count below to obtain the actual mean aggregate value. The
only possible value types are Long and Double.
name: Name of the metric.
scalar: Worker-computed aggregate value for aggregation kinds "Sum",
"Max", "Min", "And", and "Or". The possible value types are Long,
Double, and Boolean.
set: Worker-computed aggregate value for the "Set" aggregation kind. The
only possible value type is a list of Values whose type can be Long,
Double, or String, according to the metric's type. All Values in the
list must be of the same type.
updateTime: Timestamp associated with the metric value. Optional when
workers are reporting work progress; it will be filled in responses from
the metrics API.
"""
cumulative = _messages.BooleanField(1)
distribution = _messages.MessageField('extra_types.JsonValue', 2)
gauge = _messages.MessageField('extra_types.JsonValue', 3)
internal = _messages.MessageField('extra_types.JsonValue', 4)
kind = _messages.StringField(5)
meanCount = _messages.MessageField('extra_types.JsonValue', 6)
meanSum = _messages.MessageField('extra_types.JsonValue', 7)
name = _messages.MessageField('MetricStructuredName', 8)
scalar = _messages.MessageField('extra_types.JsonValue', 9)
set = _messages.MessageField('extra_types.JsonValue', 10)
updateTime = _messages.StringField(11)
class MountedDataDisk(_messages.Message):
r"""Describes mounted data disk.
Fields:
dataDisk: The name of the data disk. This name is local to the Google
Cloud Platform project and uniquely identifies the disk within that
project, for example "myproject-1014-104817-4c2-harness-0-disk-1".
"""
dataDisk = _messages.StringField(1)
class MultiOutputInfo(_messages.Message):
r"""Information about an output of a multi-output DoFn.
Fields:
tag: The id of the tag the user code will emit to this output by; this
should correspond to the tag of some SideInputInfo.
"""
tag = _messages.StringField(1)
class NameAndKind(_messages.Message):
r"""Basic metadata about a counter.
Enums:
KindValueValuesEnum: Counter aggregation kind.
Fields:
kind: Counter aggregation kind.
name: Name of the counter.
"""
class KindValueValuesEnum(_messages.Enum):
r"""Counter aggregation kind.
Values:
INVALID: Counter aggregation kind was not set.
SUM: Aggregated value is the sum of all contributed values.
MAX: Aggregated value is the max of all contributed values.
MIN: Aggregated value is the min of all contributed values.
MEAN: Aggregated value is the mean of all contributed values.
OR: Aggregated value represents the logical 'or' of all contributed
values.
AND: Aggregated value represents the logical 'and' of all contributed
values.
SET: Aggregated value is a set of unique contributed values.
DISTRIBUTION: Aggregated value captures statistics about a distribution.
LATEST_VALUE: Aggregated value tracks the latest value of a variable.
"""
INVALID = 0
SUM = 1
MAX = 2
MIN = 3
MEAN = 4
OR = 5
AND = 6
SET = 7
DISTRIBUTION = 8
LATEST_VALUE = 9
kind = _messages.EnumField('KindValueValuesEnum', 1)
name = _messages.StringField(2)
class Package(_messages.Message):
r"""The packages that must be installed in order for a worker to run the
steps of the Cloud Dataflow job that will be assigned to its worker pool.
This is the mechanism by which the Cloud Dataflow SDK causes code to be
loaded onto the workers. For example, the Cloud Dataflow Java SDK might use
this to install jars containing the user's code and all of the various
dependencies (libraries, data files, etc.) required in order for that code
to run.
Fields:
location: The resource to read the package from. The supported resource
type is: Google Cloud Storage: storage.googleapis.com/{bucket}
bucket.storage.googleapis.com/
name: The name of the package.
"""
location = _messages.StringField(1)
name = _messages.StringField(2)
class ParDoInstruction(_messages.Message):
r"""An instruction that does a ParDo operation. Takes one main input and
zero or more side inputs, and produces zero or more outputs. Runs user code.
Messages:
UserFnValue: The user function to invoke.
Fields:
input: The input.
multiOutputInfos: Information about each of the outputs, if user_fn is a
MultiDoFn.
numOutputs: The number of outputs.
sideInputs: Zero or more side inputs.
userFn: The user function to invoke.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class UserFnValue(_messages.Message):
r"""The user function to invoke.
Messages:
AdditionalProperty: An additional property for a UserFnValue object.
Fields:
additionalProperties: Properties of the object.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a UserFnValue object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
input = _messages.MessageField('InstructionInput', 1)
multiOutputInfos = _messages.MessageField('MultiOutputInfo', 2, repeated=True)
numOutputs = _messages.IntegerField(3, variant=_messages.Variant.INT32)
sideInputs = _messages.MessageField('SideInputInfo', 4, repeated=True)
userFn = _messages.MessageField('UserFnValue', 5)
class ParallelInstruction(_messages.Message):
r"""Describes a particular operation comprising a MapTask.
Fields:
flatten: Additional information for Flatten instructions.
name: User-provided name of this operation.
originalName: System-defined name for the operation in the original
workflow graph.
outputs: Describes the outputs of the instruction.
parDo: Additional information for ParDo instructions.
partialGroupByKey: Additional information for PartialGroupByKey
instructions.
read: Additional information for Read instructions.
systemName: System-defined name of this operation. Unique across the
workflow.
write: Additional information for Write instructions.
"""
flatten = _messages.MessageField('FlattenInstruction', 1)
name = _messages.StringField(2)
originalName = _messages.StringField(3)
outputs = _messages.MessageField('InstructionOutput', 4, repeated=True)
parDo = _messages.MessageField('ParDoInstruction', 5)
partialGroupByKey = _messages.MessageField('PartialGroupByKeyInstruction', 6)
read = _messages.MessageField('ReadInstruction', 7)
systemName = _messages.StringField(8)
write = _messages.MessageField('WriteInstruction', 9)
class Parameter(_messages.Message):
r"""Structured data associated with this message.
Fields:
key: Key or name for this parameter.
value: Value for this parameter.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
class ParameterMetadata(_messages.Message):
r"""Metadata for a specific parameter.
Fields:
helpText: Required. The help text to display for the parameter.
isOptional: Optional. Whether the parameter is optional. Defaults to
false.
label: Required. The label to display for the parameter.
name: Required. The name of the parameter.
regexes: Optional. Regexes that the parameter must match.
"""
helpText = _messages.StringField(1)
isOptional = _messages.BooleanField(2)
label = _messages.StringField(3)
name = _messages.StringField(4)
regexes = _messages.StringField(5, repeated=True)
class PartialGroupByKeyInstruction(_messages.Message):
r"""An instruction that does a partial group-by-key. One input and one
output.
Messages:
InputElementCodecValue: The codec to use for interpreting an element in
the input PTable.
ValueCombiningFnValue: The value combining function to invoke.
Fields:
input: Describes the input to the partial group-by-key instruction.
inputElementCodec: The codec to use for interpreting an element in the
input PTable.
originalCombineValuesInputStoreName: If this instruction includes a
combining function this is the name of the intermediate store between
the GBK and the CombineValues.
originalCombineValuesStepName: If this instruction includes a combining
function, this is the name of the CombineValues instruction lifted into
this instruction.
sideInputs: Zero or more side inputs.
valueCombiningFn: The value combining function to invoke.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class InputElementCodecValue(_messages.Message):
r"""The codec to use for interpreting an element in the input PTable.
Messages:
AdditionalProperty: An additional property for a InputElementCodecValue
object.
Fields:
additionalProperties: Properties of the object.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a InputElementCodecValue object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
@encoding.MapUnrecognizedFields('additionalProperties')
class ValueCombiningFnValue(_messages.Message):
r"""The value combining function to invoke.
Messages:
AdditionalProperty: An additional property for a ValueCombiningFnValue
object.
Fields:
additionalProperties: Properties of the object.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a ValueCombiningFnValue object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
input = _messages.MessageField('InstructionInput', 1)
inputElementCodec = _messages.MessageField('InputElementCodecValue', 2)
originalCombineValuesInputStoreName = _messages.StringField(3)
originalCombineValuesStepName = _messages.StringField(4)
sideInputs = _messages.MessageField('SideInputInfo', 5, repeated=True)
valueCombiningFn = _messages.MessageField('ValueCombiningFnValue', 6)
class PipelineDescription(_messages.Message):
r"""A descriptive representation of submitted pipeline as well as the
executed form. This data is provided by the Dataflow service for ease of
visualizing the pipeline and interpreting Dataflow provided metrics.
Fields:
displayData: Pipeline level display data.
executionPipelineStage: Description of each stage of execution of the
pipeline.
originalPipelineTransform: Description of each transform in the pipeline
and collections between them.
"""
displayData = _messages.MessageField('DisplayData', 1, repeated=True)
executionPipelineStage = _messages.MessageField('ExecutionStageSummary', 2, repeated=True)
originalPipelineTransform = _messages.MessageField('TransformSummary', 3, repeated=True)
class Position(_messages.Message):
r"""Position defines a position within a collection of data. The value can
be either the end position, a key (used with ordered collections), a byte
offset, or a record index.
Fields:
byteOffset: Position is a byte offset.
concatPosition: CloudPosition is a concat position.
end: Position is past all other positions. Also useful for the end
position of an unbounded range.
key: Position is a string key, ordered lexicographically.
recordIndex: Position is a record index.
shufflePosition: CloudPosition is a base64 encoded BatchShufflePosition
(with FIXED sharding).
"""
byteOffset = _messages.IntegerField(1)
concatPosition = _messages.MessageField('ConcatPosition', 2)
end = _messages.BooleanField(3)
key = _messages.StringField(4)
recordIndex = _messages.IntegerField(5)
shufflePosition = _messages.StringField(6)
class PubSubIODetails(_messages.Message):
r"""Metadata for a PubSub connector used by the job.
Fields:
subscription: Subscription used in the connection.
topic: Topic accessed in the connection.
"""
subscription = _messages.StringField(1)
topic = _messages.StringField(2)
class PubsubLocation(_messages.Message):
r"""Identifies a pubsub location to use for transferring data into or out of
a streaming Dataflow job.
Fields:
dropLateData: Indicates whether the pipeline allows late-arriving data.
idLabel: If set, contains a pubsub label from which to extract record ids.
If left empty, record deduplication will be strictly best effort.
subscription: A pubsub subscription, in the form of
"pubsub.googleapis.com/subscriptions/<project-id>/<subscription-name>"
timestampLabel: If set, contains a pubsub label from which to extract
record timestamps. If left empty, record timestamps will be generated
upon arrival.
topic: A pubsub topic, in the form of "pubsub.googleapis.com/topics
/<project-id>/<topic-name>"
trackingSubscription: If set, specifies the pubsub subscription that will
be used for tracking custom time timestamps for watermark estimation.
withAttributes: If true, then the client has requested to get pubsub
attributes.
"""
dropLateData = _messages.BooleanField(1)
idLabel = _messages.StringField(2)
subscription = _messages.StringField(3)
timestampLabel = _messages.StringField(4)
topic = _messages.StringField(5)
trackingSubscription = _messages.StringField(6)
withAttributes = _messages.BooleanField(7)
class ReadInstruction(_messages.Message):
r"""An instruction that reads records. Takes no inputs, produces one output.
Fields:
source: The source to read from.
"""
source = _messages.MessageField('Source', 1)
class ReportWorkItemStatusRequest(_messages.Message):
r"""Request to report the status of WorkItems.
Messages:
UnifiedWorkerRequestValue: Untranslated bag-of-bytes
WorkProgressUpdateRequest from UnifiedWorker.
Fields:
currentWorkerTime: The current timestamp at the worker.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains the WorkItem's job.
unifiedWorkerRequest: Untranslated bag-of-bytes WorkProgressUpdateRequest
from UnifiedWorker.
workItemStatuses: The order is unimportant, except that the order of the
WorkItemServiceState messages in the ReportWorkItemStatusResponse
corresponds to the order of WorkItemStatus messages here.
workerId: The ID of the worker reporting the WorkItem status. If this
does not match the ID of the worker which the Dataflow service believes
currently has the lease on the WorkItem, the report will be dropped
(with an error response).
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class UnifiedWorkerRequestValue(_messages.Message):
r"""Untranslated bag-of-bytes WorkProgressUpdateRequest from
UnifiedWorker.
Messages:
AdditionalProperty: An additional property for a
UnifiedWorkerRequestValue object.
Fields:
additionalProperties: Properties of the object. Contains field @type
with type URL.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a UnifiedWorkerRequestValue object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
currentWorkerTime = _messages.StringField(1)
location = _messages.StringField(2)
unifiedWorkerRequest = _messages.MessageField('UnifiedWorkerRequestValue', 3)
workItemStatuses = _messages.MessageField('WorkItemStatus', 4, repeated=True)
workerId = _messages.StringField(5)
class ReportWorkItemStatusResponse(_messages.Message):
r"""Response from a request to report the status of WorkItems.
Messages:
UnifiedWorkerResponseValue: Untranslated bag-of-bytes
WorkProgressUpdateResponse for UnifiedWorker.
Fields:
unifiedWorkerResponse: Untranslated bag-of-bytes
WorkProgressUpdateResponse for UnifiedWorker.
workItemServiceStates: A set of messages indicating the service-side state
for each WorkItem whose status was reported, in the same order as the
WorkItemStatus messages in the ReportWorkItemStatusRequest which
resulting in this response.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class UnifiedWorkerResponseValue(_messages.Message):
r"""Untranslated bag-of-bytes WorkProgressUpdateResponse for
UnifiedWorker.
Messages:
AdditionalProperty: An additional property for a
UnifiedWorkerResponseValue object.
Fields:
additionalProperties: Properties of the object. Contains field @type
with type URL.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a UnifiedWorkerResponseValue object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
unifiedWorkerResponse = _messages.MessageField('UnifiedWorkerResponseValue', 1)
workItemServiceStates = _messages.MessageField('WorkItemServiceState', 2, repeated=True)
class ReportedParallelism(_messages.Message):
r"""Represents the level of parallelism in a WorkItem's input, reported by
the worker.
Fields:
isInfinite: Specifies whether the parallelism is infinite. If true,
"value" is ignored. Infinite parallelism means the service will assume
that the work item can always be split into more non-empty work items by
dynamic splitting. This is a work-around for lack of support for
infinity by the current JSON-based Java RPC stack.
value: Specifies the level of parallelism in case it is finite.
"""
isInfinite = _messages.BooleanField(1)
value = _messages.FloatField(2)
class ResourceUtilizationReport(_messages.Message):
r"""Worker metrics exported from workers. This contains resource utilization
metrics accumulated from a variety of sources. For more information, see go
/df-resource-signals.
Fields:
cpuTime: CPU utilization samples.
"""
cpuTime = _messages.MessageField('CPUTime', 1, repeated=True)
class ResourceUtilizationReportResponse(_messages.Message):
r"""Service-side response to WorkerMessage reporting resource utilization.
"""
class RuntimeEnvironment(_messages.Message):
r"""The environment values to set at runtime.
Messages:
AdditionalUserLabelsValue: Additional user labels to be specified for the
job. Keys and values should follow the restrictions specified in the
[labeling restrictions](https://cloud.google.com/compute/docs/labeling-
resources#restrictions) page.
Fields:
additionalExperiments: Additional experiment flags for the job.
additionalUserLabels: Additional user labels to be specified for the job.
Keys and values should follow the restrictions specified in the
[labeling restrictions](https://cloud.google.com/compute/docs/labeling-
resources#restrictions) page.
bypassTempDirValidation: Whether to bypass the safety checks for the job's
temporary directory. Use with caution.
machineType: The machine type to use for the job. Defaults to the value
from the template if not specified.
maxWorkers: The maximum number of Google Compute Engine instances to be
made available to your pipeline during execution, from 1 to 1000.
network: Network to which VMs will be assigned. If empty or unspecified,
the service will use the network "default".
numWorkers: The initial number of Google Compute Engine instnaces for the
job.
serviceAccountEmail: The email address of the service account to run the
job as.
subnetwork: Subnetwork to which VMs will be assigned, if desired.
Expected to be of the form "regions/REGION/subnetworks/SUBNETWORK".
tempLocation: The Cloud Storage path to use for temporary files. Must be a
valid Cloud Storage URL, beginning with `gs://`.
zone: The Compute Engine [availability
zone](https://cloud.google.com/compute/docs/regions-zones/regions-zones)
for launching worker instances to run your pipeline.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class AdditionalUserLabelsValue(_messages.Message):
r"""Additional user labels to be specified for the job. Keys and values
should follow the restrictions specified in the [labeling
restrictions](https://cloud.google.com/compute/docs/labeling-
resources#restrictions) page.
Messages:
AdditionalProperty: An additional property for a
AdditionalUserLabelsValue object.
Fields:
additionalProperties: Additional properties of type
AdditionalUserLabelsValue
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a AdditionalUserLabelsValue object.
Fields:
key: Name of the additional property.
value: A string attribute.
"""
key = _messages.StringField(1)
value = _messages.StringField(2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
additionalExperiments = _messages.StringField(1, repeated=True)
additionalUserLabels = _messages.MessageField('AdditionalUserLabelsValue', 2)
bypassTempDirValidation = _messages.BooleanField(3)
machineType = _messages.StringField(4)
maxWorkers = _messages.IntegerField(5, variant=_messages.Variant.INT32)
network = _messages.StringField(6)
numWorkers = _messages.IntegerField(7, variant=_messages.Variant.INT32)
serviceAccountEmail = _messages.StringField(8)
subnetwork = _messages.StringField(9)
tempLocation = _messages.StringField(10)
zone = _messages.StringField(11)
class SdkVersion(_messages.Message):
r"""The version of the SDK used to run the job.
Enums:
SdkSupportStatusValueValuesEnum: The support status for this SDK version.
Fields:
sdkSupportStatus: The support status for this SDK version.
version: The version of the SDK used to run the job.
versionDisplayName: A readable string describing the version of the SDK.
"""
class SdkSupportStatusValueValuesEnum(_messages.Enum):
r"""The support status for this SDK version.
Values:
UNKNOWN: Cloud Dataflow is unaware of this version.
SUPPORTED: This is a known version of an SDK, and is supported.
STALE: A newer version of the SDK family exists, and an update is
recommended.
DEPRECATED: This version of the SDK is deprecated and will eventually be
no longer supported.
UNSUPPORTED: Support for this SDK version has ended and it should no
longer be used.
"""
UNKNOWN = 0
SUPPORTED = 1
STALE = 2
DEPRECATED = 3
UNSUPPORTED = 4
sdkSupportStatus = _messages.EnumField('SdkSupportStatusValueValuesEnum', 1)
version = _messages.StringField(2)
versionDisplayName = _messages.StringField(3)
class SendDebugCaptureRequest(_messages.Message):
r"""Request to send encoded debug information.
Fields:
componentId: The internal component id for which debug information is
sent.
data: The encoded debug information.
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains the job specified by job_id.
workerId: The worker id, i.e., VM hostname.
"""
componentId = _messages.StringField(1)
data = _messages.StringField(2)
location = _messages.StringField(3)
workerId = _messages.StringField(4)
class SendDebugCaptureResponse(_messages.Message):
r"""Response to a send capture request.
nothing"""
class SendWorkerMessagesRequest(_messages.Message):
r"""A request for sending worker messages to the service.
Fields:
location: The [regional endpoint]
(https://cloud.google.com/dataflow/docs/concepts/regional-endpoints)
that contains the job.
workerMessages: The WorkerMessages to send.
"""
location = _messages.StringField(1)
workerMessages = _messages.MessageField('WorkerMessage', 2, repeated=True)
class SendWorkerMessagesResponse(_messages.Message):
r"""The response to the worker messages.
Fields:
workerMessageResponses: The servers response to the worker messages.
"""
workerMessageResponses = _messages.MessageField('WorkerMessageResponse', 1, repeated=True)
class SeqMapTask(_messages.Message):
r"""Describes a particular function to invoke.
Messages:
UserFnValue: The user function to invoke.
Fields:
inputs: Information about each of the inputs.
name: The user-provided name of the SeqDo operation.
outputInfos: Information about each of the outputs.
stageName: System-defined name of the stage containing the SeqDo
operation. Unique across the workflow.
systemName: System-defined name of the SeqDo operation. Unique across the
workflow.
userFn: The user function to invoke.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class UserFnValue(_messages.Message):
r"""The user function to invoke.
Messages:
AdditionalProperty: An additional property for a UserFnValue object.
Fields:
additionalProperties: Properties of the object.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a UserFnValue object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
inputs = _messages.MessageField('SideInputInfo', 1, repeated=True)
name = _messages.StringField(2)
outputInfos = _messages.MessageField('SeqMapTaskOutputInfo', 3, repeated=True)
stageName = _messages.StringField(4)
systemName = _messages.StringField(5)
userFn = _messages.MessageField('UserFnValue', 6)
class SeqMapTaskOutputInfo(_messages.Message):
r"""Information about an output of a SeqMapTask.
Fields:
sink: The sink to write the output value to.
tag: The id of the TupleTag the user code will tag the output value by.
"""
sink = _messages.MessageField('Sink', 1)
tag = _messages.StringField(2)
class ShellTask(_messages.Message):
r"""A task which consists of a shell command for the worker to execute.
Fields:
command: The shell command to run.
exitCode: Exit code for the task.
"""
command = _messages.StringField(1)
exitCode = _messages.IntegerField(2, variant=_messages.Variant.INT32)
class SideInputInfo(_messages.Message):
r"""Information about a side input of a DoFn or an input of a SeqDoFn.
Messages:
KindValue: How to interpret the source element(s) as a side input value.
Fields:
kind: How to interpret the source element(s) as a side input value.
sources: The source(s) to read element(s) from to get the value of this
side input. If more than one source, then the elements are taken from
the sources, in the specified order if order matters. At least one
source is required.
tag: The id of the tag the user code will access this side input by; this
should correspond to the tag of some MultiOutputInfo.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class KindValue(_messages.Message):
r"""How to interpret the source element(s) as a side input value.
Messages:
AdditionalProperty: An additional property for a KindValue object.
Fields:
additionalProperties: Properties of the object.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a KindValue object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
kind = _messages.MessageField('KindValue', 1)
sources = _messages.MessageField('Source', 2, repeated=True)
tag = _messages.StringField(3)
class Sink(_messages.Message):
r"""A sink that records can be encoded and written to.
Messages:
CodecValue: The codec to use to encode data written to the sink.
SpecValue: The sink to write to, plus its parameters.
Fields:
codec: The codec to use to encode data written to the sink.
spec: The sink to write to, plus its parameters.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class CodecValue(_messages.Message):
r"""The codec to use to encode data written to the sink.
Messages:
AdditionalProperty: An additional property for a CodecValue object.
Fields:
additionalProperties: Properties of the object.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a CodecValue object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
@encoding.MapUnrecognizedFields('additionalProperties')
class SpecValue(_messages.Message):
r"""The sink to write to, plus its parameters.
Messages:
AdditionalProperty: An additional property for a SpecValue object.
Fields:
additionalProperties: Properties of the object.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a SpecValue object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
codec = _messages.MessageField('CodecValue', 1)
spec = _messages.MessageField('SpecValue', 2)
class Snapshot(_messages.Message):
r"""Represents a snapshot of a job.
Enums:
StateValueValuesEnum: State of the snapshot.
Fields:
creationTime: The time this snapshot was created.
id: The unique ID of this snapshot.
projectId: The project this snapshot belongs to.
sourceJobId: The job this snapshot was created from.
state: State of the snapshot.
ttl: The time after which this snapshot will be automatically deleted.
"""
class StateValueValuesEnum(_messages.Enum):
r"""State of the snapshot.
Values:
UNKNOWN_SNAPSHOT_STATE: Unknown state.
PENDING: Snapshot intent to create has been persisted, snapshotting of
state has not yet started.
RUNNING: Snapshotting is being performed.
READY: Snapshot has been created and is ready to be used.
FAILED: Snapshot failed to be created.
DELETED: Snapshot has been deleted.
"""
UNKNOWN_SNAPSHOT_STATE = 0
PENDING = 1
RUNNING = 2
READY = 3
FAILED = 4
DELETED = 5
creationTime = _messages.StringField(1)
id = _messages.StringField(2)
projectId = _messages.StringField(3)
sourceJobId = _messages.StringField(4)
state = _messages.EnumField('StateValueValuesEnum', 5)
ttl = _messages.StringField(6)
class SnapshotJobRequest(_messages.Message):
r"""Request to create a snapshot of a job.
Fields:
location: The location that contains this job.
ttl: TTL for the snapshot.
"""
location = _messages.StringField(1)
ttl = _messages.StringField(2)
class Source(_messages.Message):
r"""A source that records can be read and decoded from.
Messages:
BaseSpecsValueListEntry: A BaseSpecsValueListEntry object.
CodecValue: The codec to use to decode data read from the source.
SpecValue: The source to read from, plus its parameters.
Fields:
baseSpecs: While splitting, sources may specify the produced bundles as
differences against another source, in order to save backend-side memory
and allow bigger jobs. For details, see SourceSplitRequest. To support
this use case, the full set of parameters of the source is logically
obtained by taking the latest explicitly specified value of each
parameter in the order: base_specs (later items win), spec (overrides
anything in base_specs).
codec: The codec to use to decode data read from the source.
doesNotNeedSplitting: Setting this value to true hints to the framework
that the source doesn't need splitting, and using SourceSplitRequest on
it would yield SOURCE_SPLIT_OUTCOME_USE_CURRENT. E.g. a file splitter
may set this to true when splitting a single file into a set of byte
ranges of appropriate size, and set this to false when splitting a
filepattern into individual files. However, for efficiency, a file
splitter may decide to produce file subranges directly from the
filepattern to avoid a splitting round-trip. See SourceSplitRequest for
an overview of the splitting process. This field is meaningful only in
the Source objects populated by the user (e.g. when filling in a
DerivedSource). Source objects supplied by the framework to the user
don't have this field populated.
metadata: Optionally, metadata for this source can be supplied right away,
avoiding a SourceGetMetadataOperation roundtrip (see
SourceOperationRequest). This field is meaningful only in the Source
objects populated by the user (e.g. when filling in a DerivedSource).
Source objects supplied by the framework to the user don't have this
field populated.
spec: The source to read from, plus its parameters.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class BaseSpecsValueListEntry(_messages.Message):
r"""A BaseSpecsValueListEntry object.
Messages:
AdditionalProperty: An additional property for a BaseSpecsValueListEntry
object.
Fields:
additionalProperties: Properties of the object.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a BaseSpecsValueListEntry object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
@encoding.MapUnrecognizedFields('additionalProperties')
class CodecValue(_messages.Message):
r"""The codec to use to decode data read from the source.
Messages:
AdditionalProperty: An additional property for a CodecValue object.
Fields:
additionalProperties: Properties of the object.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a CodecValue object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
@encoding.MapUnrecognizedFields('additionalProperties')
class SpecValue(_messages.Message):
r"""The source to read from, plus its parameters.
Messages:
AdditionalProperty: An additional property for a SpecValue object.
Fields:
additionalProperties: Properties of the object.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a SpecValue object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
baseSpecs = _messages.MessageField('BaseSpecsValueListEntry', 1, repeated=True)
codec = _messages.MessageField('CodecValue', 2)
doesNotNeedSplitting = _messages.BooleanField(3)
metadata = _messages.MessageField('SourceMetadata', 4)
spec = _messages.MessageField('SpecValue', 5)
class SourceFork(_messages.Message):
r"""DEPRECATED in favor of DynamicSourceSplit.
Fields:
primary: DEPRECATED
primarySource: DEPRECATED
residual: DEPRECATED
residualSource: DEPRECATED
"""
primary = _messages.MessageField('SourceSplitShard', 1)
primarySource = _messages.MessageField('DerivedSource', 2)
residual = _messages.MessageField('SourceSplitShard', 3)
residualSource = _messages.MessageField('DerivedSource', 4)
class SourceGetMetadataRequest(_messages.Message):
r"""A request to compute the SourceMetadata of a Source.
Fields:
source: Specification of the source whose metadata should be computed.
"""
source = _messages.MessageField('Source', 1)
class SourceGetMetadataResponse(_messages.Message):
r"""The result of a SourceGetMetadataOperation.
Fields:
metadata: The computed metadata.
"""
metadata = _messages.MessageField('SourceMetadata', 1)
class SourceMetadata(_messages.Message):
r"""Metadata about a Source useful for automatically optimizing and tuning
the pipeline, etc.
Fields:
estimatedSizeBytes: An estimate of the total size (in bytes) of the data
that would be read from this source. This estimate is in terms of
external storage size, before any decompression or other processing done
by the reader.
infinite: Specifies that the size of this source is known to be infinite
(this is a streaming source).
producesSortedKeys: Whether this source is known to produce key/value
pairs with the (encoded) keys in lexicographically sorted order.
"""
estimatedSizeBytes = _messages.IntegerField(1)
infinite = _messages.BooleanField(2)
producesSortedKeys = _messages.BooleanField(3)
class SourceOperationRequest(_messages.Message):
r"""A work item that represents the different operations that can be
performed on a user-defined Source specification.
Fields:
getMetadata: Information about a request to get metadata about a source.
name: User-provided name of the Read instruction for this source.
originalName: System-defined name for the Read instruction for this source
in the original workflow graph.
split: Information about a request to split a source.
stageName: System-defined name of the stage containing the source
operation. Unique across the workflow.
systemName: System-defined name of the Read instruction for this source.
Unique across the workflow.
"""
getMetadata = _messages.MessageField('SourceGetMetadataRequest', 1)
name = _messages.StringField(2)
originalName = _messages.StringField(3)
split = _messages.MessageField('SourceSplitRequest', 4)
stageName = _messages.StringField(5)
systemName = _messages.StringField(6)
class SourceOperationResponse(_messages.Message):
r"""The result of a SourceOperationRequest, specified in
ReportWorkItemStatusRequest.source_operation when the work item is
completed.
Fields:
getMetadata: A response to a request to get metadata about a source.
split: A response to a request to split a source.
"""
getMetadata = _messages.MessageField('SourceGetMetadataResponse', 1)
split = _messages.MessageField('SourceSplitResponse', 2)
class SourceSplitOptions(_messages.Message):
r"""Hints for splitting a Source into bundles (parts for parallel
processing) using SourceSplitRequest.
Fields:
desiredBundleSizeBytes: The source should be split into a set of bundles
where the estimated size of each is approximately this many bytes.
desiredShardSizeBytes: DEPRECATED in favor of desired_bundle_size_bytes.
"""
desiredBundleSizeBytes = _messages.IntegerField(1)
desiredShardSizeBytes = _messages.IntegerField(2)
class SourceSplitRequest(_messages.Message):
r"""Represents the operation to split a high-level Source specification into
bundles (parts for parallel processing). At a high level, splitting of a
source into bundles happens as follows: SourceSplitRequest is applied to the
source. If it returns SOURCE_SPLIT_OUTCOME_USE_CURRENT, no further splitting
happens and the source is used "as is". Otherwise, splitting is applied
recursively to each produced DerivedSource. As an optimization, for any
Source, if its does_not_need_splitting is true, the framework assumes that
splitting this source would return SOURCE_SPLIT_OUTCOME_USE_CURRENT, and
doesn't initiate a SourceSplitRequest. This applies both to the initial
source being split and to bundles produced from it.
Fields:
options: Hints for tuning the splitting process.
source: Specification of the source to be split.
"""
options = _messages.MessageField('SourceSplitOptions', 1)
source = _messages.MessageField('Source', 2)
class SourceSplitResponse(_messages.Message):
r"""The response to a SourceSplitRequest.
Enums:
OutcomeValueValuesEnum: Indicates whether splitting happened and produced
a list of bundles. If this is USE_CURRENT_SOURCE_AS_IS, the current
source should be processed "as is" without splitting. "bundles" is
ignored in this case. If this is SPLITTING_HAPPENED, then "bundles"
contains a list of bundles into which the source was split.
Fields:
bundles: If outcome is SPLITTING_HAPPENED, then this is a list of bundles
into which the source was split. Otherwise this field is ignored. This
list can be empty, which means the source represents an empty input.
outcome: Indicates whether splitting happened and produced a list of
bundles. If this is USE_CURRENT_SOURCE_AS_IS, the current source should
be processed "as is" without splitting. "bundles" is ignored in this
case. If this is SPLITTING_HAPPENED, then "bundles" contains a list of
bundles into which the source was split.
shards: DEPRECATED in favor of bundles.
"""
class OutcomeValueValuesEnum(_messages.Enum):
r"""Indicates whether splitting happened and produced a list of bundles.
If this is USE_CURRENT_SOURCE_AS_IS, the current source should be
processed "as is" without splitting. "bundles" is ignored in this case. If
this is SPLITTING_HAPPENED, then "bundles" contains a list of bundles into
which the source was split.
Values:
SOURCE_SPLIT_OUTCOME_UNKNOWN: The source split outcome is unknown, or
unspecified.
SOURCE_SPLIT_OUTCOME_USE_CURRENT: The current source should be processed
"as is" without splitting.
SOURCE_SPLIT_OUTCOME_SPLITTING_HAPPENED: Splitting produced a list of
bundles.
"""
SOURCE_SPLIT_OUTCOME_UNKNOWN = 0
SOURCE_SPLIT_OUTCOME_USE_CURRENT = 1
SOURCE_SPLIT_OUTCOME_SPLITTING_HAPPENED = 2
bundles = _messages.MessageField('DerivedSource', 1, repeated=True)
outcome = _messages.EnumField('OutcomeValueValuesEnum', 2)
shards = _messages.MessageField('SourceSplitShard', 3, repeated=True)
class SourceSplitShard(_messages.Message):
r"""DEPRECATED in favor of DerivedSource.
Enums:
DerivationModeValueValuesEnum: DEPRECATED
Fields:
derivationMode: DEPRECATED
source: DEPRECATED
"""
class DerivationModeValueValuesEnum(_messages.Enum):
r"""DEPRECATED
Values:
SOURCE_DERIVATION_MODE_UNKNOWN: The source derivation is unknown, or
unspecified.
SOURCE_DERIVATION_MODE_INDEPENDENT: Produce a completely independent
Source with no base.
SOURCE_DERIVATION_MODE_CHILD_OF_CURRENT: Produce a Source based on the
Source being split.
SOURCE_DERIVATION_MODE_SIBLING_OF_CURRENT: Produce a Source based on the
base of the Source being split.
"""
SOURCE_DERIVATION_MODE_UNKNOWN = 0
SOURCE_DERIVATION_MODE_INDEPENDENT = 1
SOURCE_DERIVATION_MODE_CHILD_OF_CURRENT = 2
SOURCE_DERIVATION_MODE_SIBLING_OF_CURRENT = 3
derivationMode = _messages.EnumField('DerivationModeValueValuesEnum', 1)
source = _messages.MessageField('Source', 2)
class SpannerIODetails(_messages.Message):
r"""Metadata for a Spanner connector used by the job.
Fields:
databaseId: DatabaseId accessed in the connection.
instanceId: InstanceId accessed in the connection.
projectId: ProjectId accessed in the connection.
"""
databaseId = _messages.StringField(1)
instanceId = _messages.StringField(2)
projectId = _messages.StringField(3)
class SplitInt64(_messages.Message):
r"""A representation of an int64, n, that is immune to precision loss when
encoded in JSON.
Fields:
highBits: The high order bits, including the sign: n >> 32.
lowBits: The low order bits: n & 0xffffffff.
"""
highBits = _messages.IntegerField(1, variant=_messages.Variant.INT32)
lowBits = _messages.IntegerField(2, variant=_messages.Variant.UINT32)
class StageSource(_messages.Message):
r"""Description of an input or output of an execution stage.
Fields:
name: Dataflow service generated name for this source.
originalTransformOrCollection: User name for the original user transform
or collection with which this source is most closely associated.
sizeBytes: Size of the source, if measurable.
userName: Human-readable name for this source; may be user or system
generated.
"""
name = _messages.StringField(1)
originalTransformOrCollection = _messages.StringField(2)
sizeBytes = _messages.IntegerField(3)
userName = _messages.StringField(4)
class StandardQueryParameters(_messages.Message):
r"""Query parameters accepted by all methods.
Enums:
FXgafvValueValuesEnum: V1 error format.
AltValueValuesEnum: Data format for response.
Fields:
f__xgafv: V1 error format.
access_token: OAuth access token.
alt: Data format for response.
callback: JSONP
fields: Selector specifying which fields to include in a partial response.
key: API key. Your API key identifies your project and provides you with
API access, quota, and reports. Required unless you provide an OAuth 2.0
token.
oauth_token: OAuth 2.0 token for the current user.
prettyPrint: Returns response with indentations and line breaks.
quotaUser: Available to use for quota purposes for server-side
applications. Can be any arbitrary string assigned to a user, but should
not exceed 40 characters.
trace: A tracing token of the form "token:<tokenid>" to include in api
requests.
uploadType: Legacy upload protocol for media (e.g. "media", "multipart").
upload_protocol: Upload protocol for media (e.g. "raw", "multipart").
"""
class AltValueValuesEnum(_messages.Enum):
r"""Data format for response.
Values:
json: Responses with Content-Type of application/json
media: Media download with context-dependent Content-Type
proto: Responses with Content-Type of application/x-protobuf
"""
json = 0
media = 1
proto = 2
class FXgafvValueValuesEnum(_messages.Enum):
r"""V1 error format.
Values:
_1: v1 error format
_2: v2 error format
"""
_1 = 0
_2 = 1
f__xgafv = _messages.EnumField('FXgafvValueValuesEnum', 1)
access_token = _messages.StringField(2)
alt = _messages.EnumField('AltValueValuesEnum', 3, default=u'json')
callback = _messages.StringField(4)
fields = _messages.StringField(5)
key = _messages.StringField(6)
oauth_token = _messages.StringField(7)
prettyPrint = _messages.BooleanField(8, default=True)
quotaUser = _messages.StringField(9)
trace = _messages.StringField(10)
uploadType = _messages.StringField(11)
upload_protocol = _messages.StringField(12)
class StateFamilyConfig(_messages.Message):
r"""State family configuration.
Fields:
isRead: If true, this family corresponds to a read operation.
stateFamily: The state family value.
"""
isRead = _messages.BooleanField(1)
stateFamily = _messages.StringField(2)
class Status(_messages.Message):
r"""The `Status` type defines a logical error model that is suitable for
different programming environments, including REST APIs and RPC APIs. It is
used by [gRPC](https://github.com/grpc). The error model is designed to be:
- Simple to use and understand for most users - Flexible enough to meet
unexpected needs # Overview The `Status` message contains three pieces of
data: error code, error message, and error details. The error code should be
an enum value of google.rpc.Code, but it may accept additional error codes
if needed. The error message should be a developer-facing English message
that helps developers *understand* and *resolve* the error. If a localized
user-facing error message is needed, put the localized message in the error
details or localize it in the client. The optional error details may contain
arbitrary information about the error. There is a predefined set of error
detail types in the package `google.rpc` that can be used for common error
conditions. # Language mapping The `Status` message is the logical
representation of the error model, but it is not necessarily the actual wire
format. When the `Status` message is exposed in different client libraries
and different wire protocols, it can be mapped differently. For example, it
will likely be mapped to some exceptions in Java, but more likely mapped to
some error codes in C. # Other uses The error model and the `Status`
message can be used in a variety of environments, either with or without
APIs, to provide a consistent developer experience across different
environments. Example uses of this error model include: - Partial errors.
If a service needs to return partial errors to the client, it may embed
the `Status` in the normal response to indicate the partial errors. -
Workflow errors. A typical workflow has multiple steps. Each step may
have a `Status` message for error reporting. - Batch operations. If a
client uses batch request and batch response, the `Status` message
should be used directly inside batch response, one for each error sub-
response. - Asynchronous operations. If an API call embeds asynchronous
operation results in its response, the status of those operations should
be represented directly using the `Status` message. - Logging. If some
API errors are stored in logs, the message `Status` could be used
directly after any stripping needed for security/privacy reasons.
Messages:
DetailsValueListEntry: A DetailsValueListEntry object.
Fields:
code: The status code, which should be an enum value of google.rpc.Code.
details: A list of messages that carry the error details. There is a
common set of message types for APIs to use.
message: A developer-facing error message, which should be in English. Any
user-facing error message should be localized and sent in the
google.rpc.Status.details field, or localized by the client.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class DetailsValueListEntry(_messages.Message):
r"""A DetailsValueListEntry object.
Messages:
AdditionalProperty: An additional property for a DetailsValueListEntry
object.
Fields:
additionalProperties: Properties of the object. Contains field @type
with type URL.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a DetailsValueListEntry object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
code = _messages.IntegerField(1, variant=_messages.Variant.INT32)
details = _messages.MessageField('DetailsValueListEntry', 2, repeated=True)
message = _messages.StringField(3)
class Step(_messages.Message):
r"""Defines a particular step within a Cloud Dataflow job. A job consists
of multiple steps, each of which performs some specific operation as part of
the overall job. Data is typically passed from one step to another as part
of the job. Here's an example of a sequence of steps which together
implement a Map-Reduce job: * Read a collection of data from some source,
parsing the collection's elements. * Validate the elements. *
Apply a user-defined function to map each element to some value and
extract an element-specific key value. * Group elements with the same key
into a single element with that key, transforming a multiply-keyed
collection into a uniquely-keyed collection. * Write the elements out
to some data sink. Note that the Cloud Dataflow service may be used to run
many different types of jobs, not just Map-Reduce.
Messages:
PropertiesValue: Named properties associated with the step. Each kind of
predefined step has its own required set of properties. Must be provided
on Create. Only retrieved with JOB_VIEW_ALL.
Fields:
kind: The kind of step in the Cloud Dataflow job.
name: The name that identifies the step. This must be unique for each step
with respect to all other steps in the Cloud Dataflow job.
properties: Named properties associated with the step. Each kind of
predefined step has its own required set of properties. Must be provided
on Create. Only retrieved with JOB_VIEW_ALL.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class PropertiesValue(_messages.Message):
r"""Named properties associated with the step. Each kind of predefined
step has its own required set of properties. Must be provided on Create.
Only retrieved with JOB_VIEW_ALL.
Messages:
AdditionalProperty: An additional property for a PropertiesValue object.
Fields:
additionalProperties: Properties of the object.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a PropertiesValue object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
kind = _messages.StringField(1)
name = _messages.StringField(2)
properties = _messages.MessageField('PropertiesValue', 3)
class StreamLocation(_messages.Message):
r"""Describes a stream of data, either as input to be processed or as output
of a streaming Dataflow job.
Fields:
customSourceLocation: The stream is a custom source.
pubsubLocation: The stream is a pubsub stream.
sideInputLocation: The stream is a streaming side input.
streamingStageLocation: The stream is part of another computation within
the current streaming Dataflow job.
"""
customSourceLocation = _messages.MessageField('CustomSourceLocation', 1)
pubsubLocation = _messages.MessageField('PubsubLocation', 2)
sideInputLocation = _messages.MessageField('StreamingSideInputLocation', 3)
streamingStageLocation = _messages.MessageField('StreamingStageLocation', 4)
class StreamingApplianceSnapshotConfig(_messages.Message):
r"""Streaming appliance snapshot configuration.
Fields:
importStateEndpoint: Indicates which endpoint is used to import appliance
state.
snapshotId: If set, indicates the snapshot id for the snapshot being
performed.
"""
importStateEndpoint = _messages.StringField(1)
snapshotId = _messages.StringField(2)
class StreamingComputationConfig(_messages.Message):
r"""Configuration information for a single streaming computation.
Messages:
TransformUserNameToStateFamilyValue: Map from user name of stateful
transforms in this stage to their state family.
Fields:
computationId: Unique identifier for this computation.
instructions: Instructions that comprise the computation.
stageName: Stage name of this computation.
systemName: System defined name for this computation.
transformUserNameToStateFamily: Map from user name of stateful transforms
in this stage to their state family.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class TransformUserNameToStateFamilyValue(_messages.Message):
r"""Map from user name of stateful transforms in this stage to their state
family.
Messages:
AdditionalProperty: An additional property for a
TransformUserNameToStateFamilyValue object.
Fields:
additionalProperties: Additional properties of type
TransformUserNameToStateFamilyValue
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a TransformUserNameToStateFamilyValue
object.
Fields:
key: Name of the additional property.
value: A string attribute.
"""
key = _messages.StringField(1)
value = _messages.StringField(2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
computationId = _messages.StringField(1)
instructions = _messages.MessageField('ParallelInstruction', 2, repeated=True)
stageName = _messages.StringField(3)
systemName = _messages.StringField(4)
transformUserNameToStateFamily = _messages.MessageField('TransformUserNameToStateFamilyValue', 5)
class StreamingComputationRanges(_messages.Message):
r"""Describes full or partial data disk assignment information of the
computation ranges.
Fields:
computationId: The ID of the computation.
rangeAssignments: Data disk assignments for ranges from this computation.
"""
computationId = _messages.StringField(1)
rangeAssignments = _messages.MessageField('KeyRangeDataDiskAssignment', 2, repeated=True)
class StreamingComputationTask(_messages.Message):
r"""A task which describes what action should be performed for the specified
streaming computation ranges.
Enums:
TaskTypeValueValuesEnum: A type of streaming computation task.
Fields:
computationRanges: Contains ranges of a streaming computation this task
should apply to.
dataDisks: Describes the set of data disks this task should apply to.
taskType: A type of streaming computation task.
"""
class TaskTypeValueValuesEnum(_messages.Enum):
r"""A type of streaming computation task.
Values:
STREAMING_COMPUTATION_TASK_UNKNOWN: The streaming computation task is
unknown, or unspecified.
STREAMING_COMPUTATION_TASK_STOP: Stop processing specified streaming
computation range(s).
STREAMING_COMPUTATION_TASK_START: Start processing specified streaming
computation range(s).
"""
STREAMING_COMPUTATION_TASK_UNKNOWN = 0
STREAMING_COMPUTATION_TASK_STOP = 1
STREAMING_COMPUTATION_TASK_START = 2
computationRanges = _messages.MessageField('StreamingComputationRanges', 1, repeated=True)
dataDisks = _messages.MessageField('MountedDataDisk', 2, repeated=True)
taskType = _messages.EnumField('TaskTypeValueValuesEnum', 3)
class StreamingConfigTask(_messages.Message):
r"""A task that carries configuration information for streaming
computations.
Messages:
UserStepToStateFamilyNameMapValue: Map from user step names to state
families.
Fields:
maxWorkItemCommitBytes: Maximum size for work item commit supported
windmill storage layer.
streamingComputationConfigs: Set of computation configuration information.
userStepToStateFamilyNameMap: Map from user step names to state families.
windmillServiceEndpoint: If present, the worker must use this endpoint to
communicate with Windmill Service dispatchers, otherwise the worker must
continue to use whatever endpoint it had been using.
windmillServicePort: If present, the worker must use this port to
communicate with Windmill Service dispatchers. Only applicable when
windmill_service_endpoint is specified.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class UserStepToStateFamilyNameMapValue(_messages.Message):
r"""Map from user step names to state families.
Messages:
AdditionalProperty: An additional property for a
UserStepToStateFamilyNameMapValue object.
Fields:
additionalProperties: Additional properties of type
UserStepToStateFamilyNameMapValue
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a UserStepToStateFamilyNameMapValue
object.
Fields:
key: Name of the additional property.
value: A string attribute.
"""
key = _messages.StringField(1)
value = _messages.StringField(2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
maxWorkItemCommitBytes = _messages.IntegerField(1)
streamingComputationConfigs = _messages.MessageField('StreamingComputationConfig', 2, repeated=True)
userStepToStateFamilyNameMap = _messages.MessageField('UserStepToStateFamilyNameMapValue', 3)
windmillServiceEndpoint = _messages.StringField(4)
windmillServicePort = _messages.IntegerField(5)
class StreamingSetupTask(_messages.Message):
r"""A task which initializes part of a streaming Dataflow job.
Fields:
drain: The user has requested drain.
receiveWorkPort: The TCP port on which the worker should listen for
messages from other streaming computation workers.
snapshotConfig: Configures streaming appliance snapshot.
streamingComputationTopology: The global topology of the streaming
Dataflow job.
workerHarnessPort: The TCP port used by the worker to communicate with the
Dataflow worker harness.
"""
drain = _messages.BooleanField(1)
receiveWorkPort = _messages.IntegerField(2, variant=_messages.Variant.INT32)
snapshotConfig = _messages.MessageField('StreamingApplianceSnapshotConfig', 3)
streamingComputationTopology = _messages.MessageField('TopologyConfig', 4)
workerHarnessPort = _messages.IntegerField(5, variant=_messages.Variant.INT32)
class StreamingSideInputLocation(_messages.Message):
r"""Identifies the location of a streaming side input.
Fields:
stateFamily: Identifies the state family where this side input is stored.
tag: Identifies the particular side input within the streaming Dataflow
job.
"""
stateFamily = _messages.StringField(1)
tag = _messages.StringField(2)
class StreamingStageLocation(_messages.Message):
r"""Identifies the location of a streaming computation stage, for stage-to-
stage communication.
Fields:
streamId: Identifies the particular stream within the streaming Dataflow
job.
"""
streamId = _messages.StringField(1)
class StringList(_messages.Message):
r"""A metric value representing a list of strings.
Fields:
elements: Elements of the list.
"""
elements = _messages.StringField(1, repeated=True)
class StructuredMessage(_messages.Message):
r"""A rich message format, including a human readable string, a key for
identifying the message, and structured data associated with the message for
programmatic consumption.
Fields:
messageKey: Identifier for this message type. Used by external systems to
internationalize or personalize message.
messageText: Human-readable version of message.
parameters: The structured data associated with this message.
"""
messageKey = _messages.StringField(1)
messageText = _messages.StringField(2)
parameters = _messages.MessageField('Parameter', 3, repeated=True)
class TaskRunnerSettings(_messages.Message):
r"""Taskrunner configuration settings.
Fields:
alsologtostderr: Whether to also send taskrunner log info to stderr.
baseTaskDir: The location on the worker for task-specific subdirectories.
baseUrl: The base URL for the taskrunner to use when accessing Google
Cloud APIs. When workers access Google Cloud APIs, they logically do so
via relative URLs. If this field is specified, it supplies the base URL
to use for resolving these relative URLs. The normative algorithm used
is defined by RFC 1808, "Relative Uniform Resource Locators". If not
specified, the default value is "http://www.googleapis.com/"
commandlinesFileName: The file to store preprocessing commands in.
continueOnException: Whether to continue taskrunner if an exception is
hit.
dataflowApiVersion: The API version of endpoint, e.g. "v1b3"
harnessCommand: The command to launch the worker harness.
languageHint: The suggested backend language.
logDir: The directory on the VM to store logs.
logToSerialconsole: Whether to send taskrunner log info to Google Compute
Engine VM serial console.
logUploadLocation: Indicates where to put logs. If this is not specified,
the logs will not be uploaded. The supported resource type is: Google
Cloud Storage: storage.googleapis.com/{bucket}/{object}
bucket.storage.googleapis.com/{object}
oauthScopes: The OAuth2 scopes to be requested by the taskrunner in order
to access the Cloud Dataflow API.
parallelWorkerSettings: The settings to pass to the parallel worker
harness.
streamingWorkerMainClass: The streaming worker main class name.
taskGroup: The UNIX group ID on the worker VM to use for tasks launched by
taskrunner; e.g. "wheel".
taskUser: The UNIX user ID on the worker VM to use for tasks launched by
taskrunner; e.g. "root".
tempStoragePrefix: The prefix of the resources the taskrunner should use
for temporary storage. The supported resource type is: Google Cloud
Storage: storage.googleapis.com/{bucket}/{object}
bucket.storage.googleapis.com/{object}
vmId: The ID string of the VM.
workflowFileName: The file to store the workflow in.
"""
alsologtostderr = _messages.BooleanField(1)
baseTaskDir = _messages.StringField(2)
baseUrl = _messages.StringField(3)
commandlinesFileName = _messages.StringField(4)
continueOnException = _messages.BooleanField(5)
dataflowApiVersion = _messages.StringField(6)
harnessCommand = _messages.StringField(7)
languageHint = _messages.StringField(8)
logDir = _messages.StringField(9)
logToSerialconsole = _messages.BooleanField(10)
logUploadLocation = _messages.StringField(11)
oauthScopes = _messages.StringField(12, repeated=True)
parallelWorkerSettings = _messages.MessageField('WorkerSettings', 13)
streamingWorkerMainClass = _messages.StringField(14)
taskGroup = _messages.StringField(15)
taskUser = _messages.StringField(16)
tempStoragePrefix = _messages.StringField(17)
vmId = _messages.StringField(18)
workflowFileName = _messages.StringField(19)
class TemplateMetadata(_messages.Message):
r"""Metadata describing a template.
Fields:
description: Optional. A description of the template.
name: Required. The name of the template.
parameters: The parameters for the template.
"""
description = _messages.StringField(1)
name = _messages.StringField(2)
parameters = _messages.MessageField('ParameterMetadata', 3, repeated=True)
class TopologyConfig(_messages.Message):
r"""Global topology of the streaming Dataflow job, including all
computations and their sharded locations.
Messages:
UserStageToComputationNameMapValue: Maps user stage names to stable
computation names.
Fields:
computations: The computations associated with a streaming Dataflow job.
dataDiskAssignments: The disks assigned to a streaming Dataflow job.
forwardingKeyBits: The size (in bits) of keys that will be assigned to
source messages.
persistentStateVersion: Version number for persistent state.
userStageToComputationNameMap: Maps user stage names to stable computation
names.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class UserStageToComputationNameMapValue(_messages.Message):
r"""Maps user stage names to stable computation names.
Messages:
AdditionalProperty: An additional property for a
UserStageToComputationNameMapValue object.
Fields:
additionalProperties: Additional properties of type
UserStageToComputationNameMapValue
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a UserStageToComputationNameMapValue
object.
Fields:
key: Name of the additional property.
value: A string attribute.
"""
key = _messages.StringField(1)
value = _messages.StringField(2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
computations = _messages.MessageField('ComputationTopology', 1, repeated=True)
dataDiskAssignments = _messages.MessageField('DataDiskAssignment', 2, repeated=True)
forwardingKeyBits = _messages.IntegerField(3, variant=_messages.Variant.INT32)
persistentStateVersion = _messages.IntegerField(4, variant=_messages.Variant.INT32)
userStageToComputationNameMap = _messages.MessageField('UserStageToComputationNameMapValue', 5)
class TransformSummary(_messages.Message):
r"""Description of the type, names/ids, and input/outputs for a transform.
Enums:
KindValueValuesEnum: Type of transform.
Fields:
displayData: Transform-specific display data.
id: SDK generated id of this transform instance.
inputCollectionName: User names for all collection inputs to this
transform.
kind: Type of transform.
name: User provided name for this transform instance.
outputCollectionName: User names for all collection outputs to this
transform.
"""
class KindValueValuesEnum(_messages.Enum):
r"""Type of transform.
Values:
UNKNOWN_KIND: Unrecognized transform type.
PAR_DO_KIND: ParDo transform.
GROUP_BY_KEY_KIND: Group By Key transform.
FLATTEN_KIND: Flatten transform.
READ_KIND: Read transform.
WRITE_KIND: Write transform.
CONSTANT_KIND: Constructs from a constant value, such as with Create.of.
SINGLETON_KIND: Creates a Singleton view of a collection.
SHUFFLE_KIND: Opening or closing a shuffle session, often as part of a
GroupByKey.
"""
UNKNOWN_KIND = 0
PAR_DO_KIND = 1
GROUP_BY_KEY_KIND = 2
FLATTEN_KIND = 3
READ_KIND = 4
WRITE_KIND = 5
CONSTANT_KIND = 6
SINGLETON_KIND = 7
SHUFFLE_KIND = 8
displayData = _messages.MessageField('DisplayData', 1, repeated=True)
id = _messages.StringField(2)
inputCollectionName = _messages.StringField(3, repeated=True)
kind = _messages.EnumField('KindValueValuesEnum', 4)
name = _messages.StringField(5)
outputCollectionName = _messages.StringField(6, repeated=True)
class ValidateResponse(_messages.Message):
r"""Response to the validation request.
Fields:
errorMessage: Will be empty if validation succeeds.
"""
errorMessage = _messages.StringField(1)
class WorkItem(_messages.Message):
r"""WorkItem represents basic information about a WorkItem to be executed in
the cloud.
Fields:
configuration: Work item-specific configuration as an opaque blob.
id: Identifies this WorkItem.
initialReportIndex: The initial index to use when reporting the status of
the WorkItem.
jobId: Identifies the workflow job this WorkItem belongs to.
leaseExpireTime: Time when the lease on this Work will expire.
mapTask: Additional information for MapTask WorkItems.
packages: Any required packages that need to be fetched in order to
execute this WorkItem.
projectId: Identifies the cloud project this WorkItem belongs to.
reportStatusInterval: Recommended reporting interval.
seqMapTask: Additional information for SeqMapTask WorkItems.
shellTask: Additional information for ShellTask WorkItems.
sourceOperationTask: Additional information for source operation
WorkItems.
streamingComputationTask: Additional information for
StreamingComputationTask WorkItems.
streamingConfigTask: Additional information for StreamingConfigTask
WorkItems.
streamingSetupTask: Additional information for StreamingSetupTask
WorkItems.
"""
configuration = _messages.StringField(1)
id = _messages.IntegerField(2)
initialReportIndex = _messages.IntegerField(3)
jobId = _messages.StringField(4)
leaseExpireTime = _messages.StringField(5)
mapTask = _messages.MessageField('MapTask', 6)
packages = _messages.MessageField('Package', 7, repeated=True)
projectId = _messages.StringField(8)
reportStatusInterval = _messages.StringField(9)
seqMapTask = _messages.MessageField('SeqMapTask', 10)
shellTask = _messages.MessageField('ShellTask', 11)
sourceOperationTask = _messages.MessageField('SourceOperationRequest', 12)
streamingComputationTask = _messages.MessageField('StreamingComputationTask', 13)
streamingConfigTask = _messages.MessageField('StreamingConfigTask', 14)
streamingSetupTask = _messages.MessageField('StreamingSetupTask', 15)
class WorkItemServiceState(_messages.Message):
r"""The Dataflow service's idea of the current state of a WorkItem being
processed by a worker.
Messages:
HarnessDataValue: Other data returned by the service, specific to the
particular worker harness.
Fields:
harnessData: Other data returned by the service, specific to the
particular worker harness.
leaseExpireTime: Time at which the current lease will expire.
metricShortId: The short ids that workers should use in subsequent metric
updates. Workers should strive to use short ids whenever possible, but
it is ok to request the short_id again if a worker lost track of it
(e.g. if the worker is recovering from a crash). NOTE: it is possible
that the response may have short ids for a subset of the metrics.
nextReportIndex: The index value to use for the next report sent by the
worker. Note: If the report call fails for whatever reason, the worker
should reuse this index for subsequent report attempts.
reportStatusInterval: New recommended reporting interval.
splitRequest: The progress point in the WorkItem where the Dataflow
service suggests that the worker truncate the task.
suggestedStopPoint: DEPRECATED in favor of split_request.
suggestedStopPosition: Obsolete, always empty.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class HarnessDataValue(_messages.Message):
r"""Other data returned by the service, specific to the particular worker
harness.
Messages:
AdditionalProperty: An additional property for a HarnessDataValue
object.
Fields:
additionalProperties: Properties of the object.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a HarnessDataValue object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
harnessData = _messages.MessageField('HarnessDataValue', 1)
leaseExpireTime = _messages.StringField(2)
metricShortId = _messages.MessageField('MetricShortId', 3, repeated=True)
nextReportIndex = _messages.IntegerField(4)
reportStatusInterval = _messages.StringField(5)
splitRequest = _messages.MessageField('ApproximateSplitRequest', 6)
suggestedStopPoint = _messages.MessageField('ApproximateProgress', 7)
suggestedStopPosition = _messages.MessageField('Position', 8)
class WorkItemStatus(_messages.Message):
r"""Conveys a worker's progress through the work described by a WorkItem.
Fields:
completed: True if the WorkItem was completed (successfully or
unsuccessfully).
counterUpdates: Worker output counters for this WorkItem.
dynamicSourceSplit: See documentation of stop_position.
errors: Specifies errors which occurred during processing. If errors are
provided, and completed = true, then the WorkItem is considered to have
failed.
metricUpdates: DEPRECATED in favor of counter_updates.
progress: DEPRECATED in favor of reported_progress.
reportIndex: The report index. When a WorkItem is leased, the lease will
contain an initial report index. When a WorkItem's status is reported
to the system, the report should be sent with that report index, and the
response will contain the index the worker should use for the next
report. Reports received with unexpected index values will be rejected
by the service. In order to preserve idempotency, the worker should not
alter the contents of a report, even if the worker must submit the same
report multiple times before getting back a response. The worker should
not submit a subsequent report until the response for the previous
report had been received from the service.
reportedProgress: The worker's progress through this WorkItem.
requestedLeaseDuration: Amount of time the worker requests for its lease.
sourceFork: DEPRECATED in favor of dynamic_source_split.
sourceOperationResponse: If the work item represented a
SourceOperationRequest, and the work is completed, contains the result
of the operation.
stopPosition: A worker may split an active map task in two parts,
"primary" and "residual", continuing to process the primary part and
returning the residual part into the pool of available work. This event
is called a "dynamic split" and is critical to the dynamic work
rebalancing feature. The two obtained sub-tasks are called "parts" of
the split. The parts, if concatenated, must represent the same input as
would be read by the current task if the split did not happen. The exact
way in which the original task is decomposed into the two parts is
specified either as a position demarcating them (stop_position), or
explicitly as two DerivedSources, if this task consumes a user-defined
source type (dynamic_source_split). The "current" task is adjusted as a
result of the split: after a task with range [A, B) sends a
stop_position update at C, its range is considered to be [A, C), e.g.: *
Progress should be interpreted relative to the new range, e.g. "75%
completed" means "75% of [A, C) completed" * The worker should interpret
proposed_stop_position relative to the new range, e.g. "split at 68%"
should be interpreted as "split at 68% of [A, C)". * If the worker
chooses to split again using stop_position, only stop_positions in [A,
C) will be accepted. * Etc. dynamic_source_split has similar semantics:
e.g., if a task with source S splits using dynamic_source_split into {P,
R} (where P and R must be together equivalent to S), then subsequent
progress and proposed_stop_position should be interpreted relative to P,
and in a potential subsequent dynamic_source_split into {P', R'}, P' and
R' must be together equivalent to P, etc.
totalThrottlerWaitTimeSeconds: Total time the worker spent being throttled
by external systems.
workItemId: Identifies the WorkItem.
"""
completed = _messages.BooleanField(1)
counterUpdates = _messages.MessageField('CounterUpdate', 2, repeated=True)
dynamicSourceSplit = _messages.MessageField('DynamicSourceSplit', 3)
errors = _messages.MessageField('Status', 4, repeated=True)
metricUpdates = _messages.MessageField('MetricUpdate', 5, repeated=True)
progress = _messages.MessageField('ApproximateProgress', 6)
reportIndex = _messages.IntegerField(7)
reportedProgress = _messages.MessageField('ApproximateReportedProgress', 8)
requestedLeaseDuration = _messages.StringField(9)
sourceFork = _messages.MessageField('SourceFork', 10)
sourceOperationResponse = _messages.MessageField('SourceOperationResponse', 11)
stopPosition = _messages.MessageField('Position', 12)
totalThrottlerWaitTimeSeconds = _messages.FloatField(13)
workItemId = _messages.StringField(14)
class WorkerHealthReport(_messages.Message):
r"""WorkerHealthReport contains information about the health of a worker.
The VM should be identified by the labels attached to the WorkerMessage that
this health ping belongs to.
Messages:
PodsValueListEntry: A PodsValueListEntry object.
Fields:
msg: A message describing any unusual health reports.
pods: The pods running on the worker. See: http://kubernetes.io/v1.1/docs
/api-reference/v1/definitions.html#_v1_pod This field is used by the
worker to send the status of the indvidual containers running on each
worker.
reportInterval: The interval at which the worker is sending health
reports. The default value of 0 should be interpreted as the field is
not being explicitly set by the worker.
vmIsBroken: Whether the VM is in a permanently broken state. Broken VMs
should be abandoned or deleted ASAP to avoid assigning or completing any
work.
vmIsHealthy: Whether the VM is currently healthy.
vmStartupTime: The time the VM was booted.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class PodsValueListEntry(_messages.Message):
r"""A PodsValueListEntry object.
Messages:
AdditionalProperty: An additional property for a PodsValueListEntry
object.
Fields:
additionalProperties: Properties of the object.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a PodsValueListEntry object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
msg = _messages.StringField(1)
pods = _messages.MessageField('PodsValueListEntry', 2, repeated=True)
reportInterval = _messages.StringField(3)
vmIsBroken = _messages.BooleanField(4)
vmIsHealthy = _messages.BooleanField(5)
vmStartupTime = _messages.StringField(6)
class WorkerHealthReportResponse(_messages.Message):
r"""WorkerHealthReportResponse contains information returned to the worker
in response to a health ping.
Fields:
reportInterval: A positive value indicates the worker should change its
reporting interval to the specified value. The default value of zero
means no change in report rate is requested by the server.
"""
reportInterval = _messages.StringField(1)
class WorkerLifecycleEvent(_messages.Message):
r"""A report of an event in a worker's lifecycle. The proto contains one
event, because the worker is expected to asynchronously send each message
immediately after the event. Due to this asynchrony, messages may arrive out
of order (or missing), and it is up to the consumer to interpret. The
timestamp of the event is in the enclosing WorkerMessage proto.
Enums:
EventValueValuesEnum: The event being reported.
Messages:
MetadataValue: Other stats that can accompany an event. E.g. {
"downloaded_bytes" : "123456" }
Fields:
containerStartTime: The start time of this container. All events will
report this so that events can be grouped together across container/VM
restarts.
event: The event being reported.
metadata: Other stats that can accompany an event. E.g. {
"downloaded_bytes" : "123456" }
"""
class EventValueValuesEnum(_messages.Enum):
r"""The event being reported.
Values:
UNKNOWN_EVENT: Invalid event.
OS_START: The time the VM started.
CONTAINER_START: Our container code starts running. Multiple containers
could be distinguished with WorkerMessage.labels if desired.
NETWORK_UP: The worker has a functional external network connection.
STAGING_FILES_DOWNLOAD_START: Started downloading staging files.
STAGING_FILES_DOWNLOAD_FINISH: Finished downloading all staging files.
SDK_INSTALL_START: For applicable SDKs, started installation of SDK and
worker packages.
SDK_INSTALL_FINISH: Finished installing SDK.
"""
UNKNOWN_EVENT = 0
OS_START = 1
CONTAINER_START = 2
NETWORK_UP = 3
STAGING_FILES_DOWNLOAD_START = 4
STAGING_FILES_DOWNLOAD_FINISH = 5
SDK_INSTALL_START = 6
SDK_INSTALL_FINISH = 7
@encoding.MapUnrecognizedFields('additionalProperties')
class MetadataValue(_messages.Message):
r"""Other stats that can accompany an event. E.g. { "downloaded_bytes" :
"123456" }
Messages:
AdditionalProperty: An additional property for a MetadataValue object.
Fields:
additionalProperties: Additional properties of type MetadataValue
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a MetadataValue object.
Fields:
key: Name of the additional property.
value: A string attribute.
"""
key = _messages.StringField(1)
value = _messages.StringField(2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
containerStartTime = _messages.StringField(1)
event = _messages.EnumField('EventValueValuesEnum', 2)
metadata = _messages.MessageField('MetadataValue', 3)
class WorkerMessage(_messages.Message):
r"""WorkerMessage provides information to the backend about a worker.
Messages:
LabelsValue: Labels are used to group WorkerMessages. For example, a
worker_message about a particular container might have the labels: {
"JOB_ID": "2015-04-22", "WORKER_ID": "wordcount-vm-2015..."
"CONTAINER_TYPE": "worker", "CONTAINER_ID": "ac1234def"} Label tags
typically correspond to Label enum values. However, for ease of
development other strings can be used as tags. LABEL_UNSPECIFIED should
not be used here.
Fields:
labels: Labels are used to group WorkerMessages. For example, a
worker_message about a particular container might have the labels: {
"JOB_ID": "2015-04-22", "WORKER_ID": "wordcount-vm-2015..."
"CONTAINER_TYPE": "worker", "CONTAINER_ID": "ac1234def"} Label tags
typically correspond to Label enum values. However, for ease of
development other strings can be used as tags. LABEL_UNSPECIFIED should
not be used here.
time: The timestamp of the worker_message.
workerHealthReport: The health of a worker.
workerLifecycleEvent: Record of worker lifecycle events.
workerMessageCode: A worker message code.
workerMetrics: Resource metrics reported by workers.
workerShutdownNotice: Shutdown notice by workers.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class LabelsValue(_messages.Message):
r"""Labels are used to group WorkerMessages. For example, a worker_message
about a particular container might have the labels: { "JOB_ID":
"2015-04-22", "WORKER_ID": "wordcount-vm-2015..." "CONTAINER_TYPE":
"worker", "CONTAINER_ID": "ac1234def"} Label tags typically correspond
to Label enum values. However, for ease of development other strings can
be used as tags. LABEL_UNSPECIFIED should not be used here.
Messages:
AdditionalProperty: An additional property for a LabelsValue object.
Fields:
additionalProperties: Additional properties of type LabelsValue
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a LabelsValue object.
Fields:
key: Name of the additional property.
value: A string attribute.
"""
key = _messages.StringField(1)
value = _messages.StringField(2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
labels = _messages.MessageField('LabelsValue', 1)
time = _messages.StringField(2)
workerHealthReport = _messages.MessageField('WorkerHealthReport', 3)
workerLifecycleEvent = _messages.MessageField('WorkerLifecycleEvent', 4)
workerMessageCode = _messages.MessageField('WorkerMessageCode', 5)
workerMetrics = _messages.MessageField('ResourceUtilizationReport', 6)
workerShutdownNotice = _messages.MessageField('WorkerShutdownNotice', 7)
class WorkerMessageCode(_messages.Message):
r"""A message code is used to report status and error messages to the
service. The message codes are intended to be machine readable. The service
will take care of translating these into user understandable messages if
necessary. Example use cases: 1. Worker processes reporting successful
startup. 2. Worker processes reporting specific errors (e.g. package
staging failure).
Messages:
ParametersValue: Parameters contains specific information about the code.
This is a struct to allow parameters of different types. Examples: 1.
For a "HARNESS_STARTED" message parameters might provide the name of
the worker and additional data like timing information. 2. For a
"GCS_DOWNLOAD_ERROR" parameters might contain fields listing the GCS
objects being downloaded and fields containing errors. In general
complex data structures should be avoided. If a worker needs to send a
specific and complicated data structure then please consider defining a
new proto and adding it to the data oneof in WorkerMessageResponse.
Conventions: Parameters should only be used for information that isn't
typically passed as a label. hostname and other worker identifiers
should almost always be passed as labels since they will be included on
most messages.
Fields:
code: The code is a string intended for consumption by a machine that
identifies the type of message being sent. Examples: 1.
"HARNESS_STARTED" might be used to indicate the worker harness has
started. 2. "GCS_DOWNLOAD_ERROR" might be used to indicate an error
downloading a GCS file as part of the boot process of one of the
worker containers. This is a string and not an enum to make it easy to
add new codes without waiting for an API change.
parameters: Parameters contains specific information about the code. This
is a struct to allow parameters of different types. Examples: 1. For a
"HARNESS_STARTED" message parameters might provide the name of the
worker and additional data like timing information. 2. For a
"GCS_DOWNLOAD_ERROR" parameters might contain fields listing the GCS
objects being downloaded and fields containing errors. In general
complex data structures should be avoided. If a worker needs to send a
specific and complicated data structure then please consider defining a
new proto and adding it to the data oneof in WorkerMessageResponse.
Conventions: Parameters should only be used for information that isn't
typically passed as a label. hostname and other worker identifiers
should almost always be passed as labels since they will be included on
most messages.
"""
@encoding.MapUnrecognizedFields('additionalProperties')
class ParametersValue(_messages.Message):
r"""Parameters contains specific information about the code. This is a
struct to allow parameters of different types. Examples: 1. For a
"HARNESS_STARTED" message parameters might provide the name of the
worker and additional data like timing information. 2. For a
"GCS_DOWNLOAD_ERROR" parameters might contain fields listing the GCS
objects being downloaded and fields containing errors. In general complex
data structures should be avoided. If a worker needs to send a specific
and complicated data structure then please consider defining a new proto
and adding it to the data oneof in WorkerMessageResponse. Conventions:
Parameters should only be used for information that isn't typically passed
as a label. hostname and other worker identifiers should almost always be
passed as labels since they will be included on most messages.
Messages:
AdditionalProperty: An additional property for a ParametersValue object.
Fields:
additionalProperties: Properties of the object.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a ParametersValue object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
code = _messages.StringField(1)
parameters = _messages.MessageField('ParametersValue', 2)
class WorkerMessageResponse(_messages.Message):
r"""A worker_message response allows the server to pass information to the
sender.
Fields:
workerHealthReportResponse: The service's response to a worker's health
report.
workerMetricsResponse: Service's response to reporting worker metrics
(currently empty).
workerShutdownNoticeResponse: Service's response to shutdown notice
(currently empty).
"""
workerHealthReportResponse = _messages.MessageField('WorkerHealthReportResponse', 1)
workerMetricsResponse = _messages.MessageField('ResourceUtilizationReportResponse', 2)
workerShutdownNoticeResponse = _messages.MessageField('WorkerShutdownNoticeResponse', 3)
class WorkerPool(_messages.Message):
r"""Describes one particular pool of Cloud Dataflow workers to be
instantiated by the Cloud Dataflow service in order to perform the
computations required by a job. Note that a workflow job may use multiple
pools, in order to match the various computational requirements of the
various stages of the job.
Enums:
DefaultPackageSetValueValuesEnum: The default package set to install.
This allows the service to select a default set of packages which are
useful to worker harnesses written in a particular language.
IpConfigurationValueValuesEnum: Configuration for VM IPs.
TeardownPolicyValueValuesEnum: Sets the policy for determining when to
turndown worker pool. Allowed values are: `TEARDOWN_ALWAYS`,
`TEARDOWN_ON_SUCCESS`, and `TEARDOWN_NEVER`. `TEARDOWN_ALWAYS` means
workers are always torn down regardless of whether the job succeeds.
`TEARDOWN_ON_SUCCESS` means workers are torn down if the job succeeds.
`TEARDOWN_NEVER` means the workers are never torn down. If the workers
are not torn down by the service, they will continue to run and use
Google Compute Engine VM resources in the user's project until they are
explicitly terminated by the user. Because of this, Google recommends
using the `TEARDOWN_ALWAYS` policy except for small, manually supervised
test jobs. If unknown or unspecified, the service will attempt to
choose a reasonable default.
Messages:
MetadataValue: Metadata to set on the Google Compute Engine VMs.
PoolArgsValue: Extra arguments for this worker pool.
Fields:
autoscalingSettings: Settings for autoscaling of this WorkerPool.
dataDisks: Data disks that are used by a VM in this workflow.
defaultPackageSet: The default package set to install. This allows the
service to select a default set of packages which are useful to worker
harnesses written in a particular language.
diskSizeGb: Size of root disk for VMs, in GB. If zero or unspecified, the
service will attempt to choose a reasonable default.
diskSourceImage: Fully qualified source image for disks.
diskType: Type of root disk for VMs. If empty or unspecified, the service
will attempt to choose a reasonable default.
ipConfiguration: Configuration for VM IPs.
kind: The kind of the worker pool; currently only `harness` and `shuffle`
are supported.
machineType: Machine type (e.g. "n1-standard-1"). If empty or
unspecified, the service will attempt to choose a reasonable default.
metadata: Metadata to set on the Google Compute Engine VMs.
network: Network to which VMs will be assigned. If empty or unspecified,
the service will use the network "default".
numThreadsPerWorker: The number of threads per worker harness. If empty or
unspecified, the service will choose a number of threads (according to
the number of cores on the selected machine type for batch, or 1 by
convention for streaming).
numWorkers: Number of Google Compute Engine workers in this pool needed to
execute the job. If zero or unspecified, the service will attempt to
choose a reasonable default.
onHostMaintenance: The action to take on host maintenance, as defined by
the Google Compute Engine API.
packages: Packages to be installed on workers.
poolArgs: Extra arguments for this worker pool.
subnetwork: Subnetwork to which VMs will be assigned, if desired.
Expected to be of the form "regions/REGION/subnetworks/SUBNETWORK".
taskrunnerSettings: Settings passed through to Google Compute Engine
workers when using the standard Dataflow task runner. Users should
ignore this field.
teardownPolicy: Sets the policy for determining when to turndown worker
pool. Allowed values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
`TEARDOWN_NEVER`. `TEARDOWN_ALWAYS` means workers are always torn down
regardless of whether the job succeeds. `TEARDOWN_ON_SUCCESS` means
workers are torn down if the job succeeds. `TEARDOWN_NEVER` means the
workers are never torn down. If the workers are not torn down by the
service, they will continue to run and use Google Compute Engine VM
resources in the user's project until they are explicitly terminated by
the user. Because of this, Google recommends using the `TEARDOWN_ALWAYS`
policy except for small, manually supervised test jobs. If unknown or
unspecified, the service will attempt to choose a reasonable default.
workerHarnessContainerImage: Required. Docker container image that
executes the Cloud Dataflow worker harness, residing in Google Container
Registry.
zone: Zone to run the worker pools in. If empty or unspecified, the
service will attempt to choose a reasonable default.
"""
class DefaultPackageSetValueValuesEnum(_messages.Enum):
r"""The default package set to install. This allows the service to select
a default set of packages which are useful to worker harnesses written in
a particular language.
Values:
DEFAULT_PACKAGE_SET_UNKNOWN: The default set of packages to stage is
unknown, or unspecified.
DEFAULT_PACKAGE_SET_NONE: Indicates that no packages should be staged at
the worker unless explicitly specified by the job.
DEFAULT_PACKAGE_SET_JAVA: Stage packages typically useful to workers
written in Java.
DEFAULT_PACKAGE_SET_PYTHON: Stage pacakges typically useful to workers
written in Python.
"""
DEFAULT_PACKAGE_SET_UNKNOWN = 0
DEFAULT_PACKAGE_SET_NONE = 1
DEFAULT_PACKAGE_SET_JAVA = 2
DEFAULT_PACKAGE_SET_PYTHON = 3
class IpConfigurationValueValuesEnum(_messages.Enum):
r"""Configuration for VM IPs.
Values:
WORKER_IP_UNSPECIFIED: The configuration is unknown, or unspecified.
WORKER_IP_PUBLIC: Workers should have public IP addresses.
WORKER_IP_PRIVATE: Workers should have private IP addresses.
"""
WORKER_IP_UNSPECIFIED = 0
WORKER_IP_PUBLIC = 1
WORKER_IP_PRIVATE = 2
class TeardownPolicyValueValuesEnum(_messages.Enum):
r"""Sets the policy for determining when to turndown worker pool. Allowed
values are: `TEARDOWN_ALWAYS`, `TEARDOWN_ON_SUCCESS`, and
`TEARDOWN_NEVER`. `TEARDOWN_ALWAYS` means workers are always torn down
regardless of whether the job succeeds. `TEARDOWN_ON_SUCCESS` means
workers are torn down if the job succeeds. `TEARDOWN_NEVER` means the
workers are never torn down. If the workers are not torn down by the
service, they will continue to run and use Google Compute Engine VM
resources in the user's project until they are explicitly terminated by
the user. Because of this, Google recommends using the `TEARDOWN_ALWAYS`
policy except for small, manually supervised test jobs. If unknown or
unspecified, the service will attempt to choose a reasonable default.
Values:
TEARDOWN_POLICY_UNKNOWN: The teardown policy isn't specified, or is
unknown.
TEARDOWN_ALWAYS: Always teardown the resource.
TEARDOWN_ON_SUCCESS: Teardown the resource on success. This is useful
for debugging failures.
TEARDOWN_NEVER: Never teardown the resource. This is useful for
debugging and development.
"""
TEARDOWN_POLICY_UNKNOWN = 0
TEARDOWN_ALWAYS = 1
TEARDOWN_ON_SUCCESS = 2
TEARDOWN_NEVER = 3
@encoding.MapUnrecognizedFields('additionalProperties')
class MetadataValue(_messages.Message):
r"""Metadata to set on the Google Compute Engine VMs.
Messages:
AdditionalProperty: An additional property for a MetadataValue object.
Fields:
additionalProperties: Additional properties of type MetadataValue
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a MetadataValue object.
Fields:
key: Name of the additional property.
value: A string attribute.
"""
key = _messages.StringField(1)
value = _messages.StringField(2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
@encoding.MapUnrecognizedFields('additionalProperties')
class PoolArgsValue(_messages.Message):
r"""Extra arguments for this worker pool.
Messages:
AdditionalProperty: An additional property for a PoolArgsValue object.
Fields:
additionalProperties: Properties of the object. Contains field @type
with type URL.
"""
class AdditionalProperty(_messages.Message):
r"""An additional property for a PoolArgsValue object.
Fields:
key: Name of the additional property.
value: A extra_types.JsonValue attribute.
"""
key = _messages.StringField(1)
value = _messages.MessageField('extra_types.JsonValue', 2)
additionalProperties = _messages.MessageField('AdditionalProperty', 1, repeated=True)
autoscalingSettings = _messages.MessageField('AutoscalingSettings', 1)
dataDisks = _messages.MessageField('Disk', 2, repeated=True)
defaultPackageSet = _messages.EnumField('DefaultPackageSetValueValuesEnum', 3)
diskSizeGb = _messages.IntegerField(4, variant=_messages.Variant.INT32)
diskSourceImage = _messages.StringField(5)
diskType = _messages.StringField(6)
ipConfiguration = _messages.EnumField('IpConfigurationValueValuesEnum', 7)
kind = _messages.StringField(8)
machineType = _messages.StringField(9)
metadata = _messages.MessageField('MetadataValue', 10)
network = _messages.StringField(11)
numThreadsPerWorker = _messages.IntegerField(12, variant=_messages.Variant.INT32)
numWorkers = _messages.IntegerField(13, variant=_messages.Variant.INT32)
onHostMaintenance = _messages.StringField(14)
packages = _messages.MessageField('Package', 15, repeated=True)
poolArgs = _messages.MessageField('PoolArgsValue', 16)
subnetwork = _messages.StringField(17)
taskrunnerSettings = _messages.MessageField('TaskRunnerSettings', 18)
teardownPolicy = _messages.EnumField('TeardownPolicyValueValuesEnum', 19)
workerHarnessContainerImage = _messages.StringField(20)
zone = _messages.StringField(21)
class WorkerSettings(_messages.Message):
r"""Provides data to pass through to the worker harness.
Fields:
baseUrl: The base URL for accessing Google Cloud APIs. When workers
access Google Cloud APIs, they logically do so via relative URLs. If
this field is specified, it supplies the base URL to use for resolving
these relative URLs. The normative algorithm used is defined by RFC
1808, "Relative Uniform Resource Locators". If not specified, the
default value is "http://www.googleapis.com/"
reportingEnabled: Whether to send work progress updates to the service.
servicePath: The Cloud Dataflow service path relative to the root URL, for
example, "dataflow/v1b3/projects".
shuffleServicePath: The Shuffle service path relative to the root URL, for
example, "shuffle/v1beta1".
tempStoragePrefix: The prefix of the resources the system should use for
temporary storage. The supported resource type is: Google Cloud
Storage: storage.googleapis.com/{bucket}/{object}
bucket.storage.googleapis.com/{object}
workerId: The ID of the worker running this pipeline.
"""
baseUrl = _messages.StringField(1)
reportingEnabled = _messages.BooleanField(2)
servicePath = _messages.StringField(3)
shuffleServicePath = _messages.StringField(4)
tempStoragePrefix = _messages.StringField(5)
workerId = _messages.StringField(6)
class WorkerShutdownNotice(_messages.Message):
r"""Shutdown notification from workers. This is to be sent by the shutdown
script of the worker VM so that the backend knows that the VM is being shut
down.
Fields:
reason: The reason for the worker shutdown. Current possible values are:
"UNKNOWN": shutdown reason is unknown. "PREEMPTION": shutdown reason
is preemption. Other possible reasons may be added in the future.
"""
reason = _messages.StringField(1)
class WorkerShutdownNoticeResponse(_messages.Message):
r"""Service-side response to WorkerMessage issuing shutdown notice."""
class WriteInstruction(_messages.Message):
r"""An instruction that writes records. Takes one input, produces no
outputs.
Fields:
input: The input.
sink: The sink to write to.
"""
input = _messages.MessageField('InstructionInput', 1)
sink = _messages.MessageField('Sink', 2)
encoding.AddCustomJsonFieldMapping(
StandardQueryParameters, 'f__xgafv', '$.xgafv')
encoding.AddCustomJsonEnumMapping(
StandardQueryParameters.FXgafvValueValuesEnum, '_1', '1')
encoding.AddCustomJsonEnumMapping(
StandardQueryParameters.FXgafvValueValuesEnum, '_2', '2')