google-cloud-dataproc-v1beta2 0.1.0

data/proto_docs/google/cloud/dataproc/v1beta2/jobs.rb

@@ -0,0 +1,984 @@
+# frozen_string_literal: true
+
+# Copyright 2020 Google LLC
+#
+# Licensed 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
+#
+#     https://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.
+
+# Auto-generated by gapic-generator-ruby. DO NOT EDIT!
+
+
+module Google
+  module Cloud
+    module Dataproc
+      module V1beta2
+        # The runtime logging config of the job.
+        # @!attribute [rw] driver_log_levels
+        #   @return [Google::Protobuf::Map{String => Google::Cloud::Dataproc::V1beta2::LoggingConfig::Level}]
+        #     The per-package log levels for the driver. This may include
+        #     "root" package name to configure rootLogger.
+        #     Examples:
+        #       'com.google = FATAL', 'root = INFO', 'org.apache = DEBUG'
+        class LoggingConfig
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+
+          # @!attribute [rw] key
+          #   @return [String]
+          # @!attribute [rw] value
+          #   @return [Google::Cloud::Dataproc::V1beta2::LoggingConfig::Level]
+          class DriverLogLevelsEntry
+            include Google::Protobuf::MessageExts
+            extend Google::Protobuf::MessageExts::ClassMethods
+          end
+
+          # The Log4j level for job execution. When running an
+          # [Apache Hive](http://hive.apache.org/) job, Cloud
+          # Dataproc configures the Hive client to an equivalent verbosity level.
+          module Level
+            # Level is unspecified. Use default level for log4j.
+            LEVEL_UNSPECIFIED = 0
+
+            # Use ALL level for log4j.
+            ALL = 1
+
+            # Use TRACE level for log4j.
+            TRACE = 2
+
+            # Use DEBUG level for log4j.
+            DEBUG = 3
+
+            # Use INFO level for log4j.
+            INFO = 4
+
+            # Use WARN level for log4j.
+            WARN = 5
+
+            # Use ERROR level for log4j.
+            ERROR = 6
+
+            # Use FATAL level for log4j.
+            FATAL = 7
+
+            # Turn off log4j.
+            OFF = 8
+          end
+        end
+
+        # A Dataproc job for running
+        # [Apache Hadoop
+        # MapReduce](https://hadoop.apache.org/docs/current/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html)
+        # jobs on [Apache Hadoop
+        # YARN](https://hadoop.apache.org/docs/r2.7.1/hadoop-yarn/hadoop-yarn-site/YARN.html).
+        # @!attribute [rw] main_jar_file_uri
+        #   @return [String]
+        #     The HCFS URI of the jar file containing the main class.
+        #     Examples:
+        #         'gs://foo-bucket/analytics-binaries/extract-useful-metrics-mr.jar'
+        #         'hdfs:/tmp/test-samples/custom-wordcount.jar'
+        #         'file:///home/usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar'
+        # @!attribute [rw] main_class
+        #   @return [String]
+        #     The name of the driver's main class. The jar file containing the class
+        #     must be in the default CLASSPATH or specified in `jar_file_uris`.
+        # @!attribute [rw] args
+        #   @return [Array<String>]
+        #     Optional. The arguments to pass to the driver. Do not
+        #     include arguments, such as `-libjars` or `-Dfoo=bar`, that can be set as
+        #     job properties, since a collision may occur that causes an incorrect job
+        #     submission.
+        # @!attribute [rw] jar_file_uris
+        #   @return [Array<String>]
+        #     Optional. Jar file URIs to add to the CLASSPATHs of the
+        #     Hadoop driver and tasks.
+        # @!attribute [rw] file_uris
+        #   @return [Array<String>]
+        #     Optional. HCFS (Hadoop Compatible Filesystem) URIs of files to be copied
+        #     to the working directory of Hadoop drivers and distributed tasks. Useful
+        #     for naively parallel tasks.
+        # @!attribute [rw] archive_uris
+        #   @return [Array<String>]
+        #     Optional. HCFS URIs of archives to be extracted in the working directory of
+        #     Hadoop drivers and tasks. Supported file types:
+        #     .jar, .tar, .tar.gz, .tgz, or .zip.
+        # @!attribute [rw] properties
+        #   @return [Google::Protobuf::Map{String => String}]
+        #     Optional. A mapping of property names to values, used to configure Hadoop.
+        #     Properties that conflict with values set by the Dataproc API may be
+        #     overwritten. Can include properties set in /etc/hadoop/conf/*-site and
+        #     classes in user code.
+        # @!attribute [rw] logging_config
+        #   @return [Google::Cloud::Dataproc::V1beta2::LoggingConfig]
+        #     Optional. The runtime log config for job execution.
+        class HadoopJob
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+
+          # @!attribute [rw] key
+          #   @return [String]
+          # @!attribute [rw] value
+          #   @return [String]
+          class PropertiesEntry
+            include Google::Protobuf::MessageExts
+            extend Google::Protobuf::MessageExts::ClassMethods
+          end
+        end
+
+        # A Dataproc job for running [Apache Spark](http://spark.apache.org/)
+        # applications on YARN.
+        # The specification of the main method to call to drive the job.
+        # Specify either the jar file that contains the main class or the main class
+        # name. To pass both a main jar and a main class in that jar, add the jar to
+        # `CommonJob.jar_file_uris`, and then specify the main class name in
+        # `main_class`.
+        # @!attribute [rw] main_jar_file_uri
+        #   @return [String]
+        #     The HCFS URI of the jar file that contains the main class.
+        # @!attribute [rw] main_class
+        #   @return [String]
+        #     The name of the driver's main class. The jar file that contains the class
+        #     must be in the default CLASSPATH or specified in `jar_file_uris`.
+        # @!attribute [rw] args
+        #   @return [Array<String>]
+        #     Optional. The arguments to pass to the driver. Do not include arguments,
+        #     such as `--conf`, that can be set as job properties, since a collision may
+        #     occur that causes an incorrect job submission.
+        # @!attribute [rw] jar_file_uris
+        #   @return [Array<String>]
+        #     Optional. HCFS URIs of jar files to add to the CLASSPATHs of the
+        #     Spark driver and tasks.
+        # @!attribute [rw] file_uris
+        #   @return [Array<String>]
+        #     Optional. HCFS URIs of files to be copied to the working directory of
+        #     Spark drivers and distributed tasks. Useful for naively parallel tasks.
+        # @!attribute [rw] archive_uris
+        #   @return [Array<String>]
+        #     Optional. HCFS URIs of archives to be extracted in the working directory
+        #     of Spark drivers and tasks. Supported file types:
+        #     .jar, .tar, .tar.gz, .tgz, and .zip.
+        # @!attribute [rw] properties
+        #   @return [Google::Protobuf::Map{String => String}]
+        #     Optional. A mapping of property names to values, used to configure Spark.
+        #     Properties that conflict with values set by the Dataproc API may be
+        #     overwritten. Can include properties set in
+        #     /etc/spark/conf/spark-defaults.conf and classes in user code.
+        # @!attribute [rw] logging_config
+        #   @return [Google::Cloud::Dataproc::V1beta2::LoggingConfig]
+        #     Optional. The runtime log config for job execution.
+        class SparkJob
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+
+          # @!attribute [rw] key
+          #   @return [String]
+          # @!attribute [rw] value
+          #   @return [String]
+          class PropertiesEntry
+            include Google::Protobuf::MessageExts
+            extend Google::Protobuf::MessageExts::ClassMethods
+          end
+        end
+
+        # A Dataproc job for running
+        # [Apache
+        # PySpark](https://spark.apache.org/docs/0.9.0/python-programming-guide.html)
+        # applications on YARN.
+        # @!attribute [rw] main_python_file_uri
+        #   @return [String]
+        #     Required. The HCFS URI of the main Python file to use as the driver. Must
+        #     be a .py file.
+        # @!attribute [rw] args
+        #   @return [Array<String>]
+        #     Optional. The arguments to pass to the driver.  Do not include arguments,
+        #     such as `--conf`, that can be set as job properties, since a collision may
+        #     occur that causes an incorrect job submission.
+        # @!attribute [rw] python_file_uris
+        #   @return [Array<String>]
+        #     Optional. HCFS file URIs of Python files to pass to the PySpark
+        #     framework. Supported file types: .py, .egg, and .zip.
+        # @!attribute [rw] jar_file_uris
+        #   @return [Array<String>]
+        #     Optional. HCFS URIs of jar files to add to the CLASSPATHs of the
+        #     Python driver and tasks.
+        # @!attribute [rw] file_uris
+        #   @return [Array<String>]
+        #     Optional. HCFS URIs of files to be copied to the working directory of
+        #     Python drivers and distributed tasks. Useful for naively parallel tasks.
+        # @!attribute [rw] archive_uris
+        #   @return [Array<String>]
+        #     Optional. HCFS URIs of archives to be extracted in the working directory of
+        #     .jar, .tar, .tar.gz, .tgz, and .zip.
+        # @!attribute [rw] properties
+        #   @return [Google::Protobuf::Map{String => String}]
+        #     Optional. A mapping of property names to values, used to configure PySpark.
+        #     Properties that conflict with values set by the Dataproc API may be
+        #     overwritten. Can include properties set in
+        #     /etc/spark/conf/spark-defaults.conf and classes in user code.
+        # @!attribute [rw] logging_config
+        #   @return [Google::Cloud::Dataproc::V1beta2::LoggingConfig]
+        #     Optional. The runtime log config for job execution.
+        class PySparkJob
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+
+          # @!attribute [rw] key
+          #   @return [String]
+          # @!attribute [rw] value
+          #   @return [String]
+          class PropertiesEntry
+            include Google::Protobuf::MessageExts
+            extend Google::Protobuf::MessageExts::ClassMethods
+          end
+        end
+
+        # A list of queries to run on a cluster.
+        # @!attribute [rw] queries
+        #   @return [Array<String>]
+        #     Required. The queries to execute. You do not need to terminate a query
+        #     with a semicolon. Multiple queries can be specified in one string
+        #     by separating each with a semicolon. Here is an example of an Cloud
+        #     Dataproc API snippet that uses a QueryList to specify a HiveJob:
+        #
+        #         "hiveJob": {
+        #           "queryList": {
+        #             "queries": [
+        #               "query1",
+        #               "query2",
+        #               "query3;query4",
+        #             ]
+        #           }
+        #         }
+        class QueryList
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+        end
+
+        # A Dataproc job for running [Apache Hive](https://hive.apache.org/)
+        # queries on YARN.
+        # @!attribute [rw] query_file_uri
+        #   @return [String]
+        #     The HCFS URI of the script that contains Hive queries.
+        # @!attribute [rw] query_list
+        #   @return [Google::Cloud::Dataproc::V1beta2::QueryList]
+        #     A list of queries.
+        # @!attribute [rw] continue_on_failure
+        #   @return [Boolean]
+        #     Optional. Whether to continue executing queries if a query fails.
+        #     The default value is `false`. Setting to `true` can be useful when
+        #     executing independent parallel queries.
+        # @!attribute [rw] script_variables
+        #   @return [Google::Protobuf::Map{String => String}]
+        #     Optional. Mapping of query variable names to values (equivalent to the
+        #     Hive command: `SET name="value";`).
+        # @!attribute [rw] properties
+        #   @return [Google::Protobuf::Map{String => String}]
+        #     Optional. A mapping of property names and values, used to configure Hive.
+        #     Properties that conflict with values set by the Dataproc API may be
+        #     overwritten. Can include properties set in /etc/hadoop/conf/*-site.xml,
+        #     /etc/hive/conf/hive-site.xml, and classes in user code.
+        # @!attribute [rw] jar_file_uris
+        #   @return [Array<String>]
+        #     Optional. HCFS URIs of jar files to add to the CLASSPATH of the
+        #     Hive server and Hadoop MapReduce (MR) tasks. Can contain Hive SerDes
+        #     and UDFs.
+        class HiveJob
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+
+          # @!attribute [rw] key
+          #   @return [String]
+          # @!attribute [rw] value
+          #   @return [String]
+          class ScriptVariablesEntry
+            include Google::Protobuf::MessageExts
+            extend Google::Protobuf::MessageExts::ClassMethods
+          end
+
+          # @!attribute [rw] key
+          #   @return [String]
+          # @!attribute [rw] value
+          #   @return [String]
+          class PropertiesEntry
+            include Google::Protobuf::MessageExts
+            extend Google::Protobuf::MessageExts::ClassMethods
+          end
+        end
+
+        # A Dataproc job for running [Apache Spark
+        # SQL](http://spark.apache.org/sql/) queries.
+        # @!attribute [rw] query_file_uri
+        #   @return [String]
+        #     The HCFS URI of the script that contains SQL queries.
+        # @!attribute [rw] query_list
+        #   @return [Google::Cloud::Dataproc::V1beta2::QueryList]
+        #     A list of queries.
+        # @!attribute [rw] script_variables
+        #   @return [Google::Protobuf::Map{String => String}]
+        #     Optional. Mapping of query variable names to values (equivalent to the
+        #     Spark SQL command: SET `name="value";`).
+        # @!attribute [rw] properties
+        #   @return [Google::Protobuf::Map{String => String}]
+        #     Optional. A mapping of property names to values, used to configure
+        #     Spark SQL's SparkConf. Properties that conflict with values set by the
+        #     Dataproc API may be overwritten.
+        # @!attribute [rw] jar_file_uris
+        #   @return [Array<String>]
+        #     Optional. HCFS URIs of jar files to be added to the Spark CLASSPATH.
+        # @!attribute [rw] logging_config
+        #   @return [Google::Cloud::Dataproc::V1beta2::LoggingConfig]
+        #     Optional. The runtime log config for job execution.
+        class SparkSqlJob
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+
+          # @!attribute [rw] key
+          #   @return [String]
+          # @!attribute [rw] value
+          #   @return [String]
+          class ScriptVariablesEntry
+            include Google::Protobuf::MessageExts
+            extend Google::Protobuf::MessageExts::ClassMethods
+          end
+
+          # @!attribute [rw] key
+          #   @return [String]
+          # @!attribute [rw] value
+          #   @return [String]
+          class PropertiesEntry
+            include Google::Protobuf::MessageExts
+            extend Google::Protobuf::MessageExts::ClassMethods
+          end
+        end
+
+        # A Dataproc job for running [Apache Pig](https://pig.apache.org/)
+        # queries on YARN.
+        # @!attribute [rw] query_file_uri
+        #   @return [String]
+        #     The HCFS URI of the script that contains the Pig queries.
+        # @!attribute [rw] query_list
+        #   @return [Google::Cloud::Dataproc::V1beta2::QueryList]
+        #     A list of queries.
+        # @!attribute [rw] continue_on_failure
+        #   @return [Boolean]
+        #     Optional. Whether to continue executing queries if a query fails.
+        #     The default value is `false`. Setting to `true` can be useful when
+        #     executing independent parallel queries.
+        # @!attribute [rw] script_variables
+        #   @return [Google::Protobuf::Map{String => String}]
+        #     Optional. Mapping of query variable names to values (equivalent to the Pig
+        #     command: `name=[value]`).
+        # @!attribute [rw] properties
+        #   @return [Google::Protobuf::Map{String => String}]
+        #     Optional. A mapping of property names to values, used to configure Pig.
+        #     Properties that conflict with values set by the Dataproc API may be
+        #     overwritten. Can include properties set in /etc/hadoop/conf/*-site.xml,
+        #     /etc/pig/conf/pig.properties, and classes in user code.
+        # @!attribute [rw] jar_file_uris
+        #   @return [Array<String>]
+        #     Optional. HCFS URIs of jar files to add to the CLASSPATH of
+        #     the Pig Client and Hadoop MapReduce (MR) tasks. Can contain Pig UDFs.
+        # @!attribute [rw] logging_config
+        #   @return [Google::Cloud::Dataproc::V1beta2::LoggingConfig]
+        #     Optional. The runtime log config for job execution.
+        class PigJob
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+
+          # @!attribute [rw] key
+          #   @return [String]
+          # @!attribute [rw] value
+          #   @return [String]
+          class ScriptVariablesEntry
+            include Google::Protobuf::MessageExts
+            extend Google::Protobuf::MessageExts::ClassMethods
+          end
+
+          # @!attribute [rw] key
+          #   @return [String]
+          # @!attribute [rw] value
+          #   @return [String]
+          class PropertiesEntry
+            include Google::Protobuf::MessageExts
+            extend Google::Protobuf::MessageExts::ClassMethods
+          end
+        end
+
+        # A Dataproc job for running
+        # [Apache SparkR](https://spark.apache.org/docs/latest/sparkr.html)
+        # applications on YARN.
+        # @!attribute [rw] main_r_file_uri
+        #   @return [String]
+        #     Required. The HCFS URI of the main R file to use as the driver.
+        #     Must be a .R file.
+        # @!attribute [rw] args
+        #   @return [Array<String>]
+        #     Optional. The arguments to pass to the driver.  Do not include arguments,
+        #     such as `--conf`, that can be set as job properties, since a collision may
+        #     occur that causes an incorrect job submission.
+        # @!attribute [rw] file_uris
+        #   @return [Array<String>]
+        #     Optional. HCFS URIs of files to be copied to the working directory of
+        #     R drivers and distributed tasks. Useful for naively parallel tasks.
+        # @!attribute [rw] archive_uris
+        #   @return [Array<String>]
+        #     Optional. HCFS URIs of archives to be extracted in the working directory of
+        #     Spark drivers and tasks. Supported file types:
+        #     .jar, .tar, .tar.gz, .tgz, and .zip.
+        # @!attribute [rw] properties
+        #   @return [Google::Protobuf::Map{String => String}]
+        #     Optional. A mapping of property names to values, used to configure SparkR.
+        #     Properties that conflict with values set by the Dataproc API may be
+        #     overwritten. Can include properties set in
+        #     /etc/spark/conf/spark-defaults.conf and classes in user code.
+        # @!attribute [rw] logging_config
+        #   @return [Google::Cloud::Dataproc::V1beta2::LoggingConfig]
+        #     Optional. The runtime log config for job execution.
+        class SparkRJob
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+
+          # @!attribute [rw] key
+          #   @return [String]
+          # @!attribute [rw] value
+          #   @return [String]
+          class PropertiesEntry
+            include Google::Protobuf::MessageExts
+            extend Google::Protobuf::MessageExts::ClassMethods
+          end
+        end
+
+        # A Dataproc job for running [Presto](https://prestosql.io/) queries.
+        # **IMPORTANT**: The [Dataproc Presto Optional
+        # Component](/dataproc/docs/concepts/components/presto) must be enabled when
+        # the cluster is created to submit a Presto job to the cluster.
+        # @!attribute [rw] query_file_uri
+        #   @return [String]
+        #     The HCFS URI of the script that contains SQL queries.
+        # @!attribute [rw] query_list
+        #   @return [Google::Cloud::Dataproc::V1beta2::QueryList]
+        #     A list of queries.
+        # @!attribute [rw] continue_on_failure
+        #   @return [Boolean]
+        #     Optional. Whether to continue executing queries if a query fails.
+        #     The default value is `false`. Setting to `true` can be useful when
+        #     executing independent parallel queries.
+        # @!attribute [rw] output_format
+        #   @return [String]
+        #     Optional. The format in which query output will be displayed. See the
+        #     Presto documentation for supported output formats
+        # @!attribute [rw] client_tags
+        #   @return [Array<String>]
+        #     Optional. Presto client tags to attach to this query
+        # @!attribute [rw] properties
+        #   @return [Google::Protobuf::Map{String => String}]
+        #     Optional. A mapping of property names to values. Used to set Presto
+        #     [session properties](https://prestodb.io/docs/current/sql/set-session.html)
+        #     Equivalent to using the --session flag in the Presto CLI
+        # @!attribute [rw] logging_config
+        #   @return [Google::Cloud::Dataproc::V1beta2::LoggingConfig]
+        #     Optional. The runtime log config for job execution.
+        class PrestoJob
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+
+          # @!attribute [rw] key
+          #   @return [String]
+          # @!attribute [rw] value
+          #   @return [String]
+          class PropertiesEntry
+            include Google::Protobuf::MessageExts
+            extend Google::Protobuf::MessageExts::ClassMethods
+          end
+        end
+
+        # Dataproc job config.
+        # @!attribute [rw] cluster_name
+        #   @return [String]
+        #     Required. The name of the cluster where the job will be submitted.
+        # @!attribute [r] cluster_uuid
+        #   @return [String]
+        #     Output only. A cluster UUID generated by the Dataproc service when
+        #     the job is submitted.
+        class JobPlacement
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+        end
+
+        # Dataproc job status.
+        # @!attribute [r] state
+        #   @return [Google::Cloud::Dataproc::V1beta2::JobStatus::State]
+        #     Output only. A state message specifying the overall job state.
+        # @!attribute [r] details
+        #   @return [String]
+        #     Output only. Optional Job state details, such as an error
+        #     description if the state is <code>ERROR</code>.
+        # @!attribute [r] state_start_time
+        #   @return [Google::Protobuf::Timestamp]
+        #     Output only. The time when this state was entered.
+        # @!attribute [r] substate
+        #   @return [Google::Cloud::Dataproc::V1beta2::JobStatus::Substate]
+        #     Output only. Additional state information, which includes
+        #     status reported by the agent.
+        class JobStatus
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+
+          # The job state.
+          module State
+            # The job state is unknown.
+            STATE_UNSPECIFIED = 0
+
+            # The job is pending; it has been submitted, but is not yet running.
+            PENDING = 1
+
+            # Job has been received by the service and completed initial setup;
+            # it will soon be submitted to the cluster.
+            SETUP_DONE = 8
+
+            # The job is running on the cluster.
+            RUNNING = 2
+
+            # A CancelJob request has been received, but is pending.
+            CANCEL_PENDING = 3
+
+            # Transient in-flight resources have been canceled, and the request to
+            # cancel the running job has been issued to the cluster.
+            CANCEL_STARTED = 7
+
+            # The job cancellation was successful.
+            CANCELLED = 4
+
+            # The job has completed successfully.
+            DONE = 5
+
+            # The job has completed, but encountered an error.
+            ERROR = 6
+
+            # Job attempt has failed. The detail field contains failure details for
+            # this attempt.
+            #
+            # Applies to restartable jobs only.
+            ATTEMPT_FAILURE = 9
+          end
+
+          # The job substate.
+          module Substate
+            # The job substate is unknown.
+            UNSPECIFIED = 0
+
+            # The Job is submitted to the agent.
+            #
+            # Applies to RUNNING state.
+            SUBMITTED = 1
+
+            # The Job has been received and is awaiting execution (it may be waiting
+            # for a condition to be met). See the "details" field for the reason for
+            # the delay.
+            #
+            # Applies to RUNNING state.
+            QUEUED = 2
+
+            # The agent-reported status is out of date, which may be caused by a
+            # loss of communication between the agent and Dataproc. If the
+            # agent does not send a timely update, the job will fail.
+            #
+            # Applies to RUNNING state.
+            STALE_STATUS = 3
+          end
+        end
+
+        # Encapsulates the full scoping used to reference a job.
+        # @!attribute [rw] project_id
+        #   @return [String]
+        #     Required. The ID of the Google Cloud Platform project that the job
+        #     belongs to.
+        # @!attribute [rw] job_id
+        #   @return [String]
+        #     Optional. The job ID, which must be unique within the project.
+        #     The ID must contain only letters (a-z, A-Z), numbers (0-9),
+        #     underscores (_), or hyphens (-). The maximum length is 100 characters.
+        #
+        #     If not specified by the caller, the job ID will be provided by the server.
+        class JobReference
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+        end
+
+        # A YARN application created by a job. Application information is a subset of
+        # <code>org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto</code>.
+        #
+        # **Beta Feature**: This report is available for testing purposes only. It may
+        # be changed before final release.
+        # @!attribute [r] name
+        #   @return [String]
+        #     Output only. The application name.
+        # @!attribute [r] state
+        #   @return [Google::Cloud::Dataproc::V1beta2::YarnApplication::State]
+        #     Output only. The application state.
+        # @!attribute [r] progress
+        #   @return [Float]
+        #     Output only. The numerical progress of the application, from 1 to 100.
+        # @!attribute [r] tracking_url
+        #   @return [String]
+        #     Output only. The HTTP URL of the ApplicationMaster, HistoryServer, or
+        #     TimelineServer that provides application-specific information. The URL uses
+        #     the internal hostname, and requires a proxy server for resolution and,
+        #     possibly, access.
+        class YarnApplication
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+
+          # The application state, corresponding to
+          # <code>YarnProtos.YarnApplicationStateProto</code>.
+          module State
+            # Status is unspecified.
+            STATE_UNSPECIFIED = 0
+
+            # Status is NEW.
+            NEW = 1
+
+            # Status is NEW_SAVING.
+            NEW_SAVING = 2
+
+            # Status is SUBMITTED.
+            SUBMITTED = 3
+
+            # Status is ACCEPTED.
+            ACCEPTED = 4
+
+            # Status is RUNNING.
+            RUNNING = 5
+
+            # Status is FINISHED.
+            FINISHED = 6
+
+            # Status is FAILED.
+            FAILED = 7
+
+            # Status is KILLED.
+            KILLED = 8
+          end
+        end
+
+        # A Dataproc job resource.
+        # @!attribute [rw] reference
+        #   @return [Google::Cloud::Dataproc::V1beta2::JobReference]
+        #     Optional. The fully qualified reference to the job, which can be used to
+        #     obtain the equivalent REST path of the job resource. If this property
+        #     is not specified when a job is created, the server generates a
+        #     <code>job_id</code>.
+        # @!attribute [rw] placement
+        #   @return [Google::Cloud::Dataproc::V1beta2::JobPlacement]
+        #     Required. Job information, including how, when, and where to
+        #     run the job.
+        # @!attribute [rw] hadoop_job
+        #   @return [Google::Cloud::Dataproc::V1beta2::HadoopJob]
+        #     Optional. Job is a Hadoop job.
+        # @!attribute [rw] spark_job
+        #   @return [Google::Cloud::Dataproc::V1beta2::SparkJob]
+        #     Optional. Job is a Spark job.
+        # @!attribute [rw] pyspark_job
+        #   @return [Google::Cloud::Dataproc::V1beta2::PySparkJob]
+        #     Optional. Job is a PySpark job.
+        # @!attribute [rw] hive_job
+        #   @return [Google::Cloud::Dataproc::V1beta2::HiveJob]
+        #     Optional. Job is a Hive job.
+        # @!attribute [rw] pig_job
+        #   @return [Google::Cloud::Dataproc::V1beta2::PigJob]
+        #     Optional. Job is a Pig job.
+        # @!attribute [rw] spark_r_job
+        #   @return [Google::Cloud::Dataproc::V1beta2::SparkRJob]
+        #     Optional. Job is a SparkR job.
+        # @!attribute [rw] spark_sql_job
+        #   @return [Google::Cloud::Dataproc::V1beta2::SparkSqlJob]
+        #     Optional. Job is a SparkSql job.
+        # @!attribute [rw] presto_job
+        #   @return [Google::Cloud::Dataproc::V1beta2::PrestoJob]
+        #     Optional. Job is a Presto job.
+        # @!attribute [r] status
+        #   @return [Google::Cloud::Dataproc::V1beta2::JobStatus]
+        #     Output only. The job status. Additional application-specific
+        #     status information may be contained in the <code>type_job</code>
+        #     and <code>yarn_applications</code> fields.
+        # @!attribute [r] status_history
+        #   @return [Array<Google::Cloud::Dataproc::V1beta2::JobStatus>]
+        #     Output only. The previous job status.
+        # @!attribute [r] yarn_applications
+        #   @return [Array<Google::Cloud::Dataproc::V1beta2::YarnApplication>]
+        #     Output only. The collection of YARN applications spun up by this job.
+        #
+        #     **Beta** Feature: This report is available for testing purposes only. It
+        #     may be changed before final release.
+        # @!attribute [r] submitted_by
+        #   @return [String]
+        #     Output only. The email address of the user submitting the job. For jobs
+        #     submitted on the cluster, the address is <code>username@hostname</code>.
+        # @!attribute [r] driver_output_resource_uri
+        #   @return [String]
+        #     Output only. A URI pointing to the location of the stdout of the job's
+        #     driver program.
+        # @!attribute [r] driver_control_files_uri
+        #   @return [String]
+        #     Output only. If present, the location of miscellaneous control files
+        #     which may be used as part of job setup and handling. If not present,
+        #     control files may be placed in the same location as `driver_output_uri`.
+        # @!attribute [rw] labels
+        #   @return [Google::Protobuf::Map{String => String}]
+        #     Optional. The labels to associate with this job.
+        #     Label **keys** must contain 1 to 63 characters, and must conform to
+        #     [RFC 1035](https://www.ietf.org/rfc/rfc1035.txt).
+        #     Label **values** may be empty, but, if present, must contain 1 to 63
+        #     characters, and must conform to [RFC
+        #     1035](https://www.ietf.org/rfc/rfc1035.txt). No more than 32 labels can be
+        #     associated with a job.
+        # @!attribute [rw] scheduling
+        #   @return [Google::Cloud::Dataproc::V1beta2::JobScheduling]
+        #     Optional. Job scheduling configuration.
+        # @!attribute [r] job_uuid
+        #   @return [String]
+        #     Output only. A UUID that uniquely identifies a job within the project
+        #     over time. This is in contrast to a user-settable reference.job_id that
+        #     may be reused over time.
+        # @!attribute [r] done
+        #   @return [Boolean]
+        #     Output only. Indicates whether the job is completed. If the value is `false`,
+        #     the job is still in progress. If `true`, the job is completed, and
+        #     `status.state` field will indicate if it was successful, failed,
+        #     or cancelled.
+        class Job
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+
+          # @!attribute [rw] key
+          #   @return [String]
+          # @!attribute [rw] value
+          #   @return [String]
+          class LabelsEntry
+            include Google::Protobuf::MessageExts
+            extend Google::Protobuf::MessageExts::ClassMethods
+          end
+        end
+
+        # Job scheduling options.
+        # @!attribute [rw] max_failures_per_hour
+        #   @return [Integer]
+        #     Optional. Maximum number of times per hour a driver may be restarted as
+        #     a result of driver terminating with non-zero code before job is
+        #     reported failed.
+        #
+        #     A job may be reported as thrashing if driver exits with non-zero code
+        #     4 times within 10 minute window.
+        #
+        #     Maximum value is 10.
+        class JobScheduling
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+        end
+
+        # Job Operation metadata.
+        # @!attribute [r] job_id
+        #   @return [String]
+        #     Output only. The job id.
+        # @!attribute [r] status
+        #   @return [Google::Cloud::Dataproc::V1beta2::JobStatus]
+        #     Output only. Most recent job status.
+        # @!attribute [r] operation_type
+        #   @return [String]
+        #     Output only. Operation type.
+        # @!attribute [r] start_time
+        #   @return [Google::Protobuf::Timestamp]
+        #     Output only. Job submission time.
+        class JobMetadata
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+        end
+
+        # A request to submit a job.
+        # @!attribute [rw] project_id
+        #   @return [String]
+        #     Required. The ID of the Google Cloud Platform project that the job
+        #     belongs to.
+        # @!attribute [rw] region
+        #   @return [String]
+        #     Required. The Dataproc region in which to handle the request.
+        # @!attribute [rw] job
+        #   @return [Google::Cloud::Dataproc::V1beta2::Job]
+        #     Required. The job resource.
+        # @!attribute [rw] request_id
+        #   @return [String]
+        #     Optional. A unique id used to identify the request. If the server
+        #     receives two {Google::Cloud::Dataproc::V1beta2::SubmitJobRequest SubmitJobRequest} requests  with the same
+        #     id, then the second request will be ignored and the
+        #     first {Google::Cloud::Dataproc::V1beta2::Job Job} created and stored in the backend
+        #     is returned.
+        #
+        #     It is recommended to always set this value to a
+        #     [UUID](https://en.wikipedia.org/wiki/Universally_unique_identifier).
+        #
+        #     The id must contain only letters (a-z, A-Z), numbers (0-9),
+        #     underscores (_), and hyphens (-). The maximum length is 40 characters.
+        class SubmitJobRequest
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+        end
+
+        # A request to get the resource representation for a job in a project.
+        # @!attribute [rw] project_id
+        #   @return [String]
+        #     Required. The ID of the Google Cloud Platform project that the job
+        #     belongs to.
+        # @!attribute [rw] region
+        #   @return [String]
+        #     Required. The Dataproc region in which to handle the request.
+        # @!attribute [rw] job_id
+        #   @return [String]
+        #     Required. The job ID.
+        class GetJobRequest
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+        end
+
+        # A request to list jobs in a project.
+        # @!attribute [rw] project_id
+        #   @return [String]
+        #     Required. The ID of the Google Cloud Platform project that the job
+        #     belongs to.
+        # @!attribute [rw] region
+        #   @return [String]
+        #     Required. The Dataproc region in which to handle the request.
+        # @!attribute [rw] page_size
+        #   @return [Integer]
+        #     Optional. The number of results to return in each response.
+        # @!attribute [rw] page_token
+        #   @return [String]
+        #     Optional. The page token, returned by a previous call, to request the
+        #     next page of results.
+        # @!attribute [rw] cluster_name
+        #   @return [String]
+        #     Optional. If set, the returned jobs list includes only jobs that were
+        #     submitted to the named cluster.
+        # @!attribute [rw] job_state_matcher
+        #   @return [Google::Cloud::Dataproc::V1beta2::ListJobsRequest::JobStateMatcher]
+        #     Optional. Specifies enumerated categories of jobs to list.
+        #     (default = match ALL jobs).
+        #
+        #     If `filter` is provided, `jobStateMatcher` will be ignored.
+        # @!attribute [rw] filter
+        #   @return [String]
+        #     Optional. A filter constraining the jobs to list. Filters are
+        #     case-sensitive and have the following syntax:
+        #
+        #     [field = value] AND [field [= value]] ...
+        #
+        #     where **field** is `status.state` or `labels.[KEY]`, and `[KEY]` is a label
+        #     key. **value** can be `*` to match all values.
+        #     `status.state` can be either `ACTIVE` or `NON_ACTIVE`.
+        #     Only the logical `AND` operator is supported; space-separated items are
+        #     treated as having an implicit `AND` operator.
+        #
+        #     Example filter:
+        #
+        #     status.state = ACTIVE AND labels.env = staging AND labels.starred = *
+        class ListJobsRequest
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+
+          # A matcher that specifies categories of job states.
+          module JobStateMatcher
+            # Match all jobs, regardless of state.
+            ALL = 0
+
+            # Only match jobs in non-terminal states: PENDING, RUNNING, or
+            # CANCEL_PENDING.
+            ACTIVE = 1
+
+            # Only match jobs in terminal states: CANCELLED, DONE, or ERROR.
+            NON_ACTIVE = 2
+          end
+        end
+
+        # A request to update a job.
+        # @!attribute [rw] project_id
+        #   @return [String]
+        #     Required. The ID of the Google Cloud Platform project that the job
+        #     belongs to.
+        # @!attribute [rw] region
+        #   @return [String]
+        #     Required. The Dataproc region in which to handle the request.
+        # @!attribute [rw] job_id
+        #   @return [String]
+        #     Required. The job ID.
+        # @!attribute [rw] job
+        #   @return [Google::Cloud::Dataproc::V1beta2::Job]
+        #     Required. The changes to the job.
+        # @!attribute [rw] update_mask
+        #   @return [Google::Protobuf::FieldMask]
+        #     Required. Specifies the path, relative to <code>Job</code>, of
+        #     the field to update. For example, to update the labels of a Job the
+        #     <code>update_mask</code> parameter would be specified as
+        #     <code>labels</code>, and the `PATCH` request body would specify the new
+        #     value. <strong>Note:</strong> Currently, <code>labels</code> is the only
+        #     field that can be updated.
+        class UpdateJobRequest
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+        end
+
+        # A list of jobs in a project.
+        # @!attribute [r] jobs
+        #   @return [Array<Google::Cloud::Dataproc::V1beta2::Job>]
+        #     Output only. Jobs list.
+        # @!attribute [rw] next_page_token
+        #   @return [String]
+        #     Optional. This token is included in the response if there are more results
+        #     to fetch. To fetch additional results, provide this value as the
+        #     `page_token` in a subsequent <code>ListJobsRequest</code>.
+        class ListJobsResponse
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+        end
+
+        # A request to cancel a job.
+        # @!attribute [rw] project_id
+        #   @return [String]
+        #     Required. The ID of the Google Cloud Platform project that the job
+        #     belongs to.
+        # @!attribute [rw] region
+        #   @return [String]
+        #     Required. The Dataproc region in which to handle the request.
+        # @!attribute [rw] job_id
+        #   @return [String]
+        #     Required. The job ID.
+        class CancelJobRequest
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+        end
+
+        # A request to delete a job.
+        # @!attribute [rw] project_id
+        #   @return [String]
+        #     Required. The ID of the Google Cloud Platform project that the job
+        #     belongs to.
+        # @!attribute [rw] region
+        #   @return [String]
+        #     Required. The Dataproc region in which to handle the request.
+        # @!attribute [rw] job_id
+        #   @return [String]
+        #     Required. The job ID.
+        class DeleteJobRequest
+          include Google::Protobuf::MessageExts
+          extend Google::Protobuf::MessageExts::ClassMethods
+        end
+      end
+    end
+  end
+end