File: dataproc_v1alpha1.projects.regions.jobs.html

package info (click to toggle)
python-googleapi 1.5.5-1
links: PTS
area: main
in suites: buster, stretch
size: 39,832 kB
ctags: 5,921
sloc: python: 7,176; makefile: 64; sh: 53; xml: 5
file content (1056 lines) | stat: -rw-r--r-- 82,792 bytes
<html><body>
<style>

body, h1, h2, h3, div, span, p, pre, a {
  margin: 0;
  padding: 0;
  border: 0;
  font-weight: inherit;
  font-style: inherit;
  font-size: 100%;
  font-family: inherit;
  vertical-align: baseline;
}

body {
  font-size: 13px;
  padding: 1em;
}

h1 {
  font-size: 26px;
  margin-bottom: 1em;
}

h2 {
  font-size: 24px;
  margin-bottom: 1em;
}

h3 {
  font-size: 20px;
  margin-bottom: 1em;
  margin-top: 1em;
}

pre, code {
  line-height: 1.5;
  font-family: Monaco, 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', 'Lucida Console', monospace;
}

pre {
  margin-top: 0.5em;
}

h1, h2, h3, p {
  font-family: Arial, sans serif;
}

h1, h2, h3 {
  border-bottom: solid #CCC 1px;
}

.toc_element {
  margin-top: 0.5em;
}

.firstline {
  margin-left: 2 em;
}

.method  {
  margin-top: 1em;
  border: solid 1px #CCC;
  padding: 1em;
  background: #EEE;
}

.details {
  font-weight: bold;
  font-size: 14px;
}

</style>

<h1><a href="dataproc_v1alpha1.html">Google Cloud Dataproc API</a> . <a href="dataproc_v1alpha1.projects.html">projects</a> . <a href="dataproc_v1alpha1.projects.regions.html">regions</a> . <a href="dataproc_v1alpha1.projects.regions.jobs.html">jobs</a></h1>
<h2>Instance Methods</h2>
<p class="toc_element">
  <code><a href="#cancel">cancel(projectId, region, jobId, body, x__xgafv=None)</a></code></p>
<p class="firstline">Starts a job cancellation request. To access the job resource after cancellation, call regions/{region}/jobs:list or regions/{region}/jobs:get.</p>
<p class="toc_element">
  <code><a href="#delete">delete(projectId, region, jobId, x__xgafv=None)</a></code></p>
<p class="firstline">Deletes the job from the project. If the job is active, the delete fails, and the response returns `FAILED_PRECONDITION`.</p>
<p class="toc_element">
  <code><a href="#get">get(projectId, region, jobId, x__xgafv=None)</a></code></p>
<p class="firstline">Gets the resource representation for a job in a project.</p>
<p class="toc_element">
  <code><a href="#submit">submit(projectId, region, body, x__xgafv=None)</a></code></p>
<p class="firstline">Submits a job to a cluster.</p>
<h3>Method Details</h3>
<div class="method">
    <code class="details" id="cancel">cancel(projectId, region, jobId, body, x__xgafv=None)</code>
  <pre>Starts a job cancellation request. To access the job resource after cancellation, call regions/{region}/jobs:list or regions/{region}/jobs:get.

Args:
  projectId: string, [Required] The ID of the Google Cloud Platform project that the job belongs to. (required)
  region: string, [Required] The Dataproc region in which to handle the request. (required)
  jobId: string, [Required] The job ID. (required)
  body: object, The request body. (required)
    The object takes the form of:

{ # A request to cancel a job.
  }

  x__xgafv: string, V1 error format.

Returns:
  An object of the form:

    { # A Cloud Dataproc job resource.
    "status": { # Cloud Dataproc job status. # [Output-only] The job status. Additional application-specific status information may be contained in the type_job and yarn_applications fields.
      "stateStartTime": "A String", # [Output-only] The time when this state was entered.
      "insertTime": "A String", # The time of the job request.
      "state": "A String", # [Required] A state message specifying the overall job state.
      "details": "A String", # [Optional] Job state details, such as an error description if the state is ERROR.
      "startTime": "A String", # The time when the server started the job.
      "endTime": "A String", # The time when the job completed.
    },
    "hadoopJob": { # A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN. # Job is a Hadoop job.
      "jarFileUris": [ # [Optional] Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
        "A String",
      ],
      "args": [ # [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.
        "A String",
      ],
      "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
        "driverLogLevels": { # 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
          "a_key": "A String",
        },
      },
      "fileUris": [ # [Optional] HCFS URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.
        "A String",
      ],
      "mainClass": "A 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.
      "archiveUris": [ # [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.
        "A String",
      ],
      "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (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
      "properties": { # [Optional] A mapping of property names to values, used to configure Hadoop. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site and classes in user code.
        "a_key": "A String",
      },
    },
    "statusHistory": [ # [Output-only] The previous job status.
      { # Cloud Dataproc job status.
        "stateStartTime": "A String", # [Output-only] The time when this state was entered.
        "insertTime": "A String", # The time of the job request.
        "state": "A String", # [Required] A state message specifying the overall job state.
        "details": "A String", # [Optional] Job state details, such as an error description if the state is ERROR.
        "startTime": "A String", # The time when the server started the job.
        "endTime": "A String", # The time when the job completed.
      },
    ],
    "placement": { # Cloud Dataproc job configuration. # [Required] Job information, including how, when, and where to run the job.
      "clusterName": "A String", # [Required] The name of the cluster where the job will be submitted.
      "clusterUuid": "A String", # [Output-only] A cluster UUID generated by the Dataproc service when the job is submitted.
    },
    "reference": { # Encapsulates the full scoping used to reference a job. # [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 job_id.
      "projectId": "A String", # [Required] The ID of the Google Cloud Platform project that the job belongs to.
      "jobId": "A String", # [Required] The job ID, which must be unique within the project. The job ID is generated by the server upon job submission or provided by the user as a means to perform retries without creating duplicate jobs. The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), or dashes (-). The maximum length is 512 characters.
    },
    "sparkSqlJob": { # A Cloud Dataproc job for running Spark SQL queries. # Job is a SparkSql job.
      "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
      "scriptVariables": { # [Optional] Mapping of query variable names to values (equivalent to the Spark SQL command: SET name="value";).
        "a_key": "A String",
      },
      "jarFileUris": [ # [Optional] HCFS URIs of jar files to be added to the Spark CLASSPATH.
        "A String",
      ],
      "queryList": { # A list of queries to run on a cluster. # A list of queries.
        "queries": [ # [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", ] } }
          "A String",
        ],
      },
      "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
        "driverLogLevels": { # 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
          "a_key": "A String",
        },
      },
      "properties": { # [Optional] A mapping of property names to values, used to configure Spark SQL's SparkConf. Properties that conflict with values set by the Cloud Dataproc API may be overwritten.
        "a_key": "A String",
      },
    },
    "driverOutputUri": "A String", # [Output-only] A URI pointing to the location of the mixed stdout/stderr of the job's driver program—for example, gs://sysbucket123/foo-cluster/jobid-123/driver/output.
    "pigJob": { # A Cloud Dataproc job for running Pig queries on YARN. # Job is a Pig job.
      "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
      "scriptVariables": { # [Optional] Mapping of query variable names to values (equivalent to the Pig command: "name=[value]").
        "a_key": "A String",
      },
      "jarFileUris": [ # [Optional] HCFS URIs of jar files to add to the CLASSPATH of the Pig Client and Hadoop MapReduce (MR) tasks. Can contain Pig UDFs.
        "A String",
      ],
      "queryList": { # A list of queries to run on a cluster. # A list of queries.
        "queries": [ # [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", ] } }
          "A String",
        ],
      },
      "continueOnFailure": True or False, # [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.
      "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
        "driverLogLevels": { # 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
          "a_key": "A String",
        },
      },
      "properties": { # [Optional] A mapping of property names to values, used to configure Pig. Properties that conflict with values set by the Cloud 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.
        "a_key": "A String",
      },
    },
    "driverOutputResourceUri": "A String", # [Output-only] A URI pointing to the location of the stdout of the job's driver program.
    "submittedBy": "A String", # [Output-only] The email address of the user submitting the job. For jobs submitted on the cluster, the address is username@hostname.
    "driverInputResourceUri": "A String", # [Output-only] A URI pointing to the location of the stdin of the job's driver program, only set if the job is interactive.
    "driverControlFilesUri": "A 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.
    "sparkJob": { # A Cloud Dataproc job for running Spark applications on YARN. # Job is a Spark job.
      "jarFileUris": [ # [Optional] HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
        "A String",
      ],
      "args": [ # [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.
        "A String",
      ],
      "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
        "driverLogLevels": { # 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
          "a_key": "A String",
        },
      },
      "fileUris": [ # [Optional] HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
        "A String",
      ],
      "mainClass": "A 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.
      "archiveUris": [ # [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.
        "A String",
      ],
      "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (HCFS) URI of the jar file that contains the main class.
      "properties": { # [Optional] A mapping of property names to values, used to configure Spark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.
        "a_key": "A String",
      },
    },
    "yarnApplications": [ # [Output-only] The collection of Yarn applications spun up by this job.
      { # A YARN application created by a job. Application information is a subset of org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto.
        "progress": 3.14, # [Required] The numerical progress of the application, from 1 to 100.
        "state": "A String", # [Required] The application state.
        "name": "A String", # [Required] The application name.
        "trackingUrl": "A String", # [Optional] 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.
      },
    ],
    "pysparkJob": { # A Cloud Dataproc job for running PySpark applications on YARN. # Job is a Pyspark job.
      "mainPythonFileUri": "A String", # [Required] The Hadoop Compatible Filesystem (HCFS) URI of the main Python file to use as the driver. Must be a .py file.
      "args": [ # [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.
        "A String",
      ],
      "jarFileUris": [ # [Optional] HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
        "A String",
      ],
      "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
        "driverLogLevels": { # 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
          "a_key": "A String",
        },
      },
      "fileUris": [ # [Optional] HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.
        "A String",
      ],
      "archiveUris": [ # [Optional] HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
        "A String",
      ],
      "pythonFileUris": [ # [Optional] HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
        "A String",
      ],
      "properties": { # [Optional] A mapping of property names to values, used to configure PySpark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.
        "a_key": "A String",
      },
    },
    "hiveJob": { # A Cloud Dataproc job for running Hive queries on YARN. # Job is a Hive job.
      "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
      "scriptVariables": { # [Optional] Mapping of query variable names to values (equivalent to the Hive command: 'SET name="value";').
        "a_key": "A String",
      },
      "jarFileUris": [ # [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.
        "A String",
      ],
      "queryList": { # A list of queries to run on a cluster. # A list of queries.
        "queries": [ # [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", ] } }
          "A String",
        ],
      },
      "continueOnFailure": True or False, # [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.
      "properties": { # [Optional] A mapping of property names and values, used to configure Hive. Properties that conflict with values set by the Cloud 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.
        "a_key": "A String",
      },
    },
    "interactive": True or False, # [Optional] If set to true, then the driver's stdin will be kept open and driver_input_uri will be set to provide a path at which additional input can be sent to the driver.
  }</pre>
</div>

<div class="method">
    <code class="details" id="delete">delete(projectId, region, jobId, x__xgafv=None)</code>
  <pre>Deletes the job from the project. If the job is active, the delete fails, and the response returns `FAILED_PRECONDITION`.

Args:
  projectId: string, [Required] The ID of the Google Cloud Platform project that the job belongs to. (required)
  region: string, [Required] The Dataproc region in which to handle the request. (required)
  jobId: string, [Required] The job ID. (required)
  x__xgafv: string, V1 error format.

Returns:
  An object of the form:

    { # A Cloud Dataproc job resource.
    "status": { # Cloud Dataproc job status. # [Output-only] The job status. Additional application-specific status information may be contained in the type_job and yarn_applications fields.
      "stateStartTime": "A String", # [Output-only] The time when this state was entered.
      "insertTime": "A String", # The time of the job request.
      "state": "A String", # [Required] A state message specifying the overall job state.
      "details": "A String", # [Optional] Job state details, such as an error description if the state is ERROR.
      "startTime": "A String", # The time when the server started the job.
      "endTime": "A String", # The time when the job completed.
    },
    "hadoopJob": { # A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN. # Job is a Hadoop job.
      "jarFileUris": [ # [Optional] Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
        "A String",
      ],
      "args": [ # [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.
        "A String",
      ],
      "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
        "driverLogLevels": { # 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
          "a_key": "A String",
        },
      },
      "fileUris": [ # [Optional] HCFS URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.
        "A String",
      ],
      "mainClass": "A 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.
      "archiveUris": [ # [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.
        "A String",
      ],
      "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (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
      "properties": { # [Optional] A mapping of property names to values, used to configure Hadoop. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site and classes in user code.
        "a_key": "A String",
      },
    },
    "statusHistory": [ # [Output-only] The previous job status.
      { # Cloud Dataproc job status.
        "stateStartTime": "A String", # [Output-only] The time when this state was entered.
        "insertTime": "A String", # The time of the job request.
        "state": "A String", # [Required] A state message specifying the overall job state.
        "details": "A String", # [Optional] Job state details, such as an error description if the state is ERROR.
        "startTime": "A String", # The time when the server started the job.
        "endTime": "A String", # The time when the job completed.
      },
    ],
    "placement": { # Cloud Dataproc job configuration. # [Required] Job information, including how, when, and where to run the job.
      "clusterName": "A String", # [Required] The name of the cluster where the job will be submitted.
      "clusterUuid": "A String", # [Output-only] A cluster UUID generated by the Dataproc service when the job is submitted.
    },
    "reference": { # Encapsulates the full scoping used to reference a job. # [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 job_id.
      "projectId": "A String", # [Required] The ID of the Google Cloud Platform project that the job belongs to.
      "jobId": "A String", # [Required] The job ID, which must be unique within the project. The job ID is generated by the server upon job submission or provided by the user as a means to perform retries without creating duplicate jobs. The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), or dashes (-). The maximum length is 512 characters.
    },
    "sparkSqlJob": { # A Cloud Dataproc job for running Spark SQL queries. # Job is a SparkSql job.
      "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
      "scriptVariables": { # [Optional] Mapping of query variable names to values (equivalent to the Spark SQL command: SET name="value";).
        "a_key": "A String",
      },
      "jarFileUris": [ # [Optional] HCFS URIs of jar files to be added to the Spark CLASSPATH.
        "A String",
      ],
      "queryList": { # A list of queries to run on a cluster. # A list of queries.
        "queries": [ # [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", ] } }
          "A String",
        ],
      },
      "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
        "driverLogLevels": { # 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
          "a_key": "A String",
        },
      },
      "properties": { # [Optional] A mapping of property names to values, used to configure Spark SQL's SparkConf. Properties that conflict with values set by the Cloud Dataproc API may be overwritten.
        "a_key": "A String",
      },
    },
    "driverOutputUri": "A String", # [Output-only] A URI pointing to the location of the mixed stdout/stderr of the job's driver program—for example, gs://sysbucket123/foo-cluster/jobid-123/driver/output.
    "pigJob": { # A Cloud Dataproc job for running Pig queries on YARN. # Job is a Pig job.
      "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
      "scriptVariables": { # [Optional] Mapping of query variable names to values (equivalent to the Pig command: "name=[value]").
        "a_key": "A String",
      },
      "jarFileUris": [ # [Optional] HCFS URIs of jar files to add to the CLASSPATH of the Pig Client and Hadoop MapReduce (MR) tasks. Can contain Pig UDFs.
        "A String",
      ],
      "queryList": { # A list of queries to run on a cluster. # A list of queries.
        "queries": [ # [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", ] } }
          "A String",
        ],
      },
      "continueOnFailure": True or False, # [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.
      "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
        "driverLogLevels": { # 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
          "a_key": "A String",
        },
      },
      "properties": { # [Optional] A mapping of property names to values, used to configure Pig. Properties that conflict with values set by the Cloud 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.
        "a_key": "A String",
      },
    },
    "driverOutputResourceUri": "A String", # [Output-only] A URI pointing to the location of the stdout of the job's driver program.
    "submittedBy": "A String", # [Output-only] The email address of the user submitting the job. For jobs submitted on the cluster, the address is username@hostname.
    "driverInputResourceUri": "A String", # [Output-only] A URI pointing to the location of the stdin of the job's driver program, only set if the job is interactive.
    "driverControlFilesUri": "A 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.
    "sparkJob": { # A Cloud Dataproc job for running Spark applications on YARN. # Job is a Spark job.
      "jarFileUris": [ # [Optional] HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
        "A String",
      ],
      "args": [ # [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.
        "A String",
      ],
      "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
        "driverLogLevels": { # 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
          "a_key": "A String",
        },
      },
      "fileUris": [ # [Optional] HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
        "A String",
      ],
      "mainClass": "A 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.
      "archiveUris": [ # [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.
        "A String",
      ],
      "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (HCFS) URI of the jar file that contains the main class.
      "properties": { # [Optional] A mapping of property names to values, used to configure Spark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.
        "a_key": "A String",
      },
    },
    "yarnApplications": [ # [Output-only] The collection of Yarn applications spun up by this job.
      { # A YARN application created by a job. Application information is a subset of org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto.
        "progress": 3.14, # [Required] The numerical progress of the application, from 1 to 100.
        "state": "A String", # [Required] The application state.
        "name": "A String", # [Required] The application name.
        "trackingUrl": "A String", # [Optional] 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.
      },
    ],
    "pysparkJob": { # A Cloud Dataproc job for running PySpark applications on YARN. # Job is a Pyspark job.
      "mainPythonFileUri": "A String", # [Required] The Hadoop Compatible Filesystem (HCFS) URI of the main Python file to use as the driver. Must be a .py file.
      "args": [ # [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.
        "A String",
      ],
      "jarFileUris": [ # [Optional] HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
        "A String",
      ],
      "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
        "driverLogLevels": { # 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
          "a_key": "A String",
        },
      },
      "fileUris": [ # [Optional] HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.
        "A String",
      ],
      "archiveUris": [ # [Optional] HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
        "A String",
      ],
      "pythonFileUris": [ # [Optional] HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
        "A String",
      ],
      "properties": { # [Optional] A mapping of property names to values, used to configure PySpark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.
        "a_key": "A String",
      },
    },
    "hiveJob": { # A Cloud Dataproc job for running Hive queries on YARN. # Job is a Hive job.
      "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
      "scriptVariables": { # [Optional] Mapping of query variable names to values (equivalent to the Hive command: 'SET name="value";').
        "a_key": "A String",
      },
      "jarFileUris": [ # [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.
        "A String",
      ],
      "queryList": { # A list of queries to run on a cluster. # A list of queries.
        "queries": [ # [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", ] } }
          "A String",
        ],
      },
      "continueOnFailure": True or False, # [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.
      "properties": { # [Optional] A mapping of property names and values, used to configure Hive. Properties that conflict with values set by the Cloud 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.
        "a_key": "A String",
      },
    },
    "interactive": True or False, # [Optional] If set to true, then the driver's stdin will be kept open and driver_input_uri will be set to provide a path at which additional input can be sent to the driver.
  }</pre>
</div>

<div class="method">
    <code class="details" id="get">get(projectId, region, jobId, x__xgafv=None)</code>
  <pre>Gets the resource representation for a job in a project.

Args:
  projectId: string, [Required] The ID of the Google Cloud Platform project that the job belongs to. (required)
  region: string, [Required] The Dataproc region in which to handle the request. (required)
  jobId: string, [Required] The job ID. (required)
  x__xgafv: string, V1 error format.

Returns:
  An object of the form:

    { # A Cloud Dataproc job resource.
    "status": { # Cloud Dataproc job status. # [Output-only] The job status. Additional application-specific status information may be contained in the type_job and yarn_applications fields.
      "stateStartTime": "A String", # [Output-only] The time when this state was entered.
      "insertTime": "A String", # The time of the job request.
      "state": "A String", # [Required] A state message specifying the overall job state.
      "details": "A String", # [Optional] Job state details, such as an error description if the state is ERROR.
      "startTime": "A String", # The time when the server started the job.
      "endTime": "A String", # The time when the job completed.
    },
    "hadoopJob": { # A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN. # Job is a Hadoop job.
      "jarFileUris": [ # [Optional] Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
        "A String",
      ],
      "args": [ # [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.
        "A String",
      ],
      "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
        "driverLogLevels": { # 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
          "a_key": "A String",
        },
      },
      "fileUris": [ # [Optional] HCFS URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.
        "A String",
      ],
      "mainClass": "A 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.
      "archiveUris": [ # [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.
        "A String",
      ],
      "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (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
      "properties": { # [Optional] A mapping of property names to values, used to configure Hadoop. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site and classes in user code.
        "a_key": "A String",
      },
    },
    "statusHistory": [ # [Output-only] The previous job status.
      { # Cloud Dataproc job status.
        "stateStartTime": "A String", # [Output-only] The time when this state was entered.
        "insertTime": "A String", # The time of the job request.
        "state": "A String", # [Required] A state message specifying the overall job state.
        "details": "A String", # [Optional] Job state details, such as an error description if the state is ERROR.
        "startTime": "A String", # The time when the server started the job.
        "endTime": "A String", # The time when the job completed.
      },
    ],
    "placement": { # Cloud Dataproc job configuration. # [Required] Job information, including how, when, and where to run the job.
      "clusterName": "A String", # [Required] The name of the cluster where the job will be submitted.
      "clusterUuid": "A String", # [Output-only] A cluster UUID generated by the Dataproc service when the job is submitted.
    },
    "reference": { # Encapsulates the full scoping used to reference a job. # [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 job_id.
      "projectId": "A String", # [Required] The ID of the Google Cloud Platform project that the job belongs to.
      "jobId": "A String", # [Required] The job ID, which must be unique within the project. The job ID is generated by the server upon job submission or provided by the user as a means to perform retries without creating duplicate jobs. The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), or dashes (-). The maximum length is 512 characters.
    },
    "sparkSqlJob": { # A Cloud Dataproc job for running Spark SQL queries. # Job is a SparkSql job.
      "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
      "scriptVariables": { # [Optional] Mapping of query variable names to values (equivalent to the Spark SQL command: SET name="value";).
        "a_key": "A String",
      },
      "jarFileUris": [ # [Optional] HCFS URIs of jar files to be added to the Spark CLASSPATH.
        "A String",
      ],
      "queryList": { # A list of queries to run on a cluster. # A list of queries.
        "queries": [ # [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", ] } }
          "A String",
        ],
      },
      "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
        "driverLogLevels": { # 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
          "a_key": "A String",
        },
      },
      "properties": { # [Optional] A mapping of property names to values, used to configure Spark SQL's SparkConf. Properties that conflict with values set by the Cloud Dataproc API may be overwritten.
        "a_key": "A String",
      },
    },
    "driverOutputUri": "A String", # [Output-only] A URI pointing to the location of the mixed stdout/stderr of the job's driver program—for example, gs://sysbucket123/foo-cluster/jobid-123/driver/output.
    "pigJob": { # A Cloud Dataproc job for running Pig queries on YARN. # Job is a Pig job.
      "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
      "scriptVariables": { # [Optional] Mapping of query variable names to values (equivalent to the Pig command: "name=[value]").
        "a_key": "A String",
      },
      "jarFileUris": [ # [Optional] HCFS URIs of jar files to add to the CLASSPATH of the Pig Client and Hadoop MapReduce (MR) tasks. Can contain Pig UDFs.
        "A String",
      ],
      "queryList": { # A list of queries to run on a cluster. # A list of queries.
        "queries": [ # [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", ] } }
          "A String",
        ],
      },
      "continueOnFailure": True or False, # [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.
      "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
        "driverLogLevels": { # 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
          "a_key": "A String",
        },
      },
      "properties": { # [Optional] A mapping of property names to values, used to configure Pig. Properties that conflict with values set by the Cloud 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.
        "a_key": "A String",
      },
    },
    "driverOutputResourceUri": "A String", # [Output-only] A URI pointing to the location of the stdout of the job's driver program.
    "submittedBy": "A String", # [Output-only] The email address of the user submitting the job. For jobs submitted on the cluster, the address is username@hostname.
    "driverInputResourceUri": "A String", # [Output-only] A URI pointing to the location of the stdin of the job's driver program, only set if the job is interactive.
    "driverControlFilesUri": "A 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.
    "sparkJob": { # A Cloud Dataproc job for running Spark applications on YARN. # Job is a Spark job.
      "jarFileUris": [ # [Optional] HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
        "A String",
      ],
      "args": [ # [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.
        "A String",
      ],
      "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
        "driverLogLevels": { # 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
          "a_key": "A String",
        },
      },
      "fileUris": [ # [Optional] HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
        "A String",
      ],
      "mainClass": "A 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.
      "archiveUris": [ # [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.
        "A String",
      ],
      "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (HCFS) URI of the jar file that contains the main class.
      "properties": { # [Optional] A mapping of property names to values, used to configure Spark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.
        "a_key": "A String",
      },
    },
    "yarnApplications": [ # [Output-only] The collection of Yarn applications spun up by this job.
      { # A YARN application created by a job. Application information is a subset of org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto.
        "progress": 3.14, # [Required] The numerical progress of the application, from 1 to 100.
        "state": "A String", # [Required] The application state.
        "name": "A String", # [Required] The application name.
        "trackingUrl": "A String", # [Optional] 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.
      },
    ],
    "pysparkJob": { # A Cloud Dataproc job for running PySpark applications on YARN. # Job is a Pyspark job.
      "mainPythonFileUri": "A String", # [Required] The Hadoop Compatible Filesystem (HCFS) URI of the main Python file to use as the driver. Must be a .py file.
      "args": [ # [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.
        "A String",
      ],
      "jarFileUris": [ # [Optional] HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
        "A String",
      ],
      "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
        "driverLogLevels": { # 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
          "a_key": "A String",
        },
      },
      "fileUris": [ # [Optional] HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.
        "A String",
      ],
      "archiveUris": [ # [Optional] HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
        "A String",
      ],
      "pythonFileUris": [ # [Optional] HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
        "A String",
      ],
      "properties": { # [Optional] A mapping of property names to values, used to configure PySpark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.
        "a_key": "A String",
      },
    },
    "hiveJob": { # A Cloud Dataproc job for running Hive queries on YARN. # Job is a Hive job.
      "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
      "scriptVariables": { # [Optional] Mapping of query variable names to values (equivalent to the Hive command: 'SET name="value";').
        "a_key": "A String",
      },
      "jarFileUris": [ # [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.
        "A String",
      ],
      "queryList": { # A list of queries to run on a cluster. # A list of queries.
        "queries": [ # [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", ] } }
          "A String",
        ],
      },
      "continueOnFailure": True or False, # [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.
      "properties": { # [Optional] A mapping of property names and values, used to configure Hive. Properties that conflict with values set by the Cloud 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.
        "a_key": "A String",
      },
    },
    "interactive": True or False, # [Optional] If set to true, then the driver's stdin will be kept open and driver_input_uri will be set to provide a path at which additional input can be sent to the driver.
  }</pre>
</div>

<div class="method">
    <code class="details" id="submit">submit(projectId, region, body, x__xgafv=None)</code>
  <pre>Submits a job to a cluster.

Args:
  projectId: string, [Required] The ID of the Google Cloud Platform project that the job belongs to. (required)
  region: string, [Required] The Dataproc region in which to handle the request. (required)
  body: object, The request body. (required)
    The object takes the form of:

{ # A job submission request.
    "job": { # A Cloud Dataproc job resource. # [Required] The job resource.
      "status": { # Cloud Dataproc job status. # [Output-only] The job status. Additional application-specific status information may be contained in the type_job and yarn_applications fields.
        "stateStartTime": "A String", # [Output-only] The time when this state was entered.
        "insertTime": "A String", # The time of the job request.
        "state": "A String", # [Required] A state message specifying the overall job state.
        "details": "A String", # [Optional] Job state details, such as an error description if the state is ERROR.
        "startTime": "A String", # The time when the server started the job.
        "endTime": "A String", # The time when the job completed.
      },
      "hadoopJob": { # A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN. # Job is a Hadoop job.
        "jarFileUris": [ # [Optional] Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
          "A String",
        ],
        "args": [ # [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.
          "A String",
        ],
        "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
          "driverLogLevels": { # 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
            "a_key": "A String",
          },
        },
        "fileUris": [ # [Optional] HCFS URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.
          "A String",
        ],
        "mainClass": "A 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.
        "archiveUris": [ # [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.
          "A String",
        ],
        "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (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
        "properties": { # [Optional] A mapping of property names to values, used to configure Hadoop. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site and classes in user code.
          "a_key": "A String",
        },
      },
      "statusHistory": [ # [Output-only] The previous job status.
        { # Cloud Dataproc job status.
          "stateStartTime": "A String", # [Output-only] The time when this state was entered.
          "insertTime": "A String", # The time of the job request.
          "state": "A String", # [Required] A state message specifying the overall job state.
          "details": "A String", # [Optional] Job state details, such as an error description if the state is ERROR.
          "startTime": "A String", # The time when the server started the job.
          "endTime": "A String", # The time when the job completed.
        },
      ],
      "placement": { # Cloud Dataproc job configuration. # [Required] Job information, including how, when, and where to run the job.
        "clusterName": "A String", # [Required] The name of the cluster where the job will be submitted.
        "clusterUuid": "A String", # [Output-only] A cluster UUID generated by the Dataproc service when the job is submitted.
      },
      "reference": { # Encapsulates the full scoping used to reference a job. # [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 job_id.
        "projectId": "A String", # [Required] The ID of the Google Cloud Platform project that the job belongs to.
        "jobId": "A String", # [Required] The job ID, which must be unique within the project. The job ID is generated by the server upon job submission or provided by the user as a means to perform retries without creating duplicate jobs. The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), or dashes (-). The maximum length is 512 characters.
      },
      "sparkSqlJob": { # A Cloud Dataproc job for running Spark SQL queries. # Job is a SparkSql job.
        "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
        "scriptVariables": { # [Optional] Mapping of query variable names to values (equivalent to the Spark SQL command: SET name="value";).
          "a_key": "A String",
        },
        "jarFileUris": [ # [Optional] HCFS URIs of jar files to be added to the Spark CLASSPATH.
          "A String",
        ],
        "queryList": { # A list of queries to run on a cluster. # A list of queries.
          "queries": [ # [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", ] } }
            "A String",
          ],
        },
        "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
          "driverLogLevels": { # 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
            "a_key": "A String",
          },
        },
        "properties": { # [Optional] A mapping of property names to values, used to configure Spark SQL's SparkConf. Properties that conflict with values set by the Cloud Dataproc API may be overwritten.
          "a_key": "A String",
        },
      },
      "driverOutputUri": "A String", # [Output-only] A URI pointing to the location of the mixed stdout/stderr of the job's driver program—for example, gs://sysbucket123/foo-cluster/jobid-123/driver/output.
      "pigJob": { # A Cloud Dataproc job for running Pig queries on YARN. # Job is a Pig job.
        "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
        "scriptVariables": { # [Optional] Mapping of query variable names to values (equivalent to the Pig command: "name=[value]").
          "a_key": "A String",
        },
        "jarFileUris": [ # [Optional] HCFS URIs of jar files to add to the CLASSPATH of the Pig Client and Hadoop MapReduce (MR) tasks. Can contain Pig UDFs.
          "A String",
        ],
        "queryList": { # A list of queries to run on a cluster. # A list of queries.
          "queries": [ # [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", ] } }
            "A String",
          ],
        },
        "continueOnFailure": True or False, # [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.
        "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
          "driverLogLevels": { # 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
            "a_key": "A String",
          },
        },
        "properties": { # [Optional] A mapping of property names to values, used to configure Pig. Properties that conflict with values set by the Cloud 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.
          "a_key": "A String",
        },
      },
      "driverOutputResourceUri": "A String", # [Output-only] A URI pointing to the location of the stdout of the job's driver program.
      "submittedBy": "A String", # [Output-only] The email address of the user submitting the job. For jobs submitted on the cluster, the address is username@hostname.
      "driverInputResourceUri": "A String", # [Output-only] A URI pointing to the location of the stdin of the job's driver program, only set if the job is interactive.
      "driverControlFilesUri": "A 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.
      "sparkJob": { # A Cloud Dataproc job for running Spark applications on YARN. # Job is a Spark job.
        "jarFileUris": [ # [Optional] HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
          "A String",
        ],
        "args": [ # [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.
          "A String",
        ],
        "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
          "driverLogLevels": { # 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
            "a_key": "A String",
          },
        },
        "fileUris": [ # [Optional] HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
          "A String",
        ],
        "mainClass": "A 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.
        "archiveUris": [ # [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.
          "A String",
        ],
        "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (HCFS) URI of the jar file that contains the main class.
        "properties": { # [Optional] A mapping of property names to values, used to configure Spark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.
          "a_key": "A String",
        },
      },
      "yarnApplications": [ # [Output-only] The collection of Yarn applications spun up by this job.
        { # A YARN application created by a job. Application information is a subset of org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto.
          "progress": 3.14, # [Required] The numerical progress of the application, from 1 to 100.
          "state": "A String", # [Required] The application state.
          "name": "A String", # [Required] The application name.
          "trackingUrl": "A String", # [Optional] 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.
        },
      ],
      "pysparkJob": { # A Cloud Dataproc job for running PySpark applications on YARN. # Job is a Pyspark job.
        "mainPythonFileUri": "A String", # [Required] The Hadoop Compatible Filesystem (HCFS) URI of the main Python file to use as the driver. Must be a .py file.
        "args": [ # [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.
          "A String",
        ],
        "jarFileUris": [ # [Optional] HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
          "A String",
        ],
        "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
          "driverLogLevels": { # 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
            "a_key": "A String",
          },
        },
        "fileUris": [ # [Optional] HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.
          "A String",
        ],
        "archiveUris": [ # [Optional] HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
          "A String",
        ],
        "pythonFileUris": [ # [Optional] HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
          "A String",
        ],
        "properties": { # [Optional] A mapping of property names to values, used to configure PySpark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.
          "a_key": "A String",
        },
      },
      "hiveJob": { # A Cloud Dataproc job for running Hive queries on YARN. # Job is a Hive job.
        "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
        "scriptVariables": { # [Optional] Mapping of query variable names to values (equivalent to the Hive command: 'SET name="value";').
          "a_key": "A String",
        },
        "jarFileUris": [ # [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.
          "A String",
        ],
        "queryList": { # A list of queries to run on a cluster. # A list of queries.
          "queries": [ # [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", ] } }
            "A String",
          ],
        },
        "continueOnFailure": True or False, # [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.
        "properties": { # [Optional] A mapping of property names and values, used to configure Hive. Properties that conflict with values set by the Cloud 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.
          "a_key": "A String",
        },
      },
      "interactive": True or False, # [Optional] If set to true, then the driver's stdin will be kept open and driver_input_uri will be set to provide a path at which additional input can be sent to the driver.
    },
  }

  x__xgafv: string, V1 error format.

Returns:
  An object of the form:

    { # A Cloud Dataproc job resource.
    "status": { # Cloud Dataproc job status. # [Output-only] The job status. Additional application-specific status information may be contained in the type_job and yarn_applications fields.
      "stateStartTime": "A String", # [Output-only] The time when this state was entered.
      "insertTime": "A String", # The time of the job request.
      "state": "A String", # [Required] A state message specifying the overall job state.
      "details": "A String", # [Optional] Job state details, such as an error description if the state is ERROR.
      "startTime": "A String", # The time when the server started the job.
      "endTime": "A String", # The time when the job completed.
    },
    "hadoopJob": { # A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN. # Job is a Hadoop job.
      "jarFileUris": [ # [Optional] Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
        "A String",
      ],
      "args": [ # [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.
        "A String",
      ],
      "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
        "driverLogLevels": { # 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
          "a_key": "A String",
        },
      },
      "fileUris": [ # [Optional] HCFS URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.
        "A String",
      ],
      "mainClass": "A 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.
      "archiveUris": [ # [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.
        "A String",
      ],
      "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (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
      "properties": { # [Optional] A mapping of property names to values, used to configure Hadoop. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site and classes in user code.
        "a_key": "A String",
      },
    },
    "statusHistory": [ # [Output-only] The previous job status.
      { # Cloud Dataproc job status.
        "stateStartTime": "A String", # [Output-only] The time when this state was entered.
        "insertTime": "A String", # The time of the job request.
        "state": "A String", # [Required] A state message specifying the overall job state.
        "details": "A String", # [Optional] Job state details, such as an error description if the state is ERROR.
        "startTime": "A String", # The time when the server started the job.
        "endTime": "A String", # The time when the job completed.
      },
    ],
    "placement": { # Cloud Dataproc job configuration. # [Required] Job information, including how, when, and where to run the job.
      "clusterName": "A String", # [Required] The name of the cluster where the job will be submitted.
      "clusterUuid": "A String", # [Output-only] A cluster UUID generated by the Dataproc service when the job is submitted.
    },
    "reference": { # Encapsulates the full scoping used to reference a job. # [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 job_id.
      "projectId": "A String", # [Required] The ID of the Google Cloud Platform project that the job belongs to.
      "jobId": "A String", # [Required] The job ID, which must be unique within the project. The job ID is generated by the server upon job submission or provided by the user as a means to perform retries without creating duplicate jobs. The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), or dashes (-). The maximum length is 512 characters.
    },
    "sparkSqlJob": { # A Cloud Dataproc job for running Spark SQL queries. # Job is a SparkSql job.
      "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
      "scriptVariables": { # [Optional] Mapping of query variable names to values (equivalent to the Spark SQL command: SET name="value";).
        "a_key": "A String",
      },
      "jarFileUris": [ # [Optional] HCFS URIs of jar files to be added to the Spark CLASSPATH.
        "A String",
      ],
      "queryList": { # A list of queries to run on a cluster. # A list of queries.
        "queries": [ # [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", ] } }
          "A String",
        ],
      },
      "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
        "driverLogLevels": { # 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
          "a_key": "A String",
        },
      },
      "properties": { # [Optional] A mapping of property names to values, used to configure Spark SQL's SparkConf. Properties that conflict with values set by the Cloud Dataproc API may be overwritten.
        "a_key": "A String",
      },
    },
    "driverOutputUri": "A String", # [Output-only] A URI pointing to the location of the mixed stdout/stderr of the job's driver program—for example, gs://sysbucket123/foo-cluster/jobid-123/driver/output.
    "pigJob": { # A Cloud Dataproc job for running Pig queries on YARN. # Job is a Pig job.
      "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
      "scriptVariables": { # [Optional] Mapping of query variable names to values (equivalent to the Pig command: "name=[value]").
        "a_key": "A String",
      },
      "jarFileUris": [ # [Optional] HCFS URIs of jar files to add to the CLASSPATH of the Pig Client and Hadoop MapReduce (MR) tasks. Can contain Pig UDFs.
        "A String",
      ],
      "queryList": { # A list of queries to run on a cluster. # A list of queries.
        "queries": [ # [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", ] } }
          "A String",
        ],
      },
      "continueOnFailure": True or False, # [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.
      "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
        "driverLogLevels": { # 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
          "a_key": "A String",
        },
      },
      "properties": { # [Optional] A mapping of property names to values, used to configure Pig. Properties that conflict with values set by the Cloud 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.
        "a_key": "A String",
      },
    },
    "driverOutputResourceUri": "A String", # [Output-only] A URI pointing to the location of the stdout of the job's driver program.
    "submittedBy": "A String", # [Output-only] The email address of the user submitting the job. For jobs submitted on the cluster, the address is username@hostname.
    "driverInputResourceUri": "A String", # [Output-only] A URI pointing to the location of the stdin of the job's driver program, only set if the job is interactive.
    "driverControlFilesUri": "A 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.
    "sparkJob": { # A Cloud Dataproc job for running Spark applications on YARN. # Job is a Spark job.
      "jarFileUris": [ # [Optional] HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
        "A String",
      ],
      "args": [ # [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.
        "A String",
      ],
      "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
        "driverLogLevels": { # 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
          "a_key": "A String",
        },
      },
      "fileUris": [ # [Optional] HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
        "A String",
      ],
      "mainClass": "A 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.
      "archiveUris": [ # [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.
        "A String",
      ],
      "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (HCFS) URI of the jar file that contains the main class.
      "properties": { # [Optional] A mapping of property names to values, used to configure Spark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.
        "a_key": "A String",
      },
    },
    "yarnApplications": [ # [Output-only] The collection of Yarn applications spun up by this job.
      { # A YARN application created by a job. Application information is a subset of org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto.
        "progress": 3.14, # [Required] The numerical progress of the application, from 1 to 100.
        "state": "A String", # [Required] The application state.
        "name": "A String", # [Required] The application name.
        "trackingUrl": "A String", # [Optional] 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.
      },
    ],
    "pysparkJob": { # A Cloud Dataproc job for running PySpark applications on YARN. # Job is a Pyspark job.
      "mainPythonFileUri": "A String", # [Required] The Hadoop Compatible Filesystem (HCFS) URI of the main Python file to use as the driver. Must be a .py file.
      "args": [ # [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.
        "A String",
      ],
      "jarFileUris": [ # [Optional] HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
        "A String",
      ],
      "loggingConfiguration": { # The runtime logging configuration of the job. # [Optional] The runtime log configuration for job execution.
        "driverLogLevels": { # 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
          "a_key": "A String",
        },
      },
      "fileUris": [ # [Optional] HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.
        "A String",
      ],
      "archiveUris": [ # [Optional] HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
        "A String",
      ],
      "pythonFileUris": [ # [Optional] HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
        "A String",
      ],
      "properties": { # [Optional] A mapping of property names to values, used to configure PySpark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.
        "a_key": "A String",
      },
    },
    "hiveJob": { # A Cloud Dataproc job for running Hive queries on YARN. # Job is a Hive job.
      "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
      "scriptVariables": { # [Optional] Mapping of query variable names to values (equivalent to the Hive command: 'SET name="value";').
        "a_key": "A String",
      },
      "jarFileUris": [ # [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.
        "A String",
      ],
      "queryList": { # A list of queries to run on a cluster. # A list of queries.
        "queries": [ # [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", ] } }
          "A String",
        ],
      },
      "continueOnFailure": True or False, # [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.
      "properties": { # [Optional] A mapping of property names and values, used to configure Hive. Properties that conflict with values set by the Cloud 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.
        "a_key": "A String",
      },
    },
    "interactive": True or False, # [Optional] If set to true, then the driver's stdin will be kept open and driver_input_uri will be set to provide a path at which additional input can be sent to the driver.
  }</pre>
</div>

</body></html>