cancel(projectId, jobId, body, x__xgafv=None)
Starts a job cancellation request. To access the job resource after cancellation, call jobs.list or jobs.get.
delete(projectId, jobId, x__xgafv=None)
Deletes the job from the project. If the job is active, the delete fails, and the response returns FAILED_PRECONDITION.
get(projectId, jobId, x__xgafv=None)
Gets the resource representation for a job in a project.
Lists jobs in a project.
list_next(previous_request, previous_response)
Retrieves the next page of results.
patch(projectId, jobId, body, updateMask=None, x__xgafv=None)
Updates a job in a project.
submit(projectId, body, x__xgafv=None)
Submits a job to a cluster.
cancel(projectId, jobId, body, x__xgafv=None)
Starts a job cancellation request. To access the job resource after cancellation, call jobs.list or jobs.get.
Args:
projectId: string, Required The ID of the Google Cloud Platform project that the job belongs to. (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.
Allowed values
1 - v1 error format
2 - v2 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.
"state": "A String", # Required A state message specifying the overall job state.
"stateStartTime": "A String", # Output-only The time when this state was entered.
"substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
"details": "A String", # Optional Job state details, such as an error description if the state is ERROR.
},
"hadoopJob": { # A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN. # Job is a Hadoop job.
"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",
],
"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",
],
"jarFileUris": [ # Optional Jar file URIs to add to the CLASSPATHs of the Hadoop 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",
},
},
"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",
},
},
"labels": { # Optional The labels to associate with this job.Label keys must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}{0,62}Label values must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}\p{N}_-{0,63}No more than 64 labels can be associated with a given job.
"a_key": "A String",
},
"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 hyphens (-). The maximum length is 100 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",
},
},
"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.
},
],
"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",
],
"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",
},
},
"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 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.
"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",
},
},
"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.
"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.
"sparkJob": { # A Cloud Dataproc job for running Spark applications on YARN. # Job is a Spark job.
"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 Spark 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 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",
},
},
"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.
"scheduling": { # Job scheduling options.Beta Feature: These options are available for testing purposes only. They may be changed before final release. # Optional Job scheduling configuration.
"maxFailuresPerHour": 42, # 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.
},
"statusHistory": [ # Output-only The previous job status.
{ # Cloud Dataproc job status.
"state": "A String", # Required A state message specifying the overall job state.
"stateStartTime": "A String", # Output-only The time when this state was entered.
"substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
"details": "A String", # Optional Job state details, such as an error description if the state is ERROR.
},
],
"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, 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.
}
delete(projectId, jobId, x__xgafv=None)
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)
jobId: string, Required The job ID. (required)
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # A generic empty message that you can re-use to avoid defining duplicated empty messages in your APIs. A typical example is to use it as the request or the response type of an API method. For instance:
# service Foo {
# rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);
# }
# The JSON representation for Empty is empty JSON object {}.
}
get(projectId, jobId, x__xgafv=None)
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)
jobId: string, Required The job ID. (required)
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 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.
"state": "A String", # Required A state message specifying the overall job state.
"stateStartTime": "A String", # Output-only The time when this state was entered.
"substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
"details": "A String", # Optional Job state details, such as an error description if the state is ERROR.
},
"hadoopJob": { # A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN. # Job is a Hadoop job.
"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",
],
"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",
],
"jarFileUris": [ # Optional Jar file URIs to add to the CLASSPATHs of the Hadoop 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",
},
},
"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",
},
},
"labels": { # Optional The labels to associate with this job.Label keys must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}{0,62}Label values must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}\p{N}_-{0,63}No more than 64 labels can be associated with a given job.
"a_key": "A String",
},
"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 hyphens (-). The maximum length is 100 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",
},
},
"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.
},
],
"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",
],
"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",
},
},
"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 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.
"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",
},
},
"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.
"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.
"sparkJob": { # A Cloud Dataproc job for running Spark applications on YARN. # Job is a Spark job.
"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 Spark 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 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",
},
},
"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.
"scheduling": { # Job scheduling options.Beta Feature: These options are available for testing purposes only. They may be changed before final release. # Optional Job scheduling configuration.
"maxFailuresPerHour": 42, # 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.
},
"statusHistory": [ # Output-only The previous job status.
{ # Cloud Dataproc job status.
"state": "A String", # Required A state message specifying the overall job state.
"stateStartTime": "A String", # Output-only The time when this state was entered.
"substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
"details": "A String", # Optional Job state details, such as an error description if the state is ERROR.
},
],
"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, 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.
}
list(projectId, pageSize=None, x__xgafv=None, jobStateMatcher=None, pageToken=None, clusterName=None, filter=None)
Lists jobs in a project.
Args:
projectId: string, Required The ID of the Google Cloud Platform project that the job belongs to. (required)
pageSize: integer, Optional The number of results to return in each response.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
jobStateMatcher: string, Optional Specifies enumerated categories of jobs to list.
pageToken: string, Optional The page token, returned by a previous call, to request the next page of results.
clusterName: string, Optional If set, the returned jobs list includes only jobs that were submitted to the named cluster.
filter: string, Optional A filter constraining which jobs to list. Valid filters contain job state and label terms such as: labels.key1 = val1 AND (labels.k2 = val2 OR labels.k3 = val3)
Returns:
An object of the form:
{ # A list of jobs in a project.
"nextPageToken": "A 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 ListJobsRequest.
"jobs": [ # Output-only Jobs list.
{ # 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.
"state": "A String", # Required A state message specifying the overall job state.
"stateStartTime": "A String", # Output-only The time when this state was entered.
"substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
"details": "A String", # Optional Job state details, such as an error description if the state is ERROR.
},
"hadoopJob": { # A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN. # Job is a Hadoop job.
"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",
],
"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",
],
"jarFileUris": [ # Optional Jar file URIs to add to the CLASSPATHs of the Hadoop 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",
},
},
"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",
},
},
"labels": { # Optional The labels to associate with this job.Label keys must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}{0,62}Label values must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}\p{N}_-{0,63}No more than 64 labels can be associated with a given job.
"a_key": "A String",
},
"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 hyphens (-). The maximum length is 100 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",
},
},
"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.
},
],
"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",
],
"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",
},
},
"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 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.
"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",
},
},
"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.
"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.
"sparkJob": { # A Cloud Dataproc job for running Spark applications on YARN. # Job is a Spark job.
"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 Spark 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 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",
},
},
"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.
"scheduling": { # Job scheduling options.Beta Feature: These options are available for testing purposes only. They may be changed before final release. # Optional Job scheduling configuration.
"maxFailuresPerHour": 42, # 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.
},
"statusHistory": [ # Output-only The previous job status.
{ # Cloud Dataproc job status.
"state": "A String", # Required A state message specifying the overall job state.
"stateStartTime": "A String", # Output-only The time when this state was entered.
"substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
"details": "A String", # Optional Job state details, such as an error description if the state is ERROR.
},
],
"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, 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.
},
],
}
list_next(previous_request, previous_response)
Retrieves the next page of results.
Args:
previous_request: The request for the previous page. (required)
previous_response: The response from the request for the previous page. (required)
Returns:
A request object that you can call 'execute()' on to request the next
page. Returns None if there are no more items in the collection.
patch(projectId, jobId, body, updateMask=None, x__xgafv=None)
Updates a job in a project.
Args:
projectId: string, Required The ID of the Google Cloud Platform project that the job belongs to. (required)
jobId: string, Required The job ID. (required)
body: object, The request body. (required)
The object takes the form of:
{ # 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.
"state": "A String", # Required A state message specifying the overall job state.
"stateStartTime": "A String", # Output-only The time when this state was entered.
"substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
"details": "A String", # Optional Job state details, such as an error description if the state is ERROR.
},
"hadoopJob": { # A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN. # Job is a Hadoop job.
"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",
],
"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",
],
"jarFileUris": [ # Optional Jar file URIs to add to the CLASSPATHs of the Hadoop 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",
},
},
"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",
},
},
"labels": { # Optional The labels to associate with this job.Label keys must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}{0,62}Label values must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}\p{N}_-{0,63}No more than 64 labels can be associated with a given job.
"a_key": "A String",
},
"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 hyphens (-). The maximum length is 100 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",
},
},
"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.
},
],
"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",
],
"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",
},
},
"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 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.
"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",
},
},
"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.
"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.
"sparkJob": { # A Cloud Dataproc job for running Spark applications on YARN. # Job is a Spark job.
"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 Spark 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 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",
},
},
"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.
"scheduling": { # Job scheduling options.Beta Feature: These options are available for testing purposes only. They may be changed before final release. # Optional Job scheduling configuration.
"maxFailuresPerHour": 42, # 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.
},
"statusHistory": [ # Output-only The previous job status.
{ # Cloud Dataproc job status.
"state": "A String", # Required A state message specifying the overall job state.
"stateStartTime": "A String", # Output-only The time when this state was entered.
"substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
"details": "A String", # Optional Job state details, such as an error description if the state is ERROR.
},
],
"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, 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.
}
updateMask: string, Required Specifies the path, relative to Job, of the field to update. For example, to update the labels of a Job the update_mask parameter would be specified as labels, and the PATCH request body would specify the new value. Note: Currently, labels is the only field that can be updated.
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 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.
"state": "A String", # Required A state message specifying the overall job state.
"stateStartTime": "A String", # Output-only The time when this state was entered.
"substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
"details": "A String", # Optional Job state details, such as an error description if the state is ERROR.
},
"hadoopJob": { # A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN. # Job is a Hadoop job.
"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",
],
"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",
],
"jarFileUris": [ # Optional Jar file URIs to add to the CLASSPATHs of the Hadoop 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",
},
},
"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",
},
},
"labels": { # Optional The labels to associate with this job.Label keys must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}{0,62}Label values must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}\p{N}_-{0,63}No more than 64 labels can be associated with a given job.
"a_key": "A String",
},
"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 hyphens (-). The maximum length is 100 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",
},
},
"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.
},
],
"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",
],
"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",
},
},
"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 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.
"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",
},
},
"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.
"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.
"sparkJob": { # A Cloud Dataproc job for running Spark applications on YARN. # Job is a Spark job.
"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 Spark 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 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",
},
},
"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.
"scheduling": { # Job scheduling options.Beta Feature: These options are available for testing purposes only. They may be changed before final release. # Optional Job scheduling configuration.
"maxFailuresPerHour": 42, # 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.
},
"statusHistory": [ # Output-only The previous job status.
{ # Cloud Dataproc job status.
"state": "A String", # Required A state message specifying the overall job state.
"stateStartTime": "A String", # Output-only The time when this state was entered.
"substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
"details": "A String", # Optional Job state details, such as an error description if the state is ERROR.
},
],
"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, 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.
}
submit(projectId, body, x__xgafv=None)
Submits a job to a cluster.
Args:
projectId: string, Required The ID of the Google Cloud Platform project that the job belongs to. (required)
body: object, The request body. (required)
The object takes the form of:
{ # A request to submit a job.
"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.
"state": "A String", # Required A state message specifying the overall job state.
"stateStartTime": "A String", # Output-only The time when this state was entered.
"substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
"details": "A String", # Optional Job state details, such as an error description if the state is ERROR.
},
"hadoopJob": { # A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN. # Job is a Hadoop job.
"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",
],
"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",
],
"jarFileUris": [ # Optional Jar file URIs to add to the CLASSPATHs of the Hadoop 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",
},
},
"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",
},
},
"labels": { # Optional The labels to associate with this job.Label keys must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}{0,62}Label values must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}\p{N}_-{0,63}No more than 64 labels can be associated with a given job.
"a_key": "A String",
},
"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 hyphens (-). The maximum length is 100 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",
},
},
"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.
},
],
"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",
],
"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",
},
},
"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 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.
"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",
},
},
"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.
"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.
"sparkJob": { # A Cloud Dataproc job for running Spark applications on YARN. # Job is a Spark job.
"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 Spark 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 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",
},
},
"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.
"scheduling": { # Job scheduling options.Beta Feature: These options are available for testing purposes only. They may be changed before final release. # Optional Job scheduling configuration.
"maxFailuresPerHour": 42, # 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.
},
"statusHistory": [ # Output-only The previous job status.
{ # Cloud Dataproc job status.
"state": "A String", # Required A state message specifying the overall job state.
"stateStartTime": "A String", # Output-only The time when this state was entered.
"substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
"details": "A String", # Optional Job state details, such as an error description if the state is ERROR.
},
],
"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, 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.
Allowed values
1 - v1 error format
2 - v2 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.
"state": "A String", # Required A state message specifying the overall job state.
"stateStartTime": "A String", # Output-only The time when this state was entered.
"substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
"details": "A String", # Optional Job state details, such as an error description if the state is ERROR.
},
"hadoopJob": { # A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN. # Job is a Hadoop job.
"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",
],
"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",
],
"jarFileUris": [ # Optional Jar file URIs to add to the CLASSPATHs of the Hadoop 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",
},
},
"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",
},
},
"labels": { # Optional The labels to associate with this job.Label keys must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}{0,62}Label values must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}\p{N}_-{0,63}No more than 64 labels can be associated with a given job.
"a_key": "A String",
},
"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 hyphens (-). The maximum length is 100 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",
},
},
"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.
},
],
"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",
],
"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",
},
},
"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 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.
"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",
},
},
"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.
"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.
"sparkJob": { # A Cloud Dataproc job for running Spark applications on YARN. # Job is a Spark job.
"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 Spark 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 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",
},
},
"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.
"scheduling": { # Job scheduling options.Beta Feature: These options are available for testing purposes only. They may be changed before final release. # Optional Job scheduling configuration.
"maxFailuresPerHour": 42, # 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.
},
"statusHistory": [ # Output-only The previous job status.
{ # Cloud Dataproc job status.
"state": "A String", # Required A state message specifying the overall job state.
"stateStartTime": "A String", # Output-only The time when this state was entered.
"substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
"details": "A String", # Optional Job state details, such as an error description if the state is ERROR.
},
],
"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, 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.
}