blob: 7bacd91db4141df578930eaec64d281bfa0fc292 [file] [log] [blame]
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001<html><body>
2<style>
3
4body, h1, h2, h3, div, span, p, pre, a {
5 margin: 0;
6 padding: 0;
7 border: 0;
8 font-weight: inherit;
9 font-style: inherit;
10 font-size: 100%;
11 font-family: inherit;
12 vertical-align: baseline;
13}
14
15body {
16 font-size: 13px;
17 padding: 1em;
18}
19
20h1 {
21 font-size: 26px;
22 margin-bottom: 1em;
23}
24
25h2 {
26 font-size: 24px;
27 margin-bottom: 1em;
28}
29
30h3 {
31 font-size: 20px;
32 margin-bottom: 1em;
33 margin-top: 1em;
34}
35
36pre, code {
37 line-height: 1.5;
38 font-family: Monaco, 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', 'Lucida Console', monospace;
39}
40
41pre {
42 margin-top: 0.5em;
43}
44
45h1, h2, h3, p {
46 font-family: Arial, sans serif;
47}
48
49h1, h2, h3 {
50 border-bottom: solid #CCC 1px;
51}
52
53.toc_element {
54 margin-top: 0.5em;
55}
56
57.firstline {
58 margin-left: 2 em;
59}
60
61.method {
62 margin-top: 1em;
63 border: solid 1px #CCC;
64 padding: 1em;
65 background: #EEE;
66}
67
68.details {
69 font-weight: bold;
70 font-size: 14px;
71}
72
73</style>
74
75<h1><a href="dataproc_v1.html">Google Cloud Dataproc API</a> . <a href="dataproc_v1.projects.html">projects</a> . <a href="dataproc_v1.projects.regions.html">regions</a> . <a href="dataproc_v1.projects.regions.jobs.html">jobs</a></h1>
76<h2>Instance Methods</h2>
77<p class="toc_element">
78 <code><a href="#cancel">cancel(projectId, region, jobId, body, x__xgafv=None)</a></code></p>
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -040079<p class="firstline">Starts a job cancellation request. To access the job resource after cancellation, call regions/{region}/jobs.list or regions/{region}/jobs.get.</p>
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -080080<p class="toc_element">
81 <code><a href="#delete">delete(projectId, region, jobId, x__xgafv=None)</a></code></p>
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -040082<p class="firstline">Deletes the job from the project. If the job is active, the delete fails, and the response returns FAILED_PRECONDITION.</p>
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -080083<p class="toc_element">
84 <code><a href="#get">get(projectId, region, jobId, x__xgafv=None)</a></code></p>
85<p class="firstline">Gets the resource representation for a job in a project.</p>
86<p class="toc_element">
Jon Wayne Parrott692617a2017-01-06 09:58:29 -080087 <code><a href="#list">list(projectId, region, pageSize=None, x__xgafv=None, pageToken=None, clusterName=None, jobStateMatcher=None, filter=None)</a></code></p>
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -080088<p class="firstline">Lists regions/{region}/jobs in a project.</p>
89<p class="toc_element">
90 <code><a href="#list_next">list_next(previous_request, previous_response)</a></code></p>
91<p class="firstline">Retrieves the next page of results.</p>
92<p class="toc_element">
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -040093 <code><a href="#patch">patch(projectId, region, jobId, body, updateMask=None, x__xgafv=None)</a></code></p>
94<p class="firstline">Updates a job in a project.</p>
95<p class="toc_element">
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -080096 <code><a href="#submit">submit(projectId, region, body, x__xgafv=None)</a></code></p>
97<p class="firstline">Submits a job to a cluster.</p>
98<h3>Method Details</h3>
99<div class="method">
100 <code class="details" id="cancel">cancel(projectId, region, jobId, body, x__xgafv=None)</code>
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400101 <pre>Starts a job cancellation request. To access the job resource after cancellation, call regions/{region}/jobs.list or regions/{region}/jobs.get.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800102
103Args:
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400104 projectId: string, Required. The ID of the Google Cloud Platform project that the job belongs to. (required)
105 region: string, Required. The Cloud Dataproc region in which to handle the request. (required)
106 jobId: string, Required. The job ID. (required)
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800107 body: object, The request body. (required)
108 The object takes the form of:
109
110{ # A request to cancel a job.
111 }
112
113 x__xgafv: string, V1 error format.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400114 Allowed values
115 1 - v1 error format
116 2 - v2 error format
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800117
118Returns:
119 An object of the form:
120
121 { # A Cloud Dataproc job resource.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400122 "status": { # Cloud Dataproc job status. # Output-only. The job status. Additional application-specific status information may be contained in the <code>type_job</code> and <code>yarn_applications</code> fields.
123 "state": "A String", # Output-only. A state message specifying the overall job state.
124 "stateStartTime": "A String", # Output-only. The time when this state was entered.
125 "details": "A String", # Output-only. Optional job state details, such as an error description if the state is <code>ERROR</code>.
126 "substate": "A String", # Output-only. Additional state information, which includes status reported by the agent.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800127 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400128 "sparkSqlJob": { # A Cloud Dataproc job for running Apache Spark SQL (http://spark.apache.org/sql/) queries. # Job is a SparkSql job.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800129 "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400130 "scriptVariables": { # Optional. Mapping of query variable names to values (equivalent to the Spark SQL command: SET name="value";).
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800131 "a_key": "A String",
132 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400133 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400134 "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'
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800135 "a_key": "A String",
136 },
137 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400138 "jarFileUris": [ # Optional. HCFS URIs of jar files to be added to the Spark CLASSPATH.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800139 "A String",
140 ],
141 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400142 "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:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400143 # "hiveJob": {
144 # "queryList": {
145 # "queries": [
146 # "query1",
147 # "query2",
148 # "query3;query4",
149 # ]
150 # }
151 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800152 "A String",
153 ],
154 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400155 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800156 "a_key": "A String",
157 },
158 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400159 "pigJob": { # A Cloud Dataproc job for running Apache Pig (https://pig.apache.org/) queries on YARN. # Job is a Pig job.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800160 "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400161 "scriptVariables": { # Optional. Mapping of query variable names to values (equivalent to the Pig command: name=[value]).
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800162 "a_key": "A String",
163 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400164 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400165 "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'
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800166 "a_key": "A String",
167 },
168 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400169 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800170 "A String",
171 ],
172 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400173 "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:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400174 # "hiveJob": {
175 # "queryList": {
176 # "queries": [
177 # "query1",
178 # "query2",
179 # "query3;query4",
180 # ]
181 # }
182 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800183 "A String",
184 ],
185 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400186 "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.
187 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800188 "a_key": "A String",
189 },
190 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400191 "placement": { # Cloud Dataproc job config. # Required. Job information, including how, when, and where to run the job.
192 "clusterName": "A String", # Required. The name of the cluster where the job will be submitted.
193 "clusterUuid": "A String", # Output-only. A cluster UUID generated by the Cloud Dataproc service when the job is submitted.
Thomas Coffee2f245372017-03-27 10:39:26 -0700194 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400195 "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 <code>job_id</code>.
196 "projectId": "A String", # Required. The ID of the Google Cloud Platform project that the job belongs to.
197 "jobId": "A String", # Optional. 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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700198 },
199 "hadoopJob": { # A Cloud Dataproc job for running Apache Hadoop MapReduce (https://hadoop.apache.org/docs/current/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html) jobs on Apache Hadoop YARN (https://hadoop.apache.org/docs/r2.7.1/hadoop-yarn/hadoop-yarn-site/YARN.html). # Job is a Hadoop job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400200 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800201 "A String",
202 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400203 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400204 "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'
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800205 "a_key": "A String",
206 },
207 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400208 "jarFileUris": [ # Optional. Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -0700209 "A String",
210 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400211 "fileUris": [ # Optional. HCFS (Hadoop Compatible Filesystem) URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -0700212 "A String",
213 ],
214 "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.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400215 "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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700216 "A String",
217 ],
218 "mainJarFileUri": "A String", # The HCFS URI of the jar file containing the main class. Examples: 'gs://foo-bucket/analytics-binaries/extract-useful-metrics-mr.jar' 'hdfs:/tmp/test-samples/custom-wordcount.jar' 'file:///home/usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar'
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400219 "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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700220 "a_key": "A String",
221 },
222 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400223 "labels": { # Optional. The labels to associate with this job. Label keys must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). Label values may be empty, but, if present, must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). No more than 32 labels can be associated with a job.
Thomas Coffee2f245372017-03-27 10:39:26 -0700224 "a_key": "A String",
225 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400226 "driverOutputResourceUri": "A String", # Output-only. A URI pointing to the location of the stdout of the job's driver program.
Thomas Coffee2f245372017-03-27 10:39:26 -0700227 "pysparkJob": { # A Cloud Dataproc job for running Apache PySpark (https://spark.apache.org/docs/0.9.0/python-programming-guide.html) applications on YARN. # Job is a Pyspark job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400228 "mainPythonFileUri": "A String", # Required. The HCFS URI of the main Python file to use as the driver. Must be a .py file.
229 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800230 "A String",
231 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400232 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Thomas Coffee2f245372017-03-27 10:39:26 -0700233 "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'
234 "a_key": "A String",
235 },
236 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400237 "jarFileUris": [ # Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -0700238 "A String",
239 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400240 "fileUris": [ # Optional. HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800241 "A String",
242 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400243 "archiveUris": [ # Optional. HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400244 "A String",
245 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400246 "pythonFileUris": [ # Optional. HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400247 "A String",
248 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400249 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400250 "a_key": "A String",
251 },
252 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400253 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400254 "sparkJob": { # A Cloud Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN. # Job is a Spark job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400255 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400256 "A String",
257 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400258 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400259 "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'
260 "a_key": "A String",
261 },
262 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400263 "jarFileUris": [ # Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400264 "A String",
265 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400266 "fileUris": [ # Optional. HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400267 "A String",
268 ],
269 "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.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400270 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800271 "A String",
272 ],
Jon Wayne Parrott0a471d32016-05-19 10:54:38 -0700273 "mainJarFileUri": "A String", # The HCFS URI of the jar file that contains the main class.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400274 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800275 "a_key": "A String",
276 },
277 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400278 "yarnApplications": [ # Output-only. The collection of YARN applications spun up by this job.Beta Feature: This report is available for testing purposes only. It may be changed before final release.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400279 { # A YARN application created by a job. Application information is a subset of <code>org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto</code>.Beta Feature: This report is available for testing purposes only. It may be changed before final release.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400280 "progress": 3.14, # Required. The numerical progress of the application, from 1 to 100.
281 "state": "A String", # Required. The application state.
282 "name": "A String", # Required. The application name.
283 "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.
Jon Wayne Parrott692617a2017-01-06 09:58:29 -0800284 },
285 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400286 "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.
287 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800288 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400289 "statusHistory": [ # Output-only. The previous job status.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400290 { # Cloud Dataproc job status.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400291 "state": "A String", # Output-only. A state message specifying the overall job state.
292 "stateStartTime": "A String", # Output-only. The time when this state was entered.
293 "details": "A String", # Output-only. Optional job state details, such as an error description if the state is <code>ERROR</code>.
294 "substate": "A String", # Output-only. Additional state information, which includes status reported by the agent.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400295 },
296 ],
297 "hiveJob": { # A Cloud Dataproc job for running Apache Hive (https://hive.apache.org/) queries on YARN. # Job is a Hive job.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800298 "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400299 "scriptVariables": { # Optional. Mapping of query variable names to values (equivalent to the Hive command: SET name="value";).
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800300 "a_key": "A String",
301 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400302 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800303 "A String",
304 ],
305 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400306 "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:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400307 # "hiveJob": {
308 # "queryList": {
309 # "queries": [
310 # "query1",
311 # "query2",
312 # "query3;query4",
313 # ]
314 # }
315 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800316 "A String",
317 ],
318 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400319 "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.
320 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800321 "a_key": "A String",
322 },
323 },
324 }</pre>
325</div>
326
327<div class="method">
328 <code class="details" id="delete">delete(projectId, region, jobId, x__xgafv=None)</code>
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400329 <pre>Deletes the job from the project. If the job is active, the delete fails, and the response returns FAILED_PRECONDITION.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800330
331Args:
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400332 projectId: string, Required. The ID of the Google Cloud Platform project that the job belongs to. (required)
333 region: string, Required. The Cloud Dataproc region in which to handle the request. (required)
334 jobId: string, Required. The job ID. (required)
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800335 x__xgafv: string, V1 error format.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400336 Allowed values
337 1 - v1 error format
338 2 - v2 error format
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800339
340Returns:
341 An object of the form:
342
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400343 { # 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:
344 # service Foo {
345 # rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);
346 # }
347 # The JSON representation for Empty is empty JSON object {}.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800348 }</pre>
349</div>
350
351<div class="method">
352 <code class="details" id="get">get(projectId, region, jobId, x__xgafv=None)</code>
353 <pre>Gets the resource representation for a job in a project.
354
355Args:
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400356 projectId: string, Required. The ID of the Google Cloud Platform project that the job belongs to. (required)
357 region: string, Required. The Cloud Dataproc region in which to handle the request. (required)
358 jobId: string, Required. The job ID. (required)
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800359 x__xgafv: string, V1 error format.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400360 Allowed values
361 1 - v1 error format
362 2 - v2 error format
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800363
364Returns:
365 An object of the form:
366
367 { # A Cloud Dataproc job resource.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400368 "status": { # Cloud Dataproc job status. # Output-only. The job status. Additional application-specific status information may be contained in the <code>type_job</code> and <code>yarn_applications</code> fields.
369 "state": "A String", # Output-only. A state message specifying the overall job state.
370 "stateStartTime": "A String", # Output-only. The time when this state was entered.
371 "details": "A String", # Output-only. Optional job state details, such as an error description if the state is <code>ERROR</code>.
372 "substate": "A String", # Output-only. Additional state information, which includes status reported by the agent.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800373 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400374 "sparkSqlJob": { # A Cloud Dataproc job for running Apache Spark SQL (http://spark.apache.org/sql/) queries. # Job is a SparkSql job.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800375 "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400376 "scriptVariables": { # Optional. Mapping of query variable names to values (equivalent to the Spark SQL command: SET name="value";).
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800377 "a_key": "A String",
378 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400379 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400380 "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'
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800381 "a_key": "A String",
382 },
383 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400384 "jarFileUris": [ # Optional. HCFS URIs of jar files to be added to the Spark CLASSPATH.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800385 "A String",
386 ],
387 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400388 "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:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400389 # "hiveJob": {
390 # "queryList": {
391 # "queries": [
392 # "query1",
393 # "query2",
394 # "query3;query4",
395 # ]
396 # }
397 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800398 "A String",
399 ],
400 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400401 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800402 "a_key": "A String",
403 },
404 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400405 "pigJob": { # A Cloud Dataproc job for running Apache Pig (https://pig.apache.org/) queries on YARN. # Job is a Pig job.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800406 "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400407 "scriptVariables": { # Optional. Mapping of query variable names to values (equivalent to the Pig command: name=[value]).
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800408 "a_key": "A String",
409 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400410 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400411 "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'
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800412 "a_key": "A String",
413 },
414 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400415 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800416 "A String",
417 ],
418 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400419 "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:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400420 # "hiveJob": {
421 # "queryList": {
422 # "queries": [
423 # "query1",
424 # "query2",
425 # "query3;query4",
426 # ]
427 # }
428 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800429 "A String",
430 ],
431 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400432 "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.
433 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800434 "a_key": "A String",
435 },
436 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400437 "placement": { # Cloud Dataproc job config. # Required. Job information, including how, when, and where to run the job.
438 "clusterName": "A String", # Required. The name of the cluster where the job will be submitted.
439 "clusterUuid": "A String", # Output-only. A cluster UUID generated by the Cloud Dataproc service when the job is submitted.
Thomas Coffee2f245372017-03-27 10:39:26 -0700440 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400441 "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 <code>job_id</code>.
442 "projectId": "A String", # Required. The ID of the Google Cloud Platform project that the job belongs to.
443 "jobId": "A String", # Optional. 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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700444 },
445 "hadoopJob": { # A Cloud Dataproc job for running Apache Hadoop MapReduce (https://hadoop.apache.org/docs/current/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html) jobs on Apache Hadoop YARN (https://hadoop.apache.org/docs/r2.7.1/hadoop-yarn/hadoop-yarn-site/YARN.html). # Job is a Hadoop job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400446 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800447 "A String",
448 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400449 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400450 "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'
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800451 "a_key": "A String",
452 },
453 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400454 "jarFileUris": [ # Optional. Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -0700455 "A String",
456 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400457 "fileUris": [ # Optional. HCFS (Hadoop Compatible Filesystem) URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -0700458 "A String",
459 ],
460 "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.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400461 "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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700462 "A String",
463 ],
464 "mainJarFileUri": "A String", # The HCFS URI of the jar file containing the main class. Examples: 'gs://foo-bucket/analytics-binaries/extract-useful-metrics-mr.jar' 'hdfs:/tmp/test-samples/custom-wordcount.jar' 'file:///home/usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar'
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400465 "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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700466 "a_key": "A String",
467 },
468 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400469 "labels": { # Optional. The labels to associate with this job. Label keys must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). Label values may be empty, but, if present, must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). No more than 32 labels can be associated with a job.
Thomas Coffee2f245372017-03-27 10:39:26 -0700470 "a_key": "A String",
471 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400472 "driverOutputResourceUri": "A String", # Output-only. A URI pointing to the location of the stdout of the job's driver program.
Thomas Coffee2f245372017-03-27 10:39:26 -0700473 "pysparkJob": { # A Cloud Dataproc job for running Apache PySpark (https://spark.apache.org/docs/0.9.0/python-programming-guide.html) applications on YARN. # Job is a Pyspark job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400474 "mainPythonFileUri": "A String", # Required. The HCFS URI of the main Python file to use as the driver. Must be a .py file.
475 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800476 "A String",
477 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400478 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Thomas Coffee2f245372017-03-27 10:39:26 -0700479 "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'
480 "a_key": "A String",
481 },
482 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400483 "jarFileUris": [ # Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -0700484 "A String",
485 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400486 "fileUris": [ # Optional. HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800487 "A String",
488 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400489 "archiveUris": [ # Optional. HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400490 "A String",
491 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400492 "pythonFileUris": [ # Optional. HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400493 "A String",
494 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400495 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400496 "a_key": "A String",
497 },
498 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400499 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400500 "sparkJob": { # A Cloud Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN. # Job is a Spark job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400501 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400502 "A String",
503 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400504 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400505 "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'
506 "a_key": "A String",
507 },
508 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400509 "jarFileUris": [ # Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400510 "A String",
511 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400512 "fileUris": [ # Optional. HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400513 "A String",
514 ],
515 "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.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400516 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800517 "A String",
518 ],
Jon Wayne Parrott0a471d32016-05-19 10:54:38 -0700519 "mainJarFileUri": "A String", # The HCFS URI of the jar file that contains the main class.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400520 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800521 "a_key": "A String",
522 },
523 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400524 "yarnApplications": [ # Output-only. The collection of YARN applications spun up by this job.Beta Feature: This report is available for testing purposes only. It may be changed before final release.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400525 { # A YARN application created by a job. Application information is a subset of <code>org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto</code>.Beta Feature: This report is available for testing purposes only. It may be changed before final release.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400526 "progress": 3.14, # Required. The numerical progress of the application, from 1 to 100.
527 "state": "A String", # Required. The application state.
528 "name": "A String", # Required. The application name.
529 "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.
Jon Wayne Parrott692617a2017-01-06 09:58:29 -0800530 },
531 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400532 "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.
533 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800534 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400535 "statusHistory": [ # Output-only. The previous job status.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400536 { # Cloud Dataproc job status.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400537 "state": "A String", # Output-only. A state message specifying the overall job state.
538 "stateStartTime": "A String", # Output-only. The time when this state was entered.
539 "details": "A String", # Output-only. Optional job state details, such as an error description if the state is <code>ERROR</code>.
540 "substate": "A String", # Output-only. Additional state information, which includes status reported by the agent.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400541 },
542 ],
543 "hiveJob": { # A Cloud Dataproc job for running Apache Hive (https://hive.apache.org/) queries on YARN. # Job is a Hive job.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800544 "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400545 "scriptVariables": { # Optional. Mapping of query variable names to values (equivalent to the Hive command: SET name="value";).
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800546 "a_key": "A String",
547 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400548 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800549 "A String",
550 ],
551 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400552 "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:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400553 # "hiveJob": {
554 # "queryList": {
555 # "queries": [
556 # "query1",
557 # "query2",
558 # "query3;query4",
559 # ]
560 # }
561 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800562 "A String",
563 ],
564 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400565 "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.
566 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800567 "a_key": "A String",
568 },
569 },
570 }</pre>
571</div>
572
573<div class="method">
Jon Wayne Parrott692617a2017-01-06 09:58:29 -0800574 <code class="details" id="list">list(projectId, region, pageSize=None, x__xgafv=None, pageToken=None, clusterName=None, jobStateMatcher=None, filter=None)</code>
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800575 <pre>Lists regions/{region}/jobs in a project.
576
577Args:
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400578 projectId: string, Required. The ID of the Google Cloud Platform project that the job belongs to. (required)
579 region: string, Required. The Cloud Dataproc region in which to handle the request. (required)
580 pageSize: integer, Optional. The number of results to return in each response.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800581 x__xgafv: string, V1 error format.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400582 Allowed values
583 1 - v1 error format
584 2 - v2 error format
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400585 pageToken: string, Optional. The page token, returned by a previous call, to request the next page of results.
586 clusterName: string, Optional. If set, the returned jobs list includes only jobs that were submitted to the named cluster.
587 jobStateMatcher: string, Optional. Specifies enumerated categories of jobs to list (default = match ALL jobs).
588 filter: string, Optional. A filter constraining the jobs to list. Filters are case-sensitive and have the following syntax:field = value AND field = value ...where field is status.state or labels.[KEY], and [KEY] is a label key. value can be * to match all values. status.state can be either ACTIVE or INACTIVE. Only the logical AND operator is supported; space-separated items are treated as having an implicit AND operator.Example filter:status.state = ACTIVE AND labels.env = staging AND labels.starred = *
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800589
590Returns:
591 An object of the form:
592
593 { # A list of jobs in a project.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400594 "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 <code>ListJobsRequest</code>.
595 "jobs": [ # Output-only. Jobs list.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800596 { # A Cloud Dataproc job resource.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400597 "status": { # Cloud Dataproc job status. # Output-only. The job status. Additional application-specific status information may be contained in the <code>type_job</code> and <code>yarn_applications</code> fields.
598 "state": "A String", # Output-only. A state message specifying the overall job state.
599 "stateStartTime": "A String", # Output-only. The time when this state was entered.
600 "details": "A String", # Output-only. Optional job state details, such as an error description if the state is <code>ERROR</code>.
601 "substate": "A String", # Output-only. Additional state information, which includes status reported by the agent.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800602 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400603 "sparkSqlJob": { # A Cloud Dataproc job for running Apache Spark SQL (http://spark.apache.org/sql/) queries. # Job is a SparkSql job.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800604 "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400605 "scriptVariables": { # Optional. Mapping of query variable names to values (equivalent to the Spark SQL command: SET name="value";).
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800606 "a_key": "A String",
607 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400608 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400609 "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'
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800610 "a_key": "A String",
611 },
612 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400613 "jarFileUris": [ # Optional. HCFS URIs of jar files to be added to the Spark CLASSPATH.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800614 "A String",
615 ],
616 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400617 "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:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400618 # "hiveJob": {
619 # "queryList": {
620 # "queries": [
621 # "query1",
622 # "query2",
623 # "query3;query4",
624 # ]
625 # }
626 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800627 "A String",
628 ],
629 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400630 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800631 "a_key": "A String",
632 },
633 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400634 "pigJob": { # A Cloud Dataproc job for running Apache Pig (https://pig.apache.org/) queries on YARN. # Job is a Pig job.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800635 "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400636 "scriptVariables": { # Optional. Mapping of query variable names to values (equivalent to the Pig command: name=[value]).
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800637 "a_key": "A String",
638 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400639 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400640 "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'
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800641 "a_key": "A String",
642 },
643 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400644 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800645 "A String",
646 ],
647 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400648 "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:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400649 # "hiveJob": {
650 # "queryList": {
651 # "queries": [
652 # "query1",
653 # "query2",
654 # "query3;query4",
655 # ]
656 # }
657 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800658 "A String",
659 ],
660 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400661 "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.
662 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800663 "a_key": "A String",
664 },
665 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400666 "placement": { # Cloud Dataproc job config. # Required. Job information, including how, when, and where to run the job.
667 "clusterName": "A String", # Required. The name of the cluster where the job will be submitted.
668 "clusterUuid": "A String", # Output-only. A cluster UUID generated by the Cloud Dataproc service when the job is submitted.
Thomas Coffee2f245372017-03-27 10:39:26 -0700669 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400670 "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 <code>job_id</code>.
671 "projectId": "A String", # Required. The ID of the Google Cloud Platform project that the job belongs to.
672 "jobId": "A String", # Optional. 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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700673 },
674 "hadoopJob": { # A Cloud Dataproc job for running Apache Hadoop MapReduce (https://hadoop.apache.org/docs/current/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html) jobs on Apache Hadoop YARN (https://hadoop.apache.org/docs/r2.7.1/hadoop-yarn/hadoop-yarn-site/YARN.html). # Job is a Hadoop job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400675 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800676 "A String",
677 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400678 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400679 "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'
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800680 "a_key": "A String",
681 },
682 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400683 "jarFileUris": [ # Optional. Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -0700684 "A String",
685 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400686 "fileUris": [ # Optional. HCFS (Hadoop Compatible Filesystem) URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -0700687 "A String",
688 ],
689 "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.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400690 "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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700691 "A String",
692 ],
693 "mainJarFileUri": "A String", # The HCFS URI of the jar file containing the main class. Examples: 'gs://foo-bucket/analytics-binaries/extract-useful-metrics-mr.jar' 'hdfs:/tmp/test-samples/custom-wordcount.jar' 'file:///home/usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar'
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400694 "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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700695 "a_key": "A String",
696 },
697 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400698 "labels": { # Optional. The labels to associate with this job. Label keys must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). Label values may be empty, but, if present, must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). No more than 32 labels can be associated with a job.
Thomas Coffee2f245372017-03-27 10:39:26 -0700699 "a_key": "A String",
700 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400701 "driverOutputResourceUri": "A String", # Output-only. A URI pointing to the location of the stdout of the job's driver program.
Thomas Coffee2f245372017-03-27 10:39:26 -0700702 "pysparkJob": { # A Cloud Dataproc job for running Apache PySpark (https://spark.apache.org/docs/0.9.0/python-programming-guide.html) applications on YARN. # Job is a Pyspark job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400703 "mainPythonFileUri": "A String", # Required. The HCFS URI of the main Python file to use as the driver. Must be a .py file.
704 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800705 "A String",
706 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400707 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Thomas Coffee2f245372017-03-27 10:39:26 -0700708 "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'
709 "a_key": "A String",
710 },
711 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400712 "jarFileUris": [ # Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -0700713 "A String",
714 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400715 "fileUris": [ # Optional. HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800716 "A String",
717 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400718 "archiveUris": [ # Optional. HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400719 "A String",
720 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400721 "pythonFileUris": [ # Optional. HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400722 "A String",
723 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400724 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400725 "a_key": "A String",
726 },
727 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400728 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400729 "sparkJob": { # A Cloud Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN. # Job is a Spark job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400730 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400731 "A String",
732 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400733 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400734 "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'
735 "a_key": "A String",
736 },
737 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400738 "jarFileUris": [ # Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400739 "A String",
740 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400741 "fileUris": [ # Optional. HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400742 "A String",
743 ],
744 "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.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400745 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800746 "A String",
747 ],
Jon Wayne Parrott0a471d32016-05-19 10:54:38 -0700748 "mainJarFileUri": "A String", # The HCFS URI of the jar file that contains the main class.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400749 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800750 "a_key": "A String",
751 },
752 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400753 "yarnApplications": [ # Output-only. The collection of YARN applications spun up by this job.Beta Feature: This report is available for testing purposes only. It may be changed before final release.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400754 { # A YARN application created by a job. Application information is a subset of <code>org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto</code>.Beta Feature: This report is available for testing purposes only. It may be changed before final release.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400755 "progress": 3.14, # Required. The numerical progress of the application, from 1 to 100.
756 "state": "A String", # Required. The application state.
757 "name": "A String", # Required. The application name.
758 "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.
Jon Wayne Parrott692617a2017-01-06 09:58:29 -0800759 },
760 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400761 "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.
762 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800763 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400764 "statusHistory": [ # Output-only. The previous job status.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400765 { # Cloud Dataproc job status.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400766 "state": "A String", # Output-only. A state message specifying the overall job state.
767 "stateStartTime": "A String", # Output-only. The time when this state was entered.
768 "details": "A String", # Output-only. Optional job state details, such as an error description if the state is <code>ERROR</code>.
769 "substate": "A String", # Output-only. Additional state information, which includes status reported by the agent.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400770 },
771 ],
772 "hiveJob": { # A Cloud Dataproc job for running Apache Hive (https://hive.apache.org/) queries on YARN. # Job is a Hive job.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800773 "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400774 "scriptVariables": { # Optional. Mapping of query variable names to values (equivalent to the Hive command: SET name="value";).
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800775 "a_key": "A String",
776 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400777 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800778 "A String",
779 ],
780 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400781 "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:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400782 # "hiveJob": {
783 # "queryList": {
784 # "queries": [
785 # "query1",
786 # "query2",
787 # "query3;query4",
788 # ]
789 # }
790 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800791 "A String",
792 ],
793 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400794 "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.
795 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800796 "a_key": "A String",
797 },
798 },
799 },
800 ],
801 }</pre>
802</div>
803
804<div class="method">
805 <code class="details" id="list_next">list_next(previous_request, previous_response)</code>
806 <pre>Retrieves the next page of results.
807
808Args:
809 previous_request: The request for the previous page. (required)
810 previous_response: The response from the request for the previous page. (required)
811
812Returns:
813 A request object that you can call 'execute()' on to request the next
814 page. Returns None if there are no more items in the collection.
815 </pre>
816</div>
817
818<div class="method">
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400819 <code class="details" id="patch">patch(projectId, region, jobId, body, updateMask=None, x__xgafv=None)</code>
820 <pre>Updates a job in a project.
821
822Args:
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400823 projectId: string, Required. The ID of the Google Cloud Platform project that the job belongs to. (required)
824 region: string, Required. The Cloud Dataproc region in which to handle the request. (required)
825 jobId: string, Required. The job ID. (required)
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400826 body: object, The request body. (required)
827 The object takes the form of:
828
829{ # A Cloud Dataproc job resource.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400830 "status": { # Cloud Dataproc job status. # Output-only. The job status. Additional application-specific status information may be contained in the <code>type_job</code> and <code>yarn_applications</code> fields.
831 "state": "A String", # Output-only. A state message specifying the overall job state.
832 "stateStartTime": "A String", # Output-only. The time when this state was entered.
833 "details": "A String", # Output-only. Optional job state details, such as an error description if the state is <code>ERROR</code>.
834 "substate": "A String", # Output-only. Additional state information, which includes status reported by the agent.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400835 },
836 "sparkSqlJob": { # A Cloud Dataproc job for running Apache Spark SQL (http://spark.apache.org/sql/) queries. # Job is a SparkSql job.
837 "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400838 "scriptVariables": { # Optional. Mapping of query variable names to values (equivalent to the Spark SQL command: SET name="value";).
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400839 "a_key": "A String",
840 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400841 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400842 "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'
843 "a_key": "A String",
844 },
845 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400846 "jarFileUris": [ # Optional. HCFS URIs of jar files to be added to the Spark CLASSPATH.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400847 "A String",
848 ],
849 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400850 "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:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400851 # "hiveJob": {
852 # "queryList": {
853 # "queries": [
854 # "query1",
855 # "query2",
856 # "query3;query4",
857 # ]
858 # }
859 # }
860 "A String",
861 ],
862 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400863 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400864 "a_key": "A String",
865 },
866 },
867 "pigJob": { # A Cloud Dataproc job for running Apache Pig (https://pig.apache.org/) queries on YARN. # Job is a Pig job.
868 "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400869 "scriptVariables": { # Optional. Mapping of query variable names to values (equivalent to the Pig command: name=[value]).
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400870 "a_key": "A String",
871 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400872 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400873 "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'
874 "a_key": "A String",
875 },
876 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400877 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400878 "A String",
879 ],
880 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400881 "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:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400882 # "hiveJob": {
883 # "queryList": {
884 # "queries": [
885 # "query1",
886 # "query2",
887 # "query3;query4",
888 # ]
889 # }
890 # }
891 "A String",
892 ],
893 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400894 "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.
895 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400896 "a_key": "A String",
897 },
898 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400899 "placement": { # Cloud Dataproc job config. # Required. Job information, including how, when, and where to run the job.
900 "clusterName": "A String", # Required. The name of the cluster where the job will be submitted.
901 "clusterUuid": "A String", # Output-only. A cluster UUID generated by the Cloud Dataproc service when the job is submitted.
Thomas Coffee2f245372017-03-27 10:39:26 -0700902 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400903 "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 <code>job_id</code>.
904 "projectId": "A String", # Required. The ID of the Google Cloud Platform project that the job belongs to.
905 "jobId": "A String", # Optional. 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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700906 },
907 "hadoopJob": { # A Cloud Dataproc job for running Apache Hadoop MapReduce (https://hadoop.apache.org/docs/current/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html) jobs on Apache Hadoop YARN (https://hadoop.apache.org/docs/r2.7.1/hadoop-yarn/hadoop-yarn-site/YARN.html). # Job is a Hadoop job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400908 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400909 "A String",
910 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400911 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400912 "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'
913 "a_key": "A String",
914 },
915 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400916 "jarFileUris": [ # Optional. Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -0700917 "A String",
918 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400919 "fileUris": [ # Optional. HCFS (Hadoop Compatible Filesystem) URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -0700920 "A String",
921 ],
922 "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.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400923 "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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700924 "A String",
925 ],
926 "mainJarFileUri": "A String", # The HCFS URI of the jar file containing the main class. Examples: 'gs://foo-bucket/analytics-binaries/extract-useful-metrics-mr.jar' 'hdfs:/tmp/test-samples/custom-wordcount.jar' 'file:///home/usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar'
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400927 "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.
Thomas Coffee2f245372017-03-27 10:39:26 -0700928 "a_key": "A String",
929 },
930 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400931 "labels": { # Optional. The labels to associate with this job. Label keys must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). Label values may be empty, but, if present, must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). No more than 32 labels can be associated with a job.
Thomas Coffee2f245372017-03-27 10:39:26 -0700932 "a_key": "A String",
933 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400934 "driverOutputResourceUri": "A String", # Output-only. A URI pointing to the location of the stdout of the job's driver program.
Thomas Coffee2f245372017-03-27 10:39:26 -0700935 "pysparkJob": { # A Cloud Dataproc job for running Apache PySpark (https://spark.apache.org/docs/0.9.0/python-programming-guide.html) applications on YARN. # Job is a Pyspark job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400936 "mainPythonFileUri": "A String", # Required. The HCFS URI of the main Python file to use as the driver. Must be a .py file.
937 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400938 "A String",
939 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400940 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Thomas Coffee2f245372017-03-27 10:39:26 -0700941 "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'
942 "a_key": "A String",
943 },
944 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400945 "jarFileUris": [ # Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -0700946 "A String",
947 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400948 "fileUris": [ # Optional. HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400949 "A String",
950 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400951 "archiveUris": [ # Optional. HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400952 "A String",
953 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400954 "pythonFileUris": [ # Optional. HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400955 "A String",
956 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400957 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400958 "a_key": "A String",
959 },
960 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400961 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400962 "sparkJob": { # A Cloud Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN. # Job is a Spark job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400963 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400964 "A String",
965 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400966 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400967 "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'
968 "a_key": "A String",
969 },
970 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400971 "jarFileUris": [ # Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400972 "A String",
973 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400974 "fileUris": [ # Optional. HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400975 "A String",
976 ],
977 "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.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400978 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400979 "A String",
980 ],
981 "mainJarFileUri": "A String", # The HCFS URI of the jar file that contains the main class.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400982 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400983 "a_key": "A String",
984 },
985 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400986 "yarnApplications": [ # Output-only. The collection of YARN applications spun up by this job.Beta Feature: This report is available for testing purposes only. It may be changed before final release.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400987 { # A YARN application created by a job. Application information is a subset of <code>org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto</code>.Beta Feature: This report is available for testing purposes only. It may be changed before final release.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400988 "progress": 3.14, # Required. The numerical progress of the application, from 1 to 100.
989 "state": "A String", # Required. The application state.
990 "name": "A String", # Required. The application name.
991 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400992 },
993 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400994 "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.
995 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400996 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400997 "statusHistory": [ # Output-only. The previous job status.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400998 { # Cloud Dataproc job status.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400999 "state": "A String", # Output-only. A state message specifying the overall job state.
1000 "stateStartTime": "A String", # Output-only. The time when this state was entered.
1001 "details": "A String", # Output-only. Optional job state details, such as an error description if the state is <code>ERROR</code>.
1002 "substate": "A String", # Output-only. Additional state information, which includes status reported by the agent.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001003 },
1004 ],
1005 "hiveJob": { # A Cloud Dataproc job for running Apache Hive (https://hive.apache.org/) queries on YARN. # Job is a Hive job.
1006 "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001007 "scriptVariables": { # Optional. Mapping of query variable names to values (equivalent to the Hive command: SET name="value";).
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001008 "a_key": "A String",
1009 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001010 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001011 "A String",
1012 ],
1013 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001014 "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:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001015 # "hiveJob": {
1016 # "queryList": {
1017 # "queries": [
1018 # "query1",
1019 # "query2",
1020 # "query3;query4",
1021 # ]
1022 # }
1023 # }
1024 "A String",
1025 ],
1026 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001027 "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.
1028 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001029 "a_key": "A String",
1030 },
1031 },
1032}
1033
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001034 updateMask: string, Required. Specifies the path, relative to <code>Job</code>, of the field to update. For example, to update the labels of a Job the <code>update_mask</code> parameter would be specified as <code>labels</code>, and the PATCH request body would specify the new value. <strong>Note:</strong> Currently, <code>labels</code> is the only field that can be updated.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001035 x__xgafv: string, V1 error format.
1036 Allowed values
1037 1 - v1 error format
1038 2 - v2 error format
1039
1040Returns:
1041 An object of the form:
1042
1043 { # A Cloud Dataproc job resource.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001044 "status": { # Cloud Dataproc job status. # Output-only. The job status. Additional application-specific status information may be contained in the <code>type_job</code> and <code>yarn_applications</code> fields.
1045 "state": "A String", # Output-only. A state message specifying the overall job state.
1046 "stateStartTime": "A String", # Output-only. The time when this state was entered.
1047 "details": "A String", # Output-only. Optional job state details, such as an error description if the state is <code>ERROR</code>.
1048 "substate": "A String", # Output-only. Additional state information, which includes status reported by the agent.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001049 },
1050 "sparkSqlJob": { # A Cloud Dataproc job for running Apache Spark SQL (http://spark.apache.org/sql/) queries. # Job is a SparkSql job.
1051 "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001052 "scriptVariables": { # Optional. Mapping of query variable names to values (equivalent to the Spark SQL command: SET name="value";).
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001053 "a_key": "A String",
1054 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001055 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001056 "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'
1057 "a_key": "A String",
1058 },
1059 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001060 "jarFileUris": [ # Optional. HCFS URIs of jar files to be added to the Spark CLASSPATH.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001061 "A String",
1062 ],
1063 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001064 "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:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001065 # "hiveJob": {
1066 # "queryList": {
1067 # "queries": [
1068 # "query1",
1069 # "query2",
1070 # "query3;query4",
1071 # ]
1072 # }
1073 # }
1074 "A String",
1075 ],
1076 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001077 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001078 "a_key": "A String",
1079 },
1080 },
1081 "pigJob": { # A Cloud Dataproc job for running Apache Pig (https://pig.apache.org/) queries on YARN. # Job is a Pig job.
1082 "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001083 "scriptVariables": { # Optional. Mapping of query variable names to values (equivalent to the Pig command: name=[value]).
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001084 "a_key": "A String",
1085 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001086 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001087 "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'
1088 "a_key": "A String",
1089 },
1090 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001091 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001092 "A String",
1093 ],
1094 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001095 "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:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001096 # "hiveJob": {
1097 # "queryList": {
1098 # "queries": [
1099 # "query1",
1100 # "query2",
1101 # "query3;query4",
1102 # ]
1103 # }
1104 # }
1105 "A String",
1106 ],
1107 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001108 "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.
1109 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001110 "a_key": "A String",
1111 },
1112 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001113 "placement": { # Cloud Dataproc job config. # Required. Job information, including how, when, and where to run the job.
1114 "clusterName": "A String", # Required. The name of the cluster where the job will be submitted.
1115 "clusterUuid": "A String", # Output-only. A cluster UUID generated by the Cloud Dataproc service when the job is submitted.
Thomas Coffee2f245372017-03-27 10:39:26 -07001116 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001117 "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 <code>job_id</code>.
1118 "projectId": "A String", # Required. The ID of the Google Cloud Platform project that the job belongs to.
1119 "jobId": "A String", # Optional. 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.
Thomas Coffee2f245372017-03-27 10:39:26 -07001120 },
1121 "hadoopJob": { # A Cloud Dataproc job for running Apache Hadoop MapReduce (https://hadoop.apache.org/docs/current/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html) jobs on Apache Hadoop YARN (https://hadoop.apache.org/docs/r2.7.1/hadoop-yarn/hadoop-yarn-site/YARN.html). # Job is a Hadoop job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001122 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001123 "A String",
1124 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001125 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001126 "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'
1127 "a_key": "A String",
1128 },
1129 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001130 "jarFileUris": [ # Optional. Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -07001131 "A String",
1132 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001133 "fileUris": [ # Optional. HCFS (Hadoop Compatible Filesystem) URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -07001134 "A String",
1135 ],
1136 "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.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001137 "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.
Thomas Coffee2f245372017-03-27 10:39:26 -07001138 "A String",
1139 ],
1140 "mainJarFileUri": "A String", # The HCFS URI of the jar file containing the main class. Examples: 'gs://foo-bucket/analytics-binaries/extract-useful-metrics-mr.jar' 'hdfs:/tmp/test-samples/custom-wordcount.jar' 'file:///home/usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar'
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001141 "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.
Thomas Coffee2f245372017-03-27 10:39:26 -07001142 "a_key": "A String",
1143 },
1144 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001145 "labels": { # Optional. The labels to associate with this job. Label keys must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). Label values may be empty, but, if present, must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). No more than 32 labels can be associated with a job.
Thomas Coffee2f245372017-03-27 10:39:26 -07001146 "a_key": "A String",
1147 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001148 "driverOutputResourceUri": "A String", # Output-only. A URI pointing to the location of the stdout of the job's driver program.
Thomas Coffee2f245372017-03-27 10:39:26 -07001149 "pysparkJob": { # A Cloud Dataproc job for running Apache PySpark (https://spark.apache.org/docs/0.9.0/python-programming-guide.html) applications on YARN. # Job is a Pyspark job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001150 "mainPythonFileUri": "A String", # Required. The HCFS URI of the main Python file to use as the driver. Must be a .py file.
1151 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001152 "A String",
1153 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001154 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Thomas Coffee2f245372017-03-27 10:39:26 -07001155 "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'
1156 "a_key": "A String",
1157 },
1158 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001159 "jarFileUris": [ # Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -07001160 "A String",
1161 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001162 "fileUris": [ # Optional. HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001163 "A String",
1164 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001165 "archiveUris": [ # Optional. HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001166 "A String",
1167 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001168 "pythonFileUris": [ # Optional. HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001169 "A String",
1170 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001171 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001172 "a_key": "A String",
1173 },
1174 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001175 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001176 "sparkJob": { # A Cloud Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN. # Job is a Spark job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001177 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001178 "A String",
1179 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001180 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001181 "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'
1182 "a_key": "A String",
1183 },
1184 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001185 "jarFileUris": [ # Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001186 "A String",
1187 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001188 "fileUris": [ # Optional. HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001189 "A String",
1190 ],
1191 "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.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001192 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001193 "A String",
1194 ],
1195 "mainJarFileUri": "A String", # The HCFS URI of the jar file that contains the main class.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001196 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001197 "a_key": "A String",
1198 },
1199 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001200 "yarnApplications": [ # Output-only. The collection of YARN applications spun up by this job.Beta Feature: This report is available for testing purposes only. It may be changed before final release.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001201 { # A YARN application created by a job. Application information is a subset of <code>org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto</code>.Beta Feature: This report is available for testing purposes only. It may be changed before final release.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001202 "progress": 3.14, # Required. The numerical progress of the application, from 1 to 100.
1203 "state": "A String", # Required. The application state.
1204 "name": "A String", # Required. The application name.
1205 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001206 },
1207 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001208 "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.
1209 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001210 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001211 "statusHistory": [ # Output-only. The previous job status.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001212 { # Cloud Dataproc job status.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001213 "state": "A String", # Output-only. A state message specifying the overall job state.
1214 "stateStartTime": "A String", # Output-only. The time when this state was entered.
1215 "details": "A String", # Output-only. Optional job state details, such as an error description if the state is <code>ERROR</code>.
1216 "substate": "A String", # Output-only. Additional state information, which includes status reported by the agent.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001217 },
1218 ],
1219 "hiveJob": { # A Cloud Dataproc job for running Apache Hive (https://hive.apache.org/) queries on YARN. # Job is a Hive job.
1220 "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001221 "scriptVariables": { # Optional. Mapping of query variable names to values (equivalent to the Hive command: SET name="value";).
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001222 "a_key": "A String",
1223 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001224 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001225 "A String",
1226 ],
1227 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001228 "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:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001229 # "hiveJob": {
1230 # "queryList": {
1231 # "queries": [
1232 # "query1",
1233 # "query2",
1234 # "query3;query4",
1235 # ]
1236 # }
1237 # }
1238 "A String",
1239 ],
1240 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001241 "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.
1242 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001243 "a_key": "A String",
1244 },
1245 },
1246 }</pre>
1247</div>
1248
1249<div class="method">
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001250 <code class="details" id="submit">submit(projectId, region, body, x__xgafv=None)</code>
1251 <pre>Submits a job to a cluster.
1252
1253Args:
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001254 projectId: string, Required. The ID of the Google Cloud Platform project that the job belongs to. (required)
1255 region: string, Required. The Cloud Dataproc region in which to handle the request. (required)
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001256 body: object, The request body. (required)
1257 The object takes the form of:
1258
1259{ # A request to submit a job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001260 "job": { # A Cloud Dataproc job resource. # Required. The job resource.
1261 "status": { # Cloud Dataproc job status. # Output-only. The job status. Additional application-specific status information may be contained in the <code>type_job</code> and <code>yarn_applications</code> fields.
1262 "state": "A String", # Output-only. A state message specifying the overall job state.
1263 "stateStartTime": "A String", # Output-only. The time when this state was entered.
1264 "details": "A String", # Output-only. Optional job state details, such as an error description if the state is <code>ERROR</code>.
1265 "substate": "A String", # Output-only. Additional state information, which includes status reported by the agent.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001266 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001267 "sparkSqlJob": { # A Cloud Dataproc job for running Apache Spark SQL (http://spark.apache.org/sql/) queries. # Job is a SparkSql job.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001268 "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001269 "scriptVariables": { # Optional. Mapping of query variable names to values (equivalent to the Spark SQL command: SET name="value";).
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001270 "a_key": "A String",
1271 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001272 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001273 "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'
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001274 "a_key": "A String",
1275 },
1276 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001277 "jarFileUris": [ # Optional. HCFS URIs of jar files to be added to the Spark CLASSPATH.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001278 "A String",
1279 ],
1280 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001281 "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:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001282 # "hiveJob": {
1283 # "queryList": {
1284 # "queries": [
1285 # "query1",
1286 # "query2",
1287 # "query3;query4",
1288 # ]
1289 # }
1290 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001291 "A String",
1292 ],
1293 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001294 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001295 "a_key": "A String",
1296 },
1297 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001298 "pigJob": { # A Cloud Dataproc job for running Apache Pig (https://pig.apache.org/) queries on YARN. # Job is a Pig job.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001299 "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001300 "scriptVariables": { # Optional. Mapping of query variable names to values (equivalent to the Pig command: name=[value]).
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001301 "a_key": "A String",
1302 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001303 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001304 "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'
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001305 "a_key": "A String",
1306 },
1307 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001308 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001309 "A String",
1310 ],
1311 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001312 "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:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001313 # "hiveJob": {
1314 # "queryList": {
1315 # "queries": [
1316 # "query1",
1317 # "query2",
1318 # "query3;query4",
1319 # ]
1320 # }
1321 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001322 "A String",
1323 ],
1324 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001325 "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.
1326 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001327 "a_key": "A String",
1328 },
1329 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001330 "placement": { # Cloud Dataproc job config. # Required. Job information, including how, when, and where to run the job.
1331 "clusterName": "A String", # Required. The name of the cluster where the job will be submitted.
1332 "clusterUuid": "A String", # Output-only. A cluster UUID generated by the Cloud Dataproc service when the job is submitted.
Thomas Coffee2f245372017-03-27 10:39:26 -07001333 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001334 "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 <code>job_id</code>.
1335 "projectId": "A String", # Required. The ID of the Google Cloud Platform project that the job belongs to.
1336 "jobId": "A String", # Optional. 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.
Thomas Coffee2f245372017-03-27 10:39:26 -07001337 },
1338 "hadoopJob": { # A Cloud Dataproc job for running Apache Hadoop MapReduce (https://hadoop.apache.org/docs/current/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html) jobs on Apache Hadoop YARN (https://hadoop.apache.org/docs/r2.7.1/hadoop-yarn/hadoop-yarn-site/YARN.html). # Job is a Hadoop job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001339 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001340 "A String",
1341 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001342 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001343 "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'
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001344 "a_key": "A String",
1345 },
1346 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001347 "jarFileUris": [ # Optional. Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -07001348 "A String",
1349 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001350 "fileUris": [ # Optional. HCFS (Hadoop Compatible Filesystem) URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -07001351 "A String",
1352 ],
1353 "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.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001354 "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.
Thomas Coffee2f245372017-03-27 10:39:26 -07001355 "A String",
1356 ],
1357 "mainJarFileUri": "A String", # The HCFS URI of the jar file containing the main class. Examples: 'gs://foo-bucket/analytics-binaries/extract-useful-metrics-mr.jar' 'hdfs:/tmp/test-samples/custom-wordcount.jar' 'file:///home/usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar'
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001358 "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.
Thomas Coffee2f245372017-03-27 10:39:26 -07001359 "a_key": "A String",
1360 },
1361 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001362 "labels": { # Optional. The labels to associate with this job. Label keys must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). Label values may be empty, but, if present, must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). No more than 32 labels can be associated with a job.
Thomas Coffee2f245372017-03-27 10:39:26 -07001363 "a_key": "A String",
1364 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001365 "driverOutputResourceUri": "A String", # Output-only. A URI pointing to the location of the stdout of the job's driver program.
Thomas Coffee2f245372017-03-27 10:39:26 -07001366 "pysparkJob": { # A Cloud Dataproc job for running Apache PySpark (https://spark.apache.org/docs/0.9.0/python-programming-guide.html) applications on YARN. # Job is a Pyspark job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001367 "mainPythonFileUri": "A String", # Required. The HCFS URI of the main Python file to use as the driver. Must be a .py file.
1368 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001369 "A String",
1370 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001371 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Thomas Coffee2f245372017-03-27 10:39:26 -07001372 "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'
1373 "a_key": "A String",
1374 },
1375 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001376 "jarFileUris": [ # Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -07001377 "A String",
1378 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001379 "fileUris": [ # Optional. HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001380 "A String",
1381 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001382 "archiveUris": [ # Optional. HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001383 "A String",
1384 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001385 "pythonFileUris": [ # Optional. HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001386 "A String",
1387 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001388 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001389 "a_key": "A String",
1390 },
1391 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001392 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001393 "sparkJob": { # A Cloud Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN. # Job is a Spark job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001394 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001395 "A String",
1396 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001397 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001398 "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'
1399 "a_key": "A String",
1400 },
1401 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001402 "jarFileUris": [ # Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001403 "A String",
1404 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001405 "fileUris": [ # Optional. HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001406 "A String",
1407 ],
1408 "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.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001409 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001410 "A String",
1411 ],
Jon Wayne Parrott0a471d32016-05-19 10:54:38 -07001412 "mainJarFileUri": "A String", # The HCFS URI of the jar file that contains the main class.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001413 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001414 "a_key": "A String",
1415 },
1416 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001417 "yarnApplications": [ # Output-only. The collection of YARN applications spun up by this job.Beta Feature: This report is available for testing purposes only. It may be changed before final release.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001418 { # A YARN application created by a job. Application information is a subset of <code>org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto</code>.Beta Feature: This report is available for testing purposes only. It may be changed before final release.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001419 "progress": 3.14, # Required. The numerical progress of the application, from 1 to 100.
1420 "state": "A String", # Required. The application state.
1421 "name": "A String", # Required. The application name.
1422 "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.
Jon Wayne Parrott692617a2017-01-06 09:58:29 -08001423 },
1424 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001425 "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.
1426 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001427 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001428 "statusHistory": [ # Output-only. The previous job status.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001429 { # Cloud Dataproc job status.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001430 "state": "A String", # Output-only. A state message specifying the overall job state.
1431 "stateStartTime": "A String", # Output-only. The time when this state was entered.
1432 "details": "A String", # Output-only. Optional job state details, such as an error description if the state is <code>ERROR</code>.
1433 "substate": "A String", # Output-only. Additional state information, which includes status reported by the agent.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001434 },
1435 ],
1436 "hiveJob": { # A Cloud Dataproc job for running Apache Hive (https://hive.apache.org/) queries on YARN. # Job is a Hive job.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001437 "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001438 "scriptVariables": { # Optional. Mapping of query variable names to values (equivalent to the Hive command: SET name="value";).
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001439 "a_key": "A String",
1440 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001441 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001442 "A String",
1443 ],
1444 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001445 "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:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001446 # "hiveJob": {
1447 # "queryList": {
1448 # "queries": [
1449 # "query1",
1450 # "query2",
1451 # "query3;query4",
1452 # ]
1453 # }
1454 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001455 "A String",
1456 ],
1457 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001458 "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.
1459 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001460 "a_key": "A String",
1461 },
1462 },
1463 },
1464 }
1465
1466 x__xgafv: string, V1 error format.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001467 Allowed values
1468 1 - v1 error format
1469 2 - v2 error format
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001470
1471Returns:
1472 An object of the form:
1473
1474 { # A Cloud Dataproc job resource.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001475 "status": { # Cloud Dataproc job status. # Output-only. The job status. Additional application-specific status information may be contained in the <code>type_job</code> and <code>yarn_applications</code> fields.
1476 "state": "A String", # Output-only. A state message specifying the overall job state.
1477 "stateStartTime": "A String", # Output-only. The time when this state was entered.
1478 "details": "A String", # Output-only. Optional job state details, such as an error description if the state is <code>ERROR</code>.
1479 "substate": "A String", # Output-only. Additional state information, which includes status reported by the agent.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001480 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001481 "sparkSqlJob": { # A Cloud Dataproc job for running Apache Spark SQL (http://spark.apache.org/sql/) queries. # Job is a SparkSql job.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001482 "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001483 "scriptVariables": { # Optional. Mapping of query variable names to values (equivalent to the Spark SQL command: SET name="value";).
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001484 "a_key": "A String",
1485 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001486 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001487 "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'
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001488 "a_key": "A String",
1489 },
1490 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001491 "jarFileUris": [ # Optional. HCFS URIs of jar files to be added to the Spark CLASSPATH.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001492 "A String",
1493 ],
1494 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001495 "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:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001496 # "hiveJob": {
1497 # "queryList": {
1498 # "queries": [
1499 # "query1",
1500 # "query2",
1501 # "query3;query4",
1502 # ]
1503 # }
1504 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001505 "A String",
1506 ],
1507 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001508 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001509 "a_key": "A String",
1510 },
1511 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001512 "pigJob": { # A Cloud Dataproc job for running Apache Pig (https://pig.apache.org/) queries on YARN. # Job is a Pig job.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001513 "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001514 "scriptVariables": { # Optional. Mapping of query variable names to values (equivalent to the Pig command: name=[value]).
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001515 "a_key": "A String",
1516 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001517 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001518 "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'
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001519 "a_key": "A String",
1520 },
1521 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001522 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001523 "A String",
1524 ],
1525 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001526 "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:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001527 # "hiveJob": {
1528 # "queryList": {
1529 # "queries": [
1530 # "query1",
1531 # "query2",
1532 # "query3;query4",
1533 # ]
1534 # }
1535 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001536 "A String",
1537 ],
1538 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001539 "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.
1540 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001541 "a_key": "A String",
1542 },
1543 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001544 "placement": { # Cloud Dataproc job config. # Required. Job information, including how, when, and where to run the job.
1545 "clusterName": "A String", # Required. The name of the cluster where the job will be submitted.
1546 "clusterUuid": "A String", # Output-only. A cluster UUID generated by the Cloud Dataproc service when the job is submitted.
Thomas Coffee2f245372017-03-27 10:39:26 -07001547 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001548 "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 <code>job_id</code>.
1549 "projectId": "A String", # Required. The ID of the Google Cloud Platform project that the job belongs to.
1550 "jobId": "A String", # Optional. 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.
Thomas Coffee2f245372017-03-27 10:39:26 -07001551 },
1552 "hadoopJob": { # A Cloud Dataproc job for running Apache Hadoop MapReduce (https://hadoop.apache.org/docs/current/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html) jobs on Apache Hadoop YARN (https://hadoop.apache.org/docs/r2.7.1/hadoop-yarn/hadoop-yarn-site/YARN.html). # Job is a Hadoop job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001553 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001554 "A String",
1555 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001556 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001557 "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'
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001558 "a_key": "A String",
1559 },
1560 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001561 "jarFileUris": [ # Optional. Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -07001562 "A String",
1563 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001564 "fileUris": [ # Optional. HCFS (Hadoop Compatible Filesystem) URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -07001565 "A String",
1566 ],
1567 "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.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001568 "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.
Thomas Coffee2f245372017-03-27 10:39:26 -07001569 "A String",
1570 ],
1571 "mainJarFileUri": "A String", # The HCFS URI of the jar file containing the main class. Examples: 'gs://foo-bucket/analytics-binaries/extract-useful-metrics-mr.jar' 'hdfs:/tmp/test-samples/custom-wordcount.jar' 'file:///home/usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar'
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001572 "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.
Thomas Coffee2f245372017-03-27 10:39:26 -07001573 "a_key": "A String",
1574 },
1575 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001576 "labels": { # Optional. The labels to associate with this job. Label keys must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). Label values may be empty, but, if present, must contain 1 to 63 characters, and must conform to RFC 1035 (https://www.ietf.org/rfc/rfc1035.txt). No more than 32 labels can be associated with a job.
Thomas Coffee2f245372017-03-27 10:39:26 -07001577 "a_key": "A String",
1578 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001579 "driverOutputResourceUri": "A String", # Output-only. A URI pointing to the location of the stdout of the job's driver program.
Thomas Coffee2f245372017-03-27 10:39:26 -07001580 "pysparkJob": { # A Cloud Dataproc job for running Apache PySpark (https://spark.apache.org/docs/0.9.0/python-programming-guide.html) applications on YARN. # Job is a Pyspark job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001581 "mainPythonFileUri": "A String", # Required. The HCFS URI of the main Python file to use as the driver. Must be a .py file.
1582 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001583 "A String",
1584 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001585 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Thomas Coffee2f245372017-03-27 10:39:26 -07001586 "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'
1587 "a_key": "A String",
1588 },
1589 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001590 "jarFileUris": [ # Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -07001591 "A String",
1592 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001593 "fileUris": [ # Optional. HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001594 "A String",
1595 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001596 "archiveUris": [ # Optional. HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001597 "A String",
1598 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001599 "pythonFileUris": [ # Optional. HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001600 "A String",
1601 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001602 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001603 "a_key": "A String",
1604 },
1605 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001606 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001607 "sparkJob": { # A Cloud Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN. # Job is a Spark job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001608 "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.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001609 "A String",
1610 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001611 "loggingConfig": { # The runtime logging config of the job. # Optional. The runtime log config for job execution.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001612 "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'
1613 "a_key": "A String",
1614 },
1615 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001616 "jarFileUris": [ # Optional. HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001617 "A String",
1618 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001619 "fileUris": [ # Optional. HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001620 "A String",
1621 ],
1622 "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.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001623 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001624 "A String",
1625 ],
Jon Wayne Parrott0a471d32016-05-19 10:54:38 -07001626 "mainJarFileUri": "A String", # The HCFS URI of the jar file that contains the main class.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001627 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001628 "a_key": "A String",
1629 },
1630 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001631 "yarnApplications": [ # Output-only. The collection of YARN applications spun up by this job.Beta Feature: This report is available for testing purposes only. It may be changed before final release.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001632 { # A YARN application created by a job. Application information is a subset of <code>org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto</code>.Beta Feature: This report is available for testing purposes only. It may be changed before final release.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001633 "progress": 3.14, # Required. The numerical progress of the application, from 1 to 100.
1634 "state": "A String", # Required. The application state.
1635 "name": "A String", # Required. The application name.
1636 "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.
Jon Wayne Parrott692617a2017-01-06 09:58:29 -08001637 },
1638 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001639 "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.
1640 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001641 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001642 "statusHistory": [ # Output-only. The previous job status.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001643 { # Cloud Dataproc job status.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001644 "state": "A String", # Output-only. A state message specifying the overall job state.
1645 "stateStartTime": "A String", # Output-only. The time when this state was entered.
1646 "details": "A String", # Output-only. Optional job state details, such as an error description if the state is <code>ERROR</code>.
1647 "substate": "A String", # Output-only. Additional state information, which includes status reported by the agent.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001648 },
1649 ],
1650 "hiveJob": { # A Cloud Dataproc job for running Apache Hive (https://hive.apache.org/) queries on YARN. # Job is a Hive job.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001651 "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001652 "scriptVariables": { # Optional. Mapping of query variable names to values (equivalent to the Hive command: SET name="value";).
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001653 "a_key": "A String",
1654 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001655 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001656 "A String",
1657 ],
1658 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001659 "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:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001660 # "hiveJob": {
1661 # "queryList": {
1662 # "queries": [
1663 # "query1",
1664 # "query2",
1665 # "query3;query4",
1666 # ]
1667 # }
1668 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001669 "A String",
1670 ],
1671 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001672 "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.
1673 "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.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001674 "a_key": "A String",
1675 },
1676 },
1677 }</pre>
1678</div>
1679
1680</body></html>