blob: 2cd6633928b0245d067eb8ec57d30d863755257c [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 Cheemalapatic30d2b52017-03-13 12:12:03 -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 Cheemalapatic30d2b52017-03-13 12:12:03 -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>.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800126 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400127 "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 -0800128 "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400129 "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 -0800130 "a_key": "A String",
131 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400132 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
133 "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 -0800134 "a_key": "A String",
135 },
136 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400137 "jarFileUris": [ # Optional HCFS URIs of jar files to be added to the Spark CLASSPATH.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800138 "A String",
139 ],
140 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400141 "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:
142 # "hiveJob": {
143 # "queryList": {
144 # "queries": [
145 # "query1",
146 # "query2",
147 # "query3;query4",
148 # ]
149 # }
150 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800151 "A String",
152 ],
153 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400154 "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 -0800155 "a_key": "A String",
156 },
157 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400158 "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 -0800159 "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400160 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Pig command: name=[value]).
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800161 "a_key": "A String",
162 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400163 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
164 "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 -0800165 "a_key": "A String",
166 },
167 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400168 "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 -0800169 "A String",
170 ],
171 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400172 "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:
173 # "hiveJob": {
174 # "queryList": {
175 # "queries": [
176 # "query1",
177 # "query2",
178 # "query3;query4",
179 # ]
180 # }
181 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800182 "A String",
183 ],
184 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400185 "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.
186 "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 -0800187 "a_key": "A String",
188 },
189 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400190 "placement": { # Cloud Dataproc job config. # Required Job information, including how, when, and where to run the job.
191 "clusterName": "A String", # Required The name of the cluster where the job will be submitted.
192 "clusterUuid": "A String", # Output-only A cluster UUID generated by the Cloud Dataproc service when the job is submitted.
193 },
194 "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>.
195 "projectId": "A String", # Required The ID of the Google Cloud Platform project that the job belongs to.
196 "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.
197 },
198 "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.
199 "jarFileUris": [ # Optional Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
200 "A String",
201 ],
202 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
203 "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'
204 "a_key": "A String",
205 },
206 },
207 "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.
208 "A String",
209 ],
210 "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.
211 "A String",
212 ],
213 "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.
214 "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.
215 "A String",
216 ],
217 "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'
218 "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.
219 "a_key": "A String",
220 },
221 },
222 "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.
Jon Wayne Parrott692617a2017-01-06 09:58:29 -0800223 "a_key": "A String",
224 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400225 "driverOutputResourceUri": "A String", # Output-only A URI pointing to the location of the stdout of the job's driver program.
226 "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.
227 "mainPythonFileUri": "A String", # Required The HCFS URI of the main Python file to use as the driver. Must be a .py file.
228 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800229 "A String",
230 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400231 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
232 "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 -0800233 "a_key": "A String",
234 },
235 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400236 "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 -0800237 "A String",
238 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400239 "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 -0800240 "A String",
241 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400242 "archiveUris": [ # Optional HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
243 "A String",
244 ],
245 "pythonFileUris": [ # Optional HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
246 "A String",
247 ],
248 "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.
249 "a_key": "A String",
250 },
251 },
252 "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.
253 "sparkJob": { # A Cloud Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN. # Job is a Spark job.
254 "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.
255 "A String",
256 ],
257 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
258 "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'
259 "a_key": "A String",
260 },
261 },
262 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
263 "A String",
264 ],
265 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
266 "A String",
267 ],
268 "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.
269 "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 -0800270 "A String",
271 ],
Jon Wayne Parrott0a471d32016-05-19 10:54:38 -0700272 "mainJarFileUri": "A String", # The HCFS URI of the jar file that contains the main class.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400273 "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 -0800274 "a_key": "A String",
275 },
276 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400277 "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.
278 { # 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.
279 "progress": 3.14, # Required The numerical progress of the application, from 1 to 100.
280 "state": "A String", # Required The application state.
281 "name": "A String", # Required The application name.
282 "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 -0800283 },
284 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400285 "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.
286 "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 -0800287 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400288 "statusHistory": [ # Output-only The previous job status.
289 { # Cloud Dataproc job status.
290 "state": "A String", # Output-only A state message specifying the overall job state.
291 "stateStartTime": "A String", # Output-only The time when this state was entered.
292 "details": "A String", # Output-only Optional job state details, such as an error description if the state is <code>ERROR</code>.
293 },
294 ],
295 "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 -0800296 "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400297 "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 -0800298 "a_key": "A String",
299 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400300 "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 -0800301 "A String",
302 ],
303 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400304 "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:
305 # "hiveJob": {
306 # "queryList": {
307 # "queries": [
308 # "query1",
309 # "query2",
310 # "query3;query4",
311 # ]
312 # }
313 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800314 "A String",
315 ],
316 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400317 "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.
318 "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 -0800319 "a_key": "A String",
320 },
321 },
322 }</pre>
323</div>
324
325<div class="method">
326 <code class="details" id="delete">delete(projectId, region, jobId, x__xgafv=None)</code>
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400327 <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 -0800328
329Args:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400330 projectId: string, Required The ID of the Google Cloud Platform project that the job belongs to. (required)
331 region: string, Required The Cloud Dataproc region in which to handle the request. (required)
332 jobId: string, Required The job ID. (required)
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800333 x__xgafv: string, V1 error format.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400334 Allowed values
335 1 - v1 error format
336 2 - v2 error format
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800337
338Returns:
339 An object of the form:
340
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400341 { # 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:
342 # service Foo {
343 # rpc Bar(google.protobuf.Empty) returns (google.protobuf.Empty);
344 # }
345 # The JSON representation for Empty is empty JSON object {}.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800346 }</pre>
347</div>
348
349<div class="method">
350 <code class="details" id="get">get(projectId, region, jobId, x__xgafv=None)</code>
351 <pre>Gets the resource representation for a job in a project.
352
353Args:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400354 projectId: string, Required The ID of the Google Cloud Platform project that the job belongs to. (required)
355 region: string, Required The Cloud Dataproc region in which to handle the request. (required)
356 jobId: string, Required The job ID. (required)
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800357 x__xgafv: string, V1 error format.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400358 Allowed values
359 1 - v1 error format
360 2 - v2 error format
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800361
362Returns:
363 An object of the form:
364
365 { # A Cloud Dataproc job resource.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400366 "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.
367 "state": "A String", # Output-only A state message specifying the overall job state.
368 "stateStartTime": "A String", # Output-only The time when this state was entered.
369 "details": "A String", # Output-only Optional job state details, such as an error description if the state is <code>ERROR</code>.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800370 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400371 "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 -0800372 "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400373 "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 -0800374 "a_key": "A String",
375 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400376 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
377 "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 -0800378 "a_key": "A String",
379 },
380 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400381 "jarFileUris": [ # Optional HCFS URIs of jar files to be added to the Spark CLASSPATH.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800382 "A String",
383 ],
384 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400385 "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:
386 # "hiveJob": {
387 # "queryList": {
388 # "queries": [
389 # "query1",
390 # "query2",
391 # "query3;query4",
392 # ]
393 # }
394 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800395 "A String",
396 ],
397 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400398 "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 -0800399 "a_key": "A String",
400 },
401 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400402 "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 -0800403 "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400404 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Pig command: name=[value]).
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800405 "a_key": "A String",
406 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400407 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
408 "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 -0800409 "a_key": "A String",
410 },
411 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400412 "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 -0800413 "A String",
414 ],
415 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400416 "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:
417 # "hiveJob": {
418 # "queryList": {
419 # "queries": [
420 # "query1",
421 # "query2",
422 # "query3;query4",
423 # ]
424 # }
425 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800426 "A String",
427 ],
428 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400429 "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.
430 "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 -0800431 "a_key": "A String",
432 },
433 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400434 "placement": { # Cloud Dataproc job config. # Required Job information, including how, when, and where to run the job.
435 "clusterName": "A String", # Required The name of the cluster where the job will be submitted.
436 "clusterUuid": "A String", # Output-only A cluster UUID generated by the Cloud Dataproc service when the job is submitted.
437 },
438 "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>.
439 "projectId": "A String", # Required The ID of the Google Cloud Platform project that the job belongs to.
440 "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.
441 },
442 "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.
443 "jarFileUris": [ # Optional Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
444 "A String",
445 ],
446 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
447 "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'
448 "a_key": "A String",
449 },
450 },
451 "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.
452 "A String",
453 ],
454 "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.
455 "A String",
456 ],
457 "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.
458 "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.
459 "A String",
460 ],
461 "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'
462 "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.
463 "a_key": "A String",
464 },
465 },
466 "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.
Jon Wayne Parrott692617a2017-01-06 09:58:29 -0800467 "a_key": "A String",
468 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400469 "driverOutputResourceUri": "A String", # Output-only A URI pointing to the location of the stdout of the job's driver program.
470 "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.
471 "mainPythonFileUri": "A String", # Required The HCFS URI of the main Python file to use as the driver. Must be a .py file.
472 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800473 "A String",
474 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400475 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
476 "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 -0800477 "a_key": "A String",
478 },
479 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400480 "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 -0800481 "A String",
482 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400483 "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 -0800484 "A String",
485 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400486 "archiveUris": [ # Optional HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
487 "A String",
488 ],
489 "pythonFileUris": [ # Optional HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
490 "A String",
491 ],
492 "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.
493 "a_key": "A String",
494 },
495 },
496 "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.
497 "sparkJob": { # A Cloud Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN. # Job is a Spark job.
498 "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.
499 "A String",
500 ],
501 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
502 "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'
503 "a_key": "A String",
504 },
505 },
506 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
507 "A String",
508 ],
509 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
510 "A String",
511 ],
512 "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.
513 "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 -0800514 "A String",
515 ],
Jon Wayne Parrott0a471d32016-05-19 10:54:38 -0700516 "mainJarFileUri": "A String", # The HCFS URI of the jar file that contains the main class.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400517 "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 -0800518 "a_key": "A String",
519 },
520 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400521 "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.
522 { # 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.
523 "progress": 3.14, # Required The numerical progress of the application, from 1 to 100.
524 "state": "A String", # Required The application state.
525 "name": "A String", # Required The application name.
526 "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 -0800527 },
528 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400529 "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.
530 "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 -0800531 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400532 "statusHistory": [ # Output-only The previous job status.
533 { # Cloud Dataproc job status.
534 "state": "A String", # Output-only A state message specifying the overall job state.
535 "stateStartTime": "A String", # Output-only The time when this state was entered.
536 "details": "A String", # Output-only Optional job state details, such as an error description if the state is <code>ERROR</code>.
537 },
538 ],
539 "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 -0800540 "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400541 "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 -0800542 "a_key": "A String",
543 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400544 "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 -0800545 "A String",
546 ],
547 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400548 "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:
549 # "hiveJob": {
550 # "queryList": {
551 # "queries": [
552 # "query1",
553 # "query2",
554 # "query3;query4",
555 # ]
556 # }
557 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800558 "A String",
559 ],
560 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400561 "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.
562 "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 -0800563 "a_key": "A String",
564 },
565 },
566 }</pre>
567</div>
568
569<div class="method">
Jon Wayne Parrott692617a2017-01-06 09:58:29 -0800570 <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 -0800571 <pre>Lists regions/{region}/jobs in a project.
572
573Args:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400574 projectId: string, Required The ID of the Google Cloud Platform project that the job belongs to. (required)
575 region: string, Required The Cloud Dataproc region in which to handle the request. (required)
576 pageSize: integer, Optional The number of results to return in each response.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800577 x__xgafv: string, V1 error format.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400578 Allowed values
579 1 - v1 error format
580 2 - v2 error format
581 pageToken: string, Optional The page token, returned by a previous call, to request the next page of results.
582 clusterName: string, Optional If set, the returned jobs list includes only jobs that were submitted to the named cluster.
583 jobStateMatcher: string, Optional Specifies enumerated categories of jobs to list (default = match ALL jobs).
584 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 -0800585
586Returns:
587 An object of the form:
588
589 { # A list of jobs in a project.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400590 "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>.
591 "jobs": [ # Output-only Jobs list.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800592 { # A Cloud Dataproc job resource.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400593 "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.
594 "state": "A String", # Output-only A state message specifying the overall job state.
595 "stateStartTime": "A String", # Output-only The time when this state was entered.
596 "details": "A String", # Output-only Optional job state details, such as an error description if the state is <code>ERROR</code>.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800597 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400598 "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 -0800599 "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400600 "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 -0800601 "a_key": "A String",
602 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400603 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
604 "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 -0800605 "a_key": "A String",
606 },
607 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400608 "jarFileUris": [ # Optional HCFS URIs of jar files to be added to the Spark CLASSPATH.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800609 "A String",
610 ],
611 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400612 "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:
613 # "hiveJob": {
614 # "queryList": {
615 # "queries": [
616 # "query1",
617 # "query2",
618 # "query3;query4",
619 # ]
620 # }
621 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800622 "A String",
623 ],
624 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400625 "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 -0800626 "a_key": "A String",
627 },
628 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400629 "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 -0800630 "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400631 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Pig command: name=[value]).
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800632 "a_key": "A String",
633 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400634 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
635 "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 -0800636 "a_key": "A String",
637 },
638 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400639 "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 -0800640 "A String",
641 ],
642 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400643 "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:
644 # "hiveJob": {
645 # "queryList": {
646 # "queries": [
647 # "query1",
648 # "query2",
649 # "query3;query4",
650 # ]
651 # }
652 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800653 "A String",
654 ],
655 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400656 "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.
657 "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 -0800658 "a_key": "A String",
659 },
660 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400661 "placement": { # Cloud Dataproc job config. # Required Job information, including how, when, and where to run the job.
662 "clusterName": "A String", # Required The name of the cluster where the job will be submitted.
663 "clusterUuid": "A String", # Output-only A cluster UUID generated by the Cloud Dataproc service when the job is submitted.
664 },
665 "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>.
666 "projectId": "A String", # Required The ID of the Google Cloud Platform project that the job belongs to.
667 "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.
668 },
669 "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.
670 "jarFileUris": [ # Optional Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
671 "A String",
672 ],
673 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
674 "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'
675 "a_key": "A String",
676 },
677 },
678 "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.
679 "A String",
680 ],
681 "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.
682 "A String",
683 ],
684 "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.
685 "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.
686 "A String",
687 ],
688 "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'
689 "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.
690 "a_key": "A String",
691 },
692 },
693 "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.
Jon Wayne Parrott692617a2017-01-06 09:58:29 -0800694 "a_key": "A String",
695 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400696 "driverOutputResourceUri": "A String", # Output-only A URI pointing to the location of the stdout of the job's driver program.
697 "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.
698 "mainPythonFileUri": "A String", # Required The HCFS URI of the main Python file to use as the driver. Must be a .py file.
699 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800700 "A String",
701 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400702 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
703 "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 -0800704 "a_key": "A String",
705 },
706 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400707 "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 -0800708 "A String",
709 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400710 "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 -0800711 "A String",
712 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400713 "archiveUris": [ # Optional HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
714 "A String",
715 ],
716 "pythonFileUris": [ # Optional HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
717 "A String",
718 ],
719 "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.
720 "a_key": "A String",
721 },
722 },
723 "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.
724 "sparkJob": { # A Cloud Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN. # Job is a Spark job.
725 "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.
726 "A String",
727 ],
728 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
729 "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'
730 "a_key": "A String",
731 },
732 },
733 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
734 "A String",
735 ],
736 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
737 "A String",
738 ],
739 "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.
740 "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 -0800741 "A String",
742 ],
Jon Wayne Parrott0a471d32016-05-19 10:54:38 -0700743 "mainJarFileUri": "A String", # The HCFS URI of the jar file that contains the main class.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400744 "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 -0800745 "a_key": "A String",
746 },
747 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400748 "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.
749 { # 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.
750 "progress": 3.14, # Required The numerical progress of the application, from 1 to 100.
751 "state": "A String", # Required The application state.
752 "name": "A String", # Required The application name.
753 "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 -0800754 },
755 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400756 "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.
757 "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 -0800758 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400759 "statusHistory": [ # Output-only The previous job status.
760 { # Cloud Dataproc job status.
761 "state": "A String", # Output-only A state message specifying the overall job state.
762 "stateStartTime": "A String", # Output-only The time when this state was entered.
763 "details": "A String", # Output-only Optional job state details, such as an error description if the state is <code>ERROR</code>.
764 },
765 ],
766 "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 -0800767 "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400768 "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 -0800769 "a_key": "A String",
770 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400771 "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 -0800772 "A String",
773 ],
774 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400775 "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:
776 # "hiveJob": {
777 # "queryList": {
778 # "queries": [
779 # "query1",
780 # "query2",
781 # "query3;query4",
782 # ]
783 # }
784 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -0800785 "A String",
786 ],
787 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400788 "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.
789 "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 -0800790 "a_key": "A String",
791 },
792 },
793 },
794 ],
795 }</pre>
796</div>
797
798<div class="method">
799 <code class="details" id="list_next">list_next(previous_request, previous_response)</code>
800 <pre>Retrieves the next page of results.
801
802Args:
803 previous_request: The request for the previous page. (required)
804 previous_response: The response from the request for the previous page. (required)
805
806Returns:
807 A request object that you can call 'execute()' on to request the next
808 page. Returns None if there are no more items in the collection.
809 </pre>
810</div>
811
812<div class="method">
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400813 <code class="details" id="patch">patch(projectId, region, jobId, body, updateMask=None, x__xgafv=None)</code>
814 <pre>Updates a job in a project.
815
816Args:
817 projectId: string, Required The ID of the Google Cloud Platform project that the job belongs to. (required)
818 region: string, Required The Cloud Dataproc region in which to handle the request. (required)
819 jobId: string, Required The job ID. (required)
820 body: object, The request body. (required)
821 The object takes the form of:
822
823{ # A Cloud Dataproc job resource.
824 "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.
825 "state": "A String", # Output-only A state message specifying the overall job state.
826 "stateStartTime": "A String", # Output-only The time when this state was entered.
827 "details": "A String", # Output-only Optional job state details, such as an error description if the state is <code>ERROR</code>.
828 },
829 "sparkSqlJob": { # A Cloud Dataproc job for running Apache Spark SQL (http://spark.apache.org/sql/) queries. # Job is a SparkSql job.
830 "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
831 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Spark SQL command: SET name="value";).
832 "a_key": "A String",
833 },
834 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
835 "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'
836 "a_key": "A String",
837 },
838 },
839 "jarFileUris": [ # Optional HCFS URIs of jar files to be added to the Spark CLASSPATH.
840 "A String",
841 ],
842 "queryList": { # A list of queries to run on a cluster. # A list of queries.
843 "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:
844 # "hiveJob": {
845 # "queryList": {
846 # "queries": [
847 # "query1",
848 # "query2",
849 # "query3;query4",
850 # ]
851 # }
852 # }
853 "A String",
854 ],
855 },
856 "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.
857 "a_key": "A String",
858 },
859 },
860 "pigJob": { # A Cloud Dataproc job for running Apache Pig (https://pig.apache.org/) queries on YARN. # Job is a Pig job.
861 "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
862 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Pig command: name=[value]).
863 "a_key": "A String",
864 },
865 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
866 "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'
867 "a_key": "A String",
868 },
869 },
870 "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.
871 "A String",
872 ],
873 "queryList": { # A list of queries to run on a cluster. # A list of queries.
874 "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:
875 # "hiveJob": {
876 # "queryList": {
877 # "queries": [
878 # "query1",
879 # "query2",
880 # "query3;query4",
881 # ]
882 # }
883 # }
884 "A String",
885 ],
886 },
887 "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.
888 "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.
889 "a_key": "A String",
890 },
891 },
892 "placement": { # Cloud Dataproc job config. # Required Job information, including how, when, and where to run the job.
893 "clusterName": "A String", # Required The name of the cluster where the job will be submitted.
894 "clusterUuid": "A String", # Output-only A cluster UUID generated by the Cloud Dataproc service when the job is submitted.
895 },
896 "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>.
897 "projectId": "A String", # Required The ID of the Google Cloud Platform project that the job belongs to.
898 "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.
899 },
900 "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.
901 "jarFileUris": [ # Optional Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
902 "A String",
903 ],
904 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
905 "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'
906 "a_key": "A String",
907 },
908 },
909 "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.
910 "A String",
911 ],
912 "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.
913 "A String",
914 ],
915 "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.
916 "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.
917 "A String",
918 ],
919 "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'
920 "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.
921 "a_key": "A String",
922 },
923 },
924 "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.
925 "a_key": "A String",
926 },
927 "driverOutputResourceUri": "A String", # Output-only A URI pointing to the location of the stdout of the job's driver program.
928 "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.
929 "mainPythonFileUri": "A String", # Required The HCFS URI of the main Python file to use as the driver. Must be a .py file.
930 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
931 "A String",
932 ],
933 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
934 "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'
935 "a_key": "A String",
936 },
937 },
938 "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.
939 "A String",
940 ],
941 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.
942 "A String",
943 ],
944 "archiveUris": [ # Optional HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
945 "A String",
946 ],
947 "pythonFileUris": [ # Optional HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
948 "A String",
949 ],
950 "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.
951 "a_key": "A String",
952 },
953 },
954 "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.
955 "sparkJob": { # A Cloud Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN. # Job is a Spark job.
956 "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.
957 "A String",
958 ],
959 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
960 "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'
961 "a_key": "A String",
962 },
963 },
964 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
965 "A String",
966 ],
967 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
968 "A String",
969 ],
970 "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.
971 "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.
972 "A String",
973 ],
974 "mainJarFileUri": "A String", # The HCFS URI of the jar file that contains the main class.
975 "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.
976 "a_key": "A String",
977 },
978 },
979 "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.
980 { # 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.
981 "progress": 3.14, # Required The numerical progress of the application, from 1 to 100.
982 "state": "A String", # Required The application state.
983 "name": "A String", # Required The application name.
984 "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.
985 },
986 ],
987 "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.
988 "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.
989 },
990 "statusHistory": [ # Output-only The previous job status.
991 { # Cloud Dataproc job status.
992 "state": "A String", # Output-only A state message specifying the overall job state.
993 "stateStartTime": "A String", # Output-only The time when this state was entered.
994 "details": "A String", # Output-only Optional job state details, such as an error description if the state is <code>ERROR</code>.
995 },
996 ],
997 "hiveJob": { # A Cloud Dataproc job for running Apache Hive (https://hive.apache.org/) queries on YARN. # Job is a Hive job.
998 "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
999 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Hive command: SET name="value";).
1000 "a_key": "A String",
1001 },
1002 "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.
1003 "A String",
1004 ],
1005 "queryList": { # A list of queries to run on a cluster. # A list of queries.
1006 "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:
1007 # "hiveJob": {
1008 # "queryList": {
1009 # "queries": [
1010 # "query1",
1011 # "query2",
1012 # "query3;query4",
1013 # ]
1014 # }
1015 # }
1016 "A String",
1017 ],
1018 },
1019 "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.
1020 "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.
1021 "a_key": "A String",
1022 },
1023 },
1024}
1025
1026 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.
1027 x__xgafv: string, V1 error format.
1028 Allowed values
1029 1 - v1 error format
1030 2 - v2 error format
1031
1032Returns:
1033 An object of the form:
1034
1035 { # A Cloud Dataproc job resource.
1036 "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.
1037 "state": "A String", # Output-only A state message specifying the overall job state.
1038 "stateStartTime": "A String", # Output-only The time when this state was entered.
1039 "details": "A String", # Output-only Optional job state details, such as an error description if the state is <code>ERROR</code>.
1040 },
1041 "sparkSqlJob": { # A Cloud Dataproc job for running Apache Spark SQL (http://spark.apache.org/sql/) queries. # Job is a SparkSql job.
1042 "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
1043 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Spark SQL command: SET name="value";).
1044 "a_key": "A String",
1045 },
1046 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
1047 "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'
1048 "a_key": "A String",
1049 },
1050 },
1051 "jarFileUris": [ # Optional HCFS URIs of jar files to be added to the Spark CLASSPATH.
1052 "A String",
1053 ],
1054 "queryList": { # A list of queries to run on a cluster. # A list of queries.
1055 "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:
1056 # "hiveJob": {
1057 # "queryList": {
1058 # "queries": [
1059 # "query1",
1060 # "query2",
1061 # "query3;query4",
1062 # ]
1063 # }
1064 # }
1065 "A String",
1066 ],
1067 },
1068 "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.
1069 "a_key": "A String",
1070 },
1071 },
1072 "pigJob": { # A Cloud Dataproc job for running Apache Pig (https://pig.apache.org/) queries on YARN. # Job is a Pig job.
1073 "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
1074 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Pig command: name=[value]).
1075 "a_key": "A String",
1076 },
1077 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
1078 "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'
1079 "a_key": "A String",
1080 },
1081 },
1082 "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.
1083 "A String",
1084 ],
1085 "queryList": { # A list of queries to run on a cluster. # A list of queries.
1086 "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:
1087 # "hiveJob": {
1088 # "queryList": {
1089 # "queries": [
1090 # "query1",
1091 # "query2",
1092 # "query3;query4",
1093 # ]
1094 # }
1095 # }
1096 "A String",
1097 ],
1098 },
1099 "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.
1100 "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.
1101 "a_key": "A String",
1102 },
1103 },
1104 "placement": { # Cloud Dataproc job config. # Required Job information, including how, when, and where to run the job.
1105 "clusterName": "A String", # Required The name of the cluster where the job will be submitted.
1106 "clusterUuid": "A String", # Output-only A cluster UUID generated by the Cloud Dataproc service when the job is submitted.
1107 },
1108 "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>.
1109 "projectId": "A String", # Required The ID of the Google Cloud Platform project that the job belongs to.
1110 "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.
1111 },
1112 "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.
1113 "jarFileUris": [ # Optional Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
1114 "A String",
1115 ],
1116 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
1117 "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'
1118 "a_key": "A String",
1119 },
1120 },
1121 "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.
1122 "A String",
1123 ],
1124 "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.
1125 "A String",
1126 ],
1127 "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.
1128 "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.
1129 "A String",
1130 ],
1131 "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'
1132 "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.
1133 "a_key": "A String",
1134 },
1135 },
1136 "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.
1137 "a_key": "A String",
1138 },
1139 "driverOutputResourceUri": "A String", # Output-only A URI pointing to the location of the stdout of the job's driver program.
1140 "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.
1141 "mainPythonFileUri": "A String", # Required The HCFS URI of the main Python file to use as the driver. Must be a .py file.
1142 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
1143 "A String",
1144 ],
1145 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
1146 "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'
1147 "a_key": "A String",
1148 },
1149 },
1150 "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.
1151 "A String",
1152 ],
1153 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.
1154 "A String",
1155 ],
1156 "archiveUris": [ # Optional HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
1157 "A String",
1158 ],
1159 "pythonFileUris": [ # Optional HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
1160 "A String",
1161 ],
1162 "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.
1163 "a_key": "A String",
1164 },
1165 },
1166 "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.
1167 "sparkJob": { # A Cloud Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN. # Job is a Spark job.
1168 "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.
1169 "A String",
1170 ],
1171 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
1172 "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'
1173 "a_key": "A String",
1174 },
1175 },
1176 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
1177 "A String",
1178 ],
1179 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
1180 "A String",
1181 ],
1182 "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.
1183 "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.
1184 "A String",
1185 ],
1186 "mainJarFileUri": "A String", # The HCFS URI of the jar file that contains the main class.
1187 "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.
1188 "a_key": "A String",
1189 },
1190 },
1191 "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.
1192 { # 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.
1193 "progress": 3.14, # Required The numerical progress of the application, from 1 to 100.
1194 "state": "A String", # Required The application state.
1195 "name": "A String", # Required The application name.
1196 "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.
1197 },
1198 ],
1199 "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.
1200 "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.
1201 },
1202 "statusHistory": [ # Output-only The previous job status.
1203 { # Cloud Dataproc job status.
1204 "state": "A String", # Output-only A state message specifying the overall job state.
1205 "stateStartTime": "A String", # Output-only The time when this state was entered.
1206 "details": "A String", # Output-only Optional job state details, such as an error description if the state is <code>ERROR</code>.
1207 },
1208 ],
1209 "hiveJob": { # A Cloud Dataproc job for running Apache Hive (https://hive.apache.org/) queries on YARN. # Job is a Hive job.
1210 "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
1211 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Hive command: SET name="value";).
1212 "a_key": "A String",
1213 },
1214 "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.
1215 "A String",
1216 ],
1217 "queryList": { # A list of queries to run on a cluster. # A list of queries.
1218 "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:
1219 # "hiveJob": {
1220 # "queryList": {
1221 # "queries": [
1222 # "query1",
1223 # "query2",
1224 # "query3;query4",
1225 # ]
1226 # }
1227 # }
1228 "A String",
1229 ],
1230 },
1231 "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.
1232 "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.
1233 "a_key": "A String",
1234 },
1235 },
1236 }</pre>
1237</div>
1238
1239<div class="method">
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001240 <code class="details" id="submit">submit(projectId, region, body, x__xgafv=None)</code>
1241 <pre>Submits a job to a cluster.
1242
1243Args:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001244 projectId: string, Required The ID of the Google Cloud Platform project that the job belongs to. (required)
1245 region: string, Required The Cloud Dataproc region in which to handle the request. (required)
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001246 body: object, The request body. (required)
1247 The object takes the form of:
1248
1249{ # A request to submit a job.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001250 "job": { # A Cloud Dataproc job resource. # Required The job resource.
1251 "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.
1252 "state": "A String", # Output-only A state message specifying the overall job state.
1253 "stateStartTime": "A String", # Output-only The time when this state was entered.
1254 "details": "A String", # Output-only Optional job state details, such as an error description if the state is <code>ERROR</code>.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001255 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001256 "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 -08001257 "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001258 "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 -08001259 "a_key": "A String",
1260 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001261 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
1262 "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 -08001263 "a_key": "A String",
1264 },
1265 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001266 "jarFileUris": [ # Optional HCFS URIs of jar files to be added to the Spark CLASSPATH.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001267 "A String",
1268 ],
1269 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001270 "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:
1271 # "hiveJob": {
1272 # "queryList": {
1273 # "queries": [
1274 # "query1",
1275 # "query2",
1276 # "query3;query4",
1277 # ]
1278 # }
1279 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001280 "A String",
1281 ],
1282 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001283 "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 -08001284 "a_key": "A String",
1285 },
1286 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001287 "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 -08001288 "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001289 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Pig command: name=[value]).
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001290 "a_key": "A String",
1291 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001292 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
1293 "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 -08001294 "a_key": "A String",
1295 },
1296 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001297 "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 -08001298 "A String",
1299 ],
1300 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001301 "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:
1302 # "hiveJob": {
1303 # "queryList": {
1304 # "queries": [
1305 # "query1",
1306 # "query2",
1307 # "query3;query4",
1308 # ]
1309 # }
1310 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001311 "A String",
1312 ],
1313 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001314 "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.
1315 "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 -08001316 "a_key": "A String",
1317 },
1318 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001319 "placement": { # Cloud Dataproc job config. # Required Job information, including how, when, and where to run the job.
1320 "clusterName": "A String", # Required The name of the cluster where the job will be submitted.
1321 "clusterUuid": "A String", # Output-only A cluster UUID generated by the Cloud Dataproc service when the job is submitted.
1322 },
1323 "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>.
1324 "projectId": "A String", # Required The ID of the Google Cloud Platform project that the job belongs to.
1325 "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.
1326 },
1327 "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.
1328 "jarFileUris": [ # Optional Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
1329 "A String",
1330 ],
1331 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
1332 "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'
1333 "a_key": "A String",
1334 },
1335 },
1336 "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.
1337 "A String",
1338 ],
1339 "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.
1340 "A String",
1341 ],
1342 "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.
1343 "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.
1344 "A String",
1345 ],
1346 "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'
1347 "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.
1348 "a_key": "A String",
1349 },
1350 },
1351 "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.
Jon Wayne Parrott692617a2017-01-06 09:58:29 -08001352 "a_key": "A String",
1353 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001354 "driverOutputResourceUri": "A String", # Output-only A URI pointing to the location of the stdout of the job's driver program.
1355 "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.
1356 "mainPythonFileUri": "A String", # Required The HCFS URI of the main Python file to use as the driver. Must be a .py file.
1357 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001358 "A String",
1359 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001360 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
1361 "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 -08001362 "a_key": "A String",
1363 },
1364 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001365 "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 -08001366 "A String",
1367 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001368 "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 -08001369 "A String",
1370 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001371 "archiveUris": [ # Optional HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
1372 "A String",
1373 ],
1374 "pythonFileUris": [ # Optional HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
1375 "A String",
1376 ],
1377 "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.
1378 "a_key": "A String",
1379 },
1380 },
1381 "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.
1382 "sparkJob": { # A Cloud Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN. # Job is a Spark job.
1383 "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.
1384 "A String",
1385 ],
1386 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
1387 "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'
1388 "a_key": "A String",
1389 },
1390 },
1391 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
1392 "A String",
1393 ],
1394 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
1395 "A String",
1396 ],
1397 "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.
1398 "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 -08001399 "A String",
1400 ],
Jon Wayne Parrott0a471d32016-05-19 10:54:38 -07001401 "mainJarFileUri": "A String", # The HCFS URI of the jar file that contains the main class.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001402 "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 -08001403 "a_key": "A String",
1404 },
1405 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001406 "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.
1407 { # 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.
1408 "progress": 3.14, # Required The numerical progress of the application, from 1 to 100.
1409 "state": "A String", # Required The application state.
1410 "name": "A String", # Required The application name.
1411 "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 -08001412 },
1413 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001414 "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.
1415 "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 -08001416 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001417 "statusHistory": [ # Output-only The previous job status.
1418 { # Cloud Dataproc job status.
1419 "state": "A String", # Output-only A state message specifying the overall job state.
1420 "stateStartTime": "A String", # Output-only The time when this state was entered.
1421 "details": "A String", # Output-only Optional job state details, such as an error description if the state is <code>ERROR</code>.
1422 },
1423 ],
1424 "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 -08001425 "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001426 "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 -08001427 "a_key": "A String",
1428 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001429 "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 -08001430 "A String",
1431 ],
1432 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001433 "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:
1434 # "hiveJob": {
1435 # "queryList": {
1436 # "queries": [
1437 # "query1",
1438 # "query2",
1439 # "query3;query4",
1440 # ]
1441 # }
1442 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001443 "A String",
1444 ],
1445 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001446 "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.
1447 "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 -08001448 "a_key": "A String",
1449 },
1450 },
1451 },
1452 }
1453
1454 x__xgafv: string, V1 error format.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001455 Allowed values
1456 1 - v1 error format
1457 2 - v2 error format
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001458
1459Returns:
1460 An object of the form:
1461
1462 { # A Cloud Dataproc job resource.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001463 "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.
1464 "state": "A String", # Output-only A state message specifying the overall job state.
1465 "stateStartTime": "A String", # Output-only The time when this state was entered.
1466 "details": "A String", # Output-only Optional job state details, such as an error description if the state is <code>ERROR</code>.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001467 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001468 "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 -08001469 "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001470 "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 -08001471 "a_key": "A String",
1472 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001473 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
1474 "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 -08001475 "a_key": "A String",
1476 },
1477 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001478 "jarFileUris": [ # Optional HCFS URIs of jar files to be added to the Spark CLASSPATH.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001479 "A String",
1480 ],
1481 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001482 "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:
1483 # "hiveJob": {
1484 # "queryList": {
1485 # "queries": [
1486 # "query1",
1487 # "query2",
1488 # "query3;query4",
1489 # ]
1490 # }
1491 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001492 "A String",
1493 ],
1494 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001495 "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 -08001496 "a_key": "A String",
1497 },
1498 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001499 "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 -08001500 "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001501 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Pig command: name=[value]).
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001502 "a_key": "A String",
1503 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001504 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
1505 "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 -08001506 "a_key": "A String",
1507 },
1508 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001509 "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 -08001510 "A String",
1511 ],
1512 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001513 "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:
1514 # "hiveJob": {
1515 # "queryList": {
1516 # "queries": [
1517 # "query1",
1518 # "query2",
1519 # "query3;query4",
1520 # ]
1521 # }
1522 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001523 "A String",
1524 ],
1525 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001526 "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.
1527 "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 -08001528 "a_key": "A String",
1529 },
1530 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001531 "placement": { # Cloud Dataproc job config. # Required Job information, including how, when, and where to run the job.
1532 "clusterName": "A String", # Required The name of the cluster where the job will be submitted.
1533 "clusterUuid": "A String", # Output-only A cluster UUID generated by the Cloud Dataproc service when the job is submitted.
1534 },
1535 "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>.
1536 "projectId": "A String", # Required The ID of the Google Cloud Platform project that the job belongs to.
1537 "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.
1538 },
1539 "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.
1540 "jarFileUris": [ # Optional Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
1541 "A String",
1542 ],
1543 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
1544 "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'
1545 "a_key": "A String",
1546 },
1547 },
1548 "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.
1549 "A String",
1550 ],
1551 "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.
1552 "A String",
1553 ],
1554 "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.
1555 "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.
1556 "A String",
1557 ],
1558 "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'
1559 "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.
1560 "a_key": "A String",
1561 },
1562 },
1563 "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.
Jon Wayne Parrott692617a2017-01-06 09:58:29 -08001564 "a_key": "A String",
1565 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001566 "driverOutputResourceUri": "A String", # Output-only A URI pointing to the location of the stdout of the job's driver program.
1567 "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.
1568 "mainPythonFileUri": "A String", # Required The HCFS URI of the main Python file to use as the driver. Must be a .py file.
1569 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001570 "A String",
1571 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001572 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
1573 "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 -08001574 "a_key": "A String",
1575 },
1576 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001577 "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 -08001578 "A String",
1579 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001580 "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 -08001581 "A String",
1582 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001583 "archiveUris": [ # Optional HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
1584 "A String",
1585 ],
1586 "pythonFileUris": [ # Optional HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
1587 "A String",
1588 ],
1589 "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.
1590 "a_key": "A String",
1591 },
1592 },
1593 "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.
1594 "sparkJob": { # A Cloud Dataproc job for running Apache Spark (http://spark.apache.org/) applications on YARN. # Job is a Spark job.
1595 "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.
1596 "A String",
1597 ],
1598 "loggingConfig": { # The runtime logging config of the job. # Optional The runtime log config for job execution.
1599 "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'
1600 "a_key": "A String",
1601 },
1602 },
1603 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
1604 "A String",
1605 ],
1606 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
1607 "A String",
1608 ],
1609 "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.
1610 "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 -08001611 "A String",
1612 ],
Jon Wayne Parrott0a471d32016-05-19 10:54:38 -07001613 "mainJarFileUri": "A String", # The HCFS URI of the jar file that contains the main class.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001614 "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 -08001615 "a_key": "A String",
1616 },
1617 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001618 "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.
1619 { # 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.
1620 "progress": 3.14, # Required The numerical progress of the application, from 1 to 100.
1621 "state": "A String", # Required The application state.
1622 "name": "A String", # Required The application name.
1623 "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 -08001624 },
1625 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001626 "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.
1627 "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 -08001628 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001629 "statusHistory": [ # Output-only The previous job status.
1630 { # Cloud Dataproc job status.
1631 "state": "A String", # Output-only A state message specifying the overall job state.
1632 "stateStartTime": "A String", # Output-only The time when this state was entered.
1633 "details": "A String", # Output-only Optional job state details, such as an error description if the state is <code>ERROR</code>.
1634 },
1635 ],
1636 "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 -08001637 "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001638 "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 -08001639 "a_key": "A String",
1640 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001641 "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 -08001642 "A String",
1643 ],
1644 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001645 "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:
1646 # "hiveJob": {
1647 # "queryList": {
1648 # "queries": [
1649 # "query1",
1650 # "query2",
1651 # "query3;query4",
1652 # ]
1653 # }
1654 # }
Jon Wayne Parrott36e41bc2016-02-19 16:02:29 -08001655 "A String",
1656 ],
1657 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001658 "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.
1659 "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 -08001660 "a_key": "A String",
1661 },
1662 },
1663 }</pre>
1664</div>
1665
1666</body></html>