blob: e9935a0205384f535cb3b860619e17b31cd578ff [file] [log] [blame]
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001<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_v1alpha1.html">Google Cloud Dataproc API</a> . <a href="dataproc_v1alpha1.projects.html">projects</a> . <a href="dataproc_v1alpha1.projects.regions.html">regions</a> . <a href="dataproc_v1alpha1.projects.regions.jobs.html">jobs</a></h1>
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>
79<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>
80<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>
Sai Cheemalapatidf613972016-10-21 13:59:49 -070083<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">
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -040087 <code><a href="#list">list(projectId, region, body, x__xgafv=None)</a></code></p>
88<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">
93 <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">
Sai Cheemalapatidf613972016-10-21 13:59:49 -070096 <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>
101 <pre>Starts a job cancellation request. To access the job resource after cancellation, call regions/{region}/jobs:list or regions/{region}/jobs:get.
102
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 Dataproc region in which to handle the request. (required)
106 jobId: string, Required The job ID. (required)
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700107 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
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700117
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 "stateStartTime": "A String", # Output-only The time when this state was entered.
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700124 "substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700125 "startTime": "A String", # The time when the server started the job.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400126 "state": "A String", # Required A state message specifying the overall job state.
127 "details": "A String", # Optional Job state details, such as an error description if the state is <code>ERROR</code>.
128 "insertTime": "A String", # The time of the job request.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700129 "endTime": "A String", # The time when the job completed.
130 },
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700131 "hadoopJob": { # A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN. # Job is a Hadoop job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400132 "jarFileUris": [ # Optional Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -0700133 "A String",
134 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700135 "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.
136 "A String",
137 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700138 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
139 "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
140 "a_key": "A String",
141 },
142 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400143 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.
144 "A String",
145 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700146 "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.
147 "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.
148 "A String",
149 ],
150 "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (HCFS) URI of the jar file containing the main class. Examples: gs://foo-bucket/analytics-binaries/extract-useful-metrics-mr.jar hdfs:/tmp/test-samples/custom-wordcount.jar file:///home/usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar
151 "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.
152 "a_key": "A String",
153 },
154 },
155 "labels": { # Optional The labels to associate with this job.Label keys must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}{0,62}Label values must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}\p{N}_-{0,63}No more than 64 labels can be associated with a given job.
156 "a_key": "A String",
157 },
158 "placement": { # Cloud Dataproc job configuration. # Required Job information, including how, when, and where to run the job.
159 "clusterName": "A String", # Required The name of the cluster where the job will be submitted.
160 "clusterUuid": "A String", # Output-only A cluster UUID generated by the Dataproc service when the job is submitted.
161 },
162 "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>.
163 "projectId": "A String", # Required The ID of the Google Cloud Platform project that the job belongs to.
164 "jobId": "A String", # Required The job ID, which must be unique within the project. The job ID is generated by the server upon job submission or provided by the user as a means to perform retries without creating duplicate jobs. The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), or dashes (-). The maximum length is 100 characters.
165 },
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700166 "sparkSqlJob": { # A Cloud Dataproc job for running Spark SQL queries. # Job is a SparkSql job.
167 "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400168 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Spark SQL command: SET name="value";).
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700169 "a_key": "A String",
170 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400171 "jarFileUris": [ # Optional HCFS URIs of jar files to be added to the Spark CLASSPATH.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700172 "A String",
173 ],
174 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400175 "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:
176 # "hiveJob": {
177 # "queryList": {
178 # "queries": [
179 # "query1",
180 # "query2",
181 # "query3;query4",
182 # ]
183 # }
184 # }
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700185 "A String",
186 ],
187 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400188 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
189 "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
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700190 "a_key": "A String",
191 },
192 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400193 "properties": { # Optional A mapping of property names to values, used to configure Spark SQL's SparkConf. Properties that conflict with values set by the Cloud Dataproc API may be overwritten.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700194 "a_key": "A String",
195 },
196 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400197 "yarnApplications": [ # Output-only The collection of Yarn applications spun up by this job.
198 { # A YARN application created by a job. Application information is a subset of <code>org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto</code>.
199 "progress": 3.14, # Required The numerical progress of the application, from 1 to 100.
200 "state": "A String", # Required The application state.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400201 "name": "A String", # Required The application name.
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700202 "trackingUrl": "A String", # Optional The HTTP URL of the ApplicationMaster, HistoryServer, or TimelineServer that provides application-specific information. The URL uses the internal hostname, and requires a proxy server for resolution and, possibly, access.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400203 },
204 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700205 "driverOutputUri": "A String", # Output-only A URI pointing to the location of the mixed stdout/stderr of the job's driver program&mdash;for example, <code>gs://sysbucket123/foo-cluster/jobid-123/driver/output</code>.
206 "pigJob": { # A Cloud Dataproc job for running Pig queries on YARN. # Job is a Pig job.
207 "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
208 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Pig command: "name=value").
209 "a_key": "A String",
210 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400211 "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.
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700212 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATH of the Pig Client and Hadoop MapReduce (MR) tasks. Can contain Pig UDFs.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700213 "A String",
214 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400215 "queryList": { # A list of queries to run on a cluster. # A list of queries.
216 "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:
217 # "hiveJob": {
218 # "queryList": {
219 # "queries": [
220 # "query1",
221 # "query2",
222 # "query3;query4",
223 # ]
224 # }
225 # }
226 "A String",
227 ],
228 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400229 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
230 "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
231 "a_key": "A String",
232 },
233 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400234 "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.
235 "a_key": "A String",
236 },
237 },
238 "driverOutputResourceUri": "A String", # Output-only A URI pointing to the location of the stdout of the job's driver program.
239 "pysparkJob": { # A Cloud Dataproc job for running PySpark applications on YARN. # Job is a Pyspark job.
240 "mainPythonFileUri": "A String", # Required The Hadoop Compatible Filesystem (HCFS) URI of the main Python file to use as the driver. Must be a .py file.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400241 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400242 "A String",
243 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400244 "args": [ # Optional The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400245 "A String",
246 ],
247 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
248 "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
249 "a_key": "A String",
250 },
251 },
252 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.
253 "A String",
254 ],
255 "archiveUris": [ # Optional HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
256 "A String",
257 ],
258 "pythonFileUris": [ # Optional HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
259 "A String",
260 ],
261 "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.
262 "a_key": "A String",
263 },
264 },
265 "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.
266 "driverInputResourceUri": "A String", # Output-only A URI pointing to the location of the stdin of the job's driver program, only set if the job is interactive.
267 "sparkJob": { # A Cloud Dataproc job for running Spark applications on YARN. # Job is a Spark job.
Thomas Coffee2f245372017-03-27 10:39:26 -0700268 "args": [ # Optional The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400269 "A String",
270 ],
Thomas Coffee2f245372017-03-27 10:39:26 -0700271 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400272 "A String",
273 ],
274 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
275 "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
276 "a_key": "A String",
277 },
278 },
279 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700280 "A String",
281 ],
282 "mainClass": "A String", # The name of the driver's main class. The jar file that contains the class must be in the default CLASSPATH or specified in jar_file_uris.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400283 "archiveUris": [ # Optional HCFS URIs of archives to be extracted in the working directory of Spark drivers and tasks. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700284 "A String",
285 ],
286 "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (HCFS) URI of the jar file that contains the main class.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400287 "properties": { # Optional A mapping of property names to values, used to configure Spark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700288 "a_key": "A String",
289 },
290 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400291 "submittedBy": "A String", # Output-only The email address of the user submitting the job. For jobs submitted on the cluster, the address is <code>username@hostname</code>.
292 "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.
293 "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.
294 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400295 "statusHistory": [ # Output-only The previous job status.
296 { # Cloud Dataproc job status.
297 "stateStartTime": "A String", # Output-only The time when this state was entered.
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700298 "substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400299 "startTime": "A String", # The time when the server started the job.
300 "state": "A String", # Required A state message specifying the overall job state.
301 "details": "A String", # Optional Job state details, such as an error description if the state is <code>ERROR</code>.
302 "insertTime": "A String", # The time of the job request.
303 "endTime": "A String", # The time when the job completed.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700304 },
305 ],
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700306 "hiveJob": { # A Cloud Dataproc job for running Hive queries on YARN. # Job is a Hive job.
307 "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400308 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Hive command: 'SET name="value";').
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700309 "a_key": "A String",
310 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400311 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATH of the Hive server and Hadoop MapReduce (MR) tasks. Can contain Hive SerDes and UDFs.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700312 "A String",
313 ],
314 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400315 "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:
316 # "hiveJob": {
317 # "queryList": {
318 # "queries": [
319 # "query1",
320 # "query2",
321 # "query3;query4",
322 # ]
323 # }
324 # }
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700325 "A String",
326 ],
327 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400328 "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.
329 "properties": { # Optional A mapping of property names and values, used to configure Hive. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site.xml, /etc/hive/conf/hive-site.xml, and classes in user code.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700330 "a_key": "A String",
331 },
332 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400333 "interactive": True or False, # Optional If set to true, then the driver's stdin will be kept open and driver_input_uri will be set to provide a path at which additional input can be sent to the driver.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700334 }</pre>
335</div>
336
337<div class="method">
338 <code class="details" id="delete">delete(projectId, region, jobId, x__xgafv=None)</code>
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400339 <pre>Deletes the job from the project. If the job is active, the delete fails, and the response returns FAILED_PRECONDITION.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700340
341Args:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400342 projectId: string, Required The ID of the Google Cloud Platform project that the job belongs to. (required)
343 region: string, Required The Dataproc region in which to handle the request. (required)
344 jobId: string, Required The job ID. (required)
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700345 x__xgafv: string, V1 error format.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400346 Allowed values
347 1 - v1 error format
348 2 - v2 error format
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700349
350Returns:
351 An object of the form:
352
353 { # A Cloud Dataproc job resource.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400354 "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.
355 "stateStartTime": "A String", # Output-only The time when this state was entered.
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700356 "substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700357 "startTime": "A String", # The time when the server started the job.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400358 "state": "A String", # Required A state message specifying the overall job state.
359 "details": "A String", # Optional Job state details, such as an error description if the state is <code>ERROR</code>.
360 "insertTime": "A String", # The time of the job request.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700361 "endTime": "A String", # The time when the job completed.
362 },
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700363 "hadoopJob": { # A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN. # Job is a Hadoop job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400364 "jarFileUris": [ # Optional Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -0700365 "A String",
366 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700367 "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.
368 "A String",
369 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700370 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
371 "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
372 "a_key": "A String",
373 },
374 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400375 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.
376 "A String",
377 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700378 "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.
379 "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.
380 "A String",
381 ],
382 "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (HCFS) URI of the jar file containing the main class. Examples: gs://foo-bucket/analytics-binaries/extract-useful-metrics-mr.jar hdfs:/tmp/test-samples/custom-wordcount.jar file:///home/usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar
383 "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.
384 "a_key": "A String",
385 },
386 },
387 "labels": { # Optional The labels to associate with this job.Label keys must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}{0,62}Label values must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}\p{N}_-{0,63}No more than 64 labels can be associated with a given job.
388 "a_key": "A String",
389 },
390 "placement": { # Cloud Dataproc job configuration. # Required Job information, including how, when, and where to run the job.
391 "clusterName": "A String", # Required The name of the cluster where the job will be submitted.
392 "clusterUuid": "A String", # Output-only A cluster UUID generated by the Dataproc service when the job is submitted.
393 },
394 "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>.
395 "projectId": "A String", # Required The ID of the Google Cloud Platform project that the job belongs to.
396 "jobId": "A String", # Required The job ID, which must be unique within the project. The job ID is generated by the server upon job submission or provided by the user as a means to perform retries without creating duplicate jobs. The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), or dashes (-). The maximum length is 100 characters.
397 },
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700398 "sparkSqlJob": { # A Cloud Dataproc job for running Spark SQL queries. # Job is a SparkSql job.
399 "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400400 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Spark SQL command: SET name="value";).
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700401 "a_key": "A String",
402 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400403 "jarFileUris": [ # Optional HCFS URIs of jar files to be added to the Spark CLASSPATH.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700404 "A String",
405 ],
406 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400407 "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:
408 # "hiveJob": {
409 # "queryList": {
410 # "queries": [
411 # "query1",
412 # "query2",
413 # "query3;query4",
414 # ]
415 # }
416 # }
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700417 "A String",
418 ],
419 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400420 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
421 "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
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700422 "a_key": "A String",
423 },
424 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400425 "properties": { # Optional A mapping of property names to values, used to configure Spark SQL's SparkConf. Properties that conflict with values set by the Cloud Dataproc API may be overwritten.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700426 "a_key": "A String",
427 },
428 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400429 "yarnApplications": [ # Output-only The collection of Yarn applications spun up by this job.
430 { # A YARN application created by a job. Application information is a subset of <code>org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto</code>.
431 "progress": 3.14, # Required The numerical progress of the application, from 1 to 100.
432 "state": "A String", # Required The application state.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400433 "name": "A String", # Required The application name.
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700434 "trackingUrl": "A String", # Optional The HTTP URL of the ApplicationMaster, HistoryServer, or TimelineServer that provides application-specific information. The URL uses the internal hostname, and requires a proxy server for resolution and, possibly, access.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400435 },
436 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700437 "driverOutputUri": "A String", # Output-only A URI pointing to the location of the mixed stdout/stderr of the job's driver program&mdash;for example, <code>gs://sysbucket123/foo-cluster/jobid-123/driver/output</code>.
438 "pigJob": { # A Cloud Dataproc job for running Pig queries on YARN. # Job is a Pig job.
439 "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
440 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Pig command: "name=value").
441 "a_key": "A String",
442 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400443 "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.
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700444 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATH of the Pig Client and Hadoop MapReduce (MR) tasks. Can contain Pig UDFs.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700445 "A String",
446 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400447 "queryList": { # A list of queries to run on a cluster. # A list of queries.
448 "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:
449 # "hiveJob": {
450 # "queryList": {
451 # "queries": [
452 # "query1",
453 # "query2",
454 # "query3;query4",
455 # ]
456 # }
457 # }
458 "A String",
459 ],
460 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400461 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
462 "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
463 "a_key": "A String",
464 },
465 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400466 "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.
467 "a_key": "A String",
468 },
469 },
470 "driverOutputResourceUri": "A String", # Output-only A URI pointing to the location of the stdout of the job's driver program.
471 "pysparkJob": { # A Cloud Dataproc job for running PySpark applications on YARN. # Job is a Pyspark job.
472 "mainPythonFileUri": "A String", # Required The Hadoop Compatible Filesystem (HCFS) URI of the main Python file to use as the driver. Must be a .py file.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400473 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400474 "A String",
475 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400476 "args": [ # Optional The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400477 "A String",
478 ],
479 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
480 "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
481 "a_key": "A String",
482 },
483 },
484 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.
485 "A String",
486 ],
487 "archiveUris": [ # Optional HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
488 "A String",
489 ],
490 "pythonFileUris": [ # Optional HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
491 "A String",
492 ],
493 "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.
494 "a_key": "A String",
495 },
496 },
497 "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.
498 "driverInputResourceUri": "A String", # Output-only A URI pointing to the location of the stdin of the job's driver program, only set if the job is interactive.
499 "sparkJob": { # A Cloud Dataproc job for running Spark applications on YARN. # Job is a Spark job.
Thomas Coffee2f245372017-03-27 10:39:26 -0700500 "args": [ # Optional The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400501 "A String",
502 ],
Thomas Coffee2f245372017-03-27 10:39:26 -0700503 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400504 "A String",
505 ],
506 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
507 "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
508 "a_key": "A String",
509 },
510 },
511 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700512 "A String",
513 ],
514 "mainClass": "A String", # The name of the driver's main class. The jar file that contains the class must be in the default CLASSPATH or specified in jar_file_uris.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400515 "archiveUris": [ # Optional HCFS URIs of archives to be extracted in the working directory of Spark drivers and tasks. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700516 "A String",
517 ],
518 "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (HCFS) URI of the jar file that contains the main class.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400519 "properties": { # Optional A mapping of property names to values, used to configure Spark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700520 "a_key": "A String",
521 },
522 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400523 "submittedBy": "A String", # Output-only The email address of the user submitting the job. For jobs submitted on the cluster, the address is <code>username@hostname</code>.
524 "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.
525 "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.
526 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400527 "statusHistory": [ # Output-only The previous job status.
528 { # Cloud Dataproc job status.
529 "stateStartTime": "A String", # Output-only The time when this state was entered.
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700530 "substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400531 "startTime": "A String", # The time when the server started the job.
532 "state": "A String", # Required A state message specifying the overall job state.
533 "details": "A String", # Optional Job state details, such as an error description if the state is <code>ERROR</code>.
534 "insertTime": "A String", # The time of the job request.
535 "endTime": "A String", # The time when the job completed.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700536 },
537 ],
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700538 "hiveJob": { # A Cloud Dataproc job for running Hive queries on YARN. # Job is a Hive job.
539 "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400540 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Hive command: 'SET name="value";').
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700541 "a_key": "A String",
542 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400543 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATH of the Hive server and Hadoop MapReduce (MR) tasks. Can contain Hive SerDes and UDFs.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700544 "A String",
545 ],
546 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400547 "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:
548 # "hiveJob": {
549 # "queryList": {
550 # "queries": [
551 # "query1",
552 # "query2",
553 # "query3;query4",
554 # ]
555 # }
556 # }
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700557 "A String",
558 ],
559 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400560 "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.
561 "properties": { # Optional A mapping of property names and values, used to configure Hive. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site.xml, /etc/hive/conf/hive-site.xml, and classes in user code.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700562 "a_key": "A String",
563 },
564 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400565 "interactive": True or False, # Optional If set to true, then the driver's stdin will be kept open and driver_input_uri will be set to provide a path at which additional input can be sent to the driver.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700566 }</pre>
567</div>
568
569<div class="method">
570 <code class="details" id="get">get(projectId, region, jobId, x__xgafv=None)</code>
571 <pre>Gets the resource representation for a job 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 Dataproc region in which to handle the request. (required)
576 jobId: string, Required The job ID. (required)
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700577 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
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700581
582Returns:
583 An object of the form:
584
585 { # A Cloud Dataproc job resource.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400586 "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.
587 "stateStartTime": "A String", # Output-only The time when this state was entered.
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700588 "substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700589 "startTime": "A String", # The time when the server started the job.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400590 "state": "A String", # Required A state message specifying the overall job state.
591 "details": "A String", # Optional Job state details, such as an error description if the state is <code>ERROR</code>.
592 "insertTime": "A String", # The time of the job request.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700593 "endTime": "A String", # The time when the job completed.
594 },
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700595 "hadoopJob": { # A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN. # Job is a Hadoop job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400596 "jarFileUris": [ # Optional Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -0700597 "A String",
598 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700599 "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.
600 "A String",
601 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700602 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
603 "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
604 "a_key": "A String",
605 },
606 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400607 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.
608 "A String",
609 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700610 "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.
611 "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.
612 "A String",
613 ],
614 "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (HCFS) URI of the jar file containing the main class. Examples: gs://foo-bucket/analytics-binaries/extract-useful-metrics-mr.jar hdfs:/tmp/test-samples/custom-wordcount.jar file:///home/usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar
615 "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.
616 "a_key": "A String",
617 },
618 },
619 "labels": { # Optional The labels to associate with this job.Label keys must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}{0,62}Label values must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}\p{N}_-{0,63}No more than 64 labels can be associated with a given job.
620 "a_key": "A String",
621 },
622 "placement": { # Cloud Dataproc job configuration. # Required Job information, including how, when, and where to run the job.
623 "clusterName": "A String", # Required The name of the cluster where the job will be submitted.
624 "clusterUuid": "A String", # Output-only A cluster UUID generated by the Dataproc service when the job is submitted.
625 },
626 "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>.
627 "projectId": "A String", # Required The ID of the Google Cloud Platform project that the job belongs to.
628 "jobId": "A String", # Required The job ID, which must be unique within the project. The job ID is generated by the server upon job submission or provided by the user as a means to perform retries without creating duplicate jobs. The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), or dashes (-). The maximum length is 100 characters.
629 },
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700630 "sparkSqlJob": { # A Cloud Dataproc job for running Spark SQL queries. # Job is a SparkSql job.
631 "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400632 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Spark SQL command: SET name="value";).
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700633 "a_key": "A String",
634 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400635 "jarFileUris": [ # Optional HCFS URIs of jar files to be added to the Spark CLASSPATH.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700636 "A String",
637 ],
638 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400639 "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:
640 # "hiveJob": {
641 # "queryList": {
642 # "queries": [
643 # "query1",
644 # "query2",
645 # "query3;query4",
646 # ]
647 # }
648 # }
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700649 "A String",
650 ],
651 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400652 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
653 "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
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700654 "a_key": "A String",
655 },
656 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400657 "properties": { # Optional A mapping of property names to values, used to configure Spark SQL's SparkConf. Properties that conflict with values set by the Cloud Dataproc API may be overwritten.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700658 "a_key": "A String",
659 },
660 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400661 "yarnApplications": [ # Output-only The collection of Yarn applications spun up by this job.
662 { # A YARN application created by a job. Application information is a subset of <code>org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto</code>.
663 "progress": 3.14, # Required The numerical progress of the application, from 1 to 100.
664 "state": "A String", # Required The application state.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400665 "name": "A String", # Required The application name.
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700666 "trackingUrl": "A String", # Optional The HTTP URL of the ApplicationMaster, HistoryServer, or TimelineServer that provides application-specific information. The URL uses the internal hostname, and requires a proxy server for resolution and, possibly, access.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400667 },
668 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700669 "driverOutputUri": "A String", # Output-only A URI pointing to the location of the mixed stdout/stderr of the job's driver program&mdash;for example, <code>gs://sysbucket123/foo-cluster/jobid-123/driver/output</code>.
670 "pigJob": { # A Cloud Dataproc job for running Pig queries on YARN. # Job is a Pig job.
671 "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
672 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Pig command: "name=value").
673 "a_key": "A String",
674 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400675 "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.
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700676 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATH of the Pig Client and Hadoop MapReduce (MR) tasks. Can contain Pig UDFs.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700677 "A String",
678 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400679 "queryList": { # A list of queries to run on a cluster. # A list of queries.
680 "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:
681 # "hiveJob": {
682 # "queryList": {
683 # "queries": [
684 # "query1",
685 # "query2",
686 # "query3;query4",
687 # ]
688 # }
689 # }
690 "A String",
691 ],
692 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400693 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
694 "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
695 "a_key": "A String",
696 },
697 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400698 "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.
699 "a_key": "A String",
700 },
701 },
702 "driverOutputResourceUri": "A String", # Output-only A URI pointing to the location of the stdout of the job's driver program.
703 "pysparkJob": { # A Cloud Dataproc job for running PySpark applications on YARN. # Job is a Pyspark job.
704 "mainPythonFileUri": "A String", # Required The Hadoop Compatible Filesystem (HCFS) URI of the main Python file to use as the driver. Must be a .py file.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400705 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400706 "A String",
707 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400708 "args": [ # Optional The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400709 "A String",
710 ],
711 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
712 "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
713 "a_key": "A String",
714 },
715 },
716 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.
717 "A String",
718 ],
719 "archiveUris": [ # Optional HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
720 "A String",
721 ],
722 "pythonFileUris": [ # Optional HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
723 "A String",
724 ],
725 "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.
726 "a_key": "A String",
727 },
728 },
729 "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.
730 "driverInputResourceUri": "A String", # Output-only A URI pointing to the location of the stdin of the job's driver program, only set if the job is interactive.
731 "sparkJob": { # A Cloud Dataproc job for running Spark applications on YARN. # Job is a Spark job.
Thomas Coffee2f245372017-03-27 10:39:26 -0700732 "args": [ # Optional The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400733 "A String",
734 ],
Thomas Coffee2f245372017-03-27 10:39:26 -0700735 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400736 "A String",
737 ],
738 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
739 "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
740 "a_key": "A String",
741 },
742 },
743 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700744 "A String",
745 ],
746 "mainClass": "A String", # The name of the driver's main class. The jar file that contains the class must be in the default CLASSPATH or specified in jar_file_uris.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400747 "archiveUris": [ # Optional HCFS URIs of archives to be extracted in the working directory of Spark drivers and tasks. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700748 "A String",
749 ],
750 "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (HCFS) URI of the jar file that contains the main class.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400751 "properties": { # Optional A mapping of property names to values, used to configure Spark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700752 "a_key": "A String",
753 },
754 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400755 "submittedBy": "A String", # Output-only The email address of the user submitting the job. For jobs submitted on the cluster, the address is <code>username@hostname</code>.
756 "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.
758 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400759 "statusHistory": [ # Output-only The previous job status.
760 { # Cloud Dataproc job status.
761 "stateStartTime": "A String", # Output-only The time when this state was entered.
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700762 "substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400763 "startTime": "A String", # The time when the server started the job.
764 "state": "A String", # Required A state message specifying the overall job state.
765 "details": "A String", # Optional Job state details, such as an error description if the state is <code>ERROR</code>.
766 "insertTime": "A String", # The time of the job request.
767 "endTime": "A String", # The time when the job completed.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700768 },
769 ],
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700770 "hiveJob": { # A Cloud Dataproc job for running Hive queries on YARN. # Job is a Hive job.
771 "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400772 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Hive command: 'SET name="value";').
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700773 "a_key": "A String",
774 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400775 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATH of the Hive server and Hadoop MapReduce (MR) tasks. Can contain Hive SerDes and UDFs.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700776 "A String",
777 ],
778 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400779 "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:
780 # "hiveJob": {
781 # "queryList": {
782 # "queries": [
783 # "query1",
784 # "query2",
785 # "query3;query4",
786 # ]
787 # }
788 # }
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700789 "A String",
790 ],
791 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400792 "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.
793 "properties": { # Optional A mapping of property names and values, used to configure Hive. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site.xml, /etc/hive/conf/hive-site.xml, and classes in user code.
Sai Cheemalapatidf613972016-10-21 13:59:49 -0700794 "a_key": "A String",
795 },
796 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400797 "interactive": True or False, # Optional If set to true, then the driver's stdin will be kept open and driver_input_uri will be set to provide a path at which additional input can be sent to the driver.
798 }</pre>
799</div>
800
801<div class="method">
802 <code class="details" id="list">list(projectId, region, body, x__xgafv=None)</code>
803 <pre>Lists regions/{region}/jobs in a project.
804
805Args:
806 projectId: string, Required The ID of the Google Cloud Platform project that the job belongs to. (required)
807 region: string, Required The Dataproc region in which to handle the request. (required)
808 body: object, The request body. (required)
809 The object takes the form of:
810
811{ # A request to list jobs in a project.
Thomas Coffee2f245372017-03-27 10:39:26 -0700812 "filter": "A String", # Optional A filter constraining which jobs to list. Valid filters contain job state and label terms such as: labels.key1 = val1 AND (labels.k2 = val2 OR labels.k3 = val3)
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400813 "pageToken": "A String", # Optional The page token, returned by a previous call, to request the next page of results.
814 "clusterName": "A String", # Optional If set, the returned jobs list includes only jobs that were submitted to the named cluster.
Thomas Coffee2f245372017-03-27 10:39:26 -0700815 "jobStateMatcher": "A String", # Optional Specifies enumerated categories of jobs to list.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400816 "pageSize": 42, # Optional The number of results to return in each response.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400817 }
818
819 x__xgafv: string, V1 error format.
820 Allowed values
821 1 - v1 error format
822 2 - v2 error format
823
824Returns:
825 An object of the form:
826
827 { # A response to a request to list jobs in a project.
828 "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>.
829 "jobs": [ # Output-only Jobs list.
830 { # A Cloud Dataproc job resource.
831 "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.
832 "stateStartTime": "A String", # Output-only The time when this state was entered.
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700833 "substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400834 "startTime": "A String", # The time when the server started the job.
835 "state": "A String", # Required A state message specifying the overall job state.
836 "details": "A String", # Optional Job state details, such as an error description if the state is <code>ERROR</code>.
837 "insertTime": "A String", # The time of the job request.
838 "endTime": "A String", # The time when the job completed.
839 },
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700840 "hadoopJob": { # A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN. # Job is a Hadoop job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400841 "jarFileUris": [ # Optional Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -0700842 "A String",
843 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700844 "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.
845 "A String",
846 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700847 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
848 "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
849 "a_key": "A String",
850 },
851 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400852 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.
853 "A String",
854 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700855 "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.
856 "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.
857 "A String",
858 ],
859 "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (HCFS) URI of the jar file containing the main class. Examples: gs://foo-bucket/analytics-binaries/extract-useful-metrics-mr.jar hdfs:/tmp/test-samples/custom-wordcount.jar file:///home/usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar
860 "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.
861 "a_key": "A String",
862 },
863 },
864 "labels": { # Optional The labels to associate with this job.Label keys must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}{0,62}Label values must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}\p{N}_-{0,63}No more than 64 labels can be associated with a given job.
865 "a_key": "A String",
866 },
867 "placement": { # Cloud Dataproc job configuration. # Required Job information, including how, when, and where to run the job.
868 "clusterName": "A String", # Required The name of the cluster where the job will be submitted.
869 "clusterUuid": "A String", # Output-only A cluster UUID generated by the Dataproc service when the job is submitted.
870 },
871 "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>.
872 "projectId": "A String", # Required The ID of the Google Cloud Platform project that the job belongs to.
873 "jobId": "A String", # Required The job ID, which must be unique within the project. The job ID is generated by the server upon job submission or provided by the user as a means to perform retries without creating duplicate jobs. The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), or dashes (-). The maximum length is 100 characters.
874 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400875 "sparkSqlJob": { # A Cloud Dataproc job for running Spark SQL queries. # Job is a SparkSql job.
876 "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
877 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Spark SQL command: SET name="value";).
878 "a_key": "A String",
879 },
880 "jarFileUris": [ # Optional HCFS URIs of jar files to be added to the Spark CLASSPATH.
881 "A String",
882 ],
883 "queryList": { # A list of queries to run on a cluster. # A list of queries.
884 "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:
885 # "hiveJob": {
886 # "queryList": {
887 # "queries": [
888 # "query1",
889 # "query2",
890 # "query3;query4",
891 # ]
892 # }
893 # }
894 "A String",
895 ],
896 },
897 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
898 "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
899 "a_key": "A String",
900 },
901 },
902 "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.
903 "a_key": "A String",
904 },
905 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400906 "yarnApplications": [ # Output-only The collection of Yarn applications spun up by this job.
907 { # A YARN application created by a job. Application information is a subset of <code>org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto</code>.
908 "progress": 3.14, # Required The numerical progress of the application, from 1 to 100.
909 "state": "A String", # Required The application state.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400910 "name": "A String", # Required The application name.
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700911 "trackingUrl": "A String", # Optional The HTTP URL of the ApplicationMaster, HistoryServer, or TimelineServer that provides application-specific information. The URL uses the internal hostname, and requires a proxy server for resolution and, possibly, access.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400912 },
913 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700914 "driverOutputUri": "A String", # Output-only A URI pointing to the location of the mixed stdout/stderr of the job's driver program&mdash;for example, <code>gs://sysbucket123/foo-cluster/jobid-123/driver/output</code>.
915 "pigJob": { # A Cloud Dataproc job for running Pig queries on YARN. # Job is a Pig job.
916 "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
917 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Pig command: "name=value").
918 "a_key": "A String",
919 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400920 "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.
Sai Cheemalapatie833b792017-03-24 15:06:46 -0700921 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATH of the Pig Client and Hadoop MapReduce (MR) tasks. Can contain Pig UDFs.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400922 "A String",
923 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400924 "queryList": { # A list of queries to run on a cluster. # A list of queries.
925 "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:
926 # "hiveJob": {
927 # "queryList": {
928 # "queries": [
929 # "query1",
930 # "query2",
931 # "query3;query4",
932 # ]
933 # }
934 # }
935 "A String",
936 ],
937 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400938 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
939 "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
940 "a_key": "A String",
941 },
942 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400943 "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.
944 "a_key": "A String",
945 },
946 },
947 "driverOutputResourceUri": "A String", # Output-only A URI pointing to the location of the stdout of the job's driver program.
948 "pysparkJob": { # A Cloud Dataproc job for running PySpark applications on YARN. # Job is a Pyspark job.
949 "mainPythonFileUri": "A String", # Required The Hadoop Compatible Filesystem (HCFS) URI of the main Python file to use as the driver. Must be a .py file.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400950 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400951 "A String",
952 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -0400953 "args": [ # Optional The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400954 "A String",
955 ],
956 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
957 "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
958 "a_key": "A String",
959 },
960 },
961 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.
962 "A String",
963 ],
964 "archiveUris": [ # Optional HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
965 "A String",
966 ],
967 "pythonFileUris": [ # Optional HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
968 "A String",
969 ],
970 "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.
971 "a_key": "A String",
972 },
973 },
974 "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.
975 "driverInputResourceUri": "A String", # Output-only A URI pointing to the location of the stdin of the job's driver program, only set if the job is interactive.
976 "sparkJob": { # A Cloud Dataproc job for running Spark applications on YARN. # Job is a Spark job.
Thomas Coffee2f245372017-03-27 10:39:26 -0700977 "args": [ # Optional The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400978 "A String",
979 ],
Thomas Coffee2f245372017-03-27 10:39:26 -0700980 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -0400981 "A String",
982 ],
983 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
984 "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
985 "a_key": "A String",
986 },
987 },
988 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
989 "A String",
990 ],
991 "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.
992 "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.
993 "A String",
994 ],
995 "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (HCFS) URI of the jar file that contains the main class.
996 "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.
997 "a_key": "A String",
998 },
999 },
1000 "submittedBy": "A String", # Output-only The email address of the user submitting the job. For jobs submitted on the cluster, the address is <code>username@hostname</code>.
1001 "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.
1002 "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.
1003 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001004 "statusHistory": [ # Output-only The previous job status.
1005 { # Cloud Dataproc job status.
1006 "stateStartTime": "A String", # Output-only The time when this state was entered.
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001007 "substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001008 "startTime": "A String", # The time when the server started the job.
1009 "state": "A String", # Required A state message specifying the overall job state.
1010 "details": "A String", # Optional Job state details, such as an error description if the state is <code>ERROR</code>.
1011 "insertTime": "A String", # The time of the job request.
1012 "endTime": "A String", # The time when the job completed.
1013 },
1014 ],
1015 "hiveJob": { # A Cloud Dataproc job for running Hive queries on YARN. # Job is a Hive job.
1016 "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
1017 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Hive command: 'SET name="value";').
1018 "a_key": "A String",
1019 },
1020 "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.
1021 "A String",
1022 ],
1023 "queryList": { # A list of queries to run on a cluster. # A list of queries.
1024 "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:
1025 # "hiveJob": {
1026 # "queryList": {
1027 # "queries": [
1028 # "query1",
1029 # "query2",
1030 # "query3;query4",
1031 # ]
1032 # }
1033 # }
1034 "A String",
1035 ],
1036 },
1037 "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.
1038 "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.
1039 "a_key": "A String",
1040 },
1041 },
1042 "interactive": True or False, # Optional If set to true, then the driver's stdin will be kept open and driver_input_uri will be set to provide a path at which additional input can be sent to the driver.
1043 },
1044 ],
1045 }</pre>
1046</div>
1047
1048<div class="method">
1049 <code class="details" id="list_next">list_next(previous_request, previous_response)</code>
1050 <pre>Retrieves the next page of results.
1051
1052Args:
1053 previous_request: The request for the previous page. (required)
1054 previous_response: The response from the request for the previous page. (required)
1055
1056Returns:
1057 A request object that you can call 'execute()' on to request the next
1058 page. Returns None if there are no more items in the collection.
1059 </pre>
1060</div>
1061
1062<div class="method">
1063 <code class="details" id="patch">patch(projectId, region, jobId, body, updateMask=None, x__xgafv=None)</code>
1064 <pre>Updates a job in a project.
1065
1066Args:
1067 projectId: string, Required The ID of the Google Cloud Platform project that the job belongs to. (required)
1068 region: string, Required The Dataproc region in which to handle the request. (required)
1069 jobId: string, Required The job ID. (required)
1070 body: object, The request body. (required)
1071 The object takes the form of:
1072
1073{ # A Cloud Dataproc job resource.
1074 "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.
1075 "stateStartTime": "A String", # Output-only The time when this state was entered.
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001076 "substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001077 "startTime": "A String", # The time when the server started the job.
1078 "state": "A String", # Required A state message specifying the overall job state.
1079 "details": "A String", # Optional Job state details, such as an error description if the state is <code>ERROR</code>.
1080 "insertTime": "A String", # The time of the job request.
1081 "endTime": "A String", # The time when the job completed.
1082 },
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001083 "hadoopJob": { # A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN. # Job is a Hadoop job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001084 "jarFileUris": [ # Optional Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -07001085 "A String",
1086 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001087 "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.
1088 "A String",
1089 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001090 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
1091 "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
1092 "a_key": "A String",
1093 },
1094 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001095 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.
1096 "A String",
1097 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001098 "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.
1099 "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.
1100 "A String",
1101 ],
1102 "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (HCFS) URI of the jar file containing the main class. Examples: gs://foo-bucket/analytics-binaries/extract-useful-metrics-mr.jar hdfs:/tmp/test-samples/custom-wordcount.jar file:///home/usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar
1103 "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.
1104 "a_key": "A String",
1105 },
1106 },
1107 "labels": { # Optional The labels to associate with this job.Label keys must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}{0,62}Label values must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}\p{N}_-{0,63}No more than 64 labels can be associated with a given job.
1108 "a_key": "A String",
1109 },
1110 "placement": { # Cloud Dataproc job configuration. # Required Job information, including how, when, and where to run the job.
1111 "clusterName": "A String", # Required The name of the cluster where the job will be submitted.
1112 "clusterUuid": "A String", # Output-only A cluster UUID generated by the Dataproc service when the job is submitted.
1113 },
1114 "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>.
1115 "projectId": "A String", # Required The ID of the Google Cloud Platform project that the job belongs to.
1116 "jobId": "A String", # Required The job ID, which must be unique within the project. The job ID is generated by the server upon job submission or provided by the user as a means to perform retries without creating duplicate jobs. The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), or dashes (-). The maximum length is 100 characters.
1117 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001118 "sparkSqlJob": { # A Cloud Dataproc job for running Spark SQL queries. # Job is a SparkSql job.
1119 "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
1120 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Spark SQL command: SET name="value";).
1121 "a_key": "A String",
1122 },
1123 "jarFileUris": [ # Optional HCFS URIs of jar files to be added to the Spark CLASSPATH.
1124 "A String",
1125 ],
1126 "queryList": { # A list of queries to run on a cluster. # A list of queries.
1127 "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:
1128 # "hiveJob": {
1129 # "queryList": {
1130 # "queries": [
1131 # "query1",
1132 # "query2",
1133 # "query3;query4",
1134 # ]
1135 # }
1136 # }
1137 "A String",
1138 ],
1139 },
1140 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
1141 "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
1142 "a_key": "A String",
1143 },
1144 },
1145 "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.
1146 "a_key": "A String",
1147 },
1148 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001149 "yarnApplications": [ # Output-only The collection of Yarn applications spun up by this job.
1150 { # A YARN application created by a job. Application information is a subset of <code>org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto</code>.
1151 "progress": 3.14, # Required The numerical progress of the application, from 1 to 100.
1152 "state": "A String", # Required The application state.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001153 "name": "A String", # Required The application name.
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001154 "trackingUrl": "A String", # Optional The HTTP URL of the ApplicationMaster, HistoryServer, or TimelineServer that provides application-specific information. The URL uses the internal hostname, and requires a proxy server for resolution and, possibly, access.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001155 },
1156 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001157 "driverOutputUri": "A String", # Output-only A URI pointing to the location of the mixed stdout/stderr of the job's driver program&mdash;for example, <code>gs://sysbucket123/foo-cluster/jobid-123/driver/output</code>.
1158 "pigJob": { # A Cloud Dataproc job for running Pig queries on YARN. # Job is a Pig job.
1159 "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
1160 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Pig command: "name=value").
1161 "a_key": "A String",
1162 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001163 "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.
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001164 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATH of the Pig Client and Hadoop MapReduce (MR) tasks. Can contain Pig UDFs.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001165 "A String",
1166 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001167 "queryList": { # A list of queries to run on a cluster. # A list of queries.
1168 "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:
1169 # "hiveJob": {
1170 # "queryList": {
1171 # "queries": [
1172 # "query1",
1173 # "query2",
1174 # "query3;query4",
1175 # ]
1176 # }
1177 # }
1178 "A String",
1179 ],
1180 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001181 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
1182 "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
1183 "a_key": "A String",
1184 },
1185 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001186 "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.
1187 "a_key": "A String",
1188 },
1189 },
1190 "driverOutputResourceUri": "A String", # Output-only A URI pointing to the location of the stdout of the job's driver program.
1191 "pysparkJob": { # A Cloud Dataproc job for running PySpark applications on YARN. # Job is a Pyspark job.
1192 "mainPythonFileUri": "A String", # Required The Hadoop Compatible Filesystem (HCFS) URI of the main Python file to use as the driver. Must be a .py file.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001193 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001194 "A String",
1195 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001196 "args": [ # Optional The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001197 "A String",
1198 ],
1199 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
1200 "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
1201 "a_key": "A String",
1202 },
1203 },
1204 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.
1205 "A String",
1206 ],
1207 "archiveUris": [ # Optional HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
1208 "A String",
1209 ],
1210 "pythonFileUris": [ # Optional HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
1211 "A String",
1212 ],
1213 "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.
1214 "a_key": "A String",
1215 },
1216 },
1217 "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.
1218 "driverInputResourceUri": "A String", # Output-only A URI pointing to the location of the stdin of the job's driver program, only set if the job is interactive.
1219 "sparkJob": { # A Cloud Dataproc job for running Spark applications on YARN. # Job is a Spark job.
Thomas Coffee2f245372017-03-27 10:39:26 -07001220 "args": [ # Optional The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001221 "A String",
1222 ],
Thomas Coffee2f245372017-03-27 10:39:26 -07001223 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001224 "A String",
1225 ],
1226 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
1227 "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
1228 "a_key": "A String",
1229 },
1230 },
1231 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
1232 "A String",
1233 ],
1234 "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.
1235 "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.
1236 "A String",
1237 ],
1238 "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (HCFS) URI of the jar file that contains the main class.
1239 "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.
1240 "a_key": "A String",
1241 },
1242 },
1243 "submittedBy": "A String", # Output-only The email address of the user submitting the job. For jobs submitted on the cluster, the address is <code>username@hostname</code>.
1244 "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.
1245 "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.
1246 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001247 "statusHistory": [ # Output-only The previous job status.
1248 { # Cloud Dataproc job status.
1249 "stateStartTime": "A String", # Output-only The time when this state was entered.
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001250 "substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001251 "startTime": "A String", # The time when the server started the job.
1252 "state": "A String", # Required A state message specifying the overall job state.
1253 "details": "A String", # Optional Job state details, such as an error description if the state is <code>ERROR</code>.
1254 "insertTime": "A String", # The time of the job request.
1255 "endTime": "A String", # The time when the job completed.
1256 },
1257 ],
1258 "hiveJob": { # A Cloud Dataproc job for running Hive queries on YARN. # Job is a Hive job.
1259 "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
1260 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Hive command: 'SET name="value";').
1261 "a_key": "A String",
1262 },
1263 "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.
1264 "A String",
1265 ],
1266 "queryList": { # A list of queries to run on a cluster. # A list of queries.
1267 "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:
1268 # "hiveJob": {
1269 # "queryList": {
1270 # "queries": [
1271 # "query1",
1272 # "query2",
1273 # "query3;query4",
1274 # ]
1275 # }
1276 # }
1277 "A String",
1278 ],
1279 },
1280 "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.
1281 "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.
1282 "a_key": "A String",
1283 },
1284 },
1285 "interactive": True or False, # Optional If set to true, then the driver's stdin will be kept open and driver_input_uri will be set to provide a path at which additional input can be sent to the driver.
1286}
1287
1288 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.
1289 x__xgafv: string, V1 error format.
1290 Allowed values
1291 1 - v1 error format
1292 2 - v2 error format
1293
1294Returns:
1295 An object of the form:
1296
1297 { # A Cloud Dataproc job resource.
1298 "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.
1299 "stateStartTime": "A String", # Output-only The time when this state was entered.
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001300 "substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001301 "startTime": "A String", # The time when the server started the job.
1302 "state": "A String", # Required A state message specifying the overall job state.
1303 "details": "A String", # Optional Job state details, such as an error description if the state is <code>ERROR</code>.
1304 "insertTime": "A String", # The time of the job request.
1305 "endTime": "A String", # The time when the job completed.
1306 },
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001307 "hadoopJob": { # A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN. # Job is a Hadoop job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001308 "jarFileUris": [ # Optional Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -07001309 "A String",
1310 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001311 "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.
1312 "A String",
1313 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001314 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
1315 "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
1316 "a_key": "A String",
1317 },
1318 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001319 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.
1320 "A String",
1321 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001322 "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.
1323 "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.
1324 "A String",
1325 ],
1326 "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (HCFS) URI of the jar file containing the main class. Examples: gs://foo-bucket/analytics-binaries/extract-useful-metrics-mr.jar hdfs:/tmp/test-samples/custom-wordcount.jar file:///home/usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar
1327 "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.
1328 "a_key": "A String",
1329 },
1330 },
1331 "labels": { # Optional The labels to associate with this job.Label keys must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}{0,62}Label values must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}\p{N}_-{0,63}No more than 64 labels can be associated with a given job.
1332 "a_key": "A String",
1333 },
1334 "placement": { # Cloud Dataproc job configuration. # Required Job information, including how, when, and where to run the job.
1335 "clusterName": "A String", # Required The name of the cluster where the job will be submitted.
1336 "clusterUuid": "A String", # Output-only A cluster UUID generated by the Dataproc service when the job is submitted.
1337 },
1338 "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>.
1339 "projectId": "A String", # Required The ID of the Google Cloud Platform project that the job belongs to.
1340 "jobId": "A String", # Required The job ID, which must be unique within the project. The job ID is generated by the server upon job submission or provided by the user as a means to perform retries without creating duplicate jobs. The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), or dashes (-). The maximum length is 100 characters.
1341 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001342 "sparkSqlJob": { # A Cloud Dataproc job for running Spark SQL queries. # Job is a SparkSql job.
1343 "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
1344 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Spark SQL command: SET name="value";).
1345 "a_key": "A String",
1346 },
1347 "jarFileUris": [ # Optional HCFS URIs of jar files to be added to the Spark CLASSPATH.
1348 "A String",
1349 ],
1350 "queryList": { # A list of queries to run on a cluster. # A list of queries.
1351 "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:
1352 # "hiveJob": {
1353 # "queryList": {
1354 # "queries": [
1355 # "query1",
1356 # "query2",
1357 # "query3;query4",
1358 # ]
1359 # }
1360 # }
1361 "A String",
1362 ],
1363 },
1364 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
1365 "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
1366 "a_key": "A String",
1367 },
1368 },
1369 "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.
1370 "a_key": "A String",
1371 },
1372 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001373 "yarnApplications": [ # Output-only The collection of Yarn applications spun up by this job.
1374 { # A YARN application created by a job. Application information is a subset of <code>org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto</code>.
1375 "progress": 3.14, # Required The numerical progress of the application, from 1 to 100.
1376 "state": "A String", # Required The application state.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001377 "name": "A String", # Required The application name.
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001378 "trackingUrl": "A String", # Optional The HTTP URL of the ApplicationMaster, HistoryServer, or TimelineServer that provides application-specific information. The URL uses the internal hostname, and requires a proxy server for resolution and, possibly, access.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001379 },
1380 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001381 "driverOutputUri": "A String", # Output-only A URI pointing to the location of the mixed stdout/stderr of the job's driver program&mdash;for example, <code>gs://sysbucket123/foo-cluster/jobid-123/driver/output</code>.
1382 "pigJob": { # A Cloud Dataproc job for running Pig queries on YARN. # Job is a Pig job.
1383 "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
1384 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Pig command: "name=value").
1385 "a_key": "A String",
1386 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001387 "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.
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001388 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATH of the Pig Client and Hadoop MapReduce (MR) tasks. Can contain Pig UDFs.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001389 "A String",
1390 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001391 "queryList": { # A list of queries to run on a cluster. # A list of queries.
1392 "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:
1393 # "hiveJob": {
1394 # "queryList": {
1395 # "queries": [
1396 # "query1",
1397 # "query2",
1398 # "query3;query4",
1399 # ]
1400 # }
1401 # }
1402 "A String",
1403 ],
1404 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001405 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
1406 "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
1407 "a_key": "A String",
1408 },
1409 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001410 "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.
1411 "a_key": "A String",
1412 },
1413 },
1414 "driverOutputResourceUri": "A String", # Output-only A URI pointing to the location of the stdout of the job's driver program.
1415 "pysparkJob": { # A Cloud Dataproc job for running PySpark applications on YARN. # Job is a Pyspark job.
1416 "mainPythonFileUri": "A String", # Required The Hadoop Compatible Filesystem (HCFS) URI of the main Python file to use as the driver. Must be a .py file.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001417 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001418 "A String",
1419 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001420 "args": [ # Optional The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001421 "A String",
1422 ],
1423 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
1424 "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
1425 "a_key": "A String",
1426 },
1427 },
1428 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.
1429 "A String",
1430 ],
1431 "archiveUris": [ # Optional HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
1432 "A String",
1433 ],
1434 "pythonFileUris": [ # Optional HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
1435 "A String",
1436 ],
1437 "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.
1438 "a_key": "A String",
1439 },
1440 },
1441 "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.
1442 "driverInputResourceUri": "A String", # Output-only A URI pointing to the location of the stdin of the job's driver program, only set if the job is interactive.
1443 "sparkJob": { # A Cloud Dataproc job for running Spark applications on YARN. # Job is a Spark job.
Thomas Coffee2f245372017-03-27 10:39:26 -07001444 "args": [ # Optional The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001445 "A String",
1446 ],
Thomas Coffee2f245372017-03-27 10:39:26 -07001447 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001448 "A String",
1449 ],
1450 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
1451 "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
1452 "a_key": "A String",
1453 },
1454 },
1455 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
1456 "A String",
1457 ],
1458 "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.
1459 "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.
1460 "A String",
1461 ],
1462 "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (HCFS) URI of the jar file that contains the main class.
1463 "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.
1464 "a_key": "A String",
1465 },
1466 },
1467 "submittedBy": "A String", # Output-only The email address of the user submitting the job. For jobs submitted on the cluster, the address is <code>username@hostname</code>.
1468 "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.
1469 "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.
1470 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001471 "statusHistory": [ # Output-only The previous job status.
1472 { # Cloud Dataproc job status.
1473 "stateStartTime": "A String", # Output-only The time when this state was entered.
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001474 "substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001475 "startTime": "A String", # The time when the server started the job.
1476 "state": "A String", # Required A state message specifying the overall job state.
1477 "details": "A String", # Optional Job state details, such as an error description if the state is <code>ERROR</code>.
1478 "insertTime": "A String", # The time of the job request.
1479 "endTime": "A String", # The time when the job completed.
1480 },
1481 ],
1482 "hiveJob": { # A Cloud Dataproc job for running Hive queries on YARN. # Job is a Hive job.
1483 "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
1484 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Hive command: 'SET name="value";').
1485 "a_key": "A String",
1486 },
1487 "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.
1488 "A String",
1489 ],
1490 "queryList": { # A list of queries to run on a cluster. # A list of queries.
1491 "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:
1492 # "hiveJob": {
1493 # "queryList": {
1494 # "queries": [
1495 # "query1",
1496 # "query2",
1497 # "query3;query4",
1498 # ]
1499 # }
1500 # }
1501 "A String",
1502 ],
1503 },
1504 "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.
1505 "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.
1506 "a_key": "A String",
1507 },
1508 },
1509 "interactive": True or False, # Optional If set to true, then the driver's stdin will be kept open and driver_input_uri will be set to provide a path at which additional input can be sent to the driver.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001510 }</pre>
1511</div>
1512
1513<div class="method">
1514 <code class="details" id="submit">submit(projectId, region, body, x__xgafv=None)</code>
1515 <pre>Submits a job to a cluster.
1516
1517Args:
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001518 projectId: string, Required The ID of the Google Cloud Platform project that the job belongs to. (required)
1519 region: string, Required The Dataproc region in which to handle the request. (required)
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001520 body: object, The request body. (required)
1521 The object takes the form of:
1522
1523{ # A job submission request.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001524 "job": { # A Cloud Dataproc job resource. # Required The job resource.
1525 "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.
1526 "stateStartTime": "A String", # Output-only The time when this state was entered.
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001527 "substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001528 "startTime": "A String", # The time when the server started the job.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001529 "state": "A String", # Required A state message specifying the overall job state.
1530 "details": "A String", # Optional Job state details, such as an error description if the state is <code>ERROR</code>.
1531 "insertTime": "A String", # The time of the job request.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001532 "endTime": "A String", # The time when the job completed.
1533 },
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001534 "hadoopJob": { # A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN. # Job is a Hadoop job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001535 "jarFileUris": [ # Optional Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -07001536 "A String",
1537 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001538 "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.
1539 "A String",
1540 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001541 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
1542 "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
1543 "a_key": "A String",
1544 },
1545 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001546 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.
1547 "A String",
1548 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001549 "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.
1550 "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.
1551 "A String",
1552 ],
1553 "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (HCFS) URI of the jar file containing the main class. Examples: gs://foo-bucket/analytics-binaries/extract-useful-metrics-mr.jar hdfs:/tmp/test-samples/custom-wordcount.jar file:///home/usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar
1554 "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.
1555 "a_key": "A String",
1556 },
1557 },
1558 "labels": { # Optional The labels to associate with this job.Label keys must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}{0,62}Label values must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}\p{N}_-{0,63}No more than 64 labels can be associated with a given job.
1559 "a_key": "A String",
1560 },
1561 "placement": { # Cloud Dataproc job configuration. # Required Job information, including how, when, and where to run the job.
1562 "clusterName": "A String", # Required The name of the cluster where the job will be submitted.
1563 "clusterUuid": "A String", # Output-only A cluster UUID generated by the Dataproc service when the job is submitted.
1564 },
1565 "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>.
1566 "projectId": "A String", # Required The ID of the Google Cloud Platform project that the job belongs to.
1567 "jobId": "A String", # Required The job ID, which must be unique within the project. The job ID is generated by the server upon job submission or provided by the user as a means to perform retries without creating duplicate jobs. The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), or dashes (-). The maximum length is 100 characters.
1568 },
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001569 "sparkSqlJob": { # A Cloud Dataproc job for running Spark SQL queries. # Job is a SparkSql job.
1570 "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001571 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Spark SQL command: SET name="value";).
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001572 "a_key": "A String",
1573 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001574 "jarFileUris": [ # Optional HCFS URIs of jar files to be added to the Spark CLASSPATH.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001575 "A String",
1576 ],
1577 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001578 "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:
1579 # "hiveJob": {
1580 # "queryList": {
1581 # "queries": [
1582 # "query1",
1583 # "query2",
1584 # "query3;query4",
1585 # ]
1586 # }
1587 # }
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001588 "A String",
1589 ],
1590 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001591 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
1592 "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
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001593 "a_key": "A String",
1594 },
1595 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001596 "properties": { # Optional A mapping of property names to values, used to configure Spark SQL's SparkConf. Properties that conflict with values set by the Cloud Dataproc API may be overwritten.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001597 "a_key": "A String",
1598 },
1599 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001600 "yarnApplications": [ # Output-only The collection of Yarn applications spun up by this job.
1601 { # A YARN application created by a job. Application information is a subset of <code>org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto</code>.
1602 "progress": 3.14, # Required The numerical progress of the application, from 1 to 100.
1603 "state": "A String", # Required The application state.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001604 "name": "A String", # Required The application name.
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001605 "trackingUrl": "A String", # Optional The HTTP URL of the ApplicationMaster, HistoryServer, or TimelineServer that provides application-specific information. The URL uses the internal hostname, and requires a proxy server for resolution and, possibly, access.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001606 },
1607 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001608 "driverOutputUri": "A String", # Output-only A URI pointing to the location of the mixed stdout/stderr of the job's driver program&mdash;for example, <code>gs://sysbucket123/foo-cluster/jobid-123/driver/output</code>.
1609 "pigJob": { # A Cloud Dataproc job for running Pig queries on YARN. # Job is a Pig job.
1610 "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
1611 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Pig command: "name=value").
1612 "a_key": "A String",
1613 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001614 "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.
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001615 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATH of the Pig Client and Hadoop MapReduce (MR) tasks. Can contain Pig UDFs.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001616 "A String",
1617 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001618 "queryList": { # A list of queries to run on a cluster. # A list of queries.
1619 "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:
1620 # "hiveJob": {
1621 # "queryList": {
1622 # "queries": [
1623 # "query1",
1624 # "query2",
1625 # "query3;query4",
1626 # ]
1627 # }
1628 # }
1629 "A String",
1630 ],
1631 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001632 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
1633 "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
1634 "a_key": "A String",
1635 },
1636 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001637 "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.
1638 "a_key": "A String",
1639 },
1640 },
1641 "driverOutputResourceUri": "A String", # Output-only A URI pointing to the location of the stdout of the job's driver program.
1642 "pysparkJob": { # A Cloud Dataproc job for running PySpark applications on YARN. # Job is a Pyspark job.
1643 "mainPythonFileUri": "A String", # Required The Hadoop Compatible Filesystem (HCFS) URI of the main Python file to use as the driver. Must be a .py file.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001644 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001645 "A String",
1646 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001647 "args": [ # Optional The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001648 "A String",
1649 ],
1650 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
1651 "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
1652 "a_key": "A String",
1653 },
1654 },
1655 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.
1656 "A String",
1657 ],
1658 "archiveUris": [ # Optional HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
1659 "A String",
1660 ],
1661 "pythonFileUris": [ # Optional HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
1662 "A String",
1663 ],
1664 "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.
1665 "a_key": "A String",
1666 },
1667 },
1668 "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.
1669 "driverInputResourceUri": "A String", # Output-only A URI pointing to the location of the stdin of the job's driver program, only set if the job is interactive.
1670 "sparkJob": { # A Cloud Dataproc job for running Spark applications on YARN. # Job is a Spark job.
Thomas Coffee2f245372017-03-27 10:39:26 -07001671 "args": [ # Optional The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001672 "A String",
1673 ],
Thomas Coffee2f245372017-03-27 10:39:26 -07001674 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001675 "A String",
1676 ],
1677 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
1678 "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
1679 "a_key": "A String",
1680 },
1681 },
1682 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001683 "A String",
1684 ],
1685 "mainClass": "A String", # The name of the driver's main class. The jar file that contains the class must be in the default CLASSPATH or specified in jar_file_uris.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001686 "archiveUris": [ # Optional HCFS URIs of archives to be extracted in the working directory of Spark drivers and tasks. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001687 "A String",
1688 ],
1689 "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (HCFS) URI of the jar file that contains the main class.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001690 "properties": { # Optional A mapping of property names to values, used to configure Spark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001691 "a_key": "A String",
1692 },
1693 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001694 "submittedBy": "A String", # Output-only The email address of the user submitting the job. For jobs submitted on the cluster, the address is <code>username@hostname</code>.
1695 "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.
1696 "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.
1697 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001698 "statusHistory": [ # Output-only The previous job status.
1699 { # Cloud Dataproc job status.
1700 "stateStartTime": "A String", # Output-only The time when this state was entered.
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001701 "substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001702 "startTime": "A String", # The time when the server started the job.
1703 "state": "A String", # Required A state message specifying the overall job state.
1704 "details": "A String", # Optional Job state details, such as an error description if the state is <code>ERROR</code>.
1705 "insertTime": "A String", # The time of the job request.
1706 "endTime": "A String", # The time when the job completed.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001707 },
1708 ],
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001709 "hiveJob": { # A Cloud Dataproc job for running Hive queries on YARN. # Job is a Hive job.
1710 "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001711 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Hive command: 'SET name="value";').
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001712 "a_key": "A String",
1713 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001714 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATH of the Hive server and Hadoop MapReduce (MR) tasks. Can contain Hive SerDes and UDFs.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001715 "A String",
1716 ],
1717 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001718 "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:
1719 # "hiveJob": {
1720 # "queryList": {
1721 # "queries": [
1722 # "query1",
1723 # "query2",
1724 # "query3;query4",
1725 # ]
1726 # }
1727 # }
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001728 "A String",
1729 ],
1730 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001731 "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.
1732 "properties": { # Optional A mapping of property names and values, used to configure Hive. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site.xml, /etc/hive/conf/hive-site.xml, and classes in user code.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001733 "a_key": "A String",
1734 },
1735 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001736 "interactive": True or False, # Optional If set to true, then the driver's stdin will be kept open and driver_input_uri will be set to provide a path at which additional input can be sent to the driver.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001737 },
1738 }
1739
1740 x__xgafv: string, V1 error format.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001741 Allowed values
1742 1 - v1 error format
1743 2 - v2 error format
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001744
1745Returns:
1746 An object of the form:
1747
1748 { # A Cloud Dataproc job resource.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001749 "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.
1750 "stateStartTime": "A String", # Output-only The time when this state was entered.
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001751 "substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001752 "startTime": "A String", # The time when the server started the job.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001753 "state": "A String", # Required A state message specifying the overall job state.
1754 "details": "A String", # Optional Job state details, such as an error description if the state is <code>ERROR</code>.
1755 "insertTime": "A String", # The time of the job request.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001756 "endTime": "A String", # The time when the job completed.
1757 },
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001758 "hadoopJob": { # A Cloud Dataproc job for running Hadoop MapReduce jobs on YARN. # Job is a Hadoop job.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001759 "jarFileUris": [ # Optional Jar file URIs to add to the CLASSPATHs of the Hadoop driver and tasks.
Thomas Coffee2f245372017-03-27 10:39:26 -07001760 "A String",
1761 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001762 "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.
1763 "A String",
1764 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001765 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
1766 "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
1767 "a_key": "A String",
1768 },
1769 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001770 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Hadoop drivers and distributed tasks. Useful for naively parallel tasks.
1771 "A String",
1772 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001773 "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.
1774 "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.
1775 "A String",
1776 ],
1777 "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (HCFS) URI of the jar file containing the main class. Examples: gs://foo-bucket/analytics-binaries/extract-useful-metrics-mr.jar hdfs:/tmp/test-samples/custom-wordcount.jar file:///home/usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar
1778 "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.
1779 "a_key": "A String",
1780 },
1781 },
1782 "labels": { # Optional The labels to associate with this job.Label keys must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}{0,62}Label values must be between 1 and 63 characters long, and must conform to the following regular expression: \p{Ll}\p{Lo}\p{N}_-{0,63}No more than 64 labels can be associated with a given job.
1783 "a_key": "A String",
1784 },
1785 "placement": { # Cloud Dataproc job configuration. # Required Job information, including how, when, and where to run the job.
1786 "clusterName": "A String", # Required The name of the cluster where the job will be submitted.
1787 "clusterUuid": "A String", # Output-only A cluster UUID generated by the Dataproc service when the job is submitted.
1788 },
1789 "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>.
1790 "projectId": "A String", # Required The ID of the Google Cloud Platform project that the job belongs to.
1791 "jobId": "A String", # Required The job ID, which must be unique within the project. The job ID is generated by the server upon job submission or provided by the user as a means to perform retries without creating duplicate jobs. The ID must contain only letters (a-z, A-Z), numbers (0-9), underscores (_), or dashes (-). The maximum length is 100 characters.
1792 },
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001793 "sparkSqlJob": { # A Cloud Dataproc job for running Spark SQL queries. # Job is a SparkSql job.
1794 "queryFileUri": "A String", # The HCFS URI of the script that contains SQL queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001795 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Spark SQL command: SET name="value";).
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001796 "a_key": "A String",
1797 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001798 "jarFileUris": [ # Optional HCFS URIs of jar files to be added to the Spark CLASSPATH.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001799 "A String",
1800 ],
1801 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001802 "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:
1803 # "hiveJob": {
1804 # "queryList": {
1805 # "queries": [
1806 # "query1",
1807 # "query2",
1808 # "query3;query4",
1809 # ]
1810 # }
1811 # }
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001812 "A String",
1813 ],
1814 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001815 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
1816 "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
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001817 "a_key": "A String",
1818 },
1819 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001820 "properties": { # Optional A mapping of property names to values, used to configure Spark SQL's SparkConf. Properties that conflict with values set by the Cloud Dataproc API may be overwritten.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001821 "a_key": "A String",
1822 },
1823 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001824 "yarnApplications": [ # Output-only The collection of Yarn applications spun up by this job.
1825 { # A YARN application created by a job. Application information is a subset of <code>org.apache.hadoop.yarn.proto.YarnProtos.ApplicationReportProto</code>.
1826 "progress": 3.14, # Required The numerical progress of the application, from 1 to 100.
1827 "state": "A String", # Required The application state.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001828 "name": "A String", # Required The application name.
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001829 "trackingUrl": "A String", # Optional The HTTP URL of the ApplicationMaster, HistoryServer, or TimelineServer that provides application-specific information. The URL uses the internal hostname, and requires a proxy server for resolution and, possibly, access.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001830 },
1831 ],
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001832 "driverOutputUri": "A String", # Output-only A URI pointing to the location of the mixed stdout/stderr of the job's driver program&mdash;for example, <code>gs://sysbucket123/foo-cluster/jobid-123/driver/output</code>.
1833 "pigJob": { # A Cloud Dataproc job for running Pig queries on YARN. # Job is a Pig job.
1834 "queryFileUri": "A String", # The HCFS URI of the script that contains the Pig queries.
1835 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Pig command: "name=value").
1836 "a_key": "A String",
1837 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001838 "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.
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001839 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATH of the Pig Client and Hadoop MapReduce (MR) tasks. Can contain Pig UDFs.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001840 "A String",
1841 ],
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001842 "queryList": { # A list of queries to run on a cluster. # A list of queries.
1843 "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:
1844 # "hiveJob": {
1845 # "queryList": {
1846 # "queries": [
1847 # "query1",
1848 # "query2",
1849 # "query3;query4",
1850 # ]
1851 # }
1852 # }
1853 "A String",
1854 ],
1855 },
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001856 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
1857 "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
1858 "a_key": "A String",
1859 },
1860 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001861 "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.
1862 "a_key": "A String",
1863 },
1864 },
1865 "driverOutputResourceUri": "A String", # Output-only A URI pointing to the location of the stdout of the job's driver program.
1866 "pysparkJob": { # A Cloud Dataproc job for running PySpark applications on YARN. # Job is a Pyspark job.
1867 "mainPythonFileUri": "A String", # Required The Hadoop Compatible Filesystem (HCFS) URI of the main Python file to use as the driver. Must be a .py file.
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001868 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Python driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001869 "A String",
1870 ],
Sai Cheemalapati4ba8c232017-06-06 18:46:08 -04001871 "args": [ # Optional The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001872 "A String",
1873 ],
1874 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
1875 "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
1876 "a_key": "A String",
1877 },
1878 },
1879 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Python drivers and distributed tasks. Useful for naively parallel tasks.
1880 "A String",
1881 ],
1882 "archiveUris": [ # Optional HCFS URIs of archives to be extracted in the working directory of .jar, .tar, .tar.gz, .tgz, and .zip.
1883 "A String",
1884 ],
1885 "pythonFileUris": [ # Optional HCFS file URIs of Python files to pass to the PySpark framework. Supported file types: .py, .egg, and .zip.
1886 "A String",
1887 ],
1888 "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.
1889 "a_key": "A String",
1890 },
1891 },
1892 "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.
1893 "driverInputResourceUri": "A String", # Output-only A URI pointing to the location of the stdin of the job's driver program, only set if the job is interactive.
1894 "sparkJob": { # A Cloud Dataproc job for running Spark applications on YARN. # Job is a Spark job.
Thomas Coffee2f245372017-03-27 10:39:26 -07001895 "args": [ # Optional The arguments to pass to the driver. Do not include arguments, such as --conf, that can be set as job properties, since a collision may occur that causes an incorrect job submission.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001896 "A String",
1897 ],
Thomas Coffee2f245372017-03-27 10:39:26 -07001898 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATHs of the Spark driver and tasks.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001899 "A String",
1900 ],
1901 "loggingConfiguration": { # The runtime logging configuration of the job. # Optional The runtime log configuration for job execution.
1902 "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
1903 "a_key": "A String",
1904 },
1905 },
1906 "fileUris": [ # Optional HCFS URIs of files to be copied to the working directory of Spark drivers and distributed tasks. Useful for naively parallel tasks.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001907 "A String",
1908 ],
1909 "mainClass": "A String", # The name of the driver's main class. The jar file that contains the class must be in the default CLASSPATH or specified in jar_file_uris.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001910 "archiveUris": [ # Optional HCFS URIs of archives to be extracted in the working directory of Spark drivers and tasks. Supported file types: .jar, .tar, .tar.gz, .tgz, and .zip.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001911 "A String",
1912 ],
1913 "mainJarFileUri": "A String", # The Hadoop Compatible Filesystem (HCFS) URI of the jar file that contains the main class.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001914 "properties": { # Optional A mapping of property names to values, used to configure Spark. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/spark/conf/spark-defaults.conf and classes in user code.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001915 "a_key": "A String",
1916 },
1917 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001918 "submittedBy": "A String", # Output-only The email address of the user submitting the job. For jobs submitted on the cluster, the address is <code>username@hostname</code>.
1919 "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.
1920 "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.
1921 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001922 "statusHistory": [ # Output-only The previous job status.
1923 { # Cloud Dataproc job status.
1924 "stateStartTime": "A String", # Output-only The time when this state was entered.
Sai Cheemalapatie833b792017-03-24 15:06:46 -07001925 "substate": "A String", # Output-only Additional state information, which includes status reported by the agent.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001926 "startTime": "A String", # The time when the server started the job.
1927 "state": "A String", # Required A state message specifying the overall job state.
1928 "details": "A String", # Optional Job state details, such as an error description if the state is <code>ERROR</code>.
1929 "insertTime": "A String", # The time of the job request.
1930 "endTime": "A String", # The time when the job completed.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001931 },
1932 ],
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001933 "hiveJob": { # A Cloud Dataproc job for running Hive queries on YARN. # Job is a Hive job.
1934 "queryFileUri": "A String", # The HCFS URI of the script that contains Hive queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001935 "scriptVariables": { # Optional Mapping of query variable names to values (equivalent to the Hive command: 'SET name="value";').
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001936 "a_key": "A String",
1937 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001938 "jarFileUris": [ # Optional HCFS URIs of jar files to add to the CLASSPATH of the Hive server and Hadoop MapReduce (MR) tasks. Can contain Hive SerDes and UDFs.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001939 "A String",
1940 ],
1941 "queryList": { # A list of queries to run on a cluster. # A list of queries.
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001942 "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:
1943 # "hiveJob": {
1944 # "queryList": {
1945 # "queries": [
1946 # "query1",
1947 # "query2",
1948 # "query3;query4",
1949 # ]
1950 # }
1951 # }
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001952 "A String",
1953 ],
1954 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001955 "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.
1956 "properties": { # Optional A mapping of property names and values, used to configure Hive. Properties that conflict with values set by the Cloud Dataproc API may be overwritten. Can include properties set in /etc/hadoop/conf/*-site.xml, /etc/hive/conf/hive-site.xml, and classes in user code.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001957 "a_key": "A String",
1958 },
1959 },
Sai Cheemalapatic30d2b52017-03-13 12:12:03 -04001960 "interactive": True or False, # Optional If set to true, then the driver's stdin will be kept open and driver_input_uri will be set to provide a path at which additional input can be sent to the driver.
Sai Cheemalapatidf613972016-10-21 13:59:49 -07001961 }</pre>
1962</div>
1963
1964</body></html>