Tukukkk

Here i am writing queries in queryList which is under hiveJob.

To submit Hive job to dataproc cluster

def submit_hive_job(dataproc, project, region,

                       cluster_name):

    job_details = {

        'projectId': project,

        'job': {

            'placement': {

                'clusterName': cluster_name

            },

            "hiveJob": {

                "queryList": {

                    ###

                    how can i execute .sql file here which is in bucket

                    ####

                    "queries": [

                        "CREATE TABLE IF NOT EXISTS sai ( eid int, name String, salary String, destination String)",

                        "Insert into table sai values (26,'Shiv','1500','ac')"

                    ]

                }

            }

        }

    }

    result = dataproc.projects().regions().jobs().submit(

        projectId=project,

        region=region,

        body=job_details).execute()

    job_id = result['reference']['jobId']

    print('Submitted job Id {}'.format(job_id))

    return job_id

hive.sql file which is in bucket

create table employee ( employeeid: int, employeename: string, salary: float) rows format delimited fields terminated by ‘,’ ;

describe employee;

select * from employee;

I found that we can keep .sql file in bucket and then specify queryFileUri like below

"hiveJob": {

 "queryFileUri":"gs://queryfile-pandora/test.sql"             

}