def check_job_executor(data, job_id):
job = api.get_job(job_id)
# Make sure we have the right schema for the job type
# We can identify the Java action schema by looking for 'main_class'
if ('main_class' in data) ^ (job.type == 'Java'):
raise ex.InvalidException("Schema is not valid for job type %s"
% job.type)
if 'input_id' in data:
b.check_data_source_exists(data['input_id'])
b.check_data_source_exists(data['output_id'])
main_base.check_cluster_exists(data['cluster_id'])
def check_job_executor(data, job_id):
job = api.get_job(job_id)
job_type, subtype = edp.split_job_type(job.type)
# All types except Java require input and output objects
if job_type == 'Java':
if not _is_main_class_present(data):
raise ex.InvalidDataException('Java job must '
'specify edp.java.main_class')
else:
if not ('input_id' in data and 'output_id' in data):
raise ex.InvalidDataException("%s job requires 'input_id' "
"and 'output_id'" % job.type)
b.check_data_source_exists(data['input_id'])
b.check_data_source_exists(data['output_id'])
if job_type == 'MapReduce' and (subtype == 'Streaming'
and not _streaming_present(data)):
raise ex.InvalidDataException("%s job "
"must specify streaming mapper "
"and reducer" % job.type)
main_base.check_cluster_exists(data['cluster_id'])
def check_job_executor(data, **kwargs):
b.check_data_source_exists(data['input_id'])
b.check_data_source_exists(data['output_id'])
main_base.check_cluster_exists(data['cluster_id'])
def check_job_executor(data, **kwargs):
b.check_data_source_exists(data['input_id'])
b.check_data_source_exists(data['output_id'])
main_base.check_cluster_exists(data['cluster_id'])