def execute(self, notebook, snippet):
# Get document from notebook
if not notebook.get('uuid', ''):
raise PopupException(
_('Notebook is missing a uuid, please save the notebook before executing as a batch job.'
))
notebook_doc = Document2.objects.get_by_uuid(user=self.user,
uuid=notebook['uuid'],
perm_type='read')
# Create a managed workflow from the notebook doc
workflow_doc = WorkflowBuilder().create_workflow(
document=notebook_doc,
user=self.user,
managed=True,
name=_("Batch job for %s") % notebook_doc.name
or notebook_doc.type)
workflow = Workflow(document=workflow_doc, user=self.user)
# Submit workflow
job_id = _submit_workflow(user=self.user,
fs=self.fs,
jt=self.jt,
workflow=workflow,
mapping=None)
return {
'id': job_id,
'has_result_set': True,
}
def run_morphline(self, collection_name, morphline, input_path):
workspace_path = self._upload_workspace(morphline)
snippet_properties = {
u'files': [{
u'path': u'%s/log4j.properties' % workspace_path,
u'type': u'file'
}, {
u'path': u'%s/morphline.conf' % workspace_path,
u'type': u'file'
}],
u'class':
u'org.apache.solr.hadoop.MapReduceIndexerTool',
u'app_jar':
CONFIG_INDEXER_LIBS_PATH.get(),
u'arguments': [
u'--morphline-file',
u'morphline.conf',
u'--output-dir',
u'${nameNode}/user/%s/indexer' % self.username,
u'--log4j',
u'log4j.properties',
u'--go-live',
u'--zk-host',
zkensemble(),
u'--collection',
collection_name,
u'${nameNode}%s' % input_path,
],
u'archives': [],
}
notebook = make_notebook(
name='Indexer',
editor_type='java',
snippet_properties=snippet_properties).get_data()
notebook_doc, created = _save_notebook(notebook, self.user)
workflow_doc = WorkflowBuilder().create_workflow(
document=notebook_doc,
user=self.user,
managed=True,
name=_("Batch job for %s") % notebook_doc.name)
workflow = Workflow(document=workflow_doc, user=self.user)
job_id = _submit_workflow(user=self.user,
fs=self.fs,
jt=self.jt,
workflow=workflow,
mapping=None)
return job_id
def execute(self, notebook, snippet):
# Get document from notebook
if not notebook.get('uuid', ''):
raise PopupException(_('Notebook is missing a uuid, please save the notebook before executing as a batch job.'))
notebook_doc = Document2.objects.get_by_uuid(user=self.user, uuid=notebook['uuid'], perm_type='read')
# Create a managed workflow from the notebook doc
workflow_doc = WorkflowBuilder().create_workflow(document=notebook_doc, user=self.user, managed=True, name=_("Batch job for %s") % notebook_doc.name or notebook_doc.type)
workflow = Workflow(document=workflow_doc, user=self.user)
# Submit workflow
job_id = _submit_workflow(user=self.user, fs=self.fs, jt=self.jt, workflow=workflow, mapping=None)
return {
'id': job_id,
'has_result_set': True,
}
def execute(self, notebook, snippet):
# Get document from notebook
if not notebook.get('uuid', ''):
raise PopupException(
_('Notebook is missing a uuid, please save the notebook before executing as a batch job.'
))
if notebook['type'] == 'notebook' or notebook['type'] == 'query-java':
# Convert notebook to workflow
workflow_doc = WorkflowBuilder().create_notebook_workflow(
notebook=notebook,
user=self.user,
managed=True,
name=_("%s for %s") % (OozieApi.BATCH_JOB_PREFIX,
notebook['name'] or notebook['type']))
workflow = Workflow(document=workflow_doc, user=self.user)
else:
notebook_doc = Document2.objects.get_by_uuid(user=self.user,
uuid=notebook['uuid'],
perm_type='read')
# Create a managed workflow from the notebook doc
workflow_doc = WorkflowBuilder().create_workflow(
document=notebook_doc,
user=self.user,
managed=True,
name=_("Batch job for %s") %
(notebook_doc.name or notebook_doc.type))
workflow = Workflow(document=workflow_doc, user=self.user)
# Submit workflow
job_id = _submit_workflow(user=self.user,
fs=self.fs,
jt=self.jt,
workflow=workflow,
mapping=None)
return {
'id': job_id,
'has_result_set': True,
}
def run_morphline(self, collection_name, morphline, input_path):
workspace_path = self._upload_workspace(morphline)
snippet_properties = {
u'files': [
{u'path': u'%s/log4j.properties' % workspace_path, u'type': u'file'},
{u'path': u'%s/morphline.conf' % workspace_path, u'type': u'file'}
],
u'class': u'org.apache.solr.hadoop.MapReduceIndexerTool',
u'app_jar': CONFIG_INDEXER_LIBS_PATH.get(),
u'arguments': [
u'--morphline-file',
u'morphline.conf',
u'--output-dir',
u'${nameNode}/user/%s/indexer' % self.username,
u'--log4j',
u'log4j.properties',
u'--go-live',
u'--zk-host',
zkensemble(),
u'--collection',
collection_name,
u'${nameNode}%s' % input_path,
],
u'archives': [],
}
notebook = make_notebook(name='Indexer', editor_type='java', snippet_properties=snippet_properties).get_data()
notebook_doc, created = _save_notebook(notebook, self.user)
workflow_doc = WorkflowBuilder().create_workflow(document=notebook_doc, user=self.user, managed=True, name=_("Batch job for %s") % notebook_doc.name)
workflow = Workflow(document=workflow_doc, user=self.user)
job_id = _submit_workflow(user=self.user, fs=self.fs, jt=self.jt, workflow=workflow, mapping=None)
return job_id
