def execute(self, request, batch=False):
from notebook.api import _execute_notebook # Cyclic dependency
notebook_data = self.get_data()
snippet = notebook_data['snippets'][0]
snippet['wasBatchExecuted'] = batch
return _execute_notebook(request, notebook_data, snippet)
def execute(self, request, batch=False):
from notebook.api import _execute_notebook # Cyclic dependency
notebook_data = self.get_data()
#snippet = {'wasBatchExecuted': batch, 'type': 'oozie', 'id': notebook_data['snippets'][0]['id'], 'statement': ''}
snippet = notebook_data['snippets'][0]
snippet['wasBatchExecuted'] = batch
return _execute_notebook(request, notebook_data, snippet)
def execute(self, request, batch=False):
from notebook.api import _execute_notebook # Cyclic dependency
notebook_data = self.get_data()
#snippet = {'wasBatchExecuted': batch, 'type': 'oozie', 'id': notebook_data['snippets'][0]['id'], 'statement': ''}
snippet = notebook_data['snippets'][0]
snippet['wasBatchExecuted'] = batch
return _execute_notebook(request, notebook_data, snippet)
def _query_result(request, notebook, max_rows):
snippet = notebook['snippets'][0]
snippet['statement'] = notebook['snippets'][0]['statement_raw']
query_execute = _execute_notebook(request, notebook, snippet)
history_uuid = query_execute['history_uuid']
status = _check_status(request, operation_id=history_uuid)
if status['query_status']['status'] == 'available':
res = _fetch_result_data(request, operation_id=history_uuid, rows=max_rows)
return res['result']
return None
def query_result(request, notebook):
snippet = notebook['snippets'][0]
snippet['statement'] = notebook['snippets'][0]['statement_raw']
query_execute = _execute_notebook(request, notebook, snippet)
history_uuid = query_execute['history_uuid']
status = _check_status(request, operation_id=history_uuid)
if status['query_status']['status'] == 'available':
response = _fetch_result_data(request, operation_id=history_uuid)
return response['result']
return 'Query result has expired or could not be found'
def run_morphline(self, request, collection_name, morphline, input_path):
workspace_path = self._upload_workspace(morphline)
# snippets = [
# {
# u'type': u'java',
# 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'${nameNode}/user/%s/indexer' % self.username,
# u'--log4j',
# u'log4j.properties',
# u'--go-live',
# u'--zk-host',
# zkensemble(),
# u'--collection',
# collection_name,
# input_path,
# ],
# u'archives': [],
# }
# ]
#
# # managed notebook
# notebook = make_notebook2(name='Indexer job for %s' % collection_name, snippets=snippets).get_data()
# notebook_doc, created = _save_notebook(notebook, self.user)
#
# snippet = {'wasBatchExecuted': True}
snippet_properties = {
u'files': [
{u'path': u'%s/log4j.properties' % workspace_path, u'type': u'file'},
{u'path': u'%s/morphline.conf' % workspace_path, u'type': u'file'}
],
u'class': u'org.apache.solr.hadoop.MapReduceIndexerTool',
u'app_jar': CONFIG_INDEXER_LIBS_PATH.get(),
u'arguments': [
u'--morphline-file',
u'morphline.conf',
u'--output-dir',
u'${nameNode}/user/%s/indexer' % self.username,
u'--log4j',
u'log4j.properties',
u'--go-live',
u'--zk-host',
zkensemble(),
u'--collection',
collection_name,
input_path,
],
u'archives': [],
}
notebook = make_notebook(name='Indexer', editor_type='java', snippet_properties=snippet_properties, status='running').get_data()
notebook_doc, created = _save_notebook(notebook, self.user)
snippet = {'wasBatchExecuted': True, 'id': notebook['snippets'][0]['id'], 'statement': ''}
job_handle = _execute_notebook(request, notebook, snippet)
return job_handle
