def print_mc_datasets_simple(mc_datasets, keys):
if nested_dict.is_nested_dict(mc_datasets, keys):
paths = nested_dict.get_item_nested_dict(mc_datasets, keys)
for path in paths:
print(get_info_path_string_mc_datasets(path, mc_datasets, ' '))
else:
print(str(keys)+' do not exist in mc_datasets')
def check_entries(job_argument_string):
#try:
print(job_argument_string)
args = get_args(['dataset_files_info_filename', 'command'],
job_argument_string)
args_command = get_args_command(args['command'])
print(args)
print(args_command)
file_path = get_file_path(args_command['output_path'], "",
args_command['input_path'])
#print(file_path)
if not os.path.isfile(file_path):
# Wait for file to appear on raid
file_exists = False
for iWait in range(10):
time.sleep(10)
if os.path.isfile(file_path):
file_exists = True
break
if not file_exists:
return '[For queue_system] fail: no file named ' + file_path
root_file = ROOT.TFile.Open(file_path)
if not root_file:
return '[For queue_system] fail: Failed in opening ' + file_path
root_tree = root_file.Get('Events')
root_number_entries = root_tree.GetEntries()
#print(args['dataset_files_info_filename'][1:-1])
#datasets_files_info[dataset][filename] = {'number_events':number_events}
dataset_files_info = nested_dict.load_json_file(
args['dataset_files_info_filename'], False)
path_to_keys_dataset_files_info = datasets.get_path_to_keys_dataset_files_info(
dataset_files_info)
keys = path_to_keys_dataset_files_info[args_command['input_path']]
#print(keys)
#print(nested_dict.get_item_nested_dict(dataset_files_info,keys))
dataset_number_entries = nested_dict.get_item_nested_dict(
dataset_files_info, keys)['number_events']
#print(root_number_entries)
#print(dataset_number_entries)
if root_number_entries == dataset_number_entries:
return '[For queue_system] success'
else:
return '[For queue_system] fail: root_number_entries: ' + str(
root_number_entries) + ' and dataset_number_entries: ' + str(
dataset_number_entries) + ' do not match'
def get_info_path_string_mc_datasets(path, mc_datasets, prefix):
out_info_path = ''
# Make meta
path_to_keys_mc_datasets = datasets.get_path_to_keys_mc_datasets(
mc_datasets)
mini_to_nanos_from_nanoaod = datasets.get_mini_to_nanos_from_nanoaod_mc_datasets(
mc_datasets)
nano_to_mini_from_miniaod = datasets.get_nano_to_mini_from_miniaod_mc_datasets(
mc_datasets)
keys = path_to_keys_mc_datasets[path]
keys.append(path)
path_info = nested_dict.get_item_nested_dict(mc_datasets, keys)
bad_pu = filter_datasets_jsons.reject_bad_pu_2017_mc_datasets(
'', mc_datasets, keys[0], keys[1], keys[2], keys[3])
# Print extra info
if bad_pu:
out_info_path += ' BAD PU\n'
same_parent_paths = datasets.get_same_parent_paths(mc_datasets)
if has_same_parent(same_parent_paths, path):
out_info_path += ' Has same parent\n'
if 'miniaod' in keys:
if path in mini_to_nanos_from_nanoaod:
out_info_path += prefix + ' Matching nanoaod: ' + get_list_string(
mini_to_nanos_from_nanoaod[path]) + '\n'
else:
out_info_path += prefix + ' No matching nanoaod.\n'
if 'nanoaod' in keys:
if path in nano_to_mini_from_miniaod:
out_info_path += prefix + ' Matching miniaod: ' + nano_to_mini_from_miniaod[
path] + '\n'
else:
out_info_path += prefix + ' No matching miniaod.'
out_info_path += prefix + ' creation_time: ' + str(
datasets.convert_timestamp(path_info['creation_time'])) + '\n'
out_info_path += prefix + ' parent_chain:\n'
parent_prefix = ' '
for parent in path_info['parent_chain']:
out_info_path += prefix + parent_prefix + parent + '\n'
parent_prefix += ' '
#if len(path_info['children']) != 0:
# out_info_path += prefix + ' children:\n'
# for child in path_info['children']:
# out_info_path += prefix + ' ' + child+'\n'
#out_info_path = out_info_path.rstrip()
return out_info_path