def _add(index, submission_paths, only_these=None):
from aggregator.record_aggregator import RecordAggregator
record_aggregator = RecordAggregator(index)
submission_label = Label(min_length=10)
pbar = AlwaysUpdatingProgressBar(maxval=len(submission_paths),
widgets=[
Percentage(),
submission_label,
Bar(marker='#', left='[', right=']')
]).start()
for i, submission_path in enumerate(submission_paths):
shared_dcontext.dcontext.submission = os.path.basename(submission_path)
submission_label.change_text(shared_dcontext.dcontext.submission)
pbar.update(i)
if only_these is not None:
inspire_id = int(
shared_dcontext.dcontext.submission.replace('ins', ''))
if inspire_id not in only_these:
continue
try:
record_aggregator.process_submission(submission_path)
except TransportError as err:
print(err)
print(dir(err))
raise err
pbar.finish()
print('Done', file=sys.stderr)
record_aggregator.report_statistics()
def add_demo_mini():
# Add a couple of fake publications, useful to test ElasticSearch queries
from aggregator.record_aggregator import RecordAggregator
record_aggregator = RecordAggregator('hepdata-mini-demo')
record_aggregator.load_mini_demo()
record_aggregator.report_statistics()
