Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

DD-1763 Voeg --age parameter toe aan deposit-clean-data #72

Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
60 changes: 51 additions & 9 deletions src/datastation/deposit_clean_data.py
Original file line number Diff line number Diff line change
@@ -1,26 +1,68 @@
import argparse
import csv
from datetime import date, timedelta
import io
import os
import shutil

from datastation.managedeposit.manage_deposit import ManageDeposit
from datastation.common.config import init


def clean_manage_deposit_data(server_url, args):
result = ManageDeposit(args).clean_data(server_url)
if result is not None:
print(result)
class CleanHandler:
def __init__(self, server_url, cmd_args):
self.__deposit_folder_index_in_csv = 1
self.__deposit_location_index_in_csv = 7
self.__server_url = server_url
self.__command_line_args = cmd_args

def handle_request(self):
report = ManageDeposit(self.__command_line_args).create_report(self.__server_url)

if report is not None and len(report.split('\n')) > 1:
self.remove_folders(self.collect_paths(report))
else:
print("deposit_clean_data: report is empty.")

def collect_paths(self, csv_data):
paths = []
csv_mem = io.StringIO(csv_data)
csv_reader = csv.reader(csv_mem)
for row in csv_reader:
if len(row) > max(self.__deposit_folder_index_in_csv, self.__deposit_location_index_in_csv):
paths.append(row[self.__deposit_location_index_in_csv] + "/" + row[self.__deposit_folder_index_in_csv])

return paths

def remove_folders(self, paths):
for path in paths:
if os.path.exists(path) and os.path.isdir(path):
shutil.rmtree(path)
print(f"Folder '{path}' has been removed successfully.")
else:
print(f"Folder '{path}' does not exist.")


def main():
config = init()
parser = argparse.ArgumentParser(prog='deposit_data_cleaner', description='Clean up dd-manage-deposit database')
parser.add_argument('-e', '--enddate', dest='enddate', help='Filter until the record creation of this date')
parser.add_argument('-f', '--format', dest='file_format', default='text/csv', help='Output data format')
parser.add_argument('-s', '--startdate', dest='startdate', help='Filter from the record creation of this date')
parser.add_argument('-t', '--state', dest='state', help='The state of the deposit')
parser.add_argument('-u', '--user', dest='user', help='The depositor name')

group = parser.add_mutually_exclusive_group(required=False)
group.add_argument('-a', '--age', dest='age', type=int, help='Filter records older than a number of days before today')
group.add_argument('-e', '--enddate', dest='enddate', help='Filter until the record creation of this date')

parser.add_argument('-t', '--state', dest='state', help='The state of the deposit (repeatable)', action='append')
parser.add_argument('-u', '--user', dest='user', help='The depositor name (repeatable)', action='append')
args = parser.parse_args()

server_url = config['manage_deposit']['service_baseurl'] + '/delete-deposit'
if args.age is not None: # Note: args is a Namespace object
vars(args)['enddate'] = (date.today() + timedelta(days=-args.age)).strftime('%Y-%m-%d')

server_url = config['manage_deposit']['service_baseurl'] + '/report'

clean_manage_deposit_data(server_url, args)
CleanHandler(server_url, args).handle_request()


if __name__ == '__main__':
Expand Down
Loading