#
# @copyright Copyright (c) 2024, Pietro Marini (pmarini@rcasys.com)
#
# @license GNU AGPL version 3 or any later version
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as
# published by the Free Software Foundation, either version 3 of the
# License, or (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.
#

import pandas as pd

from datetime import datetime

import json

from functions import get_norm_user_agent

dt = datetime.now().strftime("%Y%m%d")

df = pd.read_csv(
                 "/var/log/apache2/archive/nextcloud-access-csv.log-%s" % dt,
                 header=None,
                 names=["timestamp","user_agent"],
                 parse_dates=["timestamp"]
                )

df.fillna("not-found",inplace=True)

df["norm_user_agent"] = df.user_agent.apply(get_norm_user_agent)

df_agg = df.value_counts("norm_user_agent")

json.dump(
          df_agg.to_dict(),
          open("/var/lib/zabbix/output/apache2_user_agent_metrics.json","w")
         )