import pandas as pd

from datetime import datetime, timedelta

import sys

import json

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"])

## EDGE
# Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36 Edg/110.0.1587.57
## Chrome
# Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36
## Firefox
# Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:110.0) Gecko/20100101 Firefox/110.0
## Safari
# Mozilla/5.0 (Macintosh; Intel Mac OS X 13_2_1) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.3 Safari/605.1.15

def get_norm_user_agent(s):
        s = s.lower()
        ## Nextcloud Talk App
        if "nextcloud-talk" in s:
                if "android" in s:
                        return "Nextcloud_Talk_Android"
                elif "ios" in s:
                        return "Nextcloud_Talk_iOS"
                else:
                        return "Nextcloud_Talk_unknown"
        ## Nextcloud Files App
        if "nextcloud-android" in s:
                return "Nextcloud_Android"
        ## Browser
        if "chrome" in s:
                if "edg" in s:
                        return "Edge_browser"
                else:
                        return "Chrome_browser"
        if "firefox" in s:
                return "Firefox_browser"
        if "macintosh" in s and "applewebkit" in s:
                return "Safari_browser"
        ## Desktop Client
        if "mirall" in s:
                if "linux" in s:
                        return "Desktop_Client_Linux"
                elif "macintosh" in s:
                        return "Desktop_Client_Mac"
                elif "windows" in s:
                        return "Desktop_Client_Windows"
                else:
                        return "Desktop_Client_Unknown"


df_24h = df[df.timestamp>datetime.now() - timedelta(hours=24)]

df_24h["norm_user_agent"] = df_24h.user_agent.apply(get_norm_user_agent)

df_24h_agg = df_24h.value_counts("norm_user_agent")

json.dump(df_24h_agg.to_dict(),
         open("/var/lib/zabbix/output/apache2_user_agent_metrics.json","w"))