counts matches per X time

match-per-xtime.py

!/usr/bin/python3

import fileinput
from datetime import datetime, date, timedelta
from collections import OrderedDict
from argparse import ArgumentParser

parser = ArgumentParser()
parser.add_argument("-s", "--step", default='minutes', help="group by seconds, minutes or hours")
parser.add_argument('files', metavar='FILE', nargs='*', help='files to read, if empty, stdin is used')
args = parser.parse_args()

#example: 17389426-082a-4441-ac34-908dacccafc6 2022-07-22 21:27:13.966846 [DEBUG] a log line
rows = {}
dates = []
for line in fileinput.input(files=args.files if len(args.files) > 0 else ('-', )):

    #split by spaces
    cols = line.split(' ')

    # get date and time
    mydatetime_str = ' '.join(cols[1:3])

    # remove ms
    mydatetime_str = mydatetime_str.split('.')[0]

    # convert to datetim
    try:
        mydatetime = datetime.strptime(mydatetime_str, '%Y-%m-%d %H:%M:%S')
    except:
        continue

    # truncate seconds
    if args.step in ('minutes', 'hours'):
        mydatetime = mydatetime.replace(second=0)

    # truncate minutes
    if args.step in ('hours'):
        mydatetime = mydatetime.replace(minute=0)

    # add to rows counter
    if mydatetime in rows:
        rows[mydatetime] += 1
    else:
        rows[mydatetime] = 1

    # add date to list (to get max and min later)
    dates.append(mydatetime)

if not dates:
    exit("No valid dates.")

# get date range
start_date = min(dates)
end_date = max(dates)

# get step
delta = timedelta(**{args.step: 1})

# print header
print("Start date: %s" %(start_date,))
print("End date: %s" %(end_date,))
print('==============================')

# insert zeros when no data
a_date = start_date
while a_date <= end_date:
    if not a_date in rows:
        rows[a_date] = 0
    a_date += delta

rows_ordered = OrderedDict(sorted(rows.items()))
for row in rows_ordered:
    print("%s,%s" % (row.strftime("%Y-%m-%d %H:%M:%S"), rows[row]))