count_metric_points.py

#!/usr/bin/env python3

import fileinput

data_points_by_id = {}
metric_names_by_id = {}

# that's expecting the output of
# MT_KAFKA_MDM_IN_OFFSET=newest time mt-kafka-mdm-sniff -format-md '{{.OrgId}} {{.Id}} {{.Name}} {{.Tags}} {{.Time}}' -format-point '{.MKey}} {{.Time}}'

for line in fileinput.input():
    line = line.rstrip()
    splits = line.split(' ')
    if len(splits) == 2:
        id = splits[0]
        time = splits[1]
    elif len(splits) == 5:
        id = splits[1]
        name = splits[2]
        tags = splits[3]
        time = splits[4]

        metric_names_by_id[id] = name
    else:
        print('invalid line: {line}'.format(line=line))
        continue

    data_points_by_id[id] = data_points_by_id.get(id, 0) + 1


ids = list(data_points_by_id.keys())
ids.sort(key=lambda id: data_points_by_id[id], reverse=False)

for id in ids:
    print('count: {count} metric: {metric}'.format(count=data_points_by_id[id], metric=metric_names_by_id.get(id, id)))