transform prev. version of logs in ES

transform.py

import sys
import json
import hashlib


def process_item(item):
    rec = item['_source']
    rec['isQuery'] = rec.pop('entryQuery')
    if rec.get('action', None) in ('wsketch', 'thes', 'wsdiff'):
        rec['isQuery'] = True
    rec['queryType'] = None
    item['_id'] = hashlib.sha1(json.dumps(rec)).hexdigest()
    item['_source'] = rec


def process(f):
    for line in f:
        d = json.loads(line)
        process_item(d)
        print(d)


if __name__ == '__main__':
    with open(sys.argv[1], 'rb') as f:
        process(f)