Last active
December 20, 2017 10:43
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import collections | |
import datetime | |
import hashlib | |
import random | |
import string | |
import sys | |
from contextlib import suppress | |
random.seed(0) | |
done = collections.Counter() | |
maximum = 5 | |
def max_for(text): | |
hasher = hashlib.blake2b() | |
hasher.update(text.encode('utf-8')) | |
return sum(hasher.digest()) % maximum | |
def random_string(size=6, chars=string.ascii_uppercase + string.digits): | |
return ''.join(random.choice(chars) for _ in range(size)) | |
def scramble(value): | |
# handle dates | |
with suppress(Exception): | |
datetime.datetime.strptime(value, "%d%m%Y") | |
return value | |
# handle floats | |
with suppress(Exception): | |
if ',' in value: | |
float(value.replace(',', '.')) | |
return value | |
# identifiers, do not touch | |
if value == "LECD" or value == "LECF": | |
return value | |
# randomize digits if only digits | |
if value.isdigit(): | |
return random_string(size=len(value), chars=string.digits) | |
# randomize generally | |
return random_string(size=len(value)) | |
def run(line): | |
if not line.startswith('|'): | |
return | |
try: | |
_, record_type, *values, _ = line.split('|') | |
except Exception: | |
return | |
if done[record_type] < max_for(record_type): | |
new_values = '|'.join(scramble(v) for v in values) | |
print(f'|{record_type}|{new_values}|') | |
done.update([record_type]) | |
if __name__ == '__main__': | |
filepath = sys.argv[1] | |
with open(filepath, encoding='latin1') as f: | |
for line in f: | |
run(line) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment