Last active
June 19, 2019 19:18
-
-
Save dramsay/9091c6684d33c554543022f5f7beee4e to your computer and use it in GitHub Desktop.
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
# use by calling from command line and passing in path to file | |
# ruby anonymizer.rb /path/to/metrics_file.csv | |
require 'csv' | |
require 'securerandom' | |
HASHED_IP = %r|ip$| | |
IDENTIFIERS = %r[id$] | |
SECONDS = %r|seconds_downloaded| | |
def transform_ip(row, hashed_ip_index) | |
hashed_ip = row[hashed_ip_index] | |
index = rand(0..16) | |
hashed_ip[index] = (('a'..'z').to_a - [hashed_ip[index]]).sample | |
row[hashed_ip_index] = hashed_ip | |
row | |
end | |
def transform_seconds(row, seconds_index) | |
seconds = row[seconds_index] | |
row[seconds_index] = ((seconds.to_i + (-100..100).to_a.sample) * 1.3).round.to_s | |
row | |
end | |
# take headers plus first 100 rows | |
rows = CSV.foreach(ARGV[0]).take(101) | |
headers = rows.shift | |
hashed_ip_index = headers.index {|i| i =~ HASHED_IP } | |
seconds_index = headers.index {|i| i =~ SECONDS } | |
identifier_indexes = headers.select {|h| h =~ IDENTIFIERS }.map {|h| headers.index(h) } | |
data = CSV.generate do |csv| | |
csv << headers | |
rows.each do |row| | |
csv << row | |
.yield_self {|r| transform_ip(row, hashed_ip_index) } | |
.yield_self {|r| transform_seconds(row, seconds_index) } | |
.yield_self {|r| identifier_indexes.each {|i| r[i] = SecureRandom.uuid unless r[i].to_s.empty? }; r } | |
end | |
end | |
puts data | |
File.open('anonymized.csv', 'w') {|f| f.puts data } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment