Created
August 15, 2012 23:47
-
-
Save afeld/3364792 to your computer and use it in GitHub Desktop.
Jux: clean up garbage Twitter usernames
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
# using Mongoid | |
# clean up leading/trailing whitespace | |
User.where(twitter_username: /(\A\s+[A-Za-z0-9_]+\s*\z)|(\A\s*[A-Za-z0-9_]+\s+\z)/).each do |user| | |
user.twitter_username = user.twitter_username.strip | |
user.save! | |
end | |
# clean up twitter usernames of the format @... or twitter.com/... | |
link_rx = /(?:\A@|\A\/|twitter\.com\/(?:#!\/)?)([A-Za-z0-9_]+)\s*\z/i | |
User.where(twitter_username: link_rx).each do |user| | |
if user.twitter_username =~ link_rx | |
new_tu = $1 | |
if new_tu =~ /\A[A-Za-z0-9_]+\z/ | |
# valid | |
user.twitter_username = new_tu | |
user.save! | |
# puts "old: #{user.twitter_username}\t\tnew: #{new_tu}" | |
else | |
puts "failed: #{new_tu}" | |
end | |
end | |
end | |
# finally, get rid of all remaining invalid ones | |
User.where(twitter_username: /[^A-Za-z0-9_]/).update_all(twitter_username: nil) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment