mirror of
https://github.com/discourse/discourse.git
synced 2024-12-01 02:53:40 +08:00
cbceadf48b
Previously we relied entirely on levenshtein_distance_spammer_emails site setting to handle "similar looking" emails. This commit improves the situation by always preferring to block (and check) canonical emails. This means that if: `samevil+test@domain.com` is blocked the system will block `samevil@domain.com` This means that `samevil+2@domain.com` (ad infinitum) will be blocked
96 lines
2.5 KiB
Ruby
96 lines
2.5 KiB
Ruby
# frozen_string_literal: true
|
|
|
|
# A ScreenedEmail record represents an email address that is being watched,
|
|
# typically when creating a new User account. If the email of the signup form
|
|
# (or some other form) matches a ScreenedEmail record, an action can be
|
|
# performed based on the action_type.
|
|
class ScreenedEmail < ActiveRecord::Base
|
|
|
|
include ScreeningModel
|
|
|
|
default_action :block
|
|
|
|
validates :email, presence: true, uniqueness: true
|
|
|
|
before_save :downcase_email
|
|
|
|
def downcase_email
|
|
self.email = email.downcase
|
|
end
|
|
|
|
def self.canonical(email)
|
|
name, domain = email.split('@', 2)
|
|
name = name.gsub(/\+.*/, '')
|
|
if ['gmail.com', 'googlemail.com'].include?(domain.downcase)
|
|
name = name.gsub('.', '')
|
|
end
|
|
"#{name}@#{domain}".downcase
|
|
end
|
|
|
|
def self.block(email, opts = {})
|
|
email = canonical(email)
|
|
find_by_email(email) || create!(opts.slice(:action_type, :ip_address).merge(email: email))
|
|
end
|
|
|
|
def self.should_block?(email)
|
|
|
|
email = canonical(email)
|
|
|
|
screened_emails = ScreenedEmail.order(created_at: :desc).limit(100)
|
|
|
|
distances = {}
|
|
screened_emails.each { |se| distances[se.email] = levenshtein(se.email.downcase, email.downcase) }
|
|
|
|
max_distance = SiteSetting.levenshtein_distance_spammer_emails
|
|
screened_email = screened_emails.select { |se| distances[se.email] <= max_distance }
|
|
.sort { |se| distances[se.email] }
|
|
.first
|
|
|
|
screened_email.record_match! if screened_email
|
|
|
|
screened_email.try(:action_type) == actions[:block]
|
|
end
|
|
|
|
def self.levenshtein(first, second)
|
|
matrix = [(0..first.length).to_a]
|
|
(1..second.length).each do |j|
|
|
matrix << [j] + [0] * (first.length)
|
|
end
|
|
|
|
(1..second.length).each do |i|
|
|
(1..first.length).each do |j|
|
|
if first[j - 1] == second[i - 1]
|
|
matrix[i][j] = matrix[i - 1][j - 1]
|
|
else
|
|
matrix[i][j] = [
|
|
matrix[i - 1][j],
|
|
matrix[i][j - 1],
|
|
matrix[i - 1][j - 1],
|
|
].min + 1
|
|
end
|
|
end
|
|
end
|
|
matrix.last.last
|
|
end
|
|
|
|
end
|
|
|
|
# == Schema Information
|
|
#
|
|
# Table name: screened_emails
|
|
#
|
|
# id :integer not null, primary key
|
|
# email :string not null
|
|
# action_type :integer not null
|
|
# match_count :integer default(0), not null
|
|
# last_match_at :datetime
|
|
# created_at :datetime not null
|
|
# updated_at :datetime not null
|
|
# ip_address :inet
|
|
#
|
|
# Indexes
|
|
#
|
|
# index_screened_emails_on_email (email) UNIQUE
|
|
# index_screened_emails_on_last_match_at (last_match_at)
|
|
#
|