Mr. Scott needed some Wufoo importing love...

dedup_emails_for_scott.rb

#!/usr/bin/env ruby
# dedup_emails_for_scott.rb
# usage:
#   ruby dedup_emails_for_scott.rb file_to_upload.csv existing_entries.csv file_to_upload_deduped.csv

EMAIL_COL = 'Email' # change this if your column name is not 'Email'

if ARGV.length == 3
  upload_filename, existing_filename, output_filename = ARGV
else
  puts "Usage: ruby dedup_emails_for_scott.rb file_to_upload.csv existing_entries.csv file_to_upload_deduped.csv"
  puts "The first 2 files must already exist. The last filename will be written."
  exit(1)
end

require 'rubygems'
require 'fastercsv'

existing = FasterCSV.parse(File.read(existing_filename), :headers => true)
headers = existing.first.to_hash.keys.sort

FasterCSV.open(output_filename, 'w') do |output|
  output << headers
  FasterCSV.open(upload_filename, 'r', :headers => true) do |csv|
    csv.each do |record|
      if existing.detect { |r| r[EMAIL_COL].downcase == record[EMAIL_COL].downcase }
        record[EMAIL_COL] = nil
      end
      existing << record
      output << headers.map { |h| record[h] }
    end
  end
end