Join Kickstarter CSV files for shipping purposes

join_kickstarter_exports.rb

require 'csv'

fields_to_keep = [
  "Backer Id", "Pledge Amount", "Shipping Name", "Shipping Address 1",
  "Shipping Address 2", "Shipping City", "Shipping State", "Shipping Postal Code",
  "Shipping Country Name"
]

sort_result_on = "Backer Id"

all_addresses = []

Dir['Kickstarter*'].each do |file|
  first_row = true
  has_address = false
  column_indexes = {}

  CSV.foreach(file) do |row|
    if first_row
      column_indexes = Hash[row.each_with_index.collect { |hfield, index| [index, fields_to_keep.find { |field| hfield[field] }] }.compact]

      first_row = false

      has_address = column_indexes.values.include?('Shipping Name')
    else
      if has_address
        data = row.each_with_index.find_all { |data| column_indexes[data.last] }.collect { |data|
          [column_indexes[data.last], data.first]
        }

        all_addresses << Hash[data]
      end
    end
  end
end

CSV.open('joined.csv', 'w') do |csv|
  csv << fields_to_keep

  all_addresses.sort { |a, b| a[sort_result_on] <=> b[sort_result_on] }.each do |address|
    csv << fields_to_keep.collect { |field| address[field] }
  end
end