treetop.rb

POSTCODE_REGEXP = /([A-Z]{1,2}[0-9R][0-9A-Z]?\s*[0-9][ABD-HJLNP-UW-Z]{2})/i

def parse(string)
  address, postcode = string.split(POSTCODE_REGEXP)
  town, county = "",""

  mode = :seeking_county
  collect = ""
  address.reverse.each_char do |c|
    case mode
      when :seeking_county
        if [',',' '].include? c
          if is_county?(collect)
            county = collect.strip
            collect = ""
            mode = :seeking_town
          elsif c == ','
            town = collect.strip
            collect = ""
            mode = :snarf_the_rest
          else
            collect = c + collect
          end
        elsif c == '.'
          next
        else
          collect = c + collect
        end
      when :seeking_town
        if c == ',' && collect.strip != "" 
          town = collect.strip
          collect = ""
          mode = :snarf_the_rest
        else
          collect = c + collect
        end
      when :snarf_the_rest
        collect = c + collect
    end
  end

  puts [collect,town,county,postcode].inspect 
end

def is_county?(s)
  ['Cambridgeshire','Mid Glam'].include?(s.strip)
end


parse("5 Brookfields, Cambridge")
parse("5 Brookfields, Cambridge CB1 3NZ")
parse("Brynllefrith, Llanfabon Rd, Nelson, Mid Glam. CF46 6PG")
parse("46 Ashburnham Place, London SE10 8UG")
parse("46 Ashburnham Place London SE10 8UG")
parse("46 Ashburnham Place London")