a.rb

#
  require 'open-uri'
  require 'json'

#
  module TargetSmartStateDictionary
    def TargetSmartStateDictionary.url
      @url ||= (
        'https://gist.githubusercontent.com/mshafrir/2646763/raw/8b0dbb93521f5d6889502305335104218454c2bf/states_hash.json'
      )
    end

    def TargetSmartStateDictionary.states
      @states ||= (
        JSON.parse(open(url){|s| s.read})
      )
    end

    def TargetSmartStateDictionary.patterns
      @patterns ||= (
        list = []

        states.each do |key, value|
          pattern = '\b' + '(' + key + ')' + '([\s0-9]*)\b'
          list.push(/#{ pattern }/i)
        end

        list
      )
    end

    def TargetSmartStateDictionary.match(string)
      string = string.to_s
      captures = []

      patterns.each do |pattern|
        captured = pattern.match(string).to_a

        if captured[0]
          captures.push(captured)
        end
      end

      case captures.size
        when 0
          raise Error.new("0 matches in #{ string.inspect }")
        when 1
          captured = captures[0]

          matched     = captured[0].to_s
          key         = captured[1].to_s
          code        = captured[2].to_s

          key         = key.strip.upcase
          state       = states[key]
          code        = code.gsub(/\s+/, '').strip
          description = string.gsub(matched, '').strip

          if code.empty?
            code = nil
          end

          result = {
            'key'         => key,
            'state'       => state,
            'code'        => code,
            'description' => description
          }
        else
          raise Error.new("N matches in #{ string.inspect }")
      end
    end

    class Error < ::StandardError; end
  end

#
  p 'STATES' => TargetSmartStateDictionary.states
  p 'patterns' => TargetSmartStateDictionary.patterns


  [
    'ma 123 foo bar',
    ' ma123 one two three  ',
    ' co four five six',
  ].each do |string|
    result = TargetSmartStateDictionary.match(string)

    pp(
      'string' => string,
      'result' => result
    )
  end





__END__

{"STATES"=>{"AL"=>"Alabama", "AK"=>"Alaska", "AS"=>"American Samoa", "AZ"=>"Arizona", "AR"=>"Arkansas", "CA"=>"California", "CO"=>"Colorado", "CT"=>"Connecticut", "DE"=>"Delaware", "DC"=>"District Of Columbia", "FM"=>"Federated States Of Micronesia", "FL"=>"Florida", "GA"=>"Georgia", "GU"=>"Guam", "HI"=>"Hawaii", "ID"=>"Idaho", "IL"=>"Illinois", "IN"=>"Indiana", "IA"=>"Iowa", "KS"=>"Kansas", "KY"=>"Kentucky", "LA"=>"Louisiana", "ME"=>"Maine", "MH"=>"Marshall Islands", "MD"=>"Maryland", "MA"=>"Massachusetts", "MI"=>"Michigan", "MN"=>"Minnesota", "MS"=>"Mississippi", "MO"=>"Missouri", "MT"=>"Montana", "NE"=>"Nebraska", "NV"=>"Nevada", "NH"=>"New Hampshire", "NJ"=>"New Jersey", "NM"=>"New Mexico", "NY"=>"New York", "NC"=>"North Carolina", "ND"=>"North Dakota", "MP"=>"Northern Mariana Islands", "OH"=>"Ohio", "OK"=>"Oklahoma", "OR"=>"Oregon", "PW"=>"Palau", "PA"=>"Pennsylvania", "PR"=>"Puerto Rico", "RI"=>"Rhode Island", "SC"=>"South Carolina", "SD"=>"South Dakota", "TN"=>"Tennessee", "TX"=>"Texas", "UT"=>"Utah", "VT"=>"Vermont", "VI"=>"Virgin Islands", "VA"=>"Virginia", "WA"=>"Washington", "WV"=>"West Virginia", "WI"=>"Wisconsin", "WY"=>"Wyoming"}}


{"patterns"=>[/\b(AL)([\s0-9]*)\b/i, /\b(AK)([\s0-9]*)\b/i, /\b(AS)([\s0-9]*)\b/i, /\b(AZ)([\s0-9]*)\b/i, /\b(AR)([\s0-9]*)\b/i, /\b(CA)([\s0-9]*)\b/i, /\b(CO)([\s0-9]*)\b/i, /\b(CT)([\s0-9]*)\b/i, /\b(DE)([\s0-9]*)\b/i, /\b(DC)([\s0-9]*)\b/i, /\b(FM)([\s0-9]*)\b/i, /\b(FL)([\s0-9]*)\b/i, /\b(GA)([\s0-9]*)\b/i, /\b(GU)([\s0-9]*)\b/i, /\b(HI)([\s0-9]*)\b/i, /\b(ID)([\s0-9]*)\b/i, /\b(IL)([\s0-9]*)\b/i, /\b(IN)([\s0-9]*)\b/i, /\b(IA)([\s0-9]*)\b/i, /\b(KS)([\s0-9]*)\b/i, /\b(KY)([\s0-9]*)\b/i, /\b(LA)([\s0-9]*)\b/i, /\b(ME)([\s0-9]*)\b/i, /\b(MH)([\s0-9]*)\b/i, /\b(MD)([\s0-9]*)\b/i, /\b(MA)([\s0-9]*)\b/i, /\b(MI)([\s0-9]*)\b/i, /\b(MN)([\s0-9]*)\b/i, /\b(MS)([\s0-9]*)\b/i, /\b(MO)([\s0-9]*)\b/i, /\b(MT)([\s0-9]*)\b/i, /\b(NE)([\s0-9]*)\b/i, /\b(NV)([\s0-9]*)\b/i, /\b(NH)([\s0-9]*)\b/i, /\b(NJ)([\s0-9]*)\b/i, /\b(NM)([\s0-9]*)\b/i, /\b(NY)([\s0-9]*)\b/i, /\b(NC)([\s0-9]*)\b/i, /\b(ND)([\s0-9]*)\b/i, /\b(MP)([\s0-9]*)\b/i, /\b(OH)([\s0-9]*)\b/i, /\b(OK)([\s0-9]*)\b/i, /\b(OR)([\s0-9]*)\b/i, /\b(PW)([\s0-9]*)\b/i, /\b(PA)([\s0-9]*)\b/i, /\b(PR)([\s0-9]*)\b/i, /\b(RI)([\s0-9]*)\b/i, /\b(SC)([\s0-9]*)\b/i, /\b(SD)([\s0-9]*)\b/i, /\b(TN)([\s0-9]*)\b/i, /\b(TX)([\s0-9]*)\b/i, /\b(UT)([\s0-9]*)\b/i, /\b(VT)([\s0-9]*)\b/i, /\b(VI)([\s0-9]*)\b/i, /\b(VA)([\s0-9]*)\b/i, /\b(WA)([\s0-9]*)\b/i, /\b(WV)([\s0-9]*)\b/i, /\b(WI)([\s0-9]*)\b/i, /\b(WY)([\s0-9]*)\b/i]}


{"string"=>"ma 123 foo bar",
 "result"=>
  {"key"=>"MA",
   "state"=>"Massachusetts",
   "code"=>"123",
   "description"=>"foo bar"}}
{"string"=>" ma123 one two three  ",
 "result"=>
  {"key"=>"MA",
   "state"=>"Massachusetts",
   "code"=>"123",
   "description"=>"one two three"}}
{"string"=>" co four five six",
 "result"=>
  {"key"=>"CO",
   "state"=>"Colorado",
   "code"=>nil,
   "description"=>"four five six"}}