vaultify 0.1.0

data/app/controllers/vaultify/application_controller.rb

@@ -0,0 +1,5 @@
+module Vaultify
+  class ApplicationController < ActionController::Base
+    protect_from_forgery with: :exception
+  end
+end

data/app/controllers/vaultify/vaultify_controller.rb

@@ -0,0 +1,370 @@
+module Vaultify
+  class VaultifyController < ApplicationController
+
+
+    require 'csv'
+    require 'net/http'
+    require 'base64'
+
+    include EdtfHelper
+
+    def initialize
+      super
+      @fields = Vaultify::Engine.config['fields']
+    end
+
+    def upload
+
+    end
+
+    def translate
+      @mvs = Vaultify::Engine.config['mvs']
+      csv = params['csv'].path
+      @csv = ::CSV.parse(File.read(csv), headers: true, encoding: 'utf-8').map(&:to_hash)
+      session[:csv] = ::CSV.parse(File.read(csv), headers: true, encoding: 'utf-8').map(&:to_hash)
+      @total = @csv.length
+      @csv.each_with_index do |row, index|
+        next if row == nil
+        @fields.each do |field_row|
+          field = field_row.first
+          api = field_row.last
+          next if (row[field].to_s.empty? || api.to_s.empty?)
+          adjusted_array = []
+          row[field].split(@mvs).each do |line|
+            adjusted_array << send("#{api}First", line) rescue nil
+          end
+          @csv[index]["#{field}-adjusted"] = adjusted_array.join(@mvs)
+        end
+      end
+    end
+
+    def export
+      @csv = session[:csv].deep_dup
+      @puramses = params
+      @fields.each do |field_row|
+        next unless params.key? field_row.first.to_sym
+
+        params.permit![field_row.first.to_sym].each do |csv_row, values|
+          adj = []
+          values.each do |_, value|
+            adj << value
+          end
+          @csv[csv_row.to_i][field_row.first] = adj.join('|')
+        end
+      end
+      csv_output = []
+      csv_output << @csv.first.keys
+      @csv.each do |row|
+        csv_output << row.values
+      end
+
+      respond_to do |format|
+        format.csv {render plain: csv_output.inject([]) {|csv, row| csv << CSV.generate_line(row)}.join, content_type: 'text/csv'}
+      end
+
+
+      #csv.each_with_index |row, index|
+      #@fields.each do |field_row|
+      # params[field_row.first.to_sym][index]
+      #  csv
+      #   end
+      #end
+    end
+
+    def fast
+      res = fastApi params['query']
+
+      respond_to do |format|
+        format.json {render plain: res}
+        format.text {render plain: res}
+      end
+    end
+
+    def aat
+      res = aatApi params['cleanQuery']
+      respond_to do |format|
+        format.xml {render plain: res}
+        format.text {render plain: res}
+        format.json {render plain: res.to_json}
+      end
+    end
+
+    def edtf
+      date = convert_date params[:query]
+      respond_to do |format|
+        format.text {render plain: date}
+      end
+    end
+
+    private
+
+    def fastFirst query, queryIndex = 'suggestall', queryReturn = '%2Cidroot%2Cauth'
+      res = JSON.parse(fastApi query, queryIndex, queryReturn)
+      res['response']['docs'][0]['auth'] + 'url:' + res['response']['docs'][0]['idroot']
+    end
+
+    def aatFirst query
+      res = aatApi query.gsub(' AAT', '')
+      #res = Hash.from_xml(res.gsub("\r\n", '').downcase).to_json.force_encoding('UTF-8')['response']['docs'][0]['auth']
+      res[0]['preferred_term'] + 'url:' + res[0]['subject_id']
+    end
+
+    def isoFirst query
+      # make list with matches, return the one with most letters matched
+      # query.split('').each do |char| { if row.alpha3.includes? char { count++ } }
+      #top = 0
+      #top_index = 0
+      #query_arr = query.split('')
+      #isoVar.each_with_index do |row, index|
+      isoVar.each do |row|
+        return row[:English] + 'url:' + [:alpha2] if query == row[:"alpha3-b"] || query == row[:alpha2] || query == row[:English]
+=begin
+        count = 0
+        query_arr.each do |ch|
+          count += 1 if row[:"alpha3-b"].include? ch
+        end
+        if count > top
+          top = count
+          top_index = index
+        end
+=end
+      end
+      #isoVar[top_index][:alpha2]
+      nil
+    end
+
+    def dcmiFirst query
+      dcmiVar.each do |row|
+        return row[:text] + 'url:' + row[:url] if query == row[:text]
+      end
+      nil
+    end
+
+    def edtfFirst query
+      date = convert_date query
+      return date + 'url:' + date if date
+      nil
+    end
+
+    def fastApi query, queryIndex = 'suggestall', queryReturn = '%2Cidroot%2Cauth'
+      query = query.gsub(/[^a-zA-Z\d\s]/, '')
+      url = 'http://fast.oclc.org/searchfast/fastsuggest?' + "&query=#{query}&queryIndex=#{queryIndex}&queryReturn=#{queryIndex + queryReturn}&suggest=autoSubject&rows=20"
+      Net::HTTP.get_response(URI.parse(url)).body
+    end
+
+    def aatApi query
+      url = URI('http://vocabsservices.getty.edu/AATService.asmx/AATGetTermMatch?term=' + query + '&logop=&notes=')
+      req = Net::HTTP::Get.new(url)
+      res = Net::HTTP.start(url.hostname, url.port) do |http|
+        http.request(req)
+      end
+      Hash.from_xml(res.body.gsub("\r\n", '').downcase)['vocabulary']['subject']
+    end
+
+    def dcmiVar
+      [
+          {"text": 'Collection', "url": 'Collection'},
+          {"text": 'Dataset', "url": 'Dataset'},
+          {"text": 'Event', "url": 'Event'},
+          {"text": 'Image', "url": 'Image'},
+          {"text": 'InteractiveResource', "url": 'InteractiveResource'},
+          {"text": 'MovingImage', "url": 'MovingImage'},
+          {"text": 'PhysicalObject', "url": 'PhysicalObject'},
+          {"text": 'Service', "url": 'Service'},
+          {"text": 'Software', "url": 'Software'},
+          {"text": 'Sound', "url": 'Sound'},
+          {"text": 'StillImage', "url": 'StillImage'},
+          {"text": 'Text', "url": 'Text'}
+      ]
+    end
+
+    def isoVar
+      [
+          {"alpha3-b": "aar", "alpha2": "aa", "English": "Afar"},
+          {"alpha3-b": "abk", "alpha2": "ab", "English": "Abkhazian"},
+          {"alpha3-b": "afr", "alpha2": "af", "English": "Afrikaans"},
+          {"alpha3-b": "aka", "alpha2": "ak", "English": "Akan"},
+          {"alpha3-b": "alb", "alpha2": "sq", "English": "Albanian"},
+          {"alpha3-b": "amh", "alpha2": "am", "English": "Amharic"},
+          {"alpha3-b": "ara", "alpha2": "ar", "English": "Arabic"},
+          {"alpha3-b": "arg", "alpha2": "an", "English": "Aragonese"},
+          {"alpha3-b": "arm", "alpha2": "hy", "English": "Armenian"},
+          {"alpha3-b": "asm", "alpha2": "as", "English": "Assamese"},
+          {"alpha3-b": "ava", "alpha2": "av", "English": "Avaric"},
+          {"alpha3-b": "ave", "alpha2": "ae", "English": "Avestan"},
+          {"alpha3-b": "aym", "alpha2": "ay", "English": "Aymara"},
+          {"alpha3-b": "aze", "alpha2": "az", "English": "Azerbaijani"},
+          {"alpha3-b": "bak", "alpha2": "ba", "English": "Bashkir"},
+          {"alpha3-b": "bam", "alpha2": "bm", "English": "Bambara"},
+          {"alpha3-b": "baq", "alpha2": "eu", "English": "Basque"},
+          {"alpha3-b": "bel", "alpha2": "be", "English": "Belarusian"},
+          {"alpha3-b": "ben", "alpha2": "bn", "English": "Bengali"},
+          {"alpha3-b": "bih", "alpha2": "bh", "English": "Bihari languages"},
+          {"alpha3-b": "bis", "alpha2": "bi", "English": "Bislama"},
+          {"alpha3-b": "bos", "alpha2": "bs", "English": "Bosnian"},
+          {"alpha3-b": "bre", "alpha2": "br", "English": "Breton"},
+          {"alpha3-b": "bul", "alpha2": "bg", "English": "Bulgarian"},
+          {"alpha3-b": "bur", "alpha2": "my", "English": "Burmese"},
+          {"alpha3-b": "cat", "alpha2": "ca", "English": "Catalan; Valencian"},
+          {"alpha3-b": "cha", "alpha2": "ch", "English": "Chamorro"},
+          {"alpha3-b": "che", "alpha2": "ce", "English": "Chechen"},
+          {"alpha3-b": "chi", "alpha2": "zh", "English": "Chinese"},
+          {"alpha3-b": "chu", "alpha2": "cu", "English": "Church Slavic; Old Slavonic; Church Slavonic; Old Bulgarian; Old Church Slavonic"},
+          {"alpha3-b": "chv", "alpha2": "cv", "English": "Chuvash"},
+          {"alpha3-b": "cor", "alpha2": "kw", "English": "Cornish"},
+          {"alpha3-b": "cos", "alpha2": "co", "English": "Corsican"},
+          {"alpha3-b": "cre", "alpha2": "cr", "English": "Cree"},
+          {"alpha3-b": "cze", "alpha2": "cs", "English": "Czech"},
+          {"alpha3-b": "dan", "alpha2": "da", "English": "Danish"},
+          {"alpha3-b": "div", "alpha2": "dv", "English": "Divehi; Dhivehi; Maldivian"},
+          {"alpha3-b": "dut", "alpha2": "nl", "English": "Dutch; Flemish"},
+          {"alpha3-b": "dzo", "alpha2": "dz", "English": "Dzongkha"},
+          {"alpha3-b": "eng", "alpha2": "en", "English": "English"},
+          {"alpha3-b": "epo", "alpha2": "eo", "English": "Esperanto"},
+          {"alpha3-b": "est", "alpha2": "et", "English": "Estonian"},
+          {"alpha3-b": "ewe", "alpha2": "ee", "English": "Ewe"},
+          {"alpha3-b": "fao", "alpha2": "fo", "English": "Faroese"},
+          {"alpha3-b": "fij", "alpha2": "fj", "English": "Fijian"},
+          {"alpha3-b": "fin", "alpha2": "fi", "English": "Finnish"},
+          {"alpha3-b": "fre", "alpha2": "fr", "English": "French"},
+          {"alpha3-b": "fry", "alpha2": "fy", "English": "Western Frisian"},
+          {"alpha3-b": "ful", "alpha2": "ff", "English": "Fulah"},
+          {"alpha3-b": "geo", "alpha2": "ka", "English": "Georgian"},
+          {"alpha3-b": "ger", "alpha2": "de", "English": "German"},
+          {"alpha3-b": "gla", "alpha2": "gd", "English": "Gaelic; Scottish Gaelic"},
+          {"alpha3-b": "gle", "alpha2": "ga", "English": "Irish"},
+          {"alpha3-b": "glg", "alpha2": "gl", "English": "Galician"},
+          {"alpha3-b": "glv", "alpha2": "gv", "English": "Manx"},
+          {"alpha3-b": "gre", "alpha2": "el", "English": "Greek, Modern (1453-)"},
+          {"alpha3-b": "grn", "alpha2": "gn", "English": "Guarani"},
+          {"alpha3-b": "guj", "alpha2": "gu", "English": "Gujarati"},
+          {"alpha3-b": "hat", "alpha2": "ht", "English": "Haitian; Haitian Creole"},
+          {"alpha3-b": "hau", "alpha2": "ha", "English": "Hausa"},
+          {"alpha3-b": "heb", "alpha2": "he", "English": "Hebrew"},
+          {"alpha3-b": "her", "alpha2": "hz", "English": "Herero"},
+          {"alpha3-b": "hin", "alpha2": "hi", "English": "Hindi"},
+          {"alpha3-b": "hmo", "alpha2": "ho", "English": "Hiri Motu"},
+          {"alpha3-b": "hrv", "alpha2": "hr", "English": "Croatian"},
+          {"alpha3-b": "hun", "alpha2": "hu", "English": "Hungarian"},
+          {"alpha3-b": "ibo", "alpha2": "ig", "English": "Igbo"},
+          {"alpha3-b": "ice", "alpha2": "is", "English": "Icelandic"},
+          {"alpha3-b": "ido", "alpha2": "io", "English": "Ido"},
+          {"alpha3-b": "iii", "alpha2": "ii", "English": "Sichuan Yi; Nuosu"},
+          {"alpha3-b": "iku", "alpha2": "iu", "English": "Inuktitut"},
+          {"alpha3-b": "ile", "alpha2": "ie", "English": "Interlingue; Occidental"},
+          {"alpha3-b": "ina", "alpha2": "ia", "English": "Interlingua (International Auxiliary Language Association)"},
+          {"alpha3-b": "ind", "alpha2": "id", "English": "Indonesian"},
+          {"alpha3-b": "ipk", "alpha2": "ik", "English": "Inupiaq"},
+          {"alpha3-b": "ita", "alpha2": "it", "English": "Italian"},
+          {"alpha3-b": "jav", "alpha2": "jv", "English": "Javanese"},
+          {"alpha3-b": "jpn", "alpha2": "ja", "English": "Japanese"},
+          {"alpha3-b": "kal", "alpha2": "kl", "English": "Kalaallisut; Greenlandic"},
+          {"alpha3-b": "kan", "alpha2": "kn", "English": "Kannada"},
+          {"alpha3-b": "kas", "alpha2": "ks", "English": "Kashmiri"},
+          {"alpha3-b": "kau", "alpha2": "kr", "English": "Kanuri"},
+          {"alpha3-b": "kaz", "alpha2": "kk", "English": "Kazakh"},
+          {"alpha3-b": "khm", "alpha2": "km", "English": "Central Khmer"},
+          {"alpha3-b": "kik", "alpha2": "ki", "English": "Kikuyu; Gikuyu"},
+          {"alpha3-b": "kin", "alpha2": "rw", "English": "Kinyarwanda"},
+          {"alpha3-b": "kir", "alpha2": "ky", "English": "Kirghiz; Kyrgyz"},
+          {"alpha3-b": "kom", "alpha2": "kv", "English": "Komi"},
+          {"alpha3-b": "kon", "alpha2": "kg", "English": "Kongo"},
+          {"alpha3-b": "kor", "alpha2": "ko", "English": "Korean"},
+          {"alpha3-b": "kua", "alpha2": "kj", "English": "Kuanyama; Kwanyama"},
+          {"alpha3-b": "kur", "alpha2": "ku", "English": "Kurdish"},
+          {"alpha3-b": "lao", "alpha2": "lo", "English": "Lao"},
+          {"alpha3-b": "lat", "alpha2": "la", "English": "Latin"},
+          {"alpha3-b": "lav", "alpha2": "lv", "English": "Latvian"},
+          {"alpha3-b": "lim", "alpha2": "li", "English": "Limburgan; Limburger; Limburgish"},
+          {"alpha3-b": "lin", "alpha2": "ln", "English": "Lingala"},
+          {"alpha3-b": "lit", "alpha2": "lt", "English": "Lithuanian"},
+          {"alpha3-b": "ltz", "alpha2": "lb", "English": "Luxembourgish; Letzeburgesch"},
+          {"alpha3-b": "lub", "alpha2": "lu", "English": "Luba-Katanga"},
+          {"alpha3-b": "lug", "alpha2": "lg", "English": "Ganda"},
+          {"alpha3-b": "mac", "alpha2": "mk", "English": "Macedonian"},
+          {"alpha3-b": "mah", "alpha2": "mh", "English": "Marshallese"},
+          {"alpha3-b": "mal", "alpha2": "ml", "English": "Malayalam"},
+          {"alpha3-b": "mao", "alpha2": "mi", "English": "Maori"},
+          {"alpha3-b": "mar", "alpha2": "mr", "English": "Marathi"},
+          {"alpha3-b": "may", "alpha2": "ms", "English": "Malay"},
+          {"alpha3-b": "mlg", "alpha2": "mg", "English": "Malagasy"},
+          {"alpha3-b": "mlt", "alpha2": "mt", "English": "Maltese"},
+          {"alpha3-b": "mon", "alpha2": "mn", "English": "Mongolian"},
+          {"alpha3-b": "nau", "alpha2": "na", "English": "Nauru"},
+          {"alpha3-b": "nav", "alpha2": "nv", "English": "Navajo; Navaho"},
+          {"alpha3-b": "nbl", "alpha2": "nr", "English": "Ndebele, South; South Ndebele"},
+          {"alpha3-b": "nde", "alpha2": "nd", "English": "Ndebele, North; North Ndebele"},
+          {"alpha3-b": "ndo", "alpha2": "ng", "English": "Ndonga"},
+          {"alpha3-b": "nep", "alpha2": "ne", "English": "Nepali"},
+          {"alpha3-b": "nno", "alpha2": "nn", "English": "Norwegian Nynorsk; Nynorsk, Norwegian"},
+          {"alpha3-b": "nob", "alpha2": "nb", "English": "Bokmål, Norwegian; Norwegian Bokmål"},
+          {"alpha3-b": "nor", "alpha2": "no", "English": "Norwegian"},
+          {"alpha3-b": "nya", "alpha2": "ny", "English": "Chichewa; Chewa; Nyanja"},
+          {"alpha3-b": "oci", "alpha2": "oc", "English": "Occitan (post 1500); Provençal"},
+          {"alpha3-b": "oji", "alpha2": "oj", "English": "Ojibwa"},
+          {"alpha3-b": "ori", "alpha2": "or", "English": "Oriya"},
+          {"alpha3-b": "orm", "alpha2": "om", "English": "Oromo"},
+          {"alpha3-b": "oss", "alpha2": "os", "English": "Ossetian; Ossetic"},
+          {"alpha3-b": "pan", "alpha2": "pa", "English": "Panjabi; Punjabi"},
+          {"alpha3-b": "per", "alpha2": "fa", "English": "Persian"},
+          {"alpha3-b": "pli", "alpha2": "pi", "English": "Pali"},
+          {"alpha3-b": "pol", "alpha2": "pl", "English": "Polish"},
+          {"alpha3-b": "por", "alpha2": "pt", "English": "Portuguese"},
+          {"alpha3-b": "pus", "alpha2": "ps", "English": "Pushto; Pashto"},
+          {"alpha3-b": "que", "alpha2": "qu", "English": "Quechua"},
+          {"alpha3-b": "roh", "alpha2": "rm", "English": "Romansh"},
+          {"alpha3-b": "rum", "alpha2": "ro", "English": "Romanian; Moldavian; Moldovan"},
+          {"alpha3-b": "run", "alpha2": "rn", "English": "Rundi"},
+          {"alpha3-b": "rus", "alpha2": "ru", "English": "Russian"},
+          {"alpha3-b": "sag", "alpha2": "sg", "English": "Sango"},
+          {"alpha3-b": "san", "alpha2": "sa", "English": "Sanskrit"},
+          {"alpha3-b": "sin", "alpha2": "si", "English": "Sinhala; Sinhalese"},
+          {"alpha3-b": "slo", "alpha2": "sk", "English": "Slovak"},
+          {"alpha3-b": "slv", "alpha2": "sl", "English": "Slovenian"},
+          {"alpha3-b": "sme", "alpha2": "se", "English": "Northern Sami"},
+          {"alpha3-b": "smo", "alpha2": "sm", "English": "Samoan"},
+          {"alpha3-b": "sna", "alpha2": "sn", "English": "Shona"},
+          {"alpha3-b": "snd", "alpha2": "sd", "English": "Sindhi"},
+          {"alpha3-b": "som", "alpha2": "so", "English": "Somali"},
+          {"alpha3-b": "sot", "alpha2": "st", "English": "Sotho, Southern"},
+          {"alpha3-b": "spa", "alpha2": "es", "English": "Spanish; Castilian"},
+          {"alpha3-b": "srd", "alpha2": "sc", "English": "Sardinian"},
+          {"alpha3-b": "srp", "alpha2": "sr", "English": "Serbian"},
+          {"alpha3-b": "ssw", "alpha2": "ss", "English": "Swati"},
+          {"alpha3-b": "sun", "alpha2": "su", "English": "Sundanese"},
+          {"alpha3-b": "swa", "alpha2": "sw", "English": "Swahili"},
+          {"alpha3-b": "swe", "alpha2": "sv", "English": "Swedish"},
+          {"alpha3-b": "tah", "alpha2": "ty", "English": "Tahitian"},
+          {"alpha3-b": "tam", "alpha2": "ta", "English": "Tamil"},
+          {"alpha3-b": "tat", "alpha2": "tt", "English": "Tatar"},
+          {"alpha3-b": "tel", "alpha2": "te", "English": "Telugu"},
+          {"alpha3-b": "tgk", "alpha2": "tg", "English": "Tajik"},
+          {"alpha3-b": "tgl", "alpha2": "tl", "English": "Tagalog"},
+          {"alpha3-b": "tha", "alpha2": "th", "English": "Thai"},
+          {"alpha3-b": "tib", "alpha2": "bo", "English": "Tibetan"},
+          {"alpha3-b": "tir", "alpha2": "ti", "English": "Tigrinya"},
+          {"alpha3-b": "ton", "alpha2": "to", "English": "Tonga (Tonga Islands)"},
+          {"alpha3-b": "tsn", "alpha2": "tn", "English": "Tswana"},
+          {"alpha3-b": "tso", "alpha2": "ts", "English": "Tsonga"},
+          {"alpha3-b": "tuk", "alpha2": "tk", "English": "Turkmen"},
+          {"alpha3-b": "tur", "alpha2": "tr", "English": "Turkish"},
+          {"alpha3-b": "twi", "alpha2": "tw", "English": "Twi"},
+          {"alpha3-b": "uig", "alpha2": "ug", "English": "Uighur; Uyghur"},
+          {"alpha3-b": "ukr", "alpha2": "uk", "English": "Ukrainian"},
+          {"alpha3-b": "urd", "alpha2": "ur", "English": "Urdu"},
+          {"alpha3-b": "uzb", "alpha2": "uz", "English": "Uzbek"},
+          {"alpha3-b": "ven", "alpha2": "ve", "English": "Venda"},
+          {"alpha3-b": "vie", "alpha2": "vi", "English": "Vietnamese"},
+          {"alpha3-b": "vol", "alpha2": "vo", "English": "Volapük"},
+          {"alpha3-b": "wel", "alpha2": "cy", "English": "Welsh"},
+          {"alpha3-b": "wln", "alpha2": "wa", "English": "Walloon"},
+          {"alpha3-b": "wol", "alpha2": "wo", "English": "Wolof"},
+          {"alpha3-b": "xho", "alpha2": "xh", "English": "Xhosa"},
+          {"alpha3-b": "yid", "alpha2": "yi", "English": "Yiddish"},
+          {"alpha3-b": "yor", "alpha2": "yo", "English": "Yoruba"},
+          {"alpha3-b": "zha", "alpha2": "za", "English": "Zhuang; Chuang"},
+          {"alpha3-b": "zul", "alpha2": "zu", "English": "Zulu"}
+      ]
+    end
+  end
+end

data/app/helpers/vaultify/application_helper.rb

@@ -0,0 +1,4 @@
+module Vaultify
+  module ApplicationHelper
+  end
+end

data/app/helpers/vaultify/edtf_helper.rb

@@ -0,0 +1,126 @@
+module Vaultify
+
+  module EdtfHelper
+
+    def scrub str
+      str.strip.downcase.gsub(/[\|,.\[\]'"]/, ' ').gsub(/(\d+)\s*(st|nd|rd|th)\b/, '\\1')
+    end
+
+    def clean_words str
+      cleaned_string = str.strip.downcase
+      months.each do |month, value|
+        cleaned_string = cleaned_string.gsub(Regexp.new(month), value)
+      end
+      seasons.each do |season, value|
+        cleaned_string = cleaned_string.gsub(Regexp.new(season), value)
+      end
+      descriptors.each do |descriptor, value|
+        cleaned_string = cleaned_string.gsub(Regexp.new(descriptor), value)
+      end
+      cleaned_string
+    end
+
+    def machine_clean str
+      clean_input = str.gsub(/open/, '*').gsub(/unknown/, '').gsub(/[^\du]u[^\du]/, '')
+      clean_input.gsub(/u/, 'X')
+    end
+
+    def clean_extra_words str
+      str.strip.gsub(/[a-z]/, '').gsub(/ +/, ' ')
+    end
+
+    def add_zeroes str
+      str.strip.gsub(/\b(\d)\b/, '0\\1').gsub(/\b([\dX][\dX][\dX])[^\dX]/, '\\1X')
+    end
+
+    def d4
+      '[\\dX][\\dX][\\dX][\\dX][?~]?'
+    end
+
+    def d2
+      '[\\dX][\\dX][?~]?'
+    end
+
+    def add_separators str
+
+      str.gsub(/([\dX?~])\s+([\dX?~])/, '\\1-\\2')
+          .gsub(' ', '').gsub(/([\dX?~])\/([\dX?~])/, '\\1-\\2')
+          .gsub(Regexp.new('(' + d2 + '-' + d4 + ')-(' + d2 + '-' + d4 + ')'), '\\1/\\2')
+          .gsub(Regexp.new('(' + d2 + '-' + d4 + ')-(' + d2 + '-' + d2 + '-' + d4 + ')'), '\\1/\\2')
+          .gsub(Regexp.new('(' + d4 + ')-(' + d4 + ')'), '\\1/\\2')
+          .gsub(Regexp.new('(' + d4 + '-' + d2 + ')-(' + d4 + ')'), '\\1/\\2')
+          .gsub(Regexp.new('(' + d4 + '-' + d2 + '-' + d2 + ')-(' + d4 + ')'), '\\1/\\2')
+    end
+
+    def arrange str
+      if Regexp.new(d4 + '-' + d2 + '-' + d2, 'g').match(str)
+        str
+      elsif Regexp.new(d2 + '-' + d2 + '-' + d4, 'g').match(str)
+        str.gsub(Regexp.new('(' + d2 + ')-(' + d2 + ')-(' + d4 + ')'), '\\3-\\2-\\1')
+      elsif Regexp.new(d2 + '-' + d4 + '-' + d2, 'g').match(str)
+        str.gsub(Regexp.new('(' + d2 + ')-(' + d4 + ')-(' + d2 + ')'), '\\2-\\1-\\3')
+      elsif Regexp.new(d4 + '-' + d2, 'g').match(str)
+        str
+      elsif Regexp.new(d2 + '-' + d4, 'g').match(str)
+        str.gsub(Regexp.new('(' + d2 + ')-(' + d4 + ')'), '\\2-\\1')
+      else
+        str
+      end
+    end
+
+    def rearrange str
+      if str.include? '/'
+        split_string = str.split('/')
+        arrange(split_string[0]) + '/' + arrange(split_string[1])
+      else
+        arrange(str)
+      end
+    end
+
+    def dirty str
+      clean_input = str.gsub(/^\*|\*$/, 'open').gsub(/^\//, 'unknown/').gsub(/\/$/, '/unknown')
+      clean_input.gsub(/X/, 'u')
+    end
+
+    def convert_date input
+      return input if Date.edtf(input)
+      clean_date = clean_extra_words(machine_clean(clean_words(scrub(input))))
+      clean_date = dirty(rearrange(add_separators(add_zeroes(clean_date))))
+      Date.edtf(clean_date) ? clean_date : nil
+    end
+
+    def months
+      {
+          'january|jan' => '01',
+          'february|feb' => '02',
+          'march|mar' => '03',
+          'april|apr' => '04',
+          'may' => '05',
+          'june|jun' => '06',
+          'july|jul' => '07',
+          'august|aug' => '08',
+          'september|sep' => '09',
+          'october|oct' => '10',
+          'november|nov' => '11',
+          'december|dec' => '12'
+      }
+    end
+
+    def seasons
+      {
+          'spring|spr' => '21',
+          'summer|summ|sum' => '22',
+          'autumn|aut|fall|fal' => '23',
+          'winter|wint|win' => '24'
+      }
+    end
+
+    def descriptors
+      {
+          '(\\d.*)to(.*\\d)' => '\\1/\\2',
+          '\\s*(around|about|abt|estimated|est|circa|approximately|approx)\\s*' => '~'
+      }
+    end
+
+  end
+end