Class: Numerizer

Inherits:
Object
  • Object
show all
Defined in:
lib/numerizer.rb

Constant Summary collapse

DIRECT_NUMS = 
[
  ['eleven', '11'],
  ['twelve', '12'],
  ['thirteen', '13'],
  ['fourteen', '14'],
  ['fifteen', '15'],
  ['sixteen', '16'],
  ['seventeen', '17'],
  ['eighteen', '18'],
  ['nineteen', '19'],
  ['ninteen', '19'], # Common mis-spelling
  ['zero', '0'],
  ['ten', '10'],
  ['\ba[\b^$]', '1'] # doesn't make sense for an 'a' at the end to be a 1
]
SINGLE_NUMS = 
[
  ['one', 1],
  ['two', 2],
  ['three', 3],
  ['four', 4],
  ['five', 5],
  ['six', 6],
  ['seven', 7],
  ['eight', 8],
  ['nine', 9]
]
TEN_PREFIXES = 
[
  ['twenty', 20],
  ['thirty', 30],
  ['forty', 40],
  ['fourty', 40], # Common misspelling
  ['fifty', 50],
  ['sixty', 60],
  ['seventy', 70],
  ['eighty', 80],
  ['ninety', 90]
]
BIG_PREFIXES = 
[
  ['hundred', 100],
  ['thousand', 1000],
  ['million', 1_000_000],
  ['billion', 1_000_000_000],
  ['trillion', 1_000_000_000_000],
]
FRACTIONS = 
[
  ['half', 2],
  ['third(s)?', 3],
  ['fourth(s)?', 4],
  ['quarter(s)?', 4],
  ['fifth(s)?', 5],
  ['sixth(s)?', 6],
  ['seventh(s)?', 7],
  ['eighth(s)?', 8],
  ['nineth(s)?', 9],
]
SINGLE_ORDINALS = 
[
  ['first', 1],
  ['third', 3],
  ['fourth', 4],
  ['fifth', 5],
  ['sixth', 6],
  ['seventh', 7],
  ['eighth', 8],
  ['ninth', 9]
]
DIRECT_ORDINALS = 
[
  ['tenth', '10'],
  ['eleventh', '11'],
  ['twelfth', '12'],
  ['thirteenth', '13'],
  ['fourteenth', '14'],
  ['fifteenth', '15'],
  ['sixteenth', '16'],
  ['seventeenth', '17'],
  ['eighteenth', '18'],
  ['nineteenth', '19'],
  ['twentieth', '20'],
  ['thirtieth', '30'],
  ['fourtieth', '40'],
  ['fiftieth', '50'],
  ['sixtieth', '60'],
  ['seventieth', '70'],
  ['eightieth', '80'],
  ['ninetieth', '90']
]

Class Method Summary collapse

Class Method Details

.numerize(string) ⇒ Object 



109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
 
# File 'lib/numerizer.rb', line 109

def self.numerize(string)
  string = string.dup

  # preprocess
  string.gsub!(/ +|([^\d])-([^\d])/, '\1 \2') # will mutilate hyphenated-words

  # easy/direct replacements
  (DIRECT_NUMS + SINGLE_NUMS).each do |dn|
    string.gsub!(/(^|\W)#{dn[0]}(?=$|\W)/i, '\1<num>' + dn[1].to_s)
  end

  # ten, twenty, etc.
  TEN_PREFIXES.each do |tp|
    SINGLE_NUMS.each do |dn|
      string.gsub!(/(^|\W)#{tp[0]}#{dn[0]}(?=$|\W)/i, '\1<num>' + (tp[1] + dn[1]).to_s)
    end
    SINGLE_ORDINALS.each do |dn|
      string.gsub!(/(^|\W)#{tp[0]}(\s)?#{dn[0]}(?=$|\W)/i, '\1<num>' + (tp[1] + dn[1]).to_s + dn[0][-2, 2])
    end
    string.gsub!(/(^|\W)#{tp[0]}(?=$|\W)/i, '\1<num>' + tp[1].to_s)
  end

  # handle fractions
  FRACTIONS.each do |tp|
    string.gsub!(/a #{tp[0]}(?=$|\W)/i, '<num>1/' + tp[1].to_s)
    string.gsub!(/\s#{tp[0]}(?=$|\W)/i, '/' + tp[1].to_s)
  end

  (DIRECT_ORDINALS + SINGLE_ORDINALS).each do |on|
    string.gsub!(/(^|\W)#{on[0]}(?=$|\W)/i, '\1<num>' + on[1].to_s + on[0][-2, 2])
  end

  # evaluate fractions when preceded by another number
  string.gsub!(/(\d+)(?: | and |-)+(<num>|\s)*(\d+)\s*\/\s*(\d+)/i) { ($1.to_f + ($3.to_f/$4.to_f)).to_s }

  # hundreds, thousands, millions, etc.
  BIG_PREFIXES.each do |bp|
    string.gsub!(/(?:<num>)?(\d*) *#{bp[0]}/i) { $1.empty? ? bp[1] : '<num>' + (bp[1] * $1.to_i).to_s }
    andition(string)
  end

  andition(string)

  string.gsub(/<num>/, '')
end