Class: Proso::Dictionary

Inherits:
Object
  • Object
show all
Includes:
Treat::Core::DSL
Defined in:
lib/proso.rb

Constant Summary collapse

SEMI_SCUDS = 
%w{a all am an and are as at be been but by can could dear did do does else for from get got had has have he her hers him his how i if in is it its just least let like may me might most must my no nor not of off on or our own said say says she should since so some than that the their them then there these they this tis to too twas us wants was we went were what when where which while who whom why will with would yet you your}

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize ⇒ Dictionary 



11
12
13
 
# File 'lib/proso.rb', line 11

def initialize
  @dict = load_from_json(File.expand_path('../../data/cmudict.json', __FILE__))
end

Class Method Details

.serialize_cmudict(filepath) ⇒ Object 



21
22
23
24
25
26
27
28
29
30
31
 
# File 'lib/proso.rb', line 21

def self.serialize_cmudict(filepath)
  cmudict = File.open(filepath, 'r'){ |f| f.read }
  matches = cmudict.scan(/^([\w\d'-]+)(\(\d+\))?\s+([\w\d ]+)$/)
  dict = matches.inject({}) do |memo, e|
    memo[e[0]] = memo[e[0]] ? memo[e[0]] << e[2] : [e[2]]
    memo
  end
  File.open("#{filepath}", "w") do |f|
    f.write(dict.to_json)
  end
end

Instance Method Details

#attridgify(string) ⇒ Object 



69
70
71
72
73
74
75
76
77
78
79
80
81
82
 
# File 'lib/proso.rb', line 69

def attridgify(string)
  # Basically we coerce the stress pattern into the best plausible
  # Attridge beat/offbeat representation. This considers any number of
  # Attridge-permissible changes equally, so it won't differentiate between
  # the simplicity of the string's fulfillment of a metrical contract.
  string
    .gsub(/www/, 'oBo')
    .gsub(/sss/, 'BoB')
    .gsub(/^ss/, 'oB')
    .gsub(/s/, 'B')
    .gsub(/w/, 'o')
    .gsub(/BBB/, 'BoB')
    .gsub(/ooo/, 'oBo')
end

#inspect ⇒ Object 



33
34
35
 
# File 'lib/proso.rb', line 33

def inspect
  "#<Prosody::Dictionary:#{object_id}>"
end

#levenshtein_distance(s1, s2) ⇒ Object 



84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
 
# File 'lib/proso.rb', line 84

def levenshtein_distance(s1, s2)
  m = s1.length
  n = s2.length
  return m if n == 0
  return n if m == 0
  d = Array.new(m+1) {Array.new(n+1)}
  (0..m).each{ |i| d[i][0] = i }
  (0..n).each{ |j| d[0][j] = j } 
  (1..n).each do |j|
    (1..m).each do |i|
      d[i][j] = if s1[i-1] == s2[j-1]
                  d[i-1][j-1]
                else
                  [ d[i-1][j] +1,
                    d[i][j-1]+1,
                    d[i-1][j-1]+1
                  ].min
                end
    end
  end
  d[m][n]
end

#load_from_json(filepath) ⇒ Object 



15
16
17
18
19
 
# File 'lib/proso.rb', line 15

def load_from_json(filepath)
  File.open("#{filepath}", "r") do |f|
    JSON.parse(File.read(f))
  end
end

#stress_distance(string, meter) ⇒ Object 



37
38
39
40
41
42
43
44
45
 
# File 'lib/proso.rb', line 37

def stress_distance(string, meter)
  begin
    stresses(string)
      .map{ |s| levenshtein_distance(s, meter*(s.size / 2)) }.min
  rescue RuntimeError => e
    puts e
    return Float::INFINITY 
  end
end

#stresses(string) ⇒ Object 



52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
 
# File 'lib/proso.rb', line 52

def stresses(string)
  p = phrase(string)
    .do(:tokenize)
    .map(&:value)
    .reject{ |t| /[[:punct:]]/.match(t) }
    .map{ |t| token_stress(t) }
  first, *rest = *p
  combinations = first
    .product(*rest)
    .map(&:join)
    .map{ |t| t.gsub(/\D/, '') }
    .map{ |t| t.gsub(/[123]/, 's') }
    .map{ |t| t.gsub(/0/, 'w') }
    .map{ |t| attridgify(t) }
    .uniq
end

#token_stress(string) ⇒ Object 



47
48
49
50
 
# File 'lib/proso.rb', line 47

def token_stress(string)
  return ["0"] if SEMI_SCUDS.include? string.downcase
  @dict[string.upcase] or raise "No pronunciation entry for '#{string}'"
end