From: William James <w_a_x_man@...>
Date: 2005-08-07T06:46:08+09:00
Subject: Re: STRING MANIPULATION: Marking syllables

basi wrote:
> How might one express the following syllabification rules:
>
> 1. A c(c)v sequence is a syllable if followed by a cv sequence
>
> pe.so (the dot indicates a syllable break)
> pra.da
>
> 2. A c(c)vc sequence is a syllable if followed by a c
>
> fal.do
> bran.di
>
> where:
> c = consonant
> v = vowel
> (c) = optional consonant

CC = {}
CC['v'] = '[aeiou]'
CC['c'] = '[^aeiou]'

class String
  # Convert rule like "c(c)vc.c" to a regular expression.
  def to_syllrule
    re = "^("
    self.scan( /\(?([cv.])(\)?)/ ) { |x|
      if "." == x[0]
        re << ")("
      else
        re << CC[ x[0] ]
        re << "?"  if ")" == x[1]
      end
    }
    Regexp.new( re + ".*)" )
  end
end

# Make a list of the rules as regular expressions.
rules = %w( c(c)v.cv  c(c)vc.c ).inject([]){|a,s| a<< s.to_syllrule }

%w( peso prada faldo brandi ).each { |word|
  rules.each { |re|
    if word =~ re
      puts $~.captures.join('.')
      break
    end
  }
}

-----------------
Output:

pe.so
pra.da
fal.do
bran.di