Demonstrating ruby string extensions

string.rb

# -*- coding: utf-8 -*-
require 'digest/md5'
require 'set'

class String
  
  ARTICLES = Set.new [
    'a','an','and','by','for','in','is','of','not','on','or','over','the','to','under', 'with']
  
  
  def starts_with str
    return self[0...str.length] == str
  end
  
  
  def md5_sum
    return Digest::MD5.hexdigest(self)
  end
  
  
  #
  # A better titleize that creates a usable
  # title according to English grammar rules.
  #
  def titleize
    result = []
    
    for word in self.downcase.split(/[[:space:]]/) # handle unicode
      if result.empty? || (! ARTICLES.include? word)
        word = word.capitalize
      end
      result << word
    end
    
    return result.join(' ')
  end
  
  
  #
  # Replace my value with the titleized version.
  #
  def titleize!
    replace titleize
  end
  
  
  #
  # Enhance with typographic characters:
  #  Single quotes: ’
  #  Section sign:  §
  #  Double quotes: “”
  #
  def add_typography
    return self.gsub("'", "’").gsub(/\bSec\./, '§').gsub(/"([^"]+)"/, '“\1”')
  end
  

  #
  # Take text with potential encoding problems and 
  # aggressively make it safe for UTF-8 import.
  #
  def utf8_safe
    return self.encode('UTF-8', 'binary', invalid: :replace, undef: :replace, replace: '')
  end
  
end