module StringExtensions
  def words
    s = self.dup
    s.gsub!(/\w+/, 'X')
    s.gsub!(/\W+/, '')
    s.length
  end
end

'some string here'.gsub(/\b\w/){$&.upcase}

def shorten (string, count = 30)
	if string.length >= count 
		shortened = string[0, count]
		splitted = shortened.split(/\s/)
		words = splitted.length
		splitted[0, words-1].join(" ") + ' ...'
	else 
		string
	end
end

DICT_PATH = '/usr/share/dict/words'
DICT_SIZE = 234936

def self.generated_name words = 2, length = 23
  name = 'a'*(length+1)
  while name.length > length
    name = (1..words).map{%x[sed -n '#{rand(DICT_SIZE)} {p;q;}' '#{DICT_PATH}'].chomp.capitalize}.join
  end
end

module Main
where

import List
import Control.Arrow

type Comparator a = (a -> a -> Ordering)

ascending :: (Ord a) => (b -> a) -> Comparator b
ascending f x y = compare (f x) (f y)

descending :: (Ord a) => (b -> a) -> Comparator b
descending = flip . ascending

secondary :: Comparator a -> Comparator a -> Comparator a
secondary f g x y = case f x y of {
                    EQ -> g x y;
                    z  -> z; }

-- Returns a list of unique elements together with their frequency. Listed in decreasing order of frequency, followed by
increasing order of the elements.
count :: (Ord a) => [a] -> [(a, Int)]
count = map (head &&& length) . sortBy (descending length `secondary` ascending head) . group . sort

main :: IO ()
main = interact $ unlines . map (\(x, y) -> (take 20 $ x ++ repeat ' ')  ++ " : " ++ show y) . count . words

# Detect stop words QUICKLY
# Uses a bloom filter instead of searching literally through a list of stopwords
# for > 3x speed increase
# 
#    using bloom filter: 2.580000   0.030000   2.610000 (  2.698829)
#  using literal search: 7.850000   0.120000   7.970000 (  8.181684)


require 'bloominsimple'
require 'digest/sha1'
require 'pp'

# Create a simple bloom filter that uses a SHA1 hash (more effective than BloominSimple's default hashing)
b = BloominSimple.new(50000) do |word|
  Digest::SHA1.digest(word.downcase.strip).unpack("VVV")
end

# Add stopwords to the bloom filter!
stopwords = []
File.open('stopwords').each { |a| b.add(a); stopwords << a.downcase.strip }

# Read in a whole dictionary of regular words
words = File.open('/usr/share/dict/words').read.split.collect{|a| a.downcase.strip }

# Define two ways to detect stopwords for comparison..
using_filter = lambda { |word| b.includes?(word) }
using_array = lambda { |word| stopwords.include?(word.downcase.strip) }
techniques = [using_filter, using_array]

# Run stopword comparisons with both techniques
t = techniques.collect { |l| words.collect { |a| l[a] } }

# See how effective the bloom filter has been compared to the literal search
if t[0] == t[1]
  puts "GOOD"
else
  words.zip(t[0],t[1]).each do |x|
    puts x.first if x[1] != x[2]
  end
end

# Now do speed benchmarks..
techniques.each { |l| puts Benchmark.measure { words.each { |a| l[a] } } }

	words: func [
		"Returns block of object words, excluding self directive."
		object [object!] "Target object."
	][
	   next first object
	]

  def truncate_words(text, length = 30, end_string = ' …')
    words = text.split()
    words[0..(length-1)].join(' ') + (words.length > length ? end_string : '')
  end