# L-7 MCS 275 Wed 27 Jan 2010 : wordswardict.py

# The file "war_of_the_worlds.txt" was downloaded from
# http://www.gutenberg.org/files/36/36.txt

book = "war_of_the_worlds.txt"

def word_count(name):
   """
   Opens the file with name and counts the
   number of words.  Anything that is separated
   by spaces is considered a word.
   """
   f = open(name,'r')
   cnt = 0
   while True:
      s = f.readline()
      if s =="": break
      L = s.split(' ')
      cnt = cnt + len(L)
   f.close()
   return cnt

def word_frequencies(name):
   """
   Returns a dictionary with the frequencies 
   of the words occurring on file with name.
   """
   f = open(name,'r')
   D = {}
   while True:
      s = f.readline()
      if s =="": break
      L = s.split(' ')
      for e in L:
         if D.has_key(e):
            D[e] = D[e] + 1
         else:
            D[e] = 1
   f.close()
   return D 

def frequencies_of_words(D):
   """
   Reverts the keys and values of the
   given dictionary D.
   Because several words may occur with
   the same frequency, the values are
   lists of words.
   """
   F = {}
   for k in D:
      if F.has_key(D[k]):
         F[D[k]].append(k)
      else:
         F[D[k]] = [k]
   return F

def main():
   """
   Analysis of words in a book.
   """
   cnt = word_count(book)
   print "words counted : ", cnt
   D = word_frequencies(book)
   print "number of different words :", len(D)
   # print "frequency table of words :", D
   F = frequencies_of_words(D)
   # print "words of most frequencies :", F
   L = F.items()
   L.sort(key=lambda e: e[0],reverse=True)
   print "words used more than 100 times :"
   for e in L:
      if e[0] < 100: break
      print e
   
main()