import speling.py

def misspell():  """returns a list of words which appear in Bush's speech but are not in our dictionary"""
    import re
    set_dictionary('dict.txt')
    input = open('input.txt')
    input = input.read()                       #input is now a string of words
    pat = re.compile('[\n(--).,?";!:/$1234567890]')   
    input = pat.sub(' ', input)                #input is now stripped of punctuation marks
    pat = re.compile('[.]')              #for words like U.S.
    input = pat.sub('', input)
    pat = re.compile('[1234567890]*\\w*]')       #for words like 20th
    input = pat.sub('', input)
    input = input.split()                      #input is now a sequence/list of words
    misspelled = []                            #misspelled is the list of misspelled words
    index = spellcheck_text(input, index)  #index is the index of the next misspelled word

    while index !=-1:                          #as long as there is one more misspelled word
        misspelled.insert(0, input[index])     #add the misspelled word into the misspelled words list 
	index = spellcheck_text(input, index + 1) #obtain the index of the next misspelled word

    misspelled.sort()
    misspelled = count(misspelled)            #misspelled is a dictionary of keys (words) and values (occurences)
    sortedmisspelled = []      
    for key in misspelled.keys():
        sortedmisspelled.append(key + ' (' + str(misspelled[key]) + ')' )   #formats the list of words and values
    sortedmisspelled.sort()                   #sorts the lists of words and values
    for element in sortedmisspelled:          #prints each word and its value on its own line
        print element
	print '\n'