| 1 | import speling |
| 2 | |
| 3 | def tokenize(line): |
| 4 | """Takes each line and returns a list of all the words in that line |
| 5 | with the pronounciation stripped.""" |
| 6 | words = line.strip().split() |
| 7 | wordlist = [] |
| 8 | for word in words: |
| 9 | newword = stripPunctuation(word) |
| 10 | if isWord(newword): |
| 11 | wordlist.append(newword) |
| 12 | return wordlist |
| 13 | |
| 14 | |
| 15 | # Main Program |
| 16 | misspelled = {} |
| 17 | input = open('input.txt') |
| 18 | for line in input: |
| 19 | wordlist = tokenize(line) |
| 20 | for word in wordlist: |
| 21 | if not search(word): # word was not found in dictionary |
| 22 | if word in misspelled: |
| 23 | misspelled[word] = misspelled[word] + 1 |
| 24 | else: |
| 25 | misspelled[word] = 1 |
| 26 | # Print words and number of occurences in alphabetical order. |
| 27 | words = misspelled.keys() |
| 28 | words.sort() |
| 29 | for word in words: |
| 30 | print word + " (" + str(misspelled[word]) + ")" |