Descobre a estrutura de palavras de um texto.

sortedcoteiners-first.py

import sys
words = set()
plain_text = list()
codded_text= list()

# read content
plain_text = [l.strip().split() for l in sys.stdin]

# build a word list from content
for line in plain_text:
    [words.add(w) for w in line]

# set() don't have an index method, then use a list
words = list(words)

# build codded content
for line in plain_text:
    codded_text.append([words.index(w) for w in line])

# how many words?
print('Total of words:', len(words))