Programa final com o sortedcontainers.

sortedcoteiners-final.py

import sys
import sortedcontainers

words = sortedcontainers.SortedSet()
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]

# in sortedcontainers, SortedSet have an index method :)
# build codded content
for line in plain_text:
    codded_text.append([words.index(w) for w in line])

# how many words?
print(len(words))