Uhmmmm... bueno aquí coloco el código con las pequeñas modificaciones que he
hecho para probar:
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import re, collections
def words(text):
text.lower()
return re.findall('\w+', 'í'.decode('utf-8'), re.UNICODE) #Para probar
si reconoce las palabras con 'í'
def train(features):
model = collections.defaultdict(lambda: 1)
for f in features:
model[f] += 1
return model
NWORDS = train(words(file('Diccionario.txt').read()))
alphabet = 'abcdefghijklmnopqrstuvwxyz'
def edits1(word):
splits = [(word[:i], word[i:]) for i in range(len(word) + 1)]
deletes = [a + b[1:] for a, b in splits if b]
transposes = [a + b[1] + b[0] + b[2:] for a, b in splits if len(b)>1]
replaces = [a + c + b[1:] for a, b in splits for c in alphabet if b]
inserts = [a + c + b for a, b in splits for c in alphabet]
return set(deletes + transposes + replaces + inserts)
def known_edits2(word):
return set(e2 for e1 in edits1(word) for e2 in edits1(e1) if e2 in
NWORDS)
def known(words): return set(w for w in words if w in NWORDS)
def correct(word):
candidates = known([word]) or known(edits1(word)) or known_edits2(word)
or [word]
key=NWORDS.get
print candidates
print key
if __name__=='__main__':
word= raw_input('Palabra en español: ')
correct(word)
Y esta es la salida:
Palabra en español: día
['d\xc3\xada']
<built-in method get of collections.defaultdict object at 0xb773f89c>
Y según lo que me explica Rolando no debería ser así verdad? :(...
Diccionario.txt no está en utf-8.
No tengo mucha experiencia con esto :(... qué puedo hacer?
Gracias! :)
_______________________________________________
Python-es mailing list
Python-es@python.org
http://mail.python.org/mailman/listinfo/python-es
FAQ: http://python-es-faq.wikidot.com/
