class DidYouMean:
def __init__(self):
self.stemmer = Porter()
def specialhash(self, s):
s = s.lower()
s = s.replace("z", "s")
s = s.replace("h", "")
for i in [chr(ord("a") + i) for i in range(26)]:
s = s.replace(i+i, i)
s = self.stemmer.stem(s)
return s
class DidYouMean:
def __init__(self):
self.stemmer = Porter()
def specialhash(self, s):
s = s.lower()
s = s.replace("z", "s")
s = s.replace("h", "")
for i in [chr(ord("a") + i) for i in range(26)]:
s = s.replace(i + i, i)
s = self.stemmer.stem(s)
return s
def test(self, token):
hashed = self.specialhash(token)
if hashed in self.learned:
words = self.learned[hashed].items()
sortby(words, 1, reverse=1)
if token in [i[0] for i in words]:
return 'This word seems OK'
else:
if len(words) == 1:
return 'Did you mean "%s" ?' % words[0][0]
else:
return 'Did you mean "%s" ? (or %s)' \
% (words[0][0], ", ".join(['"'+i[0]+'"' \
for i in words[1:]]))
return "I can't found similar word in my learned db"
def learn(self, listofsentences=[], n=2000):
self.learned = defaultdict(mydict)
if listofsentences == []:
listofsentences = brown.raw()
for i, sent in enumerate(listofsentences):
if i >= n: # Limit to the first nth sentences of the corpus
break
for word in sent:
self.learned[self.specialhash(word)][word.lower()] += 1
def __init__(self):
self.stemmer = Porter()
def __init__(self): self.stemmer = Porter()
