转载:http://norvig.com/spell-correct.html
第一次看到这篇文章,还是有些瑟瑟发抖的,不过仔细思考和阅读之后,发现这个功能还是比较容易实现的,就目前来说。同时也感谢作者对于知识的分享。
import re
from collections import Counter
def words(text): return re.findall(r'\w+', text.lower())
WORDS = Counter(words(open('big.txt').read()))
def P(word, N=sum(WORDS.values())):
"Probability of `word`."
return WORDS[word] / N
def correction(word):
"Most probable spelling correction for word."
return max(candidates(word), key=P)
def candidates(word):
"Generate possible spelling corrections for word."
return (known([word]) or known(edits1(word)) or known(edits2(word)) or [word])
def known(words):
"The subset of `words` that appear in the dictionary of WORDS."
return set(w for w in words if w in WORDS)
def edits1(word):
"All edits that are one edit away from `word`."
letters = 'abcdefghijklmnopqrstuvwxyz'
splits = [(word[:i], word[i:]) for i in range(len(word) + 1)]
deletes = [L + R[1:] for L, R in splits if R]
transposes = [L + R[1] + R[0] + R[2:] for L, R in splits if len(R)>1]
replaces = [L + c + R