def words(text):
    return re.findall('[a-z]+', text.lower())

def train(features):
    model = collections.defaultdict(lambda: 1)  # 如果默认为0则出现语料库中没有的新词会不识别，所以默认为1
    for f in features:
        model[f] += 1
    return model

NWORDS = train(words(open('data/big.txt').read()))
alphabet = 'abcdefghijklmnopqrstuvwxyz'

# 返回编辑距离为1的单词
def editsl(word):
    n = len(word)
    return set([word[0:i] + word[i + 1:] for i in range(n)] +  # 字母打多了一个
               [word[0:i] + word[i + 1] + word[i] + word[i + 2:] for i in range(n - 1)] +  # 字母打反了一个
               [word[0:i] + c + word[i + 1:] for i in range(n) for c in alphabet] +  # 字母打错了一个
               [word[0:i] + c + word[i:] for i in range(n + 1) for c in alphabet])  # 字母打少了一个

# 考虑编辑距离为2的单词
def known_edits2(word):
    return set(e2 for e1 in editsl(word) for e2 in editsl(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(editsl(word)) or known_edits2(word) or [word]
    return max(candidates, key=lambda w: NWORDS[w])

print(correct('appl'))
print(correct('appla'))
print(correct('learw'))
print(correct('tess'))
print(correct('morw'))