import re
from collections import Counter

#编辑距离为1的
def editer1(word):
    letters = 'abcdefghijklmnopqrstuvwxyz'
    splits = [(word[:i],word[i:]) for i in range(len(word) + 1) ]
    delete = [ L + R[1:] for L,R in splits if R]
    transtore = [ L + R[1] + R[0] + R[2:] for L,R in splits if len(R)>1]
    inserts = [ L + c + R for L,R in splits for c in letters]
    replaces = [ L + c + R[1:] for L,R in splits if R for c in letters]
    return set(delete + transtore + inserts + replaces)
#编辑距离为2的
def editer2(word):
    return set(e2 for e1 in editer1(word) for e2 in editer1(e1))

#读取文本
def loadData(filename):
    with open(filename) as file:
        text = file.read()
        data = re.findall(r'[a-z]+',text.lower())  #所有的字符
    return data
data = loadData('big.txt')
Words = Counter(data)

def know(words):  #找出words中所有在Words里面的词
    return set(word for word in words if word in Words)

#可能词的集合
def candicate(word):
    return (know([word]) or know(editer1(word)) or know(editer2(word)) or [word])

#词频
def p(word,N = sum(Words.values())):
    return Words[word] /float(N)

#找词频最大的
def correct(word):
    return max(candicate(word) ,key = p) #第一个是P所需要的参数

#原理：查找与word相近的所有词，依次查找原词，or 编辑距离为1，or编辑距离为2，如果有原词，就不会查找距离为1，2的，如没有则查找距离为1的，统计距离为1的所有词在词汇表中出现的概率，选择最大的即为最有可能的词