Python中文纠错的简单实现

import re,pinyin
from Pinyin2Hanzi import DefaultDagParams
from Pinyin2Hanzi import dag

class corrector():
    def __init__(self):
        self.re_compile = re.compile(r'[\u4e00-\u9fff]')
        self.DAG = DefaultDagParams()

    # 将文件中的词读取
    def getData(self):
        words = []
        with open("/Users/wys/Desktop/token.txt") as f:
            for line in f.readlines():
                word = line.split(" ")[0]
                if word and len(word) > 2:
                    res = self.re_compile.findall(word)
                    if len(res) == len(word): ## 保证都是汉字组成的分词
                        words.append(word)
        return words

    # 将每个拼音转换成同音的 10 个候选汉字，
    def pinyin_2_hanzi(self, pinyinList):
        result = []
        words = dag(self.DAG, pinyinList, path_num=10)
        for item in words:
            res = item.path  # 转换结果
            result.append(res[0])
        return result

    # 获得词经过转换的候选结结果
    def getCandidates(self, phrase):
        chars = {}
        for c in phrase:
            chars[c] = self.pinyin_2_hanzi(pinyin.get(c, format='strip', delimiter=',').split(','))
        replaces = []
        for c in phrase:
            for x in chars[c]:
                replaces.append(phrase.replace(c, x))
        return set(replaces)

    # 获得纠错之后的正确结果
    def getCorrection(self, words):
        result = []
        for word in words:
            for word in self.getCandidates(word):
                if Tree.search(word):
                    result.append(word)
                    break
        return result

class Node:
    def __init__(self):
        self.word = False
        self.child = {}


class Trie(object):
    def __init__(self):
        self.root = Node()

    def insert(self, words):
        for word in words:
            cur = self.root
            for w in word:
                if w not in cur.child:
                    cur.child[w] = Node()
                cur = cur.child[w]

            cur.word = True

    def search(self, word):
        cur = self.root
        for w in word:
            if w not in cur.child:
                return False
            cur = cur.child[w]

        if cur.word == False:
            return False
        return True

if __name__ == '__main__':
    # 初始化纠正器
    c = corrector()
    # 获得单词
    words = c.getData()
    # 初始化前缀树
    Tree = Trie()
    # 将所有的单词都插入到前缀树中
    Tree.insert(words)
    # 测试
    print(c.getCorrection(['专塘街道','转塘姐道','转塘街到']))