快捷導(dǎo)航

Python容錯的前綴樹實(shí)現(xiàn)中文糾錯

更新時(shí)間：2021年07月07日 15:31:27 作者：王大呀呀

本文使用 Python 實(shí)現(xiàn)了前綴樹，并且支持編輯距離容錯的查詢。文中通過示例代碼介紹的非常詳細(xì)，具有一定的參考價(jià)值，感興趣的小伙伴們可以參考一下

介紹

本文使用 Python 實(shí)現(xiàn)了前綴樹，并且支持編輯距離容錯的查詢。文中的前綴樹只存儲了三個(gè)分詞，格式為 (分詞字符串,頻率) ，如：('中海晉西園', 2)、('中海西園', 24)、('中南海', 4)，可以換成自己的文件進(jìn)行數(shù)據(jù)的替換。在查詢的時(shí)候要指定一個(gè)字符串和最大的容錯編輯距離。

實(shí)現(xiàn)

class Word:
    def __init__(self, word, freq):
        self.word = word
        self.freq = freq

class Trie:
    def __init__(self):
        self.root = LetterNode('')
        self.START = 3

    def insert(self, word, freq):
        self.root.insert(word, freq, 0)

    def findAll(self, query, maxDistance):
        suggestions = self.root.recommend(query, maxDistance, self.START)
        return sorted(set(suggestions), key=lambda x: x.freq)


class LetterNode:
    def __init__(self, char):
        self.REMOVE = -1
        self.ADD = 1
        self.SAME = 0
        self.CHANGE = 2
        self.START = 3
        self.pointers = []
        self.char = char
        self.word = None

    def charIs(self, c):
        return self.char == c

    def insert(self, word, freq, depth):
        if ' ' in word:
            word = [i for i in word.split(' ')]
        if depth < len(word):
            c = word[depth].lower()
            for next in self.pointers:
                if next.charIs(c):
                    return next.insert(word, freq, depth + 1)
            nextNode = LetterNode(c)
            self.pointers.append(nextNode)
            return nextNode.insert(word, freq, depth + 1)
        else:
            self.word = Word(word, freq)

    def recommend(self, query, movesLeft, lastAction):
        suggestions = []
        length = len(query)

        if length >= 0 and movesLeft - length >= 0 and self.word:
            suggestions.append(self.word)

        if movesLeft == 0 and length > 0:
            for next in self.pointers:
                if next.charIs(query[0]):
                    suggestions += next.recommend(query[1:], movesLeft, self.SAME)
                    break

        elif movesLeft > 0:
            for next in self.pointers:
                if length > 0:
                    if next.charIs(query[0]):
                        suggestions += next.recommend(query[1:], movesLeft, self.SAME)
                    else:
                        suggestions += next.recommend(query[1:], movesLeft - 1, self.CHANGE)
                        if lastAction != self.CHANGE and lastAction != self.REMOVE:
                            suggestions += next.recommend(query, movesLeft - 1, self.ADD)
                        if lastAction != self.ADD and lastAction != self.CHANGE:
                            if length > 1 and next.charIs(query[1]):
                                suggestions += next.recommend(query[2:], movesLeft - 1, self.REMOVE)
                            elif length > 2 and next.charIs(query[2]) and movesLeft == 2:
                                suggestions += next.recommend(query[3:], movesLeft - 2, self.REMOVE)
                else:
                    if lastAction != self.CHANGE and lastAction != self.REMOVE:
                        suggestions += next.recommend(query, movesLeft - 1, self.ADD)
        return suggestions



def buildTrieFromFile():
    trie = Trie()
    rows = [('中海晉西園', 2),('中海西園', 24),('中南海', 4)]
    for row in rows:
        trie.insert(row[0], int(row[1]))
    return trie


def suggestor(trie, s, maxDistance):
    if ' ' in s:
        s = [x for x in s.split(' ')]
    suggestions = trie.findAll(s, maxDistance)
    return [str(x.word) for x in suggestions]


if __name__ == "__main__":
    trie = buildTrieFromFile()
    r = suggestor(trie, '中海晉西園', 1)
    print(r)

分析