Question

我正在尝试使用trie数据结构实现拼写检查。我目前有一个Node的大纲：

class Node:
    def __init__(self):
        self.next = {}
        self.word_marker = False

    def add_item(self, string):
        #if the length of the string is 0 then return. When the end of the word 
        #comes set the word_marker to true
        if len(string) == 0:
            self.word_marker = True
            return
        #set the key to the first letter of the string and reformat the string to reflect the first letter taken out
        #ultimately going to store the letters for each node as the key
        key = string[0]
        string = string[1:]

        #if there is a key in the dictionary, then recursively call add_item with new string
        if key in self.next:
            self.next[key].add_item(string)

        else:
            node = Node()
            self.next[key] = node
            node.add_item(string)

我要做的下一件事是编写函数来搜索string，然后返回建议的拼写。（def correct(self, string)）。我如何通过这个特里来实现搜索？假设我已经通过定义根节点root向trie添加了单词列表，然后对列表中的每个单词使用add_item。

Answer 1

如果您还没有，可能需要查看Norvig的“How to Write a Spelling Corrector”

Answer 2

这里有一个与您的问题相关的答案：https://stackoverflow.com/a/11016430/793956。

还要考虑使用诸如的库 https://github.com/kmike/marisa-trie#readme或 https://github.com/kmike/datrie#readme

Answer 3

虽然不是直接的答案，但您可能希望从更加发达的Trie实现开始：

class Trie:

    def __init__(self):
        self.__final = False
        self.__nodes = {}

    def __repr__(self):
        return 'Trie<len={}, final={}>'.format(len(self), self.__final)

    def __getstate__(self):
        return self.__final, self.__nodes

    def __setstate__(self, state):
        self.__final, self.__nodes = state

    def __len__(self):
        return len(self.__nodes)

    def __bool__(self):
        return self.__final

    def __contains__(self, array):
        try:
            return self[array]
        except KeyError:
            return False

    def __iter__(self):
        yield self
        for node in self.__nodes.values():
            yield from node

    def __getitem__(self, array):
        return self.__get(array, False)

    def create(self, array):
        self.__get(array, True).__final = True

    def read(self):
        yield from self.__read([])

    def update(self, array):
        self[array].__final = True

    def delete(self, array):
        self[array].__final = False

    def prune(self):
        for key, value in tuple(self.__nodes.items()):
            if not value.prune():
                del self.__nodes[key]
        if not len(self):
            self.delete([])
        return self

    def __get(self, array, create):
        if array:
            head, *tail = array
            if create and head not in self.__nodes:
                self.__nodes[head] = Trie()
            return self.__nodes[head].__get(tail, create)
        return self

    def __read(self, name):
        if self.__final:
            yield name
        for key, value in self.__nodes.items():
            yield from value.__read(name + [key])

使用trie的Python拼写检查程序

3 个答案: