字典树

字符串集合常用字典树存储，这是一种字符串上的树形数据结构。字典树中每条边都对应一个字，从根节点往下的路径构成一个个字符串。字典树并不直接在节点上存储字符串，而是将词语视作根节点到某节点之间的一条路径，并在终点节点上做个标记“该节点对应词语的结尾”。字符串就是一条路径，要查询一个单词，只需要顺着这条路径从根节点往下走。如果能走到特殊标记的节点，则说明该字符串在集合中，否则说明不存在。

字典树的节点实现

class Node(object):
    def __init__(self, value) -> None:
        self._children = {}
        self._value = value

    def _add_child(self, char, value, overwrite=False):
        child = self._children.get(char)
        if child is None:
            child = Node(value)
            self._children[char] = child
        elif overwrite:
            child._value = value
        return child

字典树增删改查实现

“增删改查都是查”

class Node(object):
    def __init__(self, value) -> None:
        self._children = {}
        self._value = value

    def _add_child(self, char, value, overwrite=False):
        child = self._children.get(char)
        if child is None:
            child = Node(value)
            self._children[char] = child
        elif overwrite:
            child._value = value
        return child


class Trie(Node):
    def __init__(self) -> None:
        super().__init__(None)

    def __contains__(self, key):
        return self[key] is not None

    def __getitem__(self, key):
        state = self
        for char in key:
            state = state._children.get(char)
            if state is None:
                return None
        return state._value

    def __setitem__(self, key, value):
        state = self
        for i, char in enumerate(key):
            if i < len(key) - 1:
                state = state._add_child(char, None, False)
            else:
                state = state._add_child(char, value, True)


if __name__ == '__main__':
    trie = Trie()
    # 增

    trie['自然'] = 'nature'
    trie['自然人'] = 'human'
    trie['自然语言'] = 'language'
    trie['自语'] = 'talk	to oneself'
    trie['入门'] = 'introduction'
    assert '自然' in trie
    # 删
    trie['自然'] = None
    assert '自然' not in trie
    # 改
    trie['自然语言'] = 'human language'
    assert trie['自然语言'] == 'human language'
    # 查
    assert trie['入门'] == 'introduction'