二叉搜索树

1 为什么要使用二叉搜索树？

我们知道搜索算法有顺序搜索，二分搜索，还有散列表（也叫哈希表），而二叉搜索树是另一种搜索算法，利用二叉树的结构可以提高搜索效率。

2 二叉搜索树的性质

二叉搜索性：小于父节点的键都在左子树中，大于父节点的键则都在右子树中。左子树的所有键都小于根节点的键，右子树的所有键则都大于根节点的键。

3 代码实现

Python版本：
有两个类分别是BinarySearchTree和TreeNode。首先看看TreeNode，其提供了很多辅助函数，大大简化了BinarySearchTree类的工作。

# -*- coding: utf-8 -*-
"""
Created on Wed Sep 15 16:38:33 2021
@author: Ethan
"""
class TreeNode:
    def __init__(self, key, val, left=None, right=None, parent=None):
        self.key = key
        self.payload = val
        self.leftChild = left
        self.rightChild = right
        self.parent = parent
    
    ##返回当前节点的左子节点
    def hasLeftChild(self):
        return self.leftChild
    
    ##返回当前节点的右子节点
    def hasRightChild(self):
        return self.rightChild
    
    ##当前节点是左子节点
    def isLeftChild(self):
        return self.parent and self.parent.leftChild == self
    
    ##当前节点是右子节点
    def isRightChild(self):
        return self.parent and self.parent.rightChild == self
    
    ##判断是否为根节点
    def isRoot(self):
        return not self.parent
    
    ##判断是否为叶子节点
    def isLeaf(self):
        return not (self.leftChild or self.rightChild)
    
    ##判断是否有子节点
    def hasAnyChildren(self):
        return self.leftChild or self.rightChild
    
    ##判断是否有两个子节点
    def hasBothChildren(self):
        return self.leftChild and self.rightChild
    
    def replaceNodeData(self, key, val, lc, rc):
        self.key = key
        self.payload = val
        self.leftChild = lc
        self.rightChild = rc
        if self.hasLeftChild():
            self.leftChild.parent = self
        if self.hasRightChild():
            self.rightChild.parent = self
          
    def __iter__(self):
        if self:
            if self.hasLeftChild():
                for elem in self.leftChild:
                    yield elem
            yield self.key
            if self.hasRightChild():
                for elem in self.rightChild:
                    yield elem

然后就是BinarySearchTree类，采用的是节点与引用来实现的二叉搜索树

# -*- coding: utf-8 -*-
"""
Created on Wed Sep 15 15:48:08 2021
@author: Ethan
"""
from TreeNodeClass import TreeNode

class BinarySearchTree:
    def __init__(self):
        self.root = None
        self.size = 0
        
    def length(self):
        return self.size
    
    def __len__(self):
        return self.size
    
    def __iter__(self):
        return self.root.__iter__()
    
    ##往映射中加入一个新的键值对，如果键已经存在，就用新值替换旧值
    def put(self, key, val):
        if self.root == None: ##检查树是否有根节点，若没有，就创建一个TreeNode，并将其作为树的根节点
            self.root = TreeNode(key, val)
        else:  ##若树有根节点，调用私有的递归辅助函数_put在树中搜索
            self._put(key, val, self.root)  
        
        self.size = self.size + 1
        
    def _put(self, key, val, currentNode):
        if key < currentNode.key: ##比较新键与当前节点的键，若新键更小，搜索左子树
            if currentNode.hasLeftChild():
                self._put(key, val, currentNode.leftChild)
            else:  ##当没有可供搜索的左子节点时，就说明找到了新键的插入位置
                currentNode.leftChild = TreeNode(key, val, parent=currentNode)
        else:      ##若新键更小，搜索右子树
            if currentNode.hasRightChild():
                self._put(key, val, currentNode.rightChild)
            else:  ##当没有可供搜索的右子节点时，就说明找到了新键的插入位置
                currentNode.rightChild = TreeNode(key, val, parent=currentNode)
          
    ##调用put方法重载[]运算符
    def __setitem__(self, k, v):
        self.put(k, v)
        
    ##返回key对应的值，如果key不存在，则返回None
    def get(self, key):
        if self.root == None:
            return None
        else:
            ret = self._get(key, self.root)
            if ret!=None:
                return ret.payload
            else:
                return None
            
    def _get(self, key, currentNode):
        if not currentNode:
            return None
        elif currentNode.key == key:
            return currentNode
        elif key < currentNode.key:
            return self._get(key, currentNode.leftChild)
        else:
            return self._get(key, currentNode.rightChild)
    
    ##调用get方法重载[]运算符    
    def __getitem__(self, key):
        return self.get(key)
    
    ##实现in操作
    def __contains__(self, key):
        if self._get(key, self.root):
            return True
        else:
            return False
        
    ##删除键值对
    def delete(self, key):
        if self.size > 1:
            nodeToRemove = self._get(key, self.root)
            if nodeToRemove != None:
                self.remove(nodeToRemove)
                self.size = self.size - 1
            else:
                raise KeyError('Error, key not in trre')
        elif self.size == 1 and self.root.key == key:
            self.root = None
            self.size = self.size - 1
        else:
            raise KeyError('Error, key not in trre')
            
    def __delitem__(self, key):
        self.delete(key)
      
    
    def remove(self, currentNode):
        if currentNode.isLeaf(): ##当前节点为叶子节点
            if currentNode == currentNode.parent.leftChild:
                currentNode.parent.leftChild = None
            else:
                currentNode.parent.rightChild = None
        elif currentNode.hasBothChildren(): ##当前节点有两个子节点
            succ = currentNode.findSuccessor()
            succ.spliceOut()
            currentNode.key = succ.key
            currentNode.payload = succ.payload
        else: ##当前节点只有一个子节点
            if currentNode.hasLeftChild():  ##当前节点有左子节点
                if currentNode.isLeftChild(): ##当前节点是左子节点
                    currentNode.leftChild.parent = currentNode.parent
                    currentNode.parent.leftChild = currentNode.leftChild
                elif currentNode.isRightChild(): ##当前节点是右子节点
                    currentNode.leftChild.parent = currentNode.parent
                    currentNode.parent.rightChild = currentNode.leftChild
                else:  ##当前节点是根节点
                    currentNode.replaceNodeData(currentNode.leftChild.key, currentNode.leftChild.payload, 
                                                currentNode.leftChild.leftChild, currentNode.rightChild.rightChild)
            else:   ##当前节点有左子节点
                if currentNode.isLeftChild():  ##当前节点是左子节点
                    currentNode.rightChild.parent = currentNode.parent
                    currentNode.parent.leftChild = currentNode.rightChild
                elif currentNode.isRightChild():   ##当前节点是右子节点
                    currentNode.rightChild.parent = currentNode.parent
                    currentNode.parent.rightChild = currentNode.rightChild
                else:  ##当前节点是根节点
                    currentNode.replaceNodeData(currentNode.rightChild.key, currentNode.rightChild.payload, 
                                                currentNode.rightChild.leftChild, currentNode.rightChild.rightChild)
    ##寻找后继节点              
    def findSuccessor(self):
        succ = None
        if self.hasRightChild():
            succ = self.rightChild.findMin()
        else:
            if self.parent:
                if self.isLeftChild():
                    succ = self.parent
                else:
                    self.parent.rightChild = None
                    succ = self.parent.findSuccessor()
                    self.parent.rihgtChild = self
        return succ
         
    def findMin(self):
        current = self
        while current.hasLeftChild():
            current = current.leftChild
        return current
    
    def spliceOut(self):
        if self.isleaf():
            if self.isLeftChild():
                self.parent.leftChild = None
            else:
                self.parent.rightChild = None
        elif self.hasAnyChildren():
            if self.hasLeftChild():
                if self.isLeftChild():
                    self.parent.leftChild = self.leftChild
                else:
                    self.parent.rightChild = self.leftChild
                self.leftChild.parent = self.parent
            else:
                if self.isLeftChild():
                    self.parent.leftChild = self.rightChild
                else:
                    self.parent.rightChild = self.rightChild
                self.rightChild .parent = self.parent
    
if __name__ == "__main__":
    bst = BinarySearchTree()
    bst.put(5, 8)
    print(len(bst))
    print(bst.get(5))
    print(bst.get(4))

4 参考资料

《Python数据结构与算法分析》