哈希表
文章目录
概念
不经过任何比较,一次性从表中得到要搜索的元素
数组,通过哈希函数使得元素的存储位置与关键码建立一一映射关系
-
put:插入元素
- 根据key计算出存储位置存放value
-
get:搜索元素
- 根据key得到存储位置取出value
冲突:不同的关键字通过相同哈希函数得到相同哈希地址
避免冲突的方法
哈希函数设计
-
原则
- 定义域包括需要存储的全部关键码
- 地址能均匀分布在整个空间中
- 简单
-
常见函数
- 直接定址法
- 除留余数法
- 平方取中法
负载因子的调节
-
公式
- 负载因子α=表中的元素个数/散列表的长度
-
作用
- 表示散列表的装满程度,α越大,说明表中元素很多,产生冲突的概率较大
-
解决
- 当α过大时,就调节哈希表中的数组大小(即扩容),降低冲突率
解决冲突的方法
闭散列
- 线性探测
- 二次探测
开散列/哈希桶
- 具有相同地址的关键码归于同一子集合(桶),桶中的元素用链表连接,各链表的头节点保存在哈希表中
自主实现一个HashMap
get
- 根据key得到下标index
-
求出key的hashCode()
- 若key的K类型是自定义的,必须要覆写hashCode(),否则无法根据相同的key找到唯一的下标
- 让hash中的每一位都参与到找下标的过程,使得找到的下标尽可能均匀
-
利用hash得到合法的下标,前提是table.length必须是2的幂次方
- 使用下标找到链表的头节点的引用
- 在链表中,找到等于key的结点,返回该节点的value
- 若key的K类型是自定义的,必须要覆写类的equals方法,保证能判断相等
@Override
public V get(K key) {
//1.根据key得到下标
//1.1求出key的hashCode();
//若HashMap的K类型是自定义的类,必须要覆写hashCode(),否则无法根据相同的key找到唯一的下标
int hash = key.hashCode();
//让hash中的每一位都参与到找下标的过程,使得找到的下标,尽可能均匀
hash = (hash >>> 16) ^ hash;
//1.2利用hash得到合法的下标,前提是table.length 必须是 2 的幂次方
int index = hash & (table.length - 1);
//2.使用下标,找到链表的头节点的引用
MyEntry<K, V> head = table[index];
//3.在链表中,找到包含key的结点,返回该节点的value
MyEntry<K, V> node = head;
while (node != null) {
//使用了key的equals方法。
//如果使用自定义类作为HashMap的K,必须覆写类的equals方法,保证能判断是否相等
if (key.equals(node.key)) {
return node.value;
}
node = node.next;
}
return null;
}
put
-
根据key得到下标index
-
使用下标找到链表的头节点的引用
-
在链表中,找到等于key的结点,返回该节点的value
-
若链表遍历结束,未找到
- 新建结点,将结点尾插到链表中
- 表中的元素个数增加
-
计算负载因子是否超过阈值,超过则扩容
-
创建长度扩大的新数组,保证新数组的长度仍为2的幂次方
-
遍历表中的链表中的每一个元素
- 根据每个元素的key找到新下标
- 插入到链表中
-
替换掉旧的table
-
@Override
public V put(K key, V value) {
int hash = key.hashCode();
hash = (hash >>> 16) ^ hash;
int index = hash & (table.length - 1);
MyEntry<K, V> head = table[index];
MyEntry<K, V> node = head;
while (node != null) {
if (key.equals(node.key)) {
//修改旧值,返回旧值
V oldValue = node.value;
node.value = value;
return oldValue;
}
node = node.next;
}
//链表遍历结束,没有找到
//新建结点,并且把结点插入到链表中
MyEntry<K, V> entry = new MyEntry<>(key, value);
//考虑多线程的情况,使用尾插
if (head == null) {
table[index] = entry;
} else {
MyEntry<K, V> last = head;
while (last != null) {
last = last.next;
}
last.next = entry;
}
size++;
// 为了减少冲突率,所以需要考虑降低 size / table.length 的值
// 设定一个阈值,当 size / table.length 高于某个值时,进行扩容
// 所谓的扩容,就是保证 size 不变,让 table.length 变大
// 进而,使得 size / table.length 降低,进而减少冲突率
if (size * 1.0/table.length > LOADER_FACTOR_THRESHOLD) {
resize();
}
return null;
}
//扩容,需要
//1. 保证 table.length 仍然是 2 的幂次方
//2. 因为 table.length 变化了,所以 key 对象的下标一定会变化
//所以,需要把所有的 key,重新计算下标,重新插入
private void resize() {
//数组扩容
MyEntry<K, V>[] newTable = new MyEntry[table.length * 2];
for (int i = 0; i < table.length; i++) {
MyEntry<K, V> head = table[i];
MyEntry<K, V> node = head;
while (node != null) {
K key = node.key;
V value = node.value;
//利用key,找新的下标
int hash = key.hashCode();
hash = (hash >>> 16) ^ hash;
int index = hash & (newTable.length - 1);
//头插
MyEntry<K, V> entry = new MyEntry<>(key, value);
entry.next = newTable[index];
newTable[index] = entry;
node = node.next;
}
}
//替换掉旧的table
table = newTable;
}
源码
get
public V get(Object key) {
Node<K,V> e;
return (e = getNode(hash(key), key)) == null ? null : e.value;
}
/**
* Implements Map.get and related methods.
*
* @param hash hash for key
* @param key the key
* @return the node, or null if none
*/
final Node<K,V> getNode(int hash, Object key) {
Node<K,V>[] tab; Node<K,V> first, e; int n; K k;
if ((tab = table) != null && (n = tab.length) > 0 &&
(first = tab[(n - 1) & hash]) != null) {
if (first.hash == hash && // always check first node
((k = first.key) == key || (key != null && key.equals(k))))
return first;
if ((e = first.next) != null) {
if (first instanceof TreeNode)
return ((TreeNode<K,V>)first).getTreeNode(hash, key);
do {
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
return e;
} while ((e = e.next) != null);
}
}
return null;
}
put
/**
* Associates the specified value with the specified key in this map.
* If the map previously contained a mapping for the key, the old
* value is replaced.
*
* @param key key with which the specified value is to be associated
* @param value value to be associated with the specified key
* @return the previous value associated with {@code key}, or
* {@code null} if there was no mapping for {@code key}.
* (A {@code null} return can also indicate that the map
* previously associated {@code null} with {@code key}.)
*/
public V put(K key, V value) {
return putVal(hash(key), key, value, false, true);
}
/**
* Implements Map.put and related methods.
*
* @param hash hash for key
* @param key the key
* @param value the value to put
* @param onlyIfAbsent if true, don't change existing value
* @param evict if false, the table is in creation mode.
* @return previous value, or null if none
*/
final V putVal(int hash, K key, V value, boolean onlyIfAbsent,
boolean evict) {
Node<K,V>[] tab; Node<K,V> p; int n, i;
if ((tab = table) == null || (n = tab.length) == 0)
n = (tab = resize()).length;
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null);
else {
Node<K,V> e; K k;
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
e = p;
else if (p instanceof TreeNode)
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
else {
for (int binCount = 0; ; ++binCount) {
if ((e = p.next) == null) {
p.next = newNode(hash, key, value, null);
if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
treeifyBin(tab, hash);
break;
}
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
break;
p = e;
}
}
if (e != null) { // existing mapping for key
V oldValue = e.value;
if (!onlyIfAbsent || oldValue == null)
e.value = value;
afterNodeAccess(e);
return oldValue;
}
}
++modCount;
if (++size > threshold)
resize();
afterNodeInsertion(evict);
return null;
}
/**
* Initializes or doubles table size. If null, allocates in
* accord with initial capacity target held in field threshold.
* Otherwise, because we are using power-of-two expansion, the
* elements from each bin must either stay at same index, or move
* with a power of two offset in the new table.
*
* @return the table
*/
final Node<K,V>[] resize() {
Node<K,V>[] oldTab = table;
int oldCap = (oldTab == null) ? 0 : oldTab.length;
int oldThr = threshold;
int newCap, newThr = 0;
if (oldCap > 0) {
if (oldCap >= MAXIMUM_CAPACITY) {
threshold = Integer.MAX_VALUE;
return oldTab;
}
else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY &&
oldCap >= DEFAULT_INITIAL_CAPACITY)
newThr = oldThr << 1; // double threshold
}
else if (oldThr > 0) // initial capacity was placed in threshold
newCap = oldThr;
else { // zero initial threshold signifies using defaults
newCap = DEFAULT_INITIAL_CAPACITY;
newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);
}
if (newThr == 0) {
float ft = (float)newCap * loadFactor;
newThr = (newCap < MAXIMUM_CAPACITY && ft < (float)MAXIMUM_CAPACITY ?
(int)ft : Integer.MAX_VALUE);
}
threshold = newThr;
@SuppressWarnings({"rawtypes","unchecked"})
Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap];
table = newTab;
if (oldTab != null) {
for (int j = 0; j < oldCap; ++j) {
Node<K,V> e;
if ((e = oldTab[j]) != null) {
oldTab[j] = null;
if (e.next == null)
newTab[e.hash & (newCap - 1)] = e;
else if (e instanceof TreeNode)
((TreeNode<K,V>)e).split(this, newTab, j, oldCap);
else { // preserve order
Node<K,V> loHead = null, loTail = null;
Node<K,V> hiHead = null, hiTail = null;
Node<K,V> next;
do {
next = e.next;
if ((e.hash & oldCap) == 0) {
if (loTail == null)
loHead = e;
else
loTail.next = e;
loTail = e;
}
else {
if (hiTail == null)
hiHead = e;
else
hiTail.next = e;
hiTail = e;
}
} while ((e = next) != null);
if (loTail != null) {
loTail.next = null;
newTab[j] = loHead;
}
if (hiTail != null) {
hiTail.next = null;
newTab[j + oldCap] = hiHead;
}
}
}
}
}
return newTab;
}