HashMap是我们常用的数据结构之一,之前我并没有仔细了解过它的底层原理,现在就来分析一下它的源码。
HashMap 在 java.util 下,继承了 AbstractMap
下面是 一些常量定义:
// 默认初始化容量必须是2的倍数
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16
// 最大容量,被用于任何一个带参数的构造器,必须是2的倍数 且小于 2^30
static final int MAXIMUM_CAPACITY = 1 << 30;
// 默认加载因子
static final float DEFAULT_LOAD_FACTOR = 0.75f;
// 树化阈值,当桶中元素个数超过这个值时需要用将链表转化为树
static final int TREEIFY_THRESHOLD = 8;
// 在重新调整大小的操作中,当桶中元素个数少于这个值时 从树转化为 链表
static final int UNTREEIFY_THRESHOLD = 6;
// 表的容量大于这个值时,桶才会被树化
static final int MIN_TREEIFY_CAPACITY = 64;
HashMap 本质是Node 数组,Node 对象数据结构:hash, key, value, next
static class Node<K,V> implements Map.Entry<K,V> {
final int hash;
final K key;
V value;
Node<K,V> next;
Node(int hash, K key, V value, Node<K,V> next) {
this.hash = hash;
this.key = key;
this.value = value;
this.next = next;
}
public final K getKey() { return key; }
public final V getValue() { return value; }
public final String toString() { return key + "=" + value; }
public final int hashCode() {
return Objects.hashCode(key) ^ Objects.hashCode(value);
}
public final V setValue(V newValue) {
V oldValue = value;
value = newValue;
return oldValue;
}
public final boolean equals(Object o) {
if (o == this)
return true;
if (o instanceof Map.Entry) {
Map.Entry<?,?> e = (Map.Entry<?,?>)o;
if (Objects.equals(key, e.getKey()) &&
Objects.equals(value, e.getValue()))
return true;
}
return false;
}
}
HashMap 无参数构造方法,这里 默认初始大小是 16 ,加载因子是 0.75
public HashMap() {
this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted
}
带有初始容量的构造方法
public HashMap(int initialCapacity) {
this(initialCapacity, DEFAULT_LOAD_FACTOR);
}
带有初始容量和加载因子的构造方法
public HashMap(int initialCapacity, float loadFactor) {
if (initialCapacity < 0)
throw new IllegalArgumentException("Illegal initial capacity: " +
initialCapacity);
if (initialCapacity > MAXIMUM_CAPACITY)
initialCapacity = MAXIMUM_CAPACITY;
if (loadFactor <= 0 || Float.isNaN(loadFactor))
throw new IllegalArgumentException("Illegal load factor: " +
loadFactor);
this.loadFactor = loadFactor;
this.threshold = tableSizeFor(initialCapacity);//把初始容量变成2的倍数
}
下来再看看 put 操作
链表数据 put 操作源码如下:
public V put(K key, V value) {
return putVal(hash(key), key, value, false, true);
}
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;//如果table为null,初始化table
if ((p = tab[i = (n - 1) & hash]) == null)// 根据hash值计算索引下标
tab[i] = newNode(hash, key, value, null);// 如果索引对应的内容为null,直接创建
else {
Node<K,V> e; K k;
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
e = p;// 如果tab[i] 的首个元素和目标key一样,则直接赋值,后续覆盖value值
else if (p instanceof TreeNode)
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);//如果tab[i]是树节点直接跳转树节点的put的方法
else {
// 遍历tab[i] 下所有元素
for (int binCount = 0; ; ++binCount) {
if ((e = p.next) == null) {
p.next = newNode(hash, key, value, null);//遍历结束不存在key,直接创建
if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
treeifyBin(tab, hash);//如果长度大于 8, 树化 tab
break;
}
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
break;
p = e;//存在key值,直接赋值,后续覆盖value值
}
}
if (e != null) { // existing mapping for key
V oldValue = e.value;
if (!onlyIfAbsent || oldValue == null)
e.value = value;
afterNodeAccess(e);
return oldValue;// 如果键值存在,替换value值
}
}
++modCount;
if (++size > threshold)
resize();//扩容
afterNodeInsertion(evict);
return null;
}
链表树化的方法
final void treeifyBin(Node<K,V>[] tab, int hash) {
int n, index; Node<K,V> e;
if (tab == null || (n = tab.length) < MIN_TREEIFY_CAPACITY)
resize();// tab的大小 小于最小树化阖值,不进行树化,直接扩容
else if ((e = tab[index = (n - 1) & hash]) != null) {
TreeNode<K,V> hd = null, tl = null;
do {
TreeNode<K,V> p = replacementTreeNode(e, null);// 新建TreeNode,内容为tab[i]
if (tl == null)// 树头节点
hd = p;
else {
p.prev = tl;
tl.next = p;
}
tl = p;
} while ((e = e.next) != null);// 桶中第一个节点变成p
if ((tab[index] = hd) != null)
hd.treeify(tab);// 形成从该节点链接的节点的树
}
}