HashMap源码分析(JDK8)
概述
HashMap的底层实现为 数组+链表+红黑树(通过链地址法解决冲突);
默认容量为16,扩容时 2倍容量扩容,初始化时懒加载,当真正地添加元素时才会分配内存空间。
当链表长度达到阈值8时,同时满足扩容条件时(初始态树化的最小容量要求64 ),进行链表树化;
当红黑树元素个数因为扩容而减少到阈值6时,将进行红黑树链表化;
线程不安全原因:多线程下数据覆盖;(JDK8 链表头插法修改为了链表尾插法,从而解决了JDK7多线程下链表扩容的死循环问题)
可以存放空键值;其他线程安全的字典数据结构不能放空键或空值
属性与构造方法
重要属性
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; //默认容量 16
static final int MAXIMUM_CAPACITY = 1 << 30;//HashMap 数组最大容量 1<<30
static final float DEFAULT_LOAD_FACTOR = 0.75f;//默认负载因子
static final int TREEIFY_THRESHOLD = 8;//一个桶的树化阈值
static final int UNTREEIFY_THRESHOLD = 6;//一个树的链表还原阈值
static final int MIN_TREEIFY_CAPACITY = 64;//树化的最小容量要求,为了避免进行扩容、树形化选择的冲突,这个值不能小于 4 * TREEIFY_THRESHOLD
transient Node<K,V>[] table;//桶数组
transient Set<Map.Entry<K,V>> entrySet;
transient int size;
transient int modCount;
int threshold;//扩容阈值
final float loadFactor;
链表节点
//元素存储节点类
static class Node<K,V> implements Map.Entry<K,V> {
final int hash;
final K key;
V value;
Node<K,V> next;
public final int hashCode() {
return Objects.hashCode(key) ^ Objects.hashCode(value);
}
}
构造函数
在不指定容量与负载因子时,会使用默认的容量16与负载因子0.75
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);
}
public HashMap(int initialCapacity) {
this(initialCapacity, DEFAULT_LOAD_FACTOR);
}
public HashMap() {
this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted
}
扩容方法及为什么容量是2的幂
扩容流程图
扩容方法
添加数据时使用尾插法;
2倍扩容;
扩容时,每个数组(桶)内的链表元素通过e.hash & oldCap
分2类计算新的下标;
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;
//1.为新表分配空间
@SuppressWarnings({"rawtypes","unchecked"})
Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap];
table = newTab;
if (oldTab != null) {
//2.历遍所有元素
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 {//尾插法插入链表节点
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;
}
为什么 HashMap 容量是2的整数幂?
为了在计算时使用高效的位运算
在计算扩容容量时,cap为2的n次幂,tableSizeFor()能够很快的计算出距离比cap大的最近2的幂;
在通过hash函数查找元素所在数组时,(n-1) & hash <=> hash%n
能够使用位运算代替模运算(n为2的幂才行)
除此,添加元素时,这样的hash值进行位运算时,能够充分的散列,使得添加的元素均匀分布在HashMap的每个位置上,减少hash碰撞,
static final int tableSizeFor(int cap) {
int n = cap - 1; //0001XXXX
n |= n >>> 1; //0001XXXX | 00001XXX = 00011XXX
n |= n >>> 2; //00011XXX | 0001111X = 0001111X
n |= n >>> 4; //···
n |= n >>> 8;
n |= n >>> 16;
return (n < 0) ? 1 : (n >= MAXIMUM_CAPACITY) ? MAXIMUM_CAPACITY : n + 1;
}
//(n-1) & hash 《==》 hash%n
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;
}
}
添加节点分析
添加节点流程图
public V put(K key, V value) {
return putVal(hash(key), key, value, false, true);
}
static final int hash(Object key) {
int h;
return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}
// onlyIfAbsent -- if true, don't change existing value
final V putVal(int hash, K key, V value, boolean onlyIfAbsent,
boolean evict) {
Node<K,V>[] tab; Node<K,V> p; int n, i;
//检查map是否初始化,未初始化则初始化
if ((tab = table) == null || (n = tab.length) == 0)
n = (tab = resize()).length;
//如果元素为map该位置第一个元素,直接添加即可
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null);
//若不为第一个元素
else {
Node<K,V> e; K k;
//节点在链表头已经存在
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
e = p;
//节点为红黑树结构
else if (p instanceof TreeNode)
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
//历遍链表
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;
}
HashMap Hashtable 与 ConcurrentHashMap
Hashtable 遗留类,线程安全,通过加一把同步锁保证数据线程安全,效率低下;默认容量11,扩容为 2*n + 1 int newCapacity = (oldCapacity << 1) + 1;
HashMap 线程不安全,底层结构数组加链表加红黑树(JDK8),可通过Collections.synchronizedMap() 保证线程同步,
ConcurrentHashMap 线程安全,底层结构数组加链表加红黑树(JDK8),JDK7使用分段锁提高效率,JDK8使用CAS与数组元素同步锁实现,提高并发效率。
注
本文中流程图参考自:
**粗体** _斜体_ [链接](http://example.com) `代码` - 列表 > 引用
。你还可以使用@
来通知其他用户。