源码阅读相关方法及注释
public class HashMap<K,V> extends AbstractMap<K,V>
implements Map<K,V>, Cloneable, Serializable {
/*
* 0: 0.60653066
* 1: 0.30326533
* 2: 0.07581633
* 3: 0.01263606
* 4: 0.00157952
* 5: 0.00015795
* 6: 0.00001316
* 7: 0.00000094
* 8: 0.00000006
* more: less than 1 in ten million
翻译:当hashCode离散性很好的时候,树型bin用到的概率非常小,因为数据均匀分布在每个bin中,
* 几乎不会有bin中链表长度会达到阈值(树化门槛)。但是在随机hashCode下,离散性可能会变差,
* 然而JDK又不能阻止用户实现这种不好的hash算法,因此就可能导致不均匀的数据分布。
* 不过理想情况下随机hashCode算法下所有bin中节点的分布频率会遵循泊松分布,我们可以看到,
* 一个bin中链表长度达到8个元素的概率为0.00000006,几乎是不可能事件。
*/
//默认初始化容量
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16
//最大容量
static final int MAXIMUM_CAPACITY = 1 << 30;
//默认负载因子
static final float DEFAULT_LOAD_FACTOR = 0.75f;
//链表转红黑树的需要 桶中链表长度必须不少于这个数字
static final int TREEIFY_THRESHOLD = 8;
//红黑树退化成链表,桶中链表长度必须小于6
static final int UNTREEIFY_THRESHOLD = 6;
//链表转红黑树必须使数组容量大于 64
static final int MIN_TREEIFY_CAPACITY = 64;
//组成元素
static class Node<K,V> implements Map.Entry<K,V> {
final int hash; //hash值
final K key; //key值
V value; //value
Node<K,V> next; //指向下一个Node指针
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() {
//通过 异或 保留key和value的特征
return Objects.hashCode(key) ^ Objects.hashCode(value);
}
}
/* ---------------- Static utilities -------------- */
//int值32位数,通过无符号右移16位获取高16位,然后通过异或保留高16位与低16位的特征值
static final int hash(Object key) {
int h;
return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}
//生成hashMap的容量,转换后保证是2的n次方,
// 用于以后与HashCode做与运算,保证得到的数对应数组中的某一个位置,而不至于数组越界
static final int tableSizeFor(int cap) {
int n = cap - 1;
n |= n >>> 1;
n |= n >>> 2;
n |= n >>> 4;
n |= n >>> 8;
n |= n >>> 16;
return (n < 0) ? 1 : (n >= MAXIMUM_CAPACITY) ? MAXIMUM_CAPACITY : n + 1;
}
//数组,避免序列化
transient Node<K,V>[] table;
//用于遍历的entyrSet
transient Set<Map.Entry<K,V>> entrySet;
//存储key-value的数量
transient int size;
//存储数组的改动次数,改动包括put值和内部结构发生变化的次数
//用户迭代的时候触发快速失败机制(并发修改异常)
transient int modCount;
//没有初始化的时候表示数组容量或者0 ,初始化后表示下一次扩容的容量
int threshold;
//加载因子
final float loadFactor;
/* ---------------- Public operations -------------- */
//初始化方法,值进行校验和赋值容量,数组初始化操作在put的时候进行
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);
}
//无参构造,所有的字段使用默认值
public HashMap() {
this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted
}
//从map中取值
public V get(Object key) {
Node<K,V> e;
return (e = getNode(hash(key), key)) == null ? null : e.value;
}
//查找元素
final Node<K,V> getNode(int hash, Object key) {
Node<K,V>[] tab; Node<K,V> first, e; int n; K k;
//判断是否有元素,且第一个元素是不是为空
if ((tab = table) != null && (n = tab.length) > 0 &&
(first = tab[(n - 1) & hash]) != null) {
//判断第一个元素的与传入key的hash值相等,并且key是否一样
if (first.hash == hash && // always check first node
((k = first.key) == key || (key != null && key.equals(k))))
return first;
if ((e = first.next) != null) {
//判断是否是树类型,是则从树中查找
if (first instanceof TreeNode)
return ((TreeNode<K,V>)first).getTreeNode(hash, key);
//循环遍历链表,查找是否存在元素
do {
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
return e;
} while ((e = e.next) != null);
}
}
return null;
}
//存元素
public V put(K key, V value) {
return putVal(hash(key), key, value, false, true);
}
//存元素方法的内部实现
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)
//没有初始化,则触发数组初始化
n = (tab = resize()).length;
if ((p = tab[i = (n - 1) & hash]) == null)
//位置上没有元素,直接存放在数组这个位置
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)
//如果是树节点,放到红黑树中
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);
//判断如果链表长度大于等于8则转换成红黑树
if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
//树化方法内部会判断是不是超过64的数组长度,超过才转换红黑树
treeifyBin(tab, hash);
break;
}
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
break;
p = e;
}
}
//如果有覆盖原相同key的值,则返回旧的值
if (e != null) { // existing mapping for key
V oldValue = e.value;
if (!onlyIfAbsent || oldValue == null)
e.value = value;
afterNodeAccess(e);
return oldValue;
}
}
//更改次数加一
++modCount;
//判断容量超过阈值,则扩容
if (++size > threshold)
resize();
afterNodeInsertion(evict);
return null;
}
//扩容的方法
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) {
//如果超过最大容量则直接返回
if (oldCap >= MAXIMUM_CAPACITY) {
threshold = Integer.MAX_VALUE;
return oldTab;
}
//按照2倍进行扩容,设置扩容阈值为原来的两倍
else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY &&
oldCap >= DEFAULT_INITIAL_CAPACITY)
newThr = oldThr << 1; // double threshold
}
//将新容量设置为要扩容的容量
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);
}
//重新设置扩容的阈值
threshold = newThr;
//创建新数组
@SuppressWarnings({"rawtypes","unchecked"})
Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap];
table = newTab;
//循环拷贝旧数组数据到新数组
if (oldTab != null) {
for (int j = 0; j < oldCap; ++j) {
Node<K,V> e;
if ((e = oldTab[j]) != null) {
//置空数组该位置
oldTab[j] = null;
//该节点没有next节点,则重新赋值到新的索引位置
if (e.next == null)
newTab[e.hash & (newCap - 1)] = e;
//如果节点是树节点
else if (e instanceof TreeNode)
((TreeNode<K,V>)e).split(this, newTab, j, oldCap);
else { // preserve order
//链表类型
Node<K,V> loHead = null, loTail = null;
Node<K,V> hiHead = null, hiTail = null;
Node<K,V> next;
do {
next = e.next;
//哈希值与原数组容量与运算为零为的node组成一个链表,不为零的组成另一个链表
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);
//为0组成的链表放到新数组的位置与原数组相同
if (loTail != null) {
loTail.next = null;
newTab[j] = loHead;
}
//不为零的组成的链表放到新数组位置是原数组位置加上原数组的长度
if (hiTail != null) {
hiTail.next = null;
newTab[j + oldCap] = hiHead;
}
}
}
}
}
return newTab;
}
//链表转红黑树的方法
final void treeifyBin(Node<K,V>[] tab, int hash) {
int n, index; Node<K,V> e;
//判断是不是数组长度大于64,是才进行树化处理
if (tab == null || (n = tab.length) < MIN_TREEIFY_CAPACITY)
resize();
else if ((e = tab[index = (n - 1) & hash]) != null) {
TreeNode<K,V> hd = null, tl = null;
do {
TreeNode<K,V> p = replacementTreeNode(e, null);
if (tl == null)
hd = p;
else {
p.prev = tl;
tl.next = p;
}
tl = p;
} while ((e = e.next) != null);
if ((tab[index] = hd) != null)
hd.treeify(tab);
}
}
//删除元素的方法
public V remove(Object key) {
Node<K,V> e;
return (e = removeNode(hash(key), key, null, false, true)) == null ?
null : e.value;
}
//内部执行删除元素的方法
final Node<K,V> removeNode(int hash, Object key, Object value,
boolean matchValue, boolean movable) {
Node<K,V>[] tab; Node<K,V> p; int n, index;
if ((tab = table) != null && (n = tab.length) > 0 &&
(p = tab[index = (n - 1) & hash]) != null) {
Node<K,V> node = null, e; K k; V v;
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
node = p;
else if ((e = p.next) != null) {
//从红黑树中获取到要删除的node
if (p instanceof TreeNode)
node = ((TreeNode<K,V>)p).getTreeNode(hash, key);
else {
//循环从链表中查找需要删除的node
do {
if (e.hash == hash &&
((k = e.key) == key ||
(key != null && key.equals(k)))) {
node = e;
break;
}
p = e;
} while ((e = e.next) != null);
}
}
if (node != null && (!matchValue || (v = node.value) == value ||
(value != null && value.equals(v)))) {
//从红黑树中删除node
if (node instanceof TreeNode)
((TreeNode<K,V>)node).removeTreeNode(this, tab, movable);
else if (node == p)
//桶中不存在链表
tab[index] = node.next;
else
p.next = node.next;
++modCount;
--size;
afterNodeRemoval(node);
return node;
}
}
return null;
}
/**
* Removes all of the mappings from this map.
* The map will be empty after this call returns.
*/
public void clear() {
Node<K,V>[] tab;
modCount++;
if ((tab = table) != null && size > 0) {
size = 0;
for (int i = 0; i < tab.length; ++i)
tab[i] = null;
}
}
static final class TreeNode<K,V> extends LinkedHashMap.Entry<K,V> {
TreeNode<K,V> parent; // red-black tree links
TreeNode<K,V> left;
TreeNode<K,V> right;
TreeNode<K,V> prev; // needed to unlink next upon deletion
boolean red;
TreeNode(int hash, K key, V val, Node<K,V> next) {
super(hash, key, val, next);
}
//扩容时候红黑树的操作
final void split(HashMap<K,V> map, Node<K,V>[] tab, int index, int bit) {
TreeNode<K,V> b = this;
// Relink into lo and hi lists, preserving order
TreeNode<K,V> loHead = null, loTail = null;
TreeNode<K,V> hiHead = null, hiTail = null;
int lc = 0, hc = 0;
//计算高位和低位,分别组装成链表,并且记录链表的长度
for (TreeNode<K,V> e = b, next; e != null; e = next) {
next = (TreeNode<K,V>)e.next;
e.next = null;
if ((e.hash & bit) == 0) {
if ((e.prev = loTail) == null)
loHead = e;
else
loTail.next = e;
loTail = e;
++lc;
}
else {
if ((e.prev = hiTail) == null)
hiHead = e;
else
hiTail.next = e;
hiTail = e;
++hc;
}
}
if (loHead != null) {
//判断是否达到去树化的条件
if (lc <= UNTREEIFY_THRESHOLD)
tab[index] = loHead.untreeify(map); //去树化
else {
tab[index] = loHead;
if (hiHead != null) // (else is already treeified)
loHead.treeify(tab); //树化
}
}
if (hiHead != null) {
if (hc <= UNTREEIFY_THRESHOLD)
tab[index + bit] = hiHead.untreeify(map);
else {
tab[index + bit] = hiHead;
if (loHead != null)
hiHead.treeify(tab);
}
}
}
}
put()方法执行流程总结
扩容方法关键点
将原数组赋值到新数组的时候,赋值的时候会重新计算存放的索引值。如果桶中只有一个元素,则使用hashcode与运算新数组长度-1 作为新位置; 如果是链表或者红黑树,则将hashcode与运算旧数组长度,得到值为0则存放在原位置,不为0则存放的位置是原位置加上旧数组长度的新位置,然后再判断是否树化或者转链表
转红黑树条件
数组长度大于64 且 链表长度大于等于 8
红黑树转链表的时机
只有扩容的时候,发现红黑树个数小于等于6,则转换成链表
哈希码无符号右移后异或运算的原因
哈希码无符号右移16位后得到的是哈希码的高16位值。然后异或运算原哈希码,则得到的值高16位都为0 ,低16位则保留了高低16位的特征,能够使得哈希值相对比较离散。
数组容量必须是2的n次幂
获取数组的映射位置的时候,为了保证运算的高效,使用位运算是最好的,而为了使得获取的位置值不超过数组的长度,使用2的n次幂的长度就能通过与运算来保证