我们都知道 java的HashMap使用分离链接法实现
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; //16 默认初始数组大小
static final int MAXIMUM_CAPACITY = 1 << 30; //最大数组大小 int最大值
static final float DEFAULT_LOAD_FACTOR = 0.75f; //默认装填因子
static final int TREEIFY_THRESHOLD = 8; 链表转化为树的阈值 jdk8中用红黑树实现长的羊肉串
static final int UNTREEIFY_THRESHOLD = 6;//当进行resize操作时，小于这个长度的树会被转换为链表
static final int MIN_TREEIFY_CAPACITY = 64;//链表被转换成树形的最小容量，如果没有达到这个容量只会执行resize进行扩容
接口Entry的实现有两个 一个是链表实现 内部类Node
/**
* Basic hash bin node, used for most entries. (See below for
* TreeNode subclass, and in LinkedHashMap for its Entry subclass.)
*/
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;
}
}这里的hashCode实现不是为了Hashmap内部使用的 内部无调用
引用只有一个next 是一个单向链表实现
另一个是红黑树实现 内部类TreeNode
static final class TreeNode<K,V> extends LinkedHashMap.LinkedHashMapEntry<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);
}
/**
* Returns root of tree containing this node.
*/
final TreeNode<K,V> root() {
for (TreeNode<K,V> r = this, p;;) {
if ((p = r.parent) == null)
return r;
r = p;
}
}对key取hash
空键为0 非空的key右移了16位，然后与key进行异或
static final int hash(Object key) {
int h;
return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}在hash值对应入坑的时候 没有采用简单的hash % table.length
而是用二维运算符并运算 我们截取核心函数getNode的一段代码
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;
}n = tab.length
first = tab[(n – 1) & hash]
假设是默认的16的capacity n-1就等于二进制的1111 可以理解
但是如果设置了capacity为17？ 那么10000的并运算不就会产生大量碰撞嘛
带着这样的疑问 我们来看HashMap得构造方法
public HashMap() //默认构造方法 public HashMap(int initialCapacity)//参数为初始大小 public HashMap(int initialCapacity, float loadFactor)//参数为初始大小，负载因子
最终都调用到2个参数的最后这个构造
/**
* Constructs an empty <tt>HashMap</tt> with the specified initial
* capacity and load factor.
*
* @param initialCapacity the initial capacity
* @param loadFactor the load factor
* @throws IllegalArgumentException if the initial capacity is negative
* or the load factor is nonpositive
*/
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);
}在初始化阈值的时候 调用
tableSizeFor方法
/**
* Returns a power of two size for the given target capacity.
*/
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;
}这个位运算的目的 我们先来看一下 假设传入的capacity为一个二进制数 1001010110 只要capacity不等于2的幂 那么capacity-1的最高位就不会退位
n>>>1让次高位变成了1 那么n|=n>>>1运算就是让前2位变成了1
随后 11xxxxxxx这么一个数 做n>>>2运算 第3第4位变成了1 n|=n>>>2 得到了1111xxxxx这么一个数
同理
这个运算可以让最高位之后的前32位 即Integer.MAXVALUE都变成1
最终的返回是n+1 ：若capacity是2的幂返回capacity本身 若不是则返回比capacity大的最小2的幂
可以看到构造方法里 只是通过tableSizeFor函数位运算计算了threshold值 并没有初始化数组
而我们都知道threshold是用来保存阈值的 tableSize为什么要赋值给threshold？ 带着这两个疑问我们来继续往下看
真正初始化数组的地方是在resize()里懒加载 这个函数不仅肩负了扩容功能还承担了初始化数组的任务
那么我们先来看其中初始化数组的内容
final Node<K,V>[] resize() {
Node<K,V>[] oldTab = table;
int oldCap = (oldTab == null) ? 0 : oldTab.length;
int oldThr = threshold; //假设第一次进入该方法 把构造方法里计算得出的threshold放置在oldThr中
int newCap, newThr = 0; //newCapacity就是这里要初始化的数组大小
if (oldCap > 0) { //初始化过了数组的流程 我们不管
......
}
else if (oldThr > 0) // initial capacity was placed in threshold
newCap = oldThr; //如果用了设置capacity 就用大于等于它的最小二次幂
else { // zero initial threshold signifies using defaults
newCap = DEFAULT_INITIAL_CAPACITY; //没设置就用16
newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);
}
if (newThr == 0) { //被设置capacity的初始化会进入这里
float ft = (float)newCap * loadFactor; //重新计算阈值等于capacity*装填因子
newThr = (newCap < MAXIMUM_CAPACITY && ft < (float)MAXIMUM_CAPACITY ?
(int)ft : Integer.MAX_VALUE);
}
threshold = newThr; //设置回去 原来构造方法里的threshold只是暂时帮忙存储一下待加载的capacity 这里才是他真正还原身份的地方
@SuppressWarnings({"rawtypes","unchecked"})
Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap]; //new数组也就是说初始化的Node[]数组大小 一定是2的幂
这就把前面的疑惑解除了 tab[(n – 1) & hash] 如果是n是个二次幂的话 这个操作实际上就是个%取模操作 而且效率还高！
其实在jdk7里 实现也是类似的
参考一下jdk7的代码：初始化数组
if (table == EMPTY_TABLE) {
inflateTable(threshold);
}inflateTable
/**
* Inflates the table.
*/
private void inflateTable(int toSize) {
// Find a power of 2 >= toSize
int capacity = roundUpToPowerOf2(toSize);
threshold = (int) Math.min(capacity * loadFactor, MAXIMUM_CAPACITY + 1);
table = new Entry[capacity];
initHashSeedAsNeeded(capacity);
}位运算函数
private static int roundUpToPowerOf2(int number) {
// assert number >= 0 : "number must be non-negative";
return number >= MAXIMUM_CAPACITY
? MAXIMUM_CAPACITY
: (number > 1) ? Integer.highestOneBit((number - 1) << 1) : 1;
}计算entry值 对应jdk8里的tab[(n – 1) & hash]
/**
* Returns index for hash code h.
*/
static int indexFor(int h, int length) {
// assert Integer.bitCount(length) == 1 : "length must be a non-zero power of 2";
return h & (length-1);
}另一个核心函数就是取了 putVal
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;
}函数resize
该方法除了之前提到的初始化数组之外，最大的使命就是关系到HashMap性能瓶颈的扩容任务
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;
}