HashMap默認大小
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16
HashMap最大容量,2的30次方
static final int MAXIMUM_CAPACITY = 1 << 30;
HashMap負載係數,當size超過容量的0.75(初始化大小爲 16 * 0.75 = 12)後擴容
static final float DEFAULT_LOAD_FACTOR = 0.75f;
jdk8之前hashmap的數據結構是數組+鏈表,在hash碰撞很頻繁的情況下鏈表會很長,由於hashmap查詢數據的鏈表部分是通過循環來比較值的,所以效率慢。
jdk8把數據結構改爲數組+鏈表+紅黑樹的形式,當鏈表的長度大於6時,把鏈表轉換成紅黑樹。
static final int TREEIFY_THRESHOLD = 8;
紅黑樹的一些特點:
1.根結點一定是黑色
2.每個節點非黑即紅
3.紅色節點的葉子節點一定是黑色
4.從任意節點到葉子節點的黑色節點數量相同
問:hashmap爲什麼使用紅黑樹,而不是使用二分查找樹或者avl平衡樹?
二分查找樹在極端情況下會退化成鏈表影響效率。
avl平衡樹參考 https://blog.csdn.net/21aspnet/article/details/88939297
還有既然紅黑樹這麼好,那爲什麼不直接使用紅黑樹,而要在鏈表和紅黑樹之間轉換?
其實吧,紅黑樹畢竟是平衡樹需要維持平衡就需要旋轉,旋轉也是耗時的,所以在量小的情況下,鏈表效率反而高。
退化閾值,當鏈表大小小於等於此值後把紅黑樹退化成鏈表
static final int UNTREEIFY_THRESHOLD = 6;
Hash桶化樹的閾值
static final int MIN_TREEIFY_CAPACITY = 64;
static final int hash(Object key) {
int h;
return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}
計算hash值,很關鍵的一段代碼,因爲hashmap中所有的操作基本離不開它。
/**
* 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;
}
對於給定的目標容量,返回兩倍大小的冪(2的冪次方)。這個函數在初始化指定容量的構造方法中會被調用。
例如:
cap=9 return 16
cap=15 return 16
cap=16 return 16
cap=17 return 32
/**
* 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);
}
說曹操曹操就到。這個自定義容量和負載因子的構造方法中調用tableSizeFor 方法,以確保hashmap的容量是2的冪次方
/**
* Constructs an empty <tt>HashMap</tt> with the specified initial
* capacity and the default load factor (0.75).
*
* @param initialCapacity the initial capacity.
* @throws IllegalArgumentException if the initial capacity is negative.
*/
public HashMap(int initialCapacity) {
this(initialCapacity, DEFAULT_LOAD_FACTOR);
}
會調用上面的方法 public HashMap(int initialCapacity, float loadFactor) 初始化。
/**
* Constructs an empty <tt>HashMap</tt> with the default initial capacity
* (16) and the default load factor (0.75).
*/
public HashMap() {
this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted
}
默認負載因子是0.75,容量是16
public HashMap(Map<? extends K, ? extends V> m) {
this.loadFactor = DEFAULT_LOAD_FACTOR;
putMapEntries(m, false);
}
初始化的時候把參數m放入map中
final void putMapEntries(Map<? extends K, ? extends V> m, boolean evict) {
//獲取傳入map大小
int s = m.size();
if (s > 0) {//如果傳入的map沒數據就沒必要走下去了
//首先如果當前table爲null(也就是是一個新的map),根據傳入的map大小重新計算容量
//如果當前table不爲空,但傳入的map容量 大於 當前map容量,擴容
//然後把傳入的map放入新的map中
if (table == null) { // pre-size
float ft = ((float)s / loadFactor) + 1.0F;
int t = ((ft < (float)MAXIMUM_CAPACITY) ?
(int)ft : MAXIMUM_CAPACITY);
if (t > threshold)
threshold = tableSizeFor(t);
}
else if (s > threshold)
resize();
for (Map.Entry<? extends K, ? extends V> e : m.entrySet()) {
K key = e.getKey();
V value = e.getValue();
putVal(hash(key), key, value, false, evict);
}
}
}
public V get(Object key) {
Node<K,V> e;
return (e = getNode(hash(key), key)) == null ? null : e.value;
}
獲取元素的方法,調用hash算法算出下標,然後在table中取值。參數是一個object值,那也就可以是一個對象,如果一個對象作爲key在進行hash運算的時候是不是要求參數對象重新hashcode算法。
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) {
//通過hash在tab中獲取數據,沒取到直接返回null
if (first.hash == hash && // always check first node
((k = first.key) == key || (key != null && key.equals(k))))
//判斷第一個node的值是不是我們要的值
return first;
if ((e = first.next) != null) {
//如果第一個節點不是,就接着判斷後面的節點
if (first instanceof TreeNode)
//這個是紅黑樹
return ((TreeNode<K,V>)first).getTreeNode(hash, key);
//鏈表通過循環比較獲取
do {
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
return e;
} while ((e = e.next) != null);
}
}
return null;
}
//調用getNode方法判斷key存不存在
public boolean containsKey(Object key) {
return getNode(hash(key), key) != null;
}
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)
//tab還未初始化,初始化tab
n = (tab = resize()).length;
if ((p = tab[i = (n - 1) & hash]) == null)
//tab中未找到就新new一個node
tab[i] = newNode(hash, key, value, null);
else {
//如果在tab中找到了node,並且第一個節點就是
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)
//第一個節點不是,接着查找下面的節點,如果節點轉換爲紅黑樹了,就走紅黑樹邏輯
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
else {
//如果是鏈表,就循環查找
for (int binCount = 0; ; ++binCount) {
if ((e = p.next) == null) {
//鏈表找完了都沒找到的情況
p.next = newNode(hash, key, value, null);
if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
//判斷是擴容還是轉紅黑樹
treeifyBin(tab, hash);
break;
}
//找到了的情況
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
break;
p = e;
}
}
//替換值
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)
//擴容
resize();
afterNodeInsertion(evict);
return null;
}
//擴容
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) {
//如果舊map的容量超過最大容量,就把容量設置爲int最大值
threshold = Integer.MAX_VALUE;
return oldTab;
}
else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY &&
oldCap >= DEFAULT_INITIAL_CAPACITY)
//如果當前容量擴容2倍後滿足條件就擴容2倍
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) {
//遍歷舊數組
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;
//這裏的算法很有意思,擴容後原數據位置是否不變是由高位確定
//舉例討論數組大小從8擴容到16的過程
//容量是8
//tab.length -1 = 7 0 0 1 1 1
//e.hashCode = x 0 x x x x
//==============================
// 0 0 y y y
//擴容到16
//tab.length -1 = 15 0 1 1 1 1
//e.hashCode = x x x x x x
//==============================
// 0 z y y y
/**
* 擴容後,index的位置由低四位來決定,而低三位和擴容前一致。
* 也就是說擴容後index的位置是否改變是由高字節來決定的,
* 也就是說我們只需要將hashCode和高位進行運算即可得到index是否改變。
* 而剛好擴容之後的高位和oldCap的高位一樣。
* 如上面的15二進制是1111,
* 而8的二進制是1000,他們的高位都是一樣的。
* 所以我們通過e.hash & oldCap運算的結果即可判斷index是否改變。
*
* 同理,如果擴容後index該變了。
* 新的index和舊的index的值也是高位不同,
* 其新值剛好是 oldIndex + oldCap的值。
* 所以當index改變後,新的index是 j + oldCap。
*
* 至此,resize方法結束,元素被插入到了該有的位置。
*
* 鏈接:https://www.jianshu.com/p/fb282d3d2e87
*/
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;
}
//鏈表轉換爲紅黑樹
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)
//當數組tab小於64的時候,擴容?
//這個作用是通過擴容從新分配節點來減少hash碰撞後的鏈表長度?
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);
}
}