HashMap源码分析
java version 10.0.1
1. 概览
在IDEA中双击Shift键,调出search everywhere框,搜索HashMap,点击进去即可阅读源码。
public class HashMap<K,V> extends AbstractMap<K,V>
implements Map<K,V>, Cloneable, Serializable {
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; //默认大小16
static final int MAXIMUM_CAPACITY = 1 << 30;//最大的大小
static final float DEFAULT_LOAD_FACTOR = 0.75f;//负载因子
static final int TREEIFY_THRESHOLD = 8;
static final int UNTREEIFY_THRESHOLD = 6;
static final int MIN_TREEIFY_CAPACITY = 64;
内部存储结构是一个数组
transient Node<K,V>[] table;
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;
}
}
node中存放着哈希值,键值对,和指向下一个node的指针,说明node是一个链表,即数组的每个位置被当做一个桶,其中存放着一个链表。
2. 插入值
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;
if ((p = tab[i = (n - 1) & hash]) == null)//判断是否会冲突
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;
}
由以上源码可知,插入元素的步骤如下
- 判断表是否为空,若是则resize
- 判断插入是否会哈希冲突,若不会,则直接在该位置插入新的node
- 若该位置已经有元素,则判断与该位置首节点key是否相同,若相同则将值修改为新即可
- 若首节点key不同,则遍历该位置的链表,查找该位置链表中其他节点是否有key值相同,若没有则在链表尾部插入新节点。
- 判断元素个数是否超过临界值,若超过,则resize
3. 获取元素
public V get(Object key) {
Node<K,V> e;
return (e = getNode(hash(key), key)) == null ? null : e.value;
}
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;
}
获取元素值比较简单,根据key计算出hash值,找到存放元素的位置,判断该位置链表头节点key是否相等,若不是要找的元素,则顺序遍历链表,直到找到为止。
4. 扩容
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) {
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;
}
设HashMap的table长度为 M,需要存储的键值对数量为 N,如果哈希函数满足均匀性的要求,那么每条链表的长度大约为 N/M,因此平均查找次数的复杂度为 O(N/M)。
当 HashMap 中的元素越来越多的时候,hash冲突的几率也就越来越高,因为数组的长度是固定的,所以为了提高查询的效率,就要对HashMap的数组进行扩容,在HashMap数组扩容之后,最消耗性能的点是:原数组中的数据必须重新计算其在新数组中的位置,并放进去,这就是 resize
loadFactor指的是负载因子 HashMap能够承受住自身负载(大小或容量)的因子,loadFactor的默认值为 0.75认情况下,数组大小为 16,那么当HashMap中元素个数超过 16*0.75=12 的时候,就把数组的大小扩展为 2^16=32,即扩大一倍,然后重新计算每个元素在数组中的位置,而这是一个非常消耗性能的操作,所以如果我们已经预知 HashMap 中元素的个数,那么预设元素的个数能够有效的提高 HashMap 的性能
负载因子越大表示散列表的装填程度越高,反之愈小。对于使用链表法的散列表来说,查找一个元素的平均时间是 O(1+a),因此如果负载因子越大,对空间的利用更充分,然而后果是查找效率的降低;如果负载因子太小,那么散列表的数据将过于稀疏,对空间造成严重浪费
else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY &&
oldCap >= DEFAULT_INITIAL_CAPACITY)
newThr = oldThr << 1; // double threshold
根据这段代码可知,hashmap扩容后容量为原来的两倍。同时,根据源码可知,扩容时需要将原map中的键值对重新散列,因此这一步比较费时。
5. 链表转红黑树
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();
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);
}
}
从 JDK 1.8 开始,链表长度大于 8 时会将链表转换为红黑树。
if (binCount >= TREEIFY_THRESHOLD - 1) //TREEIFY_THRESHOLD = 8
treeifyBin(tab, hash);
此段代码在putVal方法中