HashMap源码阅读

核心方法

put方法

可以发现put方法是委托给putVal()方法的，值得注意的方法是hash(key)的实现。hash(key)相当简单, 它可以接受null作为key，这时hash值为0，而正常的hash值是h ^ (h >>> 16)

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);
}

看看putVal()的实现，tab[i = (n - 1) & hash]，这一行是选择一个哈希桶，也能说明为什么HashMap的哈希桶数量必须是2的幂次，如初始化大小是16，16-1的二进制是1111，然后1111 ^ hash 则是桶是索引，值肯定是[0,15]中。

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;//第一次put，要进行初始化
if ((p = tab[i = (n - 1) & hash]) == null)//选择hash桶，如果桶不存在
tab[i] = newNode(hash, key, value, null);//初始化一个桶
else {//如果桶存在，就是一个链表操作，包括转换为红黑树
Node<K,V> e; K k;
if (p.hash == hash &&//短路操作，hash不同就没有必要用equals()
((k = p.key) == key || (key != null && key.equals(k))))
e = p;//表示key相同
else if (p instanceof TreeNode)//新key，增加红黑树节点
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
else {//新key，普通节点
for (int binCount = 0; ; ++binCount) {//计数，看看是否需要变成红黑树
if ((e = p.next) == null) {//找到一个null，插入新节点
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;//修改次数，用于迭代器fail-fast
if (++size > threshold)//判断要不要rehash
resize();
afterNodeInsertion(evict);//无实现
return null;
}

static class Node<K,V> implements Map.Entry<K,V> {
final int hash;
final K key;
V value;
Node<K,V> next;
//......
}

resize方法

newCap = oldCap << 1，即也会是2的幂次

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;
}
//将Cap和Thr都扩充一倍
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 {               // 第一次resize是初始化操作
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"})
//创建新的哈希桶
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;//将原哈希桶清空，防止内存泄漏
if (e.next == null)
newTab[e.hash & (newCap - 1)] = e;//rehash
else if (e instanceof TreeNode)
((TreeNode<K,V>)e).split(this, newTab, j, oldCap);
else { //代表哈希桶是为1个以上
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;//这个措施很。。。
}
}
}
}
}
return newTab;
}

get方法

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) {//获取hash桶首节点
if (first.hash == hash && // always check first node
((k = first.key) == key || (key != null && key.equals(k))))
return first;//命中返回
if ((e = first.next) != null) {
if (first instanceof TreeNode)
return ((TreeNode<K,V>)first).getTreeNode(hash, key);
do {//沿着链表往后找
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
return e;
} while ((e = e.next) != null);
}
}
return null;
}

remove方法

public V remove(Object key) {
Node<K,V> e;
return (e = removeNode(hash(key), key, null, false, true)) == null ?
null : e.value;
}

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) {
if (p instanceof TreeNode)
node = ((TreeNode<K,V>)p).getTreeNode(hash, key);
else {
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)))) {
if (node instanceof TreeNode)
((TreeNode<K,V>)node).removeTreeNode(this, tab, movable);
else if (node == p)
tab[index] = node.next;
else
p.next = node.next;
++modCount;
--size;
afterNodeRemoval(node);
return node;
}
}
return null;
}

其他有趣的实现

找到比一个数字大的2的幂次

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;
}

从别的Map添加到HashMap

else if (s > threshold) resize();可能是先扩容，再添加。

但是问题来了，比如原先是threshold是12，map.size()是300，扩容后threshold是24，添加的时候还是要再次扩容的呀，所以这么做的意义好像不是很大，只是省去一次rehash的时间

public HashMap(Map<? extends K, ? extends V> m) {
this.loadFactor = DEFAULT_LOAD_FACTOR;
putMapEntries(m, false);
}

final void putMapEntries(Map<? extends K, ? extends V> m, boolean evict) {
int s = m.size();
if (s > 0) {
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);
}
}
}

clear方法

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;
}
}

containsValue方法

public boolean containsValue(Object value) {
Node<K,V>[] tab; V v;
if ((tab = table) != null && size > 0) {
for (Node<K, V> e : tab) {
for (; e != null; e = e.next) {
if ((v = e.value) == value ||
(value != null && value.equals(v)))
return true;
}
}
}
return false;
}

getOrDefault()

public V getOrDefault(Object key, V defaultValue) {
Node<K,V> e;
return (e = getNode(hash(key), key)) == null ? defaultValue : e.value;
}

putIfAbsent()

@Override
public V putIfAbsent(K key, V value) {
return putVal(hash(key), key, value, true, true);
}

还有大量的函数式方法和大量的红黑树实现代码

函数式代码暂时不感兴趣，而且所有Collection都差不多，写过python或Javascript的，估计很容易看懂。红黑树的代码是特别长又特别难懂，感兴趣看算法，我只要知道是一种二叉平衡树就行了。