JDK1.8 HashMap源码解析，单纯为个人理解记载，仅供参考，如有理解歧义或错误，欢迎指出讨论。（有时间会不断完善的，争取把所有方法都罗列出来）
2021-07-25
- 添加《底层数据结构简述》
- 添加《获取逻辑简述》
底层数据结构简述
/* 部分代码省略 */
class Node<K,V> {
final int hash;
final K key;
V value;
Node next;
}
transient Node<K,V>[] table;
class TreeNode<K,V> extends LinkedHashMap.Entry<K,V> {}
class LinkedHashMap.Entry<K,V> extends HashMap.Node<K,V> {}
HashMap底层采用Node[]进行存储，以key的hash值作为索引定位数据，一个Node储存同一hash值的所有数据。当key的hash碰撞次数（也就是Node自身长度）达到一定阈值TREEIFY_THRESHOLD，并且当前Node[]长度小于MIN_TREEIFY_CAPACITY，则对Node[]进行resize()操作。如果当前Node[]长度大于MIN_TREEIFY_CAPACITY，则将当前hash值索引定位到的Node转换成TreeNode进行存储。
PS：TREEIFY_THRESHOLD为静态常量，值为8。
PS：MIN_TREEIFY_CAPACITY为静态常量，值为64。
PS：TreeNode是一个红黑树结构
获取逻辑简述
根据key的hash值定位需要获取的数据的索引位置。对该节点Node进行遍历，比较传入的key与Node中的key，找到key相等的节点，返回该节点的value。
threshold 扩容阈值，当实例化时如果指定了容器的大小，会对该值进行赋值，如果实例化时容器大小为0，则该值为1，如果>0则该值通过以下代码进行计算得出。
/**
* 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;
}
我们在new一个HashMap实例时，可以给定两个值分别是int类型的initialCapacity和float类型的loadFactor。initialCapacity为HashMap的容积，默认为1 << 4 = 16，loadFactor为HashMap在判断扩容时的计算因子，默认为0.75f，扩容阈值默认为loadFactor * initialCapacity = (1 << 4) * 0.75f 。在实例化时initialCapacity可以为0，loadFactor不能为0
public V put(K key, V value) 源码解析
/**
* Associates the specified value with the specified key in this map.
* If the map previously contained a mapping for the key, the old
* value is replaced.
*
* @param key key with which the specified value is to be associated
* @param value value to be associated with the specified key
* @return the previous value associated with <tt>key</tt>, or
* <tt>null</tt> if there was no mapping for <tt>key</tt>.
* (A <tt>null</tt> return can also indicate that the map
* previously associated <tt>null</tt> with <tt>key</tt>.)
*/
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) 源码解析
由put(K key, V value)调用
/**
* Implements Map.put and related methods.
*
* @param hash hash for key
* @param key the key
* @param value the value to put
* @param onlyIfAbsent if true, don't change existing value
* @param evict if false, the table is in creation mode.
* @return previous value, or null if none
*/
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)
/*
* 判断当前HashMap是否有值，如果没有值，进行初始化容积
* table为实际的数据结构，真实存储的数据
* resize()对当前table进行初始化或者扩容
* table的size始终时2的幂
*/
//当前容积
n = (tab = resize()).length;
if ((p = tab[i = (n - 1) & hash]) == null)
/*
* 根据位运算，计算出key应该保存的index位置，如果该位置没有值，则创建一个新节点并且进行赋值
* 最大的index与key的散列值进行位运算，计算出key对应的index值
*/
tab[i] = newNode(hash, key, value, null);
else {
/*
* 根据key计算出的数组index处已经存在值了，
* 一种是key值完全相同
* 一种是key值的hash相同，实际内容不同
*/
/*
* TreeNode extends LinkedHashMap.Entry extends HashMap.Node
*/
Node<K,V> e; K k;
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
/*
* 第一种情况，散列出的hash相同，并且key的实际值也相同
*/
e = p;
else if (p instanceof TreeNode)
/*
* 如果数组对象获取到的是TreeNode，通过TreeNode方法获取value
*/
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
else {
for (int binCount = 0; ; ++binCount) {
/*
* 递归处理赋值操作
*/
if ((e = p.next) == null) {
/*
* 如果hash值相同，实际值不同，并且下一节点值为空，则直接赋值给下一节点
*/
p.next = newNode(hash, key, value, null);
if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
/*递归的深度达到了预定阈值TREEIFY_THRESHOLD8的时候，转换成树进行存储*/
treeifyBin(tab, hash);
break;
}
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
/*如果下一节点的hash值相等，并且key实际值相等，则跳出循环*/
break;
p = e;
}
}
if (e != null) { // existing mapping for key
/*
* 最终计算出key值已存在，判断是否使用新value将旧value进行覆盖，并返回旧值
*/
V oldValue = e.value;
if (!onlyIfAbsent || oldValue == null)
e.value = value;
/*
* LinkedHashMap支持方法，LinkedHashMap中会对该方法进行实现
*/
afterNodeAccess(e);
return oldValue;
}
}
//被修改的次数加一
++modCount;
/*
* threshold下一次扩容的大小
* 当前容积如果大于下次扩容阈值，则进行扩容
*/
if (++size > threshold)
resize();
//LinkedHashMap支持方法，LinkedHashMap中会对该方法进行实现
afterNodeInsertion(evict);
return null;
}
final void treeifyBin(Node<K,V>[] tab, int hash) 源码解析
这是一个树化的方法，很多地方都有用到。
/**
* Replaces all linked nodes in bin at index for given hash unless
* table is too small, in which case resizes instead.
*/
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)
/*
* MIN_TREEIFY_CAPACITY 树化的阈值
* 如果小于阈值，进行resize()
* 只有当数组长度超过阈值才进行树化操作
*/
resize();
else if ((e = tab[index = (n - 1) & hash]) != null) {
/*
* 将key以下的所有next对象转换成树，并进行前后节点转换关联
*/
/*
* 第一次循环时，hd为空，tl为空，hd=p=e，tl=p=e，后续递归中hd时不变的，也就是说hd是Tree的根节点
*/
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)
/*
* 如果key的插入位置是有值的，继续进行下面这个不知道是什么的操作。
*/
hd.treeify(tab);
}
}
final void treeify(Node<K,V>[] tab) 难道这才是真正树化的过程吗，有点晕
/**
* Forms tree of the nodes linked from this node.
*/
final void treeify(Node<K,V>[] tab) {
TreeNode<K,V> root = null;
for (TreeNode<K,V> x = this, next; x != null; x = next) {
next = (TreeNode<K,V>)x.next;
x.left = x.right = null;
if (root == null) {
x.parent = null;
x.red = false;
root = x;
}
else {
K k = x.key;
int h = x.hash;
Class<?> kc = null;
for (TreeNode<K,V> p = root;;) {
int dir, ph;
K pk = p.key;
if ((ph = p.hash) > h)
dir = -1;
else if (ph < h)
dir = 1;
else if ((kc == null &&
(kc = comparableClassFor(k)) == null) ||
(dir = compareComparables(kc, k, pk)) == 0)
dir = tieBreakOrder(k, pk);
TreeNode<K,V> xp = p;
if ((p = (dir <= 0) ? p.left : p.right) == null) {
x.parent = xp;
if (dir <= 0)
xp.left = x;
else
xp.right = x;
root = balanceInsertion(root, x);
break;
}
}
}
}
moveRootToFront(tab, root);
}
final Node<K,V>[] resize() 初始化容器或扩容值拷贝
/**
* Initializes or doubles table size. If null, allocates in
* accord with initial capacity target held in field threshold.
* Otherwise, because we are using power-of-two expansion, the
* elements from each bin must either stay at same index, or move
* with a power of two offset in the new table.
*
* @return the table
*/
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)
/*
* 在这里进行了扩容阈值调整，调正大小为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
/*
* 这里进行了容积初始化，初始容积为 1 << 4 = 16
*/
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) {
/*
* 这里看着像是递归值copy
*/
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;
}
