Java集合--HashMap源码
本文基于JKD1.8
1.关键的属性：
//默认容量
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16
//最大容量
static final int MAXIMUM_CAPACITY = 1 << 30;
//默认负载因子
static final float DEFAULT_LOAD_FACTOR = 0.75f;
//链表树化的阀值
static final int TREEIFY_THRESHOLD = 8;
//树形转为链表的阀值
static final int UNTREEIFY_THRESHOLD = 6;
//树化要求的node容量
static final int MIN_TREEIFY_CAPACITY = 64;
//实际存放节点的数组
transient Node<K,V>[] table;
//KV的Set，相当于一个快照
transient Set<Map.Entry<K,V>> entrySet;
//存储的节点的个数
transient int size;
//fial-fast机制的modify count个数
transient int modCount;
//容量×负载因子得到的阈值，超过该阈值进行扩容
int threshold;
//负载因子
final float loadFactor;
2.构造函数
构造函数可以自定义初始化容量和负载因子的大小，其中初始化容量会自动提升为2的n幂次(n>31)，提升容量的算法tableSizeFor写的很好
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);
}
/**
* 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;
}
n |= n>>>1的作用是将n的二进制中第一个1和这个1的右边一位按位与，结果赋值给n；也就是n的非0最高位起，前两位变成了1；
n |= n>>>2的作用是将n的二进制中非0最高位中的前两位和n按位与，结果赋值给n；也就是n的非0最高位起，前四位变成1了；
以此类推...
n的非0最高位到最低位都是1，然后return n+1,得到最接近的2的幂次
3.新增方法
再来看下关键的put方法，put方法会设置map中key对应的value，如果该key存在，覆盖旧值，并将其返回；
/**
* 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);
}
hash()将key的高16位拿来参与运算，这样做的目的是减少哈希碰撞，因为只取低位的值作为hash，碰撞很严重；参考：JDK 源码中 HashMap 的 hash 方法原理是什么？
static final int hash(Object key) {
int h;
return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}
putVal()方法是新增节点的实际方法
/**
* 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) //空map，按照默认大小或指定参数开辟空间，lazy init
n = (tab = resize()).length;
if ((p = tab[i = (n - 1) & hash]) == null) // key的hash值在map中的value如果是空的，
tab[i] = newNode(hash, key, value, null);//赋新值
else { //hash位置已存在旧值
Node<K,V> e; K k;
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k)))) //p的值是hash对应的旧的node节点，如果p的key和参数key值相等的话，e = p
e = p;
else if (p instanceof TreeNode) //旧值的key和参数key不相等，并且如果p是树节点，将新的KV放入树里
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
else {//旧值的key和参数key不相等
for (int binCount = 0; ; ++binCount) {
if ((e = p.next) == null) { //当前节点是不是链表的尾节点
p.next = newNode(hash, key, value, null); //在尾节点新增参数KV
if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st //在链表的尾节点判断链表节点的个数是否满足树化的条件
treeifyBin(tab, hash);
break;
}
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))//在链表中找和参数key同值或相等的key
break;
p = e;
}
}
if (e != null) { // existing mapping for key //e这个节点的作用就是保存以前存在的旧值，用来return
V oldValue = e.value;
if (!onlyIfAbsent || oldValue == null)
e.value = value;
afterNodeAccess(e);
return oldValue;
}
}
++modCount;
if (++size > threshold)//当前节点的个数是否大于阈值
resize(); //翻倍扩容数组
afterNodeInsertion(evict);//给LinkedHashMap留的坑位，便于插入节点后处理
return null;
}
现在putTreeVal()、treeifyBin()这两个树化操作还有待分析
4.resize()扩容方法
/**
* 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; //定义新表容量、新表的阀值
if (oldCap > 0) { //旧表的容量大于0
if (oldCap >= MAXIMUM_CAPACITY) { //旧表容量阀值超过定义的最大容量(2的30次方)
threshold = Integer.MAX_VALUE; //不扩容，但是调整容量阀值为整形的最大值
return oldTab;
}
else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY && //原来容量小于1<<30时，新容量为原来容量的二倍
oldCap >= DEFAULT_INITIAL_CAPACITY)
newThr = oldThr << 1; // double threshold
}
else if (oldThr > 0) // initial capacity was placed in threshold //旧表容量小于等于0并且旧表阀值大于0
newCap = oldThr; //新表容量等于旧表阀值
else { // zero initial threshold signifies using defaults //旧表容量和阀值都小于等于0
newCap = DEFAULT_INITIAL_CAPACITY; //无参初始化，默认容量16，阀值12
newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);
}
if (newThr == 0) { //如果没翻倍扩容，也没走默认容量，例如：oldCap<<29,newCap为1<<30时
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) { //遍历旧数组
Node<K,V> e;
if ((e = oldTab[j]) != null) { //数组元素不为空
oldTab[j] = null;
if (e.next == null) //数组元素不是链表，也不是树形结构，即没有hash冲突，只有一个元素的时候
newTab[e.hash & (newCap - 1)] = e; //rehash到新表
else if (e instanceof TreeNode) //红黑树的mapping
((TreeNode<K,V>)e).split(this, newTab, j, oldCap);
else { // preserve order //维持原来顺序，并且是两条链表(loHead,hiHead)，分别进行尾插法
Node<K,V> loHead = null, loTail = null;//low位置链表，位置=原表位置
Node<K,V> hiHead = null, hiTail = null;//high位置链表，位置=原表位置+原表大小
Node<K,V> next;
do {
next = e.next;
if ((e.hash & oldCap) == 0) {//rehash落在和原表相同的位置的元素
if (loTail == null)
loHead = e;
else
loTail.next = e;
loTail = e;
}
else {//rehash落在后半部分的元素
if (hiTail == null)
hiHead = e;
else
hiTail.next = e;
hiTail = e;
}
} while ((e = next) != null);
if (loTail != null) {
loTail.next = null;
newTab[j] = loHead; //前一半
}
if (hiTail != null) {
hiTail.next = null;
newTab[j + oldCap] = hiHead; //后一半
}
}
}
}
}
return newTab;
}
- Q:为什么最大容量是2的30次方？
- A:如果是32位整型的最大值(2的31次方-1)，就不能构成翻倍扩容
- Q:会造成Java1.7的多线程死循环问题吗？
- A:不会，因为都是尾插法，不会形成环形结构
假设原数组大小为4，阀值也是4。四个冲突的元素链表如下：
扩容到8的时候，重新hash后得到两个链表：
5.根据key获取value
获取value主要是get()方法
public V get(Object key) {
Node<K,V> e;
return (e = getNode(hash(key), key)) == null ? null : e.value;
}
/**
* Implements Map.get and related methods
*
* @param hash hash for key
* @param key the key
* @return the node, or null if none
*/
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) {//根据hash与数组按位与得到第一个节点
if (first.hash == hash && // always check first node //判断第一个节点与key是否相等或值相等
((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);//在树中获取节点
do {//在链表中获取节点
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
return e;
} while ((e = e.next) != null);
}
}
return null;
}
在树中获取节点getTreeNode()还有待分析
