以jdk1.8中的HashMap源码进行分析。
继承关系
public class HashMap<K,V> extends AbstractMap<K,V>
implements Map<K,V>, Cloneable, Serializable
其中,AbstractMap是对Map接口骨干实现,以最小化实现Map接口所需工作。
Node结构
是HashMap的静态内部类,实现了Map.Entry接口。
static class Node<K,V> implements Map.Entry<K,V> {
final int hash; //定位数组索引的位置
final K key;
V value;
Node<K,V> next; //hash值相同的元素通过next串联
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;
}
// 判断两个node是否相等,若key和value都相等,返回true
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;
}
}
类的属性
// 默认容量16,容量需要为2的幂次方。
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16
//容量上限2^30
static final int MAXIMUM_CAPACITY = 1 << 30;
//负载因子,默认0.75
static final float DEFAULT_LOAD_FACTOR = 0.75f;
//树形化门限
static final int TREEIFY_THRESHOLD = 8;
//恢复链表结构门限
static final int UNTREEIFY_THRESHOLD = 6;
//最小树形化容量
//HashMap容量大于64,才可能进行树形化,否则只会扩容。
//要求该值不小于4 * TREEIFY_THRESHOLD
static final int MIN_TREEIFY_CAPACITY = 64;
// 存放元素的数组,大小为2的幂次方
transient Node<K,V>[] table;
//存放具体元素的集
transient Set<Map.Entry<K,V>> entrySet;
//元素个数
transient int size;
//记录结构修改次数,failfast用
transient int modCount;
//临界值,当容量*负载因子超过临界值,会扩容
int threshold;
//负载因子
final float loadFactor;
构造函数
HasMap(int, float)型构造函数
// 满足初始容量不小于0,不大于最大值,填充因子大于0且为数字
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);
}
tableSizeFor (cap):返回大于initialCapacity的最小的2的幂次方。
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;
}
HashMap(int)型:
public HashMap(int initialCapacity) {
this(initialCapacity, DEFAULT_LOAD_FACTOR);
}
HashMap()型:
public HashMap() {
this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted
}
HashMap(Map<? extends K>)型:
public HashMap(Map<? extends K, ? extends V> m) {
this.loadFactor = DEFAULT_LOAD_FACTOR;
//将m中所有元素添加至HashMap中
putMapEntries(m, false);
}
putMapEntries将Map中所有元素添加至HashMap中:
final void putMapEntries(Map<? extends K, ? extends V> m, boolean evict) {
int s = m.size();
if (s > 0) {
//未初始化,s为元素个数
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);
}
//初始化大于阈值,扩容
else if (s > threshold)
resize();
//添加
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);
}
}
}
hash方法
获取key的hashCode(),将其右移16位与原hashCode进行异或运算,返回结果。使数组长度较短时让hashCode的高位也起作用。
static final int hash(Object key) {
int h;
return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}
put方法
put方法中调用了putVal:
public V put(K key, V value) {
//hash是针对key计算hashcode()
return putVal(hash(key), key, value, false, true);
}
putVal:
final V putVal(int hash, K key, V value, boolean onlyIfAbsent,
boolean evict) {
Node<K,V>[] tab; Node<K,V> p; int n, i;
// 判断数组是否为空或者null,否则resize扩容
if ((tab = table) == null || (n = tab.length) == 0)
n = (tab = resize()).length;
//计算hash值所在数组下标,确定存储在哪个桶里,如果桶为空,新生成一个系欸点放在桶中(直接插入数组中)
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null);
//桶中有元素
else {
Node<K,V> e; K k;
// 桶中第一个元素hash相等,key相等
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
e = p;
//红黑树
else if (p instanceof TreeNode)
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
// 链表
else {
// 在链表末尾插入节点
for (int binCount = 0; ; ++binCount) {
// 到达链表尾部
if ((e = p.next) == null) {
p.next = newNode(hash, key, value, null);
//树形化阈值,转换
if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
treeifyBin(tab, hash);
break;
}
// 在链表中判断元素key值相等
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
break;
// 前面是e = p.next, 赋值用于遍历
p = e;
}
}
//在链表的第一个节点(数组中)或者在链表中找到了key,hash相等
//此时e不为null(被赋值为p,或没判断到末尾就相等跳出)
if (e != null) { // existing mapping for key
V oldValue = e.value;
if (!onlyIfAbsent || oldValue == null)
e.value = value;
// 访问后回调
afterNodeAccess(e);
// 返回旧值
return oldValue;
}
}
// put属于结构性修改
++modCount;
// 判断扩容
if (++size > threshold)
resize();
//插入后回调
afterNodeInsertion(evict);
return null;
}
其中,计算hash值对应桶的下标时,通过:
i = (n - 1) & hash
a % b = (b - 1) & a, when b = 2k
比起取模运算,位运算效率更高。
同时,对于长度为2k的情况,(n - 1)生成111…1的形式,可作为掩码,与hash值进行位与运算时,可以得到较均匀分布的结果。
resize()方法
每次插入操作后都需要判断是否需要扩容。
final Node<K,V>[] resize() {
Node<K,V>[] oldTab = table; //指向旧的hash桶数组
int oldCap = (oldTab == null) ? 0 : oldTab.length; //未初始化就设为0
int oldThr = threshold;
int newCap, newThr = 0;
if (oldCap > 0) {
if (oldCap >= MAXIMUM_CAPACITY) { //大于最大容量就设为最大整数
threshold = Integer.MAX_VALUE;
return oldTab;
}
else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY &&
oldCap >= DEFAULT_INITIAL_CAPACITY)
newThr = oldThr << 1; // double threshold 容量*2
}
else if (oldThr > 0) // initial capacity was placed in threshold
newCap = oldThr; //之前的cap为0,threshold不为0,设为thr.
else { // zero initial threshold signifies using defaults 都采取默认值
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]; //新的hash桶数组
table = newTab; //table指向新数组
if (oldTab != null) {
for (int j = 0; j < oldCap; ++j) { //对于旧数组中的每一个桶,遍历
Node<K,V> e;
if ((e = oldTab[j]) != null) { //这个桶在j处不为空
oldTab[j] = null; //置空,方便gc
if (e.next == null) //桶里只有一个Node
newTab[e.hash & (newCap - 1)] = e; //对e元素hash求新的存储位置并放进去
else if (e instanceof TreeNode) //树节点
((TreeNode<K,V>)e).split(this, newTab, j, oldCap); //离散化
else { // 链表形式,设两个链表,分别有头尾指针
Node<K,V> loHead = null, loTail = null;
Node<K,V> hiHead = null, hiTail = null;
Node<K,V> next;
do {
next = e.next; //取链表中每个节点
if ((e.hash & oldCap) == 0) { //最高位为0,插在lo链表尾部
if (loTail == null)
loHead = e;
else
loTail.next = e;
loTail = e;
}
else { // 最高位为1,插在hi链表尾部
if (hiTail == null)
hiHead = e;
else
hiTail.next = e;
hiTail = e;
}
} while ((e = next) != null);
if (loTail != null) {
loTail.next = null;
newTab[j] = loHead; //lo链表连接到原来的j位置
}
if (hiTail != null) {
hiTail.next = null;
newTab[j + oldCap] = hiHead; //hi链表连接到j+oldCap位置
}
}
}
}
}
return newTab;
}
上面重新计算hash桶索引的代码:
e.hash & oldCap
在扩容前后,容量变为2倍,(n - 1) & hash实际上是多了一个最高位的bit位,因此做&操作时,如果hash值该位为0,就还是在原来的位置,否则就会在“原位置+旧容量”的位置上。因此在判断应属位置后,分别用两个链表存储扩容后一个旧位置对应两个新位置应有的元素,再插入新数组中。同时,保证新数组中每个桶中的节点数一定不大于旧桶,不会有更严重的冲突。
get方法
get方法是通过getNode来取得元素的。
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;
// table已初始化,长度大于0,通过hash找到的桶中元素不为空
if ((tab = table) != null && (n = tab.length) > 0 &&
(first = tab[(n - 1) & hash]) != null) {
if (first.hash == hash && // 第一项元素就相等
((k = first.key) == key || (key != null && key.equals(k))))
return first;
//不止一个节点
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;
}
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;
// hash计算的桶有元素
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)))) //第一个元素一致
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; //要移除的node存储下来
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; //第一个元素要移除,直接指向它的下一个
else
p.next = node.next; //链表中node指向p.next, 直接跳过node
++modCount; //remove是结构性改变
--size;
afterNodeRemoval(node); //回调
return node;
}
}
return null;
}
部分和红黑树有关的代码:
树的结构: 继承自LinkedHashMap
static final class TreeNode<K,V> extends LinkedHashMap.Entry<K,V> {
TreeNode<K,V> parent; // red-black tree links
TreeNode<K,V> left;
TreeNode<K,V> right;
TreeNode<K,V> prev; // needed to unlink next upon deletion
boolean red;
TreeNode(int hash, K key, V val, Node<K,V> next) {
super(hash, key, val, next);
}
treeifyBin:在插入新元素后判断链表长度,是否需要树形化
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) //没有到最小树形化容量
resize(); //直接扩容
else if ((e = tab[index = (n - 1) & hash]) != null) { //e为首节点
TreeNode<K,V> hd = null, tl = null; //树的首尾节点
do {
TreeNode<K,V> p = replacementTreeNode(e, null); //该节点转化为TreeNode节点
if (tl == null) // 尾节点为空,树没有根节点
hd = p; // 将首节点(根节点)指向当前节点
else { // 双向链表
p.prev = tl;
tl.next = p;
}
tl = p; //当前节点为尾节点
} while ((e = e.next) != null);
if ((tab[index] = hd) != null)
hd.treeify(tab); //树形化
}
}
treeify :真正的树形化
final void treeify(Node<K,V>[] tab) {
TreeNode<K,V> root = null; //定义根节点
for (TreeNode<K,V> x = this, next; x != null; x = next) {
next = (TreeNode<K,V>)x.next; //下一个节点
x.left = x.right = null;
if (root == null) { //没有根节点
x.parent = null;
x.red = false; //当前节点为黑节点
root = x; // 根节点指向当前节点
}
else { //有根节点
K k = x.key; //当前链表节点的key
int h = x.hash; //key对应的hash
Class<?> kc = null;
for (TreeNode<K,V> p = root;;) { // 从根节点开始遍历
int dir, ph; // 记录方向,hash值
K pk = p.key;
if ((ph = p.hash) > h) //当前树的hash大于链表节点hash
dir = -1; //向左
else if (ph < h)
dir = 1; //向右
//两个节点key的hash值相等,comparable比较,tieBreakOrder比较
else if ((kc == null &&
(kc = comparableClassFor(k)) == null) ||
(dir = compareComparables(kc, k, pk)) == 0)
dir = tieBreakOrder(k, pk);
TreeNode<K,V> xp = p; //保存当前树节点
// 叶节点
if ((p = (dir <= 0) ? p.left : p.right) == null) {
x.parent = xp;
if (dir <= 0)
xp.left = x; //作为左孩子
else
xp.right = x; //作为右孩子
root = balanceInsertion(root, x); //重新平衡
break;
}
}
}
}
//把红黑树的根节点设为其所在的桶的第一个元素
moveRootToFront(tab, root);
}