Java源码阅读之HashMap

1、知识汇总

HashMap的结构如下,绿色框是一个数组,数组的每一个元素都是一个单链表的头结点。红色框就是一个单链表,单链表用来解决冲突,如果不同的key值映射到了数组中的同一位置,则将其放到链表中。

Java源码阅读之HashMap_链表

HashMap中的结点重写了hashCode()方法和equals()方法,只有key和value都相等时,才认为两个结点相等,源码如下:

static class Node<K,V> implements Map.Entry<K,V> {
final int hash; // hash值
final K key; // key
V value; // value
Node<K,V> next; // 单链表中,下一个结点

// 构造方法
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; }

// 重写hashCode()
public final int hashCode() {
return Objects.hashCode(key) ^ Objects.hashCode(value);
}

public final V setValue(V newValue) {
V oldValue = value;
value = newValue;
return oldValue;
}

// 重写 equals方法
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;
}
}

HashMap与HashTable的对比:
1、二者的功能、存储结构、解决冲突的方法相似
2、HashTable的key, value都不能为null
3、HashMap线程不安全,HashTable是线程安全的

2、构造方法

HashMap初始容量默认为16,加载因子默认为0.75,当HashMap中的元素数量大于当前容量与加载因子的乘积时,HashMap就需要扩容。而扩容是比较耗时的操作,因此使用HashMap前,最好估计出HashMap的容量。

还有一点需要注意,HashMap的容量始终是2的n次方,且这个2的n次方大于HashMap的实际容量。举个例子,假如我们需要在HashMap中存储10个元素,则构造方法会将HashMap的初始容量设置为16(2^4)。

为什么要求HashMap的容量是2的n次方呢?
首先,在根据hash值求数组索引时,需要利用hash值对数组长度取模(除法散列)。比如:数组长度为8,hash值为9,则索引值index=9 % 8 == 1。当数组长度length为2的整数次方时,hash & (length-1)相当于对length取模,由于位运算比除法要快,所以要求length为2的n次方,这样我们就可以用位运算替代除法运算。

/**
* 使用初始容量和加载因子初始化HashMap
*/
public HashMap(int initialCapacity, float loadFactor) {
if (initialCapacity < 0)
throw new IllegalArgumentException("Illegal initial capacity: " +
initialCapacity);
// 不能超过最大容量(1 << 30)
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);
}

/**
* 使用初始容量初始化HashMap(加载因子默认为0.75)
*/
public HashMap(int initialCapacity) {
this(initialCapacity, DEFAULT_LOAD_FACTOR);
}

/**
* 无参的构造方法,初始容量默认为16
*/
public HashMap() {
this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted
}

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

3、扩容:resize()方法

/**
* 计算新的容量(大于cap的,最小的2的n次方)
* 话说这段位运算的代码,还没有搞懂,求大神指导
*/
static final int tableSizeFor(int cap) {
int n = cap - 1;
n |= n >>> 1; // 无符号右移
n |= n >>> 2;
n |= n >>> 4;
n |= n >>> 8;
n |= n >>> 16;
return (n < 0) ? 1 : (n >= MAXIMUM_CAPACITY) ? MAXIMUM_CAPACITY : n + 1;
}


/**
* 新建了一个HashMap底层数组,将容量扩大2倍
* 把全部元素添加到新的数组中
*/
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;
}
// 把容量扩大2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 { // 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) {
// 把原来HashMap中的键值对,重新映射到新HashMap中
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

4、插入、修改:put()方法

put方法有几点需要注意:
1、如果key为null,放到table[0]指向的单链表中
2、如果key不为null,计算hash值和数组索引,然后插入到该索引指向的单链表中(每次插入都是插入到头结点中)

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;
if ((p = tab[i = (n - 1) & hash]) == null)
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;
}

5、删除:remove()方法

/**
* 删除节点
*/
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;
}

/**
* 数组中的每个元素被设置为null,等待GC回收
*/
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;
}
}

6、查询:get()方法

查询主要用到get()方法,有两点需要注意:
1、key为null的键值对,存放在table[0]指向的单链表中
2、key不为null时,根据hash值找到table中的索引,在索引指向的单链表中查找键值对

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

/**
* 先根据hash值定位到数组中的某个位置
* 然后遍历该位置指向的单链表进行查找
*/
final Node<K,V> getNode(int hash, Object key) {
Node<K,V>[] tab; // table的副本
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;
}

今天就到这里吧,拜拜~