HashMap源代码

1. 简介

在JDK1.6中，HashMap采用位桶+链表实现，即使用链表处理冲突，同一hash值的链表都存储在一个链表里。但是当位于一个桶中的元素较多，即hash值相等的元素较多时，通过key值依次查找的效率较低。而JDK1.8中，HashMap采用位桶+链表+红黑树实现，当链表长度超过阈值时，将链表转换为红黑树，这样大大减少了查找时间。

2. 数据结构

Node

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

//如果key, value都相等表示两个Node相等
public final boolean equals(Object o) {
if (o == this)
return true;
if (o instanceof Map.Entry) {
//注意
Map.Entry<?,?> e = (Map.Entry<?,?>)o;
if (Objects.equals(key, e.getKey()) &&
Objects.equals(value, e.getValue()))
return true;
}
return false;
}
}

红黑树

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;  //结点颜色属性
TreeNode(int hash, K key, V val, Node<K,V> next) {
super(hash, key, val, next);
}

//其他部分未列出
...
}

Node数组

transient Node<K,V>[] table;

当添加一个元素（key-value）时，就首先计算元素key的hash值，以此确定插入数组中的位置，但是可能存在同一hash值的元素已经被放在数组同一位置了，这时就添加到同一hash值的元素的后面，他们在数组的同一位置，但是形成了链表，所以说数组存放的是链表。而当链表长度太长时，链表就转换为红黑树，这样大大提高了查找的效率。

3. 属性

public class HashMap<K,V> extends AbstractMap<K,V> implements Map<K,V>, Cloneable, Serializable {

private static final long serialVersionUID = 362498820763181265L;

static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16

static final int MAXIMUM_CAPACITY = 1 << 30;//最大容量

static final float DEFAULT_LOAD_FACTOR = 0.75f;//填充比

//当put一个元素到某个位桶，其链表长度达到8时将链表转换为红黑树
static final int TREEIFY_THRESHOLD = 8;

static final int UNTREEIFY_THRESHOLD = 6;

static final int MIN_TREEIFY_CAPACITY = 64;

transient Node<K,V>[] table;//存储元素的数组

transient Set<Map.Entry<K,V>> entrySet;

transient int size;//存放元素的个数

transient int modCount;//被修改的次数fast-fail机制

int threshold;//临界值 当实际大小(容量*填充比)超过临界值时，会进行扩容
//后面省略...

4. 构造函数

//构造函数1
public HashMap(int initialCapacity, float loadFactor) {
//指定的初始容量非负
if (initialCapacity < 0)
throw new IllegalArgumentException("Illegal initial capacity: " +
initialCapacity);
//如果指定的初始容量大于最大容量,置为最大容量
if (initialCapacity > MAXIMUM_CAPACITY)
initialCapacity = MAXIMUM_CAPACITY;
//填充比为正
if (loadFactor <= 0 || Float.isNaN(loadFactor))
throw new IllegalArgumentException("Illegal load factor: " +
loadFactor);
this.loadFactor = loadFactor;
this.threshold = tableSizeFor(initialCapacity);//新的扩容临界值
}

//构造函数2
public HashMap(int initialCapacity) {
this(initialCapacity, DEFAULT_LOAD_FACTOR);
}

//构造函数3
public HashMap() {
this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted
}

//构造函数4用m的元素初始化散列映射
public HashMap(Map<? extends K, ? extends V> m) {
this.loadFactor = DEFAULT_LOAD_FACTOR;
putMapEntries(m, false);
}

5. 扩容

//可用来初始化HashMap大小 或重新调整HashMap大小 变为原来2倍大小
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) {//超过1>>30大小,无法扩容只能改变 阈值
threshold = Integer.MAX_VALUE;
return oldTab;
}
else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY &&
oldCap >= DEFAULT_INITIAL_CAPACITY)//新的容量为旧的2倍 最小也是16
newThr = oldThr << 1; // 扩容阈值加倍
}
else if (oldThr > 0)
newCap = oldThr;//oldCap=0 ,oldThr>0此时newThr=0
else {               //oldCap=0,oldThr=0 相当于使用默认填充比和初始容量 初始化
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];
//数组辅助到新的数组中，分红黑树和链表讨论
table = newTab;
if (oldTab != null) {
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;
//红黑树的情况
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 {
//尾插法插入结点
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;
}

6. HashMap的get和put方法

注意HashMap中key和value都容许为null

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;
//hash & (length-1)得到对象的保存位
if ((tab = table) != null && (n = tab.length) > 0 &&
(first = tab[(n - 1) & hash]) != null) {
//判 断hash key
if (first.hash == hash && // always检查第一个结点
((k = first.key) == key || (key != null && key.equals(k))))
return first;
if ((e = first.next) != null) {
//如果第一个节点是TreeNode,说明采用的是数组+红黑树结构处理冲突
//遍历红黑树，得到节点值
if (first instanceof TreeNode)
return ((TreeNode<K,V>)first).getTreeNode(hash, key);
//链表结构处理
do {
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
return e;
} while ((e = e.next) != null);
}
}
return null;
}

put方法

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) {
Node<K,V>[] tab; Node<K,V> p; int n, i;
//如果tab为空或长度为0，则分配内存resize()
if ((tab = table) == null || (n = tab.length) == 0)
n = (tab = resize()).length;
//(n - 1) & hash找到put位置，如果为空,则直接put
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null);
else {
Node<K,V> e; K k;
//第一节节点hash值同，且key值与插入key相同
if (p.hash == hash &&((k = p.key) == key || (key != null && key.equals(k))))
e = p;
else if (p instanceof TreeNode)//属于红黑树处理冲突
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
else {
//链表处理冲突
for (int binCount = 0; ; ++binCount) {
//p第一次指向表头,以后依次后移
if ((e = p.next) == null) {
//e为空，表示已到表尾也没有找到key值相同节点，则新建节点
p.next = newNode(hash, key, value, null);
//新增节点后如果节点个数到达阈值，则将链表转换为红黑树
if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
treeifyBin(tab, hash);
break;
}
//容许null==null
if (e.hash == hash &&((k = e.key) == key || (key != null && key.equals(k))))
break;
p = e;//更新p指向下一个节点
}
}
//更新hash值和key值均相同的节点Value值
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;
}