HashMap源码分析

Posted 2020-11-07 jiaqirumeng

在java中，hashmap是一种非常重要的数据结构，现在我们来分析一下它的实现逻辑。

我们知道hashmap是存储键值对的结构，它的存储和查询都很快，而基于数组的ArrayList有较快的查询速度，和基于链表的LinendList有很好的易修改性能

hashmap则是结合了这两者的优点，大概长这样

HashMap的成员变量

static final int DEFAULT_INITIAL_CAPACITY = 1 << 4;//16 数组初始大小

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

static final float DEFAULT_LOAD_FACTOR = 0.75f;//默认加载因子

static final int TREEIFY_THRESHOLD = 8;//树化阈值 链表转成树型结构的关键值

static final int UNTREEIFY_THRESHOLD = 6;//

static final int MIN_TREEIFY_CAPACITY = 64;


transient Node<K,V>[] table;//数据实际存储位置，node数组

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

transient int size;//键值对数量

transient int modCount;//修改次数   

int threshold;//阈值--数组扩容相关

final float loadFactor;//加载因子

 

HashMap构造函数

    public HashMap(int initialCapacity, float loadFactor) {
        if (initialCapacity < 0)//初始容量不能小于0
            throw new IllegalArgumentException("Illegal initial capacity: " +
                                               initialCapacity);
        if (initialCapacity > MAXIMUM_CAPACITY)//初始容量超出最大值，设置为默认最大容量
            initialCapacity = MAXIMUM_CAPACITY;
        if (loadFactor <= 0 || Float.isNaN(loadFactor))
            throw new IllegalArgumentException("Illegal load factor: " +
                                               loadFactor);
        this.loadFactor = loadFactor;//设置加载因子
        this.threshold = tableSizeFor(initialCapacity);
    }

 

 

 HashMap的存储单元

 包含一个hash值，Key Value 和下一个节点引用

    static class Node<K,V> implements Map.Entry<K,V> {
        final int hash;
        final K key;//确保key不会被修改
        V value;
        Node<K,V> next;//链表结构，持有下一个元素的引用，方便获取下一个元素

        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;
        }

        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 添加键值对

    public V put(K key, V value) {
        return putVal(hash(key), key, value, false, true);
    }

　　//1.计算hash值
    static final int hash(Object key) {
        int h;
        return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
    }

    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;//容器初始化
        if ((p = tab[i = (n - 1) & hash]) == null)//计算数组下标，获取这个下标的对象，若为空，存入新对象
            tab[i] = newNode(hash, key, value, null);
        else {//若这个下标已经有了对象
            Node<K,V> e; K k;
            if (p.hash == hash &&
                ((k = p.key) == key || (key != null && key.equals(k))))//判断hash值和key是否和这个对象的一样，如果一样说明key是一样，替换原有键值对
                e = p;
            else if (p instanceof TreeNode)//如果不一样(hash冲突)，判断是否是树型节点
                e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);//插入树型节点
            else {//hash冲突，非树型节点，往链表后插入数据
                for (int binCount = 0; ; ++binCount) {
                    if ((e = p.next) == null) {//链表下一个节点为空，放到下一个
                        p.next = newNode(hash, key, value, null);
                        if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st 链表长度达到树型化阈值，节点转化为树型节点
                            treeifyBin(tab, hash);
                        break;
                    }
                    if (e.hash == hash &&
                        ((k = e.key) == key || (key != null && key.equals(k))))//hash相同 键相同 跳出循环处理
                        break;
                    p = e;//指针下移
                }
            }
            if (e != null) { // existing mapping for key  跳出循环处理：已存在键值对 直接替换原有值
                V oldValue = e.value;
                if (!onlyIfAbsent || oldValue == null)
                    e.value = value;
                afterNodeAccess(e);
                return oldValue;
            }
        }
        ++modCount;
        if (++size > threshold)//键值对数量达到阈值，扩容
            resize();
        afterNodeInsertion(evict);
        return null;
    }

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)
                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) {//扩容处理
            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;//重新计算下标，并赋值
                    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;
    }

    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)
            resize();
        else if ((e = tab[index = (n - 1) & hash]) != null) {
            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)
                hd.treeify(tab);
        }
    }

有几个值得注意的点：

1.hash值计算  

h = key.hashCode()) ^ (h >>> 16

这是将int类型的值右移16位，得到的h 和int的所有位数相关，保证了散列性(降低hash冲突可能性)。

2.数组下标计算

i = (n - 1) & hash

这里使用 & 保证下标不会超出 n - 1，& hash 保证了下标的散列性