HashMap探究

HashMap

前置

//初始化容量
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; 
//容器最大容量
static final int MAXIMUM_CAPACITY = 1 << 30;
//负载因子，在0.75的时候扩大。比如16的时候，12扩大    12/16=0.75
static final float DEFAULT_LOAD_FACTOR = 0.75f;
//Node超过8时，转换为红黑树。
//查找由链表的O(n)转换为O(log(n)) 对数级
static final int TREEIFY_THRESHOLD = 8;

Node

  static class Node<K,V> implements Map.Entry<K,V> {
        final int hash;
        final K key;
        V value;
        Node<K,V> next;

        Node(int hash, K key, V value, Node<K,V> next) {
            this.hash = hash;
            this.key = key;
            this.value = value;
            this.next = next;
        }

数组：

 transient Node<K,V>[] table;

put操作

 final V putVal(int hash, K key, V value, boolean onlyIfAbsent, boolean evict) {
        Node<K,V>[] tab; Node<K,V> p; int n, i;
        //为空则初始化Node[]数组
        if ((tab = table) == null || (n = tab.length) == 0)
            n = (tab = resize()).length;
        //判读数组位置是否有Node占据，如果没有，直接复制
        if ((p = tab[i = (n - 1) & hash]) == null)
            tab[i] = newNode(hash, key, value, null);
        //数据已占据，采取链表
        else {
            Node<K,V> e; K k;
            //hash和key相等,则更新值就可以了
            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 {
                //p相当于数组坐标的位置
                //把数据插入链表
                for (int binCount = 0; ; ++binCount) {
                    if ((e = p.next) == null) {
                        p.next = newNode(hash, key, value, null);
                        //如果大于TREEIFY_THRESHOLD即是大于等于7，说明链表长度为8了，做转换操作
                        if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
                            treeifyBin(tab, hash);
                        break;
                    }
                    //判断hash和key是否相等，如果相等，则进行更新操作
                    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;
            }
        }
        //修改次数
        ++modCount;
         //数组到底用了多少个格子
        //threshold记录的是当前数组格子用了多少，超出大小*负载因子则需要扩容
        if (++size > threshold)
            resize();
        afterNodeInsertion(evict);
        return null;
    }

get操作

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

hash操作

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

resize

 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;
            }
            //扩容数组，位移效率更高
            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"})
            //分配内存地址
            Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap];
        table = newTab;
        //雨露均沾
        if (oldTab != null) {
            for (int j = 0; j < oldCap; ++j) {
                Node<K,V> e;
                //如果数组位置有值
                if ((e = oldTab[j]) != null) {
                    oldTab[j] = null;
                    //数组下有链表进入
                    if (e.next == null)
                        newTab[e.hash & (newCap - 1)] = e;
                        //是二叉树，进行二叉树的拆分方式
                    else if (e instanceof TreeNode)
                        ((TreeNode<K,V>)e).split(this, newTab, j, oldCap);
                        //链表的拆分方式
                    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;
                            }
                            //很体现循环遍历的地方
                        } 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;
    }

问题要点

数据结构：链表+数组

// 链表
node{
    object key
    object value
    Node next
}
//数组
elemDate[]

hash函数实现

    static final int hash(Object key) {
        int h;
        //低16位和高16位异或，右移后异或，保证hash分散，降低重复率。防止数组后面的链表过长，尽可能用齐数组
        return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
    } 

    public native int hashCode();

检查是否hash碰撞

  if ((p = tab[i = (n - 1) & hash]) == null)
            tab[i] = newNode(hash, key, value, null);

成员变量：threshold 记录数组用了多少。易混static final int TREEIFY_THRESHOLD = 8; 为链表转红黑树的大小。

        //数组到底用了多少个格子
        ++modCount;
        if (++size > threshold)
            resize();
        afterNodeInsertion(evict);
        return null;

        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;

resize()方法：Initializes or doubles table size 初始化或者双倍扩容 以双倍扩容 （n-1)&hash与也可以体现出来

////雨露均沾，链表上的值，分配到新的数组上
if (e.next == null)
                        newTab[e.hash & (newCap - 1)] = e;

                           if ((e.hash & oldCap) == 0) {
                                if (loTail == null)
                                    loHead = e;
                                else
                                    loTail.next = e;
                                loTail = e;
                            }