Java集合 - HashMap - JDK1.8

HashMap

HashMap是以键值对进行存储的集合，其中键值是唯一的，HashMap是无序的。

改变

1.7版本的HashMap使用的数组+链表的存储方式。

1.8版本的HashMap使用的数组+链表或者数组+红黑树的存储方式，当链表长度大于某值时，链表就会转化为红黑树。当红黑树节点数小于某值时会转化为链表。虽然存入操作变得复杂，但是提高了查询的效率。

源码分析

首先看一下重要的属性。

//数组的最小容量2的4次方   16
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4;

//数组的最大容量2的30次方
static final int MAXIMUM_CAPACITY = 1 << 30;

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

//当链表长度大于该值，链表转化为红黑树。  
static final int TREEIFY_THRESHOLD = 8;

//当红黑树节点小于该值，红黑树转化为链表。
static final int UNTREEIFY_THRESHOLD = 6;

//扩容的阀值，当（加载因子 * 元素个数）大于阀值就会进行resize操作进行扩容。
int threshold;

//加载因子
final float loadFactor;

构造方法

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);
    }

//找到容量的最近二次幂的值
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;
    }

这里有一个问题延伸，为什么数组长度一定是2的倍数？
一共有两点原因：
（1）在数组长度h是2的幂次时候h & (length - 1) 与 h % length的结果是相同的，但不是等效的，位运算要快的多。这样可以提升效率。
（2）在数组长度h是2的幂次时候，散列的更加均匀。

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;
        if ((tab = table) == null || (n = tab.length) == 0)
            n = (tab = resize()).length;
/**
* p = tab[i = (n - 1) & hash]这里就是散列操作，也就是用上数组长度为2次幂的精髓所在，相当于对数组长度取余。
* 获取这个位置的元素。
* 同时会知道这里的位置是链表还是红黑树，后面插入会用上。
**/
        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))))  //如果key值相同那么下面不执行，后面会用新的value覆盖点旧的value
                e = p;
            else if (p instanceof TreeNode)      //判断节点是什么类型，如果是树节点，就插入到红黑树中，不然就是链表中。
                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;
    }

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 {              
            //初始化table数组，就是一开始什么都没有的时候，初始化为默认长度16
            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) {
            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 newTab;
    }

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;
        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)      //判断是链表结构还是红黑树结构
                    return ((TreeNode<K,V>)first).getTreeNode(hash, key);  //红黑树查找
                do {      //链表查找
                    if (e.hash == hash &&
                        ((k = e.key) == key || (key != null && key.equals(k))))
                        return e;
                } while ((e = e.next) != null);
            }
        }
        return null;
    }