Java集合（二）HashMap工作原理及扩容机制

JDK1.8中HashMap采用桶+链表+红黑树实现，当链表长度超过阈值（默认8）时，将链表转换为红黑树，以减少搜索时间。

首先每个元素都是链表（可能表述不准确）的数组，每添加一个元素（key-value）时，首先计算key的hashcode，以此确定元素的插入位置，有可能hashcode相同，那么存放在相同hashcode的元素的后面，他们在数组的同一位置的链表上。当链表长度超过阈值（默认8）时，则会转换为红黑树结构，减少搜索时间，提高查找效率。

以上为HashMap的原理图

2. JDK1.8版本中HashMap涉及到的数据结构

/**
     * The table, initialized on first use, and resized as
     * necessary. When allocated, length is always a power of two.
     * (We also tolerate length zero in some operations to allow
     * bootstrapping mechanics that are currently not needed.)
     * 【table，在首次使用的时候初始化，并且必须重新调整大小。当被分配的时候，长度为2的幂。（我们也允许长度为0，来允许当前不必要的引导程序结构/引导机制）】
     */
    transient Node<K,V>[] table;
复制代码

/**
     * Basic hash bin node, used for most entries.  (See below for
     * TreeNode subclass, and in LinkedHashMap for its Entry subclass.)
     * 【基础哈希二进制节点，用于大多数条目】
     */
    static class Node<K,V> implements Map.Entry<K,V> {
        //单项列表，实现了Map.Entry接口
        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;
        }

        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;
        }
        
        //判断两个node是否相等，key-value都相等返回true，与自身比较也返回true
        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;
        }
    }
复制代码

/**
     * Entry for Tree bins. Extends LinkedHashMap.Entry (which in turn
     * extends Node) so can be used as extension of either regular or
     * linked node.
     * 【二叉树条目。继承自LinkedHashMap.Map，所以可以作为常规胡总和linked node的扩展】
     */
    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;
        TreeNode(int hash, K key, V val, Node<K,V> next) {
            super(hash, key, val, next);
        }

        /**
         * Returns root of tree containing this node.
         * 【返回当前节点的根节点】
         */
        final TreeNode<K,V> root() {
            for (TreeNode<K,V> r = this, p;;) {
                if ((p = r.parent) == null)
                    return r;
                r = p;
            }
        }
        .
        .
        .
    }    
复制代码

3. HashMap的构造函数

/**
     * Constructs an empty <tt>HashMap</tt> with the specified initial
     * capacity and load factor.
     *
     * @param  initialCapacity the initial capacity
     * @param  loadFactor      the load factor
     * @throws IllegalArgumentException if the initial capacity is negative
     *         or the load factor is nonpositive
     */
    public HashMap(int initialCapacity, float loadFactor) {
        //initialCapacity:初始容量；loadFactor：记载因子/填充比，默认0.75
        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);
    }

    /**
     * Constructs an empty <tt>HashMap</tt> with the specified initial
     * capacity and the default load factor (0.75).
     *
     * @param  initialCapacity the initial capacity.
     * @throws IllegalArgumentException if the initial capacity is negative.
     */
    public HashMap(int initialCapacity) {
        this(initialCapacity, DEFAULT_LOAD_FACTOR);
    }

    /**
     * Constructs an empty <tt>HashMap</tt> with the default initial capacity
     * (16) and the default load factor (0.75).
     */
    public HashMap() {
        this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted
    }

    /**
     * Constructs a new <tt>HashMap</tt> with the same mappings as the
     * specified <tt>Map</tt>.  The <tt>HashMap</tt> is created with
     * default load factor (0.75) and an initial capacity sufficient to
     * hold the mappings in the specified <tt>Map</tt>.
     *
     * @param   m the map whose mappings are to be placed in this map
     * @throws  NullPointerException if the specified map is null
     */
    public HashMap(Map<? extends K, ? extends V> m) {
        this.loadFactor = DEFAULT_LOAD_FACTOR;
        putMapEntries(m, false);
    }
复制代码

4. HashMap的存取

get

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

    /**
     * Implements Map.get and related methods
     *
     * @param hash hash for key
     * @param key the key
     * @return the node, or null if none
     */
    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)
                    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;
    }
复制代码

get(key)首先获取key的hashcode，计算hash&(n-1)得到在数组中位置，得到位置之后，先判断与第一个元素是否相等，如果不等就遍历该数组位置上的链表后面的元素，找到返回value，找不到返回null。

put

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

    /**
     * Implements Map.put and related methods
     *
     * @param hash hash for key
     * @param key the key
     * @param value the value to put
     * @param onlyIfAbsent if true, don't change existing value
     * @param evict if false, the table is in creation mode.
     * @return previous value, or null if none
     */
    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;
    }
复制代码

put(key,value)先判断节点数组是否为空或者null，如果为空，就resize为默认大小。根据key计算hashcode，如果根据hashcode值，在数组中找不到相同hashcode的元素，则直接新建一个节点，即数组中节点+1，否则判断当前数组中处理hash冲突的方式是链表还是红黑树。

5. 扩容机制

构建Hash表时，如不指明初始大小，则默认大小16，如果Node数组的大小达到【填充比*length】，则扩容大小为原来的2倍。

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) {
            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;
    }
复制代码

6. 关于JDK1.8中红黑树的使用

JDK中使用链表，查询时间是O(n)，在JDK1.8中当链表长度大于阈值（默认8）时，采用红黑树（查询时间是n(logN)），有效提高查找效率。

当超过阈值后，采用二叉树，使用哈希值作为树的分支变量，如果两个哈希值不等，但指向同一个桶，较大的会插入到右子树中。如果哈希值相等，HashMap希望key值最好实现了Comparable接口，这样就可以按顺序插入，当然这不是必要的，但如果发生严重的哈希碰撞，这能有效解决哈希碰撞带来的性能问题。