java集合：HashMap

HashMap

常量

/**
 * 初始容量16，写作1 << 4是为了提示这是2的四次方
 * 初始容量如果过小会造成频繁的扩容，初始容量如果过大会造成内存浪费
 */
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16

/**
 * 最大容量必须为2的幂
 */
static final int MAXIMUM_CAPACITY = 1 << 30;

/**
 * 默认的负载因子
 * 均衡了时间和空间损耗算出来的值，较高的值会减少空间开销但增加了查找成本
 * 较小的值会造成空间浪费
 * 不扩容的条件：数组容量 > 需要的数组大小 /load factor
 */
static final float DEFAULT_LOAD_FACTOR = 0.75f;

/**
 * 链表转换为红黑树的链表长度阈值
 */
static final int TREEIFY_THRESHOLD = 8;

/**
 * 红黑树转换为链表的阈值
 */
static final int UNTREEIFY_THRESHOLD = 6;

/**
 * 链表转换为红黑树的数组长度阈值，如果数组长度小于64会先选择扩容
 */
static final int MIN_TREEIFY_CAPACITY = 64;

结点数据结构

static class Node<K,V> implements Map.Entry<K,V> {
    //节点hash
    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;
    }

    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;
    }
}

属性

 //如果存在并发修改会进行快速失败
 transient int modCount;

 //hashmap的实际大小
 transient int size;

 //存放节点的数组
 transient Node<K,V>[] table;

 //扩容阈值
 int threshold;
 
 //负载因子
 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;
    //设置初始扩容阈值为大于initialCapacity的最小2的幂
    this.threshold = tableSizeFor(initialCapacity);
}

//使用默认的负载因子赋值0.75
public HashMap(int initialCapacity) {
    this(initialCapacity, DEFAULT_LOAD_FACTOR);
}

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

public HashMap(Map<? extends K, ? extends V> m) {
    this.loadFactor = DEFAULT_LOAD_FACTOR;
    putMapEntries(m, false);
}

//返回大于cap的最小2的幂
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;
}

新增方法

/**
* hash 通过哈希算法算出的hash值
* key 键值
* value 放置的值
* onlyIfAbsent 这个值为true时如果存在映射并且value不为空则不进行替换
*/
final V putVal(int hash, K key, V value, boolean onlyIfAbsent,
               boolean evict) {
    Node<K,V>[] tab; Node<K,V> p; int n, i;
    //如果数组为空，resize初始化数组
    if ((tab = table) == null || (n = tab.length) == 0)
        n = (tab = resize()).length;
    //如果需要插入的位置没有元素则新建一个节点
    if ((p = tab[i = (n - 1) & hash]) == null)
        tab[i] = newNode(hash, key, value, null);
    //如果需要插入的位置有值
    else {
        Node<K,V> e; K k;
        // 需要插入的key与头节点的key相同时
        if (p.hash == hash &&
            ((k = p.key) == key || (key != null && key.equals(k))))
            e = p;
        // 红黑树节点走红黑树的插入流程
        else if (p instanceof TreeNode)
            e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
        else {
            for (int binCount = 0; ; ++binCount) {
                //如果已经遍历到尾节点
                if ((e = p.next) == null) {
                    //直接将新节点放到链表尾部
                    p.next = newNode(hash, key, value, null);
                    //需要转换为红黑树
                    if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
                        treeifyBin(tab, hash);
                    break;
                }
                //链表遍历过程中，发现有元素和新增的元素相等，结束循环
                if (e.hash == hash &&
                    ((k = e.key) == key || (key != null && key.equals(k))))
                    break;
                //后移遍历指针
                p = e;
            }
        }
        //存在key
        if (e != null) { // existing mapping for key
            V oldValue = e.value;
            //当 onlyIfAbsent 为 false 时，才会覆盖值 
            if (!onlyIfAbsent || oldValue == null)
                e.value = value;
            afterNodeAccess(e);
            // 返回老值
            return oldValue;
        }
    }
    // 记录 HashMap 的数据结构发生了变化
    ++modCount;
    //如果 HashMap 的实际大小大于扩容的门槛，开始扩容
    if (++size > threshold)
        resize();
    afterNodeInsertion(evict);
    return null;
}

final Node<K,V>[] resize() {
    Node<K,V>[] oldTab = table;
    //原数组大小
    int oldCap = (oldTab == null) ? 0 : oldTab.length;
    //原扩容阈值
    int oldThr = threshold;
    //新数组大小和新扩容阈值
    int newCap, newThr = 0;
    if (oldCap > 0) {
        if (oldCap >= MAXIMUM_CAPACITY) {
            threshold = Integer.MAX_VALUE;
            return oldTab;
        }
        //扩容：数组长度*2、扩容阈值*2
        else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY &&
                 oldCap >= DEFAULT_INITIAL_CAPACITY)
            newThr = oldThr << 1; // double threshold
    }
    else if (oldThr > 0) 
        //如果给定有初始阈值则用初始阈值设置数组大小
        newCap = oldThr;
    else {               
        //初始阈值为零使用默认值16赋值，并且将扩容阈值设置为16*0.75
        newCap = DEFAULT_INITIAL_CAPACITY;
        newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);
    }
    if (newThr == 0) {
        //当自己设置了初始大小时会走到这里
        float ft = (float)newCap * loadFactor;
        newThr = (newCap < MAXIMUM_CAPACITY && ft < (float)MAXIMUM_CAPACITY ?
                  (int)ft : Integer.MAX_VALUE);
    }
    threshold = newThr;
    @SuppressWarnings({"rawtypes","unchecked"})
    //初始化新的数组
    Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap];
    table = newTab;
    if (oldTab != null) {
        //如果老数组不为空，逐个遍历并且进行节点转移
        for (int j = 0; j < oldCap; ++j) {
            Node<K,V> e;
            if ((e = oldTab[j]) != null) {
                //将原数组该位置设为空
                oldTab[j] = null;
                if (e.next == null)
                    //如果该节点没有后续节点直接进行赋值
                    newTab[e.hash & (newCap - 1)] = e;
                else if (e instanceof TreeNode)
                    //如果是红黑树则走红黑树的转移逻辑
                    ((TreeNode<K,V>)e).split(this, newTab, j, oldCap);
                else { // preserve order
                    //这里创建了两个头两个尾是因为元素下标在扩容后要么是原下标+oldcap要么不变
                    Node<K,V> loHead = null, loTail = null;
                    Node<K,V> hiHead = null, hiTail = null;
                    Node<K,V> next;
                    do {
                        next = e.next;
                        //下标没有改变
                        if ((e.hash & oldCap) == 0) {
                            //第一个节点
                            if (loTail == null)
                                loHead = e;
                            //后续节点
                            else
                                loTail.next = e;
                            loTail = e;
                        }
                        //下标改变
                        else {
                            if (hiTail == null)
                                hiHead = e;
                            else
                                hiTail.next = e;
                            hiTail = e;
                        }
                    } while ((e = next) != null);
                    //对应下标不改变的链表
                    if (loTail != null) {
                        loTail.next = null;
                        newTab[j] = loHead;
                    }
                    //对应下标改变的链表
                    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;
    	//如果数组长度小于64先进行扩容
        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);
        }
    }

查找方法

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

//获取对象hash值，这里将高16位传播到了低16位，使得即使在小表中高16位也会影响到元素在数组中的位置
static final int hash(Object key) {
    int h;
    return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}

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
            //如果第一个元素和对应的key相等则返回头节点
            ((k = first.key) == key || (key != null && key.equals(k))))
            return first;
        if ((e = first.next) != null) {
            //如果是红黑树节点则走红黑树的逻辑
            if (first instanceof TreeNode)
                return ((TreeNode<K,V>)first).getTreeNode(hash, key);
            //逐个对比每个节点判断是否相等，相等则返回该节点的值
            do {
                if (e.hash == hash &&
                    ((k = e.key) == key || (key != null && key.equals(k))))
                    return e;
            } while ((e = e.next) != null);
        }
    }
    //没有找到则返回空
    return null;
}