HashMap源码解析(JDK8)

简介

Hashmap是key-value格式的键值对储存容器，key与value都支持null，但非线程安全，若需要线程安全可以使用ConcurrentHashMap。

原理

构造函数

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

// 默认因子为0.75，即size达到最大容量的0.75时执行扩容
static final float DEFAULT_LOAD_FACTOR = 0.75f;

final float loadFactor;

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);
}

public HashMap(int initialCapacity) {
    this(initialCapacity, DEFAULT_LOAD_FACTOR);
}

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

// 使数像上取整为2的次方，例如cap=7(111)之后会返回8(1000)
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;
}

tab长度需要为2的整数倍，当容量超过容量因子*tab长度后会执行扩容。最大tab长度为1 « 30，再大也不会再扩容。size最大为int值。

Node节点

// Node槽，hash冲突时会先形成链表或者红黑树
transient Node<K,V>[] table;

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;
    }
}

// LinkedHashMap.LinkedHashMapEntry是继承至HashMap.Node的
static final class TreeNode<K,V> extends LinkedHashMap.LinkedHashMapEntry<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);
    }
}

get

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

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

// 前16位与后16为进行异或，充分利用hash值，减少hash冲突
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;
    // 若对应hash槽有元素
    if ((tab = table) != null && (n = tab.length) > 0 && (first = tab[(n - 1) & hash]) != null) {
        // always check first node
        if (first.hash == hash && ((k = first.key) == key || (key != null && key.equals(k))))
            return first;
        // 如果还有元素，就开始根据是树还是链表依次查找
        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;
}

hash计算利用前16位与后16位异或，减少冲突。

contains

public boolean containsKey(Object key) {
    return getNode(hash(key), key) != null;
}

public boolean containsValue(Object value) {
    Node<K,V>[] tab; V v;
    if ((tab = table) != null && size > 0) {
        for (int i = 0; i < tab.length; ++i) {
            for (Node<K,V> e = tab[i]; e != null; e = e.next) {
                if ((v = e.value) == value ||
                    (value != null && value.equals(v)))
                    return true;
            }
        }
    }
    return false;
}

可以看出，containsKey几乎和get一致,containsValue会按照值去依次比较，找到第一个相等的返回true，效率较低。

replace

@Override
public boolean replace(K key, V oldValue, V newValue) {
    Node<K,V> e; V v;
    if ((e = getNode(hash(key), key)) != null && ((v = e.value) == oldValue || (v != null && v.equals(oldValue)))) {
        e.value = newValue;
        afterNodeAccess(e);
        return true;
    }
    return false;
}

@Override
public V replace(K key, V value) {
    Node<K,V> e;
    if ((e = getNode(hash(key), key)) != null) {
        V oldValue = e.value;
        e.value = value;
        afterNodeAccess(e);
        return oldValue;
    }
    return null;
}

可以看出，只有元素存在时才可以替换。

put

static final int TREEIFY_THRESHOLD = 8;

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

// 如果有值不修改
public V putIfAbsent(K key, V value) {
    return putVal(hash(key), key, value, true, true);
}

// @onlyIfAbsent 如果存在就不要修改值了
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tab没有初始化，则先进行初始化操作
    if ((tab = table) == null || (n = tab.length) == 0)
        n = (tab = resize()).length;
    if ((p = tab[i = (n - 1) & hash]) == null)
        // 如果槽上无元素，则直接插入
        tab[i] = newNode(hash, key, value, null);
    else {
        Node<K,V> e; K k;
        // 第一个元素就相等了，表示找到了
        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 {
            for (int binCount = 0; ; ++binCount) {
                if ((e = p.next) == null) {
                    p.next = newNode(hash, key, value, null);
                    // 链表中元素大于等于8时转化为树
                    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) { // 如果已经存在，则返回原来的旧值。
            V oldValue = e.value;
            if (!onlyIfAbsent || oldValue == null)
                e.value = value;
            afterNodeAccess(e);
            return oldValue;
        }
    }
    ++modCount;
    // 大于了因子容量
    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) {
        // 如果已经达到槽的最大限制，则不再扩容，继续在树上添加
        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)
                    // 分组，若相同hash值元素小于等于6时，会转化为链表，否则依然构建为树
                    ((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;
                    // 从头到位依次与之前容量-1进行与操作，间接得到第一位，然后依次形成链表，最后插入到其中。
                    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;
}

static final int MIN_TREEIFY_CAPACITY = 64;

final void treeifyBin(Node<K,V>[] tab, int hash) {
    int n, index; Node<K,V> e;
    // 若槽数小于64，因为很容易冲突，所以优先扩容。
    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);
    }
}

1. 首先会对为空的情况进行初始化，初始化默认为16。
2. 槽位置计算为length - 1 & hash
   • 若对应位置上无元素直接插入
   • 若对应位置有元素为链表，则依次遍历，往最后位置插入，插入后元素若大于等于8且tab长度大于等于64，则转变成树。
   • 若对应位置为树，则查找插入。
3. 最后会与容量因子进行比较，若超过则进行扩容。
   • 扩容是成倍操作。
   • 扩容操作为获取当前槽元素的第一位hash值来进行划分。
   • 树在分槽后若元素小于等于6则变更为列表，否则依然保持为树。

remove

public V remove(Object key) {
    Node<K,V> e;
    return (e = removeNode(hash(key), key, null, false, true)) == null ? null : e.value;
}

public boolean remove(Object key, Object value) {
    return removeNode(hash(key), key, value, true, true) != null;
}

final Node<K,V> removeNode(int hash, Object key, Object value, boolean matchValue, boolean movable) {
    Node<K,V>[] tab; Node<K,V> p; int n, index;
    if ((tab = table) != null && (n = tab.length) > 0 && (p = tab[index = (n - 1) & hash]) != null) {
        Node<K,V> node = null, e; K k; V v;
        if(p.hash == hash && ((k = p.key) == key || (key != null && key.equals(k))))
            node = p;
        else if ((e = p.next) != null) {
            if (p instanceof TreeNode)
                node = ((TreeNode<K,V>)p).getTreeNode(hash, key);
            else {
                do {
                    if (e.hash == hash && ((k = e.key) == key || (key != null && key.equals(k)))) {
                        node = e;
                        break;
                    }
                    p = e;
                } while ((e = e.next) != null);
            }
        }
        if (node != null && (!matchValue || (v = node.value) == value || (value != null && value.equals(v)))) {
            if (node instanceof TreeNode)
                // 移出元素，当树已经特别小的时候会转化为链表
                ((TreeNode<K,V>)node).removeTreeNode(this, tab, movable);
            else if (node == p)
                tab[index] = node.next;
            else
                p.next = node.next;
            ++modCount;
            --size;
            afterNodeRemoval(node);
            return node;
        }
    }
    return null;
}

移出操作比较简单，先确认是否有元素以及是否能移出。

迭代器

public Set<K> keySet() {
    Set<K> ks = keySet;
    if (ks == null) {
        ks = new KeySet();
        keySet = ks;
    }
    return ks;
}
public Collection<V> values() {
    Collection<V> vs = values;
    if (vs == null) {
        vs = new Values();
        values = vs;
    }
    return vs;
}
public Set<Map.Entry<K,V>> entrySet() {
    Set<Map.Entry<K,V>> es;
    return (es = entrySet) == null ? (entrySet = new EntrySet()) : es;
}

迭代器比较简单，通ArrayList一样，在迭代过程中不允许元素的增加或删除

一些额外的方法

// Callbacks to allow LinkedHashMap post-actions
// 节点访问
void afterNodeAccess(Node<K,V> p) { }
// 新节点插入
void afterNodeInsertion(boolean evict) { }
// 节点移除
void afterNodeRemoval(Node<K,V> p) { }

HashMap提供的几个空实现的方法，主要用在LinkedHashMap继承HashMap后得到操作的回掉。

总结

• hashMap由数组组成，使用链表或者红黑树来解决hash冲突。
• 默认数组长度为2的次方。
• 添加元素时，若存在hash冲突，则会从链表尾部插入元素。若链表长度大于等于8时，tab长度小于64会优先扩容。否则会转化为红黑树。
• 当容量超过容量因子上限时会执行扩容操作。扩容时hash值取最新的一位确定位置。树扩容后若元素小于等于6个会转化为链表。
• 不支持并发操作。支持迭代快速失败。