【集合源码】HashMap源码解析（基于JDK 1.8）

HashMap简介

1.基于JDK 1.8的HashMap有三种数据结构，数组，链表，红黑树。

2.HashMap是非线程安全的。多线程环境下可以采用concurrent并发包下的concurrentHashMap。

3.HashMap存储的内容是键值对(key-value)映射，key、value都可以为null。

4.HashMap中的映射不是有序的。

5.实现了Cloneable接口，能被克隆。

6.实现了Serializable接口，支持序列化。

源码解析

比较重要的方法都加了详细的注解：

package java.util;import java.io.IOException;import java.io.InvalidObjectException;import java.io.Serializable;import java.lang.reflect.ParameterizedType;import java.lang.reflect.Type;import java.util.function.BiConsumer;import java.util.function.BiFunction;import java.util.function.Consumer;import java.util.function.Function;public class HashMap<K,V> extends AbstractMap<K,V> implements Map<K,V>, Cloneable, Serializable {    private static final long serialVersionUID = 362498820763181265L;    /**     * 默认的初始容量（容量为HashMap中槽的数目）是16，且实际容量必须是2的整数次幂。     */    static final int DEFAULT_INITIAL_CAPACITY = 1 << 4;     /**     *  最大容量（必须是2的幂且小于2的30次方，传入容量过大将被这个值替换）      */    static final int MAXIMUM_CAPACITY = 1 << 30;    /**     * 默认负载因子为0.75     */    static final float DEFAULT_LOAD_FACTOR = 0.75f;    /**     * 链表转化为红黑树的临界值为8     */    static final int TREEIFY_THRESHOLD = 8;    /**     * 删除冲突节点后，hash相同的节点数目小于这个数，红黑树就恢复成链表     */    static final int UNTREEIFY_THRESHOLD = 6;    /**     * 扩容的临界值     */    static final int MIN_TREEIFY_CAPACITY = 64;    /**     * Node节点的数据结构     */    static class Node<K,V> implements Map.Entry<K,V> {        final int hash;        final K key;        V value;        Node<K,V> next;  //下一个节点        Node(int hash, K key, V value, Node<K,V> next) {//初始化            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() {            //返回hash值            return Objects.hashCode(key) ^ Objects.hashCode(value);        }        public final V setValue(V newValue) {            V oldValue = value;            value = newValue;            return oldValue;        }        //重写equals方法        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;        }    }    /**     * 计算key.hashCode()。假如key为空，返回0     */    static final int hash(Object key) {        int h;        return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);    }    /**     * 返回x的class     */    static Class<?> comparableClassFor(Object x) {        if (x instanceof Comparable) {            Class<?> c; Type[] ts, as; Type t; ParameterizedType p;            if ((c = x.getClass()) == String.class) // bypass checks                return c;            if ((ts = c.getGenericInterfaces()) != null) {                for (int i = 0; i < ts.length; ++i) {                    if (((t = ts[i]) instanceof ParameterizedType) &&                        ((p = (ParameterizedType)t).getRawType() ==                         Comparable.class) &&                        (as = p.getActualTypeArguments()) != null &&                        as.length == 1 && as[0] == c) // type arg is c                        return c;                }            }        }        return null;    }    /**     * 返回k.compareTo(x)      */    @SuppressWarnings({"rawtypes","unchecked"}) // for cast to Comparable    static int compareComparables(Class<?> kc, Object k, Object x) {        return (x == null || x.getClass() != kc ? 0 :                ((Comparable)k).compareTo(x));    }    /**     * 返回给定容量的2的幂次方大小     */    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;    }    /**     * 存储元素的数组     */    transient Node<K,V>[] table;    /**     * Holds cached entrySet().      */    transient Set<Map.Entry<K,V>> entrySet;    /**     * map中包含的键值对的个数.     */    transient int size;    /**     * HashMap被改变的次数       */    transient int modCount;    /**     * HashMap的阈值，用于判断是否需要调整HashMap的容量（threshold = 容量*加载因子）       */    int threshold;    /**     * 哈希表的负载因子     */    final float loadFactor;    /**     * 指定“容量大小”（initialCapacity）和“加载因子”（loadFactor）的构造函数     */    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);    }    /**     * 指定“容量大小”（initialCapacity）的构造函数     */    public HashMap(int initialCapacity) {        this(initialCapacity, DEFAULT_LOAD_FACTOR);    }    /**     * 默认构造函数     */    public HashMap() {        this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted    }    /**     * 包含“子Map”的构造函数     */    public HashMap(Map<? extends K, ? extends V> m) {        this.loadFactor = DEFAULT_LOAD_FACTOR;        putMapEntries(m, false);    }    /**     * 实现 Map.putAll 和 Map 构造函数     */    final void putMapEntries(Map<? extends K, ? extends V> m, boolean evict) {        int s = m.size();        if (s > 0) {            if (table == null) { // pre-size                float ft = ((float)s / loadFactor) + 1.0F;                int t = ((ft < (float)MAXIMUM_CAPACITY) ?                         (int)ft : MAXIMUM_CAPACITY);                if (t > threshold)                    threshold = tableSizeFor(t);            }            else if (s > threshold)                resize();            for (Map.Entry<? extends K, ? extends V> e : m.entrySet()) {                K key = e.getKey();                V value = e.getValue();                putVal(hash(key), key, value, false, evict);            }        }    }    /**     * 返回该map的键值对的数目     */    public int size() {        return size;    }    /**     * 该hashmap是否为空。空则返回true，否则返回false     */    public boolean isEmpty() {        return size == 0;    }    /**     * 获取key对应的value      */    public V get(Object key) {        Node<K,V> e;        return (e = getNode(hash(key), key)) == null ? null : e.value;    }    /**     * 实现 Map.get 和相关方法     */    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) {            // 数组元素相等            if (first.hash == hash && // always check first node                ((k = first.key) == key || (key != null && key.equals(k))))                return first;            // 桶中不止一个节点            if ((e = first.next) != null) {                // 在红黑树中get                if (first instanceof TreeNode)                    return ((TreeNode<K,V>)first).getTreeNode(hash, key);                // 在链表中get                do {                    if (e.hash == hash &&                        ((k = e.key) == key || (key != null && key.equals(k))))                        return e;                } while ((e = e.next) != null);            }        }        return null;    }    /**     * HashMap是否包含key     */    public boolean containsKey(Object key) {        return getNode(hash(key), key) != null;    }    /**     * 放入键值对。已存在则覆盖已有的，不存在则新建         */    public V put(K key, V value) {        return putVal(hash(key), key, value, false, true);    }    /**     * 实现Map.put和相关的方法     */    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)//tab为空则创建            n = (tab = resize()).length;         // 计算index，并对null做处理        if ((p = tab[i = (n - 1) & hash]) == null)            tab[i] = newNode(hash, key, value, null);        else {            Node<K,V> e; K k;            // 节点存在            if (p.hash == hash && ((k = p.key) == key || (key != null && key.equals(k))))                e = p;            // 该链为树            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;                }            }            // 写入            if (e != null) { // 已经存在指定键的键值对                V oldValue = e.value;                if (!onlyIfAbsent || oldValue == null)                    e.value = value;                afterNodeAccess(e);                return oldValue;            }        }        ++modCount;        // 超过负载 factor*current capacity，则resize        if (++size > threshold)            resize();        afterNodeInsertion(evict);        return null;    }    /**     * 初始化或者doubles表的尺寸.     */    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) {            // 超过最大值就不再扩充了，就只好随你碰撞去吧            if (oldCap >= MAXIMUM_CAPACITY) {                threshold = Integer.MAX_VALUE;                return oldTab;            }            // 没超过最大值，就扩充为原来的2倍            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);        }        // 计算新的resize上限        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) {            // 把每个bucket都移动到新的buckets中            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;                            // 原索引                            if ((e.hash & oldCap) == 0) {                                if (loTail == null)                                    loHead = e;                                else                                    loTail.next = e;                                loTail = e;                            }                            // 原索引+oldCap                            else {                                if (hiTail == null)                                    hiHead = e;                                else                                    hiTail.next = e;                                hiTail = e;                            }                        } while ((e = next) != null);                        // 原索引放到bucket里                        if (loTail != null) {                            loTail.next = null;                            newTab[j] = loHead;                        }                        // 原索引+oldCap放到bucket里                        if (hiTail != null) {                            hiTail.next = null;                            newTab[j + oldCap] = hiHead;                        }                    }                }            }        }        return newTab;    }    /**     * 根据给的hash，替换掉所有链表中的节点。假如表太小，则resize         */    final void treeifyBin(Node<K,V>[] tab, int hash) {        int n, index; Node<K,V> e;        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);        }    }    /**     * // 将"m"的全部元素都添加到HashMap中       */    public void putAll(Map<? extends K, ? extends V> m) {        putMapEntries(m, true);    }    /**     * 假如指定键存在，则移除该指定键的对应键值对     */    public V remove(Object key) {        Node<K,V> e;        return (e = removeNode(hash(key), key, null, false, true)) == null ?            null : e.value;    }    /**     * 实现Map.remove 和相关的方法     */    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)                    ((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;    }    /**     * 清空该HashMap     */    public void clear() {        Node<K,V>[] tab;        modCount++;        if ((tab = table) != null && size > 0) {            size = 0;            for (int i = 0; i < tab.length; ++i)                tab[i] = null;        }    }    /**     * 该HashMap是否包含指定value     */    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;    }    /**     * 返回“key的集合”，实际上返回一个“KeySet对象”     */    public Set<K> keySet() {        Set<K> ks = keySet;        if (ks == null) {            ks = new KeySet();            keySet = ks;        }        return ks;    }    /**    * Key对应的集合      * KeySet继承于AbstractSet，说明该集合中没有重复的Key。      */    final class KeySet extends AbstractSet<K> {        public final int size()                 { return size; }        public final void clear()               { HashMap.this.clear(); }        public final Iterator<K> iterator()     { return new KeyIterator(); }        public final boolean contains(Object o) { return containsKey(o); }        public final boolean remove(Object key) {            return removeNode(hash(key), key, null, false, true) != null;        }        public final Spliterator<K> spliterator() {            return new KeySpliterator<>(HashMap.this, 0, -1, 0, 0);        }        public final void forEach(Consumer<? super K> action) {            Node<K,V>[] tab;            if (action == null)                throw new NullPointerException();            if (size > 0 && (tab = table) != null) {                int mc = modCount;                for (int i = 0; i < tab.length; ++i) {                    for (Node<K,V> e = tab[i]; e != null; e = e.next)                        action.accept(e.key);                }                if (modCount != mc)                    throw new ConcurrentModificationException();            }        }    }    /**     * 返回“value集合”，实际上返回的是一个Values对象       */    public Collection<V> values() {        Collection<V> vs = values;        if (vs == null) {            vs = new Values();            values = vs;        }        return vs;    }    /**    *“value集合”      * Values继承于AbstractCollection，不同于“KeySet继承于AbstractSet”，      * Values中的元素能够重复。因为不同的key可以指向相同的value。    */    final class Values extends AbstractCollection<V> {        public final int size()                 { return size; }        public final void clear()               { HashMap.this.clear(); }        public final Iterator<V> iterator()     { return new ValueIterator(); }        public final boolean contains(Object o) { return containsValue(o); }        public final Spliterator<V> spliterator() {            return new ValueSpliterator<>(HashMap.this, 0, -1, 0, 0);        }        public final void forEach(Consumer<? super V> action) {            Node<K,V>[] tab;            if (action == null)                throw new NullPointerException();            if (size > 0 && (tab = table) != null) {                int mc = modCount;                for (int i = 0; i < tab.length; ++i) {                    for (Node<K,V> e = tab[i]; e != null; e = e.next)                        action.accept(e.value);                }                if (modCount != mc)                    throw new ConcurrentModificationException();            }        }    }    /**     * 克隆一个HashMap，并返回Object对象       */    @SuppressWarnings("unchecked")    @Override    public Object clone() {        HashMap<K,V> result;        try {            result = (HashMap<K,V>)super.clone();        } catch (CloneNotSupportedException e) {            // 因为是可克隆的，所以这不应该发生            throw new InternalError(e);        }        result.reinitialize();        result.putMapEntries(this, false);        return result;    }    // 当序列化HashSets的时候，这些方法会被调用    final float loadFactor() { return loadFactor; }    final int capacity() {        return (table != null) ? table.length :            (threshold > 0) ? threshold :            DEFAULT_INITIAL_CAPACITY;    }    /**     * java.io.Serializable的写入函数       * 将HashMap的“总的容量，实际容量，所有的Entry”都写入到输出流中       */    private void writeObject(java.io.ObjectOutputStream s) throws IOException {        int buckets = capacity();        // Write out the threshold, loadfactor, and any hidden stuff        s.defaultWriteObject();        s.writeInt(buckets);        s.writeInt(size);        internalWriteEntries(s);    }    /**     * java.io.Serializable的读取函数：根据写入方式读出       * 将HashMap的“总的容量，实际容量，所有的Entry”依次读出      */    private void readObject(java.io.ObjectInputStream s)        throws IOException, ClassNotFoundException {        // Read in the threshold (ignored), loadfactor, and any hidden stuff        s.defaultReadObject();        reinitialize();        if (loadFactor <= 0 || Float.isNaN(loadFactor))            throw new InvalidObjectException("Illegal load factor: " +                                             loadFactor);        s.readInt();                // Read and ignore number of buckets        int mappings = s.readInt(); // Read number of mappings (size)        if (mappings < 0)            throw new InvalidObjectException("Illegal mappings count: " +                                             mappings);        else if (mappings > 0) { // (if zero, use defaults)            // Size the table using given load factor only if within            // range of 0.25...4.0            float lf = Math.min(Math.max(0.25f, loadFactor), 4.0f);            float fc = (float)mappings / lf + 1.0f;            int cap = ((fc < DEFAULT_INITIAL_CAPACITY) ?                       DEFAULT_INITIAL_CAPACITY :                       (fc >= MAXIMUM_CAPACITY) ?                       MAXIMUM_CAPACITY :                       tableSizeFor((int)fc));            float ft = (float)cap * lf;            threshold = ((cap < MAXIMUM_CAPACITY && ft < MAXIMUM_CAPACITY) ?                         (int)ft : Integer.MAX_VALUE);            @SuppressWarnings({"rawtypes","unchecked"})                Node<K,V>[] tab = (Node<K,V>[])new Node[cap];            table = tab;            // Read the keys and values, and put the mappings in the HashMap            for (int i = 0; i < mappings; i++) {                @SuppressWarnings("unchecked")                    K key = (K) s.readObject();                @SuppressWarnings("unchecked")                    V value = (V) s.readObject();                putVal(hash(key), key, value, false, false);            }        }    }    /**     * 红黑树、迭代器、分割器等等相关代码就不一一罗列了。     */}

小结

• HashMap有三种数据结构，分别是数组，链表，红黑树。在JDK1.8之前是没有红黑树的。这里加上红黑树是因为仅仅用链表法解决哈希冲突时，链表的长度过长，查找的时间复杂度为O(n)，性能没有红黑树好（查找的时间复杂度为O(logn)）。

• 如果冲突节点到8时，就把链表转换成红黑树；为什么不直接用红黑树彻底代替链表呢？这里我猜测是因为当链表的长度只是个位数时，查找的时间复杂度只是常数级别的，性能完全够了。而且红黑树结构实现复杂。

• 如果bucket满了(超过load factor * current 的容量)，就要resize。

• 在resize的过程，就是把bucket扩充为2倍，之后重新计算index，把节点再放到新的bucket中。

• get过程中如果出现冲突，则通过key.equals(k)去查找对应的entry
  若为树，则在树中通过key.equals(k)查找，若为链表，则在链表中通过key.equals(k)查找。