HashSet源码解析

Set接口

在讲HashSet之前先说一下Set接口。

见源码：

package java.util;

//这里我截取部分源码中的注释
/**
 * A collection that contains no duplicate elements.  More formally, sets
 * contain no pair of elements <code>e1</code> and <code>e2</code> such that
 * <code>e1.equals(e2)</code>, and at most one null element.  As implied by
 * its name, this interface models the mathematical <i>set</i> abstraction.
 */
 //set是一个不包含重复元素的集合。更正式一点来说，set不能包含这样的一对元素：通过equals方法比较返回true。并且至多有一个null元素。
/**
 * @author  Josh Bloch(集合框架的作者，牛人)
 * @author  Neal Gafter
 * @see Collection
 * @see List
 * @see SortedSet
 * @see HashSet
 * @see TreeSet
 * @see AbstractSet
 * @see Collections#singleton(java.lang.Object)
 * @see Collections#EMPTY_SET
 * @since 1.2
 */

public interface Set<E> extends Collection<E> {
    // Query Operations

    int size();

    boolean isEmpty();

    boolean contains(Object o);

    Iterator<E> iterator();

    Object[] toArray();


    <T> T[] toArray(T[] a);


    // Modification Operations

    boolean add(E e);

    boolean remove(Object o);


    // Bulk Operations

    boolean containsAll(Collection<?> c);

    boolean addAll(Collection<? extends E> c);

    boolean retainAll(Collection<?> c);

    boolean removeAll(Collection<?> c);

    void clear();


    // Comparison and hashing

    boolean equals(Object o);//这个方法在Set中要特别注意！

    int hashCode();//这个方法在Set中要特别注意！

    //1.8之后的新特性
    @Override
    default Spliterator<E> spliterator() {
        return Spliterators.spliterator(this, Spliterator.DISTINCT);
    }
}

因为在AbstractSet中已经实现了大部分方法，因此，在HashSet中我们会感觉代码少很多。下面是HashSet的源码。

public class HashSet<E>
    extends AbstractSet<E>
    implements Set<E>, Cloneable, java.io.Serializable
{
    static final long serialVersionUID = -5024744406713321676L;

    private transient HashMap<E,Object> map;

    private static final Object PRESENT = new Object();

    public HashSet() {
        map = new HashMap<>();
    }

    public HashSet(Collection<? extends E> c) {
        map = new HashMap<>(Math.max((int) (c.size()/.75f) + 1, 16));
        addAll(c);
    }

    public HashSet(int initialCapacity, float loadFactor) {
        map = new HashMap<>(initialCapacity, loadFactor);
    }

    public HashSet(int initialCapacity) {
        map = new HashMap<>(initialCapacity);
    }


    HashSet(int initialCapacity, float loadFactor, boolean dummy) {
        map = new LinkedHashMap<>(initialCapacity, loadFactor);
    }


    public Iterator<E> iterator() {
        return map.keySet().iterator();
    }


    public int size() {
        return map.size();
    }


    public boolean isEmpty() {
        return map.isEmpty();
    }

    public boolean contains(Object o) {
        return map.containsKey(o);
    }


    public boolean add(E e) {
        return map.put(e, PRESENT)==null;
    }

    public boolean remove(Object o) {
        return map.remove(o)==PRESENT;
    }

    public void clear() {
        map.clear();
    }

    @SuppressWarnings("unchecked")
    public Object clone() {
        try {
            HashSet<E> newSet = (HashSet<E>) super.clone();
            newSet.map = (HashMap<E, Object>) map.clone();
            return newSet;
        } catch (CloneNotSupportedException e) {
            throw new InternalError(e);
        }
    }


    private void writeObject(java.io.ObjectOutputStream s)
        throws java.io.IOException {
        // Write out any hidden serialization magic
        s.defaultWriteObject();

        s.writeInt(map.capacity());
        s.writeFloat(map.loadFactor());

        s.writeInt(map.size());

        for (E e : map.keySet())
            s.writeObject(e);
    }

    private void readObject(java.io.ObjectInputStream s)
        throws java.io.IOException, ClassNotFoundException {

        s.defaultReadObject();


        int capacity = s.readInt();
        if (capacity < 0) {
            throw new InvalidObjectException("Illegal capacity: " +
                                             capacity);
        }

        float loadFactor = s.readFloat();
        if (loadFactor <= 0 || Float.isNaN(loadFactor)) {
            throw new InvalidObjectException("Illegal load factor: " +
                                             loadFactor);
        }

        int size = s.readInt();
        if (size < 0) {
            throw new InvalidObjectException("Illegal size: " +
                                             size);
        }

        capacity = (int) Math.min(size * Math.min(1 / loadFactor, 4.0f),
                HashMap.MAXIMUM_CAPACITY);

        map = (((HashSet<?>)this) instanceof LinkedHashSet ?
               new LinkedHashMap<E,Object>(capacity, loadFactor) :
               new HashMap<E,Object>(capacity, loadFactor));

        for (int i=0; i<size; i++) {
            @SuppressWarnings("unchecked")
                E e = (E) s.readObject();
            map.put(e, PRESENT);
        }
    }

    public Spliterator<E> spliterator() {
        return new HashMap.KeySpliterator<E,Object>(map, 0, -1, 0, 0);
    }
}

我们可以看到，HashSet是在HashMap的基础上，利用HashMap的key不能“相同”的特性实现的。其对应的HashMap的value值被“PRESENT”对象填充。

由于HashSet的特性是内部的元素不同，因此我们在这里再讲一下HashMap中key的特性：

这里我们先来看一下HashMap中的添加方法：

    /**
     * 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))))//这里是保持Set特性关键，因此equals（）方法的实现是很重要的。
                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;
    }

从上面我们可以看到，Set保持“无重复”的特性，需要依赖equals（）方法比较的结果。

这里我来简要说一下HashMap中寻找value值的流程，首先根据传进来的key值，计算出其hash散列值，然后通过hash值找到位置，在存储位置上再进行equals（）的比较最后得到想寻找的值。从这个过程我们可以看到，hashcode（）方法和equals（）方法之间的相关联系，我们必须维持。

在JAVA编程中，有三个约定，这三个约定是使用集合框架的基础。