HashSet源码阅读

2021-03-20

HashSet的底层实现借用了HashMap的实现，也就是HashSet本身没有新建数据结构，使用HashMap和LinkedHashMap进行了一层包装,好像linkedHashMap只是使用在LinkedHashSet的时候用,其余时候还是用的HashMap.

主要逻辑实现

add
remove
size
contains
iterator

package java.util;

import java.io.InvalidObjectException;
import sun.misc.SharedSecrets;

// HashSet的底层实现借用了HashMap的实现，也就是HashSet本身没有新建数据结构，使用HashMap和LinkedHashMap进行了一层包装
public class HashSet<E>
    extends AbstractSet<E>
    implements Set<E>, Cloneable, java.io.Serializable
{
    static final long serialVersionUID = -5024744406713321676L;
	// 内部的HashMap对象
    private transient HashMap<E,Object> map;

    // 使用一个虚拟的对象来填充hashMap的value域,这个对象不包含任何值,hashSet中的所有hashMap的值都是这一个对象.
    private static final Object PRESENT = new Object();

    // 使用HashMap的默认参数，初始化16个loadfactor=0.75
    public HashSet() {
        map = new HashMap<>();
    }

    // 使用给出的集合自动计算初始化大小
    public HashSet(Collection<? extends E> c) {
        map = new HashMap<>(Math.max((int) (c.size()/.75f) + 1, 16));
        addAll(c);
    }

    // 给出初始化大小和负载因子
    public HashSet(int initialCapacity, float loadFactor) {
        map = new HashMap<>(initialCapacity, loadFactor);
    }

    // 直接给出初始化大小
    public HashSet(int initialCapacity) {
        map = new HashMap<>(initialCapacity);
    }

    // 构造一个新的空链接哈希集。 (这个包的私有构造函数只被LinkedHashSet使用。)
    // 支持的HashMap实例是一个LinkedHashMap，具有指定的初始容量和指定的负载因子。
    HashSet(int initialCapacity, float loadFactor, boolean dummy) {
        map = new LinkedHashMap<>(initialCapacity, loadFactor);
    }

    // 调用hashMap的key视图的遍历器
    public Iterator<E> iterator() {
        return map.keySet().iterator();
    }

    // 调用hashMap的size方法
    public int size() {
        return map.size();
    }

    // 调用hashMap的判空方法
    public boolean isEmpty() {
        return map.isEmpty();
    }

    // 调用hashMap的containsKey方法
    public boolean contains(Object o) {
        return map.containsKey(o);
    }

    // 将当前的value作为key,put进hashMap,其中值用虚拟的对象PRESENT填充,注意到hashSet中的hashMap的所有的值都是同一个对象
    public boolean add(E e) {
        return map.put(e, PRESENT)==null;
    }

    // 从hashMap中移除元素，如果元素不为空，那么移除成功
    public boolean remove(Object o) {
        return map.remove(o)==PRESENT;
    }

    // 调用HashMap的clear方法
    public void clear() {
        map.clear();
    }

复制与序列化相关

    /**
     * Returns a shallow copy of this <tt>HashSet</tt> instance: the elements
     * themselves are not cloned.
     *
     * @return a shallow copy of this set
     */
    @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);
        }
    }

    /**
     * Save the state of this <tt>HashSet</tt> instance to a stream (that is,
     * serialize it).
     *
     * @serialData The capacity of the backing <tt>HashMap</tt> instance
     *             (int), and its load factor (float) are emitted, followed by
     *             the size of the set (the number of elements it contains)
     *             (int), followed by all of its elements (each an Object) in
     *             no particular order.
     */
    private void writeObject(java.io.ObjectOutputStream s)
        throws java.io.IOException {
        // Write out any hidden serialization magic
        s.defaultWriteObject();

        // Write out HashMap capacity and load factor
        s.writeInt(map.capacity());
        s.writeFloat(map.loadFactor());

        // Write out size
        s.writeInt(map.size());

        // Write out all elements in the proper order.
        for (E e : map.keySet())
            s.writeObject(e);
    }

    /**
     * Reconstitute the <tt>HashSet</tt> instance from a stream (that is,
     * deserialize it).
     */
    private void readObject(java.io.ObjectInputStream s)
        throws java.io.IOException, ClassNotFoundException {
        // Read in any hidden serialization magic
        s.defaultReadObject();

        // Read capacity and verify non-negative.
        int capacity = s.readInt();
        if (capacity < 0) {
            throw new InvalidObjectException("Illegal capacity: " +
                                             capacity);
        }

        // Read load factor and verify positive and non NaN.
        float loadFactor = s.readFloat();
        if (loadFactor <= 0 || Float.isNaN(loadFactor)) {
            throw new InvalidObjectException("Illegal load factor: " +
                                             loadFactor);
        }

        // Read size and verify non-negative.
        int size = s.readInt();
        if (size < 0) {
            throw new InvalidObjectException("Illegal size: " +
                                             size);
        }
        // Set the capacity according to the size and load factor ensuring that
        // the HashMap is at least 25% full but clamping to maximum capacity.
        capacity = (int) Math.min(size * Math.min(1 / loadFactor, 4.0f),
                HashMap.MAXIMUM_CAPACITY);

        // Constructing the backing map will lazily create an array when the first element is
        // added, so check it before construction. Call HashMap.tableSizeFor to compute the
        // actual allocation size. Check Map.Entry[].class since it's the nearest public type to
        // what is actually created.

        SharedSecrets.getJavaOISAccess()
                     .checkArray(s, Map.Entry[].class, HashMap.tableSizeFor(capacity));

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

        // Read in all elements in the proper order.
        for (int i=0; i<size; i++) {
            @SuppressWarnings("unchecked")
                E e = (E) s.readObject();
            map.put(e, PRESENT);
        }
    }

    /**
     * Creates a <em><a href="Spliterator.html#binding">late-binding</a></em>
     * and <em>fail-fast</em> {@link Spliterator} over the elements in this
     * set.
     *
     * <p>The {@code Spliterator} reports {@link Spliterator#SIZED} and
     * {@link Spliterator#DISTINCT}.  Overriding implementations should document
     * the reporting of additional characteristic values.
     *
     * @return a {@code Spliterator} over the elements in this set
     * @since 1.8
     */
    public Spliterator<E> spliterator() {
        return new HashMap.KeySpliterator<E,Object>(map, 0, -1, 0, 0);
    }
}