Java集合之HashSet

HashSet是一个没有重复元素的集合，HashSet是由HashMap实现的，不保证元素的顺序，并且HashSet允许使用null元素。HashSet不是线程安全的，当多个线程同时访问HashSet时，会出现问题，解决的方法是通过对自然封装该Set的对象执行同步操作来完成的。还可以使用Collections.synchronizedSet方法来包装set。
Set s=Collectins.synchronizedSet(new HashSet())。
HashSet的继承实现图：



从图中我们可以看出：
（1）HashSet继承于AbstractSet，并实现了Set接口。
（2）HashSet本质是一个没有重复元素的集合，通过HashMap实现的。HashSet中有一个HashMap的map变量，HashSet的操作函数，实际上都是通过map实现的。HashSet是将值存储为HashMap的key。

HashSet主要的函数：

boolean add(E object)
void clear()
Object clone()
boolean contains(Object object)
boolean isEmpty()
Iterator<E> iterator()
boolean remove(Object object)
int size()

HashSet的遍历方式：
（1）通过Iterator迭代方式遍历HashSet：首先根据iterator()获取HashSet的迭代器，迭代获取各个元素。

for(Iterator iterator = set.iterator();iterator.hasNext(); )
{
iterator.next();
}

（2）通过for-each遍历HashSet：首先通过toArray()获取HashSet的元素集合对应的数组，之后遍历数组获得元素。

String[] arr = (String[])set.toArray(new String[0]);
for (String str:arr)
{
System.out.printf("for each : %s\n", str);
}

HashSet示例代码：

public class Hello {

public static void main(String[] args) throws Exception {
// HashSet常用API
testHashSetAPIs() ;
}

/*
* HashSet除了iterator()和add()之外的其它常用API
*/
private static void testHashSetAPIs() {
// 新建HashSet
HashSet set = new HashSet();
// 将元素添加到Set中
set.add("a");
set.add("b");
set.add("c");
set.add("d");
set.add("e");
// 打印HashSet的实际大小
System.out.printf("size : %d\n", set.size());

// 判断HashSet是否包含某个值
System.out.printf("HashSet contains a :%s\n", set.contains("a"));
System.out.printf("HashSet contains g :%s\n", set.contains("g"));

// 删除HashSet中的“e”
set.remove("e");

// 将Set转换为数组
String[] arr = (String[])set.toArray(new String[0]);
for (String str:arr)
System.out.printf("for each : %s\n", str);

// 新建一个包含b、c、f的HashSet
HashSet otherset = new HashSet();
otherset.add("b");
otherset.add("c");
otherset.add("f");
// 克隆一个removeset，内容和set一模一样
HashSet removeset = (HashSet)set.clone();
// 删除“removeset中，属于otherSet的元素”
removeset.removeAll(otherset);
// 打印removeset
System.out.printf("removeset : %s\n", removeset);
// 克隆一个retainset，内容和set一模一样
HashSet retainset = (HashSet)set.clone();
// 保留“retainset中，属于otherSet的元素”
retainset.retainAll(otherset);
// 打印retainset
System.out.printf("retainset : %s\n", retainset);
// 遍历HashSet
for(Iterator iterator = set.iterator();iterator.hasNext(); )
System.out.printf("iterator : %s\n", iterator.next());
// 清空HashSet
set.clear();
// 输出HashSet是否为空
System.out.printf("%s\n", set.isEmpty()?"set is empty":"set is not empty");
}
}

结果：
size : 5
HashSet contains a :true
HashSet contains g :false
for each : a
for each : b
for each : c
for each : d
removeset : [a, d]
retainset : [b, c]
iterator : a
iterator : b
iterator : c
iterator : d
set is empty

基于Java8的HashSet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;//HashSet是利用map来存储数据
private static final Object PRESENT = new Object();

/**
* Constructs a new, empty set; the backing <tt>HashMap</tt> instance has
* default initial capacity (16) and load factor (0.75).
*/
//构造一个空Set
public HashSet() {
map = new HashMap<>();
}

/**
* Constructs a new set containing the elements in the specified
* collection.  The <tt>HashMap</tt> is created with default load factor
* (0.75) and an initial capacity sufficient to contain the elements in
* the specified collection.
*
* @param c the collection whose elements are to be placed into this set
* @throws NullPointerException if the specified collection is null
*/
//构造一个有初始参数c的构造函数
public HashSet(Collection<? extends E> c) {
map = new HashMap<>(Math.max((int) (c.size()/.75f) + 1, 16));
addAll(c);
}

/**
* Constructs a new, empty set; the backing <tt>HashMap</tt> instance has
* the specified initial capacity and the specified load factor.
*
* @param      initialCapacity   the initial capacity of the hash map
* @param      loadFactor        the load factor of the hash map
* @throws     IllegalArgumentException if the initial capacity is less
*             than zero, or if the load factor is nonpositive
*/
//初始容量和加载因子的构造函数，其实是HashMap的构造函数
public HashSet(int initialCapacity, float loadFactor) {
map = new HashMap<>(initialCapacity, loadFactor);
}

/**
* Constructs a new, empty set; the backing <tt>HashMap</tt> instance has
* the specified initial capacity and default load factor (0.75).
*
* @param      initialCapacity   the initial capacity of the hash table
* @throws     IllegalArgumentException if the initial capacity is less
*             than zero
*/
//构造初始容量的构造函数
public HashSet(int initialCapacity) {
map = new HashMap<>(initialCapacity);
}

/**
* Constructs a new, empty linked hash set.  (This package private
* constructor is only used by LinkedHashSet.) The backing
* HashMap instance is a LinkedHashMap with the specified initial
* capacity and the specified load factor.
*
* @param      initialCapacity   the initial capacity of the hash map
* @param      loadFactor        the load factor of the hash map
* @param      dummy             ignored (distinguishes this
*             constructor from other int, float constructor.)
* @throws     IllegalArgumentException if the initial capacity is less
*             than zero, or if the load factor is nonpositive
*/
//构造一个空的LinkedHashMap
HashSet(int initialCapacity, float loadFactor, boolean dummy) {
map = new LinkedHashMap<>(initialCapacity, loadFactor);
}

/**
* Returns an iterator over the elements in this set.  The elements
* are returned in no particular order.
*
* @return an Iterator over the elements in this set
* @see ConcurrentModificationException
*/
//返回key的迭代
public Iterator<E> iterator() {
return map.keySet().iterator();
}

/**
* Returns the number of elements in this set (its cardinality).
*
* @return the number of elements in this set (its cardinality)
*/
//大小
public int size() {
return map.size();
}

/**
* Returns <tt>true</tt> if this set contains no elements.
*
* @return <tt>true</tt> if this set contains no elements
*/
//判断是否为空
public boolean isEmpty() {
return map.isEmpty();
}

/**
* Returns <tt>true</tt> if this set contains the specified element.
* More formally, returns <tt>true</tt> if and only if this set
* contains an element <tt>e</tt> such that
* <tt>(o==null ? e==null : o.equals(e))</tt>.
*
* @param o element whose presence in this set is to be tested
* @return <tt>true</tt> if this set contains the specified element
*/
//判断是否包含某个对象
public boolean contains(Object o) {
return map.containsKey(o);
}

/**
* Adds the specified element to this set if it is not already present.
* More formally, adds the specified element <tt>e</tt> to this set if
* this set contains no element <tt>e2</tt> such that
* <tt>(e==null ? e2==null : e.equals(e2))</tt>.
* If this set already contains the element, the call leaves the set
* unchanged and returns <tt>false</tt>.
*
* @param e element to be added to this set
* @return <tt>true</tt> if this set did not already contain the specified
* element
*/
//增加对象
public boolean add(E e) {
return map.put(e, PRESENT)==null;
}

/**
* Removes the specified element from this set if it is present.
* More formally, removes an element <tt>e</tt> such that
* <tt>(o==null ? e==null : o.equals(e))</tt>,
* if this set contains such an element.  Returns <tt>true</tt> if
* this set contained the element (or equivalently, if this set
* changed as a result of the call).  (This set will not contain the
* element once the call returns.)
*
* @param o object to be removed from this set, if present
* @return <tt>true</tt> if the set contained the specified element
*/
//删除对象
public boolean remove(Object o) {
return map.remove(o)==PRESENT;
}

/**
* Removes all of the elements from this set.
* The set will be empty after this call returns.
*/
//清空set
public void clear() {
map.clear();
}

/**
* Returns a shallow copy of this <tt>HashSet</tt> instance: the elements
* themselves are not cloned.
*
* @return a shallow copy of this set
*/
//深拷贝
@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.
*/
//序列化写
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).
*/
//序列化读
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);

// 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);
}
}