Java集合源码分析-Hashtable

Hashtable产生于JDK 1.1，而HashMap产生于JDK 1.2，Hashtable基本已经弃用了，虽然Hashtable是线程安全的，但是并发大神Doug Lea写了util.concurrent包，高并发情况下可以使用并发包里的ConcurrentHashMap。如果向Hashtable里添加的节点key或者value为nil会触发java.lang.NullPointerException。

建议先看Java集合源码分析-HashMap，然后再看Hashtable就很简单了。

Hashtable底层的数据结构和HashMap一样，都是一个hash桶，每个桶位存储的都是一个单向非循环的链表。

Hashtable类图

可以看到Hashtable的父类是Dictionary。

Hashtable成员变量和构造器

    private transient Hashtable.Entry<?, ?>[] table;
    private transient int count;
    private int threshold;
    private float loadFactor;
    private transient int modCount;
    private static final long serialVersionUID = 1421746759512286392L;
    private static final int MAX_ARRAY_SIZE = 2147483639;
    private transient volatile Set<K> keySet;
    private transient volatile Set<java.util.Map.Entry<K, V>> entrySet;
    private transient volatile Collection<V> values;
    private static final int KEYS = 0;
    private static final int VALUES = 1;
    private static final int ENTRIES = 2;

和HashMap一样，Hashtable提供了四类构造器：

    public Hashtable() {
        this(11, 0.75f);
    }

    public Hashtable(int initialCapacity) {
        this(initialCapacity, 0.75f);
    }

    public Hashtable(int initialCapacity, float loadFactor) {
        if (initialCapacity < 0)
            throw new IllegalArgumentException("Illegal Capacity: "+
                                               initialCapacity);
        if (loadFactor <= 0 || Float.isNaN(loadFactor))
            throw new IllegalArgumentException("Illegal Load: "+loadFactor);

        if (initialCapacity==0)
            initialCapacity = 1;
        this.loadFactor = loadFactor;
        table = new Entry<?,?>[initialCapacity];
        threshold = (int)Math.min(initialCapacity * loadFactor, MAX_ARRAY_SIZE + 1);
    }

    public Hashtable(Map<? extends K, ? extends V> t) {
        this(Math.max(2*t.size(), 11), 0.75f);
        putAll(t);
    }

可以看到和HashMap的构造器所做的操作基本是一样的而且比HashMap还要简单，因为不要求hash桶的容量必须是2的次幂。
然后分析下Hashtable的核心操作：put、remove

put

    public synchronized V put(K key, V value) {
        // Make sure the value is not null
        if (value == null) {
            throw new NullPointerException();
        }

        // Makes sure the key is not already in the hashtable.
        Entry<?,?> tab[] = table;
        int hash = key.hashCode();
        int index = (hash & 0x7FFFFFFF) % tab.length;
        @SuppressWarnings("unchecked")
        Entry<K,V> entry = (Entry<K,V>)tab[index];
        for(; entry != null ; entry = entry.next) {
            if ((entry.hash == hash) && entry.key.equals(key)) {
                V old = entry.value;
                entry.value = value;
                return old;
            }
        }

        addEntry(hash, key, value, index);
        return null;
    }

    private void addEntry(int hash, K key, V value, int index) {
        modCount++;

        Entry<?,?> tab[] = table;
        if (count >= threshold) {
            // Rehash the table if the threshold is exceeded
            rehash();

            tab = table;
            hash = key.hashCode();
            index = (hash & 0x7FFFFFFF) % tab.length;
        }

        // Creates the new entry.
        @SuppressWarnings("unchecked")
        Entry<K,V> e = (Entry<K,V>) tab[index];
        tab[index] = new Entry<>(hash, key, value, e);
        count++;
    }

    protected void rehash() {
        int oldCapacity = table.length;
        Entry<?,?>[] oldMap = table;

        // overflow-conscious code
        int newCapacity = (oldCapacity << 1) + 1;
        if (newCapacity - MAX_ARRAY_SIZE > 0) {
            if (oldCapacity == MAX_ARRAY_SIZE)
                // Keep running with MAX_ARRAY_SIZE buckets
                return;
            newCapacity = MAX_ARRAY_SIZE;
        }
        Entry<?,?>[] newMap = new Entry<?,?>[newCapacity];

        modCount++;
        threshold = (int)Math.min(newCapacity * loadFactor, MAX_ARRAY_SIZE + 1);
        table = newMap;

        for (int i = oldCapacity ; i-- > 0 ;) {
            for (Entry<K,V> old = (Entry<K,V>)oldMap[i] ; old != null ; ) {
                Entry<K,V> e = old;
                old = old.next;

                int index = (e.hash & 0x7FFFFFFF) % newCapacity;
                e.next = (Entry<K,V>)newMap[index];
                newMap[index] = e;
            }
        }
    }

需要注意方法是synchronized的就行了，然后Hashtable是将新节点插入到了链表的头部，而HashMap是将新节点插入到了链表的尾部，其实插入头部还是尾部是无所谓的，不存在孰优孰劣(因为两个插入方式都要遍历链表，遇到相同key值则break并覆盖，没有相同key就遍历到尾部，所以两种方式性能是一样的)。

remove

    public synchronized V remove(Object key) {
        Entry<?,?> tab[] = table;
        int hash = key.hashCode();
        int index = (hash & 0x7FFFFFFF) % tab.length;
        @SuppressWarnings("unchecked")
        Entry<K,V> e = (Entry<K,V>)tab[index];
        for(Entry<K,V> prev = null ; e != null ; prev = e, e = e.next) {
            if ((e.hash == hash) && e.key.equals(key)) {
                modCount++;
                if (prev != null) {
                    prev.next = e.next;
                } else {
                    tab[index] = e.next;
                }
                count--;
                V oldValue = e.value;
                e.value = null;
                return oldValue;
            }
        }
        return null;
    }