哈希表 Hashmap

本文中贴出的代码为jdk 1.8

重要参数

/**
 * The default initial capacity - MUST be a power of two.
 * 默认初始化容量，2的4次方
 */
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16

/**
 * The maximum capacity, used if a higher value is implicitly specified
 * by either of the constructors with arguments.
 * MUST be a power of two <= 1<<30.
 * 最大容量，必须是2的整数幂，方便取模
 */
static final int MAXIMUM_CAPACITY = 1 << 30;

/**
 * The load factor used when none specified in constructor.
 * 默认加载因子，当使用量达到这个比例以后会扩容
 */
static final float DEFAULT_LOAD_FACTOR = 0.75f;

/**
 * The bin count threshold for using a tree rather than list for a
 * bin.  Bins are converted to trees when adding an element to a
 * bin with at least this many nodes. The value must be greater
 * than 2 and should be at least 8 to mesh with assumptions in
 * tree removal about conversion back to plain bins upon
 * shrinkage.
 * 当拉链增加到8以后，转化为红黑树，这里jdk1.8，区别于1.7
 */
static final int TREEIFY_THRESHOLD = 8;

/**
 * The bin count threshold for untreeifying a (split) bin during a
 * resize operation. Should be less than TREEIFY_THRESHOLD, and at
 * most 6 to mesh with shrinkage detection under removal.
 * 当红黑树低到6以后，转化为拉链，这里jdk1.8，区别于1.7
 */
static final int UNTREEIFY_THRESHOLD = 6;

/**
 * The smallest table capacity for which bins may be treeified.
 * (Otherwise the table is resized if too many nodes in a bin.)
 * Should be at least 4 * TREEIFY_THRESHOLD to avoid conflicts
 * between resizing and treeification thresholds.
 */
static final int MIN_TREEIFY_CAPACITY = 64;

HashMap在new的时候，有3种方式，可以指定初始容量和加载因子，也可以不指定，默认即可。

如果在创建HashMap实例时没有给定capacity、loadFactor则默认值分别是16和0.75。

• 当好多bin被映射到同一个桶时，如果这个桶中bin的数量小于TREEIFY_THRESHOLD当然不会转化成树形结构存储。
• 如果这个桶中bin的数量大于了 TREEIFY_THRESHOLD ，但是capacity小于MIN_TREEIFY_CAPACITY 则依然使用链表结构进行存储，此时会对HashMap进行扩容。
• 如果capacity大于了MIN_TREEIFY_CAPACITY ，则会进行树化。

/**
     * Constructs an empty <tt>HashMap</tt> with the specified initial
     * capacity and load factor.
     *
     * @param  initialCapacity the initial capacity
     * @param  loadFactor      the load factor
     * @throws IllegalArgumentException if the initial capacity is negative
     *         or the load factor is nonpositive
     */
    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);
    }

    /**
     * Constructs an empty <tt>HashMap</tt> with the specified initial
     * capacity and the default load factor (0.75).
     *
     * @param  initialCapacity the initial capacity.
     * @throws IllegalArgumentException if the initial capacity is negative.
     */
    public HashMap(int initialCapacity) {
        this(initialCapacity, DEFAULT_LOAD_FACTOR);
    }

    /**
     * Constructs an empty <tt>HashMap</tt> with the default initial capacity
     * (16) and the default load factor (0.75).
     */
    public HashMap() {
        this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted
    }

get

public V get(Object key) {
    Node<K,V> e;
    return (e = getNode(hash(key), key)) == null ? null : e.value;
}

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) {
        if (first.hash == hash && // always check first node
            ((k = first.key) == key || (key != null && key.equals(k))))
            return first;
        if ((e = first.next) != null) {
            if (first instanceof TreeNode)
                return ((TreeNode<K,V>)first).getTreeNode(hash, key);
            do {
                if (e.hash == hash &&
                    ((k = e.key) == key || (key != null && key.equals(k))))
                    return e;
            } while ((e = e.next) != null);
        }
    }
    return null;
}

• 对 key 取 hash ，定位桶的位置。
• 如果桶为空，返回 null 。
• 判断桶的 first 的 key 是否为查询的 key，是就返回 value。
• 桶的 first 不匹配，则判断 first 是红黑树 or 链表。
• 红黑树就则 getTreeNode。
• 或者链表则遍历判断 next。

如何计算 hash

解决哈希碰撞时，取模是一个常用方式，比如 n%k

当且仅当k为2的整数幂时，n%k==n&(k-1)

通过位运算来进行快速取模，因此必须要求容量为2的整数幂

put

public V put(K key, V value) {
    return putVal(hash(key), key, value, false, true);
}

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))))
            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;
}

put 操作复杂一些，要判断容量，是否扩容，还要判断桶中bin数量，来决定是否转换为红黑树或者链表

• 判断当前桶是否为空，空就需要初始化（resize 中会判断是否进行初始化）。
• 根据当前 key 的 hashcode 定位到具体的桶中并判断是否为空，为空表明没有 Hash 冲突就直接在当前位置创建一个新桶。
• 如果当前桶不为空（Hash 冲突），需要比较当前桶中的 key、key 的 hashcode 与写入的 key 是否相等，相等就赋值给 e，在第 8 步的时候会统一进行赋值及返回。
• 如果当前桶为红黑树，按照红黑树的方式写入数据。
• 如果是链表，就需要将当前的 key、value 封装成一个新节点写入到当前桶的后面（形成链表）。
  接着判断当前链表的大小是否大于预设的阈值，大于时就要转换为红黑树。
• 如果在遍历过程中找到 key 相同时直接退出遍历。
• 如果 e != null 就相当于存在相同的 key,那就需要将值覆盖。
  最后判断是否需要进行扩容。

resize

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) {
        if (oldCap >= MAXIMUM_CAPACITY) {
            threshold = Integer.MAX_VALUE;
            return oldTab;
        }
        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);
    }
    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) {
        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;
                        if ((e.hash & oldCap) == 0) {
                            if (loTail == null)
                                loHead = e;
                            else
                                loTail.next = e;
                            loTail = e;
                        }
                        else {
                            if (hiTail == null)
                                hiHead = e;
                            else
                                hiTail.next = e;
                            hiTail = e;
                        }
                    } while ((e = next) != null);
                    if (loTail != null) {
                        loTail.next = null;
                        newTab[j] = loHead;
                    }
                    if (hiTail != null) {
                        hiTail.next = null;
                        newTab[j + oldCap] = hiHead;
                    }
                }
            }
        }
    }
    return newTab;
}

如何进行 rehash

get方法可以使用位运算快速取模，同样的，我们在扩充HashMap的时候，不需要重新计算hash，只需要看看原来的hash值新增的那个bit是1还是0就好了，是0的话索引没变，是1的话索引变成“原索引+oldCap”

因此，resize每次扩容1倍