HashMap相关笔记（二） - 类方法

类方法

静态工具方法

• hash

/**
 * Computes key.hashCode() and spreads (XORs) higher bits of hash
 * to lower.  Because the table uses power-of-two masking, sets of
 * hashes that vary only in bits above the current mask will
 * always collide. (Among known examples are sets of Float keys
 * holding consecutive whole numbers in small tables.)  So we
 * apply a transform that spreads the impact of higher bits
 * downward. There is a tradeoff between speed, utility, and
 * quality of bit-spreading. Because many common sets of hashes
 * are already reasonably distributed (so don't benefit from
 * spreading), and because we use trees to handle large sets of
 * collisions in bins, we just XOR some shifted bits in the
 * cheapest possible way to reduce systematic lossage, as well as
 * to incorporate impact of the highest bits that would otherwise
 * never be used in index calculations because of table bounds.
 */
static final int hash(Object key) {
    int h;
    return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}

• 获取可比较的类的class对象

/**
 * Returns x's Class if it is of the form "class C implements
 * Comparable<C>", else null.
 */
static Class<?> comparableClassFor(Object x) {
    if (x instanceof Comparable) {
        Class<?> c; Type[] ts, as; Type t; ParameterizedType p;
        if ((c = x.getClass()) == String.class) // bypass checks
            return c;
        if ((ts = c.getGenericInterfaces()) != null) {
            for (int i = 0; i < ts.length; ++i) {
                if (((t = ts[i]) instanceof ParameterizedType) &&
                    ((p = (ParameterizedType)t).getRawType() ==
                     Comparable.class) &&
                    (as = p.getActualTypeArguments()) != null &&
                    as.length == 1 && as[0] == c) // type arg is c
                    return c;
            }
        }
    }
    return null;
}

• 也是用来比较的

/**
 * Returns k.compareTo(x) if x matches kc (k's screened comparable
 * class), else 0.
 */
@SuppressWarnings({"rawtypes","unchecked"}) // for cast to Comparable
static int compareComparables(Class<?> kc, Object k, Object x) {
    return (x == null || x.getClass() != kc ? 0 :
            ((Comparable)k).compareTo(x));
}

• 获取table的size（这个必须是2的整数次幂）

/**
 * Returns a power of two size for the given target capacity.
 */
static final int tableSizeFor(int cap) {
    int n = cap - 1;
    n |= n >>> 1;
    n |= n >>> 2;
    n |= n >>> 4;
    n |= n >>> 8;
    n |= n >>> 16;
    return (n < 0) ? 1 : (n >= MAXIMUM_CAPACITY) ? MAXIMUM_CAPACITY : n + 1;
}

构造方法

• 指定大小和装载引子

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);
}

• 指定大小

public HashMap(int initialCapacity) {
    this(initialCapacity, DEFAULT_LOAD_FACTOR);
}

• 没参数

public HashMap() {
    this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted
}

• 拿别的Map初始化

public HashMap(Map<? extends K, ? extends V> m) {
    this.loadFactor = DEFAULT_LOAD_FACTOR;
    putMapEntries(m, false);
}

    final void putMapEntries(Map<? extends K, ? extends V> m, boolean evict) {
        int s = m.size();
        if (s > 0) {
            if (table == null) { // pre-size
                float ft = ((float)s / loadFactor) + 1.0F;
                int t = ((ft < (float)MAXIMUM_CAPACITY) ?
                         (int)ft : MAXIMUM_CAPACITY);
                if (t > threshold)
                    threshold = tableSizeFor(t);
            }
            else if (s > threshold)
                resize();
            for (Map.Entry<? extends K, ? extends V> e : m.entrySet()) {
                K key = e.getKey();
                V value = e.getValue();
                putVal(hash(key), key, value, false, evict);
            }
        }
    }

数据结构视图

• 重要的方法：

  • 查找方法：

    • 外层：(hash & size-1)

    • 节点内部：树查找 或

      (e.hash == hash &&
          ((k = e.key) == key ||
           (key != null && key.equals(k))))
      

    • 对象hash方法：

      static final int hash(Object key) {
          int h;
          return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
      }
      

查找

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) {//注意这里，桶式存储
        //index：（n - 1) & hash
        if (first.hash == hash && // always check first node
            ((k = first.key) == key || (key != null && key.equals(k))))
            return first;
        if ((e = first.next) != null) {//往下查找
            if (first instanceof TreeNode)//树节点就按照树节点找
                return ((TreeNode<K,V>)first).getTreeNode(hash, key);
            do {//链表节点就一层层往后找，通过key的比较
                if (e.hash == hash &&
                    ((k = e.key) == key || (key != null && key.equals(k))))
                    return e;
            } while ((e = e.next) != null);
        }
    }
    return null;
}

public boolean containsKey(Object key) {
        return getNode(hash(key), key) != null;
    }

//暴力O（n*F）的查找
    public boolean containsValue(Object value) {
        Node<K,V>[] tab; V v;
        if ((tab = table) != null && size > 0) {
            for (int i = 0; i < tab.length; ++i) {
                for (Node<K,V> e = tab[i]; e != null; e = e.next) {
                    if ((v = e.value) == value ||
                        (value != null && value.equals(v)))
                        return true;
                }
            }
        }
        return false;
    }

在这里能看到：

• 相同hash值的，存储位置都是 (size - 1) & hash，而后通过链表/树状结构，进行存储

修改

添加

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;//如果table数组长度为0或者空就初始化
        if ((p = tab[i = (n - 1) & hash]) == null)
            //如果hash数组中对应索引的桶是空的就新造一个
            //并且由于该位置是空的，因此只要造一个普通的链表头就可以了
            tab[i] = newNode(hash, key, value, null);
        else {//该位置有桶了，那就对桶进行处理了，下面才是麻烦的地方
            Node<K,V> e;//e用来指向该hash桶位置的头
            K k;
            if (p.hash == hash &&
                ((k = p.key) == key || (key != null && key.equals(k))))
                //一样了：先把现在的存着
                e = p;
            //如果是树的话，插入的职责就交由自身去执行了
            else if (p instanceof TreeNode)
                e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
            else {
                for (int binCount = 0; ; ++binCount) {
                    //先赋值，往后走
                    //走到头了还是空
                    if ((e = p.next) == null) {
                        //那就插入
                        p.next = newNode(hash, key, value, null);
                      //满足条件就变树 其实这里有个问题：为什么要-1？ - > 因为第一个不算进去跳过了 
                        if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
                            treeifyBin(tab, hash);
                        break;
                    }
                    //如果一样的存过了：那就跳出去吧
                    if (e.hash == hash &&
                        ((k = e.key) == key || (key != null && key.equals(k))))
                        break;
                    //链表trick
                    p = e;
                }
            }
            //从上面的for循环中能看到：只有在数据结构中不重复，才会是空
            if (e != null) { // existing mapping for key
                //swap
                V oldValue = e.value;
                if (!onlyIfAbsent || oldValue == null)
                    e.value = value;
                //其实是给linkedHashMap留的实现，默认是空的
                afterNodeAccess(e);
                return oldValue;
            }
        }
    //注意：此处不检查fail-fast
        ++modCount;
    //大小超过阈值了：就resize
        if (++size > threshold)
            resize();
    	//给linkedHashMap留的实现
        afterNodeInsertion(evict);
        return null;
    }

这里能看到：

• 不包含后续操作以及树状节点的话，其实实现就是数组+链表的标准hash表。
• 给LinkedHashMap留了两个口子：
  • afterNodeAccess(e)
  • afterNodeInsertion(evict)
• 树状节点的查找就放到树节点内部去实现了
• 普通node没有实现查询的方法，本身也比较简单，就原地实现

删除

public V remove(Object key) {
    Node<K,V> e;
    return (e = removeNode(hash(key), key, null, false, true)) == null ?
        null : e.value;
}

final Node<K,V> removeNode(int hash, Object key, Object value,
                           boolean matchValue, boolean movable) {
    Node<K,V>[] tab; 
    Node<K,V> p; //外部节点的头
    int n, index;
    //如果能找得到，才在链表/树中查找
    if ((tab = table) != null && (n = tab.length) > 0 &&
        (p = tab[index = (n - 1) & hash]) != null) {
        Node<K,V> node = null, e; K k; V v;
        if (p.hash == hash &&
            ((k = p.key) == key || (key != null && key.equals(k))))
            node = p;
        else if ((e = p.next) != null) {
            if (p instanceof TreeNode)
                //可以看到，对于树节点，都是交给treeNode进行托管的
                node = ((TreeNode<K,V>)p).getTreeNode(hash, key);
            else {
                do {
                    if (e.hash == hash &&
                        ((k = e.key) == key ||
                         (key != null && key.equals(k)))) {
                        node = e;
                        break;
                    }
                    p = e;
                } while ((e = e.next) != null);
            }
        }
        //先找到，找不到就不remove了
        if (node != null && (!matchValue || (v = node.value) == value ||
                             (value != null && value.equals(v)))) {
            if (node instanceof TreeNode)
                ((TreeNode<K,V>)node).removeTreeNode(this, tab, movable);
            //就是链表节点删除，头就指向下一个，不然就是直接把前驱节点的next指向删除节点的next
            else if (node == p)
                tab[index] = node.next;
            else
                //上面循环查找的时候，p已经是node的前驱节点了
                p.next = node.next;
            ++modCount;
            --size;
            afterNodeRemoval(node);
            return node;
        }
    }
    return null;
}

• 整体删除

public void clear() {
    Node<K,V>[] tab;
    modCount++;
    if ((tab = table) != null && size > 0) {
        size = 0;
        for (int i = 0; i < tab.length; ++i)
            tab[i] = null;
    }
}

容器变换

外部容器

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;
    //---------- 阈值与大小的计算--------------
    if (oldCap > 0) {//---------------------(0)
        //其实最大的阈值，可以到2^31 -1 ...
        if (oldCap >= MAXIMUM_CAPACITY) {
            threshold = Integer.MAX_VALUE;
            return oldTab;
        }
        //如果没上面那种情况，直接double
        else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY &&
                 oldCap >= DEFAULT_INITIAL_CAPACITY)
            newThr = oldThr << 1; // double threshold
    }
    //往下指的都是原来数组大小都是空的情况 ---------------（1）
    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);
    }
    //补充一下没初始化的情况:(0)处，（1）处都有可能没有初始化的情况
    if (newThr == 0) {
        float ft = (float)newCap * loadFactor;
        newThr = (newCap < MAXIMUM_CAPACITY && ft < (float)MAXIMUM_CAPACITY ?
                  (int)ft : Integer.MAX_VALUE);
    }
    //--------------迁移------------------
    //先把外部的数组声明好
    threshold = newThr;
    @SuppressWarnings({"rawtypes","unchecked"})
    Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap];
    table = newTab;
    //不为空就开始迁移
    if (oldTab != null) {
        for (int j = 0; j < oldCap; ++j) {
            Node<K,V> e;
            if ((e = oldTab[j]) != null) {
                //摘下来，让GC一步步工作
                oldTab[j] = null;
                //其实就是如果是一个单节点，没有后面的尾巴的话，就rehash
                if (e.next == null)
                    newTab[e.hash & (newCap - 1)] = e;
                //树节点就内部拆分了，具体放在哪里？得看树节点的实现方式 //todo
                else if (e instanceof TreeNode)
                    ((TreeNode<K,V>)e).split(this, newTab, j, oldCap);
                else { //这里就是note里说的情况了：维持顺序
                    Node<K,V> loHead = null, loTail = null;
                    Node<K,V> hiHead = null, hiTail = null;
                    Node<K,V> next;
                    do {
                        next = e.next;
                        //拼lo
                        if ((e.hash & oldCap) == 0) {
                            if (loTail == null)
                                loHead = e;
                            else
                                loTail.next = e;
                            loTail = e;
                        }
                        //拼hi
                        else {
                            if (hiTail == null)
                                hiHead = e;
                            else
                                hiTail.next = e;
                            hiTail = e;
                        }
                    } while ((e = next) != null);
                    //如果是拼了lo这条，那就直接拼到j上
                    if (loTail != null) {
                        loTail.next = null;
                        newTab[j] = loHead;
                    }
                    //如果拼了hi这条，那就拼到j+cap上
                    if (hiTail != null) {
                        hiTail.next = null;
                        newTab[j + oldCap] = hiHead;
                    }
                }
            }
        }
    }
    return newTab;
}

有几个重点：

• 为什么要区分lo和hi？

  • 因为在同一个bin中的值，原来的计算索引方式为:

    • index = hash & （oldCap-1）

    在此处是hash &oldCap，因此值可能不同了

• 为什么rehash区分lo和hi，是根据 hash&oldCap==0,而不是oldCap-1？

• lo为什么不用移动？

  • 原因：
    • 假设原来位置K上的hash的二进制为：101111,原来的cap为：010000
    • 那么，K的索引位置为：101111 & 001111 = 1111，hash&oldCap=0，而且扩容后的那一位恰好是0。
    • 扩容后的cap，因为没有到MAX_VALUE，因此cap为：100000
    • 那么，K的新索引计算方式为 101111 & 011111 = 1111 ,和原来是一样的
    • 因此，如果hash&oldCap==0，那么就放到原来的位置上即可。（resize前后的cap数值，往前多的那一位，对hash&cap-1方法的结果恰好是没影响的）

• hi为什么是j+oldCap的索引位置？

  • 原因：
    • 同上面的说法类似：此时假设K位置上hash为：111111
    • 如果hash&oldCap！=0，说明新的那一位，原来的hash值上刚好有。
      • (111111 & 010000 = 0100000)
    • 那么，hash & newCap-1 , 刚好比原来在前面的位置多一位
      • (111111 & 001111 = 001111)
      • (111111 & 011111 = 011111)
    • 刚好是比原来的多了 010000,即：OldCap的值
  • 因此，如果hash&oldCap!=0，index = j+oldCap

次层容器

树状化

final void treeifyBin(Node<K,V>[] tab, int hash) {
    int n, index; Node<K,V> e;
    //这里就是上面注释里说的：如果太小了干脆就别变树了，变大一次看看
    if (tab == null || (n = tab.length) < MIN_TREEIFY_CAPACITY)
        resize();
    else if ((e = tab[index = (n - 1) & hash]) != null) {
        TreeNode<K,V> hd = null, tl = null;//hd-结果，tl-迭代指针
        do {//将链表变成树的结构
            TreeNode<K,V> p = replacementTreeNode(e, null);
            if (tl == null)
                hd = p;
            else {
                p.prev = tl;
                tl.next = p;
            }
            tl = p;
        } while ((e = e.next) != null);
        if ((tab[index] = hd) != null)//赋值，同时树化容器
            //其实这一步只看到这里不是很清楚是在干什么，需要树节点中去看
            hd.treeify(tab);
    }
}

//其实就是搞个新的，写个代理方法罢了
TreeNode<K,V> replacementTreeNode(Node<K,V> p, Node<K,V> next) {
        return new TreeNode<>(p.hash, p.key, p.value, next);
    }

内容视图

获取key

public Set<K> keySet() {
    Set<K> ks = keySet;
    if (ks == null) {
        ks = new KeySet();
        keySet = ks;
    }
    return ks;
}

获取value

public Collection<V> values() {
    Collection<V> vs = values;
    if (vs == null) {
        vs = new Values();
        values = vs;
    }
    return vs;
}

获取键值对

public Set<Map.Entry<K,V>> entrySet() {
    Set<Map.Entry<K,V>> es;
    return (es = entrySet) == null ? (entrySet = new EntrySet()) : es;
}

1.8相关方法

把Map里的1.8新加的方法都实现了一遍，没有什么新的特性，就是新瓶装老酒。

容器的对象属性

Clone()
loadFactor()
capacity() ()->return (table != null) ? table.length :
            (threshold > 0) ? threshold :
            DEFAULT_INITIAL_CAPACITY;
writeObject
readObject

• 值得注意的一个地方，是这些容器都支持从流直接写入内存并格式化（writeObject，readObject）。