深入HashSet底層源碼，分析實現原理(數組擴容，鏈表，二叉樹)

以add()方法爲例，查看hashSet的底層源碼實現，後面的源碼啃不動了。。。。就我理解是數組+鏈表；當鏈表結構達到8個時候，會將前面的8個鏈表轉換成二叉樹結構，而不是以第8個鏈表爲根節點，往後依次形成二叉樹，即將數組+鏈表變成了數組+二叉樹，所以最終的結構可能是：數組+鏈表+二叉樹，其中二叉樹以數組爲基礎，而不是以鏈表爲基礎，即不會在鏈表後面形成二叉樹，而是將鏈表(達到8個結點)轉換成二叉樹。

public boolean add(E e) {
        //第一次返回null，即第一次添加成功
        return map.put(e, PRESENT)==null;
}

 

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


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


hashCode()方法：
//調用非java接口
//此處調用的object的原生hashCode()方法
public native int hashCode();

 

transient Node<K,V>[] table;

final V putVal(int hash, K key, V value, boolean onlyIfAbsent,
                   boolean evict) {
        Node<K,V>[] tab; Node<K,V> p; int n, i;
        //初始化table爲null
        if ((tab = table) == null || (n = tab.length) == 0)
            //resize()方法擴容，返回Node[],數組大小是16
            n = (tab = resize()).length;
//以下判斷簡寫成15&hash，進一步寫成:15 & ((hx = ((Object)obj).hashCode()) ^ (hx >>> 16))
//hx是一個int類型的臨時變量，obj是任意類型，基本或引用數據類型
//15 & ((hx = ((Object)obj).hashCode()) ^ (hx >>> 16))
//等價於
//((Object)obj).hashCode() % 16；即tab[]數組索引在0~15之間
//用Object強轉是因爲其調用的是Object原生的hashCode()方法，而非其他重寫的hashCode()方法
        //此處if判斷，正是避免重複元素的關鍵，相同元素不會進行newNode
        if ((p = tab[i = (n - 1) & hash]) == null)
            //返回一個Node對象，其值是傳入的key，Node對象作爲Node<K,V>[]中的第i個元素
            tab[i] = newNode(hash, key, value, null);
        else {
            Node<K,V> e; K k;
//對於Set集合來說，判斷是否是同一個元素
//對於Map集合來說，判斷key是否相同
            if (p.hash == hash &&
                ((k = p.key) == key || (key != null && key.equals(k))))
                //此處的p既是Node<K,V>[]中已存在的node對象
                e = p;
            //對於Set而言，判斷元素是否是二叉樹
            else if (p instanceof TreeNode)
                e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
            else {
                //對於Set集合而言，創建鏈表結構
                for (int binCount = 0; ; ++binCount) {
                    //p是數組中存儲的Node元素，同時也是鏈表中的結點元素
                    if ((e = p.next) == null) {
                        //新創建一個Node對象，並且作爲上一個Node對象的下一個元素，即鏈表結構
                        p.next = newNode(hash, key, value, null);
                        //最大值是8
                        if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
                            treeifyBin(tab, hash);
                        break;
                    }
                    //判斷鏈表中的元素是否是同一個元素
                    if (e.hash == hash &&
                        ((k = e.key) == key || (key != null && key.equals(k))))
                        break;
                    p = e;
                }
            }
            //對於Set集合而言，同一個元素，返回一個Object地址
            //對於Map而言，判斷Map中key是否存在，新值覆蓋舊值
            if (e != null) { // existing mapping for key
                V oldValue = e.value;
                if (!onlyIfAbsent || oldValue == null)
                    //新值覆蓋原來的值
                    e.value = value;
                afterNodeAccess(e);
                //返回舊值
                return oldValue;
            }
        }
        ++modCount;
        //threshold閾值，剛開始是16*0.75=12
        if (++size > threshold)
    //當添加完第12個元素後進行擴容，同時將原來的Node<K,V>[]數組中的元素全部添加到新的數組中(32)
            resize();
        afterNodeInsertion(evict);
        //每次添加新元素都返回Null
        return null;
}

 

final Node<K,V>[] resize() {
        //開始初始化爲null
        //在添加一個元素後，table不爲null，大小是16
        Node<K,V>[] oldTab = table;
        //16
        int oldCap = (oldTab == null) ? 0 : oldTab.length;
        //開始初始化爲0
        int oldThr = threshold;
        int newCap, newThr = 0;
        if (oldCap > 0) {
            if (oldCap >= MAXIMUM_CAPACITY) {
                threshold = Integer.MAX_VALUE;
                return oldTab;
            }
            //newCap = 32，容量擴大一倍
            else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY &&
                     oldCap >= DEFAULT_INITIAL_CAPACITY)
                //閾值擴大一倍，24
                newThr = oldThr << 1; // double threshold
        }
        else if (oldThr > 0) // initial capacity was placed in threshold
            newCap = oldThr;
        else { 
            //下面的英文解釋初始化爲0，使用默認值              
            // zero initial threshold signifies using defaults
            //static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16
            newCap = DEFAULT_INITIAL_CAPACITY;//16
            //static final float DEFAULT_LOAD_FACTOR = 0.75f;
            newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);//12
        }
        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"})
            //第一次添加元素時創建大小是16的Node數組
            //擴容時創建大小是32的Node<K,V>[]數組
            Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap];
        //將新的Node<K,V>[]數組賦給成員變量table
        table = newTab;
        if (oldTab != null) {
            //將原Node<K,V>[]數組中的元素全部放入新的newTab中
            for (int j = 0; j < oldCap; ++j) {
                Node<K,V> e;
                //獲取原數組中的node對象賦給e
                if ((e = oldTab[j]) != null) {
                    oldTab[j] = null;
                    //判斷是否是數組，e.next == null 代表數組
                    if (e.next == null)
                   //同上15&hash，等價於對32取模，結果是0~31，將e放入新的Node<K,V>[]數組中
                        newTab[e.hash & (newCap - 1)] = e;
                    //判斷是否是樹結構
                    else if (e instanceof TreeNode)
                        ((TreeNode<K,V>)e).split(this, newTab, j, oldCap);
                    else { // preserve order
                        //鏈表
                        Node<K,V> loHead = null, loTail = null;
                        Node<K,V> hiHead = null, hiTail = null;
                        Node<K,V> next;
                        do {
                            //獲取鏈表中下一個元素
                            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;
                        }
                    }
                }
            }
        }
        //返回新數組
        return newTab;
}

 

final void treeifyBin(Node<K,V>[] tab, int hash) {
        int n, index; Node<K,V> e;
        if (tab == null || (n = tab.length) < MIN_TREEIFY_CAPACITY)
            //擴容後大小是64
            resize();
        else if ((e = tab[index = (n - 1) & hash]) != null) {
            TreeNode<K,V> hd = null, tl = null;
            do {
                //將鏈表的元素轉換成樹結構
                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)
                hd.treeify(tab);
        }
}

replacementTreeNode()方法：
TreeNode<K,V> replacementTreeNode(Node<K,V> p, Node<K,V> next) {
        return new TreeNode<>(p.hash, p.key, p.value, next);
}

treeify()方法：
final void treeify(Node<K,V>[] tab) {
            TreeNode<K,V> root = null;
            for (TreeNode<K,V> x = this, next; x != null; x = next) {
                next = (TreeNode<K,V>)x.next;
                x.left = x.right = null;
                if (root == null) {
                    x.parent = null;
                    x.red = false;
                    root = x;
                }
                else {
                    K k = x.key;
                    int h = x.hash;
                    Class<?> kc = null;
                    for (TreeNode<K,V> p = root;;) {
                        int dir, ph;
                        K pk = p.key;
                        if ((ph = p.hash) > h)
                            dir = -1;
                        else if (ph < h)
                            dir = 1;
                        else if ((kc == null &&
                                  (kc = comparableClassFor(k)) == null) ||
                                 (dir = compareComparables(kc, k, pk)) == 0)
                            dir = tieBreakOrder(k, pk);

                        TreeNode<K,V> xp = p;
                        if ((p = (dir <= 0) ? p.left : p.right) == null) {
                            x.parent = xp;
                            if (dir <= 0)
                                xp.left = x;
                            else
                                xp.right = x;
                            root = balanceInsertion(root, x);
                            break;
                        }
                    }
                }
            }
            moveRootToFront(tab, root);
}