【集合源碼】HashMap源碼解析（基於JDK 1.8）

HashMap簡介

1.基於JDK 1.8的HashMap有三種數據結構，數組，鏈表，紅黑樹。

2.HashMap是非線程安全的。多線程環境下可以採用concurrent併發包下的concurrentHashMap。

3.HashMap存儲的內容是鍵值對(key-value)映射，key、value都可以爲null。

4.HashMap中的映射不是有序的。

5.實現了Cloneable接口，能被克隆。

6.實現了Serializable接口，支持序列化。

源碼解析

比較重要的方法都加了詳細的註解：

package java.util;

import java.io.IOException;
import java.io.InvalidObjectException;
import java.io.Serializable;
import java.lang.reflect.ParameterizedType;
import java.lang.reflect.Type;
import java.util.function.BiConsumer;
import java.util.function.BiFunction;
import java.util.function.Consumer;
import java.util.function.Function;


public class HashMap<K,V> extends AbstractMap<K,V> implements Map<K,V>, Cloneable, Serializable {

    private static final long serialVersionUID = 362498820763181265L;

    /**
     * 默認的初始容量（容量爲HashMap中槽的數目）是16，且實際容量必須是2的整數次冪。
     */
    static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; 

    /**
     *  最大容量（必須是2的冪且小於2的30次方，傳入容量過大將被這個值替換） 
     */
    static final int MAXIMUM_CAPACITY = 1 << 30;

    /**
     * 默認負載因子爲0.75
     */
    static final float DEFAULT_LOAD_FACTOR = 0.75f;

    /**
     * 鏈表轉化爲紅黑樹的臨界值爲8
     */
    static final int TREEIFY_THRESHOLD = 8;

    /**
     * 刪除衝突節點後，hash相同的節點數目小於這個數，紅黑樹就恢復成鏈表
     */
    static final int UNTREEIFY_THRESHOLD = 6;

    /**
     * 擴容的臨界值
     */
    static final int MIN_TREEIFY_CAPACITY = 64;

    /**
     * Node節點的數據結構
     */
    static class Node<K,V> implements Map.Entry<K,V> {
        final int hash;
        final K key;
        V value;
        Node<K,V> next;  //下一個節點

        Node(int hash, K key, V value, Node<K,V> next) {//初始化
            this.hash = hash;
            this.key = key;
            this.value = value;
            this.next = next;
        }

        public final K getKey()        { return key; }
        public final V getValue()      { return value; }
        public final String toString() { return key + "=" + value; }

        public final int hashCode() {
            //返回hash值
            return Objects.hashCode(key) ^ Objects.hashCode(value);
        }

        public final V setValue(V newValue) {
            V oldValue = value;
            value = newValue;
            return oldValue;
        }

        //重寫equals方法
        public final boolean equals(Object o) {
            if (o == this)
                return true;
            if (o instanceof Map.Entry) {
                Map.Entry<?,?> e = (Map.Entry<?,?>)o;
                if (Objects.equals(key, e.getKey()) && Objects.equals(value, e.getValue()))
                    return true;
            }
            return false;
        }
    }

    /**
     * 計算key.hashCode()。假如key爲空，返回0
     */
    static final int hash(Object key) {
        int h;
        return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
    }

    /**
     * 返回x的class
     */
    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;
    }

    /**
     * 返回k.compareTo(x) 
     */
    @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));
    }

    /**
     * 返回給定容量的2的冪次方大小
     */
    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;
    }

    /**
     * 存儲元素的數組
     */
    transient Node<K,V>[] table;

    /**
     * Holds cached entrySet(). 
     */
    transient Set<Map.Entry<K,V>> entrySet;

    /**
     * map中包含的鍵值對的個數.
     */
    transient int size;

    /**
     * HashMap被改變的次數  
     */
    transient int modCount;

    /**
     * HashMap的閾值，用於判斷是否需要調整HashMap的容量（threshold = 容量*加載因子）  
     */
    int threshold;

    /**
     * 哈希表的負載因子
     */
    final float loadFactor;

    /**
     * 指定“容量大小”（initialCapacity）和“加載因子”（loadFactor）的構造函數
     */
    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“容量大小”（initialCapacity）的構造函數
     */
    public HashMap(int initialCapacity) {
        this(initialCapacity, DEFAULT_LOAD_FACTOR);
    }

    /**
     * 默認構造函數
     */
    public HashMap() {
        this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted
    }

    /**
     * 包含“子Map”的構造函數
     */
    public HashMap(Map<? extends K, ? extends V> m) {
        this.loadFactor = DEFAULT_LOAD_FACTOR;
        putMapEntries(m, false);
    }

    /**
     * 實現 Map.putAll 和 Map 構造函數
     */
    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);
            }
        }
    }

    /**
     * 返回該map的鍵值對的數目
     */
    public int size() {
        return size;
    }

    /**
     * 該hashmap是否爲空。空則返回true，否則返回false
     */
    public boolean isEmpty() {
        return size == 0;
    }

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

    /**
     * 實現 Map.get 和相關方法
     */
    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) {
            // 數組元素相等
            if (first.hash == hash && // always check first node
                ((k = first.key) == key || (key != null && key.equals(k))))
                return first;
            // 桶中不止一個節點
            if ((e = first.next) != null) {
                // 在紅黑樹中get
                if (first instanceof TreeNode)
                    return ((TreeNode<K,V>)first).getTreeNode(hash, key);
                // 在鏈表中get
                do {
                    if (e.hash == hash &&
                        ((k = e.key) == key || (key != null && key.equals(k))))
                        return e;
                } while ((e = e.next) != null);
            }
        }
        return null;
    }

    /**
     * HashMap是否包含key
     */
    public boolean containsKey(Object key) {
        return getNode(hash(key), key) != null;
    }

    /**
     * 放入鍵值對。已存在則覆蓋已有的，不存在則新建    
     */
    public V put(K key, V value) {
        return putVal(hash(key), key, value, false, true);
    }

    /**
     * 實現Map.put和相關的方法
     */
    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)//tab爲空則創建
            n = (tab = resize()).length;
         // 計算index，並對null做處理
        if ((p = tab[i = (n - 1) & hash]) == null)
            tab[i] = newNode(hash, key, value, null);
        else {
            Node<K,V> e; K k;
            // 節點存在
            if (p.hash == hash && ((k = p.key) == key || (key != null && key.equals(k))))
                e = p;
            // 該鏈爲樹
            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;
                }
            }
            // 寫入
            if (e != null) { // 已經存在指定鍵的鍵值對
                V oldValue = e.value;
                if (!onlyIfAbsent || oldValue == null)
                    e.value = value;
                afterNodeAccess(e);
                return oldValue;
            }
        }
        ++modCount;
        // 超過負載 factor*current capacity，則resize
        if (++size > threshold)
            resize();
        afterNodeInsertion(evict);
        return null;
    }

    /**
     * 初始化或者doubles表的尺寸.
     */
    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) {
            // 超過最大值就不再擴充了，就只好隨你碰撞去吧
            if (oldCap >= MAXIMUM_CAPACITY) {
                threshold = Integer.MAX_VALUE;
                return oldTab;
            }
            // 沒超過最大值，就擴充爲原來的2倍
            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);
        }
        // 計算新的resize上限
        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) {
            // 把每個bucket都移動到新的buckets中
            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;
                            // 原索引
                            if ((e.hash & oldCap) == 0) {
                                if (loTail == null)
                                    loHead = e;
                                else
                                    loTail.next = e;
                                loTail = e;
                            }
                            // 原索引+oldCap
                            else {
                                if (hiTail == null)
                                    hiHead = e;
                                else
                                    hiTail.next = e;
                                hiTail = e;
                            }
                        } while ((e = next) != null);
                        // 原索引放到bucket裏
                        if (loTail != null) {
                            loTail.next = null;
                            newTab[j] = loHead;
                        }
                        // 原索引+oldCap放到bucket裏
                        if (hiTail != null) {
                            hiTail.next = null;
                            newTab[j + oldCap] = hiHead;
                        }
                    }
                }
            }
        }
        return newTab;
    }

    /**
     * 根據給的hash，替換掉所有鏈表中的節點。假如表太小，則resize    
     */
    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)
            resize();
        else if ((e = tab[index = (n - 1) & hash]) != null) {
            TreeNode<K,V> hd = null, tl = null;
            do {
                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);
        }
    }

    /**
     * // 將"m"的全部元素都添加到HashMap中  
     */
    public void putAll(Map<? extends K, ? extends V> m) {
        putMapEntries(m, true);
    }

    /**
     * 假如指定鍵存在，則移除該指定鍵的對應鍵值對
     */
    public V remove(Object key) {
        Node<K,V> e;
        return (e = removeNode(hash(key), key, null, false, true)) == null ?
            null : e.value;
    }

    /**
     * 實現Map.remove 和相關的方法
     */
    final Node<K,V> removeNode(int hash, Object key, Object value, boolean matchValue, boolean movable) {
        Node<K,V>[] tab; Node<K,V> p; int n, index;
        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)
                    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);
                }
            }
            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);
                else if (node == p)
                    tab[index] = node.next;
                else
                    p.next = node.next;
                ++modCount;
                --size;
                afterNodeRemoval(node);
                return node;
            }
        }
        return null;
    }

    /**
     * 清空該HashMap
     */
    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;
        }
    }

    /**
     * 該HashMap是否包含指定value
     */
    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;
    }

    /**
     * 返回“key的集合”，實際上返回一個“KeySet對象”
     */
    public Set<K> keySet() {
        Set<K> ks = keySet;
        if (ks == null) {
            ks = new KeySet();
            keySet = ks;
        }
        return ks;
    }
    /**
    * Key對應的集合  
    * KeySet繼承於AbstractSet，說明該集合中沒有重複的Key。  
    */
    final class KeySet extends AbstractSet<K> {
        public final int size()                 { return size; }
        public final void clear()               { HashMap.this.clear(); }
        public final Iterator<K> iterator()     { return new KeyIterator(); }
        public final boolean contains(Object o) { return containsKey(o); }
        public final boolean remove(Object key) {
            return removeNode(hash(key), key, null, false, true) != null;
        }
        public final Spliterator<K> spliterator() {
            return new KeySpliterator<>(HashMap.this, 0, -1, 0, 0);
        }
        public final void forEach(Consumer<? super K> action) {
            Node<K,V>[] tab;
            if (action == null)
                throw new NullPointerException();
            if (size > 0 && (tab = table) != null) {
                int mc = modCount;
                for (int i = 0; i < tab.length; ++i) {
                    for (Node<K,V> e = tab[i]; e != null; e = e.next)
                        action.accept(e.key);
                }
                if (modCount != mc)
                    throw new ConcurrentModificationException();
            }
        }
    }

    /**
     * 返回“value集合”，實際上返回的是一個Values對象  
     */
    public Collection<V> values() {
        Collection<V> vs = values;
        if (vs == null) {
            vs = new Values();
            values = vs;
        }
        return vs;
    }

    /**
    *“value集合”  
    * Values繼承於AbstractCollection，不同於“KeySet繼承於AbstractSet”，  
    * Values中的元素能夠重複。因爲不同的key可以指向相同的value。
    */
    final class Values extends AbstractCollection<V> {
        public final int size()                 { return size; }
        public final void clear()               { HashMap.this.clear(); }
        public final Iterator<V> iterator()     { return new ValueIterator(); }
        public final boolean contains(Object o) { return containsValue(o); }
        public final Spliterator<V> spliterator() {
            return new ValueSpliterator<>(HashMap.this, 0, -1, 0, 0);
        }
        public final void forEach(Consumer<? super V> action) {
            Node<K,V>[] tab;
            if (action == null)
                throw new NullPointerException();
            if (size > 0 && (tab = table) != null) {
                int mc = modCount;
                for (int i = 0; i < tab.length; ++i) {
                    for (Node<K,V> e = tab[i]; e != null; e = e.next)
                        action.accept(e.value);
                }
                if (modCount != mc)
                    throw new ConcurrentModificationException();
            }
        }
    }


    /**
     * 克隆一個HashMap，並返回Object對象  
     */
    @SuppressWarnings("unchecked")
    @Override
    public Object clone() {
        HashMap<K,V> result;
        try {
            result = (HashMap<K,V>)super.clone();
        } catch (CloneNotSupportedException e) {
            // 因爲是可克隆的，所以這不應該發生
            throw new InternalError(e);
        }
        result.reinitialize();
        result.putMapEntries(this, false);
        return result;
    }

    // 當序列化HashSets的時候，這些方法會被調用
    final float loadFactor() { return loadFactor; }
    final int capacity() {
        return (table != null) ? table.length :
            (threshold > 0) ? threshold :
            DEFAULT_INITIAL_CAPACITY;
    }

    /**
     * java.io.Serializable的寫入函數  
     * 將HashMap的“總的容量，實際容量，所有的Entry”都寫入到輸出流中  
     */
    private void writeObject(java.io.ObjectOutputStream s) throws IOException {
        int buckets = capacity();
        // Write out the threshold, loadfactor, and any hidden stuff
        s.defaultWriteObject();
        s.writeInt(buckets);
        s.writeInt(size);
        internalWriteEntries(s);
    }

    /**
     * java.io.Serializable的讀取函數：根據寫入方式讀出  
     * 將HashMap的“總的容量，實際容量，所有的Entry”依次讀出 
     */
    private void readObject(java.io.ObjectInputStream s)
        throws IOException, ClassNotFoundException {
        // Read in the threshold (ignored), loadfactor, and any hidden stuff
        s.defaultReadObject();
        reinitialize();
        if (loadFactor <= 0 || Float.isNaN(loadFactor))
            throw new InvalidObjectException("Illegal load factor: " +
                                             loadFactor);
        s.readInt();                // Read and ignore number of buckets
        int mappings = s.readInt(); // Read number of mappings (size)
        if (mappings < 0)
            throw new InvalidObjectException("Illegal mappings count: " +
                                             mappings);
        else if (mappings > 0) { // (if zero, use defaults)
            // Size the table using given load factor only if within
            // range of 0.25...4.0
            float lf = Math.min(Math.max(0.25f, loadFactor), 4.0f);
            float fc = (float)mappings / lf + 1.0f;
            int cap = ((fc < DEFAULT_INITIAL_CAPACITY) ?
                       DEFAULT_INITIAL_CAPACITY :
                       (fc >= MAXIMUM_CAPACITY) ?
                       MAXIMUM_CAPACITY :
                       tableSizeFor((int)fc));
            float ft = (float)cap * lf;
            threshold = ((cap < MAXIMUM_CAPACITY && ft < MAXIMUM_CAPACITY) ?
                         (int)ft : Integer.MAX_VALUE);
            @SuppressWarnings({"rawtypes","unchecked"})
                Node<K,V>[] tab = (Node<K,V>[])new Node[cap];
            table = tab;

            // Read the keys and values, and put the mappings in the HashMap
            for (int i = 0; i < mappings; i++) {
                @SuppressWarnings("unchecked")
                    K key = (K) s.readObject();
                @SuppressWarnings("unchecked")
                    V value = (V) s.readObject();
                putVal(hash(key), key, value, false, false);
            }
        }
    }
    /**
     * 紅黑樹、迭代器、分割器等等相關代碼就不一一羅列了。
     */
}

小結

• HashMap有三種數據結構，分別是數組，鏈表，紅黑樹。在JDK1.8之前是沒有紅黑樹的。這裏加上紅黑樹是因爲僅僅用鏈表法解決哈希衝突時，鏈表的長度過長，查找的時間複雜度爲O(n)，性能沒有紅黑樹好（查找的時間複雜度爲O(logn)）。

• 如果衝突節點到8時，就把鏈表轉換成紅黑樹；爲什麼不直接用紅黑樹徹底代替鏈表呢？這裏我猜測是因爲當鏈表的長度只是個位數時，查找的時間複雜度只是常數級別的，性能完全夠了。而且紅黑樹結構實現複雜。

• 如果bucket滿了(超過load factor * current 的容量)，就要resize。

• 在resize的過程，就是把bucket擴充爲2倍，之後重新計算index，把節點再放到新的bucket中。

• get過程中如果出現衝突，則通過key.equals(k)去查找對應的entry
  若爲樹，則在樹中通過key.equals(k)查找，若爲鏈表，則在鏈表中通過key.equals(k)查找。