Java集合系列源码分析（三）--HashMap

一、HashMap

基于数组和链表实现的HashMap，当链表数据过多时，会转为红黑树提高查询效率。
实现采用了多种数据结构，所以HashMap在增删改查上的效率都很高，不考了哈希冲突时间复杂度可以达到O(1)

二、源码分析

2.1 继承结构和层次


实现了Map接口，克隆接口和序列化接口

2.2 HashMap属性

/**
 * 默认初始容量
 */
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16

/**
 *默认最大容量
 */
static final int MAXIMUM_CAPACITY = 1 << 30;

/**
 * 负载因子，当元素数量达到容量*负载因子，进行扩容
 */
static final float DEFAULT_LOAD_FACTOR = 0.75f;

/**
 * 链表转化为树的阀值
 */
static final int TREEIFY_THRESHOLD = 8;

/**
 * 树转化为链表的阀值
 */
static final int UNTREEIFY_THRESHOLD = 6;

/**
 * 桶中数据采用树存储时，最小的容量
 */
static final int MIN_TREEIFY_CAPACITY = 64;

/**
 * 存储元素的哈希表数组
 */
transient Node<K,V>[] table;

/**
 * HashMap大小
 */
transient int size;

/**
 * 修改次数
 */
transient int modCount;

/**
 * 容量临界值 (capacity * load factor).
 */
int threshold;

/**
 * 负载因子
 */
final float loadFactor;

Node节点代码如下，可以看出是一个链表

static class Node<K,V> implements Map.Entry<K,V> {
    final int hash;
    final K key;
    V value;
    Node<K,V> next;

    Node(int hash, K key, V value, Node<K,V> next) {
        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() {
        return Objects.hashCode(key) ^ Objects.hashCode(value);
    }

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

    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;
    }
}

2.3 构造方法

无参构造方法

将负载因子loadFactor设置为默认负载因子0.75

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

带容量构造方法

public HashMap(int initialCapacity) {
	//调用了带容量和默认负载因子的构造方法
    this(initialCapacity, DEFAULT_LOAD_FACTOR);
}

带容量和负载因子的构造方法

根据传入参数赋值给threshold 和 loadFactory

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);
}

map参数构造方法

public HashMap(Map<? extends K, ? extends V> m) {
	//负载因子使用默认值
    this.loadFactor = DEFAULT_LOAD_FACTOR;
    //存入数据
    putMapEntries(m, false);
}

final void putMapEntries(Map<? extends K, ? extends V> m, boolean evict) {
	//获取传入map大小
    int s = m.size();
    if (s > 0) {
    	//判断table是否初始化
        if (table == null) { // pre-size
        	//长度=容量*负载因子，此处求容量，+1.0F防止后面类型转为int时容量小了
            float ft = ((float)s / loadFactor) + 1.0F;
            //容量小于上线则使用计算出的容量
            int t = ((ft < (float)MAXIMUM_CAPACITY) ?
                     (int)ft : MAXIMUM_CAPACITY);
           //初始化临界值，
            if (t > threshold)
            	//获得比入参数大的2的高次幂
                threshold = tableSizeFor(t);
        }
        //table已经初始化了，进行扩容
        else if (s > threshold)
            resize();
        //扩容后吧map的数组转如hashmap中
        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);
        }
    }
}

2.4 常用方法

2.4.1 新增

会涉及到hash计算，先看下hash值的计算

static final int hash(Object key) {
    int h;
    //key的hash值赋给h，计算h与h移位的异或，减少hash冲突
    return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}

以及resize方法，调整table数组大小

   final Node<K,V>[] resize() {
   		//未resize前的table作为oldTab
        Node<K,V>[] oldTab = table;
        //获得oldTab的长度oldCap
        int oldCap = (oldTab == null) ? 0 : oldTab.length;
        //获得未resize前的临界值threshold作为oldThr
        int oldThr = threshold;
        //初始化新的长度和临界值
        int newCap, newThr = 0;
        //已经初始化过了
        if (oldCap > 0) {
        	//如果大于最大值
            if (oldCap >= MAXIMUM_CAPACITY) {
            	//临界值设为最大值
                threshold = Integer.MAX_VALUE;
                //返回旧table，无扩容
                return oldTab;
            }
           //扩容两倍且小于最大容量 && 旧长度大于16
            else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY &&
                     oldCap >= DEFAULT_INITIAL_CAPACITY)
                //临界值扩大两倍
                newThr = oldThr << 1; // double threshold
        }
		//如果临界值oldThr>0，说明已经被初始化了，但是无数据，
        else if (oldThr > 0) // initial capacity was placed in threshold
        	//设置新的临界值同旧临界值
            newCap = oldThr;
        else {               // zero initial threshold signifies using defaults
        	//之前未初始化，初始化为默认值
            newCap = DEFAULT_INITIAL_CAPACITY; //16
            newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY); //12
        }
        //如果扩容临界值还为0
        if (newThr == 0) {
        	//根据容量*负载因子计算临界值
            float ft = (float)newCap * loadFactor;
            newThr = (newCap < MAXIMUM_CAPACITY && ft < (float)MAXIMUM_CAPACITY ?
                      (int)ft : Integer.MAX_VALUE);
        }
        //赋值给新的临界值
        threshold = newThr;
        @SuppressWarnings({"rawtypes","unchecked"})
        //初始化table
        Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap];
        table = newTab;
        //旧数据存入
        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;
                        }
                    }
                }
            }
        }
        //返回扩容后的table
        return newTab;
    }

新增的put方法

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) {
        //定义哈希数组，哈希桶，hashmap长度，数组下标
        Node<K,V>[] tab; Node<K,V> p; int n, i;
        //未初始化则进行初始化
        if ((tab = table) == null || (n = tab.length) == 0)
            n = (tab = resize()).length;
       //计算当前哈希桶位置是否有值，为空则直接插入
        if ((p = tab[i = (n - 1) & hash]) == null)
            tab[i] = newNode(hash, key, value, null);
        //产生哈希冲突
        else {
            Node<K,V> e; K k;
            //如果当前节点的hash值和key值与传入的hash值和key值一致，则更新数据
            if (p.hash == hash &&
                ((k = p.key) == key || (key != null && key.equals(k))))
                //在后面会用到e值来更新
                e = p;
            else if (p instanceof TreeNode)
            	//如果当前节点已属于TreeNode,则在树中添加
                e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
            else {
            	//遍历链表
                for (int binCount = 0; ; ++binCount) {
                	//如果找完都没有重复，在尾部进行添加
                    if ((e = p.next) == null) {
                        p.next = newNode(hash, key, value, null);
                        //判断是否要转换为红黑树
                        if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
                            treeifyBin(tab, hash);
                        break;
                    }
                    //如果链表中有重复的key，根据后面更新e节点
                    if (e.hash == hash &&
                        ((k = e.key) == key || (key != null && key.equals(k))))
                        break;
                    p = e;
                }
            }
            //如果e不为null，存在重复key，用插入值替代旧值，返回旧值
            if (e != null) { // existing mapping for key
                V oldValue = e.value;
                if (!onlyIfAbsent || oldValue == null)
                    e.value = value;
                afterNodeAccess(e);
                return oldValue;
            }
        }
        //此处表明无重复key，修改次数+1
        ++modCount;
        //元素个数+1，并判断是否大于临界值，是否需要扩容
        if (++size > threshold)
            resize();
        afterNodeInsertion(evict);
        return null;
    }

2.4.2 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; int n, index;
        //校检table不为空且在table对应的数组下标不为null，p是数组下标的节点
        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;
            //如果数组下标的节点正好是当前要删除的节点，把p赋值给临时节点node
            if (p.hash == hash &&
                ((k = p.key) == key || (key != null && key.equals(k))))
                node = p;
            else if ((e = p.next) != null) {
            	//删除的节点在树上，查找红黑树
                if (p instanceof TreeNode)
                    node = ((TreeNode<K,V>)p).getTreeNode(hash, key);
                else {
                	//链表节点，遍历链表节点
                    do {
                        if (e.hash == hash &&
                            ((k = e.key) == key ||
                             (key != null && key.equals(k)))) {
                            node = e;
                            break;
                        }
                        p = e;
                    } while ((e = e.next) != null);
                }
            }
            //判断node是否为空，且值是否相等
            if (node != null && (!matchValue || (v = node.value) == value ||
                                 (value != null && value.equals(v)))) {
                if (node instanceof TreeNode)
                	//移除树的节点
                    ((TreeNode<K,V>)node).removeTreeNode(this, tab, movable);
                else if (node == p)
                	//直接覆盖索引位置
                    tab[index] = node.next;
                else
                	//通过链表移除node
                    p.next = node.next;
                ++modCount;
                --size;
                afterNodeRemoval(node);
                return node;
            }
        }
        return null;
    }

2.4.3 修改

修改也是put操作，将旧值覆盖，刚刚也已经分析了

2.4.4 查询

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

    final Node<K,V> getNode(int hash, Object key) {
        Node<K,V>[] tab; Node<K,V> first, e; int n; K k;
        //同之前一样
        if ((tab = table) != null && (n = tab.length) > 0 &&
            (first = tab[(n - 1) & hash]) != null) {
            //如果是头结点，则直接返回头结点
            if (first.hash == hash && // always check first node
                ((k = first.key) == key || (key != null && key.equals(k))))
                return first;
            //如果不是头结点
            if ((e = first.next) != null) {
            	//树结构则查找红黑树
                if (first instanceof TreeNode)
                    return ((TreeNode<K,V>)first).getTreeNode(hash, key);
                //链表结构，遍历链表查找
                do {
                    if (e.hash == hash &&
                        ((k = e.key) == key || (key != null && key.equals(k))))
                        return e;
                } while ((e = e.next) != null);
            }
        }
        //未找到，返回null
        return null;
    }

先分析基本方法，关于红黑树的操作比较复杂，不在这里展开。后面分析到红黑树了再说

三、总结

1. HashMap使用hashCode，可以定位到他应该放置哈希桶的位置，如果产生了hash冲突，在改为链表形式或红黑树形式继续存储元素
2. 结合了数组和链表的优势
3. 遍历时可以通过entry来取HashMap的键值对数据