HashMap

1.介绍

//Hash table based implementation of the {@code Map} interface.  This
//implementation provides all of the optional map operations, and permits
//{@code null} values and the {@code null} key. 
public class HashMap<K,V> extends AbstractMap<K,V>
    implements Map<K,V>, Cloneable, Serializable {
    /*  实现*/
}

HashMap继承于抽象Map类，抽象Map类为Map接口实现了一些操作

//This implementation provides constant-time performance for the basic
//operations ({@code get} and {@code put}), 

HasmMap实现了常量级的get和put操作实现。

//An instance of {@code HashMap} has two parameters that affect its
//performance: <i>initial capacity</i> and <i>load factor</i>.

HashMap是不同步的，可以在外面套一个 Collections.synchronizedMap来实现：

Map m = Collections.synchronizedMap(new HashMap(...));

HashMap通常使用数组+链表的实现方式，当bins变得很大时，链表会变成红黑树，每一个bin都相当于TreeMap

/*
* This map usually acts as a binned (bucketed) hash table, but
* when bins get too large, they are transformed into bins of
* TreeNodes, each structured similarly to those in
* java.util.TreeMap. Most methods try to use normal bins, but
* relay to TreeNode methods when applicable (simply by checking
* instanceof a node).  Bins of TreeNodes may be traversed and
* used like any others, but additionally support faster lookup
* when overpopulated. However, since the vast majority of bins in
* normal use are not overpopulated, checking for existence of
* tree bins may be delayed in the course of table methods.
    */

2.一些参数fields

DEFAULT_INITIAL_CAPACITY初始化容量，默认16，且必须是2的幂。（为何要2的幂，因为哈希函数为hash(key)& capacity-1 这样就可以很快的确定位置（如果使用hash%数组大小的话也可以，但是会很慢）。https://www.iteye.com/topic/539465）

MAXIMUM_CAPACITY 最大容量小于2^30。

DEFAULT_LOAD_FACTOR默认加载因子 0.75.

TREEIFY_THRESHOLD 当bins中的节点大于其是会转化为红黑树

UNTREEIFY_THRESHOLD 小于其时会变成链表

MIN_TREEIFY_CAPACITY 最小表容量应大于4*TREEIFY_THRESHOLD

/**
 * The default initial capacity - MUST be a power of two.
 */
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.
 */
static final int MAXIMUM_CAPACITY = 1 << 30;

/**
 * The load factor used when none specified in constructor.
 */
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.
 */
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.
 */
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;

3.Node类 普通Node和TreNode

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;
    }
}

static final class TreeNode<K,V> extends LinkedHashMap.Entry<K,V> {
    TreeNode<K,V> parent;  // red-black tree links
    TreeNode<K,V> left;
    TreeNode<K,V> right;
    TreeNode<K,V> prev;    // needed to unlink next upon deletion
    boolean red;
    TreeNode(int hash, K key, V val, Node<K,V> next) {
            super(hash, key, val, next);
        }
	...
}

4.类的静态方法

static final int hash(Object key) {//获得类的哈希值 右移16位
    int h;
    //https://blog.csdn.net/qq_42034205/article/details/90384772
    return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}

/**
 * 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; ParameterizedType p;
        if ((c = x.getClass()) == String.class) // bypass checks
            return c;
        if ((ts = c.getGenericInterfaces()) != null) {
            for (Type t : ts) {
                if ((t 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;
}

/**
 * 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));
}

/**
 * Returns a power of two size for the given target capacity.
 检查所传的参数是否为2的幂次方，且不能为负数（负数变为1），且不能超过常量MAXIMUM_CAPACITY（超过变为MAXIMUM_CAPACITY），如果不为2的幂次方，将其变为，比cap大的最小的2的幂次方的值
 */
static final int tableSizeFor(int cap) {
    int n = -1 >>> Integer.numberOfLeadingZeros(cap - 1);
    return (n < 0) ? 1 : (n >= MAXIMUM_CAPACITY) ? MAXIMUM_CAPACITY : n + 1;
}

5.fields

Node表

transienthttps://www.cnblogs.com/lanxuezaipiao/p/3369962.html

entrySet键值对集合

当前数量size

结构性修改的次数modcount

/**
 * The table, initialized on first use, and resized as
 * necessary. When allocated, length is always a power of two.
 * (We also tolerate length zero in some operations to allow
 * bootstrapping mechanics that are currently not needed.)
 */
transient Node<K,V>[] table;

/**
 * Holds cached entrySet(). Note that AbstractMap fields are used
 * for keySet() and values().
 */
transient Set<Map.Entry<K,V>> entrySet;

/**
 * The number of key-value mappings contained in this map.
 */
transient int size;

/**
 * The number of times this HashMap has been structurally modified
 * Structural modifications are those that change the number of mappings in
 * the HashMap or otherwise modify its internal structure (e.g.,
 * rehash).  This field is used to make iterators on Collection-views of
 * the HashMap fail-fast.  (See ConcurrentModificationException).
 */
transient int modCount;

threshold 当size>threhold时变成红黑树。

加载因子，默认0.75

/**
 * The next size value at which to resize (capacity * load factor).
 *
 * @serial
 */
// (The javadoc description is true upon serialization.
// Additionally, if the table array has not been allocated, this
// field holds the initial array capacity, or zero signifying
// DEFAULT_INITIAL_CAPACITY.)
int threshold;

/**
 * The load factor for the hash table.
 *
 * @serial
 */
final float loadFactor;

6.构造函数

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

/**
 * Constructs a new {@code HashMap} with the same mappings as the
 * specified {@code Map}.  The {@code HashMap} is created with
 * default load factor (0.75) and an initial capacity sufficient to
 * hold the mappings in the specified {@code Map}.
 *
 * @param   m the map whose mappings are to be placed in this map
 * @throws  NullPointerException if the specified map is null
 */
public HashMap(Map<? extends K, ? extends V> m) {
    this.loadFactor = DEFAULT_LOAD_FACTOR;
    putMapEntries(m, false);
}

/**
 * Implements Map.putAll and Map constructor.
 *
 * @param m the map
 * @param evict false when initially constructing this map, else
 * true (relayed to method afterNodeInsertion).
 */
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);
        }
    }
}

7.get方法

/**
get()方法调用getNode方法，传入hash值和key值
 */
public V get(Object key) {
    Node<K,V> e;
    return (e = getNode(hash(key), key)) == null ? null : e.value;
}

/**
 * @param hash hash for key
 * @param key the key
 * @return the node, or null if none
 如果 table不为空 table[(n - 1) & hash]不为空，说明该点有值
 	判断第一个是不是，然后往下判断
 		如果是TreeNode类型，直接getTreeNode();
 		否则链表往下判断；
 */
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;
}

8.put方法

/**
	调用putVal方法，设置值或更新值
 * @param key key with which the specified value is to be associated
 * @param value value to be associated with the specified key
 * @return the previous value associated with {@code key}, or
 *         {@code null} if there was no mapping for {@code key}.
 *         (A {@code null} return can also indicate that the map
 *         previously associated {@code null} with {@code key}.)
 */
public V put(K key, V value) {
    return putVal(hash(key), key, value, false, true);
}

/**
 * @param hash hash for key
 * @param key the key
 * @param value the value to put
 * @param onlyIfAbsent if true, don't change existing value
 * @param evict if false, the table is in creation mode.
 * @return previous value, or null if none
 	
 
 */
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)//如果table为空，resize一下
        n = (tab = resize()).length;
    if ((p = tab[i = (n - 1) & hash]) == null)	//如果当前table中(n - 1) & hash位置为空，则直接插入
        tab[i] = newNode(hash, key, value, null);
    else {	//如果不为空，找到key的那个entry
        Node<K,V> e; K k;
        if (p.hash == hash &&
            ((k = p.key) == key || (key != null && key.equals(k))))//先判断第一个
            e = p;
        //然后往下判断
        else if (p instanceof TreeNode) //如果是Tree实现的，调用树的putTreeVal()方法
            e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
        else {//说明是链表实现的 循环判断
            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) { //查找后存在该点，更新值返回oldValue existing mapping for key
            V oldValue = e.value;
            if (!onlyIfAbsent || oldValue == null)
                e.value = value;
            afterNodeAccess(e);
            return oldValue;
        }
    }
    //走到这里说明原来table中没有带key的entry ，插入了一个新的，判断是否需要resize()
    ++modCount;
    if (++size > threshold)
        resize();
    afterNodeInsertion(evict);
    return null;
}

9.resize方法

分为三步：获取原表、创建新表、为新表添加元素。

/**
 * Initializes or doubles table size.  If null, allocates in
 * accord with initial capacity target held in field threshold.
 * Otherwise, because we are using power-of-two expansion, the
 * elements from each bin must either stay at same index, or move
 * with a power of two offset in the new table.
 *
 * @return the table
 */
final Node<K,V>[] resize() {
    
    
    //第一部分
    Node<K,V>[] oldTab = table;  //复制旧表
    int oldCap = (oldTab == null) ? 0 : oldTab.length; //获得旧容量
    int oldThr = threshold;						//旧阈值
    int newCap, newThr = 0;						//新容量和新阈值
    
    
    
    
    //第二部分
    if (oldCap > 0) {	
        //分支1
        //说明原来表中有东西zMAX_VALUE
        //可能是添加的时候或者其他时调用了resize方法，然后将xin容量设置为原来的两倍且小于MAXIMUM_CAPACITY
        //对于阈值：如果本来的oldcap已经是MAXIMUM_CAPACITY，那么将阈值调为整数最大值，其实就是MAXIMUM_CAPACITY，这样不会再扩大容量，如果newcap还是小于MAXIMUM_CAPACITY，则也将新阈值*2
        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
        //分支2
        //说明原来表里没有元素，但是还调用了resize，说明调用了带初始容量的构造方法
        //只需要将新容量设置为旧的阈值，然后一会判断一下新阈值是否是0；如果是0，则将新阈值设置为容量*加载因子
        newCap = oldThr;
    else {               // zero initial threshold signifies using defaults
        //分支3
        //到这里就是一开始是调用了无参构造方法，只需将容量阈值设置成默认的即可。
        newCap = DEFAULT_INITIAL_CAPACITY;
        newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);
    }
    //下面的对分支2没有设置新阈值的情况在判断一下，设置一下新阈值
    if (newThr == 0) {
        float ft = (float)newCap * loadFactor;
        newThr = (newCap < MAXIMUM_CAPACITY && ft < (float)MAXIMUM_CAPACITY ?
                  (int)ft : Integer.MAX_VALUE);
    }
    threshold = newThr;
    
    
    //第三部分
    @SuppressWarnings({"rawtypes","unchecked"})
    Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap];//创建新Node数组
    table = newTab;		
    
    if (oldTab != null) {
    	//如果旧数组为空，则不需要复制；不为空就需要执行下面的赋值
        for (int j = 0; j < oldCap; ++j) {//循环遍历数组
           	//判断下当前位置是否有值，没有则跳过，有就将旧的复制到新的里面
            Node<K,V> e;
            if ((e = oldTab[j]) != null) {
                oldTab[j] = null;
                 //HashMap使用数组+链表或者数组+红黑树，需要分三种情况讨论
                if (e.next == null)
                    //说明当前桶内只有一个节点，直接复制
                    newTab[e.hash & (newCap - 1)] = e;
                else if (e instanceof TreeNode)
                    //说明是TreeNode的情况
                    ((TreeNode<K,V>)e).split(this, newTab, j, oldCap);
                else { // preserve order
                    //链表的情况，而且由于新表是原表的两倍大。对于新表的哈希地址其实有两种情况，低位和高位，分别对应c1，c2
                    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) {
                            //c1  如果等于0 说明e.hash的第i位是0,因为oldcap的第i位是1，当我们把newcap=oldcap<<1时，e.hash&newCap-1不会发生变化
                            //说明是要放在低位
                            if (loTail == null)
                                loHead = e;
                            else
                                loTail.next = e;
                            loTail = e;
                        }
                        else {
                            //c2
                            //说明要放在高位
                            if (hiTail == null)
                                hiHead = e;
                            else
                                hiTail.next = e;
                            hiTail = e;
                        }
                    } while ((e = next) != null);
                    if (loTail != null) {
                        //将低位链表放在低位
                        loTail.next = null;
                        newTab[j] = loHead;
                    }
                    if (hiTail != null) {
                        //将低位链表放在高位
                        hiTail.next = null;
                        newTab[j + oldCap] = hiHead;
                    }
                }
            }
        }
    }
    return newTab;
}

下面是TreeNode类的静态方法split，将某个树枝拆分为高位树枝和低位树枝

/**
 * Splits nodes in a tree bin into lower and upper tree bins,
 * or untreeifies if now too small. Called only from resize;
 * see above discussion about split bits and indices.
 *
 * @param map the map
 * @param tab the table for recording bin heads
 * @param index the index of the table being split
 * @param bit the bit of hash to split on
 */
final void split(HashMap<K,V> map, Node<K,V>[] tab, int index, int bit) {
    TreeNode<K,V> b = this;
    // Relink into lo and hi lists, preserving order
    TreeNode<K,V> loHead = null, loTail = null;
    TreeNode<K,V> hiHead = null, hiTail = null;
    int lc = 0, hc = 0;
    for (TreeNode<K,V> e = b, next; e != null; e = next) {
        next = (TreeNode<K,V>)e.next;
        e.next = null;
        if ((e.hash & bit) == 0) {
            if ((e.prev = loTail) == null)
                loHead = e;
            else
                loTail.next = e;
            loTail = e;
            ++lc;
        }
        else {
            if ((e.prev = hiTail) == null)
                hiHead = e;
            else
                hiTail.next = e;
            hiTail = e;
            ++hc;
        }
    }

    if (loHead != null) {
        if (lc <= UNTREEIFY_THRESHOLD)
            tab[index] = loHead.untreeify(map);
        else {
            tab[index] = loHead;
            if (hiHead != null) // (else is already treeified)
                loHead.treeify(tab);
        }
    }
    if (hiHead != null) {
        if (hc <= UNTREEIFY_THRESHOLD)
            tab[index + bit] = hiHead.untreeify(map);
        else {
            tab[index + bit] = hiHead;
            if (loHead != null)
                hiHead.treeify(tab);
        }
    }
}

2021/3/2未完