【Java】Map总结和源码注释

前言

Map为一个Java中一个重要的数据结构，主要表示<key, value>的映射关系对。本文包括了相关Map数据结构的总结和源码的阅读注释。

HashMap

初始化，可以选择第二个初始化函数来设置装载能力threshold和装载系数loadFactor：

• HashMap()
• HashMap(int initialCapacity, float loadFactor)

HashMap中定义的一些常量：

• static final int DEFAULT_INITIAL_CAPACITY = 1 << 4;

  缺省的初始大小

• static final int MAXIMUM_CAPACITY = 1 << 30;

  最大限定大小，当超过这个值时，会resize()到Integer.MAX_VALUE

• static final float DEFAULT_LOAD_FACTOR = 0.75f;

  threshold = capacity*laodFactor

HashMap的大小始终为2的倍数，若插入时超过threshold时，会调用resize()来自动将大小扩大一倍。

值在Node<K,V>[] table中的定位方式为(n-1)&hash(key)，这也是resize的时候直接double的原因

基本方法：

• V put(K key, V value)：若key不存在，则插入；若key存在，则更新value值，返回旧的value
• V putIfAbsent(K key, V value)
• V get(Object key)：get不存在的key时会返回null，需要注意NullPointerException
• int size()

遍历方式

• forEach(lambda)通过lambda表达式进行遍历

• entrySet().iterator()

  Iterator iter = map.entrySet().iterator();
  while(iter.hasNext()){
  	Map.Entry e = (Map.Entry)iter.next();
      key = e.getKey();
      value = e.getValue();
  }
  

• keySet().iterator()

  Iterator iter = map.keySet().iterator();
  while(iter.hasNext()){
      key = iter.next();
      value = map.get(key);
  }
  

• values().iterator()

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;
    if (oldCap > 0) {
        if (oldCap >= MAXIMUM_CAPACITY) { // 旧的大小已经达到设置的最大值时不再增加，改变阈值
            threshold = Integer.MAX_VALUE;
            return oldTab;
        }
        else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY && // 新大小=旧大小*2
                 oldCap >= DEFAULT_INITIAL_CAPACITY)
            newThr = oldThr << 1; // 阈值也一起*2
    }
    else if (oldThr > 0) // initial capacity was placed in threshold
        newCap = oldThr;
    else {               // oldCap为0时处于初始化阶段，进行初始化
        newCap = DEFAULT_INITIAL_CAPACITY;
        newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);
    }
    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) { // 将旧map移到新map中
        for (int j = 0; j < oldCap; ++j) {
            Node<K,V> e;
            if ((e = oldTab[j]) != null) {
                oldTab[j] = null; // 置为null值方便GC
                if (e.next == null) // 桶中没有链，直接赋值
                    newTab[e.hash & (newCap - 1)] = e;
                else if (e instanceof TreeNode) // 如果桶中为红黑树
                    ((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) { // 若为真，则在原来位置不变
                            if (loTail == null)
                                loHead = e;
                            else
                                loTail.next = e;
                            loTail = e;
                        }
                        else {	// 为假时说明扩容后原链表中的节点位置发生了改变
                            if (hiTail == null)
                                hiHead = e;
                            else
                                hiTail.next = e;
                            hiTail = e;
                        }
                    } while ((e = next) != null);
                    if (loTail != null) {
                        loTail.next = null;
                        newTab[j] = loHead; // 原链表所在
                    }
                    if (hiTail != null) {
                        hiTail.next = null;
                        newTab[j + oldCap] = hiHead; // 扩容部分节点位置加上了oldCap
                    }
                }
            }
        }
    }
    return newTab;
}

冲突解决

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; // 数组为空的情况
    if ((p = tab[i = (n - 1) & hash]) == null)
        tab[i] = newNode(hash, key, value, null); // 没有冲突直接放入
    else {
        Node<K,V> e; K k;
        if (p.hash == hash &&
            ((k = p.key) == key || (key != null && key.equals(k))))
            e = p;	// 有冲突但是key相同，则覆盖原来的值
        else if (p instanceof TreeNode)
            e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value); // 如果已经拉成红黑树则插入树中
        else {
            for (int binCount = 0; ; ++binCount) {
                if ((e = p.next) == null) {
                    p.next = newNode(hash, key, value, null); // 找到链表尾插入链表中
                    if (binCount >= TREEIFY_THRESHOLD - 1) // 如果桶的链长度超过阈值则拉成红黑树
                        treeifyBin(tab, hash);
                    break;
                }
                if (e.hash == hash &&
                    ((k = e.key) == key || (key != null && key.equals(k))))
                    break; // 在链中找到相同的key则覆盖其值
                p = e;
            }
        }
        if (e != null) { // existing mapping for key
            V oldValue = e.value;
            if (!onlyIfAbsent || oldValue == null)
                e.value = value;
            afterNodeAccess(e);
            return oldValue;
        }
    }
    ++modCount;
    if (++size > threshold)
        resize();
    afterNodeInsertion(evict);
    return null;
}

Hashtable

初始化函数：

public Hashtable() {
    this(11, 0.75f);
}

默认下initialCapacity = 11，loadFactor = 0.75。

插入操作put(K,V)

public synchronized V put(K key, V value) {
    // Make sure the value is not null
    if (value == null) {
        throw new NullPointerException();
    }

    // Makes sure the key is not already in the hashtable.
    Entry<?,?> tab[] = table;
    int hash = key.hashCode();
    int index = (hash & 0x7FFFFFFF) % tab.length;
    @SuppressWarnings("unchecked")
    Entry<K,V> entry = (Entry<K,V>)tab[index];
    for(; entry != null ; entry = entry.next) {
        if ((entry.hash == hash) && entry.key.equals(key)) { // 找到相同的key则覆盖原值
            V old = entry.value;
            entry.value = value;
            return old;
        }
    }

    addEntry(hash, key, value, index);
    return null;
}

Hashtable的hash寻址方法为(hash & 0x7FFFFFFF) % tab.length，当插入的key之前有值时返回旧值，否则返回null。

addEntry(hash, key, value, index)，当table的大小不够时，执行rehash()扩大table

private void addEntry(int hash, K key, V value, int index) {
    Entry<?,?> tab[] = table;
    if (count >= threshold) {
        // Rehash the table if the threshold is exceeded
        rehash();

        tab = table;
        hash = key.hashCode();
        index = (hash & 0x7FFFFFFF) % tab.length;
    }

    // Creates the new entry.
    @SuppressWarnings("unchecked")
    Entry<K,V> e = (Entry<K,V>) tab[index];
    tab[index] = new Entry<>(hash, key, value, e);
    count++;
    modCount++;
}

rehash():

protected void rehash() {
    int oldCapacity = table.length;
    Entry<?,?>[] oldMap = table;

    // overflow-conscious code
    int newCapacity = (oldCapacity << 1) + 1; // 新大小=原大小*2+1
    if (newCapacity - MAX_ARRAY_SIZE > 0) {
        if (oldCapacity == MAX_ARRAY_SIZE)
            // Keep running with MAX_ARRAY_SIZE buckets
            return;
        newCapacity = MAX_ARRAY_SIZE;
    }
    Entry<?,?>[] newMap = new Entry<?,?>[newCapacity];

    modCount++;
    threshold = (int)Math.min(newCapacity * loadFactor, MAX_ARRAY_SIZE + 1); // 更新阈值
    table = newMap;

    for (int i = oldCapacity ; i-- > 0 ;) { // 将旧map中的值一道新map
        for (Entry<K,V> old = (Entry<K,V>)oldMap[i] ; old != null ; ) {
            Entry<K,V> e = old;
            old = old.next;

            int index = (e.hash & 0x7FFFFFFF) % newCapacity;
            e.next = (Entry<K,V>)newMap[index];
            newMap[index] = e;
        }
    }
}

与HashMap的区别

• HashMap 继承自AbstractMap类，Hashtable继承自Dictionary类

• Hashtable中的方法均用sychronized关键字修饰，为线程安全

• 扩容方法不同，HashMap直接double，使得大小始终是2的倍数，Hashtable在double后加1

• 在table中的查找方式不同：HashMap为hash&(n-1)，Hashtable为(hash & 0x7FFFFFFF) % tab.length

TreeMap

TreeMap的本质是红黑树，红黑树是一种特殊的二叉查找树，所以TreeMap中的节点都是有序的。

TreeMap中节点Entry的定义为

static final class Entry<K,V> implements Map.Entry<K,V> {
    K key;
    V value;
    Entry<K,V> left;
    Entry<K,V> right;
    Entry<K,V> parent;
    boolean color = BLACK;
}

初始化函数：

public TreeMap() {
    comparator = null;
}
public TreeMap(Comparator<? super K> comparator) {
    this.comparator = comparator;
}

TreeMap支持自定义的比较器，若是使用空初始化函数，则默认为key的自然顺序

 /**
     * The comparator used to maintain order in this tree map, or
     * null if it uses the natural ordering of its keys.
     *
     * @serial
     */
private final Comparator<? super K> comparator;

插入操作put(K,V)

public V put(K key, V value) {
    Entry<K,V> t = root;
    if (t == null) { // root为空则直接new
        compare(key, key); // type (and possibly null) check

        root = new Entry<>(key, value, null);
        size = 1;
        modCount++;
        return null;
    }
    int cmp;
    Entry<K,V> parent;
    // split comparator and comparable paths
    Comparator<? super K> cpr = comparator;
    if (cpr != null) { // 自定义comparator时
        do {
            parent = t;
            cmp = cpr.compare(key, t.key);
            if (cmp < 0)
                t = t.left;
            else if (cmp > 0)
                t = t.right;
            else
                return t.setValue(value);	// 如果key相等则直接覆盖value
        } while (t != null);
    }
    else {	// 使用key的comparable接口
        if (key == null)
            throw new NullPointerException();
        @SuppressWarnings("unchecked")
        Comparable<? super K> k = (Comparable<? super K>) key;
        do {
            parent = t;
            cmp = k.compareTo(t.key);
            if (cmp < 0)
                t = t.left;
            else if (cmp > 0)
                t = t.right;
            else
                return t.setValue(value); //找到相同的key则直接覆盖value返回
        } while (t != null);
    }
    Entry<K,V> e = new Entry<>(key, value, parent); // 插入节点
    if (cmp < 0)
        parent.left = e;
    else
        parent.right = e;
    fixAfterInsertion(e); // 红黑树自平衡过程
    size++;
    modCount++;
    return null;
}

插入后红黑树的自平衡过程:

private void fixAfterInsertion(Entry<K,V> x) {
    x.color = RED; // 设插入节点的颜色为红

    while (x != null && x != root && x.parent.color == RED) { // 当x.parent为黑时树已经平衡
        if (parentOf(x) == leftOf(parentOf(parentOf(x)))) { // x.parent是祖父节点的左子节点
            Entry<K,V> y = rightOf(parentOf(parentOf(x))); // x的uncle节点
            if (colorOf(y) == RED) { // uncle为红的时候recolor
                setColor(parentOf(x), BLACK);
                setColor(y, BLACK);
                setColor(parentOf(parentOf(x)), RED);
                x = parentOf(parentOf(x)); // 向上变色直到满足平衡条件
            } else { // uncle为黑的时候则需要rotate
                if (x == rightOf(parentOf(x))) { // 左右的情况，向左旋转
                    x = parentOf(x);
                    rotateLeft(x);
                }
                setColor(parentOf(x), BLACK);
                setColor(parentOf(parentOf(x)), RED);
                rotateRight(parentOf(parentOf(x)));
            }
        } else {
            Entry<K,V> y = leftOf(parentOf(parentOf(x)));
            if (colorOf(y) == RED) {
                setColor(parentOf(x), BLACK);
                setColor(y, BLACK);
                setColor(parentOf(parentOf(x)), RED);
                x = parentOf(parentOf(x));
            } else {
                if (x == leftOf(parentOf(x))) { // 右左的情况，向右旋转
                    x = parentOf(x);
                    rotateRight(x);
                }
                setColor(parentOf(x), BLACK);
                setColor(parentOf(parentOf(x)), RED);
                rotateLeft(parentOf(parentOf(x)));
            }
        }
    }
    root.color = BLACK;
}