Java HashMap 的使用

---

title: HashMap 的使用
date: 2018-12-04 11:09:02
categories:

• java

---

HashMap 的使用

在开发中经常使用到 HashMap，分析一下 HashMap 带参的构造方法

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

一个参数的构造方法，传入的参数是初始大小，最终调用两个参数的构造方法，传入初始大小和负载系数。默认的负载系数 DEFAULT_LOAD_FACTOR 是 0.75f.调用tableSizeFor(int)传入初始大小值算出threshold，具体的 tableSizeFor(int) 方法,threshold实际值会在第一次put(k,v)重新计算。

/**
  * Returns a power of two size for the given target capacity.
  */
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;
}

写一个测试 tableSizeFor 方法算出的结果

public static void main(String[] args) {
  for(int i = 0; i < 20; i++) {
    System.out.println(i+":"+tableSizeFor(i));
  }
}
static final int MAXIMUM_CAPACITY = 1 << 30;

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;
}

分析输出，这里输出的规律是，最小的2的幂

0:1
1:1
2:2
3:4
4:4
5:8
6:8
7:8
8:8
9:16
10:16
11:16
12:16
13:16
14:16
15:16
16:16
17:32
18:32
19:32

put(k,v)如果是第一次调用会直接调用resize()计算threshold分配table大小，方法在最后会判断size大小是否大于 threshold,如果插入元素大于threshold则调用resize(),然后重新计算 threshold，调整table的大小.阅读源码发现threshold计算方式是table大小乘负载系数 DEFAULT_LOAD_FACTOR.也就是说如果new HashMap(8)，在第一次put(k,v)时会计算出threshold为6(负载系数0.75)，在第6个参数put(k,v)时，就会重新扩容。扩容的算法使用左移<<算出结果等同*2。如果想防止二次扩容可以使用实际参数数量 / 负载系数(默认0.75) + 1.

/**
  * Implements Map.put and related methods
  *
  * @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)
        n = (tab = resize()).length;
    if ((p = tab[i = (n - 1) & hash]) == null)
        tab[i] = newNode(hash, key, value, null);
    else {
        Node<K,V> e; K k;
        if (p.hash == hash &&
            ((k = p.key) == key || (key != null && key.equals(k))))
            e = p;
        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;
            }
        }
        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;
}

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) {
            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
        newCap = oldThr;
    else {               // zero initial threshold signifies using defaults
        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) {
        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;
                    }
                }
            }
        }
    }
    return newTab;
}

总结

如果想防止二次扩容可以使用此算法: 实际参数数量 / 负载系数(默认0.75) + 1.