HashMap java8源码详解

一 数据结构

数组+链表/红黑树，红黑树是java8的改进。

二 使用场景

HashMap是非线程安全的，所有多个线程同时写入会有问题，适用于单线程写，多线程读的场景。
ConcurrentHashMap可以解决线程安全的问题。

三 常量 变量含义

// 默认初始容量 16，2的4次方
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16

// 最大容量，2的30次方
static final int MAXIMUM_CAPACITY = 1 << 30;

// 装载因子
static final float DEFAULT_LOAD_FACTOR = 0.75f;
final float loadFactor;

// 取值是：(int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);
// 当 ++size>threshold 时，会进行扩容
int threshold;

// 当链表长度大于8，链表会变成红黑树
static final int TREEIFY_THRESHOLD = 8;

四 代码分析

1 数据存储结构

是一个Node的数组

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

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;
        }
    }

如何处理冲突？

HashMap使用链接法，当链表长度大于8会升级为红黑树。

final V putVal(int hash, K key, V value, boolean onlyIfAbsent, boolean evict) {
        Node<K,V>[] tab; Node<K,V> p; int n, i;
        //这里是第一次初始化
        if ((tab = table) == null || (n = tab.length) == 0)
            n = (tab = resize()).length;
        // i = (n - 1) & hash获取数组下标，并且所在下标没有数据    
        if ((p = tab[i = (n - 1) & hash]) == null)
            tab[i] = newNode(hash, key, value, null);
        else {
            Node<K,V> e; K k;
            // 判断第一个节点 是不是要替换节点
            if (p.hash == hash &&
                ((k = p.key) == key || (key != null && key.equals(k))))
                e = p;
            // 红黑树插入    
            else if (p instanceof TreeNode)
                e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
            else {
                // 这里遍历链表，超过TREEIFY_THRESHOLD，变换成红黑树，找出要插入（这里是链表结尾）还是更新
                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;
                }
            }
            //这里是替换老值
            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;
    }

怎么扩容？高效实现数据迁移？

这里扩容的过程是rehash，自然而然要涉及到数据迁移。比较简单的方案是，数组扩大一倍，然后计算每一个元素新的位置进行调整，但是这样效率很低。

    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) {
            //这里容量已经到了最大，不能再扩容了
            if (oldCap >= MAXIMUM_CAPACITY) {
                threshold = Integer.MAX_VALUE;
                return oldTab;
            }
            //  这里翻倍了，新的newCap = oldCap << 1，这里很关键
            else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY &&
                     oldCap >= DEFAULT_INITIAL_CAPACITY)
                // 这里翻倍了     
                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
                        // 这里是链表数据高效迁移，是一整套设计。
                        // 首先newCap = oldCap << 1，新的容量总是老的两倍，并且总是2的倍数
                        // 老的节点去计算索引时，总是在 原地 或者 newTab[j + oldCap]
                        // 这个设计真的很巧妙
                        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;
    }

在HashTable中，initialCapacity的默认值是11，取了素数。而HashMap没有取素数，而是取了合数，并进行了一整套的设计，更高效。

五 hash表知识

hash 冲突

链接法chaining

最坏的情况 是所有节点都到了 一个链表里面，时间复杂度O(n)

开发寻址法open addressing

1. 线性探查
2. 二次探查
3. 双重散列

完全散列 perfect hashing

散列函数

除法散列法

h(k) = k mod m

乘法散列法

h(k) = m(kA mod 1) 0<A<1,取kA mod 1的小数部分

全域散列法

public class MyHashMap1 {

  private Node[] items;

  private int capacity;

  public MyHashMap1(int capacity) {
    items = new Node[capacity];
    for (int i = 0; i < capacity; i++) {
      items[i] = null;
    }
    this.capacity = capacity;
  }

  public Node get(Object key) {
    int i = 1;

    while (true) {
      int j = doubleHashing(key.hashCode(), capacity, i);
      if (items[j] != null) {
        return items[j];
      }

      if (i + 1 > capacity) {
        return null;
      }
      i++;
    }

  }

  public Object put(Object key, Object value) {
    int i = 1;

    while (true) {
      int j = doubleHashing(key.hashCode(), capacity, i);

      if (items[j] == null) {
        items[j] = new Node(key, value);
        return items[j];
      }

      if (i + 1 > capacity) {
        return -1;
      }
      i++;
    }

  }

  public Object remove(Object key) {
    return null;
  }

  /**
   * 除法散列法
   */
  public int h1(int k, int m) {
    return k % m;
  }

  /**
   * 乘法散列法
   * 0 < A < 1
   */
  public int h2(int k, int m, float A) {
    return (int) (Math.random() * m);
  }

  /**
   * 全域散列法
   * p是素数
   */
  public int h3(int k, int p, int m) {
    int a = 11, b = 13;
    return ((a * k + b) % p) % m;
  }

  /**
   * 线性探测
   */
  public int linerProbing(int k, int m, int i) {
    return (h1(k, m) + i) % m;
  }

  /**
   * 二次探测
   */
  public int quadraticProbing(int k, int m, int i) {
    int c1 = 17, c2 = 67;
    return (h1(k, m) + c1 * i + c2 * i * i) % m;
  }

  /**
   * 双重散列
   */
  public int doubleHashing(int k, int m, int i) {
    return (h3(k, 17, m) + i * h1(k, m)) % m;
  }

  class Node {

    private Object key;

    private Object value;

    public Node(Object key, Object value) {
      this.key = key;
      this.value = value;
    }

    public Object getKey() {
      return key;
    }

    public Object getValue() {
      return value;
    }
  }

  public static void main(String[] args) {
    MyHashMap1 myHashMap1 = new MyHashMap1(3);
    // hash函数好像有问题，还需调试
//    myHashMap1.put(1, 1);
    myHashMap1.put(2, 2);
    myHashMap1.put(3, 3);

    System.out.println(myHashMap1.get(1).getKey() + " : " + myHashMap1.get(1).getValue());
  }
}