面试-HashMap原理与源码分析（JDK1.8）

Posted 2020-12-01 wangymd

1、HashMap介绍

HashMap为Map接口的一个实现类，实现了Map所有的操作。
HashMap除了允许key、value为null值和非线程安全外，其他实现几乎和HashTable一致。
HashMap使用散列存储的方式保存kay-value键值对，因此其不支持数据保存的顺序。如果想要使用有序容器可以使用LinkedHashMap。
在性能上当HashMap中保存的key的哈希算法能够均匀的分布在每个bucket中的时候，HashMap在基本的get和set操作的的时间复杂度都是O(n)。
在遍历HashMap的时候，其遍历节点的个数为bucket（位桶）的个数+HashMap中保存的节点个数。因此当遍历操作比较频繁的时候需要注意HashMap的初始化容量不应该太大。 这一点其实比较好理解：当保存的节点个数一致的时候，bucket越少，遍历次数越少。
另外HashMap在resize的时候会有很大的性能消耗，因此当需要在HashMap中保存大量数据的时候，传入适当的默认容量以避免resize，可以很大的提高性能。 具体的resize操作请参考下面对此方法的分析。

HashMap采用位桶+链表+红黑树（自平衡二叉查找树）实现，当链表长度超过阈值（8）时，将链表转换为红黑树，这样大大减少了查找时间.

2、默认设置

static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; //默认初始化容量
static final int MAXIMUM_CAPACITY = 1 << 30; //最大容量
static final float DEFAULT_LOAD_FACTOR = 0.75f; //默认加载因子
static final int TREEIFY_THRESHOLD = 8; //当put一个元素到某个位桶，如果其链表长度达到8时将链表转换为红黑树
static final int UNTREEIFY_THRESHOLD = 6; //
static final int MIN_TREEIFY_CAPACITY = 64; //

transient Node<K,V>[] table; //存储元素数组
transient Set<Map.Entry<K,V>> entrySet; //
transient int size; //元素个数
transient int modCount; //
int threshold; //扩容阈值
final float loadFactor; //加载因子 

3、构造方法 

    /**
     * Constructs an empty <tt>HashMap</tt> with the default initial capacity
     * (16) and the default load factor (0.75).
     */
    public HashMap() { //无参数构造方法；默认初始容量16；加载因子0.75f；
        this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted//loadFactor = 0.75f：加载因子。其他成员默认。
    }

    /**
     * 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) { //初始容量initialCapacity；默认加载因子0.75f
        this(initialCapacity, DEFAULT_LOAD_FACTOR);
    }

    /**
     * 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) { //初始容量initialCapacity；初始加载因子：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);
    }

    /**
     * Returns a power of two size for the given target capacity.
　　　* 计算初始化容量，
     */
    static final int tableSizeFor(int cap) {
        int n = cap - 1;
        n |= n >>> 1; //n右移1；按位或赋值给n
        n |= n >>> 2; //n右移2；按位或赋值给n
        n |= n >>> 4; //n右移4；按位或赋值给n
        n |= n >>> 8; //n右移8；按位或赋值给n
        n |= n >>> 16; //n右移16；按位或赋值给n
        return (n < 0) ? 1 : (n >= MAXIMUM_CAPACITY) ? MAXIMUM_CAPACITY : n + 1;
    }

4、数据存与取

存数据：

/**

     * 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) //判断添加第一个元素
            n = (tab = resize()).length; //添加一地个元素
        if ((p = tab[i = (n - 1) & hash]) == null) //判断table的在（n-1）&hash索引值是否空，如果空创建一个节点插入次位置
            tab[i] = newNode(hash, key, value, null); //创建新的节点
        else { //发生冲突时处理
            Node<K,V> e; K k;
            if (p.hash == hash &&
                ((k = p.key) == key || (key != null && key.equals(k)))) //判断第一个Node是否是要找的值
                e = p;
            else if (p instanceof TreeNode) //红黑树处理
                e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value); //
            else {
                for (int binCount = 0; ; ++binCount) { //累积hash冲突数量
                    if ((e = p.next) == null) {
                        p.next = newNode(hash, key, value, null); //
                        if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
                            treeifyBin(tab, hash); //treeifyBin首先判断HashMap长度，如果小于64进行resize扩容，如果大于64存储结构转换为红黑树
                        break;
                    }
                    if (e.hash == hash && ((k = e.key) == key || (key != null && key.equals(k)))) //如果key已经存在，停止遍历
                        break;
                    p = e;
                }
            }
            if (e != null) { // existing mapping for key //查到key已存在，更新对应value值
                V oldValue = e.value;
                if (!onlyIfAbsent || oldValue == null)
                    e.value = value; //节点赋值新值
                afterNodeAccess(e);
                return oldValue; //返回旧值
            }
        }
        ++modCount;
        if (++size > threshold) //判断当前元素容量是否大于阈值，如果是需要进行扩容
            resize(); //扩容
        afterNodeInsertion(evict);
        return null;
    }  

    /**
     * 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() { //扩容
        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) { //容量大于等于最大容量
                threshold = Integer.MAX_VALUE; //阈值等于int最大值
                return oldTab;
            }
            else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY && oldCap >= DEFAULT_INITIAL_CAPACITY)
                newThr = oldThr << 1; // double threshold //容量扩容一倍
        }
        else if (oldThr > 0) // initial capacity was placed in threshold //使用阈值初始化容量
            newCap = oldThr;
        else {               // zero initial threshold signifies using defaults
            newCap = DEFAULT_INITIAL_CAPACITY; //初始化默认容量：16
            newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY); //初始化默认阈值：加载因子（0.75f） * 初始化容量（16）
        }
        if (newThr == 0) { //如果阈值=0，初始化大小
            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]; //创建新的节点数组，数组长度为扩容后的长度
        table = newTab;
        if (oldTab != null) {
            for (int j = 0; j < oldCap; ++j) { //根据旧数组长度，进行遍历
                Node<K,V> e;
                if ((e = oldTab[j]) != null) {
                    oldTab[j] = null;
                    if (e.next == null)
                        newTab[e.hash & (newCap - 1)] = e; //将就数组元素赋值给新数组
                    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 { //遍历链表
                            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;
    } 

 

/**
* Basic hash bin node, used for most entries. (See below for
* TreeNode subclass, and in LinkedHashMap for its Entry subclass.)
*/
static class Node<K,V> implements Map.Entry<K,V> { //链表数据结构
　　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;
}

//判断两个Node节点是否相同

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;
}
} 

    /**
     * Entry for Tree bins. Extends LinkedHashMap.Entry (which in turn
     * extends Node) so can be used as extension of either regular or
     * linked node.
     */
    static final class TreeNode<K,V> extends LinkedHashMap.Entry<K,V> {
        TreeNode<K,V> parent; //父节点
        TreeNode<K,V> left; //左子树
        TreeNode<K,V> right; //右子树
        TreeNode<K,V> prev;    // needed to unlink next upon deletion
        boolean red; //颜色属性
        TreeNode(int hash, K key, V val, Node<K,V> next) {
            super(hash, key, val, next);
        }

        /**
         * Returns root of tree containing this node.
　　　　　 * 返回根节点
         */
        final TreeNode<K,V> root() {
            for (TreeNode<K,V> r = this, p;;) {
                if ((p = r.parent) == null)
                    return r;
                r = p;
            }
        }
。。。省略。。。
} 

取数据：

    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); //红黑树查询结果
                do { //遍历链表查询结果
                    if (e.hash == hash && ((k = e.key) == key || (key != null && key.equals(k))))
                        return e;
                } while ((e = e.next) != null);
            }
        }
        return null;
    }

 

5、demo程序，查看数据结构（散列数组+链表）

package com.javabasic.map;

import java.util.HashMap;
import java.util.Map;
import java.util.Map.Entry;
import java.util.Set;

/**
 * 源码分析
 * 
 * 
 * 允许使用null键和null值； 
 * 线程不同步，效率高；
 * 
 * 
 * @author wangymd
 *
 */
public class HashMapTest2 {

    public static void main(String[] args) {
        Stu stu1 = new Stu(1,"xiaojia");
        Stu stu2 = new Stu(1,"xiaoyi");
        Stu stu3 = new Stu(1,"xiaobing");
        Stu stu4 = new Stu(1,"xiaoding");
        
        Map<Stu, String> hm = new HashMap<Stu, String>();
        hm.put(stu1, "xiaojia");
        hm.put(stu2, "xiaoyi");
        hm.put(stu3, "xiaobing");
        hm.put(stu4, "xiaoding");
        
        Set<Entry<Stu, String>> entrySet = hm.entrySet(); //断点，查看数据结构；如下图
        for (Entry<Stu, String> entry : entrySet) {
            Stu key = entry.getKey();
            String value = entry.getValue();
            System.out.println(key.getName() + "----" + value);
        }
    }
    

}

class Stu{
    
    Integer id;
    String name;
    public Stu() {}
    
    public Stu(Integer id, String name) {
        this.id = id;
        this.name = name;
    }

    public Integer getId() {
        return id;
    }

    public void setId(Integer id) {
        this.id = id;
    }

    public String getName() {
        return name;
    }

    public void setName(String name) {
        this.name = name;
    }
}