HashMap 哈希表初解

HashMap 哈希表初解"/>

HashMap 哈希表初解

🎯 在一个崇高的目标支持下，不停地工作，即使慢，也一定会获得成功。 —— 爱因斯坦

一、什么是HashMap

也叫散列表，是一种非常重要的数据结构（数组+链表+红黑树），它将键映射到值，是一种快速查询数据的方法，应用场景及其丰富，许多缓存技术（比如memcached）的核心其实就是在内存中维护一张大的哈希表。

二、存储结构

从结构实现来讲，HashMap是数组+链表+红黑树（JDK1.8增加了红黑树部分）实现的，如下如所示

transient Node<K,V>[] table     // 哈希桶数组(很明显是一个Node数组)length=16
int threshold;                  // 所能容纳的key-value对极限 length*loadFactor
final float loadFactor;        // 负载因子                     0.75
int modCount;                   // 记录修改次数                  0
int size;     

哈希桶数组length大小必须为2的n次方(一定是合数)，这是一种非常规的设计，常规的设计是把桶的大小设计为素数。相对来说素数导致冲突的概率要小于合数。

主要是为了在取模和扩容时做优化，同时为了减少冲突，HashMap定位哈希桶索引位置时，也加入了高位参与运算的过程。

Node结构

static class Node<K,V> implements Map.Entry<K,V> {final int hash;            // 哈希值final K key;              V value;                    Node<K,V> next;            //链表的下一个nodeNode(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; }// 哈希值计算方法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 o 与 this 是否相等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;}
}

三、功能实现

hash()获取node的哈希值

static final int hash(Object key) {int h;// h = key.hashCode() 为第一步 取hashCode值// h ^ (h >>> 16)  为第二步 高位参与运算return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}

indexFor() 取模

static int indexFor(int h, int length) {  //jdk1.7的源码，jdk1.8没有这个方法，但是实现原理一样的return h & (length-1);  //第三步 取模运算
}

哈希值计算流程

put() 方法

final V putVal(int hash, K key, V value, boolean onlyIfAbsent,boolean evict) {Node<K,V>[] tab; Node<K,V> p; int n, i;//tab为空则创建if ((tab = table) == null || (n = tab.length) == 0)n = (tab = resize()).length;// 取模运算//计算index，并对null做处理 取模   线程安全问题（hash冲突检测）if ((p = tab[i = (n - 1) & hash]) == null)tab[i] = newNode(hash, key, value, null);else {Node<K,V> e; K k;// 节点key存在，直接覆盖valueif (p.hash == hash &&((k = p.key) == key || (key != null && key.equals(k))))e = p;// 判断该链为红黑树else if (p instanceof TreeNode)e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);// 该链为链表else {for (int binCount = 0; ; ++binCount) {if ((e = p.next) == null) {p.next = newNode(hash, key, value, null);// 链表长度大于8转换为红黑树进行处理if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1sttreeifyBin(tab, hash);break;}// key已经存在直接覆盖valueif (e.hash == hash &&((k = e.key) == key || (key != null && key.equals(k))))break;p = e;}}if (e != null) { // existing mapping for keyV oldValue = e.value;if (!onlyIfAbsent || oldValue == null)e.value = value;afterNodeAccess(e);return oldValue;}}++modCount;// 超过最大容量 就扩容。 ++size 线程安全问题if (++size > threshold)resize();afterNodeInsertion(evict);return null;
}

get() 方法

public V get(Object key) {Node<K,V> e;return (e = getNode(hash(key), key)) == null ? null : e.value;
}

getNode() 方法

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 && ((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;
}

resize()扩容

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) {   扩容前的数组大小如果已经达到最大(2^30)threshold = Integer.MAX_VALUE;  修改阈值为int的最大值(2^31-1)，这样以后就不会扩容了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 thresholdnewCap = oldThr;else {               // zero initial threshold signifies using defaultsnewCap = 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;//  *****数据转移处理*****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 orderNode<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;elseloTail.next = e;loTail = e;}else {if (hiTail == null)hiHead = e;elsehiTail.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;
}

四、线程安全性

JDK1.8 在多线程使用场景中，应该尽量避免使用线程不安全的HashMap，而使用线程安全的ConcurrentHashMap，优化了 1.7 中数组扩容的方案，解决了 Entry 链死循环和数据丢失问题，但是put 方法存在数据覆盖的问题，在链表转换树或者对树进行操作的时候会出现线程安全的问题。

对树进行操作

final TreeNode<K,V> putTreeVal(HashMap<K,V> map, Node<K,V>[] tab,int h, K k, V v) {Class<?> kc = null;boolean searched = false;TreeNode<K,V> root = (parent != null) ? root() : this;// 安全问题for (TreeNode<K,V> p = root;;) {int dir, ph; K pk;if ((ph = p.hash) > h)dir = -1;else if (ph < h)dir = 1;else if ((pk = p.key) == k || (k != null && k.equals(pk)))return p;else if ((kc == null &&(kc = comparableClassFor(k)) == null) ||(dir = compareComparables(kc, k, pk)) == 0) {if (!searched) {TreeNode<K,V> q, ch;searched = true;if (((ch = p.left) != null &&(q = ch.find(h, k, kc)) != null) ||((ch = p.right) != null &&(q = ch.find(h, k, kc)) != null))return q;}dir = tieBreakOrder(k, pk);}TreeNode<K,V> xp = p;if ((p = (dir <= 0) ? p.left : p.right) == null) {Node<K,V> xpn = xp.next;TreeNode<K,V> x = map.newTreeNode(h, k, v, xpn);if (dir <= 0)xp.left = x;elsexp.right = x;xp.next = x;x.parent = x.prev = xp;if (xpn != null)((TreeNode<K,V>)xpn).prev = x;moveRootToFront(tab, balanceInsertion(root, x));return null;}}
}

链表转化树

final void treeifyBin(Node<K,V>[] tab, int hash) {int n, index; Node<K,V> e;if (tab == null || (n = tab.length) < MIN_TREEIFY_CAPACITY)resize();else if ((e = tab[index = (n - 1) & hash]) != null) {TreeNode<K,V> hd = null, tl = null;do {TreeNode<K,V> p = replacementTreeNode(e, null);if (tl == null)hd = p;else {p.prev = tl;tl.next = p;}tl = p;} while ((e = e.next) != null);if ((tab[index] = hd) != null)hd.treeify(tab);}
}