一、HashMap概述在JDK1.8之前,HashMap采用数组+链表实现,即使用链表处理冲突,同一hash值的链表都存储在一个链表里。但是当位于一个桶中的元素较多,即hash值相等的元素较多时,通过key值依次查找的效率较低。而JDK1.8中,HashMap采用数组+链表+红黑树实现,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。下图中代表jdk1.8之前的hashmap结构,左边部分即代表哈希表,也称为哈希数组,数组的每个元素都是一个单链表的头节点,链表是用来解决冲突的,如果不同的key映射到了数组的同一位置处,就将其放入单链表中。(此图借用网上的图) 图一、jdk1.8之前hashmap结构图 jdk1.8之前的hashmap都采用上图的结构,都是基于一个数组和多个单链表,hash值冲突的时候,就将对应节点以链表的形式存储。如果在一个链表中查找其中一个节点时,将会花费O(n)的查找时间,会有很大的性能损失。到了jdk1.8,当同一个hash值的节点数不小于8时,不再采用单链表形式存储,而是采用红黑树,如下图所示(此图是借用的图)图二、jdk1.8 hashmap结构图二、重要的field//table就是存储Node类的数组,就是对应上图中左边那一栏, /** * The table, initialized on first use, and resized as * necessary. When allocated, length is always a power of two. * (We also tolerate length zero in some operations to allow * bootstrapping mechanics that are currently not needed.) */ transient Node<K,V>[] table;
/** * The number of key-value mappings contained in this map. * 记录hashmap中存储键-值对的数量 */ transient int size;/** * hashmap结构被改变的次数,fail-fast机制 */ transient int modCount; /** * The next size value at which to resize (capacity * load factor). * 扩容的门限值,当size大于这个值时,table数组进行扩容 */ int threshold; /** * The load factor for the hash table. * */ float loadFactor; /** * The default initial capacity - MUST be a power of two. * 默认初始化数组大小为16 */ static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16 /** * The maximum capacity, used if a higher value is implicitly specified * by either of the constructors with arguments. * MUST be a power of two <= 1<<30. */ static final int MAXIMUM_CAPACITY = 1 << 30; /** * The load factor used when none specified in constructor. * 默认装载因子, */ static final float DEFAULT_LOAD_FACTOR = 0.75f; /** * The bin count threshold for using a tree rather than list for a * bin. Bins are converted to trees when adding an element to a * bin with at least this many nodes. The value must be greater * than 2 and should be at least 8 to mesh with assumptions in * tree removal about conversion back to plain bins upon * shrinkage. * 这是链表的最大长度,当大于这个长度时,链表转化为红黑树 */ static final int TREEIFY_THRESHOLD = 8; /** * The bin count threshold for untreeifying a (split) bin during a * resize operation. Should be less than TREEIFY_THRESHOLD, and at * most 6 to mesh with shrinkage detection under removal. */ static final int UNTREEIFY_THRESHOLD = 6; /** * The smallest table capacity for which bins may be treeified. * (Otherwise the table is resized if too many nodes in a bin.) * Should be at least 4 * TREEIFY_THRESHOLD to avoid conflicts * between resizing and treeification thresholds. */ static final int MIN_TREEIFY_CAPACITY = 64;三、构造函数//可以自己指定初始容量和装载因子 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; //重新定义了扩容的门限 this.threshold = tableSizeFor(initialCapacity); }/** * Returns a power of two size for the given target capacity. */ static final int tableSizeFor(int cap) { int n = cap - 1; //先移位再或运算,最终保证返回值是2的整数幂 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; } /** * 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. */ //当知道所要构建的数据容量的大小时,最好直接指定大小,提高效率 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 } //将map直接放入hashmap中 public HashMap(Map<? extends K, ? extends V> m) { this.loadFactor = DEFAULT_LOAD_FACTOR; putMapEntries(m, false); }final void putMapEntries(Map<? extends K, ? extends V> m, boolean evict) { int s = m.size(); if (s > 0) { if (table == null) { // pre-size float ft = ((float)s / loadFactor) + 1.0F; int t = ((ft < (float)MAXIMUM_CAPACITY) ? (int)ft : MAXIMUM_CAPACITY); if (t > threshold) threshold = tableSizeFor(t); } else if (s > threshold) resize(); for (Map.Entry<? extends K, ? extends V> e : m.entrySet()) { K key = e.getKey(); V value = e.getValue(); putVal(hash(key), key, value, false, evict); } } } /** * Basic hash bin node, used for most entries. (See below for * TreeNode subclass, and in LinkedMyHashMap for its Entry subclass.) */ 在hashMap的结构图中,hash数组就是用Node型数组实现的,许多Node类通过next组成链表,key、value实际存储在Node内部类中。 public 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; } }四、重要的方法分析1.put方法/** * Associates the specified value with the specified key in thismap. * If the map previously contained a mapping for the key, the old * value is replaced. * */ public V put(K key, V value) { return putVal(hash(key), key, value, false, true); } static final int hash(Object key) { int h; //key的值为null时,hash值返回0,对应的table数组中的位置是0 return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16); }/** * 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; //先将table赋给tab,判断table是否为null或大小为0,若为真,就调用resize()初始化 if ((tab = table) == null || (n = tab.length) == 0) n = (tab = resize()).length; //通过i = (n - 1) & hash得到table中的index值,若为null,则直接添加一个newNode if ((p = tab[i = (n - 1) & hash]) == null) tab[i] = newNode(hash, key, value, null); else { //执行到这里,说明发生碰撞,即tab[i]不为空,需要组成单链表或红黑树 Node<K,V> e; K k; if (p.hash == hash && ((k = p.key) == key || (key != null && key.equals(k)))) //此时p指的是table[i]中存储的那个Node,如果待插入的节点中hash值和key值在p中已经存在,则将p赋给e e = p; //如果table数组中node类的hash、key的值与将要插入的Node的hash、key不吻合,就需要在这个node节点链表或者树节点中查找。 else if (p instanceof TreeNode) //当p属于红黑树结构时,则按照红黑树方式插入 e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value); else { //到这里说明碰撞的节点以单链表形式存储,for循环用来使单链表依次向后查找 for (int binCount = 0; ; ++binCount) { //将p的下一个节点赋给e,如果为null,创建一个新节点赋给p的下一个节点 if ((e = p.next) == null) { p.next = newNode(hash, key, value, null); //如果冲突节点达到8个,调用treeifyBin(tab, hash),这个treeifyBin首先回去判断当前hash表的长度,如果不足64的话,实际上就只进行resize,扩容table,如果已经达到64,那么才会将冲突项存储结构改为红黑树。 if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st treeifyBin(tab, hash); break; } //如果有相同的hash和key,则退出循环 if (e.hash == hash && ((k = e.key) == key || (key != null && key.equals(k)))) break; p = e;//将p调整为下一个节点 } } //若e不为null,表示已经存在与待插入节点hash、key相同的节点,hashmap后插入的key值对应的value会覆盖以前相同key值对应的value值,就是下面这块代码实现的 if (e != null) { // existing mapping for key V oldValue = e.value; //判断是否修改已插入节点的value if (!onlyIfAbsent || oldValue == null) e.value = value; afterNodeAccess(e); return oldValue; } } ++modCount;//插入新节点后,hashmap的结构调整次数+1 if (++size > threshold) resize();//HashMap中节点数+1,如果大于threshold,那么要进行一次扩容 afterNodeInsertion(evict); return null; }2.扩容函数resize()分析/** * 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() { Node<K,V>[] oldTab = table;//定义临时Node数组型变量,作为hash table //读取hash table的长度 int oldCap = (oldTab == null) ? 0 : oldTab.length; int oldThr = threshold;//读取扩容门限 int newCap, newThr = 0;//初始化新的table长度和门限值 if (oldCap > 0) { //执行到这里,说明table已经初始化 if (oldCap >= MAXIMUM_CAPACITY) { threshold = Integer.MAX_VALUE; return oldTab; } //二倍扩容,容量和门限值都加倍 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 //用构造器初始化了门限值,将门限值直接赋给新table容量 newCap = oldThr; else { // zero initial threshold signifies using defaults //老的table容量和门限值都为0,初始化新容量,新门限值,在调用hashmap()方式构造容器时,就采用这种方式初始化 newCap = DEFAULT_INITIAL_CAPACITY; newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY); } if (newThr == 0) { //如果门限值为0,重新设置门限 float ft = (float)newCap * loadFactor; newThr = (newCap < MAXIMUM_CAPACITY && ft < (float)MAXIMUM_CAPACITY ? (int)ft : Integer.MAX_VALUE); } threshold = newThr;//更新新门限值为threshold @SuppressWarnings({"rawtypes","unchecked"}) //初始化新的table数组 Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap]; table = newTab; //当原来的table不为null时,需要将table[i]中的节点迁移 if (oldTab != null) { for (int j = 0; j < oldCap; ++j) { Node<K,V> e; //取出链表中第一个节点保存,若不为null,继续下面操作 if ((e = oldTab[j]) != null) { oldTab[j] = null;//主动释放 if (e.next == null) //链表中只有一个节点,没有后续节点,则直接重新计算在新table中的index,并将此节点存储到新table对应的index位置处 newTab[e.hash & (newCap - 1)] = e; else if (e instanceof TreeNode) //若e是红黑树节点,则按红黑树移动 ((TreeNode<K,V>)e).split(this, newTab, j, oldCap); else { // preserve order //迁移单链表中的每个节点 Node<K,V> loHead = null, loTail = null; Node<K,V> hiHead = null, hiTail = null; Node<K,V> next; do { //下面这段暂时没有太明白,通过e.hash & oldCap将链表分为两队,参考知乎上的一段解释 /** * 把链表上的键值对按hash值分成lo和hi两串,lo串的新索引位置与原先相同[原先位 * j],hi串的新索引位置为[原先位置j+oldCap]; * 链表的键值对加入lo还是hi串取决于 判断条件if ((e.hash & oldCap) == 0),因为* capacity是2的幂,所以oldCap为10...0的二进制形式,若判断条件为真,意味着 * oldCap为1的那位对应的hash位为0,对新索引的计算没有影响(新索引 * =hash&(newCap-*1),newCap=oldCap<<2);若判断条件为假,则 oldCap为1的那位* 对应的hash位为1, * 即新索引=hash&( newCap-1 )= hash&( (oldCap<<2) - 1),相当于多了10...0, * 即 oldCap* 例子: * 旧容量=16,二进制10000;新容量=32,二进制100000 * 旧索引的计算: * hash = xxxx xxxx xxxy xxxx * 旧容量-1 1111 * &运算 xxxx * 新索引的计算: * hash = xxxx xxxx xxxy xxxx * 新容量-1 1 1111 * &运算 y xxxx * 新索引 = 旧索引 + y0000,若判断条件为真,则y=0(lo串索引不变),否则y=1(hi串 * 索引=旧索引+旧容量10000) */ 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; }3.get方法/** * Returns the value to which the specified key is mapped, * or {@code null} if this map contains no mapping for the key. * * <p>More formally, if this map contains a mapping from a key * {@code k} to a value {@code v} such that {@code (key==null ? k==null : * key.equals(k))}, then this method returns {@code v}; otherwise * it returns {@code null}. (There can be at most one such mapping.) * * <p>A return value of {@code null} does not <i>necessarily</i> * indicate that the map contains no mapping for the key; it"s also * possible that the map explicitly maps the key to {@code null}. * The {@link #containsKey containsKey} operation may be used to * distinguish these two cases. * * @see #put(Object, Object) */ public V get(Object key) { Node<K,V> e; return (e = getNode(hash(key), key)) == null ? null : e.value; } /** * Implements Map.get and related methods * * @param hash hash for key * @param key the key * @return the node, or null if none */ 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) { //分为红黑树和链表查找两种 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; } /** * Returns <tt>true</tt> if this map contains a mapping for the * specified key. * * @param key The key whose presence in this map is to be tested * @return <tt>true</tt> if this map contains a mapping for the specified * key. */ public boolean containsKey(Object key) { return getNode(hash(key), key) != null; }4.红黑树/** * Entry for Tree bins. Extends LinkedMyHashMap.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; // red-black tree links TreeNode<K,V> left; TreeNode<K,V> right; TreeNode<K,V> prev; // needed to unlink next upon deletion boolean red; TreeNode(int hash, K key, V val, Node<K,V> next) { super(hash, key, val, next); } //红黑树暂时还没有仔细研究,红黑树相关的增删改查操作后期再认真分析。五、总结仔细分析hashmap源码后,可以掌握很多常用的数据结构的用法。本次笔记只是记录了hashmap几个常用的方法,像红黑树、迭代器等还没有仔细研究,后面有时间会认真分析。本文永久更新链接地址:http://www.linuxidc.com/Linux/2017-01/139188.htm