Java深入学习04：深入理解HashMap
一 HashMap是什么
概述：HashMap是基于哈希表(散列表)，实现Map接口的双列集合，数据结构是“链表散列”，也就是数组+链表 ，key唯一的value可以重复，允许存储null 键null 值，元素无序。
HashMap在JDK1.8之前的实现方式 数组+链表,但是在JDK1.8后对HashMap进行了底层优化,改为了由 数组+链表+红黑树实现,主要的目的是提高查找效率。
哈希表
数组：一段连续控件存储数据，指定下标的查找，时间复杂度O(1),通过给定值查找，需要遍历数组，自已对比复杂度为O（n） 二分查找插值查找，复杂度为O(logn)
线性链表：增 删除仅处理结点，时间复杂度O(1)查找需要遍历也就是O(n)
二叉树：对一颗相对平衡的有序二叉树，对其进行插入，查找，删除，平均复杂度O(logn)
哈希表：哈希表中进行添加，删除，查找等操作，性能十分之高，不考虑哈希冲突的情况下，仅需一次定位即可完成，时间复杂度为O(1)哈希表的主干就是数组
hash冲突
如果两个不同的元素，通过哈希函数得出的实际存储地址相同怎么办？也就是说，当我们对某个元素进行哈希运算，得到一个存储地址，然后要进行插入的时候，发现已经被其他元素占用了，其实这就是所谓的哈希冲突，也叫哈希碰撞。前面我们提到过，哈希函数的设计至关重要，好的哈希函数会尽可能地保证 计算简单和散列地址分布均匀,但是，我们需要清楚的是，数组是一块连续的固定长度的内存空间，再好的哈希函数也不能保证得到的存储地址绝对不发生冲突。那么哈希冲突如何解决呢？哈希冲突的解决方案有多种:开放定址法（发生冲突，继续寻找下一块未被占用的存储地址），再散列函数法，链地址法，而HashMap即是采用了链地址法，也就是数组+链表的方式
链表则是主要为了解决哈希冲突而存在的，如果定位到的数组位置不含链表（当前entry的next指向null）,那么对于查找，添加等操作很快，仅需一次寻址即可；如果定位到的数组包含链表，对于添加操作，其时间复杂度为O(n)，首先遍历链表，存在即覆盖，否则新增；对于查找操作来讲，仍需遍历链表，然后通过key对象的equals方法逐一比对查找。所以，性能考虑，HashMap中的链表出现越少，性能才会越好
二 源码分析
1-变量
约定：约定前面的数组结构的每一个格称为桶；约定桶后面存放的每一个数据称为bin;bin这个术语来自于JDK 1.8的HashMap注释。
size：size表示HashMap中存放KV的数量（为链表和树中的KV的总和）。
capacity：就是指HashMap中桶的数量。默认值为16。一般第一次扩容时会扩容到64，之后好像是2倍。总之，容量都是2的幂。
loadFactor：装载因子用来衡量HashMap满的程度。loadFactor的默认值为0.75f。计算HashMap的实时装载因子的方法为：size/capacity，而不是占用桶的数量去除以capacity。
threshold：threshold表示当HashMap的size大于threshold时会执行resize操作。threshold=capacity*loadFactor
2-构造函数
HashMap()
/** * Constructs an empty <tt>HashMap</tt> with the default initial capacity * (16) and the default load factor (0.75). */ //无参构造函数：默认容量16；装载因子0.75 public HashMap() { this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted }
HashMap(int 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. */ //有参构造函数：设置初始容量；使用默认装载因子 public HashMap(int initialCapacity) { this(initialCapacity, DEFAULT_LOAD_FACTOR); }
HashMap(int initialCapacity, float loadFactor)
/** * 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 */ //有参构造函数：设置初始化容量和装载因子；并对传参做了判断和兼容处理 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); }
HashMap(Map<? extends K, ? extends V> m)
/** * Constructs a new <tt>HashMap</tt> with the same mappings as the * specified <tt>Map</tt>. The <tt>HashMap</tt> is created with * default load factor (0.75) and an initial capacity sufficient to * hold the mappings in the specified <tt>Map</tt>. * * @param m the map whose mappings are to be placed in this map * @throws NullPointerException if the specified map is null */ //有参构造函数：以已有Map为参数 public HashMap(Map<? extends K, ? extends V> m) { this.loadFactor = DEFAULT_LOAD_FACTOR; putMapEntries(m, false); }
4-其他方法
1-putMapEntries()
/** * Implements Map.putAll and Map constructor * * @param m the map * @param evict false when initially constructing this map, else * true (relayed to method afterNodeInsertion). */ //将map的key-value，放入到新map 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); } } }
2-Map扩容resize()——做三件事情：重新计算容器大小；根据新的容器大小定义新容器，将已有数据放进新容器
/** * 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 */ //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) { 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; }
3-put()
/** * Associates the specified value with the specified key in this map. * If the map previously contained a mapping for the key, the old * value is replaced. * * @param key key with which the specified value is to be associated * @param value value to be associated with the specified key * @return the previous value associated with <tt>key</tt>, or * <tt>null</tt> if there was no mapping for <tt>key</tt>. * (A <tt>null</tt> return can also indicate that the map * previously associated <tt>null</tt> with <tt>key</tt>.) */ public V put(K key, V value) { return putVal(hash(key), key, value, false, true); }
4-get()
/** * 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; }
5-containsKey()
/** * 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; }