HashMap()
/**
* Constructs an empty <tt>HashMap</tt> with the default initial capacity
* (16) and the default load factor (0.75).
* 这是一个默认的构造方法,初始化的容量大小是16,装填因子是0.75
* a 装填因子
* n 关键字个数
* m 总容量
* a = n/m
* 这里的容量大小为16,装填因子是0.75,就表示当内容达到12个的时候就会可能出现Hash冲突
* 必须在 "冲突的机会"与"空间利用率"之间寻找一种平衡与折衷.这种平衡与折衷本质上是数据 * 结构中有名的"时-空"矛盾的平衡与折衷.也就是说在空间与时间上
*/
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.
*/
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.
* 指定容量指定装填因子
* @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) {
//如果初始化容量小于零
if (initialCapacity < 0)
throw new IllegalArgumentException("Illegal initial capacity: " +
initialCapacity);
//如果初始化容量大于 1 << 30 左移表示乘以多少个 2 ,也就是表示 2的30次方;
if (initialCapacity > MAXIMUM_CAPACITY)
initialCapacity = MAXIMUM_CAPACITY;
//如果装填因子小于等于0
if (loadFactor <= 0 || Float.isNaN(loadFactor))
throw new IllegalArgumentException("Illegal load factor: " +
loadFactor);
this.loadFactor = loadFactor;
this.threshold = tableSizeFor(initialCapacity);
}
示例
HashMap<Integer,String> hashMap = new HashMap<Integer, String>(-1,0.5f);
初始化容量操作
HashMap<Integer,String> hashMap = new HashMap<>(1<<32,0.5f);
this.threshold = tableSizeFor(initialCapacity);
/**
* The next size value at which to resize (capacity * load factor).
*
* @serial
*/
// (The javadoc description is true upon serialization.
// Additionally, if the table array has not been allocated, this
// field holds the initial array capacity, or zero signifying
// DEFAULT_INITIAL_CAPACITY.)
int threshold;
表示获取最接近初始化值的2的次方值
static final int tableSizeFor(int cap) {
int n = cap - 1;
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;
}
首先,int n = cap -1是为了防止cap已经是2的幂时,执行完后面的几条无符号右移操作之后,返回的capacity是这个cap的2倍,因为cap已经是2的幂了,就已经满足条件了。 如果不懂可以往下看完几个无符号移位后再回来看。(建议自己在纸上画一下)
如果n这时为0了(经过了cap-1之后),则经过后面的几次无符号右移依然是0,最后返回的capacity是1(最后有个n+1的操作)。这里只讨论n不等于0的情况。
以16位为例,假设开始时 n 为 0000 1xxx xxxx xxxx (x代表不关心0还是1)
- 第一次右移 n |= n >>> 1;
由于n不等于0,则n的二进制表示中总会有一bit为1,这时考虑最高位的1。通过无符号右移1位,则将最高位的1右移了1位,再做或操作,使得n的二进制表示中与最高位的1紧邻的右边一位也为1,如0000 11xx xxxx xxxx 。
- 第二次右移 n |= n >>> 2;
注意,这个n已经经过了n |= n >>> 1; 操作。此时n为0000 11xx xxxx xxxx ,则n无符号右移两位,会将最高位两个连续的1右移两位,然后再与原来的n做或操作,这样n的二进制表示的高位中会有4个连续的1。如0000 1111 xxxx xxxx 。
- 第三次右移 n |= n >>> 4;
这次把已经有的高位中的连续的4个1,右移4位,再做或操作,这样n的二进制表示的高位中会有8个连续的1。如0000 1111 1111 xxxx 。
测试结果
public static void main(String[] args) {
int sizeFor = tableSizeFor(432);
System.out.println(sizeFor);
//>>> : 无符号右移,忽略符号位,空位都以0补齐
//00000000_00000000_00000000_00000111 7
//00000000_00000000_00000000_00000011 3
int a = 7 >>> 1;
System.out.println(a);
//00000000_00000000_00000000_00000111 7
//00000000_00000000_00000000_00000011 3
int b = 7;
//按位或的结果
//00000000_00000000_00000000_00000111
b |= 3;
System.out.println(b);
b |= b>>>1;
System.out.println(b);
}
// 此函数返回的结果表示获取最接近它的2的次方
static int tableSizeFor(int cap) {
int n = cap - 1;
n |= n >>> 1;
n |= n >>> 2;
n |= n >>> 4;
n |= n >>> 8;
n |= n >>> 16;
return (n < 0) ? 1 : (n >= 1<<30) ? 1<<30 : n + 1;
}
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
*/
public HashMap(Map<? extends K, ? extends V> m) {
this.loadFactor = DEFAULT_LOAD_FACTOR;
putMapEntries(m, false);
}
调用了putMapEntries(m, false);方法
/**
* Implements Map.putAll and Map constructor
*
* @param m the map
* @param evict false when initially constructing this map, else
* true (relayed to method afterNodeInsertion).
*/
final void putMapEntries(Map<? extends K, ? extends V> m, boolean evict) {
// 获取现有Map的大小
int s = m.size();
// 当m 中有元素的时候,将Map中的元素放入到现在初始化的这个Map实例中
if (s > 0) {
// 判断table是否已经被初始化了,如果没有初始化先需要进行初始化一些变量
// 例如装填因子初始化容量等参数
if (table == null) { // pre-size
//根据待插入的map的Size计算需要创建的Map的容量
float ft = ((float)s / loadFactor) + 1.0F;
//计算对应容量
int t = ((ft < (float)MAXIMUM_CAPACITY) ?
(int)ft : MAXIMUM_CAPACITY);
// 要把创建的的map的容量存在 threshold 中
if (t > threshold)
threshold = tableSizeFor(t);
}
//如果table初始化过了,因为还有其他函数的调用,所以有些Hashmap已经被初始化过了
//判断需要插入的值是否大于现有的threshold,如果需要,则进行扩容操作resize();
else if (s > threshold)
resize();
//然后就开始遍历需要插入的map ,将每一个KV都插入的本实例HashMap中
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);
}
}
}
这里需要说明一下putVal,在HashMap出入值调用put方法的时候实际上也是调用这个方法。下一边分析一边来看看具体的参数都是什么意思
首先先来介绍一下HashMap中的几个私有属性
/**
* 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.)
*/
// 用来存储实际的key,value的数组,只不过在HashMap中将其封装成了一个Node,下面会介绍
transient Node<K,V>[] table;
/**
* Holds cached entrySet(). Note that AbstractMap fields are used
* for keySet() and values().
*/
//作为一个Key的缓存存在
transient Set<Map.Entry<K,V>> entrySet;
/**
* The number of key-value mappings contained in this map.
*/
//Map中已有数据的大小
transient int size;
/**
* The number of times this HashMap has been structurally modified
* Structural modifications are those that change the number of mappings in
* the HashMap or otherwise modify its internal structure (e.g.,
* rehash). This field is used to make iterators on Collection-views of
* the HashMap fail-fast. (See ConcurrentModificationException).
*/
transient int modCount;
/**
* The next size value at which to resize (capacity * load factor).
*
* @serial
*/
// (The javadoc description is true upon serialization.
// Additionally, if the table array has not been allocated, this
// field holds the initial array capacity, or zero signifying
// DEFAULT_INITIAL_CAPACITY.)
// 因为 tableSizeFor(int) 返回值给了threshold
int threshold;
/**
* The load factor for the hash table.
*
* @serial
*/
final float loadFactor;
这里首先关注两个点
Entry
Entry 是由Map提供的接口
Node
/**
* 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> {
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;
}
}
会看到在上面调用了putMapEntries 方法的时候调用了一个putVal而在传入参数的时候调用了一个hash()方法
static final int hash(Object key) {
int h;
return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}
这里有个异或运算
(h = key.hashCode()) ^ (h >>> 16);
这里我们知道Hash值是一个int类型的使用2个字节,也就是16位二进制表示
原 来 的 hashCode : 1111 1111 1111 1111 0100 1100 0000 1010
移位后的hashCode: 0000 0000 0000 0000 1111 1111 1111 1111
进行异或运算 结果:1111 1111 1111 1111 1011 0011 1111 0101
这样做的好处是,可以将hashCode高位和地位的值进行混合做异或运算,而且混合之后,地位的信息中加入了高位的信息,这样高位的信息就会被保留下来,掺杂的元素多了,那么生成的hash的随机性会增大。
这里在补充分析一下另外的一个方法扩容方法resize()
/**
* 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() {
//保存当前table
Node<K,V>[] oldTab = table;
//保存当前table容量
int oldCap = (oldTab == null) ? 0 : oldTab.length;
//保存当前阈值
int oldThr = threshold;
//初始化新的Table的容量和阈值
int newCap, newThr = 0;
/**
1、resize()函数在size > threshold 的时候被调用,
oldCap 大于0 表示原来的table为非空,oldCap为原来表大小,
oldThread 为原来容量oldCap x load_factor
*/
if (oldCap > 0) {
// 如果旧的table容量超过最大容量,更新阈值为最大整型值这样以后就不需要再操作了
if (oldCap >= MAXIMUM_CAPACITY) {
threshold = Integer.MAX_VALUE;
return oldTab;
}
// 容量翻倍,使用左移操作效率高
else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY &&
oldCap >= DEFAULT_INITIAL_CAPACITY)
//阈值翻倍
newThr = oldThr << 1; // double threshold
}
/**
2、resize() 函数在table为空的时候调用,oldCap等于0且oldThr 大于0,代表用户创建了一个 HashMap ,但是使用的构造函数为HashMap(int initialCapacity, float loadFactor)或者HashMap(int initialCapacity)或 HashMap(Map<? extends K, ? extends V> m),导致 oldTab 为 null,oldCap 为0, oldThr 为用户指定的 HashMap的初始容量。
*/
else if (oldThr > 0) // initial capacity was placed in threshold
//当table没初始化时,threshold持有初始容量
newCap = oldThr;
/**
3、resize() 函数在table为空被调用,oldCap小于等于0且oldThr等于0,用户调用了HasHMap()构造函数 HashMap,所有值均采用默认值,oldTab(Table)表为空,oldCap为0,oldThr等于0
*/
else { // zero initial threshold signifies using defaults
newCap = DEFAULT_INITIAL_CAPACITY;
newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);
}
//新的阈值 为 0
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"})
//初始化table
Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap];
table = newTab;
if (oldTab != null) {
//把oldTab 中的节点 reHash 到 newTab中去
for (int j = 0; j < oldCap; ++j) {
Node<K,V> e;
if ((e = oldTab[j]) != null) {
oldTab[j] = null;
// 如果是一个单节点,直接再newTab中进行定位
if (e.next == null)
newTab[e.hash & (newCap - 1)] = e;
// 如果节点是一个TreeNode 要进行红黑树的 reHash操作
else if (e instanceof TreeNode)
((TreeNode<K,V>)e).split(this, newTab, j, oldCap);
// 如果是一个链表,进行链表的reHash操作
else { // preserve order
Node<K,V> loHead = null, loTail = null;
Node<K,V> hiHead = null, hiTail = null;
Node<K,V> next;
//(e.hash & oldCap)按位与 是否为零
do {
next = e.next;
//如果为零
if ((e.hash & oldCap) == 0) {
if (loTail == null)
loHead = e;
else
loTail.next = e;
loTail = e;
}
//如果不为零
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;
}
链表扩容
什么时候进行扩容
通过HashMap源码可以看到是在put操作时,即向容器中添加元素时,判断当前容器中元素的个数是否达到阈值(当前数组长度乘以加载因子的值)的时候,就要自动扩容了。
扩容(resize):其实就是重新计算容量;而这个扩容是计算出所需容器的大小之后重新定义一个新的容器,将原来容器中的元素放入其中。
/**
* 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;
//判断table是否为空或者长度为0,则进行resize();
if ((tab = table) == null || (n = tab.length) == 0)
n = (tab = resize()).length;
// 确定需要插入表的位置
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null);
//当发生碰撞的时候,有两种情况,1、key值一样替换value值
// 2、key值不一样
// 2.1
else {
Node<K,V> e; K k;
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
e = p;
else if (p instanceof TreeNode)
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
else {
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;
}
}
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;
}