HashMap是基于哈希表的Map接口的非同步实现。此实现提供所有可选的映射操作,并允许使用null值和null键。此类不保证映射的顺序,特别是它不保证该顺序恒久不变。hashmap是一种用空间换时间的数据结构,如何去定义桶的大小,是最关键的要衡量的指标。如果桶过大,则空间浪费,如果桶过小,则会频繁发生冲突。
在Java编程语言中,最基本的结构就是两种,一个是数组,另外一个是模拟指针(引用),所有的数据结构都可以用这两个基本结构来构造的,HashMap也不例外。HashMap实际上是一个“链表散列”的数据结构,即数组和链表的结构,但是在jdk1.8里加入了红黑树的实现,当链表的长度大于8时,转换为红黑树的结构。
一般情况下,遇到哈希冲突可以采用开放定址法或者使用链地址法两种方法解决。
调用put方法,会计算其中put的key的对象的hashcode,通过类中的hash函数运算进行处理,处理后在桶中找到这个地址,存放进链表的尾部。
HashMap中,如果key经过hash算法得出的数组索引位置全部不相同,即Hash算法非常好,那样的话,getKey方法的时间复杂度就是O(1),如果Hash算法技术的结果碰撞非常多,假如Hash算极其差,所有的Hash算法结果得出的索引位置一样,那样所有的键值对都集中到一个桶中,或者在一个链表中,或者在一个红黑树中,时间复杂度分别为O(n)和O(lgn)。
public class HashMap<K,V> extends AbstractMap<K,V>
implements Map<K,V>, Cloneable, Serializable {
private static final long serialVersionUID = 362498820763181265L;
/**
* 容量大小必须为2的幂,原因是从jdk1.2开始之后计算机中除法、取模
* 运算操作效率越来越低,为了防止效率过低,设置容量大小为2的幂,
* 在进行取模时,用A&(B-1)来代替A%B的操作,提高效率,至于hash分布
* 用其他的辅助方法确保效率
*/
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16
/**
* 最大容量2的29次方
*/
static final int MAXIMUM_CAPACITY = 1 << 30;
/**
* 加载因子
*/
static final float DEFAULT_LOAD_FACTOR = 0.75f;
static final int TREEIFY_THRESHOLD = 8;
static final int UNTREEIFY_THRESHOLD = 6;
static final int MIN_TREEIFY_CAPACITY = 64;
/**
* hashMap桶中的数据结构是Node,next是下一个Node的引用
*/
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;
}
}
/**
* 对key进行hash,调用key的hashcode函数并与其右移16位后的结果做异或
* 这样做的好处在于,对于hashcode大于2的16次方的数进行重调,如果数
* 小于2的16次方则不变
* h & (table.length -1) 等价于 h % table.length
* 这样做的原因是,当table的length比较小的时候,可以让高位也参与到
* hash算法中来,起到作用
*/
static final int hash(Object key) {
int h;
return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}
/**
* Returns x's Class if it is of the form "class C implements
* Comparable<C>", else null.
*/
static Class<?> comparableClassFor(Object x) {
if (x instanceof Comparable) {
Class<?> c; Type[] ts, as; Type t; ParameterizedType p;
if ((c = x.getClass()) == String.class) // bypass checks
return c;
if ((ts = c.getGenericInterfaces()) != null) {
for (int i = 0; i < ts.length; ++i) {
if (((t = ts[i]) instanceof ParameterizedType) &&
((p = (ParameterizedType)t).getRawType() ==
Comparable.class) &&
(as = p.getActualTypeArguments()) != null &&
as.length == 1 && as[0] == c) // type arg is c
return c;
}
}
}
return null;
}
/**
* Returns k.compareTo(x) if x matches kc (k's screened comparable
* class), else 0.
*/
@SuppressWarnings({"rawtypes","unchecked"}) // for cast to Comparable
static int compareComparables(Class<?> kc, Object k, Object x) {
return (x == null || x.getClass() != kc ? 0 :
((Comparable)k).compareTo(x));
}
/**
* 用1,2,4,8,16的或运算将cap的每一位设置为1,通过+1操作变为一个2的幂
* 先将数据-1,放置如果原来就是2的幂,变为2倍。
*/
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;
}
/* ---------------- Fields -------------- */
/**
* 哈希桶
*/
transient Node<K,V>[] table;
/**
* 以一个个键值对为对象的集合
*/
transient Set<Map.Entry<K,V>> entrySet;
/**
* map中包含的键值对的数量
*/
transient int size;
/**
* 重构次数
*/
transient int modCount;
/**
* 最多能够容纳的键值对数量,threshold = length * Load factor
*/
int threshold;
/**
* 负载因子,可以大于1
*/
final float loadFactor;
/* ---------------- Public operations -------------- */
/**
* 容量和装载因子做参数
*/
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);
}
/**
* 默认装载因子
*/
public HashMap(int initialCapacity) {
this(initialCapacity, DEFAULT_LOAD_FACTOR);
}
/**
* 全采用默认值
*/
public HashMap() {
this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted
}
/**
* 默认装载因子,添加参数中所有元素
*/
public HashMap(Map<? extends K, ? extends V> m) {
this.loadFactor = DEFAULT_LOAD_FACTOR;
putMapEntries(m, false);
}
/**
* 第二个参数在是初始化时调用此方法用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);
}
}
}
public int size() {
return size;
}
public boolean isEmpty() {
return size == 0;
}
public V get(Object key) {
Node<K,V> e;
return (e = getNode(hash(key), key)) == null ? null : e.value;
}
/**
* 获取此节点,获取索引地址,对比第一个元素,不是的话判断是否是红黑树,是树
* 就调用树的方法继续找,不是树就循环遍历
*/
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);
do {
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
return e;
} while ((e = e.next) != null);
}
}
return null;
}
public boolean containsKey(Object key) {
return getNode(hash(key), key) != null;
}
public V put(K key, V value) {
return putVal(hash(key), key, value, false, true);
}
/**
* 判断键值对数组table[i]是否为空或为null,否则执行resize()进行扩容;
* 根据键值key计算hash值得到插入的数组索引i,如果table[i]==null,直接新建节点添加
* 如果不为null,判断table[i]的首个元素是否和key一样,如果相同直接覆盖value,这里的相同
* 指的是hashCode以及equals;
* 判断table[i] 是否为treeNode,即table[i]是否是红黑树,如果是红黑树,则直接在树中插入
* 键值对
* 遍历table[i],判断链表长度是否大于8,大于8的话把链表转换为红黑树,在红黑树中执行插入
* 操作,否则进行链表的插入操作;遍历过程中若发现key已经存在直接覆盖value即可;
* 插入成功后,判断实际存在的键值对数量size是否超多了最大容量threshold,如果超过,进行
* 扩容。
*/
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)
n = (tab = resize()).length;
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null);
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;
}
/**
* resize是最核心的扩展方法,开始的时候判断oldCap即老数组长度,如果不是0的话在范围合理
* 的情况下进行扩展,如果范围不合理就不能再扩展了。如果老数组长度为0,说明table还没初始
* 化,如果老threshold不为零说明初始化的时候定义了容量,就采用这个容量,如果什么都没定
* 义,就都用默认的。这一步完成即完成了threshold的设置,table的创建。
*
* 之后创建一个新table,遍历老table把所有对象引用制null等待回收,根据情况判断,如果只有
* 一个节点就直接放进去,如果是红黑树就调用方法,如果是链表就循环遍历,重新hash。
*
* 因为采用2的幂做容量,所以当进行(n-1)& hashcode的时候只需要判断一个高位是0还是1。
*/
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;
}
/**
* 转换成红黑树
*/
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);
}
}
public void putAll(Map<? extends K, ? extends V> m) {
putMapEntries(m, true);
}
public V remove(Object key) {
Node<K,V> e;
return (e = removeNode(hash(key), key, null, false, true)) == null ?
null : e.value;
}
/**
* 删除元素,删除的操作流程类似于put
*/
final Node<K,V> removeNode(int hash, Object key, Object value,
boolean matchValue, boolean movable) {
Node<K,V>[] tab; Node<K,V> p; int n, index;
if ((tab = table) != null && (n = tab.length) > 0 &&
(p = tab[index = (n - 1) & hash]) != null) {
Node<K,V> node = null, e; K k; V v;
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
node = p;
else if ((e = p.next) != null) {
if (p instanceof TreeNode)
node = ((TreeNode<K,V>)p).getTreeNode(hash, key);
else {
do {
if (e.hash == hash &&
((k = e.key) == key ||
(key != null && key.equals(k)))) {
node = e;
break;
}
p = e;
} while ((e = e.next) != null);
}
}
if (node != null && (!matchValue || (v = node.value) == value ||
(value != null && value.equals(v)))) {
if (node instanceof TreeNode)
((TreeNode<K,V>)node).removeTreeNode(this, tab, movable);
else if (node == p)
tab[index] = node.next;
else
p.next = node.next;
++modCount;
--size;
afterNodeRemoval(node);
return node;
}
}
return null;
}
public void clear() {
Node<K,V>[] tab;
modCount++;
if ((tab = table) != null && size > 0) {
size = 0;
for (int i = 0; i < tab.length; ++i)
tab[i] = null;
}
}
public boolean containsValue(Object value) {
Node<K,V>[] tab; V v;
if ((tab = table) != null && size > 0) {
for (int i = 0; i < tab.length; ++i) {
for (Node<K,V> e = tab[i]; e != null; e = e.next) {
if ((v = e.value) == value ||
(value != null && value.equals(v)))
return true;
}
}
}
return false;
}