import java.io.IOException;
import java.io.InvalidObjectException;
import java.io.Serializable;
import java.lang.reflect.ParameterizedType;
import java.lang.reflect.Type;
import java.util.function.BiConsumer;
import java.util.function.BiFunction;
import java.util.function.Consumer;
import java.util.function.Function;
import sun.misc.SharedSecrets;
fast-fail事件:当多个线程对Collection进行操作时,若其中某一个线程通过iterator去遍历集合时,该集合的内容被其他线程所改变;则会抛出ConcurrentModificationException异常。因此,当存在并发修改时,迭代器会快速失败。迭代器的快速失败行为不能得到保证,一般来说,存在非同步的并发修改时,不可能作出任何坚决的保证。快速失败迭代器尽最大努力抛出 ConcurrentModificationException。因此,编写依赖于此异常的程序的做法是错误的,正确做法是:迭代器的快速失败行为应该仅用于检测程序错误。
public class HashMap<K,V> extends AbstractMap<K,V>
implements Map<K,V>, Cloneable, Serializable {
private static final long serialVersionUID = 362498820763181265L;
//默认初始容量是16,必须是2的幂(为什么?后面介绍)
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16
//最大容量,当使用带参构造函数指定初始容量时使用,避免指定的初始容量大于最大容量
static final int MAXIMUM_CAPACITY = 1 << 30;
//默认加载因子
static final float DEFAULT_LOAD_FACTOR = 0.75f;
//桶的计数阈值,当添加元素时桶中的数量至少有这些时应该转换为树,而不是继续使用链表
static final int TREEIFY_THRESHOLD = 8;
static final int UNTREEIFY_THRESHOLD = 6;
static final int MIN_TREEIFY_CAPACITY = 64;
static class Node implements Map.Entry {
final int hash;//key的hash值,用来定位数组索引的位置
final K key;
V value;
Node next;
Node(int hash, K key, V value, Node 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;
}
}
static final int hash(Object key) {
int h;
return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}
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);
}
public V get(Object key) {
Node e;
return (e = getNode(hash(key), key)) == null ? null : e.value;
}
final Node getNode(int hash, Object key) {
Node[] tab; Node first, e; int n; K k;
if ((tab = table) != null && (n = tab.length) > 0 &&
(first = tab[(n - 1) & hash]) != null) {
// always check first node
if (first.hash == hash &&
((k = first.key) == key || (key != null && key.equals(k))))
return first;
if ((e = first.next) != null) {
/**如果第一个结点是TreeNode的实例,说明此处不是链表,是红黑树的结构,则使用红黑树查找方法查找*/
if (first instanceof TreeNode)
return ((TreeNode)first).getTreeNode(hash, key);
/**否则遍历链表查找,知道找到或者查完链表为止*/
do {
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
return e;
} while ((e = e.next) != null);
}
}
return null;
}
public V put(K key, V value) {
return putVal(hash(key), key, value, false, true);
}
/**onlyIfAbsent如果为true,则不会改变已经存在的值*/
final V putVal(int hash, K key, V value, boolean onlyIfAbsent,
boolean evict) {
Node[] tab; Node p; int n, i;
/**如果是第一次放键值对,那么table还没有初始化,或者table的长度是0,则resize()进行初始化*/
if ((tab = table) == null || (n = tab.length) == 0)
n = (tab = resize()).length;
/**如果table的这个位置为null表示还没有此索引的结点,应该先建一个结点存放此键值对*/
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null);
/**以上两种情况都不是,则依次对比链表中的结点(1)此键的结点已经存在,旧值换新值;(2)此处为树形结构,调用putTreeVal();(3)将此新结点放在链表末尾*/
else {
Node 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)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);
//放入新节点后链表的节点数大于TREEIFY_THRESHOLD-1,则将链表树形化
if (binCount >= TREEIFY_THRESHOLD - 1)
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字段主要用来记录HashMap内部结构发生变化的次数,主要用于迭代的快速失败
++modCount;
/**放入新节点后HashMap中实际存在的键值对数量大于阈值,要rehash,扩容*/
if (++size > threshold)
resize();
afterNodeInsertion(evict);
return null;
}
final Node[] resize() {
Node[] oldTab = table;
int oldCap = (oldTab == null) ? 0 : oldTab.length;
int oldThr = threshold;
int newCap, newThr = 0;
if (oldCap > 0) {
// 超过最大值就不再扩充了,我已经进最大努力啦!
if (oldCap >= MAXIMUM_CAPACITY) {
threshold = Integer.MAX_VALUE;
return oldTab;
}
//扩充为原来的2倍newCap = oldCap << 1
else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY &&
oldCap >= DEFAULT_INITIAL_CAPACITY)
newThr = oldThr << 1; // double threshold
}
// initial capacity was placed in threshold
else if (oldThr > 0)
newCap = oldThr;
// zero initial threshold signifies using defaults
else {
newCap = DEFAULT_INITIAL_CAPACITY;
newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);
}
//计算新的阈值
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[] newTab = (Node[])new Node[newCap];
table = newTab;
//把每个bucket都移动到新的buckets中
if (oldTab != null) {
for (int j = 0; j < oldCap; ++j) {
Node e;
if ((e = oldTab[j]) != null) {
oldTab[j] = null;
if (e.next == null)
newTab[e.hash & (newCap - 1)] = e;
//桶的结构为红黑树
else if (e instanceof TreeNode)
((TreeNode)e).split(this, newTab, j, oldCap);
//桶的结构为链表
else { // preserve order
Node loHead = null, loTail = null;
Node hiHead = null, hiTail = null;
Node next;
do {
next = e.next;
/**原索引,为什么呢?如果原hash的后五位为01010,
*oldCap为10000,01010&10000 = 00000,即使newCap = oldCap<<1 = 100000,
*那么newCap-1后和hash的后五位与即11111&01010 = 00000,实际上是不变的*/
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);
// 原索引放到bucket里
if (loTail != null) {
loTail.next = null;
newTab[j] = loHead;
}
// 原索引+oldCap放到bucket里
if (hiTail != null) {
hiTail.next = null;
newTab[j + oldCap] = hiHead;
}
}
}
}
}
return newTab;
}
1、HashMap的原理以及内部数据结构?
底层使用哈希表(数组加链表),当链表过长(结点达到8个)就转成红黑树以实现O(logn)时间复杂度内查找。
2、HashMap中put方法的过程?
(1)对key求哈希,在计算在table中的索引位置;
(2)如果没有碰撞,直接放入桶中;
(3)如果碰撞了,以链表的方式放在链表的后面;
(4)如果链表的长度超过阈值8,将链表转换成红黑树;
(5)如果结点已经存在,就新值替换旧值,并返回旧值;
(6)如果size > threshold,就要resize。
3、hash函数的实现?
高16位不变,低16位和高16位做异或;然后(n-1)&hash得到下标。