【30期】说一下HashMap的实现原理?
来自:cnblogs.com/chengxiao/p/6059914.htm
目录
什么是哈希表
HashMap实现原理
为何HashMap的数组长度一定是2的次幂?
重写equals方法需同时重写hashCode方法
总结
一、什么是哈希表
存储位置 = f(关键字)
二、HashMap实现原理
//HashMap的主干数组,可以看到就是一个Entry数组,初始值为空数组{},主干数组的长度一定是2的次幂,至于为什么这么做,后面会有详细分析。
transient Entry<K,V>[] table = (Entry<K,V>[]) EMPTY_TABLE;
static class Entry<K,V> implements Map.Entry<K,V> {
final K key;
V value;
Entry<K,V> next;//存储指向下一个Entry的引用,单链表结构
int hash;//对key的hashcode值进行hash运算后得到的值,存储在Entry,避免重复计算
/**
* Creates new entry.
*/
Entry(int h, K k, V v, Entry<K,V> n) {
value = v;
next = n;
key = k;
hash = h;
}
//实际存储的key-value键值对的个数
transient int size;
//阈值,当table == {}时,该值为初始容量(初始容量默认为16);当table被填充了,也就是为table分配内存空间后,threshold一般为 capacity*loadFactory。HashMap在进行扩容时需要参考threshold,后面会详细谈到
int threshold;
//负载因子,代表了table的填充度有多少,默认是0.75
final float loadFactor;
//用于快速失败,由于HashMap非线程安全,在对HashMap进行迭代时,如果期间其他线程的参与导致HashMap的结构发生变化了(比如put,remove等操作),需要抛出异常ConcurrentModificationException
transient int modCount;
public HashMap(int initialCapacity, float loadFactor) {
//此处对传入的初始容量进行校验,大不能超过MAXIMUM_CAPACITY = 1<<30(230)
if (initialCapacity < )
throw new IllegalArgumentException("Illegal initial capacity: " +
initialCapacity);
if (initialCapacity > MAXIMUM_CAPACITY)
initialCapacity = MAXIMUM_CAPACITY;
if (loadFactor <= || Float.isNaN(loadFactor))
throw new IllegalArgumentException("Illegal load factor: " +
loadFactor);
this.loadFactor = loadFactor;
threshold = initialCapacity;
init();//init方法在HashMap中没有实际实现,不过在其子类如 linkedHashMap中就会有对应实现
}
public V put(K key, V value) {
//如果table数组为空数组{},进行数组填充(为table分配实际内存空间),入参为threshold,此时threshold为initialCapacity 默认是1<<4(24=16)
if (table == EMPTY_TABLE) {
inflateTable(threshold);
}
//如果key为null,存储位置为table[0]或table[0]的冲突链上
if (key == null)
return putForNullKey(value);
int hash = hash(key);//对key的hashcode进一步计算,确保散列均匀
int i = indexFor(hash, table.length);//获取在table中的实际位置
for (Entry<K,V> e = table[i]; e != null; e = e.next) {
//如果该对应数据已存在,执行覆盖操作。用新value替换旧value,并返回旧value
Object k;
if (e.hash == hash && ((k = e.key) == key || key.equals(k))) {
V oldValue = e.value;
e.value = value;
e.recordAccess(this);
return oldValue;
}
}
modCount++;//保证并发访问时,若HashMap内部结构发生变化,快速响应失败
addEntry(hash, key, value, i);//新增一个entry
return null;
}
private void inflateTable(int toSize) {
int capacity = roundUpToPowerOf2(toSize);//capacity一定是2的次幂
threshold = (int) Math.min(capacity * loadFactor, MAXIMUM_CAPACITY + 1);//此处为threshold赋值,取capacity*loadFactor和MAXIMUM_CAPACITY+1的小值,capaticy一定不会超过MAXIMUM_CAPACITY,除非loadFactor大于1
table = new Entry[capacity];
initHashSeedAsNeeded(capacity);
}
private static int roundUpToPowerOf2(int number) {
// assert number >= 0 : "number must be non-negative";
return number >= MAXIMUM_CAPACITY
? MAXIMUM_CAPACITY
: (number > 1) ? Integer.highestOneBit((number - 1) << 1) : 1;
}
//这是一个神奇的函数,用了很多的异或,移位等运算,对key的hashcode进一步进行计算以及二进制位的调整等来保证终获取的存储位置尽量分布均匀
final int hash(Object k) {
int h = hashSeed;
if ( != h && k instanceof String) {
return sun.misc.Hashing.stringHash32((String) k);
}
h ^= k.hashCode();
h ^= (h >>> 20) ^ (h >>> 12);
return h ^ (h >>> 7) ^ (h >>> 4);
}
/**
* 返回数组下标
*/
static int indexFor(int h, int length) {
return h & (length-1);
}
1 0 0 1 0
& 0 1 1 1 1
__________________
0 0 0 1 0 = 2
void addEntry(int hash, K key, V value, int bucketIndex) {
if ((size >= threshold) && (null != table[bucketIndex])) {
resize(2 * table.length);//当size超过临界阈值threshold,并且即将发生哈希冲突时进行扩容
hash = (null != key) ? hash(key) : ;
bucketIndex = indexFor(hash, table.length);
}
createEntry(hash, key, value, bucketIndex);
}
三、为何HashMap的数组长度一定是2的次幂?
void resize(int newCapacity) {
Entry[] oldTable = table;
int oldCapacity = oldTable.length;
if (oldCapacity == MAXIMUM_CAPACITY) {
threshold = Integer.MAX_VALUE;
return;
}
Entry[] newTable = new Entry[newCapacity];
transfer(newTable, initHashSeedAsNeeded(newCapacity));
table = newTable;
threshold = (int)Math.min(newCapacity * loadFactor, MAXIMUM_CAPACITY + 1);
}
void transfer(Entry[] newTable, boolean rehash) {
int newCapacity = newTable.length;
//for循环中的代码,逐个遍历链表,重新计算索引位置,将老数组数据复制到新数组中去(数组不存储实际数据,所以仅仅是拷贝引用而已)
for (Entry<K,V> e : table) {
while(null != e) {
Entry<K,V> next = e.next;
if (rehash) {
e.hash = null == e.key ? : hash(e.key);
}
int i = indexFor(e.hash, newCapacity);
//将当前entry的next链指向新的索引位置,newTable[i]有可能为空,有可能也是个entry链,如果是entry链,直接在链表头部插入。
e.next = newTable[i];
newTable[i] = e;
e = next;
}
}
}
public V get(Object key) {
//如果key为null,则直接去table[0]处去检索即可。
if (key == null)
return getForNullKey();
Entry<K,V> entry = getEntry(key);
return null == entry ? null : entry.getValue();
}
final Entry<K,V> getEntry(Object key) {
if (size == ) {
return null;
}
//通过key的hashcode值计算hash值
int hash = (key == null) ? : hash(key);
//indexFor (hash&length-1) 获取终数组索引,然后遍历链表,通过equals方法比对找出对应记录
for (Entry<K,V> e = table[indexFor(hash, table.length)];
e != null;
e = e.next) {
Object k;
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
return e;
}
return null;
}
四、重写equals方法需同时重写hashCode方法
/**
* Created by chengxiao on 2016/11/15.
*/
public class MyTest {
private static class Person{
int idCard;
String name;
public Person(int idCard, String name) {
this.idCard = idCard;
this.name = name;
}
@Override
public boolean equals(Object o) {
if (this == o) {
return true;
}
if (o == null || getClass() != o.getClass()){
return false;
}
Person person = (Person) o;
//两个对象是否等值,通过idCard来确定
return this.idCard == person.idCard;
}
}
public static void main(String []args){
HashMap<Person,String> map = new HashMap<Person, String>();
Person person = new Person(1234,"乔峰");
//put到hashmap中去
map.put(person,"天龙八部");
//get取出,从逻辑上讲应该能输出“天龙八部”
System.out.println("结果:"+map.get(new Person(1234,"萧峰")));
}
}
结果:null
五、总结
相关文章