HashMap和Hashtable的底层实现都是数组+链表结构实现的,这点上完全一致
添加、删除、获取元素时都是先计算hash,根据hash和table.length计算index也就是table数组的下标,然后进行相应操作,下面以HashMap为例说明下它的简单实现
/**
* HashMap的默认初始容量 必须为2的n次幂
*/
static final int DEFAULT_INITIAL_CAPACITY = 16;
/**
* HashMap的最大容量,可以认为是int的最大值
*/
static final int MAXIMUM_CAPACITY = 1 << 30;
/**
* 默认的加载因子
*/
static final float DEFAULT_LOAD_FACTOR = 0.75f;
/**
* HashMap用来存储数据的数组
*/
transient Entry[] table;
/**
* Constructs an empty <tt>HashMap</tt> with the default initial capacity
* (16) and the default load factor (0.75).
*/
public HashMap() {
this.loadFactor = DEFAULT_LOAD_FACTOR;
threshold = (int)(DEFAULT_INITIAL_CAPACITY * DEFAULT_LOAD_FACTOR);
table = new Entry[DEFAULT_INITIAL_CAPACITY];
init();
}
public V put(K key, V value) {
if (key == null)
return putForNullKey(value); //处理null值
int hash = hash(key.hashCode());//计算hash
int i = indexFor(hash, table.length);//计算在数组中的存储位置
//遍历table[i]位置的链表,查找相同的key,若找到则使用新的value替换掉原来的oldValue并返回oldValue
for (Entry<K,V> e = table[i]; e != null; e = e.next) {
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;
}
}
//若没有在table[i]位置找到相同的key,则添加key到table[i]位置,新的元素总是在table[i]位置的第一个元素,原来的元素后移
modCount++;
addEntry(hash, key, value, i);
return null;
}
void addEntry(int hash, K key, V value, int bucketIndex) {
//添加key到table[bucketIndex]位置,新的元素总是在table[bucketIndex]的第一个元素,原来的元素后移
Entry<K,V> e = table[bucketIndex];
table[bucketIndex] = new Entry<K,V>(hash, key, value, e);
//判断元素个数是否达到了临界值,若已达到临界值则扩容,table长度翻倍
if (size++ >= threshold)
resize(2 * table.length);
}
public V get(Object key) {
if (key == null)
return getForNullKey();//处理null值
int hash = hash(key.hashCode());//计算hash
//在table[index]遍历查找key,若找到则返回value,找不到返回null
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.equals(k)))
return e.value;
}
return null;
}
public V remove(Object key) {
Entry<K,V> e = removeEntryForKey(key);
return (e == null ? null : e.value);
}
final Entry<K,V> removeEntryForKey(Object key) {
int hash = (key == null) ? 0 : hash(key.hashCode());
int i = indexFor(hash, table.length);
Entry<K,V> prev = table[i];
Entry<K,V> e = prev;
while (e != null) {
Entry<K,V> next = e.next;
Object k;
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k)))) {
modCount++;
size--;
if (prev == e)
table[i] = next;
else
prev.next = next;
e.recordRemoval(this);
return e;
}
prev = e;
e = next;
}
return e;
}
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);
table = newTable;
threshold = (int)(newCapacity * loadFactor);
}
void transfer(Entry[] newTable) {
Entry[] src = table;
int newCapacity = newTable.length;
for (int j = 0; j < src.length; j++) {
Entry<K,V> e = src[j];
if (e != null) {
src[j] = null;
do {
Entry<K,V> next = e.next;
//重新对每个元素计算index
int i = indexFor(e.hash, newCapacity);
e.next = newTable[i];
newTable[i] = e;
e = next;
} while (e != null);
}
}
}
public void clear() {
modCount++;
Entry[] tab = table;
for (int i = 0; i < tab.length; i++)
tab[i] = null;
size = 0;
}
public boolean containsKey(Object key) {
return getEntry(key) != null;
}
final Entry<K,V> getEntry(Object key) {
int hash = (key == null) ? 0 : hash(key.hashCode());
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;
}
containsValue方法就比较粗暴了,就是直接遍历所有元素直到找到value,由此可见HashMap的containsValue方法本质上和普通数组和list的contains方法没什么区别,你别指望它会像containsKey那么高效
public boolean containsValue(Object value) {
if (value == null)
return containsNullValue();
Entry[] tab = table;
for (int i = 0; i < tab.length ; i++)
for (Entry e = tab[i] ; e != null ; e = e.next)
if (value.equals(e.value))
return true;
return false;
}
indexFor中的h & (length-1)就相当于h%length,用于计算index也就是在table数组中的下标
hash方法是对hashcode进行二次散列,以获得更好的散列值
为了更好理解这里我们可以把这两个方法简化为 int index= key.hashCode()/table.length,以put中的方法为例可以这样替换
int hash = hash(key.hashCode());//计算hash int i = indexFor(hash, table.length);//计算在数组中的存储位置 //上面这两行可以这样简化 int i = key.key.hashCode()%table.length;
static int hash(int h) {
// This function ensures that hashCodes that differ only by
// constant multiples at each bit position have a bounded
// number of collisions (approximately 8 at default load factor).
h ^= (h >>> 20) ^ (h >>> 12);
return h ^ (h >>> 7) ^ (h >>> 4);
}
static int indexFor(int h, int length) {
return h & (length-1);
}
原文:https://www.cnblogs.com/sweet6/p/9031372.html