HashMap jdk1.7
三个基础变量
//必须是2的幂次方,初始大小为16
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16
//装载的元素/容量
static final int MAXIMUM_CAPACITY = 1 << 30;
static final float DEFAULT_LOAD_FACTOR = 0.75f
//数量到达阈值时扩容,大小为装载因子乘以capacity
int threshold;
为什么默认容量必须是2的幂次方?
答:hashcode&(length-1)bu
容量是2的幂次方 length-1 所有位都是1,可以减少hash碰撞
如果与的某一位为0,那么与这一位与永远不能得到1,那么某些位置就永远空出来
初始化
初始化容量和装载因子
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;
threshold = initialCapacity;
init();
}
节点信息
1.7以前是用entry对象存储信息
本质上是一个entry数组
static class Entry<K,V> implements Map.Entry<K,V> {
final K key;
V value;
Entry<K,V> next;//下一节点
int hash;//hash值
/**
* Creates new entry.
*/
Entry(int h, K k, V v, Entry<K,V> n) {
value = v;
next = n;
key = k;
hash = h;
}
略
/**
* Adds a new entry with the specified key, value and hash code to
* the specified bucket. It is the responsibility of this
* method to resize the table if appropriate.
*
* Subclass overrides this to alter the behavior of put method.
*/
//加入一个新的对象
void addEntry(int hash, K key, V value, int bucketIndex) {
if ((size >= threshold) && (null != table[bucketIndex])) {
resize(2 * table.length);
hash = (null != key) ? hash(key) : 0;
bucketIndex = indexFor(hash, table.length);
}
createEntry(hash, key, value, bucketIndex);
}
/**
* Like addEntry except that this version is used when creating entries
* as part of Map construction or "pseudo-construction" (cloning,
* deserialization). This version needn't worry about resizing the table.
*
* Subclass overrides this to alter the behavior of HashMap(Map),
* clone, and readObject.
*/
//新建节点
void createEntry(int hash, K key, V value, int bucketIndex) {
Entry<K,V> e = table[bucketIndex];
table[bucketIndex] = new Entry<>(hash, key, value, e);
size++;
}
put方法
头插法
public V put(K key, V value) {
//当table不存在的时候
if (table == EMPTY_TABLE) {
inflateTable(threshold);
}
//key为null 插入为0的桶里有且只能有一个空值
if (key == null)
return putForNullKey(value);
int hash = hash(key);
int i = indexFor(hash, table.length);
//插入的key已经存在
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))) {
//替换旧数据为新数据
V oldValue = e.value;
e.value = value;
e.recordAccess(this);
return oldValue;
}
}
modCount++;
addEntry(hash, key, value, i);
return null;
}
inflateTable方法
/**
* Inflates the table.
* table扩张
*/
private void inflateTable(int toSize) {
// Find a power of 2 >= toSize
//不管初始容量设的是不是2的幂次,都会自动转为2的幂次
int capacity = roundUpToPowerOf2(toSize);
//扩张的阈值为capacity*loadFactor
threshold = (int) Math.min(capacity * loadFactor, MAXIMUM_CAPACITY + 1);
//table是一个Entry数组
table = new Entry[capacity];
initHashSeedAsNeeded(capacity);
}
table是一个Entry数组
不管初始容量设的是不是2的幂次,都会自动转为2的幂次
插入空值的方法
private V putForNullKey(V value) {
for (Entry<K,V> e = table[0]; e != null; e = e.next) {
if (e.key == null) {
V oldValue = e.value;
e.value = value;
e.recordAccess(this);
return oldValue;
}
}
modCount++;
addEntry(0, null, value, 0);
return null;
}
空值只能插入到位于0的bucket。且只能有一个,再次插入会覆盖value
hash
null的hash值永远为0
算出来的hash值进行右移,异或之后,让高位也参与运算,减少hash碰撞
final int hash(Object k) {
int h = hashSeed;
if (0 != h && k instanceof String) {
return sun.misc.Hashing.stringHash32((String) k);
}
h ^= k.hashCode();
// 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);
}
indexFor()除法hash
为什么容量必须是2的非0幂次方的原因
static int indexFor(int h, int length) {
// assert Integer.bitCount(length) == 1 : "length must be a non-zero power of 2";
return h & (length-1);
}
addEntry()
当元素的数目大于threshold=capacity*loadFactor 时,2倍扩容,为什么2倍等价于capacity必须是2的非0幂次方 index=hash&(length-1)
1.7扩容后的元素迁移是重新计算一次hash
void addEntry(int hash, K key, V value, int bucketIndex) {
//需要扩容就进行迁移
if ((size >= threshold) && (null != table[bucketIndex])) {
resize(2 * table.length);
hash = (null != key) ? hash(key) : 0;
bucketIndex = indexFor(hash, table.length);
}
createEntry(hash, key, value, bucketIndex);
}
resize()
void resize(int newCapacity) {
Entry[] oldTable = table;
int oldCapacity = oldTable.length;
//越界情况
if (oldCapacity == MAXIMUM_CAPACITY) {
threshold = Integer.MAX_VALUE;
return;
}
Entry[] newTable = new Entry[newCapacity];
//旧表迁移到新表
transfer(newTable, initHashSeedAsNeeded(newCapacity));
table = newTable;
threshold = (int)Math.min(newCapacity * loadFactor, MAXIMUM_CAPACITY + 1);
}
transfer()
旧表迁移到新表,重新计算hash值
void transfer(Entry[] newTable, boolean rehash) {
int newCapacity = newTable.length;
for (Entry<K,V> e : table) {
while(null != e) {
Entry<K,V> next = e.next;
if (rehash) {
e.hash = null == e.key ? 0 : hash(e.key);
}
//重新计算hash值
int i = indexFor(e.hash, newCapacity);
e.next = newTable[i];
newTable[i] = e;
e = next;
}
}
}
put 方法总结
put(){
//1.放入空值的方法
putForNullKey();
//2.计算hash值
indexforhash();
//3.插入已存在值得处理
返回旧的值
//4.添加新节点
//i是插入的位置
addEntry(hash, key, value, i){
//1.对象个数大于threshold或者发生碰撞时扩容
resize(){
//迁移数据
transfer()
头插法
}
}
newEntry() 头插法
}
1.7问题
循环链表问题
1.丢失数据 数据5丢失
2.链表成环
图片来源马士兵公开课