一、HashMap
Map是无序、以key-value的键值对形式存储元素的集合，键不可重复，值无要求，重复的键对应的值会覆盖之前的值。
1. 数据结构是什么
jdk1.7中为数组 + 链表
jdk1.8中为数组 + 链表 + 红黑树
2. 核心属性
- 基本属性
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // 初始容量，默认为16
static final int MAXIMUM_CAPACITY = 1 << 30; //最大容量
static final float DEFAULT_LOAD_FACTOR = 0.75f; //负载因子0.75，扩容的触发
static final int TREEIFY_THRESHOLD = 8; // 链表转换成红黑树的条件
static final int UNTREEIFY_THRESHOLD = 6; //红黑树转换成链表的条件之一
static final int MIN_TREEIFY_CAPACITY = 64; //变成红黑树时容量至少为64
transient Node<K,V>[] table; //存数据的Node数组
transient Set<Map.Entry<K,V>> entrySet;
transient int size;
transient int modCount;
int threshold;
final float loadFactor;
- 构造方法
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 HashMap(int initialCapacity) {
this(initialCapacity, DEFAULT_LOAD_FACTOR);
}
public HashMap() {
this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted
}
public HashMap(Map<? extends K, ? extends V> m) {
this.loadFactor = DEFAULT_LOAD_FACTOR;
putMapEntries(m, false);
}
- 内部类
//节点内部类
static class Node<K,V> implements Map.Entry<K,V> {
final int hash; //哈希值
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;
}
}
//EntrySet 内部类
final class EntrySet extends AbstractSet<Map.Entry<K,V>> {
public final int size() { return size; }
public final void clear() { HashMap.this.clear(); }
public final Iterator<Map.Entry<K,V>> iterator() {
return new EntryIterator();
}
public final boolean contains(Object o) {
if (!(o instanceof Map.Entry))
return false;
Map.Entry<?,?> e = (Map.Entry<?,?>) o;
Object key = e.getKey();
Node<K,V> candidate = getNode(hash(key), key);
return candidate != null && candidate.equals(e);
}
public final boolean remove(Object o) {
if (o instanceof Map.Entry) {
Map.Entry<?,?> e = (Map.Entry<?,?>) o;
Object key = e.getKey();
Object value = e.getValue();
return removeNode(hash(key), key, value, true, true) != null;
}
return false;
}
public final Spliterator<Map.Entry<K,V>> spliterator() {
return new EntrySpliterator<>(HashMap.this, 0, -1, 0, 0);
}
public final void forEach(Consumer<? super Map.Entry<K,V>> action) {
Node<K,V>[] tab;
if (action == null)
throw new NullPointerException();
if (size > 0 && (tab = table) != null) {
int mc = modCount;
for (int i = 0; i < tab.length; ++i) {
for (Node<K,V> e = tab[i]; e != null; e = e.next)
action.accept(e);
}
if (modCount != mc)
throw new ConcurrentModificationException();
}
}
}
3. 核心方法
//当key不为null的时候通过object的hashCode方法生成哈希值并且右移16位
static final int hash(Object key) {
int h;
return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}
//传入给定的容量值，改成临近的2的n次方
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;
}
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;
}
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;
}
put方法：
public V put(K key, V value) {
return putVal(hash(key), key, value, false, true);
}
final V putVal(int hash, K key, V value, boolean onlyIfAbsent,
boolean evict) {
Node<K,V>[] tab; Node<K,V> p; int n, i;
//1. 判断数组需不需要初始化
if ((tab = table) == null || (n = tab.length) == 0)
n = (tab = resize()).length;
//2. 判断传入的key计算完hash后所在的位置的节点是不是为空，如果为空则新建节点
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null);
//3. 到这说明传入的key所在的位置已经有节点了
else {
//4. 如果传入的key 和当前节点的key相等，则 覆盖。
Node<K,V> e; K k;
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
e = p;
// 5. 如果节点p是树的节点，调用相关方法放入
else if (p instanceof TreeNode)
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
else {
//6. 节点p是链表的节点，放入最后并判断是否需要进行树化
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;
}
}
//存在相同的 key,那就需要将值覆盖
if (e != null) { // existing mapping for key
V oldValue = e.value;
if (!onlyIfAbsent || oldValue == null)
e.value = value;
afterNodeAccess(e);
return oldValue;
}
}
++modCount;
//如果容量超过了阈值，进行扩容
if (++size > threshold)
resize();
afterNodeInsertion(evict);
return null;
}
/**
* Initializes or doubles table size. If null, allocates in
* accord with initial capacity target held in field threshold.
* Otherwise, because we are using power-of-two expansion, the
* elements from each bin must either stay at same index, or move
* with a power of two offset in the new table.
*
* @return the table
*/
final Node<K,V>[] resize() {
//获取旧数组的引用
Node<K,V>[] oldTab = table;
int oldCap = (oldTab == null) ? 0 : oldTab.length;
int oldThr = threshold;
int newCap, newThr = 0;
if (oldCap > 0) {
//当健值容量已经达到最大
if (oldCap >= MAXIMUM_CAPACITY) {
threshold = Integer.MAX_VALUE;
return oldTab;//直接返回数组最大值
}
//没有超过最大值，扩充为原来的2倍
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
//初始化容量赋值阀值
newCap = oldThr;
else { // zero initial threshold signifies using defaults
newCap = DEFAULT_INITIAL_CAPACITY; // 初始化默认值
newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);
}
//新的阀值==0重新resize
if (newThr == 0) {
float ft = (float)newCap * loadFactor;
newThr = (newCap < MAXIMUM_CAPACITY && ft < (float)MAXIMUM_CAPACITY ?
(int)ft : Integer.MAX_VALUE);
}
//重新给阀值赋值
threshold = newThr;
@SuppressWarnings({"rawtypes","unchecked"})
//建立新的数组
Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap];
table = newTab;
if (oldTab != null) {
//把每个桶里的数据转移到新的桶里
for (int j = 0; j < oldCap; ++j) {
Node<K,V> e;
//给e赋值
if ((e = oldTab[j]) != null) {
oldTab[j] = null;//清除老数组的索引
if (e.next == null)
//重新生成下标并把数据放入对应下标数组里
newTab[e.hash & (newCap - 1)] = e;
else if (e instanceof TreeNode)//给红黑树赋值
((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;
//原索引
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);
//原索引放到桶里
if (loTail != null) {
loTail.next = null;
newTab[j] = loHead;
}
//原索引+oldcap放到桶里
if (hiTail != null) {
hiTail.next = null;
newTab[j + oldCap] = hiHead;
}
}
}
}
}
return newTab;
}
get方法：
public V get(Object key) {
Node<K,V> e;
return (e = getNode(hash(key), key)) == null ? null : e.value;
}
/**
* Implements Map.get and related methods.
*
* @param hash hash for key
* @param key the key
* @return the node, or null if none
*/
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;
}
4. 为什么容量为2的n次方？
取余(%)操作中如果除数是 2 的幂次则等价于与其除数减一的与(&)操作（也就是说 hash%length==hash&(length-1)的前提是 length 是 2 的 n 次方；）。”并且 **采用二进制位操作 &，相对于%能够提高运算效率，这就解释了 HashMap 的长度为什么是 2 的幂次方。
5. 为什么树化和链化的阈值不一样？
首先红黑树优势增删改查效率高链表数据量很大的事情如果通过红黑树进行操作会提高行能。
但是链表转换红黑树是耗时操作需要链表的遍历和红黑树的插入,转换后的性能要大于成本才算合理,阀值设置8应该是开发工程严格进行系统测试均衡时间和空间复杂度后得出的值。
