HashMap
概念：key-value键值对，非线程安全，key可以为空，无序
底层：jdk1.7 数组+链表 jdk1.8数组+链表+红黑树
由来：数组的查找速度很快，但是插入和删除效率很低
链表的插入和删除的效率很低，但是查找速度很慢
HashMap，其查找速度近似O(1)。如何实现：使用了hash算法，将key映射成数组(桶bucket)下标。
key-hashCode-hash-i
如何解决hash碰撞(hash冲突)
- 增加扰动函数，减少冲突
- 冲突时，使用链地址法
源码学习
一些常量
/**
* The default initial capacity - MUST be a power of two.
*/
//默认容量
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16
/**
* The maximum capacity, used if a higher value is implicitly specified
* by either of the constructors with arguments.
* MUST be a power of two <= 1<<30.
*/
//最大容量
static final int MAXIMUM_CAPACITY = 1 << 30;
/**
* The load factor used when none specified in constructor.
*/
//默认负载因子
static final float DEFAULT_LOAD_FACTOR = 0.75f;
/**
* The bin count threshold for using a tree rather than list for a
* bin. Bins are converted to trees when adding an element to a
* bin with at least this many nodes. The value must be greater
* than 2 and should be at least 8 to mesh with assumptions in
* tree removal about conversion back to plain bins upon
* shrinkage.
*/
//当链表长度大于8时，对链表进行树化
static final int TREEIFY_THRESHOLD = 8;
/**
* The bin count threshold for untreeifying a (split) bin during a
* resize operation. Should be less than TREEIFY_THRESHOLD, and at
* most 6 to mesh with shrinkage detection under removal.
*/
//当红黑树长度小于6时，将树转换为链表
static final int UNTREEIFY_THRESHOLD = 6;
/**
* The smallest table capacity for which bins may be treeified.
* (Otherwise the table is resized if too many nodes in a bin.)
* Should be at least 4 * TREEIFY_THRESHOLD to avoid conflicts
* between resizing and treeification thresholds.
*/
// 链表树化时，hashmap的容量必须大于64
static final int MIN_TREEIFY_CAPACITY = 64;/
hash函数
取key的hascCode，将低16位与高16位异或（相同为0，不同为1），增加hash的随机性，减少hash冲突，使key分布的更均匀
static final int hash(Object key) {
int h;
return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}
tableSizeFor
扩容时，计算hashMap容量的方法，计算hashmap的最小容量，hashmap的容量比为2的n次方
16-16
15-16
/**
* Returns a power of two size for the given target capacity.
*/
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;
}
hashMap的内部变量
/**
* The table, initialized on first use, and resized as
* necessary. When allocated, length is always a power of two.
* (We also tolerate length zero in some operations to allow
* bootstrapping mechanics that are currently not needed.)
*/
//内部维护一个数组table，称作桶bucket。注意：不是所有元素都在table，存的是所有链表的头结点
transient Node<K,V>[] table;
/**
* Holds cached entrySet(). Note that AbstractMap fields are used
* for keySet() and values().
*/
//所有元素
transient Set<Map.Entry<K,V>> entrySet;
/**
* The number of key-value mappings contained in this map.
*/
// hashMap的长度，区别与容量
transient int size;
/**
* The number of times this HashMap has been structurally modified
* Structural modifications are those that change the number of mappings in
* the HashMap or otherwise modify its internal structure (e.g.,
* rehash). This field is used to make iterators on Collection-views of
* the HashMap fail-fast. (See ConcurrentModificationException).
*/
transient int modCount;
/**
* The next size value at which to resize (capacity * load factor).
*
* @serial
*/
// (The javadoc description is true upon serialization.
// Additionally, if the table array has not been allocated, this
// field holds the initial array capacity, or zero signifying
// DEFAULT_INITIAL_CAPACITY.)
int threshold;
/**
* The load factor for the hash table.
*
* @serial
*/
final float loadFactor;
hashMap的构造函数
典型的3个
- 指定容量和负载因子，阈值=大于容量的最小2的n次方
- 指定容量，负载因子=0.75f，阈值=大于容量的最小2的n次方
- 默认构造函数，负载因子=0.75。容量和阈值未初始化
/**
* Constructs an empty <tt>HashMap</tt> with the specified initial
* capacity and load factor.
*
* @param initialCapacity the initial capacity
* @param loadFactor the load factor
* @throws IllegalArgumentException if the initial capacity is negative
* or the load factor is nonpositive
*/
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);
}
/**
* Constructs an empty <tt>HashMap</tt> with the specified initial
* capacity and the default load factor (0.75).
*
* @param initialCapacity the initial capacity.
* @throws IllegalArgumentException if the initial capacity is negative.
*/
public HashMap(int initialCapacity) {
this(initialCapacity, DEFAULT_LOAD_FACTOR);
}
/**
* 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; // all other fields defaulted
}
根据key获取元素
tab[(n - 1) & hash通过hash计算元素在桶中的位置，比如容量n=16
hash = 1=>i=1
hash = 15=>i=15
hash = 16=>i=0
hash = 17=>i=1
first = tab[(n - 1) & hash = hash mod n
与操作效率大于mod操作，一个很小的优化
public V get(Object key) {
Node<K,V> e;
//计算key的hash值
//根据key的hash值去table上遍历
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 &&
//如果桶的第一元素的hash和key等于查找的元素，则返回
(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;
//查找桶的下一个元素
if ((e = first.next) != null) {
//first为树结构
if (first instanceof TreeNode)
return ((TreeNode<K,V>)first).getTreeNode(hash, key);
do {
//first为链表，则查找链表
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
return e;
} while ((e = e.next) != null);
}
}
return null;
}
插入元素
public V put(K key, V value) {
return putVal(hash(key), key, value, false, true);
}
/**
* Implements Map.put and related methods
*
* @param hash hash for key
* @param key the key
* @param value the value to put
* @param onlyIfAbsent if true, don't change existing value
* @param evict if false, the table is in creation mode.
* @return previous value, or null if none
*/
final V putVal(int hash, K key, V value, boolean onlyIfAbsent,
boolean evict) {
Node<K,V>[] tab; Node<K,V> p; int n, i;
//table为空，或者table长度为0，扩容
if ((tab = table) == null || (n = tab.length) == 0)
n = (tab = resize()).length;
//桶元素（数组上的第一个元素）为空，则直接新建一个Node并赋值到数组上
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null);
else {
Node<K,V> e; K k;
//第一个元素不为空，但是hash和key值和插入元素相等，此时将第一个元素赋值给e
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
e = p;
//第一个元素不为空，发生hash冲突，且第一个元素为树节点，此时将p节点插入到红黑树
else if (p instanceof TreeNode)
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
else {
//第一个元素不为空，发生hash冲突，且第一个元素为链表节点，此时将p节点插入到链表
for (int binCount = 0; ; ++binCount) {
//不同于jdk1.7，这里使用尾插法，将p插入到链表的最后一个节点
if ((e = p.next) == null) {
p.next = newNode(hash, key, value, null);
//如果插入后，链表的长度>8(包括桶元素)，则对链表进行树化
if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
treeifyBin(tab, hash);
break;
}
//如果再链表中找到和插入元素相等的节点，则直接跳出循环
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
break;
p = e;
}
}
//插入节点的Key在hashMap中已存在，则更新value
if (e != null) { // existing mapping for key
V oldValue = e.value;
if (!onlyIfAbsent || oldValue == null)
e.value = value;
afterNodeAccess(e);
return oldValue;
}
}
++modCount;
//如果插入节点后，hashmap的容量大于阈值（13>12），则扩容
if (++size > threshold)
resize();
afterNodeInsertion(evict);
return null;
}
扩容
关于resize链表扩容的博客，写的很详细
jdk1.8 HashMap工作原理和扩容机制(源码解析)
/**
* 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() {
Node<K,V>[] oldTab = table;
int oldCap = (oldTab == null) ? 0 : oldTab.length;
int oldThr = threshold;
int newCap, newThr = 0;
// oldCap>0，表示hashMap已经初始化了，这里是二次扩容
if (oldCap > 0) {
if (oldCap >= MAXIMUM_CAPACITY) {
threshold = Integer.MAX_VALUE;
return oldTab;
}
//newCap和newThr都*2
else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY &&
oldCap >= DEFAULT_INITIAL_CAPACITY)
newThr = oldThr << 1; // double threshold
}
//使用了初始化容量的构造器
else if (oldThr > 0) // initial capacity was placed in threshold
newCap = oldThr;
else { // zero initial threshold signifies using defaults
//使用了默认构造函数，此时newCap和newThr都取默认值
newCap = DEFAULT_INITIAL_CAPACITY;
newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);
}
//使用了初始化容量的构造器,阈值newThr=容量*loadFactor
if (newThr == 0) {
float ft = (float)newCap * loadFactor;
newThr = (newCap < MAXIMUM_CAPACITY && ft < (float)MAXIMUM_CAPACITY ?
(int)ft : Integer.MAX_VALUE);
}
threshold = newThr;
//初始化一个长度为newCap的数组newTab
@SuppressWarnings({"rawtypes","unchecked"})
Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap];
table = newTab;
if (oldTab != null) {
//将oldTab中的元素移植到newTab中
for (int j = 0; j < oldCap; ++j) {
Node<K,V> e;
if ((e = oldTab[j]) != null) {
oldTab[j] = null;
if (e.next == null)
newTab[e.hash & (newCap - 1)] = e;
else if (e instanceof TreeNode)
((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;
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);
if (loTail != null) {
loTail.next = null;
newTab[j] = loHead;
}
if (hiTail != null) {
hiTail.next = null;
newTab[j + oldCap] = hiHead;
}
}
}
}
}
return newTab;
}
删除节点
/**
* Implements Map.remove and related methods
*
* @param hash hash for key
* @param key the key
* @param value the value to match if matchValue, else ignored
* @param matchValue if true only remove if value is equal
* @param movable if false do not move other nodes while removing
* @return the node, or null if none
*/
final Node<K,V> removeNode(int hash, Object key, Object value,
boolean matchValue, boolean movable) {
Node<K,V>[] tab; Node<K,V> p; int n, index;
if ((tab = table) != null && (n = tab.length) > 0 &&
(p = tab[index = (n - 1) & hash]) != null) {
Node<K,V> node = null, e; K k; V v;
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
//删除节点是桶节点，将node节点指向该节点
node = p;
else if ((e = p.next) != null) {
//删除的节点是树节点
if (p instanceof TreeNode)
node = ((TreeNode<K,V>)p).getTreeNode(hash, key);
else {
//删除节点是链表中的某一个节点，将node系诶单你指向该节点
do {
if (e.hash == hash &&
((k = e.key) == key ||
(key != null && key.equals(k)))) {
node = e;
break;
}
p = e;
} while ((e = e.next) != null);
}
}
if (node != null && (!matchValue || (v = node.value) == value ||
(value != null && value.equals(v)))) {
//删除的节点是树节点
if (node instanceof TreeNode)
((TreeNode<K,V>)node).removeTreeNode(this, tab, movable);
//删除的节点是桶节点，将桶节点指向node节点的next节点
else if (node == p)
tab[index] = node.next;
else
//删除节点是链表的某个节点
//将删除节点的父节点指向node节点的next节点
p.next = node.next;
++modCount;
--size;
afterNodeRemoval(node);
return node;
}
}
return null;
}