HashMap源码分析
2017-09-09 本文已影响0人
ZcEDiaos
HashMap概述
HashMap是基于Hash表的Map接口的实现，以key-value的形式实现。在添加或查找时，HashMap 会计算key的hash来确定当前key所在的哈希槽来确定key-value键值对所在的位置。在哈希槽内，产生碰撞的元素以链表的方式存储，当链表的长度大于8时，产生碰撞的元素可能会以红黑树的方式进行存储。相比较与之前版本的HashMap，1.8版本的HashMap变得比较难，目前也只是以我拥有的能力对其尽行解读。等日后有能力了，估计会再度一遍。
HashMap源码分析
- 定义
public class HashMap<K,V> extends AbstractMap<K,V>
implements Map<K,V>, Cloneable, Serializable {
从该类的定义中可以看出该类实现了Cloneable、Serializable接口，该类可以进行克隆、序列化
- 属性
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16
static final int MAXIMUM_CAPACITY = 1 << 30;
static final float DEFAULT_LOAD_FACTOR = 0.75f;
static final int TREEIFY_THRESHOLD = 8;
static final int UNTREEIFY_THRESHOLD = 6;
static final int MIN_TREEIFY_CAPACITY = 64;
static class Node<K,V> implements Map.Entry<K,V> {
final int hash;
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;
}
}
static final class TreeNode<K,V> extends LinkedHashMap.Entry<K,V> {
TreeNode<K,V> parent; // red-black tree links
TreeNode<K,V> left;
TreeNode<K,V> right;
TreeNode<K,V> prev; // needed to unlink next upon deletion
boolean red;
TreeNode(int hash, K key, V val, Node<K,V> next) {
super(hash, key, val, next);
}
}
该类的属性定义包括初始容量、负载因子、红黑树化的阈值，取消红黑树化的阈值
- 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(Map<? extends K, ? extends V> m) {
this.loadFactor = DEFAULT_LOAD_FACTOR;
putMapEntries(m, false);
}
public HashMap() {
this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted
}
public HashMap(int initialCapacity) {
this(initialCapacity, DEFAULT_LOAD_FACTOR);
}
public HashMap(): 按默认参数构造一个空的HashMap
public HashMap(Map<? extends K, ? extends V> m):构造一个包含指定map的HashMap
public HashMap(int initialCapacity, float loadFactor):按照给定的参数构造一个空HashMap
public HashMap(int initialCapacity):按照给定的参数构造一个空HashMap
- 添加
final V putVal(int hash, K key, V value, boolean onlyIfAbsent,
boolean evict) {
Node<K,V>[] tab; Node<K,V> p; int n, i;
if ((tab = table) == null || (n = tab.length) == 0)
n = (tab = resize()).length;
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null);
else {
Node<K,V> e; K k;
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
e = p;
else if (p instanceof TreeNode)
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
else {
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;
}
}
if (e != null) { // existing mapping for key
V oldValue = e.value;
if (!onlyIfAbsent || oldValue == null)
e.value = value;
afterNodeAccess(e);
return oldValue;
}
}
++modCount;
if (++size > threshold)
resize();
afterNodeInsertion(evict);
return null;
}
HashMap的核心添加方法，先通过hash算法的到key-value应该插入的槽，如果槽内的元素为空，则直接添加，如果不为空，判断槽内的元素数量是否为红黑树，如果为红黑树，则调用红黑树的添加算法、如果不为红黑树，则遍历元素的数量并插入到最后一个未知，如果加上插入后的元素，槽内的元素数量大于8，则将链表变为红黑树。最后，判断key-value的数量是否大于阈值，如果大于阈值，则进行扩容。
- 删除
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))))
node = p;
else if ((e = p.next) != null) {
if (p instanceof TreeNode)
node = ((TreeNode<K,V>)p).getTreeNode(hash, key);
else {
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)))) {
if (node instanceof TreeNode)
((TreeNode<K,V>)node).removeTreeNode(this, tab, movable);
else if (node == p)
tab[index] = node.next;
else
p.next = node.next;
++modCount;
--size;
afterNodeRemoval(node);
return node;
}
}
return null;
}
HashMap的核心删除方法，通过hash算法得到对应的节点，如果节点是红黑树，则调用红黑树的删除方法。如果不是，就调用链表的删除方法。
- 查找
public boolean containsValue(Object value) {
Node<K,V>[] tab; V v;
if ((tab = table) != null && size > 0) {
for (int i = 0; i < tab.length; ++i) {
for (Node<K,V> e = tab[i]; e != null; e = e.next) {
if ((v = e.value) == value ||
(value != null && value.equals(v)))
return true;
}
}
}
return false;
}
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;
}
查找是否包含某值：遍历所有的节点进行查找
按键查找：通过哈希算法得到对应的哈希槽，从哈希槽中查找相应的key
- 迭代
会触发fail-fast机制。 - 扩容
final Node<K,V>[] resize() {
Node<K,V>[] oldTab = table;
int oldCap = (oldTab == null) ? 0 : oldTab.length;
int oldThr = threshold;
int newCap, newThr = 0;
if (oldCap > 0) {
if (oldCap >= MAXIMUM_CAPACITY) {
threshold = Integer.MAX_VALUE;
return oldTab;
}
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
newCap = oldThr;
else { // zero initial threshold signifies using defaults
newCap = DEFAULT_INITIAL_CAPACITY;
newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);
}
if (newThr == 0) {
float ft = (float)newCap * loadFactor;
newThr = (newCap < MAXIMUM_CAPACITY && ft < (float)MAXIMUM_CAPACITY ?
(int)ft : Integer.MAX_VALUE);
}
threshold = newThr;
@SuppressWarnings({"rawtypes","unchecked"})
Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap];
table = newTab;
if (oldTab != null) {
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;
}
将容量扩充为原来的两倍，接下来就是转移了，后面的代码没看懂。
HashMap 使用过程中的注意点
- hashmap 在扩容的过程中会产生复制，会造成性能影响，在数据确定的情况下，一定要设置好hashmap的容量。
- hashmap 的容量为什么是2的整数幂，h&(length-1)相当于对length取模，为了减少碰撞和提高效率。
如果length为偶数 lenght-1 则为奇数，h&(length-1)的最后一位可以为0或1
如果length为奇数 lenght-1 则为偶数，h&(length-1)的最后一位只能为0，所有下标为奇数的插槽将被浪费。 - hashmap的死循环 关于这点可以查看疫苗：JAVA HASHMAP的死循环
