HashMap原理浅谈
以下全部代码都来自jdk1.8源码HashMap.java
源码阅读一
HashMap其中部分源码
// 默认初始化数组大小
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16
// 最大容量
static final int MAXIMUM_CAPACITY = 1 << 30;
// 默认负载因子
static final float DEFAULT_LOAD_FACTOR = 0.75f;
// 转化成红黑树的链表大小的阈值
static final int TREEIFY_THRESHOLD = 8;
// 取消红黑树结构的最小阈值
static final int UNTREEIFY_THRESHOLD = 6;
// 为了避免调整大小和树化阈值之间的冲突，阈值不能高于4 * TREEIFY_THRESHOLD
static final int MIN_TREEIFY_CAPACITY = 64;
...
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);
}
从HashMap的构造函数来看，初始化数组大小和负载因子是可以指定的
源码阅读二
HashMap底层究竟是什么构成的
// 节点数组
transient Node<K,V>[] table;
...
// 节点结构，单链表
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;
}
...
}
...
// 树节点
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);
}
...
}
从代码可以看出，底层是由数组+链表+树构成
阅读源码三
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;
if ((tab = table) == null || (n = tab.length) == 0)
n = (tab = resize()).length;
// 判断节点数组的长度
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null);
// 如果经过hash的索引，添加一个新的节点
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);
// 判断如果是变成树的结构，就需要以树的形式添加
else {
for (int binCount = 0; ; ++binCount) {
if ((e = p.next) == null) {
p.next = newNode(hash, key, value, null);
// 如果链表的数量达到了8，就转化成树结构
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
// 存在key,更新value
V oldValue = e.value;
if (!onlyIfAbsent || oldValue == null)
e.value = value;
afterNodeAccess(e);
return oldValue;
}
}
++modCount;
if (++size > threshold)
resize();
// 扩容
afterNodeInsertion(evict);
return null;
}
put过程分析：
- 判断节点数组的长度
- 如果没有哈希冲突则添加第一个节点，如果哈希冲突则链接节点，如果链表长度超过8，则转化成树；由源码可知，哈希公式：index = HashCode（Key） & （Length - 1）。
- 如果已经存在key，则替换旧的value
阅读源码四
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;
}
get过程分析：
- 由key计算出哈希值
- 每次都要检查第一个节点，判断是链表节点还是树节点
- 如果是链表则链表寻找，如果是树则树寻找
阅读源码五
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) {
// 判断有没有超过最大值，如果没有，返回原数组
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);
// 新的阈值，负载因子*初始值
}
if (newThr == 0) {
float ft = (float)newCap * loadFactor;
newThr = (newCap < MAXIMUM_CAPACITY && ft < (float)MAXIMUM_CAPACITY ?
(int)ft : Integer.MAX_VALUE);
// 如果没有超过最大容量，则将扩容值更新
}
threshold = newThr;
@SuppressWarnings({"rawtypes","unchecked"})
Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap];
// 创建一个新的数组对象
table = newTab;
// 更新新的阈值
if (oldTab != null) {
// 将旧的数组的数据，按照规则迁移到新的数组上
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;
}
扩容过程分析：
- 判断有没有超过最大值，如果没有，返回原数组，有则进行扩容
- 计算新的扩容量大小，newCap = oldCap << 1，扩大一倍
- 创建新的数组
- 将旧的数组的数据，按照规则迁移到新的数组上
- 返回新数组
图解过程
put过程
初始一个新的数组
put(k1, v1)
put(k2, v2)
put(k3, v3)
k1和k2没有哈希冲突，k1和k3有哈希冲突
get过程
get(k2),计算出k2的哈希值，根据索引寻找，进行key值判断
get(k3)，计算出k3的哈希值，根据索引寻找，进行key值判断
扩容过程
根据HashMap.Size >= Capacity * LoadFactor公式，达到了扩容条件，6>=8*0.75
创建一个新的数组，old<<1的大小，根据规则重新赋值
多线程问题
总结
- HashMap是一个用于存储Key-Value键值对的集合
- 底层由数组、链表、红黑树组成
- 初始容量为8，负载因子时0.75
- 线程不安全，可能出现链表循环
ps：能力有限，如有错误，请大家积极指出，谢谢！
关注CSDN
