面试必备--手撕HashMap源码

HashMap在jdk1.8里的存储结构是数组加 链表 或者 红黑树。具体需要看整个HashMap的长度是否达到最小树化容量阈值(MIN_TREEIFY_CAPACITY默认64)和链表的长度是否达到树化阈值(TREEIFY_THRESHOLD默认是8)。
文章中还会讲到hashmap如何扩容 和 为什么要这么扩容等硬核知识。
HashMap涉及到的树化操作我会在后面单独写一篇关于红黑树的文章来分析。
好的，那么下面我为大家分析几个常用的HashMap方法。

1、HashMap()

/**
* Constructs an empty <tt>HashMap</tt> with the specified initial
* capacity and load factor.
* 初始化hashmap
*
* @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);
//如果扩容大小超过了最大值，则直接赋值最大值
if (initialCapacity > MAXIMUM_CAPACITY)
initialCapacity = MAXIMUM_CAPACITY;
if (loadFactor <= 0 || Float.isNaN(loadFactor))
throw new IllegalArgumentException("Illegal load factor: " + loadFactor);
//负载因子
this.loadFactor = loadFactor;
//扩容阈值
this.threshold = tableSizeFor(initialCapacity);
}

2、get()

/**
* Returns the value to which the specified key is mapped,
* or {@code null} if this map contains no mapping for the key.
*
* <p>More formally, if this map contains a mapping from a key
* {@code k} to a value {@code v} such that {@code (key==null ? k==null :
* key.equals(k))}, then this method returns {@code v}; otherwise
* it returns {@code null}.  (There can be at most one such mapping.)
*
* <p>A return value of {@code null} does not <i>necessarily</i>
* indicate that the map contains no mapping for the key; it's also
* possible that the map explicitly maps the key to {@code null}.
* The {@link #containsKey containsKey} operation may be used to
* distinguish these two cases.
*
* @see #put(Object, Object)
*/
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) {
//tab: 引用当前hashmap的散列表
//first: 桶位中的头元素
//e: 临时node元素
//n: table数组长度
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) {
//第一种情况：定位出来的桶位元素，即为需要get的数据
if (first.hash == hash && // always check first node
((k = first.key) == key || (key != null && key.equals(k))))
return first;
//说明当前桶位不止一个元素，可能是 链表 或者 红黑树
if ((e = first.next) != null) {
//第二种情况，桶位升级成为 红黑树
if (first instanceof TreeNode)
return ((TreeNode<K,V>)first).getTreeNode(hash, key);
//第三种情况，桶位升级成为 链表
do {
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
return e;
} while ((e = e.next) != null);
}
}
return null;
}

3、put()

/**
* Associates the specified value with the specified key in this map.
* If the map previously contained a mapping for the key, the old
* value is replaced.
*
* @param key key with which the specified value is to be associated
* @param value value to be associated with the specified key
* @return the previous value associated with <tt>key</tt>, or
*         <tt>null</tt> if there was no mapping for <tt>key</tt>.
*         (A <tt>null</tt> return can also indicate that the map
*         previously associated <tt>null</tt> with <tt>key</tt>.)
*/
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
*
* 路由算法：(n - 1) & hash
*/
final V putVal(int hash, K key, V value, boolean onlyIfAbsent,
boolean evict) {
//tab: 引用当前HashMap的散列表
//p: 表示当前散列表的元素
//n: 表示散列表数组的长度
//i: 表示路由寻址的结果(返回的下标)
Node<K,V>[] tab; Node<K,V> p; int n, i;

//延时初始化hashmap，第一次调用putVal方法时会初始化hashmap对象中最低耗费内存的散列表
if ((tab = table) == null || (n = tab.length) == 0)
n = (tab = resize()).length;

//最简单的一种情况：寻址到的桶位刚好是null，这个时候，直接将当前k-v => node放进散列表中
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null);

else {
//e: 如果不为null，表示找到了一个与当前要插入的 k-v 一致的key的元素
//k: 表示临时的一个key
Node<K,V> e; K k;

//表示桶位中的元素与当前需要插入的元素的key完全一致，即将进行替换操作
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
e = p;
//判断是否是树状，如果是则按红黑树的方式插入
else if (p instanceof TreeNode)
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);

//链表的情况，而且链表的头元素与需要插入的元素不一致
else {
//链表方式插入需要逐个遍历key是否相等
// 是：替换原有的value
// 否：在末尾插入
for (int binCount = 0; ; ++binCount) {
//条件成立的话，说明已经遍历到末尾了，并且没有找到一个与需要插入的元素的key一致的表内元素
//说明需要在链表的末尾插入元素
if ((e = p.next) == null) {
p.next = newNode(hash, key, value, null);
//条件成立的话，说明当前链表的长度达到树化的标准，需要进行树化
if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
//树化操作
treeifyBin(tab, hash);
break;
}
// 条件成立的话，说明找到了与表内key一致的元素，跳出循环准备进行替换
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
break;
//把next元素赋值给p，一直到末尾
p = e;
}
}

//两种情况下会执行这段代码
//1.桶位中的元素与需要插入的元素的key一致
//2.链表中的元素与需要插入的元素的key一致
//此时e中的值为已经存在于hashmap中的值，即准备要被替换的元素
if (e != null) { // existing mapping for key
V oldValue = e.value;
if (!onlyIfAbsent || oldValue == null)
e.value = value;
//将需要插入的元素插入到表尾
afterNodeAccess(e);
return oldValue;
}
}
//modCount 表示散列表结构被修改的次数，替换node元素的value不计数
++modCount;
//插入新元素，size自增，如果自增后的值大于扩容阈值，需要触发扩容
if (++size > threshold)
resize();
afterNodeInsertion(evict);
return null;
}

4、remove()

/**
* Removes the mapping for the specified key from this map if present.
*
* @param  key key whose mapping is to be removed from the map
* @return the previous value associated with <tt>key</tt>, or
*         <tt>null</tt> if there was no mapping for <tt>key</tt>.
*         (A <tt>null</tt> return can also indicate that the map
*         previously associated <tt>null</tt> with <tt>key</tt>.)
*/
public V remove(Object key) {
Node<K,V> e;
return (e = removeNode(hash(key), key, null, false, true)) == null ? null : e.value;
}

/**
* 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 如果为ture，则需要匹配key和value都相等才删除；如果为false，则只需要匹配key相等
* @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) {
//tab: 引用当前hashmap的散列表
//p: 当前node元素
//n: table数组的长度
//index: 计算出的桶位位置
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) {
//说明路由的桶位是有数据的，需要进行查找操作，并且删除
//node: 查找到的元素
//e: 当前node的next元素
Node<K,V> node = null, e; K k; V v;
//第一种情况：当前桶位中的头元素即为需要删除的元素
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
node = p;
else if ((e = p.next) != null) {
//第二种情况：当前桶位中的元素升级为红黑树
if (p instanceof TreeNode)
node = ((TreeNode<K,V>)p).getTreeNode(hash, key);
//第三种情况：当前桶位中的元素升级为链表
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);
}
}

//如果node有值，则进入删除逻辑
//||操作 若运算符左边为true，则不再对运算符右侧进行运算
//matchValue == false，直接返回true，不需要执行后面的判断
//matchValue == true，执行 (v = node.value) == value 的判断是否true，如果为false则继续下一个操作的判断，为true返回，以此类推。
if (node != null && (!matchValue || (v = node.value) == value || (value != null && value.equals(v)))) {
//第一种情况：node是树节点，说明需要进行树节点移除操作
if (node instanceof TreeNode)
((TreeNode<K,V>)node).removeTreeNode(this, tab, movable);
//第二种情况：桶位元素即为需要删除的元素，则将该元素的下一位元素放至桶位中
else if (node == p)
tab[index] = node.next;
//第三种情况：将当前元素p的下一个元素 设置成 要删除元素的下一个元素
else
p.next = node.next;

++modCount;
--size;
afterNodeRemoval(node);
return node;
}
}
return null;
}

5、resize()

/**
* 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.
*
* 为什么需要扩容？
* 为了解决哈希冲突导致的链化影响查询效率的问题，扩容会缓解该问题
*
* @return the table
*/
final Node<K,V>[] resize() {
//oldTab: 引用扩容前的哈希表
Node<K,V>[] oldTab = table;
//oldCap: 引用扩容前哈希表数组长度
int oldCap = (oldTab == null) ? 0 : oldTab.length;
//oldThr: 引用扩容前哈希表的扩容阈值
int oldThr = threshold;
//newCap: 扩容后哈希表数组的长度
//newThr: 扩容后哈希表触发下次扩容的阈值
int newCap, newThr = 0;

//条件如果成立说明 hashmap中的散列表已经初始化过了，这是一次正常的扩容
if (oldCap > 0) {
//扩容之前的哈希表大小已经达到最大阈值后，则不扩容，且设置扩容条件为int的最大值
if (oldCap >= MAXIMUM_CAPACITY) {
threshold = Integer.MAX_VALUE;
return oldTab;
}
//oldCap左移一位实现数值翻倍，并赋值给newCap，newCap大小<数组最大值限制 且 扩容前的阈值 >= 16(默认阈值)
//这种情况下，下一次扩容的阈值 等于当前阈值翻倍
else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY && oldCap >= DEFAULT_INITIAL_CAPACITY)
newThr = oldThr << 1; // double threshold
}

//oldCap == 0，说明hashmap中的散列表是null
//1.new HashMap(initCap,loadFactor)
//2.new HashMap(initCap)
//3.new HashMap(map)，并且这个map有数据
else if (oldThr > 0) // initial capacity was placed in threshold
newCap = oldThr;

//oldCap == 0，oldThr == 0
//new HashMap()
else {               // zero initial threshold signifies using defaults
newCap = DEFAULT_INITIAL_CAPACITY;
newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);
}

//上面步骤没有为newCap赋值的情况都会执行这段代码
//通过newCap和loadFactor计算出newThr
if (newThr == 0) {
float ft = (float)newCap * loadFactor;
newThr = (newCap < MAXIMUM_CAPACITY && ft < (float)MAXIMUM_CAPACITY ?
(int)ft : Integer.MAX_VALUE);
}

threshold = newThr;
//创建出一个更大的数组
@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) {
//当前node节点
Node<K,V> e;
if ((e = oldTab[j]) != null) {
//方便jvm GC时回收内存
oldTab[j] = null;
//第一种情况：当前桶位只有一个元素，从未发生过碰撞
//计算出此元素在新哈希表中的位置，并放入
if (e.next == null)
newTab[e.hash & (newCap - 1)] = e;
//第二种情况：桶位已经树化
else if (e instanceof TreeNode)
((TreeNode<K,V>)e).split(this, newTab, j, oldCap);
//第三种情况：桶位已经形成链表
else { // preserve order
//低位链表：存放在扩容之后的数组的下标位置，与当前数组的下标位置一致
Node<K,V> loHead = null, loTail = null;
//高位链表：存放在扩容之后的数组的下标位置为 当前数组下标位置 + 扩容前数组的长度
Node<K,V> hiHead = null, hiTail = null;
//表示当前链表的下一个元素
Node<K,V> next;
do {
next = e.next;
//hash -> .... 1 1111
//hash -> .... 0 1111
//oldCap -> 0b 1 0000
//如果e.hash & oldCap == 0，则放入低位链表中
if ((e.hash & oldCap) == 0) {
if (loTail == null)
//第一次进入，将此节点设置为头结点
loHead = e;
else
//将节点插入到链表末尾
loTail.next = e;
//将指针指向最后一个元素
loTail = e;
}
//如果e.hash & oldCap != 0，则放入高位链表中
else {
if (hiTail == null)
//第一次进入，将此节点设置为头结点
hiHead = e;
else
//将节点插入到链表末尾
hiTail.next = e;
//将指针指向最后一个元素
hiTail = e;
}
} while ((e = next) != null);

if (loTail != null) {
//此时loTail是指向低位链表的最后一个元素，next可能会指向旧关系的节点，因此需要置为null
loTail.next = null;
//将低位链表的头指针赋值给新哈希表对应桶位上
newTab[j] = loHead;
}
if (hiTail != null) {
//此时hiTail是指向低位链表的最后一个元素，next可能会指向旧关系的节点，因此需要置为null
hiTail.next = null;
//将高位链表的头指针赋值给新哈希表对应桶位上
newTab[j + oldCap] = hiHead;
}
}
}
}
}
return newTab;
}

6、hash()

/**
* Computes key.hashCode() and spreads (XORs) higher bits of hash
* to lower.  Because the table uses power-of-two masking, sets of
* hashes that vary only in bits above the current mask will
* always collide. (Among known examples are sets of Float keys
* holding consecutive whole numbers in small tables.)  So we
* apply a transform that spreads the impact of higher bits
* downward. There is a tradeoff between speed, utility, and
* quality of bit-spreading. Because many common sets of hashes
* are already reasonably distributed (so don't benefit from
* spreading), and because we use trees to handle large sets of
* collisions in bins, we just XOR some shifted bits in the
* cheapest possible way to reduce systematic lossage, as well as
* to incorporate impact of the highest bits that would otherwise
* never be used in index calculations because of table bounds.
*
* 1.7 是用key的hash值与低位进行 & 运算，这样会使得到的下标不够散列
* 1.8 是用key的hash值与高位进行 & 运算，这样会让得到的下标更加散列
*
* 由于1.7 hash 和（length-1）运算，length 绝大多数情况小于2的16次方。
* 所以始终是hashcode 的低16位（甚至更低）参与运算。
* 要是高16位也参与运算，会让得到的下标更加散列。
* 因此1.8先通过 h >>> 16 获取key的高位 然后再与key的hash值进行 ^ 运算
* 用 ^ 运算是因为 &和|都会使得结果偏向0或者1 ,并不是均匀的概念,所以用 ^
*/
static final int hash(Object key) {
int h;
//如果传入的key为null则会默认返回0，也就是桶位的第一位
return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}