Java-Collection源码分析（七）——HashMap

阅读源码的能力还是太菜，光理解HashMap的数据结构就花了我大半天的时间。JDK1.8中的HashMap的数据结构采用了数组、单向链表和红黑树组合的形式。

一、数据结构

数组中保存的是链表的首节点，当链表的数量大于8时，就会将链表结构转换为红黑树结构。否则采用单向链表的结构进行操作。

通过分析可以得到HashMap的key和value可以为Null，但是key不允许重复，如果key相同，新的value值会自动覆盖原先的value值。

1.1 单向链表

每个节点中保存了hash，key，value和下一个节点，所以为单项链表。

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;
}

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);
}
//设置value值，返回旧的value值
public final V setValue(V newValue) {
V oldValue = value;
value = newValue;
return oldValue;
}
//判断两Entry是否相等，只有key和value同时相等时，才会返回true
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;
}
}

1.2 数组

//该表首先使用初始化，并根据需要调整大小。 分配时，长度总是2的幂。
//定义数组结构
transient Node<K,V>[] table;

1.3 红黑树：

红黑树结构太麻烦，就不予赘述。

二、底层操作

对于节点的操作通常是先通过key的hashcode获取链表的首节点或红黑树中的节点在数组中的位置，然后判断该节点为红黑树结构还是链表结构，采用相应的方法获取节点，进行操作。

2.1 putMapEntries():

//实现Map.putAll和Map构造函数
final void putMapEntries(Map<? extends K, ? extends V> m, boolean evict) {
int s = m.size();
if (s > 0) {
if (table == null) { // pre-size
float ft = ((float)s / loadFactor) + 1.0F;
int t = ((ft
4000
< (float)MAXIMUM_CAPACITY) ?
(int)ft : MAXIMUM_CAPACITY);
if (t > threshold)
threshold = tableSizeFor(t);
}
else if (s > threshold)
resize();
for (Map.Entry<? extends K, ? extends V> e : m.entrySet()) {
K key = e.getKey();
V value = e.getValue();
putVal(hash(key), key, value, false, evict);
}
}
}

2.2 getNode(int hash, Object key):

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 &&
//(length-1) &hash得到对象的保存位
(first = tab[(n - 1) & hash]) != null) {
if (first.hash == hash && ((k = first.key) == key || (key != null && key.equals(k))))	 //总是检查第一个节点
return first;
if ((e = first.next) != null) {
//如果第一个节点是TreeNode,说明采用的是数组+红黑树结构处理冲突遍历红黑树，得到节点值
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;
}

getNode的处理流程图：

2.3  putVal()：

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);//将链表节点转换为红黑树节点
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;
}

2.4 resize()：

初始化HashMap的大小，或扩容为原来的2倍

final Node<K,V>[] resize() {
Node<K,V>[] oldTab = table;
int oldCap = (oldTab == null) ? 0 : oldTab.length;		//数组长度
int oldThr = threshold;		//临界值
int newCap, newThr = 0;
if (oldCap > 0) {
//如果原始数组的长度大于最大容量，则将临界值设置为Integer设置为最大值
if (oldCap >= MAXIMUM_CAPACITY) {
threshold = Integer.MAX_VALUE;
return oldTab;
}
//先将新数组的容量设置为旧数组容量的两倍
//如果新数组的容量小于最大容量，并且旧数组容量大于等于缺省值容量，将临界值也扩大为原来的两倍
else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY &&
oldCap >= DEFAULT_INITIAL_CAPACITY)
newThr = oldThr << 1; // double threshold
}
else if (oldThr > 0) //初始容量被设置为临界值
newCap = oldThr;
else {               // 零初始临界值表示使用默认值
newCap = DEFAULT_INITIAL_CAPACITY;
newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);
}
if (newThr == 0) {		//计算新的临界值
float ft = (float)newCap * loadFactor;
newThr = (newCap < MAXIMUM_CAPACITY && ft < (float)MAXIMUM_CAPACITY ?
(int)ft : Integer.MAX_VALUE);
}
threshold = newThr;	//将临界值设置为新的临界值
@SuppressWarnings({"rawtypes","unchecked"})
//扩容之后对数组内容进行处理
Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap];
table = newTab;
if (oldTab != null) {
//遍历整个数组，将非空元素进行复制
for (int j = 0; j < oldCap; ++j) {
Node<K,V> e;
if ((e = oldTab[j]) != null) {
oldTab[j] = null;
//如果链表中只有一个元素，就直接进行赋值
if (e.next == null)
newTab[e.hash & (newCap - 1)] = e;
//如果为红黑树结构，就调用红黑树进行操作
else if (e instanceof TreeNode)
((TreeNode<K,V>)e).split(this, newTab, j, oldCap);
//对链表元素进行复制操作
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);
//将链表的尾节点的next元素设置为空
if (loTail != null) {
loTail.next = null;
newTab[j] = loHead;
}
if (hiTail != null) {
hiTail.next = null;
newTab[j + oldCap] = hiHead;
}
}
}
}
}
return newTab;
}

2.5 treeifyBin(Node<K,V>[] tab, int hash) ：用红黑树节点替换bin中所有链接的节点，除非表格太小，否则重新调整大小。

final void treeifyBin(Node<K,V>[] tab, int hash) {
int n, index; Node<K,V> e;
if (tab == null || (n = tab.length) < MIN_TREEIFY_CAPACITY)
resize();
else if ((e = tab[index = (n - 1) & hash]) != null) {
TreeNode<K,V> hd = null, tl = null;
do {
TreeNode<K,V> p = replacementTreeNode(e, null);
if (tl == null)
hd = p;
else {
p.prev = tl;
tl.next = p;
}
tl = p;
} while ((e = e.next) != null);
if ((tab[index] = hd) != null)
hd.treeify(tab);
}
}

2.6 removeNode()：

remove方法与getnode方法实现方法类似，首先获取节点，然后对节点进行操作，最后返回删除节点的value

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;
}

2.7 clear()和containValue():

这两个方法类似，使用双重循环结构分别遍历数组和链表来获取节点。

public void clear() {
Node<K,V>[] tab;
modCount++;
if ((tab = table) != null && size > 0) {
size = 0;
for (int i = 0; i < tab.length; ++i)
tab[i] = null;
}
}
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;
}

三、实现的主要方法：

这些实现的方法，主要是通过调用底层操作实现。

//返回指定键映射到的值，如果此映射不包含键的映射，则返回defaultValue。
public V getOrDefault(Object key, V defaultValue) {
Node<K,V> e;
return (e = getNode(hash(key), key)) == null ? defaultValue : e.value;
}
//如果指定的键还没有与值相关联（或映射到null）将其与给定值相关联并返回null，否则返回当前值。
public V putIfAbsent(K key, V value) {
return putVal(hash(key), key, value, true, true);
}
//只有当目标映射到指定的值时，才能删除指定键的条目。
public boolean remove(Object key, Object value) {
return removeNode(hash(key), key, value, true, true) != null;
}
//仅当当前映射到指定的值时，才能替换指定键的条目。
public boolean replace(K key, V oldValue, V newValue) {
Node<K,V> e; V v;
if ((e = getNode(hash(key), key)) != null &&
((v = e.value) == oldValue || (v != null && v.equals(oldValue)))) {
e.value = newValue;
afterNodeAccess(e);
return true;
}
return false;
}
//只有当目标映射到某个值时，才能替换指定键的条目。
public V replace(K key, V value) {
Node<K,V> e;
if ((e = getNode(hash(key), key)) != null) {
V oldValue = e.value;
e.value = value;
afterNodeAccess(e);
return oldValue;
}
return null;
}
//如果指定的键尚未与值相关联（或映射到null），则尝试使用给定的映射函数计算其值，并将其输入到此映射中，除非为null。
public V computeIfAbsent(K key,
Function<? super K, ? extends V> mappingFunction) {
if (mappingFunction == null)
throw new NullPointerException();
int hash = hash(key);
Node<K,V>[] tab; Node<K,V> first; int n, i;
int binCount = 0;
TreeNode<K,V> t = null;
Node<K,V> old = null;
if (size > threshold || (tab = table) == null ||
(n = tab.length) == 0)
n = (tab = resize()).length;
if ((first = tab[i = (n - 1) & hash]) != null) {
if (first instanceof TreeNode)
old = (t = (TreeNode<K,V>)first).getTreeNode(hash, key);
else {
Node<K,V> e = first; K k;
do {
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k)))) {
old = e;
break;
}
++binCount;
} while ((e = e.next) != null);
}
V oldValue;
if (old != null && (oldValue = old.value) != null) {
afterNodeAccess(old);
return oldValue;
}
}
V v = mappingFunction.apply(key);
if (v == null) {
return null;
} else if (old != null) {
old.value = v;
afterNodeAccess(old);
return v;
}
else if (t != null)
t.putTreeVal(this, tab, hash, key, v);
else {
tab[i] = newNode(hash, key, v, first);
if (binCount >= TREEIFY_THRESHOLD - 1)
treeifyBin(tab, hash);
}
++modCount;
++size;
afterNodeInsertion(true);
return v;
}
//如果指定的键的值存在且非空，则尝试计算给定键的新映射及其当前映射的值。
public V computeIfPresent(K key, BiFunction<? super K, ? super V, ? extends V> remappingFunction) {
if (remappingFunction == null)
throw new NullPointerException();
Node<K,V> e; V oldValue;
int hash = hash(key);
if ((e = getNode(hash, key)) != null &&
(oldValue = e.value) != null) {
V v = remappingFunction.apply(key, oldValue);
if (v != null) {
e.value = v;
afterNodeAccess(e);
return v;
}
else
removeNode(hash, key, null, false, true);
}
return null;
}
//尝试计算指定密钥及其当前映射值的映射（如果没有当前映射
ac79
，则为null）。
public V compute(K key,
BiFunction<? super K, ? super V, ? extends V> remappingFunction) {
if (remappingFunction == null)
throw new NullPointerException();
int hash = hash(key);
Node<K,V>[] tab; Node<K,V> first; int n, i;
int binCount = 0;
TreeNode<K,V> t = null;
Node<K,V> old = null;
if (size > threshold || (tab = table) == null ||
(n = tab.length) == 0)
n = (tab = resize()).length;
if ((first = tab[i = (n - 1) & hash]) != null) {
if (first instanceof TreeNode)
old = (t = (TreeNode<K,V>)first).getTreeNode(hash, key);
else {
Node<K,V> e = first; K k;
do {
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k)))) {
old = e;
break;
}
++binCount;
} while ((e = e.next) != null);
}
}
V oldValue = (old == null) ? null : old.value;
V v = remappingFunction.apply(key, oldValue);
if (old != null) {
if (v != null) {
old.value = v;
afterNodeAccess(old);
}
else
removeNode(hash, key, null, false, true);
}
else if (v != null) {
if (t != null)
t.putTreeVal(this, tab, hash, key, v);
else {
tab[i] = newNode(hash, key, v, first);
if (binCount >= TREEIFY_THRESHOLD - 1)
treeifyBin(tab, hash);
}
++modCount;
++size;
afterNodeInsertion(true);
}
return v;
}
//如果指定的键尚未与值相关联或与null相关联，则将其与给定的非空值相关联。
public V merge(K key, V value,
BiFunction<? super V, ? super V, ? extends V> remappingFunction) {
if (value == null)
throw new NullPointerException();
if (remappingFunction == null)
throw new NullPointerException();
int hash = hash(key);
Node<K,V>[] tab; Node<K,V> first; int n, i;
int binCount = 0;
TreeNode<K,V> t = null;
Node<K,V> old = null;
if (size > threshold || (tab = table) == null ||
(n = tab.length) == 0)
n = (tab = resize()).length;
if ((first = tab[i = (n - 1) & hash]) != null) {
if (first instanceof TreeNode)
old = (t = (TreeNode<K,V>)first).getTreeNode(hash, key);
else {
Node<K,V> e = first; K k;
do {
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k)))) {
old = e;
break;
}
++binCount;
} while ((e = e.next) != null);
}
}
if (old != null) {
V v;
if (old.value != null)
v = remappingFunction.apply(old.value, value);
else
v = value;
if (v != null) {
old.value = v;
afterNodeAccess(old);
}
else
removeNode(hash, key, null, false, true);
return v;
}
if (value != null) {
if (t != null)
t.putTreeVal(this, tab, hash, key, value);
else {
tab[i] = newNode(hash, key, value, first);
if (binCount >= TREEIFY_THRESHOLD - 1)
treeifyBin(tab, hash);
}
++modCount;
++size;
afterNodeInsertion(true);
}
return value;
}
//对此映射中的每个条目执行给定的操作，直到所有条目都被处理或操作引发异常。
public void forEach(BiConsumer<? super K, ? super 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.key, e.value);
}
if (modCount != mc)
throw new ConcurrentModificationException();
}
}
//将每个条目的值替换为对该条目调用给定函数的结果，直到所有条目都被处理或该函数抛出异常。
public void replaceAll(BiFunction<? super K, ? super V, ? extends V> function) {
Node<K,V>[] tab;
if (function == 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) {
e.value = function.apply(e.key, e.value);
}
}
if (modCount != mc)
throw new ConcurrentModificationException();
}
}
//创建这个散列表的浅拷贝。
public Object clone() {
HashMap<K,V> result;
try {
result = (HashMap<K,V>)super.clone();
} catch (CloneNotSupportedException e) {
// this shouldn't happen, since we are Cloneable
throw new InternalError(e);
}
result.reinitialize();
result.putMapEntries(this, false);
return result;
}