以jdk1.8的HashMap常用方法的源码分析。
常用的成员属性
//初始容量,必须是2的幂
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;
// HashMap解决hash冲突使用的是链表法,但是当链表过长极端情况下搜索效率会降低到O(n)。所以给定了阈值8,
// 当链表长度到8时,转换成树结构
static final int TREEIFY_THRESHOLD = 8;
//取消阈值6,当树的节点减少到6的时候变成链表。因为树的维护成本高,节点少的情况下遍历链表也不会很费时间,
static final int UNTREEIFY_THRESHOLD = 6;
//只有当容器中节点达到64的时候,才会开启树化
static final int MIN_TREEIFY_CAPACITY = 64;
// 容器的初始数组
transient Node<K,V>[] table;
// 一个Node组成的Set集合
transient Set<Map.Entry<K,V>> entrySet;
// 元素个数
transient int size;
// 记录修改次数,多用于线程不安全的方法。如果修改前与修改后的modCount值不同则抛异常。
transient int modCount;
// 阈值 = 容量*负载系数 ,当size == threshold时就需要扩容了
int threshold;
// 负载系数
final float loadFactor;
构造方法
// 构造函数,可以给定初始容量和负载因子 此时并没有创建数组空间
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
}
// 构造函数,给定一个map集合
public HashMap(Map<? extends K, ? extends V> m) {
this.loadFactor = DEFAULT_LOAD_FACTOR;
putMapEntries(m, false);
}
常用方法
//扰动函数。计算哈希值时把高16位、低16位做与运算,充分利用所有数字降低hash冲突
static final int hash(Object key) {
int h;
return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}
//给定一个cap,返回大于cap的最小的2的整数次幂
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;
//通过上面的运算得到一个 0011...111的二进制数,+1就是 100000000(2的整数次幂)
return (n < 0) ? 1 : (n >= MAXIMUM_CAPACITY) ? MAXIMUM_CAPACITY : n + 1;
}
// 返回元素个数
public int size() { return size; }
// 返回是否为空
public boolean isEmpty() { return size == 0; }
// 返回容量负载因子
final float loadFactor() { return loadFactor; }
// 返回容量
final int capacity() {
return (table != null) ? table.length : (threshold > 0) ? threshold : DEFAULT_INITIAL_CAPACITY;
}
// 是否存在这个 key
public boolean containsKey(Object key) {
return getNode(hash(key), key) != null;
}
// 是否存在这个 value ,从头遍历table时间复杂度 O(n)
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;
}
// 返回由 key 组成的Set 用于迭代
public Set<K> keySet() {
Set<K> ks = keySet;
if (ks == null) {
ks = new KeySet();
keySet = ks;
}
return ks;
}
// 返回由 node节点组成的Set 用于迭代遍历,使用的很频繁
public Set<Map.Entry<K,V>> entrySet() {
Set<Map.Entry<K,V>> es;
return (es = entrySet) == null ? (entrySet = new EntrySet()) : es;
}
remove 方法
// 根据key 移除一个node ,并返回value
public V remove(Object key) {
Node<K,V> e;
return (e = removeNode(hash(key), key, null, false, true)) == null ? null : e.value;
}
// 移除一个node
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;
// 先找到这个node
if (p.hash == hash && ((k = p.key) == key || (key != null && key.equals(k))))
node = p;
else if ((e = p.next) != null) {
// 在树或链表上找这个节点
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);
}
}
// 移除这个节点
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) // node 是头节点
tab[index] = node.next;
else
p.next = node.next;
++modCount;
--size;
afterNodeRemoval(node);
return node;
}
}
return null;
}
// 清空table
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;
}
}
put方法
// 向map中放入 (key 和 value)
public V put(K key, V value) {
return putVal(hash(key), key, value, false, true);
}
// 放入一个map
public void putAll(Map<? extends K, ? extends V> m) {
putMapEntries(m, true);
}
// 把指定map添加到HashMap中
final void putMapEntries(Map<? extends K, ? extends V> m, boolean evict) {
int s = m.size();
if (s > 0) {
if (table == null) { // table为空,根据s计算threshold
float ft = ((float)s / loadFactor) + 1.0F;
int t = ((ft < (float)MAXIMUM_CAPACITY) ? (int)ft : MAXIMUM_CAPACITY);
if (t > threshold)
threshold = tableSizeFor(t);
}
else if (s > threshold)
resize();
// 遍历m ,一个一个放入hashmap
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);
}
}
}
// 放入 k,v 的具体方法
final V putVal(int hash, K key, V value, boolean onlyIfAbsent,
boolean evict) {
Node<K,V>[] tab; Node<K,V> p; int n, i;
// map是否为空 ,为空创建table
if ((tab = table) == null || (n = tab.length) == 0)
n = (tab = resize()).length;
// 链表头节点是否为空
if ((p = tab[i = (n - 1) & hash]) == null) // (tab.length - 1)&hash 哈希取模运算,因为n是一个2的整数幂,n-1的二进制是1111,直接与运算可以取模
tab[i] = newNode(hash, key, value, null);
else {// 检验key是否存在,存在替换value,否则添加到树或链表
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) { // 不存在 key 的映射
p.next = newNode(hash, key, value, null);
if (binCount >= TREEIFY_THRESHOLD - 1) // 链上的节点达到阈值8 ,树化
treeifyBin(tab, hash);
break;
}
if (e.hash == hash && ((k = e.key) == key || (key != null && key.equals(k)))) //找到 key映射
break;
p = e;
}
}
if (e != null) { // 存在 key 的映射
V oldValue = e.value;
if (!onlyIfAbsent || oldValue == null)
e.value = value;
afterNodeAccess(e);
return oldValue;
}
}
++modCount;
if (++size > threshold)
resize();
afterNodeInsertion(evict);
return null;
}
get方法
// 根据key 返回value
public V get(Object key) {
Node<K,V> e;
return (e = getNode(hash(key), key)) == null ? null : e.value;
}
// 根据key返回value ,当key不存在时返回一个默认值defaultValue
@Override
public V getOrDefault(Object key, V defaultValue) {
Node<K,V> e;
return (e = getNode(hash(key), key)) == null ? defaultValue : e.value;
}
// 给定key 与 hash值,返回Node。因为有哈希冲突,多个node可能拥有相同的hash,
// 所以要寻找指定的node还需要比较key值
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) {// 检查map不为空,次hash对应的有node
if (first.hash == hash && ((k = first.key) == key || (key != null && key.equals(k)))) // 检查第一个node是否是要找的
return first;
if ((e = first.next) != null) {// 第一个node不是,然后从后面的链表或树中寻找
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;
}
resize,初始化数组 或者扩容
// 初始化数组 或者扩容
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) // threshold 做初始容量
newCap = oldThr;
else { // 都使用默认值
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];// 此时才真正创建了Node数组
table = newTab;
if (oldTab != null) { // 需要把旧数组的值 复制到新的数组
for (int j = 0; j < oldCap; ++j) {
Node<K,V> e;
if ((e = oldTab[j]) != null) {
oldTab[j] = null;
if (e.next == null) // 链上只有一个节点
newTab[e.hash & (newCap - 1)] = e;
else if (e instanceof TreeNode)// 树
((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 { // 把链表上的节点移动到新table,从头开始遍历,往尾部插
next = e.next;
//oldCap代表高位与低位不同的二进制位 0001000。
if ((e.hash & oldCap) == 0) { //插到小下标的这部分
if (loTail == null)
loHead = e;
else
loTail.next = e;
loTail = e;
}
else { //插到大下标的这部分
if (hiTail == null)
hiHead = e;
else
hiTail.next = e;
hiTail = e;
}
} while ((e = next) != null);
if (loTail != null) { // 尾节点的next清空
loTail.next = null;
newTab[j] = loHead;
}
if (hiTail != null) {
hiTail.next = null;
newTab[j + oldCap] = hiHead;
}
}
}
}
}
return newTab;
}
内部类
内部类的代码比较多,不用知道太详细的过程,大同小异,部分略过
//hash节点包含hash值、key、value、next四个属性,是HashMap的基础元素
static class Node<K,V> implements Map.Entry<K,V> {
final int hash;
final K key;
V value;
Node<K,V> next;//链表法相同hash值的下一个节点
Node(int hash, K key, V value, Node<K,V> next) {
this.hash = hash;
this.key = key;
this.value = value;
this.next = next;
}
// 获取 key value
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);
}
public final V setValue(V newValue) {
V oldValue = value;
value = newValue;
return oldValue;
}
}
// 在返回以value组成的集合时使用
final class Values extends AbstractCollection<V> {
public final int size() { return size; }
public final void clear() { this.clear(); }
public final Iterator<V> iterator() { return new ValueIterator(); }
public final boolean contains(Object o) { return containsValue(o); }
public final Spliterator<V> spliterator() {
return new ValueSpliterator<>(this, 0, -1, 0, 0);
}
}
// KeySet 和 EntrySet在迭代时使用的最多
final class KeySet extends AbstractSet<K> {
public final int size() { return size; }
public final void clear() { this.clear(); }
public final Iterator<K> iterator() { return new KeyIterator(); }
public final boolean contains(Object o) { return containsKey(o); }
public final boolean remove(Object key) {
return removeNode(hash(key), key, null, false, true) != null;
}
public final void forEach(Consumer<? super K> action) {
}
}
final class EntrySet extends AbstractSet<Map.Entry<K,V>> {
public final int size() { return size; }
public final void clear() { this.clear(); }
public final Iterator<Map.Entry<K,V>> iterator() {
return new EntryIterator();
}
public final boolean remove(Object o) {
if (o instanceof Map.Entry) {
Map.Entry<?,?> e = (Map.Entry<?,?>) o;
Object key = e.getKey();
Object value = e.getValue();
return removeNode(hash(key), key, value, true, true) != null;
}
return false;
}
}
jdk1.8与jdk1.7的HashMap与变化挺大的。很多方法的实现都改了。
1.7的扩容存在bug。移动链表时是 从头开始遍历,从头开始插入,多线程下有可能形成循环链表死循环。