HashMap的的结构是由数组+链表 or 红黑树实现的。(JDK1.8之后增加了红黑树部分)
链表:
因为数组table的长度是有限的,并且不同的key可能会具有相同的hash值,此时通过hash值计算出来的索引就有可能会相同,这种情况称为Hash冲突。而为了解决这一现象,就需要链表来解决冲突,数组Table中的每一个元素不单纯只是一个Entry对象,它还是一个链表的头节点,每一个Entry对象通过Next指针指向下一个Entry节点;当新来的Entry映射到冲突数组位置时,只需要插入对应的链表位置即可。
一、继承结构
public class HashMap<K,V> extends AbstractMap<K,V>
implements Map<K,V>, Cloneable, Serializable {
HashMap继承了AbstractMap及实现了Map、Cloneable和Serializable接口。
HashMap与Hashtable的第一个区别在于此,HashMap继承了AbstractMap,而Hashtable继承的是Dictionary抽象类
疑问:,为什么HashMap既继承AbstractMap抽象类还需要实现Map接口吗?
从功能上来说:HashMap实现Map是没有任何作用的。
从结构上来说:由于我们一般是面对接口编程,为了维护结构清晰和完整,是需要实现Map接口的。
而HashMap继承AbstractMap的作用为:AbstractMap 提供 Map 接口的骨干实现,以最大限度地减少实现此接口所需的工作。
二、属性
private static final long serialVersionUID = 362498820763181265L;
/**
* 默认初始化容量 16
*/
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16
/**
* 最大容量
*/
static final int MAXIMUM_CAPACITY = 1 << 30;
/**
* 加载因子
*/
static final float DEFAULT_LOAD_FACTOR = 0.75f;
/**
* 使用树(而不是列表)的存储箱计数阈值。将元素添加到至少具有这么多节点的bin时,存储单元将转换为树。该值必须大于2,且至少应为8,以符合树木移除中关于在收缩时转换回普通垃圾箱的假设。
*/
static final int TREEIFY_THRESHOLD = 8;
static final int UNTREEIFY_THRESHOLD = 6;
static final int MIN_TREEIFY_CAPACITY = 64;
//Node型数组
transient Node<K,V>[] table;
//实体型Set集合,每个实体都是不同的
transient Set<Map.Entry<K,V>> entrySet;
//元素个数
transient int size;
//修改次数
transient int modCount;
//阈值
int threshold;
//加载因子
final float loadFactor;
三、内部类
Node<K,V>
//基本哈希bin节点,用于大多数条目。(TreeNode子类见下文,Entry子类见LinkedHashMap。)
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);
}
public final V setValue(V newValue) {
V oldValue = value;
value = newValue;
return oldValue;
}
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;
}
}
TreeNode<K,V>
当链表长度大于 8 时,会转换为红黑树结构(java8)
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);
}
/**
* Returns root of tree containing this node.
*/
final TreeNode<K,V> root() {
for (TreeNode<K,V> r = this, p;;) {
if ((p = r.parent) == null)
return r;
r = p;
}
}
/**
* Ensures that the given root is the first node of its bin.
*/
static <K,V> void moveRootToFront(Node<K,V>[] tab, TreeNode<K,V> root) {
int n;
if (root != null && tab != null && (n = tab.length) > 0) {
int index = (n - 1) & root.hash;
TreeNode<K,V> first = (TreeNode<K,V>)tab[index];
if (root != first) {
Node<K,V> rn;
tab[index] = root;
TreeNode<K,V> rp = root.prev;
if ((rn = root.next) != null)
((TreeNode<K,V>)rn).prev = rp;
if (rp != null)
rp.next = rn;
if (first != null)
first.prev = root;
root.next = first;
root.prev = null;
}
assert checkInvariants(root);
}
}
/**
* Finds the node starting at root p with the given hash and key.
* The kc argument caches comparableClassFor(key) upon first use
* comparing keys.
*/
final TreeNode<K,V> find(int h, Object k, Class<?> kc) {
TreeNode<K,V> p = this;
do {
int ph, dir; K pk;
TreeNode<K,V> pl = p.left, pr = p.right, q;
if ((ph = p.hash) > h)
p = pl;
else if (ph < h)
p = pr;
else if ((pk = p.key) == k || (k != null && k.equals(pk)))
return p;
else if (pl == null)
p = pr;
else if (pr == null)
p = pl;
else if ((kc != null ||
(kc = comparableClassFor(k)) != null) &&
(dir = compareComparables(kc, k, pk)) != 0)
p = (dir < 0) ? pl : pr;
else if ((q = pr.find(h, k, kc)) != null)
return q;
else
p = pl;
} while (p != null);
return null;
}
/**
* Calls find for root node.
*/
final TreeNode<K,V> getTreeNode(int h, Object k) {
return ((parent != null) ? root() : this).find(h, k, null);
}
/**
* Tie-breaking utility for ordering insertions when equal
* hashCodes and non-comparable. We don't require a total
* order, just a consistent insertion rule to maintain
* equivalence across rebalancings. Tie-breaking further than
* necessary simplifies testing a bit.
*/
static int tieBreakOrder(Object a, Object b) {
int d;
if (a == null || b == null ||
(d = a.getClass().getName().
compareTo(b.getClass().getName())) == 0)
d = (System.identityHashCode(a) <= System.identityHashCode(b) ?
-1 : 1);
return d;
}
/**
* Forms tree of the nodes linked from this node.
*/
final void treeify(Node<K,V>[] tab) {
TreeNode<K,V> root = null;
for (TreeNode<K,V> x = this, next; x != null; x = next) {
next = (TreeNode<K,V>)x.next;
x.left = x.right = null;
if (root == null) {
x.parent = null;
x.red = false;
root = x;
}
else {
K k = x.key;
int h = x.hash;
Class<?> kc = null;
for (TreeNode<K,V> p = root;;) {
int dir, ph;
K pk = p.key;
if ((ph = p.hash) > h)
dir = -1;
else if (ph < h)
dir = 1;
else if ((kc == null &&
(kc = comparableClassFor(k)) == null) ||
(dir = compareComparables(kc, k, pk)) == 0)
dir = tieBreakOrder(k, pk);
TreeNode<K,V> xp = p;
if ((p = (dir <= 0) ? p.left : p.right) == null) {
x.parent = xp;
if (dir <= 0)
xp.left = x;
else
xp.right = x;
root = balanceInsertion(root, x);
break;
}
}
}
}
moveRootToFront(tab, root);
}
/**
* Returns a list of non-TreeNodes replacing those linked from
* this node.
*/
final Node<K,V> untreeify(HashMap<K,V> map) {
Node<K,V> hd = null, tl = null;
for (Node<K,V> q = this; q != null; q = q.next) {
Node<K,V> p = map.replacementNode(q, null);
if (tl == null)
hd = p;
else
tl.next = p;
tl = p;
}
return hd;
}
/**
* Tree version of putVal.
*/
final TreeNode<K,V> putTreeVal(HashMap<K,V> map, Node<K,V>[] tab,
int h, K k, V v) {
Class<?> kc = null;
boolean searched = false;
TreeNode<K,V> root = (parent != null) ? root() : this;
for (TreeNode<K,V> p = root;;) {
int dir, ph; K pk;
if ((ph = p.hash) > h)
dir = -1;
else if (ph < h)
dir = 1;
else if ((pk = p.key) == k || (k != null && k.equals(pk)))
return p;
else if ((kc == null &&
(kc = comparableClassFor(k)) == null) ||
(dir = compareComparables(kc, k, pk)) == 0) {
if (!searched) {
TreeNode<K,V> q, ch;
searched = true;
if (((ch = p.left) != null &&
(q = ch.find(h, k, kc)) != null) ||
((ch = p.right) != null &&
(q = ch.find(h, k, kc)) != null))
return q;
}
dir = tieBreakOrder(k, pk);
}
TreeNode<K,V> xp = p;
if ((p = (dir <= 0) ? p.left : p.right) == null) {
Node<K,V> xpn = xp.next;
TreeNode<K,V> x = map.newTreeNode(h, k, v, xpn);
if (dir <= 0)
xp.left = x;
else
xp.right = x;
xp.next = x;
x.parent = x.prev = xp;
if (xpn != null)
((TreeNode<K,V>)xpn).prev = x;
moveRootToFront(tab, balanceInsertion(root, x));
return null;
}
}
}
/**
* Removes the given node, that must be present before this call.
* This is messier than typical red-black deletion code because we
* cannot swap the contents of an interior node with a leaf
* successor that is pinned by "next" pointers that are accessible
* independently during traversal. So instead we swap the tree
* linkages. If the current tree appears to have too few nodes,
* the bin is converted back to a plain bin. (The test triggers
* somewhere between 2 and 6 nodes, depending on tree structure).
*/
final void removeTreeNode(HashMap<K,V> map, Node<K,V>[] tab,
boolean movable) {
int n;
if (tab == null || (n = tab.length) == 0)
return;
int index = (n - 1) & hash;
TreeNode<K,V> first = (TreeNode<K,V>)tab[index], root = first, rl;
TreeNode<K,V> succ = (TreeNode<K,V>)next, pred = prev;
if (pred == null)
tab[index] = first = succ;
else
pred.next = succ;
if (succ != null)
succ.prev = pred;
if (first == null)
return;
if (root.parent != null)
root = root.root();
if (root == null
|| (movable
&& (root.right == null
|| (rl = root.left) == null
|| rl.left == null))) {
tab[index] = first.untreeify(map); // too small
return;
}
TreeNode<K,V> p = this, pl = left, pr = right, replacement;
if (pl != null && pr != null) {
TreeNode<K,V> s = pr, sl;
while ((sl = s.left) != null) // find successor
s = sl;
boolean c = s.red; s.red = p.red; p.red = c; // swap colors
TreeNode<K,V> sr = s.right;
TreeNode<K,V> pp = p.parent;
if (s == pr) { // p was s's direct parent
p.parent = s;
s.right = p;
}
else {
TreeNode<K,V> sp = s.parent;
if ((p.parent = sp) != null) {
if (s == sp.left)
sp.left = p;
else
sp.right = p;
}
if ((s.right = pr) != null)
pr.parent = s;
}
p.left = null;
if ((p.right = sr) != null)
sr.parent = p;
if ((s.left = pl) != null)
pl.parent = s;
if ((s.parent = pp) == null)
root = s;
else if (p == pp.left)
pp.left = s;
else
pp.right = s;
if (sr != null)
replacement = sr;
else
replacement = p;
}
else if (pl != null)
replacement = pl;
else if (pr != null)
replacement = pr;
else
replacement = p;
if (replacement != p) {
TreeNode<K,V> pp = replacement.parent = p.parent;
if (pp == null)
root = replacement;
else if (p == pp.left)
pp.left = replacement;
else
pp.right = replacement;
p.left = p.right = p.parent = null;
}
TreeNode<K,V> r = p.red ? root : balanceDeletion(root, replacement);
if (replacement == p) { // detach
TreeNode<K,V> pp = p.parent;
p.parent = null;
if (pp != null) {
if (p == pp.left)
pp.left = null;
else if (p == pp.right)
pp.right = null;
}
}
if (movable)
moveRootToFront(tab, r);
}
/**
* Splits nodes in a tree bin into lower and upper tree bins,
* or untreeifies if now too small. Called only from resize;
* see above discussion about split bits and indices.
*
* @param map the map
* @param tab the table for recording bin heads
* @param index the index of the table being split
* @param bit the bit of hash to split on
*/
final void split(HashMap<K,V> map, Node<K,V>[] tab, int index, int bit) {
TreeNode<K,V> b = this;
// Relink into lo and hi lists, preserving order
TreeNode<K,V> loHead = null, loTail = null;
TreeNode<K,V> hiHead = null, hiTail = null;
int lc = 0, hc = 0;
for (TreeNode<K,V> e = b, next; e != null; e = next) {
next = (TreeNode<K,V>)e.next;
e.next = null;
if ((e.hash & bit) == 0) {
if ((e.prev = loTail) == null)
loHead = e;
else
loTail.next = e;
loTail = e;
++lc;
}
else {
if ((e.prev = hiTail) == null)
hiHead = e;
else
hiTail.next = e;
hiTail = e;
++hc;
}
}
if (loHead != null) {
if (lc <= UNTREEIFY_THRESHOLD)
tab[index] = loHead.untreeify(map);
else {
tab[index] = loHead;
if (hiHead != null) // (else is already treeified)
loHead.treeify(tab);
}
}
if (hiHead != null) {
if (hc <= UNTREEIFY_THRESHOLD)
tab[index + bit] = hiHead.untreeify(map);
else {
tab[index + bit] = hiHead;
if (loHead != null)
hiHead.treeify(tab);
}
}
}
/* ------------------------------------------------------------ */
// Red-black tree methods, all adapted from CLR
static <K,V> TreeNode<K,V> rotateLeft(TreeNode<K,V> root,
TreeNode<K,V> p) {
TreeNode<K,V> r, pp, rl;
if (p != null && (r = p.right) != null) {
if ((rl = p.right = r.left) != null)
rl.parent = p;
if ((pp = r.parent = p.parent) == null)
(root = r).red = false;
else if (pp.left == p)
pp.left = r;
else
pp.right = r;
r.left = p;
p.parent = r;
}
return root;
}
static <K,V> TreeNode<K,V> rotateRight(TreeNode<K,V> root,
TreeNode<K,V> p) {
TreeNode<K,V> l, pp, lr;
if (p != null && (l = p.left) != null) {
if ((lr = p.left = l.right) != null)
lr.parent = p;
if ((pp = l.parent = p.parent) == null)
(root = l).red = false;
else if (pp.right == p)
pp.right = l;
else
pp.left = l;
l.right = p;
p.parent = l;
}
return root;
}
static <K,V> TreeNode<K,V> balanceInsertion(TreeNode<K,V> root,
TreeNode<K,V> x) {
x.red = true;
for (TreeNode<K,V> xp, xpp, xppl, xppr;;) {
if ((xp = x.parent) == null) {
x.red = false;
return x;
}
else if (!xp.red || (xpp = xp.parent) == null)
return root;
if (xp == (xppl = xpp.left)) {
if ((xppr = xpp.right) != null && xppr.red) {
xppr.red = false;
xp.red = false;
xpp.red = true;
x = xpp;
}
else {
if (x == xp.right) {
root = rotateLeft(root, x = xp);
xpp = (xp = x.parent) == null ? null : xp.parent;
}
if (xp != null) {
xp.red = false;
if (xpp != null) {
xpp.red = true;
root = rotateRight(root, xpp);
}
}
}
}
else {
if (xppl != null && xppl.red) {
xppl.red = false;
xp.red = false;
xpp.red = true;
x = xpp;
}
else {
if (x == xp.left) {
root = rotateRight(root, x = xp);
xpp = (xp = x.parent) == null ? null : xp.parent;
}
if (xp != null) {
xp.red = false;
if (xpp != null) {
xpp.red = true;
root = rotateLeft(root, xpp);
}
}
}
}
}
}
static <K,V> TreeNode<K,V> balanceDeletion(TreeNode<K,V> root,
TreeNode<K,V> x) {
for (TreeNode<K,V> xp, xpl, xpr;;) {
if (x == null || x == root)
return root;
else if ((xp = x.parent) == null) {
x.red = false;
return x;
}
else if (x.red) {
x.red = false;
return root;
}
else if ((xpl = xp.left) == x) {
if ((xpr = xp.right) != null && xpr.red) {
xpr.red = false;
xp.red = true;
root = rotateLeft(root, xp);
xpr = (xp = x.parent) == null ? null : xp.right;
}
if (xpr == null)
x = xp;
else {
TreeNode<K,V> sl = xpr.left, sr = xpr.right;
if ((sr == null || !sr.red) &&
(sl == null || !sl.red)) {
xpr.red = true;
x = xp;
}
else {
if (sr == null || !sr.red) {
if (sl != null)
sl.red = false;
xpr.red = true;
root = rotateRight(root, xpr);
xpr = (xp = x.parent) == null ?
null : xp.right;
}
if (xpr != null) {
xpr.red = (xp == null) ? false : xp.red;
if ((sr = xpr.right) != null)
sr.red = false;
}
if (xp != null) {
xp.red = false;
root = rotateLeft(root, xp);
}
x = root;
}
}
}
else { // symmetric
if (xpl != null && xpl.red) {
xpl.red = false;
xp.red = true;
root = rotateRight(root, xp);
xpl = (xp = x.parent) == null ? null : xp.left;
}
if (xpl == null)
x = xp;
else {
TreeNode<K,V> sl = xpl.left, sr = xpl.right;
if ((sl == null || !sl.red) &&
(sr == null || !sr.red)) {
xpl.red = true;
x = xp;
}
else {
if (sl == null || !sl.red) {
if (sr != null)
sr.red = false;
xpl.red = true;
root = rotateLeft(root, xpl);
xpl = (xp = x.parent) == null ?
null : xp.left;
}
if (xpl != null) {
xpl.red = (xp == null) ? false : xp.red;
if ((sl = xpl.left) != null)
sl.red = false;
}
if (xp != null) {
xp.red = false;
root = rotateRight(root, xp);
}
x = root;
}
}
}
}
}
/**
* Recursive invariant check
*/
static <K,V> boolean checkInvariants(TreeNode<K,V> t) {
TreeNode<K,V> tp = t.parent, tl = t.left, tr = t.right,
tb = t.prev, tn = (TreeNode<K,V>)t.next;
if (tb != null && tb.next != t)
return false;
if (tn != null && tn.prev != t)
return false;
if (tp != null && t != tp.left && t != tp.right)
return false;
if (tl != null && (tl.parent != t || tl.hash > t.hash))
return false;
if (tr != null && (tr.parent != t || tr.hash < t.hash))
return false;
if (t.red && tl != null && tl.red && tr != null && tr.red)
return false;
if (tl != null && !checkInvariants(tl))
return false;
if (tr != null && !checkInvariants(tr))
return false;
return true;
}
}
EntrySet
final class EntrySet extends AbstractSet<Map.Entry<K,V>> {
public final int size() { return size; }
public final void clear() { HashMap.this.clear(); }
public final Iterator<Map.Entry<K,V>> iterator() {
return new EntryIterator();
}
public final boolean contains(Object o) {
if (!(o instanceof Map.Entry))
return false;
Map.Entry<?,?> e = (Map.Entry<?,?>) o;
Object key = e.getKey();
Node<K,V> candidate = getNode(hash(key), key);
return candidate != null && candidate.equals(e);
}
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;
}
public final Spliterator<Map.Entry<K,V>> spliterator() {
return new EntrySpliterator<>(HashMap.this, 0, -1, 0, 0);
}
public final void forEach(Consumer<? super Map.Entry<K,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);
}
if (modCount != mc)
throw new ConcurrentModificationException();
}
}
}
好奇EntrySet没有写出构造器,我们在遍历Map集合的时候,可以使用map.entrySet()获得实体类的Set<Map.Entry<K k,V v>> 的集合。然后使用增强for去遍历的,那么 HashMap中的这个内部类是如何获取到 内部数据结构的呢?
大致思路如图所示,我自己的粗浅理解是 拿到Entry迭代器,迭代器调用 nextNode( )去数据结构中获取下一个个的Node结点,键值对的数据就封装在Node结点之中。
四、构造函数
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);
}
产生HashMap对象,其它的构造函数都是调用此构造函数来实现的
参数的说明:
- initialCapacity:分配数组的大小,默认大小为16,且只能是2的幂次方
- loadFactor:加载因子,作用为:当数组中存储的数据大于了分配空间的总长度*loadFactor之后就进行扩容
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);
}
五、重要方法
put (K key, V value)
public V put(K key, V value) {
return putVal(hash(key), key, value, false, true);
}
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;
/*
根据key的hash值找到要存储的位置,
如果该位置还没有存储元素,则直接在该位置保存值即可
*/
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null);
else {
Node<K,V> e; K k;
/*
检查该位置的链表中是否有了该key,
在下面的代码中,是先检查头结点是否为该key,如果不等于,则在剩余的节点中寻找
*/
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 {
/*
在剩余的节点中寻找key的位置
将节点(key,value)加到链表的末尾
*/
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;
}
}
//如果e为空,则说明是添加的新节点,如果e不为空,则说明该key已经存在,只需要更新value
if (e != null) { // existing mapping for key
V oldValue = e.value;
if (!onlyIfAbsent || oldValue == null)
e.value = value;
afterNodeAccess(e);
return oldValue;
}
}
++modCount;
//检查看是否需要扩容
if (++size > threshold)
resize();
afterNodeInsertion(evict);
return null;
}
此方法的思想为:首先根据key
得到hashcode
,根据 hashcode
得到要存储的位置i=hash&(n-1)
, 其中n为数组的长度
(只有n为2的幂次方时,这句话才与hash%n等价,这就解释了为什么了HashMap的容量必须为2的幂次方)。
得到存储位置 i 之后,检查此位置是否已经有元素,如果没有,则直接存储在该位置即可.
如果有,则在位置的所有节点中遍历是否含有该key,如果已经有了该key,则更新其value即可,如果没有该key,则在该链表的末尾加入该新节点即可。
上面调用了resize方法来进行扩容,前面提到,在HashMap所有的构造函数中,都没有对数组table分配存储空间。而是将这一步放入到了在put方法中进行table检测,如果为空,则调用resize方法进行扩容(或者说是为了给其开辟空间)。