HashMap 底层数据结构是数组、哈希表。数组称之为哈希桶,它是线程不安全的。
允许key为null,value为null。
遍历时无序。
在JDK8中,当链表长度达到8,会转化成红黑树,以提升它的查询、插入效率。
HashMap继承AbstractMap<K,V>,实现了Map,Cloneable, Serializable。如下:
public class HashMap<K,V> extends AbstractMap<K,V>
implements Map<K,V>, Cloneable, Serializable
HashMap中有两种数据结构,一种链表,一种红黑树。
static class Node<K,V> implements Map.Entry<K,V> {
// hash值
final int hash;
// key
final K key;
// value
V value;
// 下一节点
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; }
// ^ : 位异或运算。二进制数,从高位到低位逐一比较,相同为0,不同为1。
// 每个节点的hash值是通过key和value的hash值亦或得到。
public final int hashCode() {
return Objects.hashCode(key) ^ Objects.hashCode(value);
}
// 设置新值,覆盖旧值,同时返回旧值
public final V setValue(V newValue) {
V oldValue = value;
value = newValue;
return oldValue;
}
// 比较是否是同一个对象
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;
}
}
总结:通过分析得知,这是一个单链表;每个节点的hash值是通过key和value的hash值亦或得到。
static final class TreeNode<K,V> extends LinkedHashMap.Entry<K,V> {
TreeNode<K,V> parent; // 红黑树的链接
TreeNode<K,V> left;
TreeNode<K,V> right;
TreeNode<K,V> prev; // 需要取消链接后删除
boolean red;
TreeNode(int hash, K key, V val, Node<K,V> next) {
super(hash, key, val, next);
}
//只是部分代码,缺少一个右大括号
/**
* The default initial capacity - MUST be a power of two.
* - 默认的初始容量(必须是2的幂)。
*/
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16
/**
* The maximum capacity, used if a higher value is implicitly specified
* by either of the constructors with arguments.
* MUST be a power of two <= 1<<30.
* - << : 左移运算符,eg:1<<1 = 2^1 ; 1<<30 = 2^30
* - 最大容量,如果更高的值是由任何一个带有参数的构造函数隐式指定的,则使用该值。必须是2的幂<= 1<<30。
*/
static final int MAXIMUM_CAPACITY = 1 << 30;
/**
* The load factor used when none specified in constructor.
* - 默认加载因子,在构造函数中没有指定时使用的负载因子
*/
static final float DEFAULT_LOAD_FACTOR = 0.75f;
/**
* The bin count threshold for using a tree rather than list for a
* bin. Bins are converted to trees when adding an element to a
* bin with at least this many nodes. The value must be greater
* than 2 and should be at least 8 to mesh with assumptions in
* tree removal about conversion back to plain bins upon
* shrinkage.
* - 桶的树化阈值:链表转成红黑树的阈值
* - 当冲突的元素数增加到8时,链表变为树。
*/
static final int TREEIFY_THRESHOLD = 8;
/**
* The bin count threshold for untreeifying a (split) bin during a
* resize operation. Should be less than TREEIFY_THRESHOLD, and at
* most 6 to mesh with shrinkage detection under removal.
* - 桶的链表还原阈值:红黑树转为链表的阈值。
* - 当减少至6时,树切换为链表。
*/
static final int UNTREEIFY_THRESHOLD = 6;
/**
* The smallest table capacity for which bins may be treeified.
* (Otherwise the table is resized if too many nodes in a bin.)
* Should be at least 4 * TREEIFY_THRESHOLD to avoid conflicts
* between resizing and treeification thresholds.
* - 最小树形化容量阈值:当哈希表中的容量 > 该值时,才允许树形化链表 (即 将链表 转换成红黑树)
* - 否则,若桶内元素太多时,则直接扩容,而不是树形化
* - 为了避免进行扩容、树形化选择的冲突,这个值不能小于 4 * TREEIFY_THRESHOLD
*/
static final int MIN_TREEIFY_CAPACITY = 64;
/**
* The table, initialized on first use, and resized as
* necessary. When allocated, length is always a power of two.
* (We also tolerate length zero in some operations to allow
* bootstrapping mechanics that are currently not needed.)
* - 哈希桶,存放链表。 长度是2的N次方,或者初始化时为0.
*/
transient Node<K,V>[] table;
/**
* Holds cached entrySet(). Note that AbstractMap fields are used
* for keySet() and values().
* - 数据转换成set的另一种存储形式,主要用于迭代功能。
*/
transient Set<Map.Entry<K,V>> entrySet;
/**
* The number of key-value mappings contained in this map.
* - 列表大小:此映射中包含的键-值映射的数目。
*/
transient int size;
/**
* The number of times this HashMap has been structurally modified
* Structural modifications are those that change the number of mappings in
* the HashMap or otherwise modify its internal structure (e.g.,
* rehash). This field is used to make iterators on Collection-views of
* the HashMap fail-fast. (See ConcurrentModificationException).
* - 记录被修改的次数
*/
transient int modCount;
/**
* The next size value at which to resize (capacity * load factor).
*
* @serial
*/
// (The javadoc description is true upon serialization.
// Additionally, if the table array has not been allocated, this
// field holds the initial array capacity, or zero signifying
// DEFAULT_INITIAL_CAPACITY.)
// 扩容阈值:要调整大小的下一个大小值(容量*负载因子)。
int threshold;
/**
* The load factor for the hash table.
* - 负载因子,可计算出当前table长度下的扩容阈值:threshold = loadFactor * table.length。
* @serial
*/
final float loadFactor;
无参构造:构造一个空的HashMap,具有默认的初始容量16和默认的负载因子0.75。
/**
* Constructs an empty HashMap with the default initial capacity
* (16) and the default load factor (0.75).
* - 构造一个空的HashMap,具有默认的初始容量16和默认的负载因子0.75。
*/
public HashMap() {
this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted
}
使用指定的初始容量和负载因子构造一个空的HashMap。
/**
* Constructs an empty HashMap with the specified initial
* capacity and load factor.
* - 使用指定的初始容量和负载因子构造一个空的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) {
// 初始容量 < 0 抛出异常
if (initialCapacity < 0)
throw new IllegalArgumentException("Illegal initial capacity: " +
initialCapacity);
//初始容量大于对打容量,取最大容量
if (initialCapacity > MAXIMUM_CAPACITY)
initialCapacity = MAXIMUM_CAPACITY;
// 负载因子 <= 0 或 负载因子为空
if (loadFactor <= 0 || Float.isNaN(loadFactor))
throw new IllegalArgumentException("Illegal load factor: " +
loadFactor);
// 赋值
this.loadFactor = loadFactor;
// 新的扩容临界值
this.threshold = tableSizeFor(initialCapacity);
}
/**
* Returns a power of two size for the given target capacity.
*/
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;
return (n < 0) ? 1 : (n >= MAXIMUM_CAPACITY) ? MAXIMUM_CAPACITY : n + 1;
}
>>> : 无符号右移详情 →Java 按位运算符
构造一个空的HashMap,具有指定的初始容量和缺省负载因子0.75。
/**
* Constructs an empty HashMap with the specified initial
* capacity and the default load factor (0.75).
* - 构造一个空的HashMap,具有指定的初始容量和缺省负载因子0.75。
* @param initialCapacity the initial capacity.
* - 初始容量
* @throws IllegalArgumentException if the initial capacity is negative.
* - 抛出异常
*/
public HashMap(int initialCapacity) {
// 使用HashMap(int initialCapacity, float loadFactor)构造,创建
this(initialCapacity, DEFAULT_LOAD_FACTOR);
}
使用与指定的Map构造新的HashMap,新HashMap使用默认负载因子(0.75)和足够容纳指定Map中的元素的初始容量创建的。
/**
* Constructs a new HashMap with the same mappings as the
* specified Map . The HashMap is created with
* default load factor (0.75) and an initial capacity sufficient to
* hold the mappings in the specified Map .
*
* @param m the map whose mappings are to be placed in this map
* - 这个Map的元素将被放在这个Map中
* @throws NullPointerException if the specified map is null
*/
public HashMap(Map<? extends K, ? extends V> m) {
// 默认负载因子 0.75f
this.loadFactor = DEFAULT_LOAD_FACTOR;
putMapEntries(m, false);
}
/**
* - 哈希桶,存放链表。 长度是2的N次方,或者初始化时为0.
*/
transient Node<K,V>[] table;
/**
* Implements Map.putAll and Map constructor.
*
* @param m the map
* @param evict false when initially constructing this map, else true (relayed to method afterNodeInsertion).
* - 在最初构造这个映射时为false,否则为true。
*/
final void putMapEntries(Map<? extends K, ? extends V> m, boolean evict) {
int s = m.size();
// Map的大小是不是大于0(等于0就没必要初始化了)
if (s > 0) {
// 通过构造器新建一个HashMap,所以table是null(table是Node数组)
if (table == null) { // pre-size
//计算阀值,判断是否大于最大容量,如果没超过则还是原阀值ft,将ft赋给t。
float ft = ((float)s / loadFactor) + 1.0F;
int t = ((ft < (float)MAXIMUM_CAPACITY) ? (int)ft : MAXIMUM_CAPACITY);
//判断阀值t是否大于原阀值(原阀值是16,默认容量是16),如果大于原阀值,重新计算tableSizeFor(t)。
if (t > threshold)
threshold = tableSizeFor(t);
}
else if (s > threshold)
//构造调用,先不做解释
resize();
//
for (Map.Entry<? extends K, ? extends V> e : m.entrySet()) {
K key = e.getKey();
V value = e.getValue();
// putVal()方法先不看,主要功能是创建一个节点,把这个节点放到了tab中
putVal(hash(key), key, value, false, evict);
}
}
}
/**
* Returns a power of two size for the given target capacity.
*/
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;
return (n < 0) ? 1 : (n >= MAXIMUM_CAPACITY) ? MAXIMUM_CAPACITY : n + 1;
}
返回此Map中的键值对个数。
如果此Map不包含键值映射,则返回true
public boolean isEmpty() { return size == 0; }
返回指定key对应的value,如果没有改键值对,则返回 null。
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.
* - 实现于 Map.get 方法 和 相关方法
* @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;
// 判断Node[]不等与空,并且第一个元素不等于空
if ((tab = table) != null && (n = tab.length) > 0 && (first = tab[(n - 1) & hash]) != null) {
// 判断是否是第一个元素
if (first.hash == hash && // always check first node
((k = first.key) == key || (key != null && key.equals(k))))
return first;
//判断下一个元素不等于空
if ((e = first.next) != null) {
//判断是否是红黑树
if (first instanceof TreeNode)
// 红黑树循环遍历获取ke对应的value
return ((TreeNode<K,V>)first).getTreeNode(hash, key);
// 链表循环遍历获取ke对应的value
do {
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
return e;
} while ((e = e.next) != null);
}
}
return null;
}
判断指定key是否存在,如果存在则返回true,否则返回false。
public boolean containsKey(Object key) {
return getNode(hash(key), key) != null;
}
/**
* Implements Map.get and related methods.
* - 实现于 Map.get 方法 和 相关方法
* @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;
// 判断Node[]不等与空,并且第一个元素不等于空
if ((tab = table) != null && (n = tab.length) > 0 && (first = tab[(n - 1) & hash]) != null) {
// 判断是否是第一个元素
if (first.hash == hash && // always check first node
((k = first.key) == key || (key != null && key.equals(k))))
return first;
//判断下一个元素不等于空
if ((e = first.next) != null) {
//判断是否是红黑树
if (first instanceof TreeNode)
// 红黑树循环遍历获取ke对应的value
return ((TreeNode<K,V>)first).getTreeNode(hash, key);
// 链表循环遍历获取ke对应的value
do {
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
return e;
} while ((e = e.next) != null);
}
}
return null;
}
判断指定value是否存在,如果存在则返回true,否则返回false。
public boolean containsValue(Object value) {
Node<K,V>[] tab; V v;
//判断table不等与空
if ((tab = table) != null && size > 0) {
//循环遍历table数组
for (int i = 0; i < tab.length; ++i) {
//循环遍历链表
for (Node<K,V> e = tab[i]; e != null; e = e.next) {
//判断value是否存在,存在返回true
if ((v = e.value) == value || (value != null && value.equals(v)))
return true;
}
}
}
return false;
}
删除Map中的元素
public void clear() {
Node<K,V>[] tab;
//集合修改次数加1
modCount++;
//循环遍历Node数组
if ((tab = table) != null && size > 0) {
//长度置空
size = 0;
//循环遍历,链表置空
for (int i = 0; i < tab.length; ++i)
tab[i] = null;
}
}
将指定键与值进行关联,并存储。如果键已存在,则新value值覆盖旧value值。
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;
// 如果table为空,则进行必要字段的初始化
if ((tab = table) == null || (n = tab.length) == 0)
n = (tab = resize()).length;// 获取长度(16)
// 如果根据hash值获取的结点为空,则新建一个结点
if ((p = tab[i = (n - 1) & hash]) == null) // 此处 & 代替了 % (除法散列法进行散列)
// 这里的p结点是根据hash值算出来对应在数组中的元素
tab[i] = newNode(hash, key, value, null);
else {
Node<K,V> e;
K k;
// 如果新插入的结点和table中p结点的hash值,key值相同的话
if (p.hash == hash && ((k = p.key) == key || (key != null && key.equals(k))))
e = p;
//如果是红黑树结点,则进行红黑树插入
else if (p instanceof TreeNode)
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
else {
for (int binCount = 0; ; ++binCount) {
//代表这个单链表只有一个头部结点,则直接新建一个结点即可
if ((e = p.next) == null) {
p.next = newNode(hash, key, value, null);
// 链表长度大于8时,将链表转红黑树
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;
// 及时更新p
p = e;
}
}
// 如果存在这个映射就覆盖
if (e != null) { // existing mapping for key
V oldValue = e.value;
//判断是否允许覆盖,并且value是否为空
if (!onlyIfAbsent || oldValue == null)
e.value = value;
afterNodeAccess(e); //回调以允许LinkedHashMap后置操作
return oldValue;
}
}
// 更改操作次数
++modCount;
// 大于临界值
if (++size > threshold)
// 将数组大小设置为原来的2倍,并将原先的数组中的元素放到新数组中
// 因为有链表,红黑树之类,因此还要调整他们
resize();
afterNodeInsertion(evict); //回调以允许LinkedHashMap后置操作
return null;
}
/**
*初始化或者扩容之后元素调整
*/
final Node<K,V>[] resize() {
// 获取旧元素数组的各种信息
Node<K,V>[] oldTab = table;
// 旧元素的长度
int oldCap = (oldTab == null) ? 0 : oldTab.length;
// 旧元素的临界值
int oldThr = threshold;
// 定义新元素的长度及临界值
int newCap, newThr = 0;
// 如果旧元素不为空
if (oldCap > 0) {
// 如果旧元素长度达到最大值,则修改临界值为Integer.MAX_VALUE
if (oldCap >= MAXIMUM_CAPACITY) {
threshold = Integer.MAX_VALUE;
return oldTab;
}
// 下面就是扩容操作(2倍)
else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY && oldCap >= DEFAULT_INITIAL_CAPACITY)
// threshold也变为二倍
newThr = oldThr << 1; // double threshold
}
else if (oldThr > 0) // 初始容量设置为旧元素的临界值
newCap = oldThr;
else { // threshold为0,则使用默认值
newCap = DEFAULT_INITIAL_CAPACITY;
newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);
}
if (newThr == 0) { // 如果临界值还为0,则设置临界值
float ft = (float)newCap * loadFactor;
newThr = (newCap < MAXIMUM_CAPACITY && ft < (float)MAXIMUM_CAPACITY ?
(int)ft : Integer.MAX_VALUE);
}
threshold = newThr; // 更新填充因子
@SuppressWarnings({"rawtypes","unchecked"})
Node<K,V>[] newTab = (Node<K,V>[])new Node[newCap];
table = newTab;
if (oldTab != null) { // 调整数组大小之后,需要调整红黑树或者链表的指向
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) // 红黑树调整
((TreeNode<K,V>)e).split(this, newTab, j, oldCap);
else { // preserve order
// 链表调整
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;
}
// 链表转双向链表操作
final void treeifyBin(Node<K,V>[] tab, int hash) {
int n, index; Node<K,V> e;
// 如果元素总个数小于64,则继续进行扩容,结点指向调节
if (tab == null || (n = tab.length) < MIN_TREEIFY_CAPACITY)
resize();
// 先找到那个链表的头
else if ((e = tab[index = (n - 1) & hash]) != null) {
TreeNode<K,V> hd = null, tl = null;
do {
//创建红黑树根结点
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)
// 此处才是真正的转为红黑树
hd.treeify(tab);
}
}
//将链表中每个值进行红黑树插入操作
final void treeify(Node<K,V>[] tab) {
TreeNode<K,V> root = null;
// TreeNode<K,V> x = this 相当于初始化了一个结点
for (TreeNode<K,V> x = this, next; x != null; x = next) {
next = (TreeNode<K,V>)x.next;
// 初始化Root
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 &&
// comparableClassFor(k) 返回 k 类型的比较器
(kc = comparableClassFor(k)) == null) ||
// compareComparables(kc, k, pk) 返回p,pk比较的结果
(dir = compareComparables(kc, k, pk)) == 0)
// tieBreakOrder(k, pk) 比较两个hash码
dir = tieBreakOrder(k, pk);
// 此处进行红黑树操作
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;
// 平衡调节
root = balanceInsertion(root, x);
break;
}
}
}
}
// 确保给定的根是根结点
moveRootToFront(tab, root);
}
如果存在,则从此映射中删除指定键的映射。
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.
* - 实现了与remove相关操作
* @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
* @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) {
Node<K,V>[] tab; Node<K,V> p; int n, index;
//table不为空
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;
//如果要删除的结点和table中p结点的hash值,key值相同的话
if (p.hash == hash && ((k = p.key) == key || (key != null && key.equals(k))))
node = p;
else if ((e = p.next) != null) {
//如果是红黑树结点,则进行红黑树查找key对应的value
if (p instanceof TreeNode)
node = ((TreeNode<K,V>)p).getTreeNode(hash, key);
else {
// 链表循环遍历获取ke对应的value
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)))) {
//如果是红黑树,则进行红黑树删除
if (node instanceof TreeNode)
((TreeNode<K,V>)node).removeTreeNode(this, tab, movable);
else if (node == p) //头元素的删除
tab[index] = node.next;
else //非头元素的删除
p.next = node.next;
//操作的次数
++modCount;
//长度减一
--size;
afterNodeRemoval(node); //回调以允许LinkedHashMap后置操作
return node;
}
}
return null;
}