JAVA读源码之-HashMap
提交于 2021-01-11
本篇文章是类似笔记的形式。文笔写不好，而且会大量摘抄别人的文章。
- 参考视频 https://www.bilibili.com/video/BV1LJ411W7dP?p=6
- 参考文档 https://gitee.com/gu_chun_bo/java-construct/blob/d466640dc977a61433fecbbb069ffe7a56d46d1a/java%E9%9B%86%E5%90%88/HashMap.md
底层结构
数组+ 链表+ 红黑树
image
类图
image
image
内部结构
Node
HashMap中元素是通过 Node数组、Node链表、红黑树存储的。 Node起到承载数据的作用，也是通过Node实现链表的。
/**
* Basic hash bin node, used for most entries. (See below for
* TreeNode subclass, and in LinkedHashMap for its Entry subclass.)
*/
static class Node implements Map.Entry {
//可以理解为Hash地址。不过是经过扰动的Hash地址
final int hash;
// 也就是Map的key
final K key;
// 也就是Map的value
V value;
// 链表结构。hash碰撞出现的话。会存到next中。 可以看上面的示意图。
Node next;
Node(int hash, K key, V value, Node 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;
}
}
类定义
public class HashMap extends AbstractMap implements Map, Cloneable, Serializable {}
AbstractMap : 抽抽象类。提供方法封装。 不过HashMap把大部分方法重写了。就不一一列举了。
Cloneable : 克隆。
- cloneable其实就是一个标记接口，只有实现这个接口后，然后在类中重写Object中的clone方法，然后通过类调用clone方法才能克隆成功，如果不实现这个接口，则会抛出CloneNotSupportedException(克隆不被支持)异常。
- 相关联的知识还有深克隆和浅克隆
- 设计模式 `原型模式` 就是依据 cloneable 接口实现的。感兴趣的可以看一下。
Serializable: 序列化
代码分析
常量
/**
* The default initial capacity - MUST be a power of two.
*
* 缺省table大小
*/
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.
*
* table最大长度
*/
static final int MAXIMUM_CAPACITY = 1 << 30;
/**
* The load factor used when none specified in constructor.
*
* 缺省负载因子大小
*/
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.
*
* 树化阈值
* 插入数据时，如果链表过长时，将链表转化为红黑树
* 具体算法看代码
*/
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.
*
* 树降级称为链表的阈值
*/
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.
*
* 树化的另一个参数，当哈希表中的所有元素个数超过64时，才会允许树化
*/
static final int MIN_TREEIFY_CAPACITY = 64;
重点
数化
Todo
成员变量
transientjava关键字。表示不序列化 百度百科
/* ---------------- Fields -------------- */
/**
* 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.)
*
* 哈希表
*
* 什么时候初始化？
* //延迟初始化逻辑，第一次调用putVal时会初始化hashMap对象中的最耗费内存的散列表
* if ((tab = table) == null || (n = tab.length) == 0)
* n = (tab = resize()).length;
*
*/
transient Node[] table;
/**
* Holds cached entrySet(). Note that AbstractMap fields are used
* for keySet() and values().
*/
transient Set> entrySet;
/**
* The number of key-value mappings contained in this map.
* 当前哈希表中元素个数
*/
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).
*
* 当前哈希表结构修改次数
*/
transient int modCount;
/**
* The next size value at which to resize (capacity * load factor).
*
* 扩容阈值，当你的哈希表中的元素超过阈值时，触发扩容
* @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.)
int threshold;
/**
* The load factor for the hash table.
*
* 负载因子
*
* threshold = capacity * loadFactor
*
* @serial
*/
final float loadFactor;
构造方法
/* ---------------- Public operations -------------- */
/**
* Constructs an empty HashMap with the specified initial
* capacity and load factor.
*
* @param initialCapacity the initial capacity 初始容量
* @param loadFactor the load factor 负载因子
* @throws IllegalArgumentException if the initial capacity is negative
* or the load factor is nonpositive
*/
public HashMap(int initialCapacity, float loadFactor) {
//其实就是做了一些校验
//capacity必须是大于0 ，最大值也就是 MAX_CAP
if (initialCapacity < 0)
throw new IllegalArgumentException("Illegal initial capacity: " +
initialCapacity);
if (initialCapacity > MAXIMUM_CAPACITY)
initialCapacity = MAXIMUM_CAPACITY;
//loadFactor必须大于0
if (loadFactor <= 0 || Float.isNaN(loadFactor))
throw new IllegalArgumentException("Illegal load factor: " +
loadFactor);
this.loadFactor = loadFactor;
this.threshold = tableSizeFor(initialCapacity);
}
/**
* Constructs an empty HashMap with the specified initial
* capacity and the default load factor (0.75).
*
* @param initialCapacity the initial capacity.
* @throws IllegalArgumentException if the initial capacity is negative.
*/
public HashMap(int initialCapacity) {
this(initialCapacity, DEFAULT_LOAD_FACTOR);
}
/**
* Constructs an empty HashMap with the default initial capacity
* (16) and the default load factor (0.75).
*/
public HashMap() {
this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted
}
/**
* 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
* @throws NullPointerException if the specified map is null
*/
public HashMap(Map m) {
this.loadFactor = DEFAULT_LOAD_FACTOR;
putMapEntries(m, false);
}
/**
* Implements Map.putAll and Map constructor.
*
* @param m the map
* @param evict false when initially constructing this map, else
* true (relayed to method afterNodeInsertion).
*/
final void putMapEntries(Map 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 < (float)MAXIMUM_CAPACITY) ?
(int)ft : MAXIMUM_CAPACITY);
if (t > threshold)
threshold = tableSizeFor(t);
}
else if (s > threshold)
resize();
for (Map.Entry e : m.entrySet()) {
K key = e.getKey();
V value = e.getValue();
putVal(hash(key), key, value, false, evict);
}
}
}
tableSizeFor
位运算（二进制，说实话看不懂）
/**
* Returns a power of two size for the given target capacity.
* 作用：返回一个大于等于当前值cap的一个数字，并且这个数字一定是2的次方数
*
* cap = 10
* n = 10 - 1 => 9
* 0b1001 | 0b0100 => 0b1101
* 0b1101 | 0b0011 => 0b1111
* 0b1111 | 0b0000 => 0b1111
*
* 0b1111 => 15
*
* return 15 + 1;
*
* cap = 16
* n = 16;
* 0b10000 | 0b01000 =>0b11000
* 0b11000 | 0b00110 =>0b11110
* 0b11110 | 0b00001 =>0b11111
* =>0b11111 => 31
* return 31 + 1;
*
* 0001 1101 1100 => 0001 1111 1111 + 1 => 0010 0000 0000 一定是2的次方数
*
*/
static final int tableSizeFor(int cap) {
int n = cap;
n |= n >>> 1;
n |= n >>> 2;
n |= n >>> 4;
n |= n >>> 8;
n |= n >>> 16;
// 套娃三目运算
return (n < 0) ? 1 : (n >= MAXIMUM_CAPACITY) ? MAXIMUM_CAPACITY : n + 1;
}
put方法
image
/**
* 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 key, or
* null if there was no mapping for key.
* (A null return can also indicate that the map
* previously associated null with key.)
* 返回先前key对应的value值（如果value为null，也返回null），如果先前不存在这个key，那么返回的就是null；
*/
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
*/
final V putVal(int hash, K key, V value, boolean onlyIfAbsent,
boolean evict) {
//tab：表示当前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 结果
Node[] tab; Node p; int n, i;
//延迟初始化逻辑，第一次调用putVal时会初始化hashMap对象中的最耗费内存的散列表
if ((tab = table) == null || (n = tab.length) == 0)
n = (tab = resize()).length;
//最简单的一种情况：寻址找到的桶位 刚好是 null，这个时候，直接将当前k-v=>node 扔进去就可以了
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null);
else {
//e：不为null的话，找到了一个与当前要插入的key-value一致的key的元素
//k：表示临时的一个key
Node e; K k;
//表示桶位中的该元素，与你当前插入的元素的key完全一致，表示后续需要进行替换操作
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
e = p;
else if (p instanceof TreeNode)//红黑树，下期讲。进QQ群:865-373-238
e = ((TreeNode)p).putTreeVal(this, tab, hash, key, value);
else {
//链表的情况，而且链表的头元素与我们要插入的key不一致。
for (int binCount = 0; ; ++binCount) {
//条件成立的话，说明迭代到最后一个元素了，也没找到一个与你要插入的key一致的node
//说明需要加入到当前链表的末尾
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，达到树化标准了，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，说明找到了相同key的node元素，需要进行替换操作
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
break;
p = e;
}
}
//e不等于null，条件成立说明，找到了一个与你插入元素key完全一致的数据，需要进行替换
if (e != null) { // existing mapping for key
V oldValue = e.value;
if (!onlyIfAbsent || oldValue == null)
e.value = value;
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，则触发扩容。
if (++size > threshold)
resize();
afterNodeInsertion(evict);
return null;
}
hash 方法
- 小知识。 key是null的话。那它一定是放在第0位。
(key == null) ? 0 : - 这就是前面有说的扰动方法，让key值算出的hash值更均匀，减少hash碰撞的几率。也就提高了性能。 hash碰撞多了,就会加快数据向链表转化，向树转化。
/**
* 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.
*
* 作用：让key的hash值的高16位也参与路由运算
* 异或：相同则返回0，不同返回1
*
* h = 0b 0010 0101 1010 1100 0011 1111 0010 1110
* 0b 0010 0101 1010 1100 0011 1111 0010 1110
* ^
* 0b 0000 0000 0000 0000 0010 0101 1010 1100
* => 0010 0101 1010 1100 0001 1010 1000 0010
*/
static final int hash(Object key) {
int h;
return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}
resize方法
重新计算大小。会涉及到链表转换和树化。也就是咱们说的自动扩容
//插入新元素，size自增，如果自增后的值大于扩容阈值，则触发扩容。
if (++size > threshold)
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[] resize() {
//oldTab：引用扩容前的哈希表
Node[] oldTab = table;
//oldCap：表示扩容之前table数组的长度
int oldCap = (oldTab == null) ? 0 : oldTab.length;
//oldThr：表示扩容之前的扩容阈值，触发本次扩容的阈值
int oldThr = threshold;
//newCap：扩容之后table数组的大小
//newThr：扩容之后，下次再次触发扩容的条件
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，这是一次正常扩容
if (oldCap > 0) {
//扩容之前的table数组大小已经达到 最大阈值后，则不扩容，且设置扩容条件为 int 最大值。
if (oldCap >= MAXIMUM_CAPACITY) {
threshold = Integer.MAX_VALUE;
return oldTab;
}
//oldCap左移一位实现数值翻倍，并且赋值给newCap， newCap 小于数组最大值限制 且 扩容之前的阈值 >= 16
//这种情况下，则 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;//16
newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);//12
}
//newThr为零时，通过newCap和loadFactor计算出一个newThr
if (newThr == 0) {
float ft = (float)newCap * loadFactor;
newThr = (newCap < MAXIMUM_CAPACITY && ft < (float)MAXIMUM_CAPACITY ?
(int)ft : Integer.MAX_VALUE);
}
threshold = newThr;
//创建出一个更长 更大的数组
@SuppressWarnings({"rawtypes","unchecked"})
Node[] newTab = (Node[])new Node[newCap];
table = newTab;
//说明，hashMap本次扩容之前，table不为null
if (oldTab != null) {
for (int j = 0; j < oldCap; ++j) {
//当前node节点
Node e;
//说明当前桶位中有数据，但是数据具体是 单个数据，还是链表 还是 红黑树 并不知道
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，这情况 直接计算出当前元素应存放在 新数组中的位置，然后
//扔进去就可以了
if (e.next == null)
newTab[e.hash & (newCap - 1)] = e;
//第二种情况：当前节点已经树化，本期先不讲，下一期讲，红黑树。QQ群：865-373-238
else if (e instanceof TreeNode)
((TreeNode)e).split(this, newTab, j, oldCap);
else { // preserve order
//第三种情况：桶位已经形成链表
//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 loHead = null, loTail = null;
//高位链表：存放在扩容之后的数组的下表位置为 当前数组下标位置 + 扩容之前数组的长度
Node hiHead = null, hiTail = null;
Node next;
do {
next = e.next;
//hash-> .... 1 1111
//hash-> .... 0 1111
// 0b 10000
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;
}
get方法
/**
* Returns the value to which the specified key is mapped,
* or {@code null} if this map contains no mapping for the key.
*
* 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.)
*
*
A return value of {@code null} does not necessarily
* 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 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 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[] tab; Node 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 即为咱们要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 也可能是 红黑树
if ((e = first.next) != null) {
//第二种情况：桶位升级成了 红黑树
if (first instanceof TreeNode)//下一期说
return ((TreeNode)first).getTreeNode(hash, key);
//第三种情况：桶位形成链表
do {
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
return e;
} while ((e = e.next) != null);
}
}
return null;
}
remove方法
/**
* 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 key, or
* null if there was no mapping for key.
* (A null return can also indicate that the map
* previously associated null with key.)
*/
public V remove(Object key) {
Node 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
* @param movable if false do not move other nodes while removing
* @return the node, or null if none
*/
final Node removeNode(int hash, Object key, Object value,
boolean matchValue, boolean movable) {
//tab：引用当前hashMap中的散列表
//p：当前node元素
//n：表示散列表数组长度
//index：表示寻址结果
Node[] tab; Node 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：查找到的结果
//e：当前Node的下一个元素
Node node = null, e; K k; V v;
//第一种情况：当前桶位中的元素 即为 你要删除的元素
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
node = p;
else if ((e = p.next) != null) {
//说明，当前桶位 要么是 链表 要么 是红黑树
if (p instanceof TreeNode)//判断当前桶位是否升级为 红黑树了
//第二种情况
//红黑树查找操作，下一期再说
node = ((TreeNode)p).getTreeNode(hash, key);
else {
//第三种情况
//链表的情况
do {
if (e.hash == hash &&
((k = e.key) == key ||
(key != null && key.equals(k)))) {
node = e;
break;
}
p = e;
} while ((e = e.next) != null);
}
}
//判断node不为空的话，说明按照key查找到需要删除的数据了
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)node).removeTreeNode(this, tab, movable);
//第二种情况：桶位元素即为查找结果，则将该元素的下一个元素放至桶位中
else if (node == p)
tab[index] = node.next;
else
//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。
p.next = node.next;
++modCount;
--size;
afterNodeRemoval(node);
return node;
}
}
return null;
}
replace方法
@Override
public boolean replace(K key, V oldValue, V newValue) {
Node 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;
}
@Override
public V replace(K key, V value) {
Node e;
if ((e = getNode(hash(key), key)) != null) {
V oldValue = e.value;
e.value = value;
afterNodeAccess(e);
return oldValue;
}
return null;
}
中文注释后的源码
链接 》