目录
2.3.5 addEntry方法和createEntry方法
2.3.7 transfer方法:扩容时将当前哈希表数据复制到新的哈希表
1. HashMap结构特点
HashMap基于哈希表的Map接口实现，采用Entry数组+链表存储，Entry以key-value形式存储，其中key是可以允许为null但是只能是一个，并且key不允许重复(如果重复则新值覆盖旧值)。通过计算key的hash值来找Entry数组的索引，如果Entry数组索引位置上为空，则将值放入索引处，如果不为空，则插入到链表头。计算key的hash函数及插入的函数在后面会提到
2. JDK7 HashMap
2.1 HashMap的参数
/**
* The default initial capacity - MUST be a power of two.
*/
static final int DEFAULT_INITIAL_CAPACITY = 16; //默认的初始容量为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.
*/
static final int MAXIMUM_CAPACITY = 1 << 30; //最大的容量为 2 ^ 30
/**
* The load factor used when none specified in constructor.
*/
static final float DEFAULT_LOAD_FACTOR = 0.75f; //默认的负载因子为 0.75f
/**
* The table, resized as necessary. Length MUST Always be a power of two.
*/
transient Entry<K,V>[] table; //存放数据的Entry数组
/**
* The number of key-value mappings contained in this map.
*/
transient int size; 记录了Map中Entry<K,V>的个数
/**
* The next size value at which to resize (capacity * load factor).
* @serial
*/
int threshold; //阈值 table为空，初始为默认16，table不为空时，为capacity*loadFactory
/**
* The load factor for the hash table.
*
* @serial
*/
final float loadFactor; //负载因子
/**
* 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).
*/
transient int modCount;//记录修改次数，多线程情况下，当出现expectedModCount和ModCount不相等，抛出ConcurrentModificationException异常
/**
* The default threshold of map capacity above which alternative hashing is
* used for String keys. Alternative hashing reduces the incidence of
* collisions due to weak hash code calculation for String keys.
* <p/>
* This value may be overridden by defining the system property
* {@code jdk.map.althashing.threshold}. A property value of {@code 1}
* forces alternative hashing to be used at all times whereas
* {@code -1} value ensures that alternative hashing is never used.
*/
//阈值的默认值
static final int ALTERNATIVE_HASHING_THRESHOLD_DEFAULT = Integer.MAX_VALUE;2.2 HashMap构造函数
public HashMap(int initialCapacity, float loadFactor) {
//初始容量大于0 ，否则抛出异常
if (initialCapacity < 0)
throw new IllegalArgumentException("Illegal initial capacity: " +
initialCapacity);
//初始容量不能超过2^30 (1073741824)
if (initialCapacity > MAXIMUM_CAPACITY)
initialCapacity = MAXIMUM_CAPACITY;
//加载因子不能小于等于0,或者加载因子不能是非数字,否则抛异常
if (loadFactor <= 0 || Float.isNaN(loadFactor))
throw new IllegalArgumentException("Illegal load factor: " +
loadFactor);
// Find a power of 2 >= initialCapacity
//初始容量为1 ,while循环确保容量为大于initialCapacity的最小的2次方幂
int capacity = 1;
while (capacity < initialCapacity)
capacity <<= 1; //capacity 左移一位
//设置负载因子
this.loadFactor = loadFactor;
//设置临界值
threshold = (int)Math.min(capacity * loadFactor, MAXIMUM_CAPACITY + 1);
//初始化table
table = new Entry[capacity];
useAltHashing = sun.misc.VM.isBooted() &&
(capacity >= Holder.ALTERNATIVE_HASHING_THRESHOLD);
init();
}
/**
* Constructs an empty <tt>HashMap</tt> 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 <tt>HashMap</tt> with the default initial capacity
* (16) and the default load factor (0.75).
*/
public HashMap() {
//无参构造器 默认16，负载因子是0.75f
this(DEFAULT_INITIAL_CAPACITY, DEFAULT_LOAD_FACTOR);
}
/**
* Constructs a new <tt>HashMap</tt> with the same mappings as the
* specified <tt>Map</tt>. The <tt>HashMap</tt> is created with
* default load factor (0.75) and an initial capacity sufficient to
* hold the mappings in the specified <tt>Map</tt>.
*
* @param m the map whose mappings are to be placed in this map
* @throws NullPointerException if the specified map is null
*/
/**
* 待补充
*/
public HashMap(Map<? extends K, ? extends V> m) {
this(Math.max((int) (m.size() / DEFAULT_LOAD_FACTOR) + 1,
DEFAULT_INITIAL_CAPACITY), DEFAULT_LOAD_FACTOR);
putAllForCreate(m);
}2.3 HashMap添加新的<K,V>应用的方法
2.3.1 put方法
public V put(K key, V value) {
//如果key等于null，存储位置为table[0]或table[0]的链表
if (key == null)
return putForNullKey(value);
//计算hashcode
int hash = hash(key);
//获取在table中的索引
int i = indexFor(hash, table.length);
//在索引i位置上进行遍历，查找到hash值相等并且key相等时，覆盖value值并返回旧的value
for (Entry<K,V> e = table[i]; e != null; e = e.next) {
Object k;
if (e.hash == hash && ((k = e.key) == key || key.equals(k))) {
V oldValue = e.value;
e.value = value;
e.recordAccess(this);
return oldValue;
}
}
//修改次数加1
modCount++;
//i索引上新增一个entry
addEntry(hash, key, value, i);
return null;
}2.3.2 putForNullKey方法
/**
* Offloaded version of put for null keys
* key为空时调用该方法
*/
private V putForNullKey(V value) {
//查找哈希表中0索引的位置，是否不为空，如果不为空，则遍历0索引的链表
for (Entry<K,V> e = table[0]; e != null; e = e.next) {
//找到key==null的键值,覆盖并返回旧值
if (e.key == null) {
V oldValue = e.value;
e.value = value;
e.recordAccess(this);
return oldValue;
}
}
//修改次数加1
modCount++;
//添加新entry在哈希表0索引的位置
addEntry(0, null, value, 0);
return null;
}2.3.3 hash函数
hash函数可以将不同的key值输入，得到散列值，但散列值存在相同的情况。当散列值相同时，就会产生冲突，两个值会发生覆盖的可能，即hash冲突，这时需要解决hash冲突的方法，hashmap中使用的便是链地址法
1 开放地址法
1.1 线性探测
1.2 二次探测
1.3 再哈希法
2 链地址法 ：在哈希表的每个单元设置链表，数据的key值映射到哈希表的单元，数据项本身插入到链表中/**
* Retrieve object hash code and applies a supplemental hash function to the
* result hash, which defends against poor quality hash functions. This is
* critical because HashMap uses power-of-two length hash tables, that
* otherwise encounter collisions for hashCodes that do not differ
* in lower bits. Note: Null keys always map to hash 0, thus index 0.
*/
final int hash(Object k) {
//hash 函数，即散列函数,哈希函数
int h = 0;
if (useAltHashing) {
if (k instanceof String) {
return sun.misc.Hashing.stringHash32((String) k);
}
h = hashSeed;
}
h ^= k.hashCode();
// This function ensures that hashCodes that differ only by
// constant multiples at each bit position have a bounded
// number of collisions (approximately 8 at default load factor).
h ^= (h >>> 20) ^ (h >>> 12);
return h ^ (h >>> 7) ^ (h >>> 4);
}2.3.4 indexFor方法
/**
* Returns index for hash code h. 计算hashcode的index索引
*/
static int indexFor(int h, int length) {
/**
* HashMap的初始容量和扩容都是以2的次方来进行的，那么length-1换算成二进制的话肯定所有位都
* 为1，就比如2的3次方为8，length-1的二进制表示就是111， 而按位与计算的原则是两位同时
* 为“1”，结果才为“1”，否则为“0”。所以h& (length-1)运算从数值上来讲其实等价于对length取
* 模，也就是h%length。发生碰撞的几率较小
* 计算位与,长度必须是非0的2次方，
*/
return h & (length-1);
}2.3.5 addEntry方法和createEntry方法
/**
* Adds a new entry with the specified key, value and hash code to
* the specified bucket. It is the responsibility of this
* method to resize the table if appropriate.
*
* Subclass overrides this to alter the behavior of put method.
*/
void addEntry(int hash, K key, V value, int bucketIndex) {
//size大于等于临界值threshold并且哈希表索引位置不为空，将table扩容2倍
if ((size >= threshold) && (null != table[bucketIndex])) {
resize(2 * table.length);
//当key不等于Null时，计算key的hash值，否则hash值为0
hash = (null != key) ? hash(key) : 0;
//扩容之后重写计算哈希表的索引
bucketIndex = indexFor(hash, table.length);
}
//创建新的链表Entry节点
createEntry(hash, key, value, bucketIndex);
}
/**
* Like addEntry except that this version is used when creating entries
* as part of Map construction or "pseudo-construction" (cloning,
* deserialization). This version needn't worry about resizing the table.
*
* Subclass overrides this to alter the behavior of HashMap(Map),
* clone, and readObject.
*/
void createEntry(int hash, K key, V value, int bucketIndex) {
//创建新的e引用table[bucketIndex]的Entry,之后再创建新的entry，其entry.next指向e，相当于把新的entry插在了头部
Entry<K,V> e = table[bucketIndex];
table[bucketIndex] = new Entry<>(hash, key, value, e);
size++;
}2.3.6 resize方法： hashmap扩容
单线程情况下，resize是线程安全的，多线程时，线程不安全，有可能会形成循环链表
/**
* Rehashes the contents of this map into a new array with a
* larger capacity. This method is called automatically when the
* number of keys in this map reaches its threshold.
*
* If current capacity is MAXIMUM_CAPACITY, this method does not
* resize the map, but sets threshold to Integer.MAX_VALUE.
* This has the effect of preventing future calls.
*
* @param newCapacity the new capacity, MUST be a power of two;
* must be greater than current capacity unless current
* capacity is MAXIMUM_CAPACITY (in which case value
* is irrelevant).
*/
void resize(int newCapacity) {
//建一个Entry[]数组引用table数据
Entry[] oldTable = table;
//获取旧的长度
int oldCapacity = oldTable.length;
//当旧的长度达到最大值时，修改阈值为Tnteger的最大值
if (oldCapacity == MAXIMUM_CAPACITY) {
threshold = Integer.MAX_VALUE;
return;
}
//创建新的Entry数组，使用新的长度
Entry[] newTable = new Entry[newCapacity];
boolean oldAltHashing = useAltHashing;
useAltHashing |= sun.misc.VM.isBooted() &&
(newCapacity >= Holder.ALTERNATIVE_HASHING_THRESHOLD);
//计算是否要重写hash
boolean rehash = oldAltHashing ^ useAltHashing;
//将当前哈希表数据复制到新的哈希表
transfer(newTable, rehash);
//修改hashmap的table为新的table
table = newTable;
//修改阈值
threshold = (int)Math.min(newCapacity * loadFactor, MAXIMUM_CAPACITY + 1);
}2.3.7 transfer方法:扩容时将当前哈希表数据复制到新的哈希表
/**
* Transfers all entries from current table to newTable.
*/
void transfer(Entry[] newTable, boolean rehash) {
//计算容量
int newCapacity = newTable.length;
//遍历旧的table表
for (Entry<K,V> e : table) {
while(null != e) {
Entry<K,V> next = e.next;
//entry不为空时，如果要重写hash，则计算hash值
if (rehash) {
e.hash = null == e.key ? 0 : hash(e.key);
}
//定位hash索引位置
int i = indexFor(e.hash, newCapacity);
//相当于链表的插入，总是插入在前面，newTable[i]的值为e，之后继续e的下一个元素
e.next = newTable[i];
newTable[i] = e;
e = next;
}
}
}2.4. HashMap获取<K,V>
2.4.1 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.
*
* <p>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.)
*
* <p>A return value of {@code null} does not <i>necessarily</i>
* 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) {
//当key为null时，查找table表0位置的链表，如果找到key为null的则返回该Entry的value，否则返回null
if (key == null)
return getForNullKey();
Entry<K,V> entry = getEntry(key);
return null == entry ? null : entry.getValue();
}2.4.2 getForNullKey方法
/**
* Offloaded version of get() to look up null keys. Null keys map
* to index 0. This null case is split out into separate methods
* for the sake of performance in the two most commonly used
* operations (get and put), but incorporated with conditionals in
* others.
*/
private V getForNullKey() {
//查找table表0位置的链表，如果找到key为null的则返回该Entry的value，否则返回null
for (Entry<K,V> e = table[0]; e != null; e = e.next) {
if (e.key == null)
return e.value;
}
return null;
}3. JDK8 HashMap
3.1 JDK7与JDK8的区别
JDK7与JDK8中HashMap实现的最大区别就是对于冲突的处理方法。JDK 1.8 中引入了红黑树（查找时间复杂度为 O(logn)）,用数组+链表+红黑树的结构来优化这个问题。当链表长度大于等于8时，则将链表转化为红黑树
3.2 HashMap参数
/**
* The default initial capacity - MUST be a power of two.
*/
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16 默认初始化容量 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.
*/
static final int MAXIMUM_CAPACITY = 1 << 30;//最大的容量大小2^30
/**
* The load factor used when none specified in constructor.
*/
static final float DEFAULT_LOAD_FACTOR = 0.75f;//默认负载因子
/**
* 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.
*/
static final int TREEIFY_THRESHOLD = 8; //阈值 8，当单个segment的容量超过阈值时，将链表转化为红黑树。
/**
* 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.
*/
static final int UNTREEIFY_THRESHOLD = 6;//链表化阈值 6。当resize后或者删除操作后单个segment的容量低于阈值时，将红黑树转化为链表。
/**
* 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.
*/
static final int MIN_TREEIFY_CAPACITY = 64; //最小树化容量 64。当桶中的bin被树化时最小的hash表容量，低于该容量时不会树化。
3.3 put函数
流程：
1. 判断table是否为空或长度等于0，否则resize扩容
2. 根据键值key计算hash值得到索引i，如果table[i]为空，直接新建node添加，并跳出循环，如果table[i]不为空，进入else判断
3. 判断table[i]的首个元素是否和key一样，如果相同直接覆盖value，否则转向else if
4. else if判断是否是红黑树结点，如果是，则新增红黑树结点，否则进入else遍历
5. 遍历table[i],遍历到链表尾依然为空，则新增链表结点，并判断长度是否大于等于8，是则转换为红黑树，如果遍历过程中找到key值相等的，则覆盖value
6. 插入成功后判断size是否大于threshold，是则扩容
/**
* 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) {
Node<K,V>[] tab; Node<K,V> p; int n, i;
//判断table是否为空或者length=0，如果是，则进行扩容
if ((tab = table) == null || (n = tab.length) == 0)
n = (tab = resize()).length;
//hash值与n-1与运算获得索引i，如果i位置为空，则插入新node，否则进入else判断
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null);
else {
Node<K,V> e; K k;
//判断node的hash与key值是否相等，如果相等，则将p赋值给e,(node已存在)
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
e = p;
//判断是否为红黑树，如果是，直接在红黑树插入键值对
else if (p instanceof TreeNode)
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
else {
//遍历table[i],链表尾部插入新node后，判断binCount是否大于等于7，即长度是否大于等于8，大于8则转化为红黑树
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;
}
//遍历的时候若找到hash与key都相等，则跳出，进行value覆盖
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
break;
p = e;
}
}
//e不等于null时，代表node已存在，则直接覆盖value，并返回旧值
if (e != null) { // existing mapping for key
V oldValue = e.value;
if (!onlyIfAbsent || oldValue == null)
e.value = value;
afterNodeAccess(e);
return oldValue;
}
}
//修改次数加1
++modCount;
//size大于threshold，进行扩容
if (++size > threshold)
resize();
afterNodeInsertion(evict);
return null;
}3.3 hash函数
根据key值计算出hash值，再对32位的hashcode高16位和低16位进行异或，大大减少了哈希冲突
/**
* 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.
*/
static final int hash(Object key) {
//hash函数,key不为空时，将hashcode右移16位，低16位与高16位进行异或操作，将高位信息存储到低位，目的减少冲突的可能
int h;
return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}3.4 resize函数
HashMap扩容不需要像JDK1.7重新计算hash，只需要判断原来的hash值新增的那个bit是1还是0，0的话索引没变（因为任何数与0与都依旧是0），bit为1 ，则index变成原索引+oldCap，oldCap为原hashmap的length
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) // initial capacity was placed in threshold
newCap = oldThr;
else { // zero initial threshold signifies using defaults
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];
table = newTab;
if (oldTab != null) {
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)
((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 {
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;
}
110
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
