HashMap
2017-03-26 本文已影响0人
Jokerone_
java version "1.7.0_75"
1.png
特点
HashMap内部是链式数组。是一种键值对的存储结构。
key和value都可以为空。key不允许重复，value允许重复。无序的（遍历顺序和存储顺序肯定不同）。非线程安全。
问题
为什么HashMap中的数组大小必须是2的N次幂？
<small>答：看下图，左边两组是数组长度为16（2的4次方），右边两组是数组长度为15。两组的hashcode均为8和9，但是很明显，当它们和1110“与”的时候，产生了相同的结果，也就是说它们会定位到数组中的同一个位置上去，这就产生了碰撞，8和9会被放到同一个链表上，那么查询的时候就需要遍历这个链表，得到8或者9，这样就降低了查询的效率。同时，我们也可以发现，当数组长度为15的时候，hashcode的值会与14（1110）进行“与”，那么最后一位永远是0，而0001，0011，0101，1001，1011，0111，1101这几个位置永远都不能存放元素了，空间浪费相当大，更糟的是这种情况中，数组可以使用的位置比数组长度小了很多，这意味着进一步增加了碰撞的几率，减慢了查询的效率！
2
所以说，当数组长度为2的n次幂的时候，不同的key算得得index相同的几率较小，那么数据在数组上分布就比较均匀，也就是说碰撞的几率小，相对的，查询的时候就不用遍历某个位置上的链表，这样查询效率也就较高了。</small>
HashMap扩容在什么情况下会导致死循环？
<small>答：不正确地使用HashMap引发死循环及元素丢失
</small>
HashMap的table为什么是transient的？
<small>答：HashCode和底层实现有关，不同的虚拟机可能有不同的HashCode算法。
如果table不被transient修饰，那么hashMap对象序列化之后，在虚拟机A上可用的程序到虚拟机B上可能就不能用了，失去了跨平台性。
为了避免这一点，Java采取了重写自己序列化table的方法，在writeObject选择将key和value追加到序列化的文件最后面
</small>
HashMap中为什么要对key的HashCode做一次rehash？
<small>答：防止一些key糟糕的Hash算法生成糟糕的HashCode。我们是通过hashCode来确定元素在动态数组中的位置。为了使entry均匀地分布在table上，我们要求hashCode有很强的随机性。因为在链表遍历中，有对key的equals比较：if (e.hash == hash && ((k = e.key) == key || key.equals(k)))，如果hash冲突概率大，意味着equals的比较次数增多，必然降低了hashMap的效率了。
</small>
基本属性
/**
* The default initial capacity - MUST be a power of two.
*/
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.
*/
static final int MAXIMUM_CAPACITY = 1 << 30;
/**
* The load factor used when none specified in constructor.
*/
static final float DEFAULT_LOAD_FACTOR = 0.75f;
/**
* An empty table instance to share when the table is not inflated.
*/
static final Entry<?,?>[] EMPTY_TABLE = {};
/**
* The table, resized as necessary. Length MUST Always be a power of two.
*/
transient Entry<K,V>[] table = (Entry<K,V>[]) EMPTY_TABLE;
/**
* The number of key-value mappings contained in this map.
*/
transient int size;
/**
* The next size value at which to resize (capacity * load factor).
* @serial
*/
// If table == EMPTY_TABLE then this is the initial capacity at which the
// table will be created when inflated.
int threshold;//hashMaprehash的阈值。
/**
* The load factor for the hash table.
*
* @serial
*/
final float loadFactor;
/**
* 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;
其中Entry的定义：
可以看出Entry构成了一个单向链表（之后后继entry没有前驱entry）。
static class Entry<K,V> implements Map.Entry<K,V> {
final K key;
V value;
Entry<K,V> next;
int hash;
/**
* Creates new entry.
*/
Entry(int h, K k, V v, Entry<K,V> n) {
value = v;
next = n;
key = k;
hash = h;
}
...
...
}
构造器
/**
* Constructs an empty <tt>HashMap</tt> with the default initial capacity
* (16) and the default load factor (0.75).
*/
public HashMap() {
this(DEFAULT_INITIAL_CAPACITY, DEFAULT_LOAD_FACTOR);
}
/**
* Constructs an empty <tt>HashMap</tt> with the specified initial
* capacity and load factor.
*
* @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) {
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;
threshold = initialCapacity;
init();
}
//给hashmap的子类进行实现，如linkedHashMap。
void init() {
}
put()
/**
* 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 <tt>key</tt>, or
* <tt>null</tt> if there was no mapping for <tt>key</tt>.
* (A <tt>null</tt> return can also indicate that the map
* previously associated <tt>null</tt> with <tt>key</tt>.)
*/
public V put(K key, V value) {
if (table == EMPTY_TABLE) {
//填充hashTable的值，即动态初始化数组大小为16。
inflateTable(threshold);
}
if (key == null)
return putForNullKey(value);//key为null的值都存入table[0]中，但是table[0]中会有其他key值的。
int hash = hash(key);//对key再做一次hash，减少hashMap中的hash碰撞。
int i = indexFor(hash, table.length);//确定此键值存放的动态数组的位置。
//遍历当前数组位置中的链表，如果存在此key，则覆盖，否则添加一个Entry
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;
}
}
modCount++;
addEntry(hash, key, value, i);
return null;
}
/**
* Returns index for hash code h.
*/
static int indexFor(int h, int length) {
// assert Integer.bitCount(length) == 1 : "length must be a non-zero power of 2";
return h & (length-1);
}
/**
* 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.
*/
//当hashMap中元素个数大于等于阈值时，将hashTable扩容为原来的两倍，并进行rehash，重新分配原来的元素。
void addEntry(int hash, K key, V value, int bucketIndex) {
if ((size >= threshold) && (null != table[bucketIndex])) {
resize(2 * table.length);
hash = (null != key) ? hash(key) : 0;
bucketIndex = indexFor(hash, table.length);
}
createEntry(hash, key, value, bucketIndex);
}
get()
public V get(Object key) {
if (key == null)
return getForNullKey();
Entry<K,V> entry = getEntry(key);
return null == entry ? null : entry.getValue();
}
/**
* Returns the entry associated with the specified key in the
* HashMap. Returns null if the HashMap contains no mapping
* for the key.
*/
final Entry<K,V> getEntry(Object key) {
if (size == 0) {
return null;
}
int hash = (key == null) ? 0 : hash(key);
for (Entry<K,V> e = table[indexFor(hash, table.length)];
e != null;
e = e.next) {
Object k;
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
return e;
}
return null;
}
remove()
/**
* 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 <tt>key</tt>, or
* <tt>null</tt> if there was no mapping for <tt>key</tt>.
* (A <tt>null</tt> return can also indicate that the map
* previously associated <tt>null</tt> with <tt>key</tt>.)
*/
public V remove(Object key) {
Entry<K,V> e = removeEntryForKey(key);
return (e == null ? null : e.value);
}
/**
* Removes and returns the entry associated with the specified key
* in the HashMap. Returns null if the HashMap contains no mapping
* for this key.
*/
final Entry<K,V> removeEntryForKey(Object key) {
if (size == 0) {
return null;
}
int hash = (key == null) ? 0 : hash(key);
int i = indexFor(hash, table.length);
Entry<K,V> prev = table[i];
Entry<K,V> e = prev;
while (e != null) {
Entry<K,V> next = e.next;
Object k;
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k)))) {
modCount++;
size--;
if (prev == e)
table[i] = next;
else
prev.next = next;
e.recordRemoval(this);
return e;
}
prev = e;
e = next;
}
return e;
}
