环境
C:\Users\chwl>java -version
java version "1.7.0_51"
Java(TM) SE Runtime Environment (build 1.7.0_51-b13)
Java HotSpot(TM) 64-Bit Server VM (build 24.51-b03, mixed mode)
介绍
HashMap底层使用hash表实现，解决冲突的方法是链地址法，简单理解起来就是采用数组加链表得数据结构来存储数据。
哈希表以及存储节点的定义。
//哈希表
transient Entry<K,V>[] table = (Entry<K,V>[]) EMPTY_TABLE;
//存储节点定义（单链表）
static class Entry<K,V> implements Map.Entry<K,V> {
final K key;
V value;
Entry<K,V> next;
int hash;
Entry(int h, K k, V v, Entry<K,V> n) {
value = v;
next = n;
key = k;
hash = h;
}
public final K getKey() {
return key;
}
public final V getValue() {
return value;
}
public final V setValue(V newValue) {
V oldValue = value;
value = newValue;
return oldValue;
}
public final boolean equals(Object o) {
if (!(o instanceof Map.Entry))
return false;
Map.Entry e = (Map.Entry)o;
Object k1 = getKey();
Object k2 = e.getKey();
if (k1 == k2 || (k1 != null && k1.equals(k2))) {
Object v1 = getValue();
Object v2 = e.getValue();
if (v1 == v2 || (v1 != null && v1.equals(v2)))
return true;
}
return false;
}
public final int hashCode() {
return Objects.hashCode(getKey()) ^ Objects.hashCode(getValue());
}
public final String toString() {
return getKey() + "=" + getValue();
}
void recordAccess(HashMap<K,V> m) {
}
void recordRemoval(HashMap<K,V> m) {
}
}
下面开始分析HashMap的源代码，从数据的增删该查等方面进行分析。
签名
public class HashMap<K,V>
extends AbstractMap<K,V>
implements Map<K,V>, Cloneable, Serializable
创建HashMap
1.构造函数
设置HashMap的初始化大小initialCapacity和平衡因子loadFactor;
无参构造函数使用默认的初始化大小16，平衡因子0.75；
当entry数大于capacity*loadFactor时，HashMap考虑进行resize。
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();
}
public HashMap(int initialCapacity) {
this(initialCapacity, DEFAULT_LOAD_FACTOR);
}
public HashMap() {
this(DEFAULT_INITIAL_CAPACITY, DEFAULT_LOAD_FACTOR);
}
新增与修改
HashMap的新增与修改操作，通过put方法实现。
1.put方法源码
public V put(K key, V value) {
//table为空时，需初始化
if (table == EMPTY_TABLE) {
inflateTable(threshold);
}
//处理Null键
if (key == null)
return putForNullKey(value);
int hash = hash(key);
//索引桶的位置
int i = indexFor(hash, table.length);
for (Entry<K,V> e = table[i]; e != null; e = e.next) {
Object k;
//对已存在的键，覆盖其值
if (e.hash == hash && ((k = e.key) == key || key.equals(k))) {
V oldValue = e.value;
e.value = value;
//记录访问，Entry.recordAccess()在LinkedHashMap.Entry中覆盖，可用来实现LRU访问
e.recordAccess(this);
return oldValue;
}
}
modCount++;
addEntry(hash, key, value, i);
return null;
}
void addEntry(int hash, K key, V value, int bucketIndex) {
//是否重新调整table数组的大小
if ((size >= threshold) && (null != table[bucketIndex])) {
resize(2 * table.length);
hash = (null != key) ? hash(key) : 0;
bucketIndex = indexFor(hash, table.length);
}
//将元素添加到桶中，采用链表的头插法
createEntry(hash, key, value, bucketIndex);
}
void createEntry(int hash, K key, V value, int bucketIndex) {
//链表的头插法
Entry<K,V> e = table[bucketIndex];
table[bucketIndex] = new Entry<>(hash, key, value, e);
size++;
}
2.分析
使用put方法为HashMap新增键值对。
table为一个Entry<K,V>数组，Entry<k,v>为一个链表元素，也就是说table数组中存储的是链表，可把它看成bucket（桶）；
键的hash值相同的Entry存储在同一个bucket（桶）中；
源码采用函数indexFor来索引桶的位置，hash(key)和table.length-1作与运算，这样可确保所得结果处于0~table.length
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);
}
索引到数组的位置后，接着就是将元素存入相应的桶中，遍历桶中元素，将键值与入参键（key）比较，若相同，则替换掉键对应的值（value），此处不仅要比较hash值，还要equals比较。若桶中无相同键，调用addEntry新增元素。
addEntry并不是简单的往桶中添加的元素，如上文中提到，当entry数大于capacity*loadFactor时，会考虑进行resize。
void addEntry(int hash, K key, V value, int bucketIndex) {
//但size大于阀值，且当前桶为null时，进行resize
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);
}
resize根据initHashSeedAsNeeded(newCapacity)的返回值决定是否key进行rehash。
void resize(int newCapacity) {
Entry[] oldTable = table;
int oldCapacity = oldTable.length;
if (oldCapacity == MAXIMUM_CAPACITY) {
threshold = Integer.MAX_VALUE;
return;
}
Entry[] newTable = new Entry[newCapacity];
transfer(newTable, initHashSeedAsNeeded(newCapacity));
table = newTable;
threshold = (int)Math.min(newCapacity * loadFactor, MAXIMUM_CAPACITY + 1);
}
//用来改变hashSeed的值
final boolean initHashSeedAsNeeded(int capacity) {
boolean currentAltHashing = hashSeed != 0;
boolean useAltHashing = sun.misc.VM.isBooted() &&
(capacity >= Holder.ALTERNATIVE_HASHING_THRESHOLD);
boolean switching = currentAltHashing ^ useAltHashing;
if (switching) {
hashSeed = useAltHashing
? sun.misc.Hashing.randomHashSeed(this)
: 0;
}
return switching;
}
void transfer(Entry[] newTable, boolean rehash) {
int newCapacity = newTable.length;
for (Entry<K,V> e : table) {
while(null != e) {
Entry<K,V> next = e.next;
if (rehash) {
e.hash = null == e.key ? 0 : hash(e.key);
}
int i = indexFor(e.hash, newCapacity);
e.next = newTable[i];
newTable[i] = e;
e = next;
}
}
}
删除
1.remove方法源码
public V remove(Object key) {
Entry<K,V> e = removeEntryForKey(key);
return (e == null ? null : e.value);
}
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;
}
2.分析
remove方法与put方法原理大致相同。
通过key索引数组位置，遍历相应位置的桶，找到相同元素，执行链表删除。
查找
1.get方法源码
public V get(Object key) {
if (key == null)
return getForNullKey();
Entry<K,V> entry = getEntry(key);
return null == entry ? null : entry.getValue();
}
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;
}
2.分析
get方法调用getEntry,getEntry的实现与put和removeEntryForKey类似。
HashIterator
HashIterator是fast-fail的，若一线程在使用它遍历集合的同时，另一线程对集合中的元素进行了增减，则会抛出ConcurrentModificationException异常。
private abstract class HashIterator<E> implements Iterator<E> {
Entry<K,V> next; // next entry to return
int expectedModCount; // For fast-fail
int index; // current slot
Entry<K,V> current; // current entry
HashIterator() {
expectedModCount = modCount;
if (size > 0) { // advance to first entry
Entry[] t = table;
while (index < t.length && (next = t[index++]) == null)
;
}
}
public final boolean hasNext() {
return next != null;
}
final Entry<K,V> nextEntry() {
//通过判断集合size实现fast-fail
if (modCount != expectedModCount)
throw new ConcurrentModificationException();
Entry<K,V> e = next;
if (e == null)
throw new NoSuchElementException();
if ((next = e.next) == null) {
Entry[] t = table;
while (index < t.length && (next = t[index++]) == null)
;
}
current = e;
return e;
}
public void remove() {
if (current == null)
throw new IllegalStateException();
if (modCount != expectedModCount)
throw new ConcurrentModificationException();
Object k = current.key;
current = null;
HashMap.this.removeEntryForKey(k);
expectedModCount = modCount;
}
}
HashMap提供三种集合视角，均集成自HashIterator。
private final class ValueIterator extends HashIterator<V> {
public V next() {
return nextEntry().value;
}
}
private final class KeyIterator extends HashIterator<K> {
public K next() {
return nextEntry().getKey();
}
}
private final class EntryIterator extends HashIterator<Map.Entry<K,V>> {
public Map.Entry<K,V> next() {
return nextEntry();
}
}
Null键
HashMap允许使用Null作为键，相应的增删该查方法也有对Null键的特殊处理；
分析代码我们不难看出，Null键索引的是table[0]
private V putForNullKey(V value) {
for (Entry<K,V> e = table[0]; e != null; e = e.next) {
if (e.key == null) {
V oldValue = e.value;
e.value = value;
e.recordAccess(this);
return oldValue;
}
}
modCount++;
addEntry(0, null, value, 0);
return null;
}
private V getForNullKey() {
if (size == 0) {
return null;
}
for (Entry<K,V> e = table[0]; e != null; e = e.next) {
if (e.key == null)
return e.value;
}
return null;
}
removeEntryForKey也对Null键做了处理
int hash = (key == null) ? 0 : hash(key);
int i = indexFor(hash, table.length);
实现Cloneable接口
重写Object类中的clone方法，实现了浅拷贝。
1.clone方法源码
/**
* Returns a shallow copy of this <tt>HashMap</tt> instance: the keys and
* values themselves are not cloned.
*
* @return a shallow copy of this map
*/
public Object clone() {
HashMap<K,V> result = null;
try {
result = (HashMap<K,V>)super.clone();
} catch (CloneNotSupportedException e) {
// assert false;
}
if (result.table != EMPTY_TABLE) {
result.inflateTable(Math.min(
(int) Math.min(
size * Math.min(1 / loadFactor, 4.0f),
// we have limits...
HashMap.MAXIMUM_CAPACITY),
table.length));
}
result.entrySet = null;
result.modCount = 0;
result.size = 0;
result.init();
result.putAllForCreate(this);
return result;
}
private void putAllForCreate(Map<? extends K, ? extends V> m) {
for (Map.Entry<? extends K, ? extends V> e : m.entrySet())
putForCreate(e.getKey(), e.getValue());
}
private void putForCreate(K key, V value) {
int hash = null == key ? 0 : hash(key);
int i = indexFor(hash, table.length);
/**
* Look for preexisting entry for key. This will never happen for
* clone or deserialize. It will only happen for construction if the
* input Map is a sorted map whose ordering is inconsistent w/ equals.
*/
for (Entry<K,V> e = table[i]; e != null; e = e.next) {
Object k;
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k)))) {
e.value = value;
return;
}
}
createEntry(hash, key, value, i);
}
2.示例证明浅拷贝
package edu.zju.chwl.map;
import java.util.HashMap;
import org.junit.Test;
public class TestHashMap {
@Test
public void test() {
HashMap<String, Student> hashMap = new HashMap<String, Student>();
Student stu = new Student("tom", 26);
hashMap.put("tom", stu);
HashMap<String, String> cloneHashMap = (HashMap<String, String>) hashMap.clone();
stu.setName("tony");
System.out.println("hashMap:" + hashMap);
System.out.println("cloneHashMap:" + cloneHashMap);
}
class Student {
private String name;
private int age;
Student(String name, int age) {
this.name = name;
this.age = age;
}
public void setName(String name) {
this.name = name;
}
@Override
public String toString() {
return "name:" + name + ",age:" + age;
}
}
}
打印结果：
hashMap:{tom=name:tony,age:26}
cloneHashMap:{tom=name:tony,age:26}
证明clone方法并未对键，值进行深拷贝。
实现Serializable接口
保存Entry的table数组为transient的，也就是说在进行序列化时，并不会包含该成员，这是为什么呢？
transient Entry<K,V>[] table = (Entry<K,V>[]) EMPTY_TABLE;
我们可以试想下面的场景：
我们在机器A上算出对象A的哈希值与索引，然后把它插入到HashMap中，然后把该HashMap序列化后，在机器B上重新算对象的哈希值与索引，这与机器A上算出的可能是不一样的（取决于
hashCode方法的实现），所以我们在机器B上get对象A时，会得到错误的结果。所以说，当序列化一个HashMap对象时，保存Entry的table是不需要序列化进来的，因为它在另一台机器上是错误的。
HashMap实现自己的序列化，重现了readObject方法与writeObject方法。
//序列化
private void writeObject(java.io.ObjectOutputStream s)
throws IOException
{
// Write out the threshold, loadfactor, and any hidden stuff
s.defaultWriteObject();
// Write out number of buckets
if (table==EMPTY_TABLE) {
s.writeInt(roundUpToPowerOf2(threshold));
} else {
s.writeInt(table.length);
}
// Write out size (number of Mappings)
s.writeInt(size);
// Write out keys and values (alternating)
if (size > 0) {
for(Map.Entry<K,V> e : entrySet0()) {
s.writeObject(e.getKey());
s.writeObject(e.getValue());
}
}
}
//反序列化
private void readObject(java.io.ObjectInputStream s)
throws IOException, ClassNotFoundException
{
// Read in the threshold (ignored), loadfactor, and any hidden stuff
s.defaultReadObject();
if (loadFactor <= 0 || Float.isNaN(loadFactor)) {
throw new InvalidObjectException("Illegal load factor: " +
loadFactor);
}
// set other fields that need values
table = (Entry<K,V>[]) EMPTY_TABLE;
// Read in number of buckets
s.readInt(); // ignored.
// Read number of mappings
int mappings = s.readInt();
if (mappings < 0)
throw new InvalidObjectException("Illegal mappings count: " +
mappings);
// capacity chosen by number of mappings and desired load (if >= 0.25)
int capacity = (int) Math.min(
mappings * Math.min(1 / loadFactor, 4.0f),
// we have limits...
HashMap.MAXIMUM_CAPACITY);
// allocate the bucket array;
if (mappings > 0) {
inflateTable(capacity);
} else {
threshold = capacity;
}
init(); // Give subclass a chance to do its thing.
// Read the keys and values, and put the mappings in the HashMap
for (int i = 0; i < mappings; i++) {
K key = (K) s.readObject();
V value = (V) s.readObject();
putForCreate(key, value);
}
}
private void putForCreate(K key, V value) {
int hash = null == key ? 0 : hash(key);
int i = indexFor(hash, table.length);
for (Entry<K,V> e = table[i]; e != null; e = e.next) {
Object k;
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k)))) {
e.value = value;
return;
}
}
createEntry(hash, key, value, i);
}
void createEntry(int hash, K key, V value, int bucketIndex) {
Entry<K,V> e = table[bucketIndex];
table[bucketIndex] = new Entry<>(hash, key, value, e);
size++;
}
HashMap在序列化时，对key和value分别单独序列化，反序列化时再对key进行hash，构造数据结构。