List
ArrayList
本质是一个数组。
/**
* Default initial capacity.
*/
private static final int DEFAULT_CAPACITY = 10;
/**
* Shared empty array instance used for empty instances.
*/
private static final Object[] EMPTY_ELEMENTDATA = {};
/**
* Shared empty array instance used for default sized empty instances. We
* distinguish this from EMPTY_ELEMENTDATA to know how much to inflate when
* first element is added.
*/
private static final Object[] DEFAULTCAPACITY_EMPTY_ELEMENTDATA = {};
/**
* The array buffer into which the elements of the ArrayList are stored.
* The capacity of the ArrayList is the length of this array buffer. Any
* empty ArrayList with elementData == DEFAULTCAPACITY_EMPTY_ELEMENTDATA
* will be expanded to DEFAULT_CAPACITY when the first element is added.
*/
transient Object[] elementData; // non-private to simplify nested class access
/**
* The size of the ArrayList (the number of elements it contains).
*
* @serial
*/
private int size;
- DEFAULT_CAPACITY:默认初始容量。
- EMPTY_ELEMENTDATA:用于空实例的共享空数组实例。
- DEFAULTCAPACITY_EMPTY_ELEMENTDATA:用于默认大小的空实例的共享空数组实例。我们将其与 EMPTY_ELEMENTDATA 区分开来,以了解添加第一个元素时要膨胀多少。
- elementData:存储 ArrayList 元素的数组缓冲区。 ArrayList 的容量就是这个数组缓冲区的长度。当添加第一个元素时,任何具有 elementData == DEFAULTCAPACITY_EMPTY_ELEMENTDATA 的空 ArrayList 都将扩展为 DEFAULT_CAPACITY。
- size:ArrayList 的大小(它包含的元素数量)。
add方法
public boolean add(E e) {
ensureCapacityInternal(size + 1); // Increments modCount!!
elementData[size++] = e;
return true;
}
private void ensureCapacityInternal(int minCapacity) {
if (elementData == DEFAULTCAPACITY_EMPTY_ELEMENTDATA) {
minCapacity = Math.max(DEFAULT_CAPACITY, minCapacity);
}
ensureExplicitCapacity(minCapacity);
}
- 添加元素。调用ensureCapacityInternal方法,比较初始容量DEFAULT_CAPACITY和minCapacity取最大值。
private void ensureExplicitCapacity(int minCapacity) {
modCount++;
// overflow-conscious code
if (minCapacity - elementData.length > 0)
grow(minCapacity);
}
- 当存储容量不足,调用**grow()**方法进行扩容
private void grow(int minCapacity) {
// overflow-conscious code
int oldCapacity = elementData.length;
int newCapacity = oldCapacity + (oldCapacity >> 1);
if (newCapacity - minCapacity < 0)
newCapacity = minCapacity;
if (newCapacity - MAX_ARRAY_SIZE > 0)
newCapacity = hugeCapacity(minCapacity);
// minCapacity is usually close to size, so this is a win:
elementData = Arrays.copyOf(elementData, newCapacity);
}
private static int hugeCapacity(int minCapacity) {
if (minCapacity < 0) // overflow
throw new OutOfMemoryError();
return (minCapacity > MAX_ARRAY_SIZE) ?
Integer.MAX_VALUE :
MAX_ARRAY_SIZE;
}
- ArrayList扩容到原有存储的1.5倍
- 当存储容量超过Integer.MAX_VALUE时,抛出OutOfMemoryError异常
get方法
public E get(int index) {
rangeCheck(index);
return elementData(index);
}
private void rangeCheck(int index) {
if (index >= size)
throw new IndexOutOfBoundsException(outOfBoundsMsg(index));
}
- 当获取的index索引大于等于ArrayList长度,抛出IndexOutOfBoundsException
LinkedList
本质是双向链表。
transient int size = 0;
/**
* Pointer to first node.
* Invariant: (first == null && last == null) ||
* (first.prev == null && first.item != null)
*/
transient Node<E> first;
/**
* Pointer to last node.
* Invariant: (first == null && last == null) ||
* (last.next == null && last.item != null)
*/
transient Node<E> last;
/**
* Constructs an empty list.
*/
public LinkedList() {
}
- first:链表的起始元素
- last:链表的结尾元素
- size:链表的长度
无参构造函数没有具体实现,实例一个空的链表。
add方法
private static class Node<E> {
E item;
Node<E> next;
Node<E> prev;
Node(Node<E> prev, E element, Node<E> next) {
this.item = element;
this.next = next;
this.prev = prev;
}
}
链表连接的是一个个Node节点。节点里包括:
- item:当前节点存储的数据
- next:当前节点链接的下一个节点
- prev:当前节点链接的上一个节点
public boolean add(E e) {
linkLast(e);
return true;
}
void linkLast(E e) {
final Node<E> l = last;
final Node<E> newNode = new Node<>(l, e, null);
last = newNode;
if (l == null)
first = newNode;
else
l.next = newNode;
size++;
modCount++;
}
链表向后追加节点数据。
当前链表不存在节点,则把当前节点设置为起始节点和结尾节点。
当前链表存在节点,则把当前节点设置为结尾节点。
get方法
public E get(int index) {
checkElementIndex(index);
return node(index).item;
}
private void checkElementIndex(int index) {
if (!isElementIndex(index))
throw new IndexOutOfBoundsException(outOfBoundsMsg(index));
}
Node<E> node(int index) {
// assert isElementIndex(index);
if (index < (size >> 1)) {
Node<E> x = first;
for (int i = 0; i < index; i++)
x = x.next;
return x;
} else {
Node<E> x = last;
for (int i = size - 1; i > index; i--)
x = x.prev;
return x;
}
}
- 先校验index是否超出链表长度,超出抛出IndexOutOfBoundsException
- index < (size >> 1):判断index是否小于1/2的链表长度,大于则从链表起始位置往后遍历,小于则从链表结尾位置开始往前遍历。
Map
HashMap
数组+链表的实现方式。
/**
* 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;
/**
* 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;
/**
* 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;
/**
* 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;
/* ---------------- 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.)
*/
transient Node<K,V>[] 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
*/
// (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.
*
* @serial
*/
final float loadFactor;
static class Node<K,V> implements Map.Entry<K,V> {
final int hash;
final K key;
V value;
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; }
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;
}
}
-
DEFAULT_INITIAL_CAPACITY:默认初始容量16,容量必须是2的幂
-
MAXIMUM_CAPACITY:最大容量
-
DEFAULT_LOAD_FACTOR:默认负载因子
-
TREEIFY_THRESHOLD:链表转换成红黑树的阈值为8
-
UNTREEIFY_THRESHOLD:红黑树转成链表的阈值为6
-
MIN_TREEIFY_CAPACITY:链表转成树的最小容量,值为64。
-
table:HashMap的数组部分实现。存储的是Node<K, V>,实现Map.Entry<K,V>。该表在首次使用时初始化,并根据需要调整大小。分配时,长度始终是 2 的幂。
-
size:键值映射的数量,即HashMap的存储数据个数。
-
threshold:要调整大小的下一个大小值(容量 * 负载因子)。
-
loadFactor:哈希表的负载因子。
构造函数
/**
* 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;
this.threshold = tableSizeFor(initialCapacity);
}
/**
* 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() {
this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted
}
/**
* 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
*/
public HashMap(Map<? extends K, ? extends V> m) {
this.loadFactor = DEFAULT_LOAD_FACTOR;
putMapEntries(m, false);
}
- HashMap有4个构造函数。常用的是默认无参
HashMap()
和指定初始容量和HashMap(int initialCapacity)
的两个构造函数。
put方法
public V put(K key, V value) {
return putVal(hash(key), key, value, false, true);
}
static final int hash(Object key) {
int h;
return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}
final V putVal(int hash, K key, V value, boolean onlyIfAbsent,
boolean evict) {
Node<K,V>[] tab; Node<K,V> p; int n, i;
// map的table还未初始化或者长度为0,调用resize()并返回n
if ((tab = table) == null || (n = tab.length) == 0)
n = (tab = resize()).length;
// 要插入的数组位置上没有数据,直接放置newNode对象
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null);
else {
Node<K,V> e; K k;
// 插入数组位置上有数据,且hash和key相同,直接替换值
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
e = p;
// 如果存在的节点是TreeNode,执行putTreeVal()方法
else if (p instanceof TreeNode)
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
else {
// 遍历链表
for (int binCount = 0; ; ++binCount) {
// 如果下一个节点为null,创建newNode
if ((e = p.next) == null) {
p.next = newNode(hash, key, value, null);
// 如果链表长度 >= TREEIFY_THRESHOLD - 1 则链表转换成红黑树
if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
treeifyBin(tab, hash);
break;
}
// 如果下个节点的hash和key与插入的数据相等,直接替换值
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
break;
p = e;
}
}
if (e != null) { // existing mapping for key
V oldValue = e.value;
if (!onlyIfAbsent || oldValue == null)
e.value = value;
afterNodeAccess(e);
return oldValue;
}
}
++modCount;
// 存储长度超过容量 进行扩容
if (++size > threshold)
resize();
afterNodeInsertion(evict);
return null;
}
get方法
public V get(Object key) {
Node<K,V> e;
return (e = getNode(hash(key), key)) == null ? null : e.value;
}
final Node<K,V> getNode(int hash, Object key) {
Node<K,V>[] tab; Node<K,V> first, e; int n; K k;
// 计算key的存储位置
if ((tab = table) != null && (n = tab.length) > 0 &&
(first = tab[(n - 1) & hash]) != null) {
// 总是检验第一个节点,第一个节点hash和key都相等直接返回
if (first.hash == hash && // always check first node
((k = first.key) == key || (key != null && key.equals(k))))
return first;
// 判断是否有下一个节点
if ((e = first.next) != null) {
// 如果节点属于TreeNode,则执行getTreeNode
if (first instanceof TreeNode)
return ((TreeNode<K,V>)first).getTreeNode(hash, key);
// 不属于TreeNode,则遍历链表返回值
do {
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
return e;
} while ((e = e.next) != null);
}
}
return null;
}
扩容为什么是2幂次方
HashMap确定数据存储在数组的位置是通过位运算。取模%也可以,但是位运算效率比较高。
位运算方法**(table.length - 1) & hash**
- 是因为方便低位异或运算,并且尽可能避免计算结果发生hash碰撞。
- 方便扩容重新计算数组下角标
# 16的二进制表示
1000 0000
# 16-1的二进制表示
0111 1111
例子:
hash = 23
table.length - 1 = 15
HEX(23) = 0001 0111
HEX(15) = 0000 1111
---------------------
0000 0111 = 7
hash = 46
table.length - 1 = 15
HEX(46) = 0010 1110
HEX(15) = 0000 1111
---------------------
0000 1110 = 14
#扩容成长度32
hash = 23
table.length - 1 = 31
HEX(23) = 0001 0111
HEX(31) = 0001 1111
---------------------
0001 0111 = 16 + 7
1)、h & length == 0,则该节点在新数组中仍在旧索引值处
2)、h & length != 0,则该节点在新数组中的旧索引 + 旧容量的位置