Java源码分析之HashMap(JDK1.8)
一、HashMap概述
HashMap是常用的Java集合之一，是基于哈希表的Map接口的实现。与HashTable主要区别为不支持同步和允许null作为key和value。由于HashMap不是线程安全的，如果想要线程安全，可以使用ConcurrentHashMap代替。
二、HashMap数据结构
HashMap的底层是哈希数组，数组元素为Entry。HashMap通过key的hashCode来计算hash值，当hashCode相同时，通过“拉链法”解决冲突，如下图所示。
相比于之前的版本，jdk1.8在解决哈希冲突时有了较大的变化，当链表长度大于阈值（默认为8）时，将链表转化为红黑树，以减少搜索时间。原本Map.Entry接口的实现类Entry改名为了Node。转化为红黑树时改用另一种实现TreeNode。
Node类
static class Node implements Map.Entry {
final int hash; // 哈希值
final K key;
V value;
Node next; // 指向下一个节点
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;
}
} TreeNode类
static final class TreeNode extends LinkedHashMap.Entry {
TreeNode parent; // red-black tree links
TreeNode left;
TreeNode right;
TreeNode prev; // needed to unlink next upon deletion
boolean red;
TreeNode(int hash, K key, V val, Node next) {
super(hash, key, val, next);
}
} HashMap就是这样一个Entry（包括Node和TreeNode）数组，Node对象中包含键、值和hash值，next指向下一个Entry，用来处理哈希冲突。TreeNode对象包含指向父节点、子节点和前一个节点（移除对象时使用）的指针，以及表示红黑节点的boolean标识。
三、HashMap源码分析
1. 主要属性
transient Node[] table; // 哈希数组
transient Set> entrySet; // entry缓存Set
transient int size; // 元素个数
transient int modCount; // 修改次数
int threshold; // 阈值，等于加载因子*容量，当实际大小超过阈值则进行扩容
final float loadFactor; // 加载因子，默认值为0.75 2. 构造方法
以下是HashMap的几个构造方法。
/**
* 根据初始化容量和加载因子构建一个空的HashMap.
*/
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);
}
/**
* 使用初始化容量和默认加载因子(0.75).
*/
public HashMap(int initialCapacity) {
this(initialCapacity, DEFAULT_LOAD_FACTOR);
}
/**
* 使用默认初始化大小(16)和默认加载因子(0.75).
*/
public HashMap() {
this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted
}
/**
* 用已有的Map构造一个新的HashMap.
*/
public HashMap(Map m) {
this.loadFactor = DEFAULT_LOAD_FACTOR;
putMapEntries(m, false);
}3. 数据存取
- putAll方法
public void putAll(Map m) {
putMapEntries(m, true);
}
/**
* 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); // put核心方法
}
}
}- put方法
public V put(K key, V value) {
return putVal(hash(key), key, value, false, true);
}
final V putVal(int hash, K key, V value, boolean onlyIfAbsent,
boolean evict) {
Node[] tab; Node p; int n, i;
if ((tab = table) == null || (n = tab.length) == 0) // table为空或length为0
n = (tab = resize()).length; // 初始化
if ((p = tab[i = (n - 1) & hash]) == null) // 如果hash所在位置为null，直接put
tab[i] = newNode(hash, key, value, null);
else { // tab[i]有元素，遍历节点后添加
Node e; K k;
// 如果hash、key都相等，直接覆盖
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
e = p;
else if (p instanceof TreeNode) // 红黑树添加节点
e = ((TreeNode)p).putTreeVal(this, tab, hash, key, value);
else { // 链表
for (int binCount = 0; ; ++binCount) {
if ((e = p.next) == null) { // 找到链表最后一个节点，插入新节点
p.next = newNode(hash, key, value, null);
// 链表节点大于阈值8，调用treeifyBin方法，当tab.length大于64将链表改为红黑树
// 如果tab.length < 64或tab为null，则调用resize方法重构链表.
if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
treeifyBin(tab, hash);
break;
}
// hash、key都相等，此时节点即要更新节点
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
break;
p = e;
}
}
// 当前节点e = p.next不为null，表示链表中原本存在相同的key，则返回oldValue
if (e != null) { // existing mapping for key
V oldValue = e.value;
// onlyIfAbsent值为false，参数主要决定存在相同key时是否执行替换
if (!onlyIfAbsent || oldValue == null)
e.value = value;
afterNodeAccess(e);
return oldValue;
}
}
++modCount;
if (++size > threshold) // 检查是否超过阈值
resize();
afterNodeInsertion(evict);
return null; // 原HashMap中不存在相同的key，插入键值对后返回null
} - get方法
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) {
Node[] tab; Node first, e; int n; K k;
if ((tab = table) != null && (n = tab.length) > 0 &&
(first = tab[(n - 1) & hash]) != null) {
if (first.hash == hash && // always check first node
((k = first.key) == key || (key != null && key.equals(k))))
return first;
if ((e = first.next) != null) {
if (first instanceof TreeNode) // 红黑树
return ((TreeNode)first).getTreeNode(hash, key);
// 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;
}
// 遍历红黑树搜索节点
/**
* Calls find for root node.
*/
final TreeNode getTreeNode(int h, Object k) {
return ((parent != null) ? root() : this).find(h, k, null);
}
/**
* Returns root of tree containing this node.
*/
final TreeNode root() {
for (TreeNode r = this, p;;) {
if ((p = r.parent) == null)
return r;
r = p;
}
}
/**
* Finds the node starting at root p with the given hash and key.
* The kc argument caches comparableClassFor(key) upon first use
* comparing keys.
*/
final TreeNode find(int h, Object k, Class kc) {
TreeNode p = this;
do {
int ph, dir; K pk;
TreeNode pl = p.left, pr = p.right, q;
if ((ph = p.hash) > h) // 当前节点hash大
p = pl; // 查左子树
else if (ph < h) // 当前节点hash小
p = pr; // 查右子树
else if ((pk = p.key) == k || (k != null && k.equals(pk)))
return p; // hash、key都相等，即找到，返回当前节点
else if (pl == null) // hash相等，key不等，左子树为null，查右子树
p = pr;
else if (pr == null)
p = pl;
else if ((kc != null ||
(kc = comparableClassFor(k)) != null) &&
(dir = compareComparables(kc, k, pk)) != 0)
p = (dir < 0) ? pl : pr;
else if ((q = pr.find(h, k, kc)) != null)
return q;
else
p = pl;
} while (p != null);
return null;
} - remove方法
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) {
Node[] tab; Node p; int n, index;
if ((tab = table) != null && (n = tab.length) > 0 &&
(p = tab[index = (n - 1) & hash]) != null) {
Node node = null, e; K k; V v;
// 直接命中
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
node = p;
else if ((e = p.next) != null) {
if (p instanceof TreeNode) // 在红黑树中查找
node = ((TreeNode)p).getTreeNode(hash, key);
else { // 在链表中查找
do {
if (e.hash == hash &&
((k = e.key) == key ||
(key != null && key.equals(k)))) {
node = e;
break;
}
p = e;
} while ((e = e.next) != null);
}
}
// 命中后删除
if (node != null && (!matchValue || (v = node.value) == value ||
(value != null && value.equals(v)))) {
if (node instanceof TreeNode) // 在红黑树中删除节点
((TreeNode)node).removeTreeNode(this, tab, movable);
else if (node == p) // 链表首节点删除
tab[index] = node.next;
else // 多节点链表删除
p.next = node.next;
++modCount;
--size;
afterNodeRemoval(node);
return node;
}
}
return null;
} - clear方法
/**
* Removes all of the mappings from this map.
* The map will be empty after this call returns.
*/
public void clear() {
Node[] tab;
modCount++;
if ((tab = table) != null && size > 0) {
size = 0;
for (int i = 0; i < tab.length; ++i)
tab[i] = null; // 把哈希数组中所有位置都赋为null
}
} 四、总结
本文从源码入手，简单地分析了HashMap底层的结构和实现。在源码分析部分主要分析了常用的几个方法，还有一些方法比如调整哈希表大小的resize、将链表转化为红黑树的treeify以及逆操作untreeify等，在此不再详细分析。红黑树部分的代码只理解了大概，实现细节上还有待进一步阅读分析。