HashMap的get方法与put方法
前言:HashMap的源码先前是看过了的(我自以为),直到昨天贝壳面试官让我详细讲讲HashMap的get和put方法我才知道,这知识,他不进脑子啊,于是又看了一遍,很多细节的地方还是没能有耐心去细读,但大概流程还是走了一遍
1.注释
允许key和value为null
和HashTable的区别在于非线程安全和允许null
所以需要安全的HashMap有三种选择:
- Collections.synchronizedMap(map)
- HashTable
- ConcurrentHashMap
默认装载因子(0.75)在空间和时间开销上提供了一个很好的平衡
使用分布良好的hash函数时,红黑树的结构是很难出现的;当使用随机分布的hash函数时,红黑树出现的频率服从泊松分布,当装载因子为0.75,树化阈值为8时,概率为6*10^-8^
2.底层结构
Node数组
transient Node<K,V>[] table; 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() { //会需要用到整个Node的hashCode吗? //put,get是没用到的 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<?,?>是一个接口,所以这里应该是多态的表现了,但是接口还能这么. 的? Map.Entry<?,?> e = (Map.Entry<?,?>)o; if (Objects.equals(key, e.getKey()) && Objects.equals(value, e.getValue())) return true; } return false; } }可以看到Node有一个next属性,表述一下就是:
数组实现,但是数组中存放的Node除了key,value之外,还有一个next属性,可以作为链表的头结点
3.常量
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16 static final float DEFAULT_LOAD_FACTOR = 0.75f; static final int MAXIMUM_CAPACITY = 1 << 30; static final int MIN_TREEIFY_CAPACITY = 64; static final int TREEIFY_THRESHOLD = 8; static final int UNTREEIFY_THRESHOLD = 6;
4.构造方法
//无参 //final float loadFactor; //其余使用默认值,等下分析put方法时就可以看到是怎样使用默认值的了 //不过为什么无参的一定要赋值默认装载因子呢? public HashMap() { this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted } //调用public HashMap(int initialCapacity, float loadFactor) public HashMap(int initialCapacity) { this(initialCapacity, DEFAULT_LOAD_FACTOR); } //三个if语句 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; //tableSizeFor返回比当前initialCapacity大的最小的二次幂 //但是为什么赋值给了threshold,这个threshold后面起的也是初始容量的作用啊? //可能是为了和threshold为0的情况区分开来 this.threshold = tableSizeFor(initialCapacity); } //输入一个Map,通过遍历转为HashMap public HashMap(Map<? extends K, ? extends V> m) { this.loadFactor = DEFAULT_LOAD_FACTOR; putMapEntries(m, false); }四个构造函数,无参,
<int>,<int,float>,<Map>
5.put
//实际使用过程中我们使用的方法 //可以看到帮我们封装了一层,调用了putVal public V put(K key, V value) { //这里的hash也是对Object.hashCode()的封装,返回的是hashCode的低16位 ^ 高16位 //因为当table数组的长度很小时,高16位是不参与运算的;因为数组索引是通过&运算获取的 return putVal(hash(key), key, value, false, true); } final V putVal(int hash, K key, V value, boolean onlyIfAbsent, boolean evict) { Node<K,V>[] tab; Node<K,V> p; int n, i; if ((tab = table) == null || (n = tab.length) == 0) //如果table数组未空,就先去resize()初始化 n = (tab = resize()).length; if ((p = tab[i = (n - 1) & hash]) == null) //当前索引位置是空的,newNode就完事了,null对应的是next tab[i] = newNode(hash, key, value, null); else { Node<K,V> e; K k; if (p.hash == hash && ((k = p.key) == key || (key != null && key.equals(k)))) //e最终记下的都是key相同的那个结点 e = p; else if (p instanceof TreeNode) //当前是红黑树,向红黑树中插入值 //算法基础好的话可以考虑看红黑树怎么插入的,我就算了吧 e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value); else { //当前是链表,遍历链表 for (int binCount = 0; ; ++binCount) { if ((e = p.next) == null) { //尾插法,遍历完了还没有key相同的 p.next = newNode(hash, key, value, null); //插入之后检查是否需要变成红黑树 if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st treeifyBin(tab, hash); break; } 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); //如果是更新旧值,就没有下面的判断扩容操作了 return oldValue; } } ++modCount; if (++size > threshold) resize(); afterNodeInsertion(evict); return null; }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) //对于已初始化的table数组,扩容到2倍 newThr = oldThr << 1; // double threshold } else if (oldThr > 0) // initial capacity was placed in threshold //只有<int,float>构造方***初始化threshold的值 newCap = oldThr; else { // zero initial threshold signifies using defaults //这是未赋初始容量的情况,使用默认 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) { //遍历赋值 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; }表述:常用的put(k,v)API中封装了一层putVal(hash,k,v,onlyIfAbsent,evict),在插入之前检查table数组是否已经初始化(resize),已经初始化再通过hash值&数组长度计算出索引,如果当前结点为null,直接插入,否则判断结构是红黑树还是链表,遍历决定是更新值还是尾插法插入(未找到key相同的结点)
6.get
//get方法也封装了一层getNode 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; 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) return ((TreeNode<K,V>)first).getTreeNode(hash, key); do { if (e.hash == hash && ((k = e.key) == key || (key != null && key.equals(k)))) return e; } while ((e = e.next) != null); } } //table未初始化直接返回null return null; }表述:常用的get(k,v)也封装了一层get(hash,k),首先判断数组是否初始化,如果数组为空直接返回null,不为空则分情况遍历红黑树或者链表(头结点就是当然皆大欢喜),写到这里我想起来,昨天表述的时候至少讲一下hashCode和equals的关系吧,答得还是太烂了
投递牛客等公司10个岗位 >