java version "1.7.0_67"
HashMap的草图:
Entry数组:
static final Entry<?,?>[] EMPTY_TABLE = {}; transient Entry<K,V>[] table = (Entry<K,V>[]) EMPTY_TABLE; transient int size; // map中键值对数量
构造函数只是设置了 loadFactor 和 threshold 的值,所以table还是空的。
装填因子loadFactor默认为0.75,loadFactor = 键值对数量 / 数组大小
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; //默认0.75 threshold = initialCapacity; //默认16 init(); } void init() { }
简单分析put操作:
public V put(K key, V value) { //第一次put时,table是空的,需要扩容 if (table == EMPTY_TABLE) { inflateTable(threshold); } //null也可以作为键 if (key == null) return putForNullKey(value); //根据key的hashCode计算出hash值 int hash = hash(key); //根据hash值,定位到table中的位置 int i = indexFor(hash, table.length); //如果已存在相等key,更新value,并返回旧value for (Entry<K,V> e = table[i]; e != null; e = e.next) { Object k; // 两个key相等的判断条件: //1. key的hash值相等,key的地址相等 //2. key的hash值相等,key用equals比较相等 if (e.hash == hash && ((k = e.key) == key || key.equals(k))) { V oldValue = e.value; e.value = value; e.recordAccess(this); return oldValue; } } modCount++; //不存在相等的key,则使用头插法加入链表中 addEntry(hash, key, value, i); return null; }
其实HashMap的内部数据结构还是比较清晰的,平常用得也挺多,听到最多的说法就是HashMap不是线程安全的,原因简单提一句,是在resize的过程中可能会产生环。
分析下HashMap resize的过程:HashMap的数据迁移是一次性的,相对而言,redis的做法比较有趣,把数据迁移分摊到get和set操作上。当map中键值对数量超过threshold时,不一定会发生resize。
void addEntry(int hash, K key, V value, int bucketIndex) { // 如果map中键值对的数量达到了threshold,且当前槽挂着entry if ((size >= threshold) && (null != table[bucketIndex])) { //2倍扩展 resize(2 * table.length); hash = (null != key) ? hash(key) : 0; //扩展之后,table指向了新的数组,length也变了,重新计算index bucketIndex = indexFor(hash, table.length); } createEntry(hash, key, value, bucketIndex); } 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); } 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); //这里也是使用头插法,所以原来链表的顺序会翻转 e.next = newTable[i]; newTable[i] = e; e = next; } } }