看了下JAVA里面有HashMap、Hashtable、HashSet三种hash集合的实现源码，这里总结下，理解错误的地方还望指正
int hash = key.hashCode(); int index = (hash & 0x7FFFFFFF) % tab.length;
HashMap计算hash对key的hashcode进行了二次hash，以获得更好的散列值，然后对table数组长度取摸
static int hash(int h) { // This function ensures that hashCodes that differ only by // constant multiples at each bit position have a bounded // number of collisions (approximately 8 at default load factor). h ^= (h >>> 20) ^ (h >>> 12); return h ^ (h >>> 7) ^ (h >>> 4); } static int indexFor(int h, int length) { return h & (length-1); }
除开HashMap和Hashtable外，还有一个hash集合HashSet，有所区别的是HashSet不是key value结构，仅仅是存储不重复的元素，相当于简化版的HashMap，只是包含HashMap中的key而已
通过查看源码也证实了这一点，HashSet内部就是使用HashMap实现，只不过HashSet里面的HashMap所有的value都是同一个Object而已，因此HashSet也是非线程安全的，至于HashSet和Hashtable的区别，HashSet就是个简化的HashMap的，所以你懂的
下面是HashSet几个主要方法的实现
private transient HashMap<E,Object> map;
private static final Object PRESENT = new Object(); public HashSet() { map = new HashMap<E,Object>(); } public boolean contains(Object o) { return map.containsKey(o); } public boolean add(E e) { return map.put(e, PRESENT)==null; } public boolean add(E e) { return map.put(e, PRESENT)==null; } public boolean remove(Object o) { return map.remove(o)==PRESENT; } public void clear() { map.clear(); }
HashMap和Hashtable的底层实现都是数组+链表结构实现的，这点上完全一致
添加、删除、获取元素时都是先计算hash，根据hash和table.length计算index也就是table数组的下标，然后进行相应操作，下面以HashMap为例说明下它的简单实现
/** * HashMap的默认初始容量 必须为2的n次幂 */ static final int DEFAULT_INITIAL_CAPACITY = 16; /** * HashMap的最大容量，可以认为是int的最大值 */ static final int MAXIMUM_CAPACITY = 1 << 30; /** * 默认的加载因子 */ static final float DEFAULT_LOAD_FACTOR = 0.75f; /** * HashMap用来存储数据的数组 */ transient Entry[] table;
/** * 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; threshold = (int)(DEFAULT_INITIAL_CAPACITY * DEFAULT_LOAD_FACTOR); table = new Entry[DEFAULT_INITIAL_CAPACITY]; init(); }
public V put(K key, V value) { if (key == null) return putForNullKey(value); //处理null值 int hash = hash(key.hashCode());//计算hash int i = indexFor(hash, table.length);//计算在数组中的存储位置 //遍历table[i]位置的链表，查找相同的key，若找到则使用新的value替换掉原来的oldValue并返回oldValue for (Entry<K,V> e = table[i]; e != null; e = e.next) { Object k; if (e.hash == hash && ((k = e.key) == key || key.equals(k))) { V oldValue = e.value; e.value = value; e.recordAccess(this); return oldValue; } } //若没有在table[i]位置找到相同的key，则添加key到table[i]位置，新的元素总是在table[i]位置的第一个元素，原来的元素后移 modCount++; addEntry(hash, key, value, i); return null; } void addEntry(int hash, K key, V value, int bucketIndex) { //添加key到table[bucketIndex]位置，新的元素总是在table[bucketIndex]的第一个元素，原来的元素后移 Entry<K,V> e = table[bucketIndex]; table[bucketIndex] = new Entry<K,V>(hash, key, value, e); //判断元素个数是否达到了临界值，若已达到临界值则扩容，table长度翻倍 if (size++ >= threshold) resize(2 * table.length); }
public V get(Object key) { if (key == null) return getForNullKey();//处理null值 int hash = hash(key.hashCode());//计算hash //在table[index]遍历查找key，若找到则返回value，找不到返回null 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.equals(k))) return e.value; } return null; }
public V remove(Object key) { Entry<K,V> e = removeEntryForKey(key); return (e == null ? null : e.value); } final Entry<K,V> removeEntryForKey(Object key) { int hash = (key == null) ? 0 : hash(key.hashCode()); 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; }
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); table = newTable; threshold = (int)(newCapacity * loadFactor); } void transfer(Entry[] newTable) { Entry[] src = table; int newCapacity = newTable.length; for (int j = 0; j < src.length; j++) { Entry<K,V> e = src[j]; if (e != null) { src[j] = null; do { Entry<K,V> next = e.next;
//重新对每个元素计算index int i = indexFor(e.hash, newCapacity); e.next = newTable[i]; newTable[i] = e; e = next; } while (e != null); } } }
public void clear() { modCount++; Entry[] tab = table; for (int i = 0; i < tab.length; i++) tab[i] = null; size = 0; }
public boolean containsKey(Object key) { return getEntry(key) != null; } final Entry<K,V> getEntry(Object key) { int hash = (key == null) ? 0 : hash(key.hashCode()); 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; }
containsValue方法就比较粗暴了，就是直接遍历所有元素直到找到value，由此可见HashMap的containsValue方法本质上和普通数组和list的contains方法没什么区别，你别指望它会像containsKey那么高效
public boolean containsValue(Object value) { if (value == null) return containsNullValue(); Entry[] tab = table; for (int i = 0; i < tab.length ; i++) for (Entry e = tab[i] ; e != null ; e = e.next) if (value.equals(e.value)) return true; return false; }
indexFor中的h & (length-1)就相当于h%length，用于计算index也就是在table数组中的下标
hash方法是对hashcode进行二次散列，以获得更好的散列值
为了更好理解这里我们可以把这两个方法简化为 int index= key.hashCode()/table.length,以put中的方法为例可以这样替换
int hash = hash(key.hashCode());//计算hash int i = indexFor(hash, table.length);//计算在数组中的存储位置 //上面这两行可以这样简化 int i = key.key.hashCode()%table.length;
static int hash(int h) { // This function ensures that hashCodes that differ only by // constant multiples at each bit position have a bounded // number of collisions (approximately 8 at default load factor). h ^= (h >>> 20) ^ (h >>> 12); return h ^ (h >>> 7) ^ (h >>> 4); } static int indexFor(int h, int length) { return h & (length-1); }
为了加深理解，我个人实现了一个简化版本的HashMap，注意哦，仅仅是简化版的功能并不完善，仅供参考
package cn.lzrabbit.structure; /** * Created by rabbit on 14-5-4. */ public class MyHashMap { //默认初始化大小 16 private static final int DEFAULT_INITIAL_CAPACITY = 16; //默认负载因子 0.75 private static final float DEFAULT_LOAD_FACTOR = 0.75f; //临界值 private int threshold; //元素个数 private int size; //扩容次数 private int resize; private HashEntry[] table; public MyHashMap() { table = new HashEntry[DEFAULT_INITIAL_CAPACITY]; threshold = (int) (DEFAULT_INITIAL_CAPACITY * DEFAULT_LOAD_FACTOR); size = 0; } private int index(Object key) { //根据key的hashcode和table长度取模计算key在table中的位置 return key.hashCode() % table.length; } public void put(Object key, Object value) { //key为null时需要特殊处理，为简化实现忽略null值 if (key == null) return; int index = index(key); //遍历index位置的entry，若找到重复key则更新对应entry的值，然后返回 HashEntry entry = table[index]; while (entry != null) { if (entry.getKey().hashCode() == key.hashCode() && (entry.getKey() == key || entry.getKey().equals(key))) { entry.setValue(value); return; } entry = entry.getNext(); } //若index位置没有entry或者未找到重复的key，则将新key添加到table的index位置 add(index, key, value); } private void add(int index, Object key, Object value) { //将新的entry放到table的index位置第一个，若原来有值则以链表形式存放 HashEntry entry = new HashEntry(key, value, table[index]); table[index] = entry; //判断size是否达到临界值，若已达到则进行扩容，将table的capacicy翻倍 if (size++ >= threshold) { resize(table.length * 2); } } private void resize(int capacity) { if (capacity <= table.length) return; HashEntry[] newTable = new HashEntry[capacity]; //遍历原table，将每个entry都重新计算hash放入newTable中 for (int i = 0; i < table.length; i++) { HashEntry old = table[i]; while (old != null) { HashEntry next = old.getNext(); int index = index(old.getKey()); old.setNext(newTable[index]); newTable[index] = old; old = next; } } //用newTable替table table = newTable; //修改临界值 threshold = (int) (table.length * DEFAULT_LOAD_FACTOR); resize++; } public Object get(Object key) { //这里简化处理，忽略null值 if (key == null) return null; HashEntry entry = getEntry(key); return entry == null ? null : entry.getValue(); } public HashEntry getEntry(Object key) { HashEntry entry = table[index(key)]; while (entry != null) { if (entry.getKey().hashCode() == key.hashCode() && (entry.getKey() == key || entry.getKey().equals(key))) { return entry; } entry = entry.getNext(); } return null; } public void remove(Object key) { if (key == null) return; int index = index(key); HashEntry pre = null; HashEntry entry = table[index]; while (entry != null) { if (entry.getKey().hashCode() == key.hashCode() && (entry.getKey() == key || entry.getKey().equals(key))) { if (pre == null) table[index] = entry.getNext(); else pre.setNext(entry.getNext()); //如果成功找到并删除，修改size size--; return; } pre = entry; entry = entry.getNext(); } } public boolean containsKey(Object key) { if (key == null) return false; return getEntry(key) != null; } public int size() { return this.size; } public void clear() { for (int i = 0; i < table.length; i++) { table[i] = null; } this.size = 0; } @Override public String toString() { StringBuilder sb = new StringBuilder(); sb.append(String.format("size:%s capacity:%s resize:%s\n\n", size, table.length, resize)); for (HashEntry entry : table) { while (entry != null) { sb.append(entry.getKey() + ":" + entry.getValue() + "\n"); entry = entry.getNext(); } } return sb.toString(); } } class HashEntry { private final Object key; private Object value; private HashEntry next; public HashEntry(Object key, Object value, HashEntry next) { this.key = key; this.value = value; this.next = next; } public Object getKey() { return key; } public Object getValue() { return value; } public void setValue(Object value) { this.value = value; } public HashEntry getNext() { return next; } public void setNext(HashEntry next) { this.next = next; } }
原文：http://www.cnblogs.com/lzrabbit/p/3721067.html
