散列表是数据结构中的重要技术,散列表的最大优点在于便于查找,缺点在于插入删除较为麻烦。java中很多数据类型如hashMap,hashTable,hashSet基本实现就是采用散列表技术。首先看下HashSet。
package java.util; /* 1.HashSet中不允许重复元素 2.HashSet中大量调用了HashMap的方法,其内部封装了一个HashMap */ public class HashSet<E> extends AbstractSet<E> implements Set<E>, Cloneable, java.io.Serializable { static final long serialVersionUID = -5024744406713321676L; //hashSet内部使用HashMap来存储元素, private transient HashMap<E,Object> map; //定义一个静态对象,作为所有key的value private static final Object PRESENT = new Object(); public HashSet() { map = new HashMap<>(); } public HashSet(Collection<? extends E> c) { map = new HashMap<>(Math.max((int) (c.size()/.75f) + 1, 16)); addAll(c); } public HashSet(int initialCapacity, float loadFactor) { map = new HashMap<>(initialCapacity, loadFactor); } public HashSet(int initialCapacity) { map = new HashMap<>(initialCapacity); } HashSet(int initialCapacity, float loadFactor, boolean dummy) { map = new LinkedHashMap<>(initialCapacity, loadFactor); } public Iterator<E> iterator() { return map.keySet().iterator(); } public int size() { return map.size(); } public boolean isEmpty() { return map.isEmpty(); } public boolean contains(Object o) { return map.containsKey(o); } 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(); } public Object clone() { try { HashSet<E> newSet = (HashSet<E>) super.clone(); newSet.map = (HashMap<E, Object>) map.clone(); return newSet; } catch (CloneNotSupportedException e) { throw new InternalError(); } } }
HashSet内部封装了一个HashMap,将要存储的对象作为每个键值对中的key,然后采用静态变量对象PRESENT作为所有key的value。在看HashMap之前来讲讲什么叫做散列(hash)?Hash的具体含义参见百度百科(hash)。简单的来说是指对所以的关键字,不直接采用关键字作为存储数组的下标,而是根据关键字计算出相应下标。hash的关键技术在于如何产生合适的hashcode,以及如何解决冲突(多个key映射到一个位置上)。hash表在查找方面上平均只需要O(1)的时间,也就是一找就到的节奏。在来看HashMap的内部实现。
package java.util; import java.io.*; /* HashMap是线程不同步的,可以进行封装 Map m = Collections.synchronizedMap(new HashMap(...)); */ public class HashMap<K,V> extends AbstractMap<K,V> implements Map<K,V>, Cloneable, Serializable { /* HashMap 的实例有两个参数影响其性能:初始容量 和加载因子。 容量是哈希表中桶的数量,初始容量只是哈希表在创建时的容量。 加载因子是哈希表在其容量自动增加之前可以达到多满的一种尺度。 当哈希表中的条目数超出了加载因子与当前容量的乘积时, 则要对该哈希表进行 rehash 操作(即重建内部数据结构), 从而哈希表将具有大约两倍的桶数。 在Java编程语言中,加载因子默认值为0.75,默认哈希表元为101 */ //初始化容量 static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16 //最大容量 static final int MAXIMUM_CAPACITY = 1 << 30; //加载因子 static final float DEFAULT_LOAD_FACTOR = 0.75f; //用来存储键值对的Entry数组,用于设置刚刚初始化的HashMap对象,用来减少存储空间 static final Entry<?,?>[] EMPTY_TABLE = {}; //大小必须是2的倍数 transient Entry<K,V>[] table = (Entry<K,V>[]) EMPTY_TABLE; //存储的键值对的数目 transient int size; //阈值,当size超过threshold时,table将会扩容. //threshold = capacity * loadFactor int threshold; //加载因子 final float loadFactor; //修改次数,用于检查线程是否同步 transient int modCount; //默认的阀值 static final int ALTERNATIVE_HASHING_THRESHOLD_DEFAULT = Integer.MAX_VALUE; private static class Holder { static final int ALTERNATIVE_HASHING_THRESHOLD; static { //获取jdk内置的阀值 String altThreshold = java.security.AccessController.doPrivileged( new sun.security.action.GetPropertyAction( "jdk.map.althashing.threshold")); int threshold; try { //设置当前阀值 threshold = (null != altThreshold) ? Integer.parseInt(altThreshold) : ALTERNATIVE_HASHING_THRESHOLD_DEFAULT; // disable alternative hashing if -1 if (threshold == -1) { threshold = Integer.MAX_VALUE; } if (threshold < 0) { throw new IllegalArgumentException("value must be positive integer."); } } catch(IllegalArgumentException failed) { throw new Error("Illegal value for 'jdk.map.althashing.threshold'", failed); } ALTERNATIVE_HASHING_THRESHOLD = threshold; } } //使用初始化容量和加载因子初始化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; threshold = initialCapacity; init(); } public HashMap(int initialCapacity) { this(initialCapacity, DEFAULT_LOAD_FACTOR); } public HashMap() { this(DEFAULT_INITIAL_CAPACITY, DEFAULT_LOAD_FACTOR); } /* * Constructs a new HashMap with the same mappings as the * specified Map. The HashMap is created with * default load factor (0.75) and an initial capacity sufficient to * hold the mappings in the specified Map. */ public HashMap(Map<? extends K, ? extends V> m) { this(Math.max((int) (m.size() / DEFAULT_LOAD_FACTOR) + 1, DEFAULT_INITIAL_CAPACITY), DEFAULT_LOAD_FACTOR); inflateTable(threshold); putAllForCreate(m); } /** * A randomizing value associated with this instance that is applied to * hash code of keys to make hash collisions harder to find. If 0 then alternative hashing is disabled. */ transient int hashSeed = 0; //工具函数,将number扩展成2的倍数 private static int roundUpToPowerOf2(int number) { // assert number >= 0 : "number must be non-negative"; int rounded = number >= MAXIMUM_CAPACITY ? MAXIMUM_CAPACITY : (rounded = Integer.highestOneBit(number)) != 0 ? (Integer.bitCount(number) > 1) ? rounded << 1 : rounded : 1; return rounded; } //将表格大小扩展到toSize private void inflateTable(int toSize) { // Find a power of 2 >= toSize int capacity = roundUpToPowerOf2(toSize); //重新设置阀值 threshold = (int) Math.min(capacity * loadFactor, MAXIMUM_CAPACITY + 1); //重新设置table table = new Entry[capacity]; //根据capacity初始化hashSeed initHashSeedAsNeeded(capacity); } // internal utilities void init() { } /** * Initialize the hashing mask value. We defer initialization until we * really need it. */ final boolean initHashSeedAsNeeded(int capacity) { boolean currentAltHashing = hashSeed != 0; //根据系统函数得到一个hash boolean useAltHashing = sun.misc.VM.isBooted() && (capacity >= Holder.ALTERNATIVE_HASHING_THRESHOLD); boolean switching = currentAltHashing ^ useAltHashing; //如果hashSeed初始化为0则跳过switching //否则使用系统函数得到新的hashSeed if (switching) { hashSeed = useAltHashing ? sun.misc.Hashing.randomHashSeed(this) : 0; } return switching; } /* 哈希算法的核心:哈希函数 * Retrieve object hash code and applies a supplemental hash function to the * result hash, which defends against poor quality hash functions. This is * critical because HashMap uses power-of-two length hash tables, that * otherwise encounter collisions for hashCodes that do not differ * in lower bits. Note: Null keys always map to hash 0, thus index 0. */ */ final int hash(Object k) { int h = hashSeed; //通过hashSeed初始化的值的不同来选择不同的hash方式 if (0 != h && k instanceof String) { return sun.misc.Hashing.stringHash32((String) k); } h ^= k.hashCode(); h ^= (h >>> 20) ^ (h >>> 12); return h ^ (h >>> 7) ^ (h >>> 4); } //Returns index for hash code h.通过得到的hash值来确定它在table中的位置 static int indexFor(int h, int length) { // assert Integer.bitCount(length) == 1 : "length must be a non-zero power of 2"; return h & (length-1); } public int size() { return size; } public boolean isEmpty() { return size == 0; } public V get(Object key) { if (key == null) return getForNullKey(); Entry<K,V> entry = getEntry(key);//查看调用函数,在下面 return null == entry ? null : entry.getValue(); } private V getForNullKey() { if (size == 0) { return null; } for (Entry<K,V> e = table[0]; e != null; e = e.next) { if (e.key == null) return e.value; } return null; } public boolean containsKey(Object key) { return getEntry(key) != null; } final Entry<K,V> getEntry(Object key) { if (size == 0) { return null; } //通过key的hash值确定table下标(null对应下标0) int hash = (key == null) ? 0 : hash(key); //indexFor() = h & (length-1) = hash&(table.length-1) for (Entry<K,V> e = table[indexFor(hash, table.length)]; e != null; e = e.next) //对冲突的处理办法是将线性探查,即将元素放到冲突位置的下一个可用位置上 { Object k; /*注意:因为元素可能不是刚好存在它对应hash值得下一个位置 (如果该位置之前有元素,则要放在下两个的位置,以此类推) */ if (e.hash == hash && ((k = e.key) == key || (key != null && key.equals(k)))) //所以不仅要判断hash还要判断key(因为不同的key可能有相同的hash值) return e; } return null; } /* * 1. 通过key的hash值确定table下标 * 2. 查找table下标,如果key存在则更新对应的value * 3. 如果key不存在则调用addEntry()方法 */ public V put(K key, V value) { if (table == EMPTY_TABLE) { //初始化存储表空间 inflateTable(threshold); } if (key == null) return putForNullKey(value); int hash = hash(key); int i = indexFor(hash, table.length); /* 注意: 我不断的寻找,hash值对应位置之后的可用位置在哪里 */ 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; } } //上面的循环结束表示当前的key不存在与表中,需要另外增加 modCount++; addEntry(hash, key, value, i);//函数在下面 return null; } /* 为减少篇幅,删除了一些功能实现类似的方法 大家可以自行阅读分析 */ /** * Transfers all entries from current table to newTable. */ 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; //是否重新进行hash计算 if (rehash) { e.hash = null == e.key ? 0 : hash(e.key); } int i = indexFor(e.hash, newCapacity); e.next = newTable[i]; newTable[i] = e; e = next; } } } //扩展到指定的大小 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]; //重新hash transfer(newTable, initHashSeedAsNeeded(newCapacity)); table = newTable; threshold = (int)Math.min(newCapacity * loadFactor, MAXIMUM_CAPACITY + 1); } //Entry类就是一个简单的键值对的类 static class Entry<K,V> implements Map.Entry<K,V> { final K key; V value; Entry<K,V> next;//这是一种类似指针的东西 int hash;//还要存放hash值 /* 下面是一些十分基本的构造函数以及get,set方法 */ Entry(int h, K k, V v, Entry<K,V> n) { value = v; next = n; key = k; hash = h; } public final K getKey() { return key; } public final V getValue() { return value; } public final V setValue(V newValue) { V oldValue = value; value = newValue; return oldValue; } //必须要key和value都一样才equals public final boolean equals(Object o) { if (!(o instanceof Map.Entry)) return false; Map.Entry e = (Map.Entry)o; Object k1 = getKey(); Object k2 = e.getKey(); if (k1 == k2 || (k1 != null && k1.equals(k2))) { Object v1 = getValue(); Object v2 = e.getValue(); if (v1 == v2 || (v1 != null && v1.equals(v2))) return true; } return false; } public final int hashCode() { return Objects.hashCode(getKey()) ^ Objects.hashCode(getValue()); } public final String toString() { return getKey() + "=" + getValue(); } /** * This method is invoked whenever the value in an entry is * overwritten by an invocation of put(k,v) for a key k that's already * in the HashMap. */ void recordAccess(HashMap<K,V> m) { } /** * This method is invoked whenever the entry is * removed from the table. */ void recordRemoval(HashMap<K,V> m) { } } //根据需要,可能要扩容 //由于它由Put函数调用,调用之前已经确定表中没有key的记录 //addEntry默认当前表中没有指定key的记录,直接增加记录 void addEntry(int hash, K key, V value, int bucketIndex) { //计算存放位置 if ((size >= threshold) && (null != table[bucketIndex])) { resize(2 * table.length);//将容量翻倍 hash = (null != key) ? hash(key) : 0; //寻找指定hash值对应的存放位置 bucketIndex = indexFor(hash, table.length); } createEntry(hash, key, value, bucketIndex); } //由于默认没有key的记录,所以直接增加 void createEntry(int hash, K key, V value, int bucketIndex) { Entry<K,V> e = table[bucketIndex]; table[bucketIndex] = new Entry<>(hash, key, value, e); size++; } //类似于Entry数组的迭代器,主要是对table进行操作 private abstract class HashIterator<E> implements Iterator<E> { Entry<K,V> next; // next entry to return int expectedModCount; // For fast-fail int index; // current slot Entry<K,V> current; // current entry HashIterator() { expectedModCount = modCount; if (size > 0) { // advance to first entry Entry[] t = table; while (index < t.length && (next = t[index++]) == null) ; } } public final boolean hasNext() { return next != null; } final Entry<K,V> nextEntry() { if (modCount != expectedModCount) throw new ConcurrentModificationException(); Entry<K,V> e = next; if (e == null) throw new NoSuchElementException(); if ((next = e.next) == null) { Entry[] t = table; while (index < t.length && (next = t[index++]) == null) ; } current = e; return e; } public void remove() { if (current == null) throw new IllegalStateException(); if (modCount != expectedModCount) throw new ConcurrentModificationException(); Object k = current.key; current = null; HashMap.this.removeEntryForKey(k); expectedModCount = modCount; } } private final class ValueIterator extends HashIterator<V> { public V next() { return nextEntry().value; } } private final class KeyIterator extends HashIterator<K> { public K next() { return nextEntry().getKey(); } } private final class EntryIterator extends HashIterator<Map.Entry<K,V>> { public Map.Entry<K,V> next() { return nextEntry(); } } // Subclass overrides these to alter behavior of views' iterator() method Iterator<K> newKeyIterator() { return new KeyIterator(); } Iterator<V> newValueIterator() { return new ValueIterator(); } Iterator<Map.Entry<K,V>> newEntryIterator() { return new EntryIterator(); } // Views private transient Set<Map.Entry<K,V>> entrySet = null; /** * Returns a link Set view of the keys contained in this map. */ public Set<K> keySet() { Set<K> ks = keySet; return (ks != null ? ks : (keySet = new KeySet())); } private final class KeySet extends AbstractSet<K> { public Iterator<K> iterator() { return newKeyIterator(); } public int size() { return size; } public boolean contains(Object o) { return containsKey(o); } public boolean remove(Object o) { return HashMap.this.removeEntryForKey(o) != null; } public void clear() { HashMap.this.clear(); } } /** * Returns a Collection view of the values contained in this map. */ public Collection<V> values() { Collection<V> vs = values; return (vs != null ? vs : (values = new Values())); } private final class Values extends AbstractCollection<V> { public Iterator<V> iterator() { return newValueIterator(); } public int size() { return size; } public boolean contains(Object o) { return containsValue(o); } public void clear() { HashMap.this.clear(); } } /** return a set view of the mappings contained in this map */ public Set<Map.Entry<K,V>> entrySet() { return entrySet0(); } private Set<Map.Entry<K,V>> entrySet0() { Set<Map.Entry<K,V>> es = entrySet; return es != null ? es : (entrySet = new EntrySet()); } private final class EntrySet extends AbstractSet<Map.Entry<K,V>> { public Iterator<Map.Entry<K,V>> iterator() { return newEntryIterator(); } public boolean contains(Object o) { if (!(o instanceof Map.Entry)) return false; Map.Entry<K,V> e = (Map.Entry<K,V>) o; Entry<K,V> candidate = getEntry(e.getKey()); return candidate != null && candidate.equals(e); } public boolean remove(Object o) { return removeMapping(o) != null; } public int size() { return size; } public void clear() { HashMap.this.clear(); } } private static final long serialVersionUID = 362498820763181265L; // These methods are used when serializing HashSets int capacity() { return table.length; } float loadFactor() { return loadFactor; } }
个人体会:
1.hash算法,通过系统得到初始化的hashSeed(可能是因为系统能够做到类似完全的随机吧),然后就开始各种的与运算,争取把元素都均匀分散开。
2.冲突(collision)解决的办法,线性探查:寻找当前位置之后可用的位置。所以在put,get的时候都要检测是否冲突,然后通过比较hash值和key来确定具体的寻找、删除、修改位置。
3.对于hashSeed的分析,由于系统函数较多,真的不够清晰,请多多指教
一起学习,一起进步,欢迎访问我的博客:http://blog.csdn.net/wanghao109