天天看點

JDK源碼學習(1)-HashMap源碼分析,HashMap與HashTable的差别

Hashtable是HashMap的線程安全版本,它的實作和HashMap實作基本一緻,除了它不能包含null值的key和value,并且它在計算hash值和數組索引值的方式要稍微簡單一些。

Hashtable線程安全實作方式是将所有方法都标記成synchronized,但這樣加鎖的粒度大,容易引起一些性能問題,是以目使用java.concurrent.ConcurrentHashMap類性能更佳

在JDK1.7之後,HashMap和HashTable的哈希函數都一樣了,但由hash值轉換成表索引的方式不一樣:

  • HashMap使用&位操作 : h & (length-1);
  • HashTable使用取餘操作 : (hash & 0x7FFFFFFF) % tab.length;

HashMap源碼如下:

package java.util;  
import java.io.*;  
public class HashMap<K,V>  
    extends AbstractMap<K,V>  
    implements Map<K,V>, Cloneable, Serializable  
{  

    /* 
        HashMap 的執行個體有兩個參數影響其性能:初始容量 和加載因子。 
        容量是哈希表中桶的數量,初始容量隻是哈希表在建立時的容量。 
        加載因子是哈希表在其容量自動增加之前可以達到多滿的一種尺度。 
        當哈希表中的條目數超出了加載因子與目前容量的乘積時, 
        則要對該哈希表進行 rehash 操作(即重建内部資料結構), 
        進而哈希表将具有大約兩倍的桶數。 
        加載因子預設值為0.75,預設哈希表容量為16
    */  
    //初始化容量16 hashMap的容量必須是2的指數倍        Hashtable是11
    static final int DEFAULT_INITIAL_CAPACITY =  << ; 
    //最大容量2的30次方  
    static final int MAXIMUM_CAPACITY =  << ;  
    //預設加載因子預設的平衡因子為0.75,這是權衡了時間複雜度與空間複雜度之後的最好取值(JDK說是最好的),過高的因子會降低存儲空間但是查找(lookup,包括HashMap中的put與get方法)的時間就會增加。
    static final float DEFAULT_LOAD_FACTOR = f;  
    //用來存儲鍵值對的Entry數組,用于設定剛剛初始化的HashMap對象,用來減少存儲空間  
    static final Entry<?,?>[] EMPTY_TABLE = {};  
    //大小必須是2的倍數  
    transient Entry<K,V>[] table = (Entry<K,V>[]) EMPTY_TABLE;  
    //存儲的鍵值對的數目  
    transient int size;  

    //門檻值,當size超過threshold時,table将會擴容.  
    //threshold = capacity * loadFactor  
    int threshold;  

    //加載因子      
    final float loadFactor;  
    //修改次數,用于檢查線程是否同步  
    transient int modCount;     
    //預設的閥值  
    static final int ALTERNATIVE_HASHING_THRESHOLD_DEFAULT = Integer.MAX_VALUE;  

    private static class Holder {          
        static final int ALTERNATIVE_HASHING_THRESHOLD;  
        static {  
            //擷取jdk内置的閥值  
            String altThreshold = java.security.AccessController.doPrivileged(  
                new sun.security.action.GetPropertyAction(  
                    "jdk.map.althashing.threshold"));  

            int threshold;  
            try {  
                //設定目前閥值  
                threshold = (null != altThreshold)  
                        ? Integer.parseInt(altThreshold)  
                        : ALTERNATIVE_HASHING_THRESHOLD_DEFAULT;  
                // disable alternative hashing if -1  
                if (threshold == -) {  
                    threshold = Integer.MAX_VALUE;  
                }  
                if (threshold < ) {  
                    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載因子初始化HashMap  
    public HashMap(int initialCapacity, float loadFactor) {  
        if (initialCapacity < )  
            throw new IllegalArgumentException("Illegal initial capacity: " +  
                                               initialCapacity);  
        if (initialCapacity > MAXIMUM_CAPACITY)  
            initialCapacity = MAXIMUM_CAPACITY;  
        if (loadFactor <=  || 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) + ,  
                      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 = ;  

    //工具函數,将number擴充成2的倍數  
    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)) !=   
                    ? (Integer.bitCount(number) > ) ? rounded <<  : rounded  
                    : ;  

        return rounded;  
    }  

    //将表格大小擴充到toSize  
    private void inflateTable(int toSize) {  
        // Find a power of 2 >= toSize  
        int capacity = roundUpToPowerOf2(toSize);  
        //重新設定閥值  
        threshold = (int) Math.min(capacity * loadFactor, MAXIMUM_CAPACITY + );  
        //重新設定table  
        table = new Entry[capacity];  
        //根據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 != ;  
        //根據系統函數得到一個hash  
        boolean useAltHashing = sun.misc.VM.isBooted() &&  
                (capacity >= Holder.ALTERNATIVE_HASHING_THRESHOLD);  
        boolean switching = currentAltHashing ^ useAltHashing;  
        //如果hashSeed初始化為0則跳過switching  
        //否則使用系統函數得到新的hashSeed  
        if (switching) {  
            hashSeed = useAltHashing  
                ? sun.misc.Hashing.randomHashSeed(this)  
                : ;  
        }  
        return switching;  
    }  

    /* 
        雜湊演算法的核心:哈希函數 
     * 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;  
        //通過hashSeed初始化的值的不同來選擇不同的hash方式  
        if ( != h && k instanceof String) {  
 //String類采用不同的hash函數
            return sun.misc.Hashing.stringHash32((String) k);  
        }    
        h ^= k.hashCode();    
        h ^= (h >>> ) ^ (h >>> );  
        return h ^ (h >>> ) ^ (h >>> );  
    }  

    //Returns index for hash code h.通過得到的hash值來确定它在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-);  
    }  
           

上面的hash()方法和indexFor()是hashMap當中的一個重點。

看到這麼多位操作,是不是覺得暈頭轉向了呢,還是搞清楚原理就行了,畢竟位操作速度是很快的,不能因為不好了解就不用了。

在哈希表容量(也就是buckets或slots大小)為length的情況下,為了使每個key都能在沖突最小的情況下映射到[0,length)(注意是左閉右開區間)的索引(index)内,一般有兩種做法:

  • 方法1:讓length為素數,然後用hashCode(key) mod length的方法得到索引
  • 方法2:讓length為2的指數倍,然後用hashCode(key) & (length-1)的方法得到索引

HashTable用的是方法1,HashMap用的是方法2。重點說說方法2的情況,方法2其實也比較好了解:

因為length為2的指數倍,是以length-1所對應的二進制位都為1,然後在與hashCode(key)做與運算,即可得到[0,length)内的索引。但是這裡有個問題,如果hashCode(key)的大于length的值,而且hashCode(key)的二進制位的低位變化不大,那麼沖突就會很多,舉個例子:

Java中對象的哈希值都32位整數,而HashMap預設大小為16,那麼有兩個對象那麼的哈希值分别為:0xABAB0000與0xBABA0000,它們的後幾位都是一樣,那麼與16異或後得到結果應該也是一樣的,也就是産生了沖突。造成沖突的原因關鍵在于16限制了隻能用低位來計算,高位直接舍棄了,是以我們需要額外的哈希函數而不隻是簡單的對象的hashCode方法了。具體來說,就是HashMap中hash函數幹的事了。

繼續分析源碼:

public int size() {  
        return size;  
    }  

    public boolean isEmpty() {  
        return size == ;  
    }  

    public V get(Object key) {  
        if (key == null)  
            return getForNullKey();  
        Entry<K,V> entry = getEntry(key);//檢視調用函數,在下面  

        return null == entry ? null : entry.getValue();  
    }  

    private V getForNullKey() {  
        if (size == ) {  
            return null;  
        }  
        for (Entry<K,V> e = table[]; 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 == ) {  
            return null;  
        }  
        //通過key的hash值确定table下标(null對應下标0)  
        int hash = (key == null) ?  : 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)  
        //對沖突的處理辦法是将線性探查,即将元素放到沖突位置的下一個可用位置上  
        {  
            Object k;  
            /*注意:因為元素可能不是剛好存在它對應hash值得下一個位置 
                (如果該位置之前有元素,則要放在下兩個的位置,以此類推) 
            */  
            if (e.hash == hash &&  
                ((k = e.key) == key || (key != null && key.equals(k))))  
                //是以不僅要判斷hash還要判斷key(因為不同的key可能有相同的hash值)  
                return e;  
        }  
        return null;  
    }  

     /* 
     * 1. 通過key的hash值确定table下标 
     * 2. 查找table下标,如果key存在則更新對應的value 
     * 3. 如果key不存在則調用addEntry()方法 
     */  
    public V put(K key, V value) {  
        if (table == EMPTY_TABLE) {  
        //初始化存儲表空間  
            inflateTable(threshold);  
        }  
        if (key == null)  
            return putForNullKey(value);  
        int hash = hash(key);  
        int i = indexFor(hash, table.length);  
        /* 
            注意: 
            我不斷的尋找,hash值對應位置之後的可用位置在哪裡 
        */  
        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;  
            }  
        }  
        //上面的循環結束表示目前的key不存在與表中,需要另外增加  
        modCount++;  
        addEntry(hash, key, value, i);//函數在下面  
        return null;  
    }  

    /* 
        為減少篇幅,删除了一些功能實作類似的方法 
        大家可以自行閱讀分析   
    */  


     /** 
     * 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;  
                //是否重新進行hash計算  
                if (rehash) {  
                    e.hash = null == e.key ?  : hash(e.key);  
                }  
                int i = indexFor(e.hash, newCapacity);  
                e.next = newTable[i];  
                newTable[i] = e;  
                e = next;  
            }  
        }  
    }  

    //擴充到指定的大小  
    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 + );  
    }  


    //Entry類就是一個簡單的鍵值對的類  
    static class Entry<K,V> implements Map.Entry<K,V> {  
        final K key;  
        V value;  
        Entry<K,V> next;//這是一種類似指針的東西  
        int hash;//還要存放hash值  

        /* 
        下面是一些十分基本的構造函數以及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;  
        }  

        //必須要key和value都一樣才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) {  
        }  
    }  

     //根據需要,可能要擴容  
     //由于它由Put函數調用,調用之前已經确定表中沒有key的記錄  
     //addEntry預設目前表中沒有指定key的記錄,直接增加記錄  
    void addEntry(int hash, K key, V value, int bucketIndex) {  
        //計算存放位置  
        if ((size >= threshold) && (null != table[bucketIndex])) {  
            resize( * table.length);//将容量翻倍  
            hash = (null != key) ? hash(key) : ;  
            //尋找指定hash值對應的存放位置  
            bucketIndex = indexFor(hash, table.length);  
        }  

        createEntry(hash, key, value, bucketIndex);  
    }  


     //由于預設沒有key的記錄,是以直接增加  
    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++;  
    }  

    //類似于Entry數組的疊代器,主要是對table進行操作  
    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 > ) { // 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();  
        }  
    }  
}  
           

其他文章: JDK源碼學習(2)-TreeMap源碼分析

深入Java集合學習系列:HashMap的實作原理

繼續閱讀