HashMap源码分析

本文的写作，参考了兰亭风雨的相关博客。

读懂HashMap需要具备一些基础知识

一、基础知识

1、散列

参考【数据结构与算法分析java语言描述】第五章【散列】，

这里我们不讨论具体的哈希的原理。

     1）散列表数据结构只不过是一个包含项（item）的具有固定大小的数组。

     2）散列数组中，每一个项，叫做一个“桶”，英文bucket，它的下标叫bucketIndex。HashMap的结构如下，

HashMap就是一个散列结构，具体到它的内部，就是名为table的Entry数组，代表这个HashMap。table的下标，是每一个Entry的key的hash值与table的length做“与运算”得到的int值（这个功能是indexFor()实现的）。

2、链表

HashMap中的Entry<K,V>，是一个静态内部类，它是一个链表结构；每一个Entry保存自身的key，value，hashCode，以及指向下一个的Entry。

二、indexFor函数的说明：

indexFor函数，参数h代表，hashMap每次put的时候的key的hash值，length代码hashMap当前的大小。

indexFor作用是根据当前key的hash来确定，这一个放入HashMap数组中的Entry应该出于数组的哪一个位置（index）中？

    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);
    }

必要条件是，这个位置bucketIndex肯定不能超过数组大小。于是，最容易的方法是肯定取模。即int bucketIndex = hashNumber % length；然而这个方法效率不高。

另一种方法：

任意正整数a，除以2^n，所得余数c，有如下公式 a = c + k * 2^n（即 被除数= 余数 + 商*除数，这里除数2^n）

把a转换为二进制数，如下，

当除数是2^n，将被除数a的二进制数，右移n位，得到的数就是商，而被移除掉的数字就是余数。

也就是说我们只要得到上图红线右侧的内容就是余数，那么只要将原数字a & （2^n - 1）就可以。

即indexFor()中的

return h & (length-1);

Integer.bitCount(int param)，获取param的二进制数中1的个数。

Integer.highestOneBit(int param)，获取param的二进制数中，最左侧第一个1，所代表的int值。也就是不大于当前param的最大的2的n次方。

以下是全部代码分析，必要的地方做了注释，

package java.util;
import java.io.*;

public class HashMap<K,V> extends AbstractMap<K,V> implements Map<K,V>, Cloneable, Serializable{

    static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16

    static final int MAXIMUM_CAPACITY = 1 << 30;
    static final float DEFAULT_LOAD_FACTOR = 0.75f;
    // 空Entry数组
    static final Entry<?,?>[] EMPTY_TABLE = {};
    // 初始化table
    transient Entry<K,V>[] table = (Entry<K,V>[]) EMPTY_TABLE;
    // 保存的Entry数量
    transient int size;
    // 当threshold大于size（Entry的数量）时，调用resize，
    int threshold;

    final float loadFactor;
    // 修改次数
    transient int modCount;

    static final int ALTERNATIVE_HASHING_THRESHOLD_DEFAULT = Integer.MAX_VALUE;
    private static class Holder {
        static final int ALTERNATIVE_HASHING_THRESHOLD;

        static {
            String altThreshold = java.security.AccessController.doPrivileged(
                new sun.security.action.GetPropertyAction(
                    "jdk.map.althashing.threshold"));

            int threshold;
            try {
                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;
        }
    }

    transient int hashSeed = 0;

    // HashMap初始化，table仍然是EMPTY_TABLE，即空Entry数组
    // threshold赋值为initialCapacity，默认情况这个值是16
    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);
    }

    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);
    }

    // 取得当前大于number的最小的2的n次方
    // number >= MAXIMUM_CAPACITY            = MAXIMUM_CAPACITY
    // number <= 1                           = 1
    // 1 < number < MAXIMUM_CAPACITY         = 大于当前number的最小的2的n次方
    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;
    }
    
    //上面版本不太好阅读，翻译成以下版本。
    private static int roundUpToPowerOf2(int number){
        int rounded;
        if(number >= MAXIMUM_CAPACITY){
            rounded = MAXIMUM_CAPACITY;
        }else{
            //Integer.highestOneBit，取大于number的最小的2的幂。
            if( (rounded = Integer.highestOneBit(number)) != 0){//如果number不为0
                if(Integer.bitCount(number) > 1){//如果number>1
                    //注意，此时rounded已经是大于number的最小的2的幂。
                    rounded = rounded << 1;      //将上述rounded左移一位，即乘以2。
                }else{
                    rounded = rounded;
                }
            }else{//如果number为0
                rounded = 1;
            }
        }
        return rounded;
    }


    // 1、将table变量指向一个新Entry数组，数组length为大于参数的最小2的n次方
    // 2、修改threshold，为 数组大小* loadFactor
    // 3、修正hashSeed
    private void inflateTable(int toSize) {
        // Find a power of 2 >= toSize
        int capacity = roundUpToPowerOf2(toSize);

        threshold = (int) Math.min(capacity * loadFactor, MAXIMUM_CAPACITY + 1);
        table = new Entry[capacity];
        initHashSeedAsNeeded(capacity);
    }

    void init() {
    }
    // initHashSeedAsNeeded，1：修正hashSeed；2：返回boolean
    final boolean initHashSeedAsNeeded(int capacity) {
        boolean currentAltHashing = hashSeed != 0;
        boolean useAltHashing = sun.misc.VM.isBooted() &&
                (capacity >= Holder.ALTERNATIVE_HASHING_THRESHOLD);
        boolean switching = currentAltHashing ^ useAltHashing;
        if (switching) {
            hashSeed = useAltHashing
                ? sun.misc.Hashing.randomHashSeed(this)
                : 0;
        }
        return switching;
    }

    final int hash(Object k) {
        int h = hashSeed;
        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);
    }
    // 将key的hash值与table的length做与运算，得到的int值即为该key在Entry数组中的位置，即bucketIndex。
    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);

        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;
    }
    
    // 1、根据key值获取hash值
    // 2、在Entry数组中找到指定的bucket，取出其中的Entry（链表），
    // 3、遍历这个Entry，如果Entry链表中存在一个Entry的key与传入的key相同，则返回这个Entry
    final Entry<K,V> getEntry(Object key) {
        if (size == 0) {
            return null;
        }

        int hash = (key == null) ? 0 : hash(key);
        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;
    }

    // 1、判断table是否为null，若是则调用inflateTable()，参数threshold的值为16（在构造函数中赋值），
    //    调用roundUpToPowerOf2（大于当前数值的最小的2的n次方）确定capacity，然后new一个Entry数组
    //    调整threshold的值，调整hashseed
    // 2、计算key的hash值，调用indexFor确定此key在Entry数组中的bucketIndex
    // 3、取出Entry数组中的第一个Entry（链表），遍历这个链表，
    //    3.1、若存在一个Entry的key等于当前key则把这个Entry的value修改，并把old value返回出去，put函数终止
    //    3.2、若不存在，modCount++，调用addEntry
    //       3.2.1、判断size是否大于threshold，若是则调用resize()，
    //       3.2.2、调用createEntry()，先根据bucketIndex取出Entry数组中的Entry（可能为null）
    //              然后new一个Entry，并把刚取出的Entry作为新Entry的next，
    //              size++（Entry的数量）
    public V put(K key, V value) {
        if (table == EMPTY_TABLE) {
            inflateTable(threshold);
        }
        if (key == null)
            return putForNullKey(value);
        int hash = hash(key);
        int i = indexFor(hash, table.length);
        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;
            }
        }

        modCount++;
        addEntry(hash, key, value, i);
        return null;
    }

    private V putForNullKey(V value) {
        for (Entry<K,V> e = table[0]; e != null; e = e.next) {
            if (e.key == null) {
                V oldValue = e.value;
                e.value = value;
                e.recordAccess(this);
                return oldValue;
            }
        }
        modCount++;
        addEntry(0, null, value, 0);
        return null;
    }

    private void putForCreate(K key, V value) {
        int hash = null == key ? 0 : hash(key);
        int i = indexFor(hash, table.length);

        for (Entry<K,V> e = table[i]; e != null; e = e.next) {
            Object k;
            if (e.hash == hash &&
                ((k = e.key) == key || (key != null && key.equals(k)))) {
                e.value = value;
                return;
            }
        }

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

    private void putAllForCreate(Map<? extends K, ? extends V> m) {
        for (Map.Entry<? extends K, ? extends V> e : m.entrySet())
            putForCreate(e.getKey(), e.getValue());
    }

    // 1、从暴露给外界的函数看，HashMap中调用resize()地方只有两处1：put()；2：putAll()
    //    put()传给resize的参数是Entry数组的length*2；putAll不知道
    // 2、resize()根据传入的参数newCapacity，new一个新Entry数组，
    // 3、调用initHashSeedAsNeeded，修正hashSeed，并返回，
    // 4、调用transfer()将旧Entry数组中的内容全部copy到新Entry数组
    // 5、调整threshold的值newCapacity * loadFactor
    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);
                e.next = newTable[i];
                newTable[i] = e;
                e = next;
            }
        }
    }

    public void putAll(Map<? extends K, ? extends V> m) {
        int numKeysToBeAdded = m.size();
        if (numKeysToBeAdded == 0)
            return;

        if (table == EMPTY_TABLE) {
            inflateTable((int) Math.max(numKeysToBeAdded * loadFactor, threshold));
        }

        if (numKeysToBeAdded > threshold) {
            int targetCapacity = (int)(numKeysToBeAdded / loadFactor + 1);
            if (targetCapacity > MAXIMUM_CAPACITY)
                targetCapacity = MAXIMUM_CAPACITY;
            int newCapacity = table.length;
            while (newCapacity < targetCapacity)
                newCapacity <<= 1;
            if (newCapacity > table.length)
                resize(newCapacity);
        }

        for (Map.Entry<? extends K, ? extends V> e : m.entrySet())
            put(e.getKey(), e.getValue());
    }

    public V remove(Object key) {
        Entry<K,V> e = removeEntryForKey(key);
        return (e == null ? null : e.value);
    }

    final Entry<K,V> removeEntryForKey(Object key) {
        if (size == 0) {
            return null;
        }
        int hash = (key == null) ? 0 : hash(key);
        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;
    }

    final Entry<K,V> removeMapping(Object o) {
        if (size == 0 || !(o instanceof Map.Entry))
            return null;

        Map.Entry<K,V> entry = (Map.Entry<K,V>) o;
        Object key = entry.getKey();
        int hash = (key == null) ? 0 : hash(key);
        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;
            if (e.hash == hash && e.equals(entry)) {
                modCount++;
                size--;
                if (prev == e)
                    table[i] = next;
                else
                    prev.next = next;
                e.recordRemoval(this);
                return e;
            }
            prev = e;
            e = next;
        }

        return e;
    }

    public void clear() {
        modCount++;
        Arrays.fill(table, null);
        size = 0;
    }

    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;
    }

    private boolean containsNullValue() {
        Entry[] tab = table;
        for (int i = 0; i < tab.length ; i++)
            for (Entry e = tab[i] ; e != null ; e = e.next)
                if (e.value == null)
                    return true;
        return false;
    }

    public Object clone() {
        HashMap<K,V> result = null;
        try {
            result = (HashMap<K,V>)super.clone();
        } catch (CloneNotSupportedException e) {
            // assert false;
        }
        if (result.table != EMPTY_TABLE) {
            result.inflateTable(Math.min(
                (int) Math.min(
                    size * Math.min(1 / loadFactor, 4.0f),
                    // we have limits...
                    HashMap.MAXIMUM_CAPACITY),
               table.length));
        }
        result.entrySet = null;
        result.modCount = 0;
        result.size = 0;
        result.init();
        result.putAllForCreate(this);

        return result;
    }

    static class Entry<K,V> implements Map.Entry<K,V> {
        final K key;
        V value;
        Entry<K,V> next;
        int hash;

        /**
         * Creates new entry.
         */
        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;
        }

        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();
        }

        void recordAccess(HashMap<K,V> m) {
        }

        void recordRemoval(HashMap<K,V> m) {
        }
    }

    void addEntry(int hash, K key, V value, int bucketIndex) {
        if ((size >= threshold) && (null != table[bucketIndex])) {
            resize(2 * table.length);
            hash = (null != key) ? hash(key) : 0;
            bucketIndex = indexFor(hash, table.length);
        }

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


    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++;
    }

    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;

    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();
        }
    }

    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();
        }
    }

    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 void writeObject(java.io.ObjectOutputStream s)
        throws IOException
    {
        // Write out the threshold, loadfactor, and any hidden stuff
        s.defaultWriteObject();

        // Write out number of buckets
        if (table==EMPTY_TABLE) {
            s.writeInt(roundUpToPowerOf2(threshold));
        } else {
           s.writeInt(table.length);
        }

        // Write out size (number of Mappings)
        s.writeInt(size);

        // Write out keys and values (alternating)
        if (size > 0) {
            for(Map.Entry<K,V> e : entrySet0()) {
                s.writeObject(e.getKey());
                s.writeObject(e.getValue());
            }
        }
    }

    private static final long serialVersionUID = 362498820763181265L;

    private void readObject(java.io.ObjectInputStream s)
         throws IOException, ClassNotFoundException
    {
        // Read in the threshold (ignored), loadfactor, and any hidden stuff
        s.defaultReadObject();
        if (loadFactor <= 0 || Float.isNaN(loadFactor)) {
            throw new InvalidObjectException("Illegal load factor: " +
                                               loadFactor);
        }

        // set other fields that need values
        table = (Entry<K,V>[]) EMPTY_TABLE;

        // Read in number of buckets
        s.readInt(); // ignored.

        // Read number of mappings
        int mappings = s.readInt();
        if (mappings < 0)
            throw new InvalidObjectException("Illegal mappings count: " +
                                               mappings);

        // capacity chosen by number of mappings and desired load (if >= 0.25)
        int capacity = (int) Math.min(
                    mappings * Math.min(1 / loadFactor, 4.0f),
                    // we have limits...
                    HashMap.MAXIMUM_CAPACITY);

        // allocate the bucket array;
        if (mappings > 0) {
            inflateTable(capacity);
        } else {
            threshold = capacity;
        }

        init();  // Give subclass a chance to do its thing.

        // Read the keys and values, and put the mappings in the HashMap
        for (int i = 0; i < mappings; i++) {
            K key = (K) s.readObject();
            V value = (V) s.readObject();
            putForCreate(key, value);
        }
    }

    // These methods are used when serializing HashSets
    int   capacity()     { return table.length; }
    float loadFactor()   { return loadFactor;   }
}