HashMap 源码解析

1. 基本结构

HashMap 的核心是一个数组，每个数组元素是一个链表或红黑树（JDK 1.8 及以后）。当哈希冲突发生时，链表或红黑树用于存储多个键值对。

// HashMap的基本结构
public class HashMap<K, V> extends AbstractMap<K, V>
    implements Map<K, V>, Cloneable, Serializable {
    
    // 默认初始容量为16
    static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // aka 16

    // 最大容量为2^30
    static final int MAXIMUM_CAPACITY = 1 << 30;

    // 默认加载因子为0.75
    static final float DEFAULT_LOAD_FACTOR = 0.75f;

    // 链表转化为红黑树的阈值
    static final int TREEIFY_THRESHOLD = 8;

    // 红黑树转化为链表的阈值
    static final int UNTREEIFY_THRESHOLD = 6;

    // 最小树化容量
    static final int MIN_TREEIFY_CAPACITY = 64;

    // 存储元素的数组
    transient Node<K, V>[] table;

    // 存储具体键值对的集合
    transient Set<Map.Entry<K, V>> entrySet;

    // 存储的键值对的数量
    transient int size;

    // 扩容和其他结构修改次数
    transient int modCount;

    // 阈值
    int threshold;

    // 加载因子
    final float loadFactor;

    // Node 是 HashMap 的基本结构
    static class Node<K, V> implements Map.Entry<K, V> {
        final int hash;
        final K key;
        V value;
        Node<K, V> next;

        Node(int hash, K key, V value, Node<K, V> next) {
            this.hash = hash;
            this.key = key;
            this.value = value;
            this.next = next;
        }

        public final K getKey()        { return key; }
        public final V getValue()      { return value; }
        public final String toString() { return key + "=" + value; }
        public final int hashCode()    { return Objects.hashCode(key) ^ Objects.hashCode(value); }
        public final V setValue(V newValue) {
            V oldValue = value;
            value = newValue;
            return oldValue;
        }
        public final boolean equals(Object o) {
            if (o == this)
                return true;
            if (o instanceof Map.Entry) {
                Map.Entry<?,?> e = (Map.Entry<?,?>)o;
                if (Objects.equals(key, e.getKey()) &&
                    Objects.equals(value, e.getValue()))
                    return true;
            }
            return false;
        }
    }
    
    // 其他重要的方法和类
    // ...
}

2. 哈希算法

HashMap 使用的哈希算法通过扰动函数减少哈希冲突，提高查找效率。

static final int hash(Object key) {
    int h;
    return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}

这个方法对键的哈希码进行高低16位混合，以增加随机性，减少冲突。

3. 初始化和扩容

HashMap 在插入元素时，会检查当前容量是否需要扩容，如果需要，就进行扩容。扩容时，新容量是旧容量的两倍。

// 初始化
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;
    this.threshold = tableSizeFor(initialCapacity);
}

// 扩容
final Node<K, V>[] resize() {
    Node<K, V>[] oldTable = table;
    int oldCap = (oldTable == null) ? 0 : oldTable.length;
    int oldThr = threshold;
    int newCap, newThr = 0;
    if (oldCap > 0) {
        if (oldCap >= MAXIMUM_CAPACITY) {
            threshold = Integer.MAX_VALUE;
            return oldTable;
        }
        else if ((newCap = oldCap << 1) < MAXIMUM_CAPACITY &&
                 oldCap >= DEFAULT_INITIAL_CAPACITY)
            newThr = oldThr << 1; // double threshold
    }
    else if (oldThr > 0) // initial capacity was placed in threshold
        newCap = oldThr;
    else {               // zero initial threshold signifies using defaults
        newCap = DEFAULT_INITIAL_CAPACITY;
        newThr = (int)(DEFAULT_LOAD_FACTOR * DEFAULT_INITIAL_CAPACITY);
    }
    if (newThr == 0) {
        float ft = (float)newCap * loadFactor;
        newThr = (newCap < MAXIMUM_CAPACITY && ft < (float)MAXIMUM_CAPACITY ?
                  (int)ft : Integer.MAX_VALUE);
    }
    threshold = newThr;
    @SuppressWarnings({"rawtypes","unchecked"})
    Node<K, V>[] newTable = (Node<K, V>[])new Node[newCap];
    table = newTable;
    if (oldTable != null) {
        for (int j = 0; j < oldCap; ++j) {
            Node<K, V> e;
            if ((e = oldTable[j]) != null) {
                oldTable[j] = null;
                if (e.next == null)
                    newTable[e.hash & (newCap - 1)] = e;
                else if (e instanceof TreeNode)
                    ((TreeNode<K, V>)e).split(this, newTable, j, oldCap);
                else { // preserve order
                    Node<K, V> loHead = null, loTail = null;
                    Node<K, V> hiHead = null, hiTail = null;
                    Node<K, V> next;
                    do {
                        next = e.next;
                        if ((e.hash & oldCap) == 0) {
                            if (loTail == null)
                                loHead = e;
                            else
                                loTail.next = e;
                            loTail = e;
                        }
                        else {
                            if (hiTail == null)
                                hiHead = e;
                            else
                                hiTail.next = e;
                            hiTail = e;
                        }
                    } while ((e = next) != null);
                    if (loTail != null) {
                        loTail.next = null;
                        newTable[j] = loHead;
                    }
                    if (hiTail != null) {
                        hiTail.next = null;
                        newTable[j + oldCap] = hiHead;
                    }
                }
            }
        }
    }
    return newTable;
}

4. 插入元素

插入元素时，首先计算元素的哈希值，然后确定存储位置。如果发生哈希冲突，将元素链入当前链表或红黑树中。

public V put(K key, V value) {
    return putVal(hash(key), key, value, false, true);
}

final V putVal(int hash, K key, V value, boolean onlyIfAbsent, boolean evict) {
    Node<K, V>[] tab; Node<K, V> p; int n, i;
    if ((tab = table) == null || (n = tab.length) == 0)
        n = (tab = resize()).length;
    if ((p = tab[i = (n - 1) & hash]) == null)
        tab[i] = newNode(hash, key, value, null);
    else {
        Node<K, V> e; K k;
        if (p.hash == hash && ((k = p.key) == key || (key != null && key.equals(k))))
            e = p;
        else if (p instanceof TreeNode)
            e = ((TreeNode<K, V>)p).putTreeVal(this, tab, hash, key, value);
        else {
            for (int binCount = 0; ; ++binCount) {
                if ((e = p.next) == null) {
                    p.next = newNode(hash, key, value, null);
                    if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for 1st
                        treeifyBin(tab, hash);
                    break;
                }
                if (e.hash == hash && ((k = e.key) == key || (key != null && key.equals(k))))
                    break;
                p = e;
            }
        }
        if (e != null) { // existing mapping for key
            V oldValue = e.value;
            if (!onlyIfAbsent || oldValue == null)
                e.value = value;
            afterNodeAccess(e);
            return oldValue;
        }
    }
    
    ++modCount;