近期对JDK1.7和JDK1.8的HashMap源码进行了学习，今天也在这里进行个人总结一下。首先，众所周知，HashMap是以键值对的方式存储数据的，1.7的底层数据结构是数组+链表，是一个Entry数组。1.8的底层数据结构是数组+链表+红黑树·，是一个Node对象的数组。下面我就根据源码分析下HashMap是怎么进行初始化、插入数据的。
JDK1.8
1.初始化。
//构造方法1 public HashMap() { this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted }
//构造方法2 public HashMap(int initialCapacity) { this(initialCapacity, DEFAULT_LOAD_FACTOR); }
//构造方法3 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); }
构造方法主要有以上几个主要是对加载因子、阈值进行初始化。构造方法1初始化了加载因子，取默认值0.75，构造方法2初始化了阈值，默认的加载因子0.75，构造方法3初始化了阈值和加载因子。阈值的取值做了处理，取入参最小的2的幂次方的值。此时HashMap的数组还没有进行初始化，那什么时候开始初始化呢？源码在put方法的时候，如果数组为空，才进行了初始化。
2.HashMap的put方法
public V put(K key, V value) { return putVal(hash(key), key, value, false, true); }
/** * Implements Map.put and related methods *
* @param hash hash for key * @param key the key * @param value the value to put * @param onlyIfAbsent if true, don't change existing value * @param evict if false, the table is in creation mode. * @return previous value, or null if none */ 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)
//如果数组为空或长度为0就进行数据初始化
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; if (++size > threshold) resize(); afterNodeInsertion(evict); return null; }
final Node<K,V>[] resize() { Node<K,V>[] oldTab = table; int oldCap = (oldTab == null) ? 0 : oldTab.length; int oldThr = threshold; int newCap, newThr = 0; if (oldCap > 0) { if (oldCap >= MAXIMUM_CAPACITY) { threshold = Integer.MAX_VALUE; return oldTab; } 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>[] newTab = (Node<K,V>[])new Node[newCap]; table = newTab; if (oldTab != null) { for (int j = 0; j < oldCap; ++j) { Node<K,V> e; if ((e = oldTab[j]) != null) { oldTab[j] = null; if (e.next == null) newTab[e.hash & (newCap - 1)] = e; else if (e instanceof TreeNode) ((TreeNode<K,V>)e).split(this, newTab, 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; newTab[j] = loHead; } if (hiTail != null) { hiTail.next = null; newTab[j + oldCap] = hiHead; } } } } } return newTab; }
2.1.当HashMap的table为空时，就会把阈值当作容量进行初始化，然后重新根据加载因子重新计算阈值。
2.2.当HashMap的table不为空时，就计算put元素的key的下标，如果数组下标没有值，那就new一个Node对象直接插入到数组；如果key相等就覆盖；如果key不相等，就遍历这个下标的链表，如果key相等就覆盖，不相等就遍历到链表的尾部进行插入，
插入完，再判断链表的长度是否大于8，如果大于8而且数据的长度小于64，则进行数组扩容，否则就将链表转成红黑树；修改次数modCount++，长度size++，判断下如果长度大于阈值，则进行扩容；
JDK1.7
1.初始化
/** * 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(); }
/** * Constructs an empty <tt>HashMap</tt> with the specified initial * capacity and the default load factor (0.75). * * @param initialCapacity the initial capacity. * @throws IllegalArgumentException if the initial capacity is negative. */ public HashMap(int initialCapacity) { this(initialCapacity, DEFAULT_LOAD_FACTOR); }
/** * Constructs an empty <tt>HashMap</tt> with the specified initial * capacity and load factor. * * @param initialCapacity the initial capacity * @param loadFactor the load factor * @throws IllegalArgumentException if the initial capacity is negative * or the load factor is nonpositive */ 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); // Find a power of 2 >= initialCapacity int capacity = 1; while (capacity < initialCapacity) capacity <<= 1; this.loadFactor = loadFactor; threshold = (int)(capacity * loadFactor); table = new Entry[capacity]; init(); }
1.构造方法1初始化，取了默认的加载因子0.75，阈值取了16*加载因子，初始化了一个16的数组；构造方法2初始化，取入参初始容量，取最下2的幂次方容量，默认加载因子0.75，初始化阈值，初始化数组；构造方法3同样道理；
2.插入元素
/** * Associates the specified value with the specified key in this map. * If the map previously contained a mapping for the key, the old * value is replaced. * * @param key key with which the specified value is to be associated * @param value value to be associated with the specified key * @return the previous value associated with <tt>key</tt>, or * <tt>null</tt> if there was no mapping for <tt>key</tt>. * (A <tt>null</tt> return can also indicate that the map * previously associated <tt>null</tt> with <tt>key</tt>.) */ public V put(K key, V value) { if (key == null) return putForNullKey(value); int hash = hash(key.hashCode()); 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; }
/** * Offloaded version of put for null keys */ 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; }
/** * Adds a new entry with the specified key, value and hash code to * the specified bucket. It is the responsibility of this * method to resize the table if appropriate. * * Subclass overrides this to alter the behavior of put method. */ void addEntry(int hash, K key, V value, int bucketIndex) { Entry<K,V> e = table[bucketIndex]; table[bucketIndex] = new Entry<>(hash, key, value, e); if (size++ >= threshold) resize(2 * table.length); }
2.1.如果key为null，则找到数组的第一个元素，遍历这个元素的链表，如果key为null，则覆盖值，否则使用头插法插入到第一个元素中，size++，如果size大于阈值，则进行2倍扩容，扩容后遍历每个元素，使用头插法重新插入；如果key不为null，
根据key的哈希计算下标，剩下的步骤和上面一样；