首页 > 代码库 > HashMap源代码剖析
HashMap源代码剖析
大部分思路都是一样的 。仅仅是一些细节不一样。源代码中都标了出来。jdk容器源代码还是挺简单的。
public class HashMap<K,V> extends AbstractMap<K,V> implements Map<K,V>, Cloneable, Serializable { //容量默认值 static final int DEFAULT_INITIAL_CAPACITY = 16; //最大容量 static final int MAXIMUM_CAPACITY = 1 << 30; //装载因子 static final float DEFAULT_LOAD_FACTOR = 0.75f; //数据域 transient Entry[] table; //元素个数 transient int size; //阈值 int threshold; //装在因子 final float loadFactor; //volatile不会再线程私有的地方保留副本。直接写入主存,而且防止JVM重排序 transient volatile int modCount; //构造函数 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); //选取比initialCapacity大的最小2的幂次 int capacity = 1; while (capacity < initialCapacity) capacity <<= 1; this.loadFactor = loadFactor; threshold = (int)(capacity * loadFactor); table = new Entry[capacity]; init(); } //构造函数 public HashMap(int initialCapacity) { this(initialCapacity, DEFAULT_LOAD_FACTOR); } //默认构造函数 public HashMap() { this.loadFactor = DEFAULT_LOAD_FACTOR; threshold = (int)(DEFAULT_INITIAL_CAPACITY * DEFAULT_LOAD_FACTOR); table = new Entry[DEFAULT_INITIAL_CAPACITY]; init(); } public HashMap(Map<? extends K, ? extends V> m) { this(Math.max((int) (m.size() / DEFAULT_LOAD_FACTOR) + 1, DEFAULT_INITIAL_CAPACITY), DEFAULT_LOAD_FACTOR); putAllForCreate(m); } void init() { } //关键 使hash分布跟均匀 冲突更少 static int hash(int h) { // This function ensures that hashCodes that differ only by // constant multiples at each bit position have a bounded // number of collisions (approximately 8 at default load factor). h ^= (h >>> 20) ^ (h >>> 12); return h ^ (h >>> 7) ^ (h >>> 4); } //与hashTable不同这里进行与运算 static int indexFor(int h, int length) { 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(); int hash = hash(key.hashCode()); 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.equals(k))) return e.value; } return null; } //得到 null key的value private V getForNullKey() { 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; } //得到key final Entry<K,V> getEntry(Object key) { int hash = (key == null) ? 0 : hash(key.hashCode()); for (Entry<K,V> e = table[indexFor(hash, table.length)]; e != null; e = e.next) { Object k; //key相等要 hash和equals同一时候满足 if (e.hash == hash && ((k = e.key) == key || (key != null && key.equals(k)))) return e; } return null; } 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 = http://www.mamicode.com/e.value;>0 : hash(key.hashCode()); int i = indexFor(hash, table.length); /** * Look for preexisting entry for key. This will never happen for * clone or deserialize. It will only happen for construction if the * input Map is a sorted map whose ordering is inconsistent w/ equals. */ 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 = http://www.mamicode.com/value;>
extends V> m) { for (Iterator<? extends Map.Entry<?
extends K, ? extends V>> i = m.entrySet().iterator(); i.hasNext(); ) { Map.Entry<? extends K, ? extends V> e = i.next(); putForCreate(e.getKey(), e.getValue()); } } //扩容 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); table = newTable; threshold = (int)(newCapacity * loadFactor); } //转移元素 void transfer(Entry[] newTable) { Entry[] src = http://www.mamicode.com/table;>
extends Map.Entry<?
extends K, ? extends V>> i = m.entrySet().iterator(); i.hasNext(); ) { Map.Entry<? extends K, ?
extends V> e = i.next(); 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) { int hash = (key == null) ? 0 : hash(key.hashCode()); 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 (!(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.hashCode()); 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++; Entry[] tab = table; for (int i = 0; i < tab.length; i++) tab[i] = null; size = 0; } public boolean containsValue(Object value) { if (value =http://www.mamicode.com/= null)>
0 : key.hashCode()) ^ (value=http://www.mamicode.com/=null ? 0 : value.hashCode());"=" + 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) { } } void addEntry(int hash, K key, V value, int bucketIndex) { Entry<K,V> e = table[bucketIndex]; table[bucketIndex] = new Entry<K,V>(hash, key, value, e); if (size++ >= threshold) resize(2 * table.length); } void createEntry(int hash, K key, V value, int bucketIndex) { Entry<K,V> e = table[bucketIndex]; table[bucketIndex] = new Entry<K,V>(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; } } //直接从 HashIterator的返回值改一下 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 { Iterator<Map.Entry<K,V>> i = (size > 0) ? entrySet0().iterator() : null; // Write out the threshold, loadfactor, and any hidden stuff s.defaultWriteObject(); // Write out number of buckets s.writeInt(table.length); // Write out size (number of Mappings) s.writeInt(size); // Write out keys and values (alternating) if (i != null) { while (i.hasNext()) { Map.Entry<K,V> e = i.next(); 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, loadfactor, and any hidden stuff s.defaultReadObject(); // Read in number of buckets and allocate the bucket array; int numBuckets = s.readInt(); table = new Entry[numBuckets]; init(); // Give subclass a chance to do its thing. // Read in size (number of Mappings) int size = s.readInt(); // Read the keys and values, and put the mappings in the HashMap for (int i=0; i<size; i++) { K key = (K) s.readObject(); V value = http://www.mamicode.com/(V) s.readObject();>
几点总结
1、首先要清楚HashMap的存储结构,例如以下图所看到的:
图中,紫色部分即代表哈希表。也称为哈希数组,数组的每一个元素都是一个单链表的头节点。链表是用来解决冲突的,假设不同的key映射到了数组的同一位置处,就将其放入单链表中。
2、首先看链表中节点的数据结构:
- // Entry是单向链表。
- // 它是 “HashMap链式存储法”相应的链表。
- // 它实现了Map.Entry 接口,即实现getKey(), getValue(), setValue(V value), equals(Object o), hashCode()这些函数
- static class Entry<K,V> implements Map.Entry<K,V> {
- final K key;
- V value;
- // 指向下一个节点
- Entry<K,V> next;
- final int hash;
-
// 构造函数。
- // 输入參数包含"哈希值(h)", "键(k)", "值(v)", "下一节点(n)"
- 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;
- }
- // 推断两个Entry是否相等
- // 若两个Entry的“key”和“value”都相等,则返回true。
- // 否则,返回false
- 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;
- }
- // 实现hashCode()
- public final int hashCode() {
- return (key==null ? 0 : key.hashCode()) ^
- (value=http://www.mamicode.com/=null ? 0 : value.hashCode());
- }
- public final String toString() {
- return getKey() + "=" + getValue();
- }
- // 当向HashMap中加入元素时。绘调用recordAccess()。
- // 这里不做不论什么处理
- void recordAccess(HashMap<K,V> m) {
- }
- // 当从HashMap中删除元素时,绘调用recordRemoval()。
- // 这里不做不论什么处理
- void recordRemoval(HashMap<K,V> m) {
- }
- }
3、HashMap共同拥有四个构造方法。构造方法中提到了两个非常重要的參数:初始容量和载入因子。这两个參数是影响HashMap性能的重要參数,当中容量表示哈希表中槽的数量(即哈希数组的长度),初始容量是创建哈希表时的容量(从构造函数中能够看出。假设不指明,则默觉得16)。载入因子是哈希表在其容量自己主动添加之前能够达到多满的一种尺度,当哈希表中的条目数超出了载入因子与当前容量的乘积时,则要对该哈希表进行 resize 操作(即扩容)。
以下说下载入因子。假设载入因子越大,对空间的利用更充分。可是查找效率会减少(链表长度会越来越长)。假设载入因子太小,那么表中的数据将过于稀疏(非常多空间还没用。就開始扩容了),对空间造成严重浪费。假设我们在构造方法中不指定。则系统默认载入因子为0.75,这是一个比較理想的值。普通情况下我们是无需改动的。
另外。不管我们指定的容量为多少,构造方法都会将实际容量设为不小于指定容量的2的次方的一个数,且最大值不能超过2的30次方
4、HashMap中key和value都同意为null。
5、要重点分析下HashMap中用的最多的两个方法put和get。先从比較简单的get方法着手,源代码例如以下:
- // 获取key相应的value
- public V get(Object key) {
- if (key == null)
- return getForNullKey();
- // 获取key的hash值
- int hash = hash(key.hashCode());
- // 在“该hash值相应的链表”上查找“键值等于key”的元素
- for (Entry<K,V> e = table[indexFor(hash, table.length)];
- e != null;
- e = e.next) {
- Object k;
- /推断key是否同样
- if (e.hash == hash && ((k = e.key) == key || key.equals(k)))
- return e.value;
- }
- 没找到则返回null
- return null;
- }
- // 获取“key为null”的元素的值
-
// HashMap将“key为null”的元素存储在table[0]位置,但不一定是该链表的第一个位置!
- private V getForNullKey() {
- for (Entry<K,V> e = table[0]; e != null; e = e.next) {
- if (e.key == null)
- return e.value;
- }
- return null;
- }
假设key不为null,则先求的key的hash值,依据hash值找到在table中的索引,在该索引相应的单链表中查找是否有键值对的key与目标key相等,有就返回相应的value,没有则返回null。
put方法略微复杂些,代码例如以下:
- // 将“key-value”加入到HashMap中
- public V put(K key, V value) {
- // 若“key为null”,则将该键值对加入到table[0]中。
- if (key == null)
- return putForNullKey(value);
- // 若“key不为null”,则计算该key的哈希值,然后将其加入到该哈希值相应的链表中。
- 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;
-
// 若“该key”相应的键值对已经存在,则用新的value代替旧的value。
然后退出!
- if (e.hash == hash && ((k = e.key) == key || key.equals(k))) {
- V oldValue = e.value;
- e.value = value;
- e.recordAccess(this);
- return oldValue;
- }
- }
- // 若“该key”相应的键值对不存在,则将“key-value”加入到table中
- modCount++;
- //将key-value加入到table[i]处
- addEntry(hash, key, value, i);
- return null;
- }
- // putForNullKey()的作用是将“key为null”键值对加入到table[0]位置
- 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;
- }
- }
- // 假设没有存在key为null的键值对。则直接题阿见到table[0]处!
- modCount++;
- addEntry(0, null, value, 0);
- return null;
- }
- // 新增Entry。将“key-value”插入指定位置。bucketIndex是位置索引。
- void addEntry(int hash, K key, V value, int bucketIndex) {
- // 保存“bucketIndex”位置的值到“e”中
- Entry<K,V> e = table[bucketIndex];
- // 设置“bucketIndex”位置的元素为“新Entry”。
- // 设置“e”为“新Entry的下一个节点”
- table[bucketIndex] = new Entry<K,V>(hash, key, value, e);
- // 若HashMap的实际大小 不小于 “阈值”,则调整HashMap的大小
- if (size++ >= threshold)
- resize(2 * table.length);
- }
该方法也说明,每次put键值对的时候,总是将新的该键值对放在table[bucketIndex]处(即头结点处)。
两外注意最后两行代码,每次增加键值对时,都要推断当前已用的槽的数目是否大于等于阀值(容量*载入因子),假设大于等于,则进行扩容。将容量扩为原来容量的2倍。
6、关于扩容。上面我们看到了扩容的方法,resize方法。它的源代码例如以下:
- // 又一次调整HashMap的大小。newCapacity是调整后的单位
- void resize(int newCapacity) {
- Entry[] oldTable = table;
- int oldCapacity = oldTable.length;
- if (oldCapacity == MAXIMUM_CAPACITY) {
- threshold = Integer.MAX_VALUE;
- return;
- }
- // 新建一个HashMap,将“旧HashMap”的所有元素加入到“新HashMap”中,
- // 然后。将“新HashMap”赋值给“旧HashMap”。
- Entry[] newTable = new Entry[newCapacity];
- transfer(newTable);
- table = newTable;
- threshold = (int)(newCapacity * loadFactor);
- }
- // 将HashMap中的所有元素都加入到newTable中
- void transfer(Entry[] newTable) {
- Entry[] src = table;
- int newCapacity = newTable.length;
- for (int j = 0; j < src.length; j++) {
- Entry<K,V> e = src[j];
- if (e != null) {
- src[j] = null;
- do {
- Entry<K,V> next = e.next;
- int i = indexFor(e.hash, newCapacity);
- e.next = newTable[i];
- newTable[i] = e;
- e = next;
- } while (e != null);
- }
- }
- }
7、注意containsKey方法和containsValue方法。前者直接能够通过key的哈希值将搜索范围定位到指定索引相应的链表。而后者要对哈希数组的每一个链表进行搜索。
8、我们重点来分析下求hash值和索引值的方法,这两个方法便是HashMap设计的最为核心的部分。二者结合能保证哈希表中的元素尽可能均匀地散列。
计算哈希值的方法例如以下:
- static int hash(int h) {
- h ^= (h >>> 20) ^ (h >>> 12);
- return h ^ (h >>> 7) ^ (h >>> 4);
- }
由hash值找到相应索引的方法例如以下:
- static int indexFor(int h, int length) {
- return h & (length-1);
- }
接下来,我们分析下为什么哈希表的容量一定要是2的整数次幂。首先,length为2的整数次幂的话。h&(length-1)就相当于对length取模,这样便保证了散列的均匀。同一时候也提升了效率;其次,length为2的整数次幂的话,为偶数。这样length-1为奇数,奇数的最后一位是1,这样便保证了h&(length-1)的最后一位可能为0,也可能为1(这取决于h的值),即与后的结果可能为偶数,也可能为奇数,这样便能够保证散列的均匀性,而假设length为奇数的话,非常明显length-1为偶数,它的最后一位是0,这样h&(length-1)的最后一位肯定为0。即仅仅能为偶数,这样不论什么hash值都仅仅会被散列到数组的偶数下标位置上。这便浪费了近一半的空间。因此,length取2的整数次幂,是为了使不同hash值发生碰撞的概率较小,这样就能使元素在哈希表中均匀地散列。
HashMap源代码剖析