基於哈希表的 Map 接口的實現。此實現提供全部可選的映射操做,並容許使用 null 值和 null 鍵。(除了非同步和容許使用 null 以外,HashMap 類與 Hashtable 大體相同。)此類不保證映射的順序,特別是它不保證該順序恆久不變。java
此實現假定哈希函數將元素適當地分佈在各桶之間,可爲基本操做(get 和 put)提供穩定的性能。迭代 collection 視圖所需的時間與 HashMap 實例的「容量」(桶的數量)及其大小(鍵-值映射關係數)成比例。因此,若是迭代性能很重要,則不要將初始容量設置得過高(或將加載因子設置得過低)。算法
HashMap的實例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
只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長以前能夠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當前容量的乘積時,則要對該哈希表進行 rehash 操做(即重建內部數據結構),從而哈希表將具備大約兩倍的桶數。數組
一般,默認加載因子 (0.75)
在時間和空間成本上尋求一種折衷。加載因子太高雖然減小了空間開銷,但同時也增長了查詢成本(在大多數 HashMap 類的操做中,包括 get 和 put 操做,都反映了這一點)。在設置初始容量時應該考慮到映射中所需的條目數及其加載因子,以便最大限度地減小 rehash 操做次數。若是初始容量大於最大條目數除以加載因子,則不會發生 rehash 操做。安全
若是不少映射關係要存儲在 HashMap 實例中,則相對於按需執行自動的 rehash 操做以增大表的容量來講,使用足夠大的初始容量建立它將使得映射關係能更有效地存儲。數據結構
##HashMap的數據結構## HashMap用了一個名字爲table的Entry類型數組;數組中的每一項又是一個Entry鏈表。 app
// 默認的初始化大小 static final int DEFAULT_INITIAL_CAPACITY = 16; // 最大的容量 static final int MAXIMUM_CAPACITY = 1 << 30; // 負載因子 static final float DEFAULT_LOAD_FACTOR = 0.75f; // 儲存key-value鍵值對的數組,一個鍵值對對象映射一個Entry對象 transient Entry[] table; // 鍵值對的數目 transient int size; // 調整HashMap大小門檻,該變量包含了HashMap能容納的key-value對的極限,它的值等於HashMap的容量乘以負載因子 int threshold; // 加載因子 final float loadFactor; // HashMap結構修改次數,防止在遍歷時,有其餘的線程在進行修改 transient volatile int modCount; 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; // 使得capacity 的大小爲2的冪,至於爲何,請看下面 while (capacity < initialCapacity) capacity <<= 1; this.loadFactor = loadFactor; threshold = (int) (capacity * loadFactor); table = new Entry[capacity]; init(); }
下面是用於包裝key-value映射關係的Entry,它是HashMap的靜態內部類:函數
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(); } /** * 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) { } }
##HashMap的put和get及remove方法##性能
// 根據key獲取value public V get(Object key) { if (key == null) return getForNullKey(); //根據key的hashCode值計算它的hash碼 int hash = hash(key.hashCode()); //直接取出table數組中指定索引處的值 for (Entry<K, V> e = table[indexFor(hash, table.length)]; e != null; //搜索該Entry鏈的下一個Entry e = e.next) { Object k; //若是該Entry的key與被搜索key相同 if (e.hash == hash && ((k = e.key) == key || key.equals(k))) return e.value; } return null; } private V getForNullKey() { //key爲null,hash碼爲0,也就是說key爲null的Entry位於table[0]的Entry鏈上 for (Entry<K, V> e = table[0]; e != null; e = e.next) { if (e.key == null) return e.value; } return null; } public V put(K key, V value) { if (key == null) return putForNullKey(value); //根據key的hashCode值計算它的hash碼 int hash = hash(key.hashCode()); //搜索指定hash值對應table中的索引值 int i = indexFor(hash, table.length); for (Entry<K, V> e = table[i]; e != null; e = e.next) { Object k; //若是找到指定key與須要放入的key相等(hash值相同,經過equals比較返回true) if (e.hash == hash && ((k = e.key) == key || key.equals(k))) { V oldValue = e.value; //新的值覆蓋舊值 e.value = value; //這個方法是個空方法,多是表示個標記,字面意思是表示記錄訪問 e.recordAccess(this); //返回舊值 return oldValue; } } modCount++; //若是i處索引處的Entry爲null,表示此處尚未Entry //將key、value添加到i索引處 addEntry(hash, key, value, i); return null; } //key=null的鍵值對,默認存放table[0]的Entry鏈 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; } 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); } //根據鍵值移除key-value映射對象 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; //空方法,表示移除記錄 e.recordRemoval(this); return e; } prev = e; e = next; } return e; }
##HashMap的hash算法和size大小調整##this
static int hash(int h) {//這裏不是很懂,得向他人請教 // 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); } /** * Returns index for hash code h. */ // 根據hash碼求的數組小標並返回,當length爲2的冪時,h & (length-1)等價於h%(length-1),這裏也就是爲何前面說table的長度必須是2的冪 static int indexFor(int h, int length) { return h & (length - 1); } // 調整大小 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]; transfer(newTable); table = newTable; threshold = (int) (newCapacity * loadFactor); } /** * Transfers all entries from current table to newTable. */ 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 { //注意這裏哈,HashMap不保證順序恆久不變 //在這裏能夠找到答案 Entry<K, V> next = e.next; int i = indexFor(e.hash, newCapacity); e.next = newTable[i]; newTable[i] = e; e = next; } while (e != null); } } }
##HashMap與Set的關係## Set表明一種集合元素無序、集合元素不可重複的集合。若是隻考察HashMap中的key,不難發現集合中的key有一個特徵:全部的key不能重複,key之間無序。具有了Set的特徵,全部的key集合起來組成一個Set集合。同理全部的Entry集合起來,也是一個Set集合。而value是能夠重複的,不能組成一個Set集合,在HashMap源代碼中提供了values()方法把value集合起來組成Collection集合。線程
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(); } } 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; //把全部的key集合成Set集合 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(); } } //把全部的values集合成Collection集合 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(); } } //把全部的Entry對象集合成Set集合 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(); } }
##Fail-Fast策略(速錯)## HashMap不是線程安全的,所以若是在使用迭代器的過程當中有其餘線程修改了map,那麼將拋ConcurrentModificationException,這就是所謂fail-fast策略(速錯),這一策略在源碼中的實現是經過modCount域,modCount顧名思義就是修改次數,對HashMap內容的修改都將增長這個值,那麼在迭代器初始化過程當中會將這個值賦給迭代器的expectedModCount。在迭代過程當中,判斷modCount跟expectedModCount是否相等,若是不相等就表示已經有其餘線程修改了。
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; } }