HashMap
10 mins
HashMap is the most widely used Map implementation in Java, providing O(1) average-time performance for basic operations.
Source Code #
Core Implementation #
HashMap uses a hash table with separate chaining (array of linked lists/trees) to store key-value pairs:
transient Node<K,V>[] table;
transient Set<Map.Entry<K,V>> entrySet;
transient int size;
int modCount;
int threshold;
final float loadFactor;
Implementation Details #
Node Structure #
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;
}
}
TreeNode Structure (for balanced trees) #
static final class TreeNode<K,V> extends LinkedHashMap.Entry<K,V> {
TreeNode<K,V> parent; // red-black tree links
TreeNode<K,V> left;
TreeNode<K,V> right;
TreeNode<K,V> prev; // needed to unlink next upon deletion
boolean red;
TreeNode(int hash, K key, V val, Node<K,V> next) {
super(hash, key, val, next);
}
// Red-black tree methods
final TreeNode<K,V> root() {
for (TreeNode<K,V> r = this, p;;) {
if ((p = r.parent) == null)
return r;
r = p;
}
}
static <K,V> void moveRootToFront(Node<K,V>[] tab, TreeNode<K,V> root) {
int n;
if (root != null && tab != null && (n = tab.length) > 0) {
int index = (n - 1) & root.hash;
TreeNode<K,V> first = (TreeNode<K,V>)tab[index];
if (root != first) {
Node<K,V> rn;
tab[index] = root;
TreeNode<K,V> rp = root.prev;
if ((rn = root.next) != null)
((TreeNode<K,V>)rn).prev = rp;
if (rp != null)
rp.next = rn;
if (first != null)
first.prev = root;
root.next = first;
root.prev = null;
}
assert checkInvariants(root);
}
}
}
Construction #
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);
}
public HashMap(int initialCapacity) {
this(initialCapacity, DEFAULT_LOAD_FACTOR);
}
public HashMap() {
this.loadFactor = DEFAULT_LOAD_FACTOR; // all other fields defaulted
}
public HashMap(Map<? extends K, ? extends V> m) {
this.loadFactor = DEFAULT_LOAD_FACTOR;
putMapEntries(m, false);
}
Table Size Calculation #
static final int tableSizeFor(int cap) {
int n = cap - 1;
n |= n >>> 1;
n |= n >>> 2;
n |= n >>> 4;
n |= n >>> 8;
n |= n >>> 16;
return (n < 0) ? 1 : (n >= MAXIMUM_CAPACITY) ? MAXIMUM_CAPACITY : n + 1;
}
This method finds the smallest power-of-two ≥ cap using bit manipulation.
Hash Function #
static final int hash(Object key) {
int h;
return (key == null) ? 0 : (h = key.hashCode()) ^ (h >>> 16);
}
The hash function:
- Returns 0 for null keys
- XORs high 16 bits with low 16 bits to improve distribution
- Reduces collisions by mixing bits
Put Operation #
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;
// Initialize table if needed
if ((tab = table) == null || (n = tab.length) == 0)
n = (tab = resize()).length;
// Calculate bucket index
if ((p = tab[i = (n - 1) & hash]) == null)
tab[i] = newNode(hash, key, value, null); // Empty bucket
else {
Node<K,V> e; K k;
// Check first node
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
e = p;
else if (p instanceof TreeNode) // Tree bucket
e = ((TreeNode<K,V>)p).putTreeVal(this, tab, hash, key, value);
else { // Linked list bucket
for (int binCount = 0; ; ++binCount) {
if ((e = p.next) == null) {
p.next = newNode(hash, key, value, null);
if (binCount >= TREEIFY_THRESHOLD - 1) // -1 for first
treeifyBin(tab, hash);
break;
}
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
break;
p = e;
}
}
// Update existing node
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;
}
Treeify Bin #
final void treeifyBin(Node<K,V>[] tab, int hash) {
int n, index; Node<K,V> e;
// Minimum capacity check - don't treeify if table is too small
if (tab == null || (n = tab.length) < MIN_TREEIFY_CAPACITY)
resize();
else if ((e = tab[index = (n - 1) & hash]) != null) {
TreeNode<K,V> hd = null, tl = null;
// Convert linked list to balanced tree
do {
TreeNode<K,V> p = replacementTreeNode(e, null);
if (tl == null)
hd = p;
else {
p.prev = tl;
tl.next = p;
}
tl = p;
} while ((e = e.next) != null);
if ((tab[index] = hd) != null)
hd.treeify(tab); // Build tree structure
}
}
Resize Operation #
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; // Single node
else if (e instanceof TreeNode)
((TreeNode<K,V>)e).split(this, newTab, j, oldCap); // Tree
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;
}
Get Operation #
public V get(Object key) {
Node<K,V> e;
return (e = getNode(hash(key), key)) == null ? null : e.value;
}
final Node<K,V> getNode(int hash, Object key) {
Node<K,V>[] tab; Node<K,V> first, e; int n; K k;
if ((tab = table) != null && (n = tab.length) > 0 &&
(first = tab[(n - 1) & hash]) != null) {
if (first.hash == hash && // always check first node
((k = first.key) == key || (key != null && key.equals(k))))
return first;
if ((e = first.next) != null) {
if (first instanceof TreeNode)
return ((TreeNode<K,V>)first).getTreeNode(hash, key);
do { // Traverse linked list
if (e.hash == hash &&
((k = e.key) == key || (key != null && key.equals(k))))
return e;
} while ((e = e.next) != null);
}
}
return null;
}
Remove Operation #
public V remove(Object key) {
Node<K,V> e;
return (e = removeNode(hash(key), key, null, false, true)) == null ?
null : e.value;
}
final Node<K,V> removeNode(int hash, Object key, Object value,
boolean matchValue, boolean movable) {
Node<K,V>[] tab; Node<K,V> p; int n, index;
if ((tab = table) != null && (n = tab.length) > 0 &&
(p = tab[index = (n - 1) & hash]) != null) {
Node<K,V> node = null, e; K k; V v;
if (p.hash == hash &&
((k = p.key) == key || (key != null && key.equals(k))))
node = p;
else if ((e = p.next) != null) {
if (p instanceof TreeNode)
node = ((TreeNode<K,V>)p).find(hash, key, null);
else {
do {
if (e.hash == hash &&
((k = e.key) == key ||
(key != null && key.equals(k)))) {
node = e;
break;
}
p = e;
} while ((e = e.next) != null);
}
}
if (node != null && (!matchValue || (v = node.value) == value ||
(value != null && value.equals(v)))) {
if (node instanceof TreeNode)
((TreeNode<K,V>)node).removeTreeNode(this, tab, movable);
else if (node == p)
tab[index] = node.next;
else
p.next = node.next;
++modCount;
--size;
afterNodeRemoval(node);
return node;
}
}
return null;
}
Iteration Support #
public Set<Map.Entry<K,V>> entrySet() {
Set<Map.Entry<K,V>> es;
return (es = entrySet) == null ? (entrySet = new EntrySet()) : es;
}
final class EntrySet extends AbstractSet<Map.Entry<K,V>> {
public final int size() { return size; }
public final void clear() { HashMap.this.clear(); }
public final Iterator<Map.Entry<K,V>> iterator() {
return new EntryIterator();
}
public final boolean contains(Object o) {
if (!(o instanceof Map.Entry))
return false;
Map.Entry<?,?> e = (Map.Entry<?,?>)o;
Object key = e.getKey();
Node<K,V> candidate = getNode(hash(key), key);
return candidate != null && candidate.equals(e);
}
public final boolean remove(Object o) {
if (o instanceof Map.Entry) {
Map.Entry<?,?> e = (Map.Entry<?,?>)o;
Object key = e.getKey();
Object value = e.getValue();
return removeNode(hash(key), key, value, true, true) != null;
}
return false;
}
}
final class EntryIterator extends HashIterator implements Iterator<Map.Entry<K,V>> {
public final Map.Entry<K,V> next() { return nextNode(); }
}
abstract class HashIterator {
Node<K,V> next; // next entry to return
Node<K,V> current; // current entry
int expectedModCount; // for fast-fail
int index; // current slot
HashIterator() {
expectedModCount = modCount;
Node<K,V>[] t = table;
current = next = null;
index = 0;
if (t != null && size > 0) { // advance to first entry
do {} while (index < t.length && (next = t[index++]) == null);
}
}
public final boolean hasNext() {
return next != null;
}
final Node<K,V> nextNode() {
Node<K,V>[] t;
Node<K,V> e = next;
if (modCount != expectedModCount)
throw new ConcurrentModificationException();
if (e == null)
throw new NoSuchElementException();
if ((next = (current = e).next) == null && (t = table) != null) {
do {} while (index < t.length && (next = t[index++]) == null);
}
return e;
}
public final void remove() {
Node<K,V> p = current;
if (p == null)
throw new IllegalStateException();
if (modCount != expectedModCount)
throw new ConcurrentModificationException();
current = null;
K key = p.key;
removeNode(hash(key), key, null, false, false);
expectedModCount = modCount;
}
}
Performance Characteristics #
Time Complexity:
get(Object key): O(1) average, O(n) worst case (all keys collide)put(K key, V value): O(1) average, O(n) worst caseremove(Object key): O(1) average, O(n) worst casecontainsKey(Object key): O(1) average, O(n) worst case
Space Complexity: O(n) where n is the number of key-value pairs
Load Factor: Default 0.75 (balance between time and space costs)
Tree Threshold: Converts to tree when bucket size ≥ 8 (TREEIFY_THRESHOLD)
Untree Threshold: Converts back to linked list when bucket size ≤ 6 (UNTREEIFY_THRESHOLD)
Key Constants #
static final int DEFAULT_INITIAL_CAPACITY = 1 << 4; // 16
static final int MAXIMUM_CAPACITY = 1 << 30; // 1073741824
static final float DEFAULT_LOAD_FACTOR = 0.75f;
static final int TREEIFY_THRESHOLD = 8;
static final int UNTREEIFY_THRESHOLD = 6;
static final int MIN_TREEIFY_CAPACITY = 64;
Best Practices #
- Pre-size when possible: Use constructor with initial capacity to avoid early resizing
- Choose appropriate load factor: Higher values save space but increase lookup time
- Use immutable keys: Keys should not change their hashCode() after insertion
- Consider alternatives: For sorted data, use
TreeMap; for concurrent access, useConcurrentHashMap - Null handling: HashMap allows one null key and multiple null values
Common Pitfalls #
- ConcurrentModificationException: Modifying map while iterating
- Memory leaks: Using mutable objects as keys that change their hashCode
- Performance degradation: Poor hashCode() implementation causing many collisions
- Initial capacity too small: Causes frequent resizing (expensive operation)
- Initial capacity too large: Wastes memory