参见英文答案 >
Why does a HashMap rehash the hashcode supplied by the key object? 4个
以下是从简介到Java编程(Liang)的示例:
import java.util.LinkedList;
public class MyHashSet implements MySet {
// Define the default hash table size. Must be a power of 2
private static int DEFAULT_INITIAL_CAPACITY = 16;
// Define the maximum hash table size. 1 << 30 is same as 2^30
private static int MAXIMUM_CAPACITY = 1 << 30;
// Current hash table capacity. Capacity is a power of 2
private int capacity;
// Define default load factor
private static float DEFAULT_MAX_LOAD_FACTOR = 0.75f;
// Specify a load factor threshold used in the hash table
private float loadFactorThreshold;
// The number of entries in the set
private int size = 0;
// Hash table is an array with each cell that is a linked list
private LinkedList[] table;
/** Construct a set with the default capacity and load factor */
public MyHashSet() {
this(DEFAULT_INITIAL_CAPACITY, DEFAULT_MAX_LOAD_FACTOR);
}
/** Construct a set with the specified initial capacity and
* default load factor */
public MyHashSet(int initialCapacity) {
this(initialCapacity, DEFAULT_MAX_LOAD_FACTOR);
}
/** Construct a set with the specified initial capacity
* and load factor */
public MyHashSet(int initialCapacity, float loadFactorThreshold) {
if (initialCapacity > MAXIMUM_CAPACITY)
this.capacity = MAXIMUM_CAPACITY;
else
this.capacity = trimToPowerOf2(initialCapacity);
this.loadFactorThreshold = loadFactorThreshold;
table = new LinkedList[capacity];
}
/** Remove all elements from this set */
public void clear() {
size = 0;
removeElements();
}
/** Return true if the element is in the set */
public boolean contains(E e) {
int bucketIndex = hash(e.hashCode());
if (table[bucketIndex] != null) {
LinkedList bucket = table[bucketIndex];
for (E element: bucket)
if (element.equals(e))
return true;
}
return false;
}
/** Add an element to the set */
public boolean add(E e) {
if (contains(e))
return false;
if (size > capacity * loadFactorThreshold) {
if (capacity == MAXIMUM_CAPACITY)
throw new RuntimeException("Exceeding maximum capacity");
rehash();
}
int bucketIndex = hash(e.hashCode());
// Create a linked list for the bucket if it is not created
if (table[bucketIndex] == null) {
table[bucketIndex] = new LinkedList();
}
// Add e to hashTable[index]
table[bucketIndex].add(e);
size++; // Increase size
return true;
}
/** Remove the element from the set */
public boolean remove(E e) {
if (!contains(e))
return false;
int bucketIndex = hash(e.hashCode());
// Create a linked list for the bucket if it is not created
if (table[bucketIndex] != null) {
LinkedList bucket = table[bucketIndex];
for (E element: bucket)
if (e.equals(element)) {
bucket.remove(element);
break;
}
}
size--; // Decrease size
return true;
}
/** Return true if the set contains no elements */
public boolean isEmpty() {
return size == 0;
}
/** Return the number of elements in the set */
public int size() {
return size;
}
/** Return an iterator for the elements in this set */
public java.util.Iterator iterator() {
return new MyHashSetIterator(this);
}
/** Inner class for iterator */
private class MyHashSetIterator implements java.util.Iterator {
// Store the elements in a list
private java.util.ArrayList list;
private int current = 0; // Point to the current element in list
MyHashSet set;
/** Create a list from the set */
public MyHashSetIterator(MyHashSet set) {
this.set = set;
list = setToList();
}
/** Next element for traversing? */
public boolean hasNext() {
if (current < list.size())
return true;
return false;
}
/** Get the current element and move cursor to the next */
public E next() {
return list.get(current++);
}
/** Remove the current element and refresh the list */
public void remove() {
// Delete the current element from the hash set
set.remove(list.get(current));
list.remove(current); // Remove the current element from the list
}
}
/** Hash function */
private int hash(int hashCode) {
return supplementalHash(hashCode) & (capacity - 1);
}
/** Ensure the hashing is evenly distributed */
private static int supplementalHash(int h) {
h ^= (h >>> 20) ^ (h >>> 12);
return h ^ (h >>> 7) ^ (h >>> 4);
}
/** Return a power of 2 for initialCapacity */
private int trimToPowerOf2(int initialCapacity) {
int capacity = 1;
while (capacity < initialCapacity) {
capacity <<= 1;
}
return capacity;
}
/** Remove all e from each bucket */
private void removeElements() {
for (int i = 0; i < capacity; i++) {
if (table[i] != null) {
table[i].clear();
}
}
}
/** Rehash the set */
private void rehash() {
java.util.ArrayList list = setToList(); // Copy to a list
capacity <<= 1; // Double capacity
table = new LinkedList[capacity]; // Create a new hash table
size = 0;
for (E element: list) {
add(element); // Add from the old table to the new table
}
}
/** Copy elements in the hash set to an array list */
private java.util.ArrayList setToList() {
java.util.ArrayList list = new java.util.ArrayList();
for (int i = 0; i < capacity; i++) {
if (table[i] != null) {
for (E e: table[i]) {
list.add(e);
}
}
}
return list;
}
/** Return a string representation for this set */
public String toString() {
java.util.ArrayList list = setToList();
StringBuilder builder = new StringBuilder("[");
// Add the elements except the last one to the string builder
for (int i = 0; i < list.size() - 1; i++) {
builder.append(list.get(i) + ", ");
}
// Add the last element in the list to the string builder
if (list.size() == 0)
builder.append("]");
else
builder.append(list.get(list.size() - 1) + "]");
return builder.toString();
}
}
我不太关注这一部分:
/** Ensure the hashing is evenly distributed */
private static int supplementalHash(int h) {
h ^= (h >>> 20) ^ (h >>> 12);
return h ^ (h >>> 7) ^ (h >>> 4);
}
操作都很清楚,但是它们如何确保均匀分布的散列?
关于此代码的另一个问题,在这部分:
/** Add an element to the set */
public boolean add(E e) {
if (contains(e))
return false;
if (size > capacity * loadFactorThreshold) {
if (capacity == MAXIMUM_CAPACITY)
throw new RuntimeException("Exceeding maximum capacity");
rehash();
}
int bucketIndex = hash(e.hashCode());
// Create a linked list for the bucket if it is not created
if (table[bucketIndex] == null) {
table[bucketIndex] = new LinkedList();
}
// Add e to hashTable[index]
table[bucketIndex].add(e);
size++; // Increase size
return true;
}
为什么不在尺寸后放置尺寸检查和重复块?