集合(Set)特点:
不包含重复元素,适用于快速去重操作
典型应用:客户统计、词汇量统计
集合的实现
创建集合类型接口
public interface Set<E> {
void add(E e);
void remove(E e);
boolean contains(E e);
int getSize();
boolean isEmpty();
}
基于二分搜索树实现的集合
public class BSTSet<E extends Comparable<E>> implements Set{
private BST<E> bst;
public BSTSet(){
bst = new BST<>();
}
public int getSize(){
return bst.size();
}
public boolean isEmpty(){
return bst.isEmpty();
}
public void add(E e){
bst.add(e);
}
public boolean contains(E e){
return bst.contains(e);
}
public void remove(E e){
bst.remove(e);
}
}
基于链表实现集合
先实现一个自己的链表结构
public class LinkedList<E> {
private class Node{
public E e;
public Node next;
public Node(E e, Node next){
this.e = e;
this.next = next;
}
public Node(E e){
this(e, null);
}
public Node(){
this(null, null);
}
@Override
public String toString(){
return e.toString();
}
}
private Node dummyHead;
private int size;
public LinkedList(){
dummyHead = new Node();
size = 0;
}
// 获取链表中的元素个数
public int getSize(){
return size;
}
// 返回链表是否为空
public boolean isEmpty(){
return size == 0;
}
// 在链表的index(0-based)位置添加新的元素e
// 在链表中不是一个常用的操作,练习用:)
public void add(int index, E e){
if(index < 0 || index > size)
throw new IllegalArgumentException("Add failed. Illegal index.");
Node prev = dummyHead;
for(int i = 0 ; i < index ; i ++)
prev = prev.next;
prev.next = new Node(e, prev.next);
size ++;
}
// 在链表头添加新的元素e
public void addFirst(E e){
add(0, e);
}
// 在链表末尾添加新的元素e
public void addLast(E e){
add(size, e);
}
// 获得链表的第index(0-based)个位置的元素
// 在链表中不是一个常用的操作,练习用:)
public E get(int index){
if(index < 0 || index >= size)
throw new IllegalArgumentException("Get failed. Illegal index.");
Node cur = dummyHead.next;
for(int i = 0 ; i < index ; i ++)
cur = cur.next;
return cur.e;
}
// 获得链表的第一个元素
public E getFirst(){
return get(0);
}
// 获得链表的最后一个元素
public E getLast(){
return get(size - 1);
}
// 修改链表的第index(0-based)个位置的元素为e
// 在链表中不是一个常用的操作,练习用:)
public void set(int index, E e){
if(index < 0 || index >= size)
throw new IllegalArgumentException("Set failed. Illegal index.");
Node cur = dummyHead.next;
for(int i = 0 ; i < index ; i ++)
cur = cur.next;
cur.e = e;
}
// 查找链表中是否有元素e
public boolean contains(E e){
Node cur = dummyHead.next;
while(cur != null){
if(cur.e.equals(e))
return true;
cur = cur.next;
}
return false;
}
// 从链表中删除index(0-based)位置的元素, 返回删除的元素
// 在链表中不是一个常用的操作,练习用:)
public E remove(int index){
if(index < 0 || index >= size)
throw new IllegalArgumentException("Remove failed. Index is illegal.");
Node prev = dummyHead;
for(int i = 0 ; i < index ; i ++)
prev = prev.next;
Node retNode = prev.next;
prev.next = retNode.next;
retNode.next = null;
size --;
return retNode.e;
}
// 从链表中删除第一个元素, 返回删除的元素
public E removeFirst(){
return remove(0);
}
// 从链表中删除最后一个元素, 返回删除的元素
public E removeLast(){
return remove(size - 1);
}
// 从链表中删除元素e
public void removeElement(E e){
Node prev = dummyHead;
while(prev.next != null){
if(prev.next.e.equals(e))
break;
prev = prev.next;
}
if(prev.next != null){
Node delNode = prev.next;
prev.next = delNode.next;
delNode.next = null;
size --;
}
}
@Override
public String toString(){
StringBuilder res = new StringBuilder();
Node cur = dummyHead.next;
while(cur != null){
res.append(cur + "->");
cur = cur.next;
}
res.append("NULL");
return res.toString();
}
}
基于链表的集合实现
public class LinkedListSet<E> implements Set{
private LinkedList<E> list;
public LinkedListSet(){
list = new LinkedList<>();
}
@Override
public int getSize(){
return list.getSize();
}
@Override
public boolean isEmpty(){
return list.isEmpty();
}
@Override
public void add(E e){
if(!list.contains(e))
list.addFirst(e);
}
@Override
public boolean contains(E e){
return list.contains(e);
}
@Override
public void remove(E e){
list.removeElement(e);
}
}
链表集合与二叉树集合对比
import java.io.BufferedInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Locale;
import java.util.Scanner;
// 文件相关操作
public class FileOperation {
// 读取文件名称为filename中的内容,并将其中包含的所有词语放进words中
public static boolean readFile(String filename, ArrayList<String> words){
if (filename == null || words == null){
System.out.println("filename is null or words is null");
return false;
}
// 文件读取
Scanner scanner;
try {
File file = new File(filename);
if(file.exists()){
FileInputStream fis = new FileInputStream(file);
scanner = new Scanner(new BufferedInputStream(fis), "UTF-8");
scanner.useLocale(Locale.ENGLISH);
}
else
return false;
}
catch(IOException ioe){
System.out.println("Cannot open " + filename);
return false;
}
// 简单分词
// 这个分词方式相对简陋, 没有考虑很多文本处理中的特殊问题
// 在这里只做demo展示用
if (scanner.hasNextLine()) {
String contents = scanner.useDelimiter("\\A").next();
int start = firstCharacterIndex(contents, 0);
for (int i = start + 1; i <= contents.length(); )
if (i == contents.length() || !Character.isLetter(contents.charAt(i))) {
String word = contents.substring(start, i).toLowerCase();
words.add(word);
start = firstCharacterIndex(contents, i);
i = start + 1;
} else
i++;
}
return true;
}
// 寻找字符串s中,从start的位置开始的第一个字母字符的位置
private static int firstCharacterIndex(String s, int start){
for( int i = start ; i < s.length() ; i ++ )
if( Character.isLetter(s.charAt(i)) )
return i;
return s.length();
}
}
创建main函数开始对比
//链表
public static void main(String[] args) {
System.out.println("Pride and Prejudice");
ArrayList<String> words1 = new ArrayList<>();
if(FileOperation.readFile("pride-and-prejudice.txt", words1)) {
System.out.println("Total words: " + words1.size());
LinkedListSet<String> set1 = new LinkedListSet<>();
for (String word : words1)
set1.add(word);
System.out.println("Total different words: " + set1.getSize());
}
System.out.println();
System.out.println("A Tale of Two Cities");
ArrayList<String> words2 = new ArrayList<>();
if(FileOperation.readFile("a-tale-of-two-cities.txt", words2)){
System.out.println("Total words: " + words2.size());
LinkedListSet<String> set2 = new LinkedListSet<>();
for(String word: words2)
set2.add(word);
System.out.println("Total different words: " + set2.getSize());
}
}
//二叉树
public static void main(String[] args) {
System.out.println("Pride and Prejudice");
ArrayList<String> words1 = new ArrayList<>();
if(FileOperation.readFile("pride-and-prejudice.txt", words1)) {
System.out.println("Total words: " + words1.size());
BSTSet<String> set1 = new BSTSet<>();
for (String word : words1)
set1.add(word);
System.out.println("Total different words: " + set1.getSize());
}
System.out.println();
System.out.println("A Tale of Two Cities");
ArrayList<String> words2 = new ArrayList<>();
if(FileOperation.readFile("a-tale-of-two-cities.txt", words2)){
System.out.println("Total words: " + words2.size());
BSTSet<String> set2 = new BSTSet<>();
for(String word: words2)
set2.add(word);
System.out.println("Total different words: " + set2.getSize());
}
}
其中h为树的深度值
假设为一颗满二叉树则,
h-1层:2(h-1),h层由等比数列可得为2h-1=n个节点
可得h = log2(n+1)=O(log2n)
时间复杂度为O(logn)
经过运行对比,可以明显看出链表执行效率低于二叉树
有序集合和无序集合
有序集合具有顺序性:基于搜索树的实现
无序集合不具有顺序性:基于哈希表的实现
哈希表在随机访问效率高于搜索树,但却不具有顺序性