Java通过Lambda表达式根据指定字段去除重复数据（集合去重）

曾经终败给现在 2023-10-11 20:03 69阅读 0赞

这里博主给大家封装好了一个工具类，里面有两个方法。

*  方法一：可以根据指定字段去除重复数据。
 *  方法二：可以获取到重复的数据。

**大家在使用过程中直接拷贝下方代码在要去重的类中调用即可。**

package com.jzmy.specialist.entity.util;
    import java.util.Map;
    import java.util.concurrent.ConcurrentHashMap;
    import java.util.function.Function;
    import java.util.function.Predicate;
    
    /**
     * 操作去重工具类
     * @author mengzhichao
     * @create 2022-11-02-15:15
     */
    public class DeduplicationUtil {
        
        /**
         * 自定义函数去重（采用 Predicate函数式判断，采用 Function获取比较key）
         * 内部维护一个 ConcurrentHashMap，并采用 putIfAbsent特性实现
         *
         * @param keyExtractor
         * @param <T>
         * @return
         */
        public static <T> Predicate<T> distinctByKey(Function<? super T, ?> keyExtractor) {
        
            Map<Object,Boolean> seen = new ConcurrentHashMap<>();
            return t -> seen.putIfAbsent(keyExtractor.apply(t), Boolean.TRUE) == null;
        }
    
        /**
         * 只获取重复的数据
         *
         * @param keyExtractor
         * @param <T>
         * @return
         */
        public static <T> Predicate<T> distinctNotByKey(Function<? super T, ?> keyExtractor) {
        
            Map<Object,Boolean> seen = new ConcurrentHashMap<>();
            return t -> seen.putIfAbsent(keyExtractor.apply(t), Boolean.TRUE) != null;
        }
    }

导入这个工具类后怎么使用呢？我们接着往下看。

### 方法一根据指定字段去重 ###

package com.jzmy.specialist.entity.util;
    
    import java.util.ArrayList;
    import java.util.List;
    import java.util.stream.Collectors;
    
    /**
     * @author mengzhichao
     * @create 2022-12-02-10:46
     */
    public class Test {
        
        public static class Student{
        
    
            private String id;
    
            private String name;
    
            public String getId() {
        
                return id;
            }
    
            public void setId(String id) {
        
                this.id = id;
            }
    
            public String getName() {
        
                return name;
            }
    
            public void setName(String name) {
        
                this.name = name;
            }
        }
    
        public static void main(String[] args) {
        
    
            List<Student> list =new ArrayList<>();
    
            Student student =new Student();
            student.setId("1");
            student.setName("张三");
            list.add(student);
    
            Student student2 =new Student();
            student2.setId("1");
            student2.setName("张三");
            list.add(student2);
    
            Student student3 =new Student();
            student3.setId("1");
            student3.setName("李四");
            list.add(student3);
    
            Student student4 =new Student();
            student4.setId("2");
            student4.setName("王五");
            list.add(student4);
    
            System.out.println("未去重前list有几条数据："+list.size());
    
    
            List<Student> rstList = list.stream().filter(DeduplicationUtil.distinctByKey(Student::getId)).collect(Collectors.toList());
    
            System.out.println("未去重前list有几条数据："+rstList.size());
        }
    }

List rstList = list.stream().filter(DeduplicationUtil.distinctByKey(Student::getId)).collect(Collectors.toList());

*  这段代码的意思是通过stream的filter方法进行过滤，过滤Id不相同的数据并通过collect方法收集为一个新的集合。

代码运行结果

![在这里插入图片描述][3990be33ad6347fcb3c35d331416e208.png]

### 方法二获取重复数据 ###

package com.jzmy.specialist.entity.util;
    
    import java.util.ArrayList;
    import java.util.List;
    import java.util.stream.Collectors;
    
    /**
     * @author mengzhichao
     * @create 2022-12-02-10:46
     */
    public class Test {
        
        public static class Student{
        
    
            private String id;
    
            private String name;
    
            public String getId() {
        
                return id;
            }
    
            public void setId(String id) {
        
                this.id = id;
            }
    
            public String getName() {
        
                return name;
            }
    
            public void setName(String name) {
        
                this.name = name;
            }
        }
    
        public static void main(String[] args) {
        
    
            List<Student> list =new ArrayList<>();
    
            Student student =new Student();
            student.setId("1");
            student.setName("张三");
            list.add(student);
    
            Student student2 =new Student();
            student2.setId("1");
            student2.setName("张三");
            list.add(student2);
    
            Student student3 =new Student();
            student3.setId("1");
            student3.setName("李四");
            list.add(student3);
    
            Student student4 =new Student();
            student4.setId("2");
            student4.setName("王五");
            list.add(student4);
    
            System.out.println("集合中的全部数据");
            for (int i=0;i<list.size();i++){
        
                System.out.println(list.get(i).getId());
                System.out.println(list.get(i).getName());
            }
    
            List<Student> rstList = list.stream().filter(DeduplicationUtil.distinctNotByKey(Student::getId)).collect(Collectors.toList());
    
            System.out.println("集合中的重复数据");
            for (int i=0;i<rstList.size();i++){
        
                System.out.println(rstList.get(i).getId());
                System.out.println(rstList.get(i).getName());
            }
        }
    }

List rstList = list.stream().filter(DeduplicationUtil.distinctNotByKey(Student::getId)).collect(Collectors.toList());

*  这个和上面那个方法原理一样的只是换了一个调用方法而已。

代码运行结果

![在这里插入图片描述][ec424a1599d942fabc1d097acad8d157.png]

[3990be33ad6347fcb3c35d331416e208.png]: https://img-blog.csdnimg.cn/3990be33ad6347fcb3c35d331416e208.png
[ec424a1599d942fabc1d097acad8d157.png]: https://img-blog.csdnimg.cn/ec424a1599d942fabc1d097acad8d157.png