java8 stream对list中的对象去重及获取重复数据的方法

1. 需求描述:

前端可编辑表格或者excel导入数据的时候, 对数据库中已有的数据以及新提交的数据进行重复数据判断. 即:不允许提交重复的数据.

2. Entity

@Data
public class MappingTableAccount extends BaseEntity {
    private static final long serialVersionUID = 1L;
 
    private Long id;
    private String account;
    private Date effectiveDate;
    private String description;
    private String accountType;
    private String status;
    
    @Override
    public boolean equals(Object o) {
        if (this == o) return true;
        
        if (o == null || getClass() != o.getClass()) return false;
        
        MappingTableAccount that = (MappingTableAccount) o;
        
        return new EqualsBuilder().append(account, that.account).append(effectiveDate, that.effectiveDate)
                .append(description, that.description).append(accountType, that.accountType)
                .append(status, that.status).isEquals();
    }
    
    @Override
    public int hashCode() {
        return new HashCodeBuilder(17, 37).append(account).append(effectiveDate).append(description)
                .append(accountType).append(status).toHashCode();
    }

public static void main(String[] args) {
        List<MappingTableAccount> list = new ArrayList<>();
        MappingTableAccount account1 = new MappingTableAccount();
        account1.setId(1L);
        account1.setAccount("3302");
        account1.setEffectiveDate(DateUtil.parse("2022-11-11", "yyyy-MM-dd"));
        account1.setDescription("123");
        account1.setAccountType("444");
        list.add(account1);
        
        MappingTableAccount account2 = new MappingTableAccount();
        account2.setId(2L);
        account2.setAccount("3302");
        account2.setEffectiveDate(DateUtil.parse("2022-11-11", "yyyy-MM-dd"));
        account2.setDescription("123");
        account2.setAccountType("444");
        list.add(account2);
        
        MappingTableAccount account3 = new MappingTableAccount();
        account3.setId(3L);
        account3.setAccount("3302");
        account3.setEffectiveDate(DateUtil.parse("2022-11-12", "yyyy-MM-dd"));
        account3.setDescription("123");
        account3.setAccountType("444");
        list.add(account3);
        
        MappingTableAccount account4 = new MappingTableAccount();
        account4.setId(4L);
        account4.setAccount("3302");
        account4.setEffectiveDate(DateUtil.parse("2022-11-12", "yyyy-MM-dd"));
        account4.setDescription("123");
        account4.setAccountType("444");
        list.add(account4);
        
        System.out.println(account1.equals(account2));
        
        // 第一种方法: 去重(必须重写equals和hashCode),返回去重后的集合. 无法获取重复的数据
        List<MappingTableAccount> collect = list.stream().distinct().collect(Collectors.toList());
        // 第二中方法: 分组, 返回分组后的数据. 可以获取重复的数据
        Map<String, Long> groupMap = list.stream().collect(Collectors.groupingBy(MappingTableAccount::getGroupKey, counting()));
        for(Map.Entry<String, Long> entry : groupMap.entrySet()) {
            System.out.println(entry.getKey().replaceAll(",null",""));
        }
    }
    
    /**
     * 自定义分组key的规则是拼接某几个参数
     */
    private String getGroupKey() {
        String groupKey = String.format("%s,%s,%s,%s,%s",
                this.account, this.effectiveDate, this.description, this.accountType, this.status);
        return groupKey;
    }
}

3. Service

    /**
     * 重复数据检查
     *
     * @param list
     * @return true: 没有重复记录, false: 有重复记录
     */
    default boolean duplicateRecordsCheck(List<T> list) {
        // 获取已经存储的数据
        List<T> allList = this.list(null);
        allList.addAll(list);
        
        List<T> distinctList = list.stream().distinct().collect(Collectors.toList());
        if (allList.size() == distinctList.size()) {
            return true;
        } 
        return false;
    }