java8 groupby 對多個字段進行去重, 統計

package com.icil.elsa.test.utils; import java.util.ArrayList; import java.util.Comparator; import java.util.List; import java.util.Map; import java.util.TreeSet; import java.util.stream.Collectors; import org.junit.Test; import lombok.ToString; import lombok.Data; /** * 用 java8 對 list 按照多個字段進行去重 id , message ,orderNO 去重 * 對對象 MilestonesValidTO 按照 field * 參考1:https://blog.csdn.net/robotfive/article/details/89200294 * 參考2:https://blog.csdn.net/weixin_39643007/article/details/90511098 * @throws Exception */
public class GroupBYTest { @Data @ToString public class MilestonesValidTO { private String id; private String message; private String orderNO; private String courierBillNo; private String status; public MilestonesValidTO(String id, String message, String orderNO, String courierBillNo) { super(); this.id = id; this.message = message; this.orderNO = orderNO; this.courierBillNo = courierBillNo; } } /**
　　　　　#####若是 id + message + orderNo 都同樣， 就認爲是一條數據#######

 * 用 java8 對 list 按照多個字段進行去重 id , message ,orderNO 去重 * 對對象 MilestonesValidTO 按照 field * 若是僅僅是去重,推薦使用方式1 * @throws Exception */
     /*################# 方式1: 直接重寫 comparater 方法 ####################*/ @Test public void testGroupByMutilFiled1() throws Exception { ArrayList<MilestonesValidTO> list = new ArrayList<MilestonesValidTO>(); list.add(new MilestonesValidTO("1","A","sea","2341")); list.add(new MilestonesValidTO("1","A","sea","2341")); list.add(new MilestonesValidTO("3","B","sea","2341")); list.add(new MilestonesValidTO("4","A","sea","2341")); list.add(new MilestonesValidTO("5","C","sea","2341")); List<MilestonesValidTO> lst = list.parallelStream().collect(Collectors.collectingAndThen(Collectors.toCollection( () -> new TreeSet<>(Comparator.comparing(o -> o.getId() + "#" + o.getMessage() + "#" + o.getOrderNO()))), ArrayList<MilestonesValidTO>::new)); lst.forEach(m-> System.err.println(m.toString())); } /** * 用 java8 對 list 按照多個字段進行去重 id , message ,orderNO 去重 * 對對象 MilestonesValidTO 按照 field * 方式2:用於收集,統計,比較合適 * @throws Exception */
     /*################# 方式2: Collectors.groupingBy(內嵌groupBy) ####################*/ @Test public void testGroupByMutilFiled2() throws Exception { ArrayList<MilestonesValidTO> list = new ArrayList<MilestonesValidTO>(); list.add(new MilestonesValidTO("1","A","sea","2341")); list.add(new MilestonesValidTO("1","A","sea","2341")); list.add(new MilestonesValidTO("3","B","sea","2341")); list.add(new MilestonesValidTO("4","A","sea","2341")); list.add(new MilestonesValidTO("5","C","sea","2341")); // Map<String, Map<String, Double>> sumCase = statisticalAnalyses.stream() // .collect(Collectors.groupingBy( // StatisticalAnalysis::getCreateTime, // Collectors.groupingBy(StatisticalAnalysis::getHandlingDepartmentName, Collectors.summingDouble(StatisticalAnalysis::getSimplePenaltyAmount))));
 Map<String, Map<String, List<MilestonesValidTO>>> collect = list.parallelStream() .collect(Collectors.groupingBy(MilestonesValidTO::getId,Collectors.groupingBy(MilestonesValidTO::getMessage))); collect.forEach((k,v)->{System.err.println("K->"+k+" V-->"+v);}); } }

 

經常使用：

//提取Bean 中的個別字段
List<String> hbookingNo = houseLinkList.stream().map(MasterLinkDO::getBookingNo).collect(Collectors.toList()); //把一個大的list切割
List<List<String>> ListbookingNoList = Lists.partition(bookingNoList, 100); //過濾去重

List<MilestoneInfo> successAndDistincList = worktbMileAllList.stream().filter(m->m.getSuccess()==true).collect(Collectors.collectingAndThen(Collectors.toCollection(
// () -> new TreeSet<>(Comparator.comparing(o -> o.getCourierBillNo()))),
() -> new TreeSet<>(Comparator.comparing(o -> o.getStatus() + "#" + o.getBookingNo() + "#" + o.getCourierBillNo()))),
ArrayList<MilestoneInfo>::new));

 //分組 Map<String, Map<String, List<MilestoneInfo>>> status_bookingNoAndDetailMap_map = worktbMileSuccessAndDistincList.stream() .collect(Collectors.groupingBy(MilestoneInfo::getStatus,Collectors.groupingBy(MilestoneInfo::getBookingNo)));