使用Java8進行分組(多個欄位的組合分組)

2022-07-18 14:04:06

java8分組傳統寫法（單個欄位分組）

場景：根據城市進行分組

使用的是方法參照：User::getCity 來完成分組

import java.time.LocalDateTime;
import java.time.format.DateTimeFormatter;
import java.util.Arrays;
import java.util.List;
import java.util.Map;
import java.util.stream.Collectors;

public class Demo2 {
    public static void main(String[] args) {
        DateTimeFormatter df = DateTimeFormatter.ofPattern("yyyy-MM-dd HH:mm:ss");
        // data list
        List<User> userList = Arrays.asList(
                User.builder().id(123456).name("Zhang, San").city("ShangHai").sex("man").birthDay(LocalDateTime.parse("2022-07-01 12:00:00", df)).build(),
                User.builder().id(777777).name("Zhang, San").city("ShangHai").sex("woman").birthDay(LocalDateTime.parse("2022-07-01 12:00:00", df)).build(),
                User.builder().id(888888).name("Li, Si").city("ShangHai").sex("man").birthDay(LocalDateTime.parse("2022-07-01 12:00:00", df)).build(),
                User.builder().id(999999).name("Zhan, San").city("HangZhou").sex("woman").birthDay(LocalDateTime.parse("2022-07-01 12:00:00", df)).build(),
                User.builder().id(555555).name("Li, Si").city("NaJin").sex("man").birthDay(LocalDateTime.parse("2022-07-01 12:00:00", df)).build()
        );
        Map<String, List<User>> groupMap = userList.stream()
        	.collect(Collectors.groupingBy(User::getCity));
        groupMap.forEach((k, v) -> {
            System.out.println(k);
            System.out.println(v);
        });
    }
}

java8分組傳統寫法（多個欄位分組）

① 場景：根據 城市,性別進行分組

一般的寫法會是下面的這種寫法，通過lambda表示式將key的生成邏輯傳入進去：u -> u.getCity() + "|" + u.getSex() 來實現分組的效果。

import java.time.LocalDateTime;
import java.time.format.DateTimeFormatter;
import java.util.Arrays;
import java.util.List;
import java.util.Map;
import java.util.stream.Collectors;

public class Demo2 {
    public static void main(String[] args) {
        DateTimeFormatter df = DateTimeFormatter.ofPattern("yyyy-MM-dd HH:mm:ss");
        // data list
        List<User> userList = Arrays.asList(
                User.builder().id(123456).name("Zhang, San").city("ShangHai").sex("man").birthDay(LocalDateTime.parse("2022-07-01 12:00:00", df)).build(),
                User.builder().id(777777).name("Zhang, San").city("ShangHai").sex("woman").birthDay(LocalDateTime.parse("2022-07-01 12:00:00", df)).build(),
                User.builder().id(888888).name("Li, Si").city("ShangHai").sex("man").birthDay(LocalDateTime.parse("2022-07-01 12:00:00", df)).build(),
                User.builder().id(999999).name("Zhan, San").city("HangZhou").sex("woman").birthDay(LocalDateTime.parse("2022-07-01 12:00:00", df)).build(),
                User.builder().id(555555).name("Li, Si").city("NaJin").sex("man").birthDay(LocalDateTime.parse("2022-07-01 12:00:00", df)).build()
        );
        Map<String, List<User>> groupMap = userList.stream()
        	.collect(Collectors.groupingBy(u -> u.getCity() + "|" + u.getSex()));
        groupMap.forEach((k, v) -> {
            System.out.println(k);
            System.out.println(v);
        });
    }
}

分析：多個分組條件與單個分組條件兩種寫法

單個條件的分組用的比較多，userList.stream().collect(Collectors.groupingBy(User::getCity));
這種方法參照的方式看起來很清爽。
在我們遇到多個欄位的分組的時候，我並不太想使用前面那種傳統的寫法①。

我在想，既然單個欄位的分組寫法是：

userList.stream().collect(Collectors.groupingBy(User::getCity));

那麼多個欄位的寫法可否是下面這種( 類推 )，傳入多個方法參照！

userList.stream().collect(Collectors.groupingBy(User::getCity,User::getSex));

很可惜 jdk 類庫中Collectors 沒有提供這種寫法

多個欄位的優雅寫法

因為jdk沒有提供這種寫法，於是自己就想寫了一個Util來幫助我們使用多個方法參照的方式完成組合分組

MyBeanUtil groupingBy(userList, User::getSex, User::getCity);

Demo：

import java.time.LocalDateTime;
import java.time.format.DateTimeFormatter;
import java.util.*;
import java.util.function.Function;
import java.util.stream.Collectors;

public class MyBeanUtil {

    public static void main(String[] args) {
        DateTimeFormatter df = DateTimeFormatter.ofPattern("yyyy-MM-dd HH:mm:ss");
        // data list
        List<User> userList = Arrays.asList(
                User.builder().id(123456).name("Zhang, San").city("ShangHai").sex("man").birthDay(LocalDateTime.parse("2022-07-01 12:00:00", df)).build(),
                User.builder().id(777777).name("Zhang, San").city("ShangHai").sex("woman").birthDay(LocalDateTime.parse("2022-07-01 12:00:00", df)).build(),
                User.builder().id(888888).name("Li, Si").city("ShangHai").sex("man").birthDay(LocalDateTime.parse("2022-07-01 12:00:00", df)).build(),
                User.builder().id(999999).name("Zhan, San").city("HangZhou").sex("woman").birthDay(LocalDateTime.parse("2022-07-01 12:00:00", df)).build(),
                User.builder().id(555555).name("Li, Si").city("NaJin").sex("man").birthDay(LocalDateTime.parse("2022-07-01 12:00:00", df)).build()
        );
        // 進行分組，根據名字和城市分組
        Map<String, List<User>> groupMap = groupingBy(userList, User::getSex, User::getCity);
        //列印分組結果
        groupMap.forEach((k, v) -> {
            System.out.println(k);
            System.out.println(v);
        });
    }
    /**
     * 將資料分組，根據方法參照（bean的get方法）
     *
     * @param list      為分組的資料
     * @param functions get方法陣列
     */
    @SafeVarargs
    public static <T, R> Map<String, List<T>> groupingBy(List<T> list, Function<T, R>... functions) {
        return list.stream().collect(Collectors.groupingBy(t -> groupingBy(t, functions)));
    }

    /**
     * 分組工具根據函數式介面使用分組，將資料根據分組結果進行拆分
     */
    @SafeVarargs
    public static <T, R> String groupingBy(T t, Function<T, R>... functions) {
        if (functions == null || functions.length == 0) {
            throw new NullPointerException("functions陣列不可以為空");
        } else if (functions.length == 1) {
            return functions[0].apply(t).toString();
        } else {
            return Arrays.stream(functions).map(fun -> fun.apply(t).toString()).reduce((str1, str2) -> str1 + "|" + str2).get();
        }
    }
}

再度優化

依然不是很滿足這種寫法，因為這種寫法需要藉助 Util 類，不夠接地氣！
我更希望是下面這種接地氣的寫法：能夠完全整合在jdk類庫中

userList.stream().collect(Collectors.groupingBy(User::getCity,User::getSex));

為了達到上述的效果，那麼顯然我們是需要修改jdk原始碼的；
於是我就將java.util.stream.Collectors原始碼完整copy出來，然後加入下面3個方法

    public static <T, K> Collector<T, ?, HashMap<K, List<T>>>
    groupingBy(Function<? super T, ? extends K>... classifier) {
        return groupingBy("|", classifier);
    }
    
    public static <T, K> Collector<T, ?, HashMap<K, List<T>>>
    groupingBy(String split, Function<? super T, ? extends K>... classifier) {
        return groupingBy(split, classifier, HashMap::new, toList());
    }
    
    public static <T, K, D, A, M extends Map<? super K, D>>
    Collector<T, ?, M> groupingBy(String split,
                                  Function<? super T, ? extends K>[] classifierArr,
                                  Supplier<M> mapFactory,
                                  Collector<? super T, A, D> downstream) {
        Supplier<A> downstreamSupplier = downstream.supplier();
        BiConsumer<A, ? super T> downstreamAccumulator = downstream.accumulator();
        BiConsumer<Map<K, A>, T> accumulator = (m, t) -> {
            String key = Arrays.stream(classifierArr).map(classifier -> Objects.requireNonNull(classifier.apply(t))).map(String::valueOf).reduce((s1, s2) -> s1 + split + s2).get();
            A container = m.computeIfAbsent((K) key, k -> downstreamSupplier.get());
            downstreamAccumulator.accept(container, t);
        };
        BinaryOperator<Map<K, A>> merger = Collectors.<K, A, Map<K, A>>mapMerger(downstream.combiner());
        @SuppressWarnings("unchecked")
        Supplier<Map<K, A>> mangledFactory = (Supplier<Map<K, A>>) mapFactory;

        if (downstream.characteristics().contains(Collector.Characteristics.IDENTITY_FINISH)) {
            return new CollectorImpl<>(mangledFactory, accumulator, merger, CH_ID);
        } else {
            @SuppressWarnings("unchecked")
            Function<A, A> downstreamFinisher = (Function<A, A>) downstream.finisher();
            Function<Map<K, A>, M> finisher = intermediate -> {
                intermediate.replaceAll((k, v) -> downstreamFinisher.apply(v));
                @SuppressWarnings("unchecked")
                M castResult = (M) intermediate;
                return castResult;
            };
            return new CollectorImpl<>(mangledFactory, accumulator, merger, finisher, CH_NOID);
        }
    }

就達到了我們預期的效果，為了方便大家也一起體驗一下，我已經將demo完整的放到了github上

原始碼地址：https://github.com/1015770492/CollectorsDemo

下載好原始碼後，找到下面這個類

Demo：

import java.io.Serializable;
import java.time.LocalDateTime;
import java.time.format.DateTimeFormatter;
import java.util.*;

public class MultiGroupByDemo {


    public static void main(String[] args) {
        DateTimeFormatter df = DateTimeFormatter.ofPattern("yyyy-MM-dd HH:mm:ss");
        // data list
        List<User> userList = Arrays.asList(
                User.builder().id(123456).name("Zhang, San").city("ShangHai").sex("man").birthDay(LocalDateTime.parse("2022-07-01 12:00:00", df)).build(),
                User.builder().id(777777).name("Zhang, San").city("ShangHai").sex("woman").birthDay(LocalDateTime.parse("2022-07-01 12:00:00", df)).build(),
                User.builder().id(888888).name("Li, Si").city("ShangHai").sex("man").birthDay(LocalDateTime.parse("2022-07-01 12:00:00", df)).build(),
                User.builder().id(999999).name("Zhan, San").city("HangZhou").sex("woman").birthDay(LocalDateTime.parse("2022-07-01 12:00:00", df)).build(),
                User.builder().id(555555).name("Li, Si").city("NaJin").sex("man").birthDay(LocalDateTime.parse("2022-07-01 12:00:00", df)).build()
        );
        /*
         * maybe we can
         */

        // 1.Use the default vertical separator
        System.out.println("Use the default vertical separator:");
        HashMap<String, List<User>> defaultSpilt = userList.stream().collect(Collectors.groupingBy(User::getName, User::getCity));
        printMap(defaultSpilt);
        System.out.println();

        // 2.Use custom delimiters
        System.out.println("Use custom delimiters:");
        userList.stream().collect(Collectors.groupingBy("--", User::getName, User::getCity, User::getId));
        HashMap<? extends Serializable, List<User>> collect = userList.stream().collect(Collectors.groupingBy("--", User::getName, User::getCity, User::getId));
        printMap(collect);
        System.out.println();

        // 3.Use custom delimiters
        System.out.println("Use custom delimiters:");
        userList.stream().collect(Collectors.groupingBy("--", User::getName, User::getCity, User::getId));
        HashMap<? extends Serializable, List<User>> collect2 = userList.stream().collect(Collectors.groupingBy(User::getName, User::getCity, User::getBirthDay));
        printMap(collect2);


    }

    public static <T> void printMap(Map<? extends Serializable, List<T>> map){
        map.forEach((k, v) -> {
            System.out.println(k);
            System.out.println(v);
        });
    }

}