java分组topN

import java.util.*;

public class TopN2 {
    public static void main(String[] args) {
        List<String> list = new ArrayList<String>();
        Random random = new Random();
        for (int i = 0; i < 10; i++) {
            int score = random.nextInt(100);
            list.add("theme_id" + i + ":" + score);
        }
        String[] topN = getTopN(list, 3);
        myPrint(list, topN);
    }

    public static String[] getTopN(List<String> list, int N) {
        String[] topN = new String[N];
        Iterator<String> it = list.iterator();
        while (it.hasNext()) {
            String value = it.next();
            for (int i = 0; i < topN.length; i++) {
                if (topN[i] == null) {
                    topN[i] = value;
                    break;
                } else {
                    String lastValue = topN[i];
                    if (Integer.valueOf(value.split(":")[1]) >= Integer.valueOf(lastValue.split(":")[1])) {
                        for (int j = topN.length - 1; j > i; j--) {
                            topN[j] = topN[j - 1];
                        }
                        topN[i] = value;
                        break;
                    }
                }
            }
        }
        return topN;
    }

    public static void myPrint(List<String> list, String[] topN) {
        for (int i = 0; i < list.size(); i++) {
            System.out.println(list.get(i));
        }
        System.out.println("-----------------------------");
        for (int i = 0; i < topN.length; i++) {
            System.out.println(topN[i]);
        }
    }
}

package udf;

import org.apache.hadoop.hive.ql.exec.UDF;

import java.util.Arrays;
import java.util.Iterator;
import java.util.List;

public class TopnUDF extends UDF {
    public String[] evaluate(String str, String sep1, String sep2, int a, int b) {
        String[] topN = new String[b];
        try {
            if (!str.isEmpty()) {
                List<String> list = Arrays.asList(str.split(sep2));
                Iterator<String> it = list.iterator();
                while (it.hasNext()) {
                    String value = it.next();
                    for (int i = 0; i < topN.length; i++) {
                        if (topN[i] == null) {
                            topN[i] = value;
                            break;
                        } else {
                            String lastValue = topN[i];
                            if (Integer.valueOf(value.split(sep1)[a]) >= Integer.valueOf(lastValue.split(sep1)[a])) {
                                for (int j = topN.length - 1; j > i; j--) {
                                    topN[j] = topN[j - 1];
                                }
                                topN[i] = value;
                                break;
                            }
                        }
                    }
                }
            }

        } catch (Exception e) {
            System.out.println(e.toString());
        }
        return topN;
    }

    public static void main(String[] args) {
        String str = "10001:8:95#10001:9:90#10002:10:85#10003:11:80#10004:11:99";
        String[] topn = new TopnUDF().evaluate(str, ":", "#", 2, 3);
        for (int i = 0; i < topn.length; i++) {
            System.out.println(topn[i]);
        }
    }

}

参考：https://blog.youkuaiyun.com/zeb_perfect/article/details/53333606