package dev.java;

import dev.utils.Utils;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.RowFactory;
import org.apache.spark.sql.SparkSession;
import org.apache.spark.sql.types.StructType;
import scala.Tuple2;

import java.util.List;

public class Spark1 {

  private static final String fileData = "seed";
  private static final String fileSave = "result";
  private static SparkSession spark = SparkSession.builder()
        .appName("Java-Spark")
        .master("local[*]")
        .config("spark.default.parallelism", 100)
        .config("spark.sql.shuffle.partitions", 100)
        .config("spark.driver.maxResultSize", "3g")
        .getOrCreate();
  private static JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());

  public static void main(String[] args) {
    Utils.delete(fileSave);
    //
    t1();
  }

  private static void t1() {
    JavaRDD<Row> rdd = sc.textFile(fileData)
        .map(v -> {
          String[] parts = v.split("\t");
          return RowFactory.create(parts[0], Long.parseLong(parts[1]));
        })
        .filter(v -> v.getLong(1) >= 10000)
        .sortBy(v -> v.getLong(1), false, 100)
        .coalesce(2);
    Dataset<Row> df = spark.createDataFrame(rdd, StructType.fromDDL("title string, qty long"));
    df.write().csv(fileSave);
    spark.stop();
  }
}