package eu.dnetlib.deeplearning.featureextraction;

import eu.dnetlib.featureextraction.ScalaFeatureTransformer;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.ml.linalg.DenseVector;
import org.apache.spark.ml.linalg.DenseVector$;
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.DataTypes;
import org.apache.spark.sql.types.Metadata;
import org.apache.spark.sql.types.StructField;
import org.apache.spark.sql.types.StructType;
import org.junit.jupiter.api.BeforeAll;
import org.junit.jupiter.api.Test;
import scala.collection.JavaConversions;
import scala.collection.mutable.WrappedArray;

import javax.xml.crypto.Data;
import java.io.IOException;
import java.util.Arrays;

public class FeatureTransformerTest {

    static SparkSession spark;
    static JavaSparkContext context;
    static Dataset<Row> inputData;
    static StructType inputSchema = new StructType(new StructField[]{
            new StructField("title", DataTypes.StringType, false, Metadata.empty()),
            new StructField("abstract", DataTypes.StringType, false, Metadata.empty())
    });

    @BeforeAll
    public static void setup() throws IOException {

        spark = SparkSession
                .builder()
                .appName("Testing")
                .master("local[*]")
                .getOrCreate();

        context = JavaSparkContext.fromSparkContext(spark.sparkContext());

        inputData = spark.createDataFrame(Arrays.asList(
                RowFactory.create("article title 1", "article description 1"),
                RowFactory.create("article title 2", "article description 2")
        ), inputSchema);

    }

}