diff --git a/.gitignore b/.gitignore
index 394a54797a..f77bee021c 100644
--- a/.gitignore
+++ b/.gitignore
@@ -5,4 +5,5 @@
 /*/target
 /target
 /*/build
-/build
\ No newline at end of file
+/build
+spark-warehouse
\ No newline at end of file
diff --git a/dhp-spark-jobs/src/main/java/eu/dnetlib/collection/GenerateNativeStoreSparkJob.java b/dhp-spark-jobs/src/main/java/eu/dnetlib/collection/GenerateNativeStoreSparkJob.java
deleted file mode 100644
index d21c0a18e6..0000000000
--- a/dhp-spark-jobs/src/main/java/eu/dnetlib/collection/GenerateNativeStoreSparkJob.java
+++ /dev/null
@@ -1,79 +0,0 @@
-package eu.dnetlib.collection;
-
-import org.apache.hadoop.io.IntWritable;
-import org.apache.hadoop.io.Text;
-import org.apache.spark.api.java.JavaPairRDD;
-import org.apache.spark.api.java.JavaRDD;
-import org.apache.spark.api.java.JavaSparkContext;
-import org.apache.spark.api.java.function.Function;
-import org.apache.spark.sql.*;
-import org.apache.spark.sql.types.DataTypes;
-import org.apache.spark.sql.types.StructField;
-import org.apache.spark.sql.types.StructType;
-import scala.Tuple2;
-
-import java.util.ArrayList;
-import java.util.Arrays;
-import java.util.Collections;
-import java.util.List;
-import static org.apache.spark.sql.functions.array_contains;
-
-public class GenerateNativeStoreSparkJob {
-
-
-    public static void main(String[] args) {
-
-        final SparkSession spark = SparkSession
-                .builder()
-                .appName("GenerateNativeStoreSparkJob")
-                .master("local[*]")
-                .getOrCreate();
-
-        final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
-
-        JavaPairRDD<IntWritable, Text> f = sc.sequenceFile("/home/sandro/Downloads/mdstore_oai", IntWritable.class, Text.class);
-
-        String first = f.map(a -> a._2().toString()).first();
-
-
-        final List<StructField> fields = new ArrayList<>();
-
-        fields.add(DataTypes.createStructField("id", DataTypes.StringType, false));
-        fields.add(DataTypes.createStructField("format", DataTypes.StringType, false));
-        fields.add(DataTypes.createStructField("formatName", DataTypes.StringType, true));
-        fields.add(DataTypes.createStructField("body", DataTypes.StringType, true));
-
-        JavaRDD<Row> mdRdd = f.map((Function<Tuple2<IntWritable, Text>, Row>) item -> RowFactory.create("" + item._1().get(), "xml", null, item._2().toString()));
-
-        final StructType schema = DataTypes.createStructType(fields);
-        Dataset<Row> ds = spark.createDataFrame(mdRdd, schema);
-
-//        ds.write().save("/home/sandro/Downloads/test.parquet");
-
-        Publication p2 = new Publication();
-        p2.setDates(Collections.singletonList("2018-09-09"));
-        p2.setTitles(Collections.singletonList("Titolo 2"));
-        p2.setIdentifiers(Collections.singletonList(new PID("pmID", "1234567")));
-
-        Publication p1 = new Publication();
-        p1.setDates(Collections.singletonList("2018-09-09"));
-        p1.setTitles(Collections.singletonList("Titolo 1"));
-        p1.setIdentifiers(Collections.singletonList(new PID("doi", "1234567")));
-
-
-
-
-        Encoder<Publication> encoder = Encoders.bean(Publication.class);
-
-        Dataset<Publication> dp = spark.createDataset(Arrays.asList(p1,p2), encoder);
-
-
-        long count = dp.where(array_contains(new Column("identifiers.schema"), "doi")).count();
-
-        System.out.println("count = " + count);
-
-        System.out.println(ds.count());
-
-
-    }
-}
diff --git a/dhp-wf/pom.xml b/dhp-wf/pom.xml
deleted file mode 100644
index 9444f0d4a7..0000000000
--- a/dhp-wf/pom.xml
+++ /dev/null
@@ -1,22 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<project xmlns="http://maven.apache.org/POM/4.0.0"
-         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
-         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
-	<modelVersion>4.0.0</modelVersion>
-
-	<parent>
-		<groupId>eu.dnetlib.dhp</groupId>
-		<artifactId>dhp</artifactId>
-		<version>1.0.0-SNAPSHOT</version>
-	</parent>
-
-	<artifactId>dhp-wf</artifactId>
-	<packaging>pom</packaging>
-
-	<modules>
-
-	</modules>
-
-
-
-</project>
diff --git a/pom.xml b/pom.xml
index 731bfe984e..c0e1048255 100644
--- a/pom.xml
+++ b/pom.xml
@@ -21,10 +21,8 @@
 
     <modules>
         <!--<module>dhp-build</module>-->
-        <!--<module>dhp-common</module>-->
-        <!--<module>dhp-schemas</module>-->
-        <!--<module>dhp-wf</module>-->
-        <!--<module>dhp-collector-worker</module>-->
+        <module>dhp-common</module>
+        <module>dhp-workflows</module>
     </modules>
 
     <issueManagement>
@@ -104,6 +102,7 @@
                 <groupId>org.apache.hadoop</groupId>
                 <artifactId>hadoop-hdfs</artifactId>
                 <version>${dhp.hadoop.version}</version>
+                <scope>provided</scope>
             </dependency>
             <dependency>
                 <groupId>org.apache.spark</groupId>
@@ -118,6 +117,20 @@
                 <scope>provided</scope>
             </dependency>
 
+            <dependency>
+                <groupId>org.apache.commons</groupId>
+                <artifactId>commons-lang3</artifactId>
+                <version>${dhp.commons.lang.version}</version>
+            </dependency>
+
+            <dependency>
+                <groupId>commons-codec</groupId>
+                <artifactId>commons-codec</artifactId>
+                <version>1.9</version>
+            </dependency>
+
+
+
         </dependencies>
     </dependencyManagement>
 
@@ -239,6 +252,7 @@
         <dhp.cdh.version>cdh5.9.2</dhp.cdh.version>
         <dhp.hadoop.version>2.6.0-${dhp.cdh.version}</dhp.hadoop.version>
         <dhp.spark.version>2.2.0</dhp.spark.version>
+        <dhp.commons.lang.version>3.5</dhp.commons.lang.version>
         <scala.version>2.11.8</scala.version>
     </properties>
 </project>