Merge branch 'doiboost' of code-repo.d4science.org:D-Net/dnet-hadoop into doiboost

dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/ActivitiesDecompressor.java

@@ -0,0 +1,151 @@
+package eu.dnetlib.doiboost.orcid;
+
+import eu.dnetlib.doiboost.orcid.json.JsonWriter;
+import eu.dnetlib.doiboost.orcid.model.WorkData;
+import eu.dnetlib.doiboost.orcid.xml.XMLRecordParser;
+import java.io.BufferedReader;
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.InputStreamReader;
+import java.net.URI;
+import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
+import org.apache.commons.compress.archivers.tar.TarArchiveInputStream;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.io.IOUtils;
+import org.apache.hadoop.io.SequenceFile;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.io.compress.CompressionCodec;
+import org.apache.hadoop.io.compress.CompressionCodecFactory;
+import org.mortbay.log.Log;
+
+public class ActivitiesDecompressor {
+
+    private static final int MAX_XML_WORKS_PARSED = -1;
+    private static final int XML_WORKS_PARSED_COUNTER_LOG_INTERVAL = 100000;
+
+    public static void parseGzActivities(Configuration conf, String inputUri, Path outputPath)
+            throws Exception {
+        String uri = inputUri;
+        FileSystem fs = FileSystem.get(URI.create(uri), conf);
+        Path inputPath = new Path(uri);
+        CompressionCodecFactory factory = new CompressionCodecFactory(conf);
+        CompressionCodec codec = factory.getCodec(inputPath);
+        if (codec == null) {
+            System.err.println("No codec found for " + uri);
+            System.exit(1);
+        }
+        CompressionCodecFactory.removeSuffix(uri, codec.getDefaultExtension());
+        InputStream gzipInputStream = null;
+        try {
+            gzipInputStream = codec.createInputStream(fs.open(inputPath));
+            parseTarActivities(fs, conf, gzipInputStream, outputPath);
+
+        } finally {
+            Log.debug("Closing gzip stream");
+            IOUtils.closeStream(gzipInputStream);
+        }
+    }
+
+    private static void parseTarActivities(
+            FileSystem fs, Configuration conf, InputStream gzipInputStream, Path outputPath) {
+        int counter = 0;
+        int doiFound = 0;
+        int errorFromOrcidFound = 0;
+        int xmlParserErrorFound = 0;
+        try (TarArchiveInputStream tais = new TarArchiveInputStream(gzipInputStream)) {
+            TarArchiveEntry entry = null;
+
+            try (SequenceFile.Writer writer =
+                    SequenceFile.createWriter(
+                            conf,
+                            SequenceFile.Writer.file(outputPath),
+                            SequenceFile.Writer.keyClass(Text.class),
+                            SequenceFile.Writer.valueClass(Text.class))) {
+                while ((entry = tais.getNextTarEntry()) != null) {
+                    String filename = entry.getName();
+
+                    try {
+                        if (entry.isDirectory() || !filename.contains("works")) {
+
+                        } else {
+                            Log.debug("XML work entry name: " + entry.getName());
+                            counter++;
+                            BufferedReader br =
+                                    new BufferedReader(
+                                            new InputStreamReader(
+                                                    tais)); // Read directly from tarInput
+                            String line;
+                            StringBuffer buffer = new StringBuffer();
+                            while ((line = br.readLine()) != null) {
+                                buffer.append(line);
+                            }
+                            WorkData workData =
+                                    XMLRecordParser.VTDParseWorkData(buffer.toString().getBytes());
+                            if (workData != null) {
+                                if (workData.getErrorCode() != null) {
+                                    errorFromOrcidFound += 1;
+                                    Log.debug(
+                                            "error from Orcid with code "
+                                                    + workData.getErrorCode()
+                                                    + " for entry "
+                                                    + entry.getName());
+                                    continue;
+                                }
+                                if (workData.isDoiFound()) {
+                                    String jsonData = JsonWriter.create(workData);
+                                    Log.debug("oid: " + workData.getOid() + " data: " + jsonData);
+
+                                    final Text key = new Text(workData.getOid());
+                                    final Text value = new Text(jsonData);
+
+                                    try {
+                                        writer.append(key, value);
+                                    } catch (IOException e) {
+                                        Log.debug("Writing to sequence file: " + e.getMessage());
+                                        Log.debug(e);
+                                        throw new RuntimeException(e);
+                                    }
+                                    doiFound += 1;
+                                }
+
+                            } else {
+                                Log.warn(
+                                        "Data not retrievable ["
+                                                + entry.getName()
+                                                + "] "
+                                                + buffer.toString());
+                                xmlParserErrorFound += 1;
+                            }
+                        }
+                    } catch (Exception e) {
+                        Log.warn(
+                                "Parsing work from tar archive and xml work: "
+                                        + filename
+                                        + "  "
+                                        + e.getMessage());
+                        Log.warn(e);
+                    }
+
+                    if ((counter % XML_WORKS_PARSED_COUNTER_LOG_INTERVAL) == 0) {
+                        Log.info("Current xml works parsed: " + counter);
+                    }
+
+                    if ((MAX_XML_WORKS_PARSED > -1) && (counter > MAX_XML_WORKS_PARSED)) {
+                        break;
+                    }
+                }
+            }
+        } catch (IOException e) {
+            Log.warn("Parsing work from gzip archive: " + e.getMessage());
+            Log.warn(e);
+            throw new RuntimeException(e);
+        }
+        Log.info("Activities parse completed");
+        Log.info("Total XML works parsed: " + counter);
+        Log.info("Total doi found: " + doiFound);
+        Log.info("Error from Orcid found: " + errorFromOrcidFound);
+        Log.info("Error parsing xml work found: " + xmlParserErrorFound);
+    }
+}

dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/OrcidAuthorsDOIsDataGen.java

@@ -0,0 +1,49 @@
+package eu.dnetlib.doiboost.orcid;
+
+import eu.dnetlib.dhp.application.ArgumentApplicationParser;
+import java.io.IOException;
+import org.apache.commons.io.IOUtils;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.mortbay.log.Log;
+
+public class OrcidAuthorsDOIsDataGen extends OrcidDSManager {
+
+    private String activitiesFileNameTarGz;
+    private String outputAuthorsDOIsPath;
+
+    public static void main(String[] args) throws IOException, Exception {
+        OrcidAuthorsDOIsDataGen orcidAuthorsDOIsDataGen = new OrcidAuthorsDOIsDataGen();
+        orcidAuthorsDOIsDataGen.loadArgs(args);
+        orcidAuthorsDOIsDataGen.generateAuthorsDOIsData();
+    }
+
+    public void generateAuthorsDOIsData() throws Exception {
+        Configuration conf = initConfigurationObject();
+        FileSystem fs = initFileSystemObject(conf);
+        String tarGzUri =
+                hdfsServerUri.concat(hdfsOrcidDefaultPath).concat(activitiesFileNameTarGz);
+        Path outputPath =
+                new Path(hdfsServerUri.concat(hdfsOrcidDefaultPath).concat(outputAuthorsDOIsPath));
+        ActivitiesDecompressor.parseGzActivities(conf, tarGzUri, outputPath);
+    }
+
+    private void loadArgs(String[] args) throws IOException, Exception {
+        final ArgumentApplicationParser parser =
+                new ArgumentApplicationParser(
+                        IOUtils.toString(
+                                OrcidAuthorsDOIsDataGen.class.getResourceAsStream(
+                                        "/eu/dnetlib/dhp/doiboost/create_orcid_authors_dois_data.json")));
+        parser.parseArgument(args);
+
+        hdfsServerUri = parser.get("hdfsServerUri");
+        Log.info("HDFS URI: " + hdfsServerUri);
+        hdfsOrcidDefaultPath = parser.get("hdfsOrcidDefaultPath");
+        Log.info("Default Path: " + hdfsOrcidDefaultPath);
+        activitiesFileNameTarGz = parser.get("activitiesFileNameTarGz");
+        Log.info("Activities File Name: " + activitiesFileNameTarGz);
+        outputAuthorsDOIsPath = parser.get("outputAuthorsDOIsPath");
+        Log.info("Output Authors DOIs Data: " + outputAuthorsDOIsPath);
+    }
+}

dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/OrcidDSManager.java

@@ -11,8 +11,8 @@ import org.mortbay.log.Log;
 
 public class OrcidDSManager {
 
-    private String hdfsServerUri;
-    private String hdfsOrcidDefaultPath;
+    protected String hdfsServerUri;
+    protected String hdfsOrcidDefaultPath;
     private String summariesFileNameTarGz;
     private String outputAuthorsPath;
 
@@ -35,7 +35,7 @@ public class OrcidDSManager {
         SummariesDecompressor.parseGzSummaries(conf, tarGzUri, outputPath);
     }
 
-    private Configuration initConfigurationObject() {
+    protected Configuration initConfigurationObject() {
         // ====== Init HDFS File System Object
         Configuration conf = new Configuration();
         // Set FileSystem URI
@@ -46,7 +46,7 @@ public class OrcidDSManager {
         return conf;
     }
 
-    private FileSystem initFileSystemObject(Configuration conf) {
+    protected FileSystem initFileSystemObject(Configuration conf) {
         // Get the filesystem - HDFS
         FileSystem fs = null;
         try {

dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/SummariesDecompressor.java

@@ -82,7 +82,8 @@ public class SummariesDecompressor {
                                 buffer.append(line);
                             }
                             AuthorData authorData =
-                                    XMLRecordParser.VTDParse(buffer.toString().getBytes());
+                                    XMLRecordParser.VTDParseAuthorData(
+                                            buffer.toString().getBytes());
                             if (authorData != null) {
                                 if (authorData.getErrorCode() != null) {
                                     errorFromOrcidFound += 1;

dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/json/JsonWriter.java

@@ -2,6 +2,7 @@ package eu.dnetlib.doiboost.orcid.json;
 
 import com.google.gson.JsonObject;
 import eu.dnetlib.doiboost.orcid.model.AuthorData;
+import eu.dnetlib.doiboost.orcid.model.WorkData;
 
 public class JsonWriter {
 
@@ -15,4 +16,11 @@ public class JsonWriter {
         }
         return author.toString();
     }
+
+    public static String create(WorkData workData) {
+        JsonObject work = new JsonObject();
+        work.addProperty("oid", workData.getOid());
+        work.addProperty("doi", workData.getDoi());
+        return work.toString();
+    }
 }

dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/model/WorkData.java

@@ -0,0 +1,42 @@
+package eu.dnetlib.doiboost.orcid.model;
+
+public class WorkData {
+
+    private String oid;
+    private String doi;
+    private boolean doiFound = false;
+
+    public boolean isDoiFound() {
+        return doiFound;
+    }
+
+    public void setDoiFound(boolean doiFound) {
+        this.doiFound = doiFound;
+    }
+
+    public String getOid() {
+        return oid;
+    }
+
+    public void setOid(String oid) {
+        this.oid = oid;
+    }
+
+    public String getDoi() {
+        return doi;
+    }
+
+    public void setDoi(String doi) {
+        this.doi = doi;
+    }
+
+    public String getErrorCode() {
+        return errorCode;
+    }
+
+    public void setErrorCode(String errorCode) {
+        this.errorCode = errorCode;
+    }
+
+    private String errorCode;
+}

dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/xml/XMLRecordParser.java

@@ -10,6 +10,7 @@ import com.ximpleware.VTDNav;
 import eu.dnetlib.dhp.parser.utility.VtdException;
 import eu.dnetlib.dhp.parser.utility.VtdUtilityParser;
 import eu.dnetlib.doiboost.orcid.model.AuthorData;
+import eu.dnetlib.doiboost.orcid.model.WorkData;
 import java.util.Arrays;
 import java.util.List;
 
@@ -26,9 +27,13 @@ public class XMLRecordParser {
     private static final String NS_RECORD_URL = "http://www.orcid.org/ns/record";
     private static final String NS_RECORD = "record";
     private static final String NS_ERROR_URL = "http://www.orcid.org/ns/error";
+
+    private static final String NS_WORK = "work";
+    private static final String NS_WORK_URL = "http://www.orcid.org/ns/work";
+
     private static final String NS_ERROR = "error";
 
-    public static AuthorData VTDParse(byte[] bytes)
+    public static AuthorData VTDParseAuthorData(byte[] bytes)
             throws VtdException, EncodingException, EOFException, EntityException, ParseException {
         final VTDGen vg = new VTDGen();
         vg.setDoc(bytes);
@@ -78,4 +83,44 @@ public class XMLRecordParser {
         }
         return authorData;
     }
+
+    public static WorkData VTDParseWorkData(byte[] bytes)
+            throws VtdException, EncodingException, EOFException, EntityException, ParseException {
+        final VTDGen vg = new VTDGen();
+        vg.setDoc(bytes);
+        vg.parse(true);
+        final VTDNav vn = vg.getNav();
+        final AutoPilot ap = new AutoPilot(vn);
+        ap.declareXPathNameSpace(NS_COMMON, NS_COMMON_URL);
+        ap.declareXPathNameSpace(NS_WORK, NS_WORK_URL);
+        ap.declareXPathNameSpace(NS_ERROR, NS_ERROR_URL);
+
+        WorkData workData = new WorkData();
+        final List<String> errors = VtdUtilityParser.getTextValue(ap, vn, "//error:response-code");
+        if (!errors.isEmpty()) {
+            workData.setErrorCode(errors.get(0));
+            return workData;
+        }
+
+        List<VtdUtilityParser.Node> workNodes =
+                VtdUtilityParser.getTextValuesWithAttributes(
+                        ap, vn, "//work:work", Arrays.asList("path"));
+        if (!workNodes.isEmpty()) {
+            final String oid = (workNodes.get(0).getAttributes().get("path")).split("/")[1];
+            workData.setOid(oid);
+        } else {
+            return null;
+        }
+
+        final List<String> dois =
+                VtdUtilityParser.getTextValue(
+                        ap,
+                        vn,
+                        "//common:external-id-type[text()=\"doi\"]/../common:external-id-value");
+        if (!dois.isEmpty()) {
+            workData.setDoi(dois.get(0));
+            workData.setDoiFound(true);
+        }
+        return workData;
+    }
 }

dhp-workflows/dhp-doiboost/src/main/resources/eu/dnetlib/dhp/doiboost/create_orcid_authors_dois_data.json

@@ -0,0 +1,6 @@
+[
+  {"paramName":"n",   "paramLongName":"hdfsServerUri",	"paramDescription": "the server uri",   "paramRequired": true},
+  {"paramName":"d",   "paramLongName":"hdfsOrcidDefaultPath",	"paramDescription": "the default work path",	"paramRequired": true},
+  {"paramName":"f",   "paramLongName":"activitiesFileNameTarGz",	"paramDescription": "the name of the activities orcid file",	"paramRequired": true},
+  {"paramName":"o",   "paramLongName":"outputAuthorsDOIsPath",	"paramDescription": "the relative folder of the sequencial file to write",	"paramRequired": true}
+]

dhp-workflows/dhp-doiboost/src/main/resources/eu/dnetlib/dhp/doiboost/orcid_authors_dois_data/oozie_app/config-default.xml

@@ -0,0 +1,22 @@
+<configuration>
+    <property>
+        <name>jobTracker</name>
+        <value>yarnRM</value>
+    </property>
+    <property>
+        <name>nameNode</name>
+        <value>hdfs://nameservice1</value>
+    </property>
+    <property>
+        <name>oozie.action.sharelib.for.java</name>
+        <value>spark2</value>
+    </property>
+    <property>
+        <name>oozie.launcher.mapreduce.user.classpath.first</name>
+        <value>true</value>
+    </property>
+    <property>
+      <name>oozie.launcher.mapreduce.map.java.opts</name>
+      <value>-Xmx4g</value>
+    </property>
+</configuration>

dhp-workflows/dhp-doiboost/src/main/resources/eu/dnetlib/dhp/doiboost/orcid_authors_dois_data/oozie_app/workflow.xml

@@ -0,0 +1,505 @@
+<workflow-app name="Gen Orcid Authors DOIs" xmlns="uri:oozie:workflow:0.5">
+    <parameters>
+        <property>
+            <name>workingPath_activities</name>
+            <description>the working dir base path</description>
+        </property>
+        <property>
+            <name>shell_cmd_0</name>
+            <value>wget -O /tmp/ORCID_2019_activites_0.tar.gz https://orcid.figshare.com/ndownloader/files/18017660 ; hdfs dfs -copyFromLocal /tmp/ORCID_2019_activites_0.tar.gz /data/orcid_activities/ORCID_2019_activites_0.tar.gz
+            </value>
+            <description>the shell command that downloads and puts to hdfs orcid activity file 0</description>
+        </property>
+        <property>
+            <name>shell_cmd_1</name>
+            <value>wget -O /tmp/ORCID_2019_activites_1.tar.gz https://orcid.figshare.com/ndownloader/files/18017675 ; hdfs dfs -copyFromLocal /tmp/ORCID_2019_activites_1.tar.gz /data/orcid_activities/ORCID_2019_activites_1.tar.gz
+            </value>
+            <description>the shell command that downloads and puts to hdfs orcid activity file 1</description>
+        </property>
+        <property>
+            <name>shell_cmd_2</name>
+            <value>wget -O /tmp/ORCID_2019_activites_2.tar.gz https://orcid.figshare.com/ndownloader/files/18017717 ; hdfs dfs -copyFromLocal /tmp/ORCID_2019_activites_2.tar.gz /data/orcid_activities/ORCID_2019_activites_2.tar.gz
+            </value>
+            <description>the shell command that downloads and puts to hdfs orcid activity file 2</description>
+        </property>
+        <property>
+            <name>shell_cmd_3</name>
+            <value>wget -O /tmp/ORCID_2019_activites_3.tar.gz https://orcid.figshare.com/ndownloader/files/18017765 ; hdfs dfs -copyFromLocal /tmp/ORCID_2019_activites_3.tar.gz /data/orcid_activities/ORCID_2019_activites_3.tar.gz
+            </value>
+            <description>the shell command that downloads and puts to hdfs orcid activity file 3</description>
+        </property> 
+        <property>
+            <name>shell_cmd_4</name>
+            <value>wget -O /tmp/ORCID_2019_activites_4.tar.gz https://orcid.figshare.com/ndownloader/files/18017831 ; hdfs dfs -copyFromLocal /tmp/ORCID_2019_activites_4.tar.gz /data/orcid_activities/ORCID_2019_activites_4.tar.gz
+            </value>
+            <description>the shell command that downloads and puts to hdfs orcid activity file 4</description>
+        </property> 
+        <property>
+            <name>shell_cmd_5</name>
+            <value>wget -O /tmp/ORCID_2019_activites_5.tar.gz https://orcid.figshare.com/ndownloader/files/18017987 ; hdfs dfs -copyFromLocal /tmp/ORCID_2019_activites_5.tar.gz /data/orcid_activities/ORCID_2019_activites_5.tar.gz
+            </value>
+            <description>the shell command that downloads and puts to hdfs orcid activity file 5</description>
+        </property>  
+        <property>
+            <name>shell_cmd_6</name>
+            <value>wget -O /tmp/ORCID_2019_activites_6.tar.gz https://orcid.figshare.com/ndownloader/files/18018053 ; hdfs dfs -copyFromLocal /tmp/ORCID_2019_activites_6.tar.gz /data/orcid_activities/ORCID_2019_activites_6.tar.gz
+            </value>
+            <description>the shell command that downloads and puts to hdfs orcid activity file 6</description>
+        </property>
+        <property>
+            <name>shell_cmd_7</name>
+            <value>wget -O /tmp/ORCID_2019_activites_7.tar.gz https://orcid.figshare.com/ndownloader/files/18018023 ; hdfs dfs -copyFromLocal /tmp/ORCID_2019_activites_7.tar.gz /data/orcid_activities/ORCID_2019_activites_7.tar.gz
+            </value>
+            <description>the shell command that downloads and puts to hdfs orcid activity file 7</description>
+        </property>
+        <property>
+            <name>shell_cmd_8</name>
+            <value>wget -O /tmp/ORCID_2019_activites_8.tar.gz https://orcid.figshare.com/ndownloader/files/18018248 ; hdfs dfs -copyFromLocal /tmp/ORCID_2019_activites_8.tar.gz /data/orcid_activities/ORCID_2019_activites_8.tar.gz
+            </value>
+            <description>the shell command that downloads and puts to hdfs orcid activity file 8</description>
+        </property>
+        <property>
+            <name>shell_cmd_9</name>
+            <value>wget -O /tmp/ORCID_2019_activites_9.tar.gz https://orcid.figshare.com/ndownloader/files/18018029 ; hdfs dfs -copyFromLocal /tmp/ORCID_2019_activites_9.tar.gz /data/orcid_activities/ORCID_2019_activites_9.tar.gz
+            </value>
+            <description>the shell command that downloads and puts to hdfs orcid activity file 9</description>
+        </property> 
+        <property>
+            <name>shell_cmd_X</name>
+            <value>wget -O /tmp/ORCID_2019_activites_X.tar.gz https://orcid.figshare.com/ndownloader/files/18018182 ; hdfs dfs -copyFromLocal /tmp/ORCID_2019_activites_X.tar.gz /data/orcid_activities/ORCID_2019_activites_X.tar.gz
+            </value>
+            <description>the shell command that downloads and puts to hdfs orcid activity file X</description>
+        </property>  
+    </parameters>
+    
+    <start to="ResetWorkingPath"/>
+    
+    
+    <kill name="Kill">
+        <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
+    </kill>
+    
+    <action name="ResetWorkingPath">
+        <fs>
+            <delete path='${workingPath_activities}/output'/>
+            <mkdir path='${workingPath_activities}/output'/>
+        </fs>
+        <ok to="fork_gen_orcid_authors_dois"/>
+        <error to="Kill"/>
+    </action>
+    
+    <fork name = "fork_gen_orcid_authors_dois">
+      <path start = "check_exist_on_hdfs_activities_0"/>
+      <path start = "check_exist_on_hdfs_activities_1"/>
+      <path start = "check_exist_on_hdfs_activities_2"/>
+	  <path start = "check_exist_on_hdfs_activities_3"/>
+	  <path start = "check_exist_on_hdfs_activities_4"/>
+	  <path start = "check_exist_on_hdfs_activities_5"/>
+	  <path start = "check_exist_on_hdfs_activities_6"/>
+	  <path start = "check_exist_on_hdfs_activities_7"/>
+	  <path start = "check_exist_on_hdfs_activities_8"/>
+	  <path start = "check_exist_on_hdfs_activities_9"/>
+	  <path start = "check_exist_on_hdfs_activities_X"/>
+   	</fork>
+   	
+    <decision name="check_exist_on_hdfs_activities_0">
+         <switch>
+            <case to="Gen_Orcid_Authors_DOIs_0">
+              ${fs:exists(concat(workingPath_activities,'/ORCID_2019_activites_0.tar.gz'))}
+            </case>
+            <default to="Download_0" />
+         </switch>
+	</decision>
+	
+    <action name="Download_0">
+		<shell xmlns="uri:oozie:shell-action:0.1">
+		<job-tracker>${jobTracker}</job-tracker>
+		<name-node>${nameNode}</name-node>
+		<exec>bash</exec>
+	    <argument>-c</argument>
+	    <argument>${shell_cmd_0}</argument>
+		<capture-output/>
+		</shell>
+	<ok to="Gen_Orcid_Authors_DOIs_0"/>
+	<error to="Kill"/>
+	</action>
+	
+	<action name="Gen_Orcid_Authors_DOIs_0">
+        <java>
+            <job-tracker>${jobTracker}</job-tracker>
+            <name-node>${nameNode}</name-node>
+            <main-class>eu.dnetlib.doiboost.orcid.OrcidAuthorsDOIsDataGen</main-class>
+            <arg>-d</arg><arg>${workingPath_activities}/</arg>
+            <arg>-n</arg><arg>${nameNode}</arg>
+            <arg>-f</arg><arg>ORCID_2019_activites_0.tar.gz</arg>
+            <arg>-o</arg><arg>output/authors_dois_0.seq</arg>
+        </java>
+        <ok to="join_node"/>
+        <error to="Kill"/>
+    </action>
+    
+    <decision name="check_exist_on_hdfs_activities_1">
+         <switch>
+            <case to="Gen_Orcid_Authors_DOIs_1">
+              ${fs:exists(concat(workingPath_activities,'/ORCID_2019_activites_1.tar.gz'))}
+            </case>
+            <default to="Download_1" />
+         </switch>
+	</decision>
+	
+    <action name="Download_1">
+		<shell xmlns="uri:oozie:shell-action:0.1">
+		<job-tracker>${jobTracker}</job-tracker>
+		<name-node>${nameNode}</name-node>
+		<exec>bash</exec>
+	    <argument>-c</argument>
+	    <argument>${shell_cmd_1}</argument>
+		<capture-output/>
+		</shell>
+	<ok to="Gen_Orcid_Authors_DOIs_1"/>
+	<error to="Kill"/>
+	</action>
+	
+	<action name="Gen_Orcid_Authors_DOIs_1">
+        <java>
+            <job-tracker>${jobTracker}</job-tracker>
+            <name-node>${nameNode}</name-node>
+            <main-class>eu.dnetlib.doiboost.orcid.OrcidAuthorsDOIsDataGen</main-class>
+            <arg>-d</arg><arg>${workingPath_activities}/</arg>
+            <arg>-n</arg><arg>${nameNode}</arg>
+            <arg>-f</arg><arg>ORCID_2019_activites_1.tar.gz</arg>
+            <arg>-o</arg><arg>output/authors_dois_1.seq</arg>
+        </java>
+        <ok to="join_node"/>
+        <error to="Kill"/>
+    </action>
+    
+    <decision name="check_exist_on_hdfs_activities_2">
+         <switch>
+            <case to="Gen_Orcid_Authors_DOIs_2">
+              ${fs:exists(concat(workingPath_activities,'/ORCID_2019_activites_2.tar.gz'))}
+            </case>
+            <default to="Download_2" />
+         </switch>
+	</decision>
+	
+    <action name="Download_2">
+		<shell xmlns="uri:oozie:shell-action:0.1">
+		<job-tracker>${jobTracker}</job-tracker>
+		<name-node>${nameNode}</name-node>
+		<exec>bash</exec>
+	    <argument>-c</argument>
+	    <argument>${shell_cmd_2}</argument>
+		<capture-output/>
+		</shell>
+	<ok to="Gen_Orcid_Authors_DOIs_2"/>
+	<error to="Kill"/>
+	</action>
+	
+	<action name="Gen_Orcid_Authors_DOIs_2">
+        <java>
+            <job-tracker>${jobTracker}</job-tracker>
+            <name-node>${nameNode}</name-node>
+            <main-class>eu.dnetlib.doiboost.orcid.OrcidAuthorsDOIsDataGen</main-class>
+            <arg>-d</arg><arg>${workingPath_activities}/</arg>
+            <arg>-n</arg><arg>${nameNode}</arg>
+            <arg>-f</arg><arg>ORCID_2019_activites_2.tar.gz</arg>
+            <arg>-o</arg><arg>output/authors_dois_2.seq</arg>
+        </java>
+        <ok to="join_node"/>
+        <error to="Kill"/>
+    </action>
+    
+    <decision name="check_exist_on_hdfs_activities_3">
+         <switch>
+            <case to="Gen_Orcid_Authors_DOIs_3">
+              ${fs:exists(concat(workingPath_activities,'/ORCID_2019_activites_3.tar.gz'))}
+            </case>
+            <default to="Download_3" />
+         </switch>
+	</decision>
+	
+    <action name="Download_3">
+		<shell xmlns="uri:oozie:shell-action:0.1">
+		<job-tracker>${jobTracker}</job-tracker>
+		<name-node>${nameNode}</name-node>
+		<exec>bash</exec>
+	    <argument>-c</argument>
+	    <argument>${shell_cmd_3}</argument>
+		<capture-output/>
+		</shell>
+	<ok to="Gen_Orcid_Authors_DOIs_3"/>
+	<error to="Kill"/>
+	</action>
+	
+	<action name="Gen_Orcid_Authors_DOIs_3">
+        <java>
+            <job-tracker>${jobTracker}</job-tracker>
+            <name-node>${nameNode}</name-node>
+            <main-class>eu.dnetlib.doiboost.orcid.OrcidAuthorsDOIsDataGen</main-class>
+            <arg>-d</arg><arg>${workingPath_activities}/</arg>
+            <arg>-n</arg><arg>${nameNode}</arg>
+            <arg>-f</arg><arg>ORCID_2019_activites_3.tar.gz</arg>
+            <arg>-o</arg><arg>output/authors_dois_3.seq</arg>
+        </java>
+        <ok to="join_node"/>
+        <error to="Kill"/>
+    </action>
+    
+    <decision name="check_exist_on_hdfs_activities_4">
+         <switch>
+            <case to="Gen_Orcid_Authors_DOIs_4">
+              ${fs:exists(concat(workingPath_activities,'/ORCID_2019_activites_4.tar.gz'))}
+            </case>
+            <default to="Download_4" />
+         </switch>
+	</decision>
+	
+    <action name="Download_4">
+		<shell xmlns="uri:oozie:shell-action:0.1">
+		<job-tracker>${jobTracker}</job-tracker>
+		<name-node>${nameNode}</name-node>
+		<exec>bash</exec>
+	    <argument>-c</argument>
+	    <argument>${shell_cmd_4}</argument>
+		<capture-output/>
+		</shell>
+	<ok to="Gen_Orcid_Authors_DOIs_4"/>
+	<error to="Kill"/>
+	</action>
+	
+	<action name="Gen_Orcid_Authors_DOIs_4">
+        <java>
+            <job-tracker>${jobTracker}</job-tracker>
+            <name-node>${nameNode}</name-node>
+            <main-class>eu.dnetlib.doiboost.orcid.OrcidAuthorsDOIsDataGen</main-class>
+            <arg>-d</arg><arg>${workingPath_activities}/</arg>
+            <arg>-n</arg><arg>${nameNode}</arg>
+            <arg>-f</arg><arg>ORCID_2019_activites_4.tar.gz</arg>
+            <arg>-o</arg><arg>output/authors_dois_4.seq</arg>
+        </java>
+        <ok to="join_node"/>
+        <error to="Kill"/>
+    </action>
+    
+    <decision name="check_exist_on_hdfs_activities_5">
+         <switch>
+            <case to="Gen_Orcid_Authors_DOIs_5">
+              ${fs:exists(concat(workingPath_activities,'/ORCID_2019_activites_5.tar.gz'))}
+            </case>
+            <default to="Download_5" />
+         </switch>
+	</decision>
+	
+    <action name="Download_5">
+		<shell xmlns="uri:oozie:shell-action:0.1">
+		<job-tracker>${jobTracker}</job-tracker>
+		<name-node>${nameNode}</name-node>
+		<exec>bash</exec>
+	    <argument>-c</argument>
+	    <argument>${shell_cmd_5}</argument>
+		<capture-output/>
+		</shell>
+	<ok to="Gen_Orcid_Authors_DOIs_5"/>
+	<error to="Kill"/>
+	</action>
+	
+	<action name="Gen_Orcid_Authors_DOIs_5">
+        <java>
+            <job-tracker>${jobTracker}</job-tracker>
+            <name-node>${nameNode}</name-node>
+            <main-class>eu.dnetlib.doiboost.orcid.OrcidAuthorsDOIsDataGen</main-class>
+            <arg>-d</arg><arg>${workingPath_activities}/</arg>
+            <arg>-n</arg><arg>${nameNode}</arg>
+            <arg>-f</arg><arg>ORCID_2019_activites_5.tar.gz</arg>
+            <arg>-o</arg><arg>output/authors_dois_5.seq</arg>
+        </java>
+        <ok to="join_node"/>
+        <error to="Kill"/>
+    </action>
+    
+    <decision name="check_exist_on_hdfs_activities_6">
+         <switch>
+            <case to="Gen_Orcid_Authors_DOIs_6">
+              ${fs:exists(concat(workingPath_activities,'/ORCID_2019_activites_6.tar.gz'))}
+            </case>
+            <default to="Download_6" />
+         </switch>
+	</decision>
+	
+    <action name="Download_6">
+		<shell xmlns="uri:oozie:shell-action:0.1">
+		<job-tracker>${jobTracker}</job-tracker>
+		<name-node>${nameNode}</name-node>
+		<exec>bash</exec>
+	    <argument>-c</argument>
+	    <argument>${shell_cmd_6}</argument>
+		<capture-output/>
+		</shell>
+	<ok to="Gen_Orcid_Authors_DOIs_6"/>
+	<error to="Kill"/>
+	</action>
+	
+	<action name="Gen_Orcid_Authors_DOIs_6">
+        <java>
+            <job-tracker>${jobTracker}</job-tracker>
+            <name-node>${nameNode}</name-node>
+            <main-class>eu.dnetlib.doiboost.orcid.OrcidAuthorsDOIsDataGen</main-class>
+            <arg>-d</arg><arg>${workingPath_activities}/</arg>
+            <arg>-n</arg><arg>${nameNode}</arg>
+            <arg>-f</arg><arg>ORCID_2019_activites_6.tar.gz</arg>
+            <arg>-o</arg><arg>output/authors_dois_6.seq</arg>
+        </java>
+        <ok to="join_node"/>
+        <error to="Kill"/>
+    </action>
+    
+    
+    <decision name="check_exist_on_hdfs_activities_7">
+         <switch>
+            <case to="Gen_Orcid_Authors_DOIs_7">
+              ${fs:exists(concat(workingPath_activities,'/ORCID_2019_activites_7.tar.gz'))}
+            </case>
+            <default to="Download_7" />
+         </switch>
+	</decision>
+	
+    <action name="Download_7">
+		<shell xmlns="uri:oozie:shell-action:0.1">
+		<job-tracker>${jobTracker}</job-tracker>
+		<name-node>${nameNode}</name-node>
+		<exec>bash</exec>
+	    <argument>-c</argument>
+	    <argument>${shell_cmd_7}</argument>
+		<capture-output/>
+		</shell>
+	<ok to="Gen_Orcid_Authors_DOIs_7"/>
+	<error to="Kill"/>
+	</action>
+	
+	<action name="Gen_Orcid_Authors_DOIs_7">
+        <java>
+            <job-tracker>${jobTracker}</job-tracker>
+            <name-node>${nameNode}</name-node>
+            <main-class>eu.dnetlib.doiboost.orcid.OrcidAuthorsDOIsDataGen</main-class>
+            <arg>-d</arg><arg>${workingPath_activities}/</arg>
+            <arg>-n</arg><arg>${nameNode}</arg>
+            <arg>-f</arg><arg>ORCID_2019_activites_7.tar.gz</arg>
+            <arg>-o</arg><arg>output/authors_dois_7.seq</arg>
+        </java>
+        <ok to="join_node"/>
+        <error to="Kill"/>
+    </action>
+    
+    <decision name="check_exist_on_hdfs_activities_8">
+         <switch>
+            <case to="Gen_Orcid_Authors_DOIs_8">
+              ${fs:exists(concat(workingPath_activities,'/ORCID_2019_activites_8.tar.gz'))}
+            </case>
+            <default to="Download_8" />
+         </switch>
+	</decision>
+	
+    <action name="Download_8">
+		<shell xmlns="uri:oozie:shell-action:0.1">
+		<job-tracker>${jobTracker}</job-tracker>
+		<name-node>${nameNode}</name-node>
+		<exec>bash</exec>
+	    <argument>-c</argument>
+	    <argument>${shell_cmd_8}</argument>
+		<capture-output/>
+		</shell>
+	<ok to="Gen_Orcid_Authors_DOIs_8"/>
+	<error to="Kill"/>
+	</action>
+	
+	<action name="Gen_Orcid_Authors_DOIs_8">
+        <java>
+            <job-tracker>${jobTracker}</job-tracker>
+            <name-node>${nameNode}</name-node>
+            <main-class>eu.dnetlib.doiboost.orcid.OrcidAuthorsDOIsDataGen</main-class>
+            <arg>-d</arg><arg>${workingPath_activities}/</arg>
+            <arg>-n</arg><arg>${nameNode}</arg>
+            <arg>-f</arg><arg>ORCID_2019_activites_8.tar.gz</arg>
+            <arg>-o</arg><arg>output/authors_dois_8.seq</arg>
+        </java>
+        <ok to="join_node"/>
+        <error to="Kill"/>
+    </action>
+    
+    <decision name="check_exist_on_hdfs_activities_9">
+         <switch>
+            <case to="Gen_Orcid_Authors_DOIs_9">
+              ${fs:exists(concat(workingPath_activities,'/ORCID_2019_activites_9.tar.gz'))}
+            </case>
+            <default to="Download_9" />
+         </switch>
+	</decision>
+	
+    <action name="Download_9">
+		<shell xmlns="uri:oozie:shell-action:0.1">
+		<job-tracker>${jobTracker}</job-tracker>
+		<name-node>${nameNode}</name-node>
+		<exec>bash</exec>
+	    <argument>-c</argument>
+	    <argument>${shell_cmd_9}</argument>
+		<capture-output/>
+		</shell>
+	<ok to="Gen_Orcid_Authors_DOIs_9"/>
+	<error to="Kill"/>
+	</action>
+	
+	<action name="Gen_Orcid_Authors_DOIs_9">
+        <java>
+            <job-tracker>${jobTracker}</job-tracker>
+            <name-node>${nameNode}</name-node>
+            <main-class>eu.dnetlib.doiboost.orcid.OrcidAuthorsDOIsDataGen</main-class>
+            <arg>-d</arg><arg>${workingPath_activities}/</arg>
+            <arg>-n</arg><arg>${nameNode}</arg>
+            <arg>-f</arg><arg>ORCID_2019_activites_9.tar.gz</arg>
+            <arg>-o</arg><arg>output/authors_dois_9.seq</arg>
+        </java>
+        <ok to="join_node"/>
+        <error to="Kill"/>
+    </action>
+    
+    <decision name="check_exist_on_hdfs_activities_X">
+         <switch>
+            <case to="Gen_Orcid_Authors_DOIs_X">
+              ${fs:exists(concat(workingPath_activities,'/ORCID_2019_activites_X.tar.gz'))}
+            </case>
+            <default to="Download_X" />
+         </switch>
+	</decision>
+	
+    <action name="Download_X">
+		<shell xmlns="uri:oozie:shell-action:0.1">
+		<job-tracker>${jobTracker}</job-tracker>
+		<name-node>${nameNode}</name-node>
+		<exec>bash</exec>
+	    <argument>-c</argument>
+	    <argument>${shell_cmd_X}</argument>
+		<capture-output/>
+		</shell>
+	<ok to="Gen_Orcid_Authors_DOIs_X"/>
+	<error to="Kill"/>
+	</action>
+	
+	<action name="Gen_Orcid_Authors_DOIs_X">
+        <java>
+            <job-tracker>${jobTracker}</job-tracker>
+            <name-node>${nameNode}</name-node>
+            <main-class>eu.dnetlib.doiboost.orcid.OrcidAuthorsDOIsDataGen</main-class>
+            <arg>-d</arg><arg>${workingPath_activities}/</arg>
+            <arg>-n</arg><arg>${nameNode}</arg>
+            <arg>-f</arg><arg>ORCID_2019_activites_X.tar.gz</arg>
+            <arg>-o</arg><arg>output/authors_dois_X.seq</arg>
+        </java>
+        <ok to="join_node"/>
+        <error to="Kill"/>
+    </action>
+    
+    <join name = "join_node" to = "End"/>
+    
+   <end name="End"/>
+</workflow-app>

dhp-workflows/dhp-doiboost/src/test/java/eu/dnetlib/doiboost/orcid/xml/XMLRecordParserTest.java

@@ -3,13 +3,14 @@ package eu.dnetlib.doiboost.orcid.xml;
 import static org.junit.jupiter.api.Assertions.assertNotNull;
 
 import eu.dnetlib.doiboost.orcid.model.AuthorData;
+import eu.dnetlib.doiboost.orcid.model.WorkData;
 import org.apache.commons.io.IOUtils;
 import org.junit.jupiter.api.Test;
 
 public class XMLRecordParserTest {
 
     @Test
-    public void testOrcidXMLRecordParser() throws Exception {
+    public void testOrcidAuthorDataXMLParser() throws Exception {
 
         String xml =
                 IOUtils.toString(
@@ -17,7 +18,7 @@ public class XMLRecordParserTest {
 
         XMLRecordParser p = new XMLRecordParser();
 
-        AuthorData authorData = p.VTDParse(xml.getBytes());
+        AuthorData authorData = p.VTDParseAuthorData(xml.getBytes());
         assertNotNull(authorData);
         assertNotNull(authorData.getName());
         System.out.println("name: " + authorData.getName());
@@ -32,9 +33,27 @@ public class XMLRecordParserTest {
 
         XMLRecordParser p = new XMLRecordParser();
 
-        AuthorData authorData = p.VTDParse(xml.getBytes());
+        AuthorData authorData = p.VTDParseAuthorData(xml.getBytes());
         assertNotNull(authorData);
         assertNotNull(authorData.getErrorCode());
         System.out.println("error: " + authorData.getErrorCode());
     }
+
+    @Test
+    public void testOrcidWorkDataXMLParser() throws Exception {
+
+        String xml =
+                IOUtils.toString(
+                        this.getClass()
+                                .getResourceAsStream("activity_work_0000-0002-5982-8983.xml"));
+
+        XMLRecordParser p = new XMLRecordParser();
+
+        WorkData workData = p.VTDParseWorkData(xml.getBytes());
+        assertNotNull(workData);
+        assertNotNull(workData.getOid());
+        System.out.println("oid: " + workData.getOid());
+        assertNotNull(workData.getDoi());
+        System.out.println("doi: " + workData.getDoi());
+    }
 }

dhp-workflows/dhp-doiboost/src/test/resources/eu/dnetlib/doiboost/orcid/xml/activity_work_0000-0002-5982-8983.xml

@@ -0,0 +1,79 @@
+<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
+<work:work xmlns:address="http://www.orcid.org/ns/address"
+    xmlns:email="http://www.orcid.org/ns/email" xmlns:history="http://www.orcid.org/ns/history"
+    xmlns:employment="http://www.orcid.org/ns/employment"
+    xmlns:education="http://www.orcid.org/ns/education"
+    xmlns:other-name="http://www.orcid.org/ns/other-name"
+    xmlns:deprecated="http://www.orcid.org/ns/deprecated"
+    xmlns:funding="http://www.orcid.org/ns/funding"
+    xmlns:research-resource="http://www.orcid.org/ns/research-resource"
+    xmlns:service="http://www.orcid.org/ns/service"
+    xmlns:researcher-url="http://www.orcid.org/ns/researcher-url"
+    xmlns:distinction="http://www.orcid.org/ns/distinction"
+    xmlns:internal="http://www.orcid.org/ns/internal"
+    xmlns:membership="http://www.orcid.org/ns/membership"
+    xmlns:person="http://www.orcid.org/ns/person"
+    xmlns:personal-details="http://www.orcid.org/ns/personal-details"
+    xmlns:bulk="http://www.orcid.org/ns/bulk" xmlns:common="http://www.orcid.org/ns/common"
+    xmlns:record="http://www.orcid.org/ns/record" xmlns:keyword="http://www.orcid.org/ns/keyword"
+    xmlns:activities="http://www.orcid.org/ns/activities"
+    xmlns:qualification="http://www.orcid.org/ns/qualification"
+    xmlns:external-identifier="http://www.orcid.org/ns/external-identifier"
+    xmlns:error="http://www.orcid.org/ns/error"
+    xmlns:preferences="http://www.orcid.org/ns/preferences"
+    xmlns:invited-position="http://www.orcid.org/ns/invited-position"
+    xmlns:work="http://www.orcid.org/ns/work"
+    xmlns:peer-review="http://www.orcid.org/ns/peer-review" put-code="50101152"
+    path="/0000-0001-5349-4030/work/50101152" visibility="public">
+    <common:created-date>2018-11-01T19:49:45.562Z</common:created-date>
+    <common:last-modified-date>2018-11-01T19:49:45.562Z</common:last-modified-date>
+    <common:source>
+        <common:source-client-id>
+            <common:uri>https://orcid.org/client/0000-0002-5982-8983</common:uri>
+            <common:path>0000-0002-5982-8983</common:path>
+            <common:host>orcid.org</common:host>
+        </common:source-client-id>
+        <common:source-name>Scopus - Elsevier</common:source-name>
+    </common:source>
+    <work:title>
+        <common:title>"Calling Out" in class: Degrees of candor in addressing social injustices in
+            racially homogenous and heterogeneous U.S. history classrooms</common:title>
+    </work:title>
+    <work:journal-title>Journal of Social Studies Research</work:journal-title>
+    <work:citation>
+        <work:citation-type>bibtex</work:citation-type>
+        <work:citation-value>@article{Massaro2018,title = {{"}Calling Out{"} in class: Degrees of
+            candor in addressing social injustices in racially homogenous and heterogeneous U.S.
+            history classrooms},journal = {Journal of Social Studies Research},year = {2018},author
+            = {Parkhouse, H. and Massaro, V.R.}}</work:citation-value>
+    </work:citation>
+    <work:type>journal-article</work:type>
+    <common:publication-date>
+        <common:year>2018</common:year>
+    </common:publication-date>
+    <common:external-ids>
+        <common:external-id>
+            <common:external-id-type>doi</common:external-id-type>
+            <common:external-id-value>10.1016/j.jssr.2018.01.004</common:external-id-value>
+            <common:external-id-normalized transient="true"
+                >10.1016/j.jssr.2018.01.004</common:external-id-normalized>
+            <common:external-id-relationship>self</common:external-id-relationship>
+        </common:external-id>
+        <common:external-id>
+            <common:external-id-type>eid</common:external-id-type>
+            <common:external-id-value>2-s2.0-85041949043</common:external-id-value>
+            <common:external-id-normalized transient="true"
+                >2-s2.0-85041949043</common:external-id-normalized>
+            <common:external-id-relationship>self</common:external-id-relationship>
+        </common:external-id>
+    </common:external-ids>
+    <common:url>http://www.scopus.com/inward/record.url?eid=2-s2.0-85041949043&amp;partnerID=MN8TOARS</common:url>
+    <work:contributors>
+        <work:contributor>
+            <work:credit-name>Parkhouse, H.</work:credit-name>
+        </work:contributor>
+        <work:contributor>
+            <work:credit-name>Massaro, V.R.</work:credit-name>
+        </work:contributor>
+    </work:contributors>
+</work:work>