added the reader for the dump of crossref

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

@@ -0,0 +1,7 @@
+[
+  {"paramName":"n",   "paramLongName":"hdfsServerUri",	"paramDescription": "the server uri",   "paramRequired": true},
+  {"paramName":"w",   "paramLongName":"workingPath",	"paramDescription": "the default work path",	"paramRequired": true},
+  {"paramName":"f",   "paramLongName":"crossrefFileNameTarGz",	"paramDescription": "the name of the activities orcid file",	"paramRequired": true},
+  {"paramName":"issm",   "paramLongName":"isSparkSessionManaged",	"paramDescription": "the name of the activities orcid file",	"paramRequired": false}
+
+]

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

@@ -1,9 +1,9 @@
 <workflow-app name="read Crossref dump from HDFS" xmlns="uri:oozie:workflow:0.5">
     <parameters>
-        <property>
-            <name>workingPath</name>
-            <description>the working dir base path</description>
-        </property>
+<!--        <property>-->
+<!--            <name>workingPath</name>-->
+<!--            <description>the working dir base path</description>-->
+<!--        </property>-->
         <property>
             <name>sparkDriverMemory</name>
             <description>memory for driver process</description>
@@ -19,7 +19,7 @@
 
     </parameters>
 
-    <start to="SparkReadCrossRefDump"/>
+    <start to="ReadCrossRefDump"/>
 
     <kill name="Kill">
         <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
@@ -29,11 +29,10 @@
         <java>
             <job-tracker>${jobTracker}</job-tracker>
             <name-node>${nameNode}</name-node>
-            <main-class>eu.dnetlib.doiboost.crossref.CrossrefDumpReader</main-class>
-            <arg>-n</arg><arg>${nameNode}</arg>
-            <arg>-w</arg><arg>/data/doiboost/crossref/</arg>
-            <arg>-f</arg><arg>crossref.tar.gz</arg>
-            <arg>-o</arg><arg>/user/enrico.ottonello/crossref/</arg>
+            <main-class>eu.dnetlib.doiboost.crossref.ExtractCrossrefRecords</main-class>
+            <arg>--hdfsServerUri</arg><arg>${nameNode}</arg>
+            <arg>--workingPath</arg><arg>/data/doiboost/crossref/</arg>
+            <arg>--crossrefFileNameTarGz</arg><arg>crossref.tar.gz</arg>
         </java>
         <ok to="End"/>
         <error to="Kill"/>
@@ -44,7 +43,7 @@
             <master>yarn-cluster</master>
             <mode>cluster</mode>
             <name>SparkReadCrossRefDump</name>
-            <class>eu.dnetlib.doiboost.crossref.SparkExtractCrossrefRecords</class>
+            <class>eu.dnetlib.doiboost.crossref.ExtractCrossrefRecords</class>
             <jar>dhp-doiboost-${projectVersion}.jar</jar>
             <spark-opts>
                 --conf spark.dynamicAllocation.enabled=true
@@ -56,10 +55,10 @@
                 --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
                 --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
             </spark-opts>
-            <arg>-n</arg><arg>${nameNode}</arg>
-            <arg>-w</arg><arg>/data/doiboost/crossref/</arg>
-            <arg>-f</arg><arg>crossref.tar.gz</arg>
-            <arg>-o</arg><arg>/data/doiboost/crossref/</arg>
+            <arg>--hdfsServerUri</arg><arg>${nameNode}</arg>
+            <arg>--workingPath</arg><arg>/data/doiboost/crossref/</arg>
+            <arg>--crossrefFileNameTarGz</arg><arg>crossref.tar.gz</arg>
+
         </spark>
         <ok to="End"/>
         <error to="Kill"/>