[OpenCitations] move the extracted contents under a backup path to avoid needing to re-download it in case of errors

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/opencitations/ReadCOCI.java

@@ -49,6 +49,9 @@ public class ReadCOCI implements Serializable {
 		final String workingPath = parser.get("inputPath");
 		log.info("workingPath {}", workingPath);
 
+		final String backupPath = parser.get("backupPath");
+		log.info("backupPath {}", backupPath);
+
 		SparkConf sconf = new SparkConf();
 
 		Configuration conf = new Configuration();
@@ -68,12 +71,14 @@ public class ReadCOCI implements Serializable {
 					workingPath,
 					fileSystem,
 					outputPath,
+					backupPath,
 					delimiter);
 			});
 	}
 
 	private static void doRead(SparkSession spark, String workingPath, FileSystem fileSystem,
 		String outputPath,
+		String backupPath,
 		String delimiter) throws IOException {
 		RemoteIterator<LocatedFileStatus> fileStatusListIterator = fileSystem
 			.listFiles(
@@ -107,7 +112,8 @@ public class ReadCOCI implements Serializable {
 				.mode(SaveMode.Append)
 				.option("compression", "gzip")
 				.json(outputPath);
-			fileSystem.rename(fileStatus.getPath(), new Path("/tmp/miriam/OC/DONE"));
+
+			fileSystem.rename(fileStatus.getPath(), new Path(backupPath));
 		}
 
 	}

dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/opencitations/input_readcoci_parameters.json

@@ -24,12 +24,19 @@
     "paramLongName": "outputPath",
     "paramDescription": "the hdfs name node",
     "paramRequired": true
-  },  {
+  },
+  {
     "paramName": "nn",
     "paramLongName": "hdfsNameNode",
     "paramDescription": "the hdfs name node",
     "paramRequired": true
-}
+  },
+  {
+    "paramName": "bp",
+    "paramLongName": "backupPath",
+    "paramDescription": "the hdfs path to move the OC data after the extraction",
+    "paramRequired": true
+  }
 ]
 
 

dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/opencitations/oozie_app/workflow.xml

@@ -129,6 +129,7 @@
             </spark-opts>
             <arg>--inputPath</arg><arg>${inputPath}/Extracted</arg>
             <arg>--outputPath</arg><arg>${inputPath}/JSON</arg>
+            <arg>--backupPath</arg><arg>${inputPath}/backup</arg>
             <arg>--delimiter</arg><arg>${delimiter}</arg>
             <arg>--hdfsNameNode</arg><arg>${nameNode}</arg>
         </spark>