enrico.ottonello
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

changed hadoop setting to connect to s3

This commit is contained in:
Miriam Baglioni 2020-08-04 15:37:25 +02:00
parent 5b651abf82
commit 873e9cd50c
1 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/dump/community/CommunitySplitS3.java
View File

@ -13,14 +13,15 @@ import org.apache.spark.SparkContext;
import org.apache.spark.sql.Dataset; import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.SaveMode; import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession; import org.apache.spark.sql.SparkSession;
import eu.dnetlib.dhp.oa.graph.dump.Utils;
import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
import org.slf4j.Logger; import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.oa.graph.dump.Utils;
import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
public class CommunitySplitS3 implements Serializable { public class CommunitySplitS3 implements Serializable {
private static final Logger log = LoggerFactory.getLogger(CommunitySplitS3.class); private static final Logger log = LoggerFactory.getLogger(CommunitySplitS3.class);
public void run(Boolean isSparkSessionManaged, String inputPath, String outputPath, String communityMapPath) { public void run(Boolean isSparkSessionManaged, String inputPath, String outputPath, String communityMapPath) {
// public void run(Boolean isSparkSessionManaged, String inputPath, String outputPath, CommunityMap // public void run(Boolean isSparkSessionManaged, String inputPath, String outputPath, CommunityMap
// communityMap) { // communityMap) {
@ -33,9 +34,9 @@ public class CommunitySplitS3 implements Serializable {
sc.hadoopConfiguration().set("fs.s3.impl", "org.apache.hadoop.fs.s3native.NativeS3FileSystem"); sc.hadoopConfiguration().set("fs.s3.impl", "org.apache.hadoop.fs.s3native.NativeS3FileSystem");
sc.hadoopConfiguration().set("fs.s3.awsAccessKeyId", "AK0MM6C2BYA0K1PNJYYX"); sc.hadoopConfiguration().set("fs.s3.awsAccessKeyId", "AK0MM6C2BYA0K1PNJYYX");
sc.hadoopConfiguration().set("fs.s3.awsSecretAccessKey", "fpeiqUUpKAUOtO6JWMWLTxxlSxJ+yGYwHozm3jHK"); sc.hadoopConfiguration().set("fs.s3.awsSecretAccessKey", "fpeiqUUpKAUOtO6JWMWLTxxlSxJ+yGYwHozm3jHK");
sc.hadoopConfiguration().set("fs.s3.endpoint", "s3.acm.edu.pl");
execSplit(spark, inputPath, outputPath, communityMapPath); // communityMap.keySet());// , execSplit(spark, inputPath, outputPath, communityMapPath); // communityMap.keySet());// ,
// inputClazz);
// execSplit(spark, inputPath, outputPath, communityMap.keySet());
}); });
} }