updated stuff for zenodo upload

This commit is contained in:
Sandro La Bruzzo 2020-11-23 14:41:38 +01:00
parent eeebd5a920
commit 264723ffd8
4 changed files with 107 additions and 95 deletions

View File

@ -42,21 +42,32 @@ class QueryTest {
}
def extractId(input:String):String = {
implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
lazy val json: json4s.JValue = parse(input)
(json \ "id").extractOrElse[String](null)
}
def myQuery(spark:SparkSession, sc:SparkContext): Unit = {
implicit val mapEncoderPub: Encoder[Publication] = Encoders.kryo[Publication]
val mapper = new ObjectMapper()
mapper.getSerializationConfig.enable(SerializationConfig.Feature.INDENT_OUTPUT)
val ds:Dataset[Publication] = spark.read.load("/tmp/p").as[Publication]
val sc = spark.sparkContext
ds.filter(p =>p.getBestaccessright!= null && p.getBestaccessright.getClassname.nonEmpty).count()
val typologies =List("dataset","datasource","organization","otherresearchproduct","project","publication","software")
val basePath ="/tt"
typologies.map(tp => sc.textFile(s"$basePath/dataset").map(s =>extractId(tp) ).distinct.count()).sum()
}

View File

@ -12,6 +12,7 @@ import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.MakeTarArchive;
public class MakeTar implements Serializable {
@ -41,71 +42,71 @@ public class MakeTar implements Serializable {
FileSystem fileSystem = FileSystem.get(conf);
makeTArArchive(fileSystem, inputPath, outputPath);
MakeTarArchive.tarMaxSize(fileSystem, inputPath, outputPath, "scholix_dump", 25);
}
public static void makeTArArchive(FileSystem fileSystem, String inputPath, String outputPath) throws IOException {
RemoteIterator<LocatedFileStatus> dir_iterator = fileSystem.listLocatedStatus(new Path(inputPath));
while (dir_iterator.hasNext()) {
LocatedFileStatus fileStatus = dir_iterator.next();
Path p = fileStatus.getPath();
String p_string = p.toString();
String entity = p_string.substring(p_string.lastIndexOf("/") + 1);
write(fileSystem, p_string, outputPath + "/" + entity + ".tar", entity);
}
}
private static void write(FileSystem fileSystem, String inputPath, String outputPath, String dir_name)
throws IOException {
Path hdfsWritePath = new Path(outputPath);
FSDataOutputStream fsDataOutputStream = null;
if (fileSystem.exists(hdfsWritePath)) {
fileSystem.delete(hdfsWritePath, true);
}
fsDataOutputStream = fileSystem.create(hdfsWritePath);
TarArchiveOutputStream ar = new TarArchiveOutputStream(fsDataOutputStream.getWrappedStream());
RemoteIterator<LocatedFileStatus> fileStatusListIterator = fileSystem
.listFiles(
new Path(inputPath), true);
while (fileStatusListIterator.hasNext()) {
LocatedFileStatus fileStatus = fileStatusListIterator.next();
Path p = fileStatus.getPath();
String p_string = p.toString();
if (!p_string.endsWith("_SUCCESS")) {
String name = p_string.substring(p_string.lastIndexOf("/") + 1);
TarArchiveEntry entry = new TarArchiveEntry(dir_name + "/" + name + ".json.gz");
entry.setSize(fileStatus.getLen());
ar.putArchiveEntry(entry);
InputStream is = fileSystem.open(fileStatus.getPath());
BufferedInputStream bis = new BufferedInputStream(is);
int count;
byte data[] = new byte[1024];
while ((count = bis.read(data, 0, data.length)) != -1) {
ar.write(data, 0, count);
}
bis.close();
ar.closeArchiveEntry();
}
}
ar.close();
}
// public static void makeTArArchive(FileSystem fileSystem, String inputPath, String outputPath) throws IOException {
//
// RemoteIterator<LocatedFileStatus> dir_iterator = fileSystem.listLocatedStatus(new Path(inputPath));
//
// while (dir_iterator.hasNext()) {
// LocatedFileStatus fileStatus = dir_iterator.next();
//
// Path p = fileStatus.getPath();
// String p_string = p.toString();
// String entity = p_string.substring(p_string.lastIndexOf("/") + 1);
//
// write(fileSystem, p_string, outputPath + "/" + entity + ".tar", entity);
// }
//
// }
//
// private static void write(FileSystem fileSystem, String inputPath, String outputPath, String dir_name)
// throws IOException {
//
// Path hdfsWritePath = new Path(outputPath);
// FSDataOutputStream fsDataOutputStream = null;
// if (fileSystem.exists(hdfsWritePath)) {
// fileSystem.delete(hdfsWritePath, true);
//
// }
// fsDataOutputStream = fileSystem.create(hdfsWritePath);
//
// TarArchiveOutputStream ar = new TarArchiveOutputStream(fsDataOutputStream.getWrappedStream());
//
// RemoteIterator<LocatedFileStatus> fileStatusListIterator = fileSystem
// .listFiles(
// new Path(inputPath), true);
//
// while (fileStatusListIterator.hasNext()) {
// LocatedFileStatus fileStatus = fileStatusListIterator.next();
//
// Path p = fileStatus.getPath();
// String p_string = p.toString();
// if (!p_string.endsWith("_SUCCESS")) {
// String name = p_string.substring(p_string.lastIndexOf("/") + 1);
// TarArchiveEntry entry = new TarArchiveEntry(dir_name + "/" + name + ".json.gz");
// entry.setSize(fileStatus.getLen());
// ar.putArchiveEntry(entry);
//
// InputStream is = fileSystem.open(fileStatus.getPath());
//
// BufferedInputStream bis = new BufferedInputStream(is);
//
// int count;
// byte data[] = new byte[1024];
// while ((count = bis.read(data, 0, data.length)) != -1) {
// ar.write(data, 0, count);
// }
// bis.close();
// ar.closeArchiveEntry();
//
// }
//
// }
//
// ar.close();
// }
}

View File

@ -73,7 +73,7 @@ public class SendToZenodoHDFS implements Serializable {
}
zenodoApiClient.sendMretadata(metadata);
zenodoApiClient.publish();
// zenodoApiClient.publish();
}

View File

@ -8,10 +8,10 @@
<name>targetPath</name>
<description>the target path</description>
</property>
<property>
<name>metadata</name>
<description>the metadata</description>
</property>
<!-- <property>-->
<!-- <name>metadata</name>-->
<!-- <description>the metadata</description>-->
<!-- </property>-->
</parameters>
<start to="send_zenodo"/>
@ -34,20 +34,20 @@
</action>
<action name="send_zenodo">
<java>
<main-class>eu.dnetlib.dhp.export.zenodo.SendToZenodoHDFS</main-class>
<arg>--hdfsPath</arg><arg>/user/dnet.scholexplorer/scholix/provision/scholix.tar/scholix-2020-10-16.tar</arg>
<arg>--nameNode</arg><arg>${nameNode}</arg>
<arg>--accessToken</arg><arg>b6ddrY6b77WxcDEevn9gqVE5sL5sDNjdUijt75W3o7cQo5vpFFI48dMiu8Gv</arg>
<arg>--connectionUrl</arg><arg>https://zenodo.org/api/deposit/depositions</arg>
<arg>--metadata</arg><arg>${metadata}</arg>
<arg>--conceptRecordId</arg><arg>1200252</arg>
<arg>--newDeposition</arg><arg>false</arg>
</java>
<ok to="End"/>
<error to="Kill"/>
</action>
<!-- <action name="send_zenodo">-->
<!-- <java>-->
<!-- <main-class>eu.dnetlib.dhp.export.zenodo.SendToZenodoHDFS</main-class>-->
<!-- <arg>&#45;&#45;hdfsPath</arg><arg>/user/dnet.scholexplorer/scholix/provision/scholix.tar/scholix-2020-10-16.tar</arg>-->
<!-- <arg>&#45;&#45;nameNode</arg><arg>${nameNode}</arg>-->
<!-- <arg>&#45;&#45;accessToken</arg><arg>b6ddrY6b77WxcDEevn9gqVE5sL5sDNjdUijt75W3o7cQo5vpFFI48dMiu8Gv</arg>-->
<!-- <arg>&#45;&#45;connectionUrl</arg><arg>https://zenodo.org/api/deposit/depositions</arg>-->
<!-- <arg>&#45;&#45;metadata</arg><arg>${metadata}</arg>-->
<!-- <arg>&#45;&#45;conceptRecordId</arg><arg>1200252</arg>-->
<!-- <arg>&#45;&#45;newDeposition</arg><arg>false</arg>-->
<!-- </java>-->
<!-- <ok to="End"/>-->
<!-- <error to="Kill"/>-->
<!-- </action>-->
<end name="End"/>
</workflow-app>