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

This commit is contained in:
Sandro La Bruzzo 2020-04-20 13:26:41 +02:00
commit 7029942e06
4 changed files with 31 additions and 49 deletions

View File

@ -1,35 +1,30 @@
package eu.dnetlib.doiboost.orcid;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.net.URI;
import java.util.Properties;
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.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
public class OrcidDSManager {
private static final Logger logger = LoggerFactory.getLogger(OrcidDSManager.class);
private String hdfsServerUri;
private String hadoopUsername;
private String hdfsOrcidDefaultPath;
private String summariesFileNameTarGz;
private String outputAuthorsPath;
public static void main(String[] args) {
public static void main(String[] args) throws IOException, Exception {
logger.info("OrcidDSManager started");
OrcidDSManager orcidDSManager = new OrcidDSManager();
try {
orcidDSManager.initGARRProperties();
orcidDSManager.generateAuthors();
} catch (Exception e) {
logger.error("Generating authors data: "+e.getMessage());
}
orcidDSManager.loadArgs(args);
orcidDSManager.generateAuthors();
}
public void generateAuthors() throws Exception {
@ -37,7 +32,7 @@ public class OrcidDSManager {
FileSystem fs = initFileSystemObject(conf);
String tarGzUri = hdfsServerUri.concat(hdfsOrcidDefaultPath).concat(summariesFileNameTarGz);
logger.info("Started parsing "+tarGzUri);
Path outputPath = new Path(hdfsServerUri.concat(hdfsOrcidDefaultPath).concat(outputAuthorsPath).concat(Long.toString(System.currentTimeMillis())).concat("/authors_part"));
Path outputPath = new Path(hdfsServerUri.concat(hdfsOrcidDefaultPath).concat(outputAuthorsPath).concat(Long.toString(System.currentTimeMillis())).concat("/authors.seq"));
SummariesDecompressor.parseGzSummaries(conf, tarGzUri, outputPath);
}
@ -49,9 +44,6 @@ public class OrcidDSManager {
// Because of Maven
conf.set("fs.hdfs.impl", org.apache.hadoop.hdfs.DistributedFileSystem.class.getName());
conf.set("fs.file.impl", org.apache.hadoop.fs.LocalFileSystem.class.getName());
// Set HADOOP user
System.setProperty("HADOOP_USER_NAME", hadoopUsername);
System.setProperty("hadoop.home.dir", "/");
return conf;
}
@ -67,33 +59,17 @@ public class OrcidDSManager {
return fs;
}
private void loadProperties() throws FileNotFoundException, IOException {
private void loadArgs(String[] args) throws IOException, Exception {
final ArgumentApplicationParser parser = new ArgumentApplicationParser(IOUtils.toString(OrcidDSManager.class.getResourceAsStream("/eu/dnetlib/dhp/doiboost/create_orcid_authors_data.json")));
parser.parseArgument(args);
Properties appProps = new Properties();
ClassLoader classLoader = ClassLoader.getSystemClassLoader();
appProps.load(classLoader.getResourceAsStream("orciddsmanager/props/app.properties"));
hdfsServerUri = appProps.getProperty("hdfs.server.uri");
hadoopUsername = appProps.getProperty("hdfs.hadoopusername");
hdfsOrcidDefaultPath = appProps.getProperty("hdfs.orcid.defaultpath");
summariesFileNameTarGz = appProps.getProperty("hdfs.orcid.summariesfilename.tar.gz");
outputAuthorsPath = appProps.getProperty("hdfs.orcid.output.authorspath");
}
private void initDefaultProperties() throws FileNotFoundException, IOException {
hdfsServerUri = "hdfs://localhost:9000";
hadoopUsername = "enrico.ottonello";
hdfsOrcidDefaultPath = "/user/enrico.ottonello/orcid/";
summariesFileNameTarGz = "ORCID_2019_summaries.tar.gz";
outputAuthorsPath = "output/";
}
private void initGARRProperties() throws FileNotFoundException, IOException {
hdfsServerUri = "hdfs://hadoop-rm1.garr-pa1.d4science.org:8020";
hadoopUsername = "root";
hdfsOrcidDefaultPath = "/data/orcid_summaries/";
summariesFileNameTarGz = "ORCID_2019_summaries.tar.gz";
outputAuthorsPath = "output/";
final String hdfsServerUri = parser.get("hdfsServerUri");
logger.info("HDFS URI: "+hdfsServerUri);
Path hdfsOrcidDefaultPath = new Path(parser.get("hdfsOrcidDefaultPath"));
logger.info("Default Path: "+hdfsOrcidDefaultPath);
final String summariesFileNameTarGz = parser.get("summariesFileNameTarGz");
logger.info("Summaries File Name: "+summariesFileNameTarGz);
final String outputAuthorsPath = parser.get("summariesFileNameTarGz");
logger.info("Output Authors Data: "+outputAuthorsPath);
}
}

View File

@ -122,14 +122,14 @@ public class SummariesDecompressor {
}
}
if ((counter % 1000) == 0) {
if ((counter % 100000) == 0) {
logger.info("Current xml records parsed: "+counter);
}
}
}
} catch (IOException e) {
logger.error("Parsing record from gzip archive: "+e.getMessage());
e.printStackTrace();
throw new RuntimeException(e);
}
logger.info("Summaries parse completed");
logger.info("Total XML records parsed: "+counter);

View File

@ -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":"summariesFileNameTarGz", "paramDescription": "the name of the summaries orcid file", "paramRequired": true},
{"paramName":"o", "paramLongName":"outputAuthorsPath", "paramDescription": "the relative folder of the sequencial file to write", "paramRequired": true}
]

View File

@ -29,10 +29,10 @@
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<main-class>eu.dnetlib.doiboost.orcid.OrcidDSManager</main-class>
<!-- ENRICO FILL THE RIGHT ARG SECTION -->
<arg>-t</arg><arg>${workingPath}/input/crossref/index_dump</arg>
<arg>-d</arg><arg>${workingPath}/</arg>
<arg>-n</arg><arg>${nameNode}</arg>
<arg>-f</arg><arg>ORCID_2019_summaries.tar.gz</arg>
<arg>-o</arg><arg>output/</arg>
</java>
<ok to="End"/>
<error to="Kill"/>