Merge branch 'beta' of https://code-repo.d4science.org/D-Net/dnet-hadoop into beta
commit
33bb79459e
@ -0,0 +1,108 @@
|
||||
|
||||
package eu.dnetlib.dhp.oa.graph.raw;
|
||||
|
||||
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||
|
||||
import java.util.Arrays;
|
||||
import java.util.List;
|
||||
import java.util.Objects;
|
||||
import java.util.Optional;
|
||||
import java.util.stream.Collectors;
|
||||
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.hadoop.io.Text;
|
||||
import org.apache.spark.SparkConf;
|
||||
import org.apache.spark.api.java.JavaSparkContext;
|
||||
import org.apache.spark.rdd.RDD;
|
||||
import org.apache.spark.sql.Encoders;
|
||||
import org.apache.spark.sql.SaveMode;
|
||||
import org.apache.spark.sql.SparkSession;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||
import eu.dnetlib.dhp.common.HdfsSupport;
|
||||
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
|
||||
import eu.dnetlib.dhp.schema.oaf.Oaf;
|
||||
import eu.dnetlib.dhp.utils.ISLookupClientFactory;
|
||||
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
|
||||
import scala.Tuple2;
|
||||
|
||||
public class VerifyRecordsApplication {
|
||||
|
||||
private static final Logger log = LoggerFactory.getLogger(VerifyRecordsApplication.class);
|
||||
|
||||
public static void main(final String[] args) throws Exception {
|
||||
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
|
||||
IOUtils
|
||||
.toString(
|
||||
VerifyRecordsApplication.class
|
||||
.getResourceAsStream("/eu/dnetlib/dhp/oa/graph/verify_records_parameters.json")));
|
||||
|
||||
parser.parseArgument(args);
|
||||
|
||||
final Boolean isSparkSessionManaged = Optional
|
||||
.ofNullable(parser.get("isSparkSessionManaged"))
|
||||
.map(Boolean::valueOf)
|
||||
.orElse(Boolean.TRUE);
|
||||
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
|
||||
|
||||
final String sourcePaths = parser.get("sourcePaths");
|
||||
log.info("sourcePaths: {}", sourcePaths);
|
||||
|
||||
final String invalidPath = parser.get("invalidPath");
|
||||
log.info("invalidPath: {}", invalidPath);
|
||||
|
||||
final String isLookupUrl = parser.get("isLookupUrl");
|
||||
log.info("isLookupUrl: {}", isLookupUrl);
|
||||
|
||||
final ISLookUpService isLookupService = ISLookupClientFactory.getLookUpService(isLookupUrl);
|
||||
final VocabularyGroup vocs = VocabularyGroup.loadVocsFromIS(isLookupService);
|
||||
|
||||
final SparkConf conf = new SparkConf();
|
||||
runWithSparkSession(conf, isSparkSessionManaged, spark -> {
|
||||
HdfsSupport.remove(invalidPath, spark.sparkContext().hadoopConfiguration());
|
||||
validateRecords(spark, sourcePaths, invalidPath, vocs);
|
||||
});
|
||||
}
|
||||
|
||||
private static void validateRecords(SparkSession spark, String sourcePaths, String invalidPath,
|
||||
VocabularyGroup vocs) {
|
||||
|
||||
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
|
||||
final List<String> existingSourcePaths = Arrays
|
||||
.stream(sourcePaths.split(","))
|
||||
.filter(p -> HdfsSupport.exists(p, sc.hadoopConfiguration()))
|
||||
.collect(Collectors.toList());
|
||||
|
||||
log.info("Verify records in files:");
|
||||
existingSourcePaths.forEach(log::info);
|
||||
|
||||
for (final String sp : existingSourcePaths) {
|
||||
RDD<String> invalidRecords = sc
|
||||
.sequenceFile(sp, Text.class, Text.class)
|
||||
.map(k -> tryApplyMapping(k._1().toString(), k._2().toString(), true, vocs))
|
||||
.filter(Objects::nonNull)
|
||||
.rdd();
|
||||
spark
|
||||
.createDataset(invalidRecords, Encoders.STRING())
|
||||
.write()
|
||||
.mode(SaveMode.Append)
|
||||
.option("compression", "gzip")
|
||||
.text(invalidPath);
|
||||
}
|
||||
}
|
||||
|
||||
private static String tryApplyMapping(
|
||||
final String id,
|
||||
final String xmlRecord,
|
||||
final boolean shouldHashId,
|
||||
final VocabularyGroup vocs) {
|
||||
|
||||
final List<Oaf> oaf = GenerateEntitiesApplication.convertToListOaf(id, xmlRecord, shouldHashId, vocs);
|
||||
if (Optional.ofNullable(oaf).map(List::isEmpty).orElse(false)) {
|
||||
return xmlRecord;
|
||||
}
|
||||
return null;
|
||||
}
|
||||
}
|
||||
@ -0,0 +1,26 @@
|
||||
[
|
||||
{
|
||||
"paramName": "issm",
|
||||
"paramLongName": "isSparkSessionManaged",
|
||||
"paramDescription": "when true will stop SparkSession after job execution",
|
||||
"paramRequired": false
|
||||
},
|
||||
{
|
||||
"paramName": "s",
|
||||
"paramLongName": "sourcePaths",
|
||||
"paramDescription": "the HDFS source paths which contains the sequential file (comma separated)",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "i",
|
||||
"paramLongName": "invalidPath",
|
||||
"paramDescription": "the path of the invalid records file",
|
||||
"paramRequired": false
|
||||
},
|
||||
{
|
||||
"paramName": "isu",
|
||||
"paramLongName": "isLookupUrl",
|
||||
"paramDescription": "the url of the ISLookupService",
|
||||
"paramRequired": true
|
||||
}
|
||||
]
|
||||
@ -0,0 +1,70 @@
|
||||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<record xmlns:dc="http://purl.org/dc/elements/1.1/"
|
||||
xmlns:dr="http://www.driver-repository.eu/namespace/dr"
|
||||
xmlns:dri="http://www.driver-repository.eu/namespace/dri"
|
||||
xmlns:oaf="http://namespace.openaire.eu/oaf"
|
||||
xmlns:oai="http://www.openarchives.org/OAI/2.0/"
|
||||
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
|
||||
<header xmlns="http://namespace.openaire.eu/">
|
||||
<dri:objIdentifier>jairo_______::000012e58ed836576ef2a0d38b0f726f</dri:objIdentifier>
|
||||
<dri:recordIdentifier>oai:irdb.nii.ac.jp:01221:0000010198</dri:recordIdentifier>
|
||||
<dri:dateOfCollection/>
|
||||
<dri:mdFormat/>
|
||||
<dri:mdFormatInterpretation/>
|
||||
<dri:repositoryId/>
|
||||
<dr:objectIdentifier/>
|
||||
<dr:dateOfCollection>2021-05-10T11:31:09.424Z</dr:dateOfCollection>
|
||||
<dr:dateOfTransformation>2021-06-03T01:45:42.536Z</dr:dateOfTransformation>
|
||||
<oaf:datasourceprefix>jairo_______</oaf:datasourceprefix>
|
||||
</header>
|
||||
<metadata xmlns="http://namespace.openaire.eu/">
|
||||
<dc:title>多項式GCDを用いた復号法に関する研究<dc:title>
|
||||
<dc:creator>上原, 剛</dc:creator>
|
||||
<dc:creator>甲斐, 博</dc:creator>
|
||||
<dc:creator>野田, 松太郎</dc:creator>
|
||||
<dc:format>application/pdf</dc:format>
|
||||
<dc:identifier>http://hdl.handle.net/2433/25934</dc:identifier>
|
||||
<dc:language>jpn</dc:language>
|
||||
<dc:publisher>京都大学数理解析研究所</dc:publisher>
|
||||
<dc:subject classid="ndc" classname="ndc"
|
||||
schemeid="dnet:subject_classification_typologies" schemename="dnet:subject_classification_typologies">410</dc:subject>
|
||||
<dc:type>Departmental Bulletin Paper</dc:type>
|
||||
<dr:CobjCategory type="publication">0014</dr:CobjCategory>
|
||||
<oaf:dateAccepted>2004-10-01</oaf:dateAccepted>
|
||||
<oaf:projectid/>
|
||||
<oaf:collectedDatasourceid>openaire____::554c7c2873</oaf:collectedDatasourceid>
|
||||
<oaf:accessrights>OPEN</oaf:accessrights>
|
||||
<oaf:hostedBy id="openaire____::554c7c2873" name="JAIRO"/>
|
||||
<oaf:collectedFrom id="openaire____::554c7c2873" name="JAIRO"/>
|
||||
<oaf:identifier identifierType="handle">2433/25934</oaf:identifier>
|
||||
<oaf:identifier identifierType="ncid">AN00061013</oaf:identifier>
|
||||
<oaf:identifier identifierType="LandingPage">http://hdl.handle.net/2433/25934</oaf:identifier>
|
||||
<oaf:fulltext>http://repository.kulib.kyoto-u.ac.jp/dspace/bitstream/2433/25934/1/1395-16.pdf</oaf:fulltext>
|
||||
<oaf:journal ep="110" iss="" issn="1880-2818" sp="104" vol="1395">数理解析研究所講究録</oaf:journal>
|
||||
</metadata>
|
||||
<about>
|
||||
<provenance xmlns="http://www.openarchives.org/OAI/2.0/provenance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/provenance http://www.openarchives.org/OAI/2.0/provenance.xsd">
|
||||
<originDescription altered="true" harvestDate="2021-05-10T11:31:09.424Z">
|
||||
<baseURL>https%3A%2F%2Firdb.nii.ac.jp%2Foai</baseURL>
|
||||
<identifier>oai:irdb.nii.ac.jp:01221:0000010198</identifier>
|
||||
<datestamp>2021-04-13T13:36:29Z</datestamp>
|
||||
<metadataNamespace/>
|
||||
<originDescription altered="true" harvestDate="2021-04-13T13:36:29Z">
|
||||
<baseURL>http://repository.kulib.kyoto-u.ac.jp/dspace-oai/request</baseURL>
|
||||
<identifier>oai:repository.kulib.kyoto-u.ac.jp:2433/25934</identifier>
|
||||
<datestamp>2012-07-12T14:15:41Z</datestamp>
|
||||
<metadataNamespace>http://irdb.nii.ac.jp/oai</metadataNamespace>
|
||||
</originDescription>
|
||||
</originDescription>
|
||||
</provenance>
|
||||
<oaf:datainfo>
|
||||
<oaf:inferred>false</oaf:inferred>
|
||||
<oaf:deletedbyinference>false</oaf:deletedbyinference>
|
||||
<oaf:trust>0.9</oaf:trust>
|
||||
<oaf:inferenceprovenance/>
|
||||
<oaf:provenanceaction classid="sysimport:crosswalk:repository"
|
||||
classname="sysimport:crosswalk:repository"
|
||||
schemeid="dnet:provenanceActions" schemename="dnet:provenanceActions"/>
|
||||
</oaf:datainfo>
|
||||
</about>
|
||||
</record>
|
||||
@ -0,0 +1,8 @@
|
||||
# Root logger option
|
||||
log4j.rootLogger=DEBUG, stdout
|
||||
|
||||
# Direct log messages to stdout
|
||||
log4j.appender.stdout=org.apache.log4j.ConsoleAppender
|
||||
log4j.appender.stdout.Target=System.out
|
||||
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
|
||||
log4j.appender.stdout.layout.ConversionPattern=%d{yyyy-MM-dd HH:mm:ss} %-5p %c{1}:%L - %m%n
|
||||
Loading…
Reference in New Issue