1
0
Fork 0

integrated changes from discard-non-wellformed

This commit is contained in:
Claudio Atzori 2022-09-22 10:06:07 +02:00
commit 7225fe9cbe
7 changed files with 203 additions and 18 deletions

View File

@ -107,7 +107,7 @@ public abstract class AbstractMdRecordToOafMapper {
this.forceOriginalId = false; this.forceOriginalId = false;
} }
public List<Oaf> processMdRecord(final String xml) throws DocumentException { public List<Oaf> processMdRecord(final String xml) {
DocumentFactory.getInstance().setXPathNamespaceURIs(nsContext); DocumentFactory.getInstance().setXPathNamespaceURIs(nsContext);
try { try {
@ -143,7 +143,7 @@ public abstract class AbstractMdRecordToOafMapper {
return createOafs(doc, type, instances, collectedFrom, info, lastUpdateTimestamp); return createOafs(doc, type, instances, collectedFrom, info, lastUpdateTimestamp);
} catch (DocumentException e) { } catch (DocumentException e) {
log.error("Error with record:\n" + xml); log.error("Error with record:\n" + xml);
throw e; return Lists.newArrayList();
} }
} }

View File

@ -16,6 +16,9 @@ import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.spark.SparkConf; import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD; import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext; 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.apache.spark.sql.SparkSession;
import org.dom4j.DocumentException; import org.dom4j.DocumentException;
import org.slf4j.Logger; import org.slf4j.Logger;
@ -127,8 +130,8 @@ public class GenerateEntitiesApplication {
.sequenceFile(sp, Text.class, Text.class) .sequenceFile(sp, Text.class, Text.class)
.map(k -> new Tuple2<>(k._1().toString(), k._2().toString())) .map(k -> new Tuple2<>(k._1().toString(), k._2().toString()))
.map(k -> convertToListOaf(k._1(), k._2(), shouldHashId, vocs)) .map(k -> convertToListOaf(k._1(), k._2(), shouldHashId, vocs))
.filter(Objects::nonNull) .flatMap(List::iterator)
.flatMap(List::iterator)); .filter(Objects::nonNull));
} }
switch (mode) { switch (mode) {
@ -155,11 +158,11 @@ public class GenerateEntitiesApplication {
.saveAsTextFile(targetPath, GzipCodec.class); .saveAsTextFile(targetPath, GzipCodec.class);
} }
private static List<Oaf> convertToListOaf( public static List<Oaf> convertToListOaf(
final String id, final String id,
final String s, final String s,
final boolean shouldHashId, final boolean shouldHashId,
final VocabularyGroup vocs) throws DocumentException { final VocabularyGroup vocs) {
final String type = StringUtils.substringAfter(id, ":"); final String type = StringUtils.substringAfter(id, ":");
switch (type.toLowerCase()) { switch (type.toLowerCase()) {
@ -200,8 +203,7 @@ public class GenerateEntitiesApplication {
try { try {
return OBJECT_MAPPER.readValue(s, clazz); return OBJECT_MAPPER.readValue(s, clazz);
} catch (final Exception e) { } catch (final Exception e) {
log.error("Error parsing object of class: {}", clazz); log.error("Error parsing object of class: {}:\n{}", clazz, s);
log.error(s);
throw new IllegalArgumentException(e); throw new IllegalArgumentException(e);
} }
} }

View File

@ -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;
}
}

View File

@ -4,6 +4,7 @@ package eu.dnetlib.dhp.oa.graph.raw.common;
import java.io.Closeable; import java.io.Closeable;
import java.io.IOException; import java.io.IOException;
import java.util.Arrays; import java.util.Arrays;
import java.util.List;
import java.util.Set; import java.util.Set;
import java.util.concurrent.atomic.AtomicInteger; import java.util.concurrent.atomic.AtomicInteger;
import java.util.stream.Collectors; import java.util.stream.Collectors;
@ -24,8 +25,11 @@ import org.apache.http.impl.client.HttpClients;
import com.fasterxml.jackson.core.JsonProcessingException; import com.fasterxml.jackson.core.JsonProcessingException;
import com.fasterxml.jackson.databind.ObjectMapper; import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
import eu.dnetlib.dhp.oa.graph.raw.OafToOafMapper;
import eu.dnetlib.dhp.oa.graph.raw.OdfToOafMapper;
import eu.dnetlib.dhp.schema.mdstore.MDStoreWithInfo; import eu.dnetlib.dhp.schema.mdstore.MDStoreWithInfo;
import eu.dnetlib.dhp.schema.oaf.Oaf; import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.utils.DHPUtils; import eu.dnetlib.dhp.utils.DHPUtils;
public class AbstractMigrationApplication implements Closeable { public class AbstractMigrationApplication implements Closeable {

View File

@ -446,10 +446,34 @@
<join name="wait_import" to="fork_generate_entities"/> <join name="wait_import" to="fork_generate_entities"/>
<fork name="fork_generate_entities"> <fork name="fork_generate_entities">
<path start="GenerateEntities_claim"/> <path start="VerifyRecords_claim"/>
<path start="GenerateEntities"/> <path start="VerifyRecords"/>
</fork> </fork>
<action name="VerifyRecords_claim">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>VerifyRecords_claim</name>
<class>eu.dnetlib.dhp.oa.graph.raw.VerifyRecordsApplication</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory ${sparkExecutorMemory}
--executor-cores ${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePaths</arg><arg>${contentPath}/db_claims,${contentPath}/oaf_claims,${contentPath}/odf_claims</arg>
<arg>--invalidPath</arg><arg>${workingDir}/invalid_records_claim</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
</spark>
<ok to="GenerateEntities_claim"/>
<error to="Kill"/>
</action>
<action name="GenerateEntities_claim"> <action name="GenerateEntities_claim">
<spark xmlns="uri:oozie:spark-action:0.2"> <spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master> <master>yarn</master>
@ -499,6 +523,30 @@
<error to="Kill"/> <error to="Kill"/>
</action> </action>
<action name="VerifyRecords">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>VerifyRecords</name>
<class>eu.dnetlib.dhp.oa.graph.raw.VerifyRecordsApplication</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory ${sparkExecutorMemory}
--executor-cores ${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePaths</arg><arg>${contentPath}/db_openaire,${contentPath}/db_openorgs,${contentPath}/oaf_records,${contentPath}/odf_records,${contentPath}/oaf_records_hdfs,${contentPath}/odf_records_hdfs,${contentPath}/oaf_records_invisible</arg>
<arg>--invalidPath</arg><arg>${workingDir}/invalid_records</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
</spark>
<ok to="GenerateEntities"/>
<error to="Kill"/>
</action>
<action name="GenerateEntities"> <action name="GenerateEntities">
<spark xmlns="uri:oozie:spark-action:0.2"> <spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master> <master>yarn</master>

View File

@ -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
}
]

View File

@ -21,7 +21,6 @@ import org.junit.jupiter.api.extension.ExtendWith;
import org.mockito.Mock; import org.mockito.Mock;
import org.mockito.junit.jupiter.MockitoExtension; import org.mockito.junit.jupiter.MockitoExtension;
import com.fasterxml.jackson.core.JsonProcessingException;
import com.fasterxml.jackson.databind.ObjectMapper; import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup; import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
@ -722,7 +721,7 @@ class MappersTest {
assertEquals(1, p.getInstance().size()); assertEquals(1, p.getInstance().size());
assertNotNull(p.getInstance().get(0).getAlternateIdentifier()); assertNotNull(p.getInstance().get(0).getAlternateIdentifier());
assertEquals(0, p.getInstance().get(0).getAlternateIdentifier().size()); assertEquals(0, p.getInstance().get(0).getAlternateIdentifier().size());
assertEquals(1, p.getInstance().get(0).getUrl().size()); assertEquals(2, p.getInstance().get(0).getUrl().size());
} }
@Test @Test
@ -952,11 +951,9 @@ class MappersTest {
void testNotWellFormed() throws IOException { void testNotWellFormed() throws IOException {
final String xml = IOUtils final String xml = IOUtils
.toString(Objects.requireNonNull(getClass().getResourceAsStream("oaf_notwellformed.xml"))); .toString(Objects.requireNonNull(getClass().getResourceAsStream("oaf_notwellformed.xml")));
final DocumentException generalEx = new DocumentException(); final List<Oaf> actual = new OafToOafMapper(vocs, false, true).processMdRecord(xml);
assertNotNull(actual);
DocumentException exception = assertThrows(DocumentException.class, () -> { assertTrue(actual.isEmpty());
new OafToOafMapper(vocs, false, true).processMdRecord(xml);
});
} }
private void assertValidId(final String id) { private void assertValidId(final String id) {