dimitris.pierrakos
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Pull Requests Activity

WIP: error handling during XSLT transformation

This commit is contained in:
Claudio Atzori 2022-09-29 11:05:43 +02:00
parent f0a9c370b6
commit a2095dc725
2 changed files with 26 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/transformation/TransformSparkJobNode.java
View File

@ -77,11 +77,11 @@ public class TransformSparkJobNode {
.ofNullable(parser.get("recordsPerTask")) .ofNullable(parser.get("recordsPerTask"))
.map(Integer::valueOf) .map(Integer::valueOf)
.orElse(RECORDS_PER_TASK); .orElse(RECORDS_PER_TASK);
log.info("recordsPerTask: {}", rpt);
final ISLookUpService isLookupService = ISLookupClientFactory.getLookUpService(isLookupUrl); final ISLookUpService isLookupService = ISLookupClientFactory.getLookUpService(isLookupUrl);
final VocabularyGroup vocabularies = VocabularyGroup.loadVocsFromIS(isLookupService); final VocabularyGroup vocabularies = VocabularyGroup.loadVocsFromIS(isLookupService);
log.info("Retrieved {} vocabularies", vocabularies.vocabularyNames().size()); log.info("Retrieved {} vocabularies", vocabularies.vocabularyNames().size());
SparkConf conf = new SparkConf(); SparkConf conf = new SparkConf();
@ -120,7 +120,6 @@ public class TransformSparkJobNode {
final MessageSender messageSender = new MessageSender(dnetMessageManagerURL, workflowId); final MessageSender messageSender = new MessageSender(dnetMessageManagerURL, workflowId);
try (AggregatorReport report = new AggregatorReport(messageSender)) { try (AggregatorReport report = new AggregatorReport(messageSender)) {
try {
final MapFunction<MetadataRecord, MetadataRecord> tr = TransformationFactory final MapFunction<MetadataRecord, MetadataRecord> tr = TransformationFactory
.getTransformationPlugin(args, ct, report, isLookUpService); .getTransformationPlugin(args, ct, report, isLookUpService);
@ -139,14 +138,6 @@ public class TransformSparkJobNode {
writeHdfsFile( writeHdfsFile(
spark.sparkContext().hadoopConfiguration(), spark.sparkContext().hadoopConfiguration(),
"" + mdStoreSize, outputBasePath + MDSTORE_SIZE_PATH); "" + mdStoreSize, outputBasePath + MDSTORE_SIZE_PATH);
} catch (Throwable e) {
log.error("error during record transformation", e);
report.put(e.getClass().getName(), e.getMessage());
report.put(CONTENT_TOTALITEMS, ct.getTotalItems().value().toString());
report.put(CONTENT_INVALIDRECORDS, ct.getErrorItems().value().toString());
report.put(CONTENT_TRANSFORMEDRECORDS, ct.getProcessedItems().value().toString());
throw e;
}
} }
} }

11
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/transformation/xslt/XSLTTransformationFunction.java
View File

@ -1,6 +1,9 @@
package eu.dnetlib.dhp.transformation.xslt; package eu.dnetlib.dhp.transformation.xslt;
import static eu.dnetlib.dhp.common.Constants.*;
import java.io.IOException;
import java.io.Serializable; import java.io.Serializable;
import java.io.StringWriter; import java.io.StringWriter;
import java.nio.charset.StandardCharsets; import java.nio.charset.StandardCharsets;
@ -70,7 +73,13 @@ public class XSLTTransformationFunction implements MapFunction<MetadataRecord, M
.compile(new StreamSource(IOUtils.toInputStream(transformationRule, StandardCharsets.UTF_8))) .compile(new StreamSource(IOUtils.toInputStream(transformationRule, StandardCharsets.UTF_8)))
.load(); .load();
} catch (SaxonApiException e) { } catch (SaxonApiException e) {
throw new RuntimeException(e); report.put(e.getClass().getName(), e.getMessage());
try {
report.close();
} catch (IOException ex) {
throw new IllegalArgumentException("error compiling the XSLT", e);
}
throw new IllegalArgumentException("error compiling the XSLT", e);
} }
transformer transformer