D-Net
/
dnet-hadoop
14
5
Fork 11
Code Issues 14 Pull Requests 14 Projects 2 Releases 2 Wiki Activity

affroNewModelonBeta #494

Merged
claudio.atzori merged 5 commits from affroNewModelonBeta into beta 2024-10-28 10:48:34 +01:00
Conversation 0 Commits 5 Files Changed 6 +4 -3
2 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit 2b27afaec8 - Show all commits

6
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/hive/GraphHiveTableImporterJob.java
View File

@ -72,9 +72,9 @@ public class GraphHiveTableImporterJob {
final Encoder<T> clazzEncoder = Encoders.bean(clazz); final Encoder<T> clazzEncoder = Encoders.bean(clazz);
Dataset<Row> dataset = spark Dataset<Row> dataset = spark
.read() .read()
.schema(clazzEncoder.schema()) .schema(clazzEncoder.schema())
.json(inputPath); .json(inputPath);
if (numPartitions > 0) { if (numPartitions > 0) {
log.info("repartitioning {} to {} partitions", clazz.getSimpleName(), numPartitions); log.info("repartitioning {} to {} partitions", clazz.getSimpleName(), numPartitions);

1
dhp-workflows/dhp-graph-mapper/src/test/scala/eu/dnetlib/dhp/enrich/orcid/ORCIDAuthorMatchersTest.scala
View File

@ -31,6 +31,7 @@ class ORCIDAuthorMatchersTest {
assertTrue(matchOrderedTokenAndAbbreviations("孙林 Sun Lin", "Sun Lin")) assertTrue(matchOrderedTokenAndAbbreviations("孙林 Sun Lin", "Sun Lin"))
// assertTrue(AuthorsMatchRevised.compare("孙林 Sun Lin", "孙林")); // not yet implemented // assertTrue(AuthorsMatchRevised.compare("孙林 Sun Lin", "孙林")); // not yet implemented
} }
@Test def testDocumentationNames(): Unit = { @Test def testDocumentationNames(): Unit = {
assertTrue(matchOrderedTokenAndAbbreviations("James C. A. Miller-Jones", "James Antony Miller-Jones")) assertTrue(matchOrderedTokenAndAbbreviations("James C. A. Miller-Jones", "James Antony Miller-Jones"))
} }