D-Net
/
dnet-hadoop
14
5
Fork 11
Code Issues 14 Pull Requests 13 Projects 2 Releases 2 Wiki Activity

ORCID Enrichment and Download #364

Merged
claudio.atzori merged 14 commits from orcid_import into beta 2023-12-01 15:05:45 +01:00
Conversation 0 Commits 14 Files Changed 43 +6 -13
2 changed files with 6 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit bf0fd27c36 - Show all commits

11
dhp-common/src/main/java/eu/dnetlib/dhp/oa/merge/AuthorMerger.java
View File

@ -132,17 +132,6 @@ public class AuthorMerger {
.trim();
}
static int hammingDist(String str1, String str2) {
if (str1.length() != str2.length())
return Math.max(str1.length(), str2.length());
int i = 0, count = 0;
while (i < str1.length()) {
if (str1.charAt(i) != str2.charAt(i))
count++;
i++;
}
return count;
}
private static String authorFieldToBeCompared(Author author) {
if (StringUtils.isNotBlank(author.getSurname())) {
giambattista.bloisi commented 2023-12-01 11:08:55 +01:00
Review
Copy Link

Out of context this seems to account too much difference for strings of different length.
What about ensure to take as reference for while loop the shorter string, prefill count with the length difference and then add the char-by-char comparison difference?
That would be more permissive about strings that have the very same prefix.

Out of context this seems to account too much difference for strings of different length. What about ensure to take as reference for while loop the shorter string, prefill count with the length difference and then add the char-by-char comparison difference? That would be more permissive about strings that have the very same prefix.
sandro.labruzzo commented 2023-12-01 11:53:26 +01:00
Review
Copy Link

About hammingDist function is never used, was a test of previous comparing function so I delete it

About hammingDist function is never used, was a test of previous comparing function so I delete it

8
dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/enrich/orcid/SparkEnrichGraphWithOrcidAuthors.scala
View File

@ -2,10 +2,12 @@ package eu.dnetlib.dhp.enrich.orcid
import eu.dnetlib.dhp.application.AbstractScalaApplication
import eu.dnetlib.dhp.oa.merge.AuthorMerger
import eu.dnetlib.dhp.schema.common.ModelSupport
import eu.dnetlib.dhp.schema.oaf.{OtherResearchProduct, Publication, Result, Software}
import org.apache.spark.sql.functions._
import org.apache.spark.sql._
import org.slf4j.{Logger, LoggerFactory}
import scala.collection.JavaConverters._
class SparkEnrichGraphWithOrcidAuthors(propertyPath: String, args: Array[String], log: Logger)
extends AbstractScalaApplication(propertyPath, args, log: Logger) {
@ -21,6 +23,8 @@ class SparkEnrichGraphWithOrcidAuthors(propertyPath: String, args: Array[String]
val targetPath = parser.get("targetPath")
log.info(s"targetPath is '$targetPath'")
giambattista.bloisi commented 2023-12-01 11:22:46 +01:00
Outdated
Review
Copy Link

This can be transformed in a loop using ModelSupport.entityTypes filtering non-result types

This can be transformed in a loop using ModelSupport.entityTypes filtering non-result types
val orcidPublication: Dataset[Row] = generateOrcidTable(spark, orcidPath)
// ModelSupport.entityTypes.entrySet().asScala.filter(k => k.getKey.getClass isInstance(Result))
enrichResult(
spark,
s"$graphPath/publication",
@ -63,7 +67,7 @@ class SparkEnrichGraphWithOrcidAuthors(propertyPath: String, args: Array[String]
.schema(enc.schema)
.json(graphPath)
.select(col("id"), col("datainfo"), col("instance"))
.where("datainfo.deletedbyinference = false")
.where("datainfo.deletedbyinference != true")
.drop("datainfo")
.withColumn("instances", explode(col("instance")))
.withColumn("pids", explode(col("instances.pid")))
@ -109,7 +113,7 @@ class SparkEnrichGraphWithOrcidAuthors(propertyPath: String, args: Array[String]
.load(s"$inputPath/Works")
.select(col("orcid"), explode(col("pids")).alias("identifier"))
.where(
"identifier.schema = 'doi' or identifier.schema ='pmid' or identifier.schema ='pmc' or identifier.schema ='arxiv' or identifier.schema ='handle'"
"identifier.schema IN('doi','pmid','pmc','arxiv','handle')"
)
val orcidPublication = orcidAuthors
.join(orcidWorks, orcidAuthors("orcid").equalTo(orcidWorks("orcid")))