przemyslaw.jacewicz
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge branch 'beta' into UsageCountOnProjectAndDatasource

This commit is contained in:
Claudio Atzori 2023-02-22 09:55:51 +01:00
parent 5cf902a2b0 c20c1c9159
commit 477a7c416f
21 changed files with 2037 additions and 1589 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/GraphCleaningFunctions.java
View File

@ -13,6 +13,8 @@ import java.util.stream.Collectors;
import java.util.stream.Stream;
import org.apache.commons.lang3.StringUtils;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Encoders;
import com.github.sisyphsu.dateparser.DateParserUtils;
import com.google.common.collect.Lists;
@ -23,8 +25,6 @@ import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.*;
import me.xuender.unidecode.Unidecode;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Encoders;
public class GraphCleaningFunctions extends CleaningFunctions {

3
dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/sx/bio/ebi/SparkCreateBaselineDataFrame.scala
View File

@ -27,7 +27,8 @@ object SparkCreateBaselineDataFrame {
def requestBaseLineUpdatePage(maxFile: String): List[(String, String)] = {
val data = requestPage("https://ftp.ncbi.nlm.nih.gov/pubmed/updatefiles/")
val result = data.linesWithSeparators.map(l =>l.stripLineEnd)
val result = data.linesWithSeparators
.map(l => l.stripLineEnd)
.filter(l => l.startsWith("<a href="))
.map { l =>
val end = l.lastIndexOf("\">")

32
dhp-workflows/dhp-aggregation/src/test/scala/eu/dnetlib/dhp/sx/bio/BioScholixTest.scala
View File

@ -63,7 +63,9 @@ class BioScholixTest extends AbstractVocabularyTest {
val records: String = Source
.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/graph/bio/pubmed_dump"))
.mkString
val r: List[Oaf] = records.linesWithSeparators.map(l =>l.stripLineEnd).toList
val r: List[Oaf] = records.linesWithSeparators
.map(l => l.stripLineEnd)
.toList
.map(s => mapper.readValue(s, classOf[PMArticle]))
.map(a => PubMedToOaf.convert(a, vocabularies))
assertEquals(10, r.size)
@ -173,9 +175,10 @@ class BioScholixTest extends AbstractVocabularyTest {
val records: String = Source
.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/graph/bio/pdb_dump"))
.mkString
records.linesWithSeparators.map(l =>l.stripLineEnd).foreach(s => assertTrue(s.nonEmpty))
records.linesWithSeparators.map(l => l.stripLineEnd).foreach(s => assertTrue(s.nonEmpty))
val result: List[Oaf] = records.linesWithSeparators.map(l =>l.stripLineEnd).toList.flatMap(o => BioDBToOAF.pdbTOOaf(o))
val result: List[Oaf] =
records.linesWithSeparators.map(l => l.stripLineEnd).toList.flatMap(o => BioDBToOAF.pdbTOOaf(o))
assertTrue(result.nonEmpty)
result.foreach(r => assertNotNull(r))
@ -194,9 +197,10 @@ class BioScholixTest extends AbstractVocabularyTest {
val records: String = Source
.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/graph/bio/uniprot_dump"))
.mkString
records.linesWithSeparators.map(l =>l.stripLineEnd).foreach(s => assertTrue(s.nonEmpty))
records.linesWithSeparators.map(l => l.stripLineEnd).foreach(s => assertTrue(s.nonEmpty))
val result: List[Oaf] = records.linesWithSeparators.map(l =>l.stripLineEnd).toList.flatMap(o => BioDBToOAF.uniprotToOAF(o))
val result: List[Oaf] =
records.linesWithSeparators.map(l => l.stripLineEnd).toList.flatMap(o => BioDBToOAF.uniprotToOAF(o))
assertTrue(result.nonEmpty)
result.foreach(r => assertNotNull(r))
@ -239,9 +243,10 @@ class BioScholixTest extends AbstractVocabularyTest {
val records: String = Source
.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/graph/bio/crossref_links"))
.mkString
records.linesWithSeparators.map(l =>l.stripLineEnd).foreach(s => assertTrue(s.nonEmpty))
records.linesWithSeparators.map(l => l.stripLineEnd).foreach(s => assertTrue(s.nonEmpty))
val result: List[Oaf] = records.linesWithSeparators.map(l =>l.stripLineEnd).map(s => BioDBToOAF.crossrefLinksToOaf(s)).toList
val result: List[Oaf] =
records.linesWithSeparators.map(l => l.stripLineEnd).map(s => BioDBToOAF.crossrefLinksToOaf(s)).toList
assertNotNull(result)
assertTrue(result.nonEmpty)
@ -276,14 +281,17 @@ class BioScholixTest extends AbstractVocabularyTest {
getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/graph/bio/scholix_resolved")
)
.mkString
records.linesWithSeparators.map(l =>l.stripLineEnd).foreach(s => assertTrue(s.nonEmpty))
records.linesWithSeparators.map(l => l.stripLineEnd).foreach(s => assertTrue(s.nonEmpty))
implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
val l: List[ScholixResolved] = records.linesWithSeparators.map(l =>l.stripLineEnd).map { input =>
lazy val json = parse(input)
json.extract[ScholixResolved]
}.toList
val l: List[ScholixResolved] = records.linesWithSeparators
.map(l => l.stripLineEnd)
.map { input =>
lazy val json = parse(input)
json.extract[ScholixResolved]
}
.toList
val result: List[Oaf] = l.map(s => BioDBToOAF.scholixResolvedToOAF(s))

18
dhp-workflows/dhp-broker-events/src/main/java/eu/dnetlib/dhp/broker/oa/util/SubscriptionUtils.java
View File

@ -37,12 +37,24 @@ public class SubscriptionUtils {
}
public static boolean verifyDateRange(final long date, final String min, final String max) {
long from = 0;
long to = Long.MAX_VALUE;
try {
return date >= DateUtils.parseDate(min, "yyyy-MM-dd").getTime()
&& date < DateUtils.parseDate(max, "yyyy-MM-dd").getTime() + ONE_DAY;
from = min != null ? DateUtils.parseDate(min, "yyyy-MM-dd").getTime() : 0;
} catch (final ParseException e) {
return false;
from = 0;
}
try {
to = max != null ? DateUtils.parseDate(max, "yyyy-MM-dd").getTime() + ONE_DAY : Long.MAX_VALUE;
} catch (final ParseException e) {
to = Long.MAX_VALUE;
}
return date >= from && date < to;
}
public static boolean verifyExact(final String s1, final String s2) {

12
dhp-workflows/dhp-broker-events/src/test/java/eu/dnetlib/dhp/broker/oa/util/SubscriptionUtilsTest.java
View File

@ -41,6 +41,18 @@ public class SubscriptionUtilsTest {
assertTrue(SubscriptionUtils.verifyDateRange(date, "2010-01-01", "2011-01-01"));
assertFalse(SubscriptionUtils.verifyDateRange(date, "2020-01-01", "2021-01-01"));
assertTrue(SubscriptionUtils.verifyDateRange(date, "2010-01-01", "NULL"));
assertTrue(SubscriptionUtils.verifyDateRange(date, "2010-01-01", null));
assertTrue(SubscriptionUtils.verifyDateRange(date, "NULL", "2011-01-01"));
assertTrue(SubscriptionUtils.verifyDateRange(date, null, "2011-01-01"));
assertTrue(SubscriptionUtils.verifyDateRange(date, "NULL", "NULL"));
assertTrue(SubscriptionUtils.verifyDateRange(date, null, null));
assertFalse(SubscriptionUtils.verifyDateRange(date, "2020-01-01", null));
assertFalse(SubscriptionUtils.verifyDateRange(date, "2020-01-01", "NULL"));
assertFalse(SubscriptionUtils.verifyDateRange(date, null, "2005-01-01"));
assertFalse(SubscriptionUtils.verifyDateRange(date, "NULL", "2005-01-01"));
}
@Test

69
dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/crossref/Crossref2Oaf.scala
View File

@ -370,10 +370,50 @@ case object Crossref2Oaf {
case dataset: Dataset => convertDataset(dataset)
}
val doisReference: List[String] = for {
JObject(reference_json) <- json \ "reference"
JField("DOI", JString(doi_json)) <- reference_json
} yield doi_json
if (doisReference != null && doisReference.nonEmpty) {
val citation_relations: List[Relation] = generateCitationRelations(doisReference, result)
resultList = resultList ::: citation_relations
}
resultList = resultList ::: List(result)
resultList
}
private def createCiteRelation(source: Result, targetPid: String, targetPidType: String): List[Relation] = {
val targetId = IdentifierFactory.idFromPid("50", targetPidType, targetPid, true)
val from = new Relation
from.setSource(source.getId)
from.setTarget(targetId)
from.setRelType(ModelConstants.RESULT_RESULT)
from.setRelClass(ModelConstants.CITES)
from.setSubRelType(ModelConstants.CITATION)
from.setCollectedfrom(source.getCollectedfrom)
from.setDataInfo(source.getDataInfo)
from.setLastupdatetimestamp(source.getLastupdatetimestamp)
val to = new Relation
to.setTarget(source.getId)
to.setSource(targetId)
to.setRelType(ModelConstants.RESULT_RESULT)
to.setRelClass(ModelConstants.IS_CITED_BY)
to.setSubRelType(ModelConstants.CITATION)
to.setCollectedfrom(source.getCollectedfrom)
to.setDataInfo(source.getDataInfo)
to.setLastupdatetimestamp(source.getLastupdatetimestamp)
List(from, to)
}
def generateCitationRelations(dois: List[String], result: Result): List[Relation] = {
dois.flatMap(d => createCiteRelation(result, d, "doi"))
}
def mappingFunderToRelations(
funders: List[mappingFunder],
sourceId: String,
@ -446,6 +486,7 @@ case object Crossref2Oaf {
case "10.13039/501100000781" =>
generateSimpleRelationFromAward(funder, "corda_______", extractECAward)
generateSimpleRelationFromAward(funder, "corda__h2020", extractECAward)
generateSimpleRelationFromAward(funder, "corda_____he", extractECAward)
case "10.13039/100000001" => generateSimpleRelationFromAward(funder, "nsf_________", a => a)
case "10.13039/501100001665" => generateSimpleRelationFromAward(funder, "anr_________", a => a)
case "10.13039/501100002341" => generateSimpleRelationFromAward(funder, "aka_________", a => a)
@ -487,6 +528,34 @@ case object Crossref2Oaf {
val targetId = getProjectId("wt__________", "1e5e62235d094afd01cd56e65112fc63")
queue += generateRelation(sourceId, targetId, ModelConstants.IS_PRODUCED_BY)
queue += generateRelation(targetId, sourceId, ModelConstants.PRODUCES)
//ASAP
case "10.13039/100018231" => generateSimpleRelationFromAward(funder, "asap________", a => a)
//CHIST-ERA
case "10.13039/501100001942" =>
val targetId = getProjectId("chistera____", "1e5e62235d094afd01cd56e65112fc63")
queue += generateRelation(sourceId, targetId, ModelConstants.IS_PRODUCED_BY)
queue += generateRelation(targetId, sourceId, ModelConstants.PRODUCES)
//HE
case "10.13039/100018693" | "10.13039/100018694" | "10.13039/100019188" | "10.13039/100019180" |
"10.13039/100018695" | "10.13039/100019185" | "10.13039/100019186" | "10.13039/100019187" =>
generateSimpleRelationFromAward(funder, "corda_____he", extractECAward)
//FCT
case "10.13039/501100001871" =>
generateSimpleRelationFromAward(funder, "fct_________", extractECAward)
//NHMRC
case "10.13039/501100000925" =>
generateSimpleRelationFromAward(funder, "mhmrc_______", extractECAward)
//NIH
case "10.13039/100000002" =>
generateSimpleRelationFromAward(funder, "nih_________", extractECAward)
//NWO
case "10.13039/501100003246" =>
generateSimpleRelationFromAward(funder, "nwo_________", extractECAward)
//UKRI
case "10.13039/100014013" | "10.13039/501100000267" | "10.13039/501100000268" | "10.13039/501100000269" |
"10.13039/501100000266" | "10.13039/501100006041" | "10.13039/501100000265" | "10.13039/501100000270" |
"10.13039/501100013589" | "10.13039/501100000271" =>
generateSimpleRelationFromAward(funder, "nwo_________", extractECAward)
case _ => logger.debug("no match for " + funder.DOI.get)

3006
dhp-workflows/dhp-doiboost/src/test/resources/eu/dnetlib/doiboost/crossref/publication_license_embargo.json
View File

File diff suppressed because it is too large Load Diff

50
dhp-workflows/dhp-doiboost/src/test/scala/eu/dnetlib/dhp/doiboost/crossref/CrossrefMappingTest.scala
View File

@ -1,9 +1,14 @@
package eu.dnetlib.dhp.doiboost.crossref
import eu.dnetlib.dhp.schema.common.ModelConstants
import eu.dnetlib.dhp.schema.oaf._
import eu.dnetlib.dhp.utils.DHPUtils
import eu.dnetlib.doiboost.crossref.Crossref2Oaf
import org.codehaus.jackson.map.{ObjectMapper, SerializationConfig}
import org.json4s
import org.json4s.JsonAST.{JField, JObject, JString}
import org.json4s.{DefaultFormats, JValue}
import org.json4s.jackson.JsonMethods
import org.junit.jupiter.api.Assertions._
import org.junit.jupiter.api.Test
import org.slf4j.{Logger, LoggerFactory}
@ -31,13 +36,13 @@ class CrossrefMappingTest {
.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/funder_doi"))
.mkString
for (line <- funder_doi.linesWithSeparators.map(l =>l.stripLineEnd)) {
for (line <- funder_doi.linesWithSeparators.map(l => l.stripLineEnd)) {
val json = template.replace("%s", line)
val resultList: List[Oaf] = Crossref2Oaf.convert(json)
assertTrue(resultList.nonEmpty)
checkRelation(resultList)
}
for (line <- funder_name.linesWithSeparators.map(l =>l.stripLineEnd)) {
for (line <- funder_name.linesWithSeparators.map(l => l.stripLineEnd)) {
val json = template.replace("%s", line)
val resultList: List[Oaf] = Crossref2Oaf.convert(json)
assertTrue(resultList.nonEmpty)
@ -109,6 +114,47 @@ class CrossrefMappingTest {
}
private def parseJson(input: String): JValue = {
implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
lazy val json: json4s.JValue = JsonMethods.parse(input)
json
}
@Test
def testCitationRelations(): Unit = {
val json = Source
.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/publication_license_embargo.json"))
.mkString
assertNotNull(json)
assertFalse(json.isEmpty)
val result: List[Oaf] = Crossref2Oaf.convert(json)
assertTrue(result.nonEmpty)
val j = parseJson(json)
val doisReference: List[String] = for {
JObject(reference_json) <- j \ "reference"
JField("DOI", JString(doi_json)) <- reference_json
} yield doi_json
val relationList: List[Relation] = result
.filter(s => s.isInstanceOf[Relation])
.map(r => r.asInstanceOf[Relation])
.filter(r => r.getSubRelType.equalsIgnoreCase(ModelConstants.CITATION))
assertNotNull(relationList)
assertFalse(relationList.isEmpty)
assertEquals(doisReference.size * 2, relationList.size)
mapper.getSerializationConfig.enable(SerializationConfig.Feature.INDENT_OUTPUT)
relationList.foreach(p => println(mapper.writeValueAsString(p)))
}
@Test
def testEmptyTitle(): Unit = {
val json = Source

8
dhp-workflows/dhp-doiboost/src/test/scala/eu/dnetlib/dhp/doiboost/orcid/MappingORCIDToOAFTest.scala
View File

@ -25,9 +25,11 @@ class MappingORCIDToOAFTest {
.mkString
assertNotNull(json)
assertFalse(json.isEmpty)
json.linesWithSeparators.map(l =>l.stripLineEnd).foreach(s => {
assertNotNull(ORCIDToOAF.extractValueFromInputString(s))
})
json.linesWithSeparators
.map(l => l.stripLineEnd)
.foreach(s => {
assertNotNull(ORCIDToOAF.extractValueFromInputString(s))
})
}
@Test

4
dhp-workflows/dhp-doiboost/src/test/scala/eu/dnetlib/dhp/doiboost/uw/UnpayWallMappingTest.scala
View File

@ -22,7 +22,7 @@ class UnpayWallMappingTest {
.mkString
var i: Int = 0
for (line <- Ilist.linesWithSeparators.map(l =>l.stripLineEnd)) {
for (line <- Ilist.linesWithSeparators.map(l => l.stripLineEnd)) {
val p = UnpayWallToOAF.convertToOAF(line)
if (p != null) {
@ -43,7 +43,7 @@ class UnpayWallMappingTest {
i = i + 1
}
val l = Ilist.linesWithSeparators.map(l =>l.stripLineEnd).next()
val l = Ilist.linesWithSeparators.map(l => l.stripLineEnd).next()
val item = UnpayWallToOAF.convertToOAF(l)

41
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/clean/CleanCountryTest.java
View File

@ -5,7 +5,6 @@ import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
import eu.dnetlib.dhp.schema.oaf.Dataset;
import org.apache.commons.io.FileUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
@ -27,6 +26,7 @@ import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.oa.graph.clean.country.CleanCountrySparkJob;
import eu.dnetlib.dhp.schema.oaf.Dataset;
import eu.dnetlib.dhp.schema.oaf.Publication;
public class CleanCountryTest {
@ -151,41 +151,40 @@ public class CleanCountryTest {
@Test
public void testDatasetClean() throws Exception {
final String sourcePath = getClass()
.getResource("/eu/dnetlib/dhp/oa/graph/clean/dataset_clean_country.json")
.getPath();
.getResource("/eu/dnetlib/dhp/oa/graph/clean/dataset_clean_country.json")
.getPath();
spark
.read()
.textFile(sourcePath)
.map(
(MapFunction<String, Dataset>) r -> OBJECT_MAPPER.readValue(r, Dataset.class),
Encoders.bean(Dataset.class))
.write()
.json(workingDir.toString() + "/dataset");
.read()
.textFile(sourcePath)
.map(
(MapFunction<String, Dataset>) r -> OBJECT_MAPPER.readValue(r, Dataset.class),
Encoders.bean(Dataset.class))
.write()
.json(workingDir.toString() + "/dataset");
CleanCountrySparkJob.main(new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--inputPath", workingDir.toString() + "/dataset",
"-graphTableClassName", Dataset.class.getCanonicalName(),
"-workingDir", workingDir.toString() + "/working",
"-country", "NL",
"-verifyParam", "10.17632",
"-collectedfrom", "NARCIS",
"-hostedBy", getClass()
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--inputPath", workingDir.toString() + "/dataset",
"-graphTableClassName", Dataset.class.getCanonicalName(),
"-workingDir", workingDir.toString() + "/working",
"-country", "NL",
"-verifyParam", "10.17632",
"-collectedfrom", "NARCIS",
"-hostedBy", getClass()
.getResource("/eu/dnetlib/dhp/oa/graph/clean/hostedBy")
.getPath()
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<Dataset> tmp = sc
.textFile(workingDir.toString() + "/dataset")
.map(item -> OBJECT_MAPPER.readValue(item, Dataset.class));
.textFile(workingDir.toString() + "/dataset")
.map(item -> OBJECT_MAPPER.readValue(item, Dataset.class));
Assertions.assertEquals(1, tmp.count());
Assertions.assertEquals(0, tmp.first().getCountry().size());
}
}

8
dhp-workflows/dhp-graph-mapper/src/test/scala/eu/dnetlib/dhp/oa/graph/resolution/ResolveEntitiesTest.scala
View File

@ -53,7 +53,8 @@ class ResolveEntitiesTest extends Serializable {
def generateUpdates(spark: SparkSession): Unit = {
val template = Source.fromInputStream(this.getClass.getResourceAsStream("updates")).mkString
val pids: List[String] = template.linesWithSeparators.map(l =>l.stripLineEnd)
val pids: List[String] = template.linesWithSeparators
.map(l => l.stripLineEnd)
.map { id =>
val r = new Result
r.setId(id.toLowerCase.trim)
@ -127,7 +128,7 @@ class ResolveEntitiesTest extends Serializable {
entities.foreach { e =>
val template = Source.fromInputStream(this.getClass.getResourceAsStream(s"$e")).mkString
spark
.createDataset(spark.sparkContext.parallelize(template.linesWithSeparators.map(l =>l.stripLineEnd).toList))
.createDataset(spark.sparkContext.parallelize(template.linesWithSeparators.map(l => l.stripLineEnd).toList))
.as[String]
.write
.option("compression", "gzip")
@ -264,7 +265,8 @@ class ResolveEntitiesTest extends Serializable {
Source
.fromInputStream(this.getClass.getResourceAsStream(s"publication"))
.mkString
.linesWithSeparators.map(l =>l.stripLineEnd)
.linesWithSeparators
.map(l => l.stripLineEnd)
.next(),
classOf[Publication]
)

5
dhp-workflows/dhp-graph-mapper/src/test/scala/eu/dnetlib/dhp/sx/graph/scholix/ScholixGraphTest.scala
View File

@ -47,7 +47,7 @@ class ScholixGraphTest extends AbstractVocabularyTest {
val inputRelations = Source
.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/graph/oaf_to_summary"))
.mkString
val items = inputRelations.linesWithSeparators.map(l =>l.stripLineEnd).toList
val items = inputRelations.linesWithSeparators.map(l => l.stripLineEnd).toList
assertNotNull(items)
items.foreach(i => assertTrue(i.nonEmpty))
val result =
@ -69,7 +69,8 @@ class ScholixGraphTest extends AbstractVocabularyTest {
getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/graph/merge_result_scholix")
)
.mkString
val result: List[(Relation, ScholixSummary)] = inputRelations.linesWithSeparators.map(l =>l.stripLineEnd)
val result: List[(Relation, ScholixSummary)] = inputRelations.linesWithSeparators
.map(l => l.stripLineEnd)
.sliding(2)
.map(s => (s.head, s(1)))
.map(p => (mapper.readValue(p._1, classOf[Relation]), mapper.readValue(p._2, classOf[ScholixSummary])))

32
dhp-workflows/dhp-monitor-update/pom.xml Normal file
View File

@ -0,0 +1,32 @@
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<parent>
<artifactId>dhp-workflows</artifactId>
<groupId>eu.dnetlib.dhp</groupId>
<version>1.2.4-SNAPSHOT</version>
</parent>
<modelVersion>4.0.0</modelVersion>
<artifactId>dhp-monitor-update</artifactId>
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>pl.project13.maven</groupId>
<artifactId>git-commit-id-plugin</artifactId>
<version>2.1.11</version>
<configuration>
<failOnNoGitDirectory>false</failOnNoGitDirectory>
</configuration>
</plugin>
</plugins>
</build>
</project>

34
dhp-workflows/dhp-monitor-update/src/main/resources/eu/dnetlib/dhp/oa/graph/monitor/oozie_app/config-default.xml Normal file
View File

@ -0,0 +1,34 @@
<configuration>
<property>
<name>jobTracker</name>
<value>${jobTracker}</value>
</property>
<property>
<name>nameNode</name>
<value>${nameNode}</value>
</property>
<property>
<name>oozie.use.system.libpath</name>
<value>true</value>
</property>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>spark2</value>
</property>
<property>
<name>hive_metastore_uris</name>
<value>thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083</value>
</property>
<property>
<name>hive_jdbc_url</name>
<value>jdbc:hive2://iis-cdh5-test-m3.ocean.icm.edu.pl:10000/;UseNativeQuery=1;?spark.executor.memory=19166291558;spark.yarn.executor.memoryOverhead=3225;spark.driver.memory=11596411699;spark.yarn.driver.memoryOverhead=1228</value>
</property>
<property>
<name>oozie.wf.workflow.notification.url</name>
<value>{serviceUrl}/v1/oozieNotification/jobUpdate?jobId=$jobId%26status=$status</value>
</property>
<property>
<name>stats_tool_api_url</name>
<value>${stats_tool_api_url}</value>
</property>
</configuration>

18
dhp-workflows/dhp-monitor-update/src/main/resources/eu/dnetlib/dhp/oa/graph/monitor/oozie_app/monitor.sh Normal file
View File

@ -0,0 +1,18 @@
export PYTHON_EGG_CACHE=/home/$(whoami)/.python-eggs
export link_folder=/tmp/impala-shell-python-egg-cache-$(whoami)
if ! [ -L $link_folder ]
then
rm -Rf "$link_folder"
ln -sfn ${PYTHON_EGG_CACHE}${link_folder} ${link_folder}
fi
export SOURCE=$1
export TARGET=$2
export SCRIPT_PATH=$3
echo "Getting file from " $3
hdfs dfs -copyToLocal $3
echo "Updating monitor database"
cat createMonitorDB.sql | sed s/SOURCE/$1/g | sed s/TARGET/$2/g1 | impala-shell -f -
echo "Impala shell finished"

146
dhp-workflows/dhp-monitor-update/src/main/resources/eu/dnetlib/dhp/oa/graph/monitor/oozie_app/scripts/createMonitorDB.sql Normal file
View File

@ -0,0 +1,146 @@
DROP TABLE IF EXISTS TARGET.result_new;
create table TARGET.result_new as
select distinct * from (
select * from SOURCE.result r where exists (select 1 from SOURCE.result_organization ro where ro.id=r.id and ro.organization in (
-- 'openorgs____::b8b8ca674452579f3f593d9f5e557483', -- University College Cork
-- 'openorgs____::38d7097854736583dde879d12dacafca' -- Brown University
'openorgs____::57784c9e047e826fefdb1ef816120d92' --Arts et Métiers ParisTech
) )) foo;
COMPUTE STATS TARGET.result_new;
INSERT INTO TARGET.result select * from TARGET.result_new;
COMPUTE STATS TARGET.result;
INSERT INTO TARGET.result_citations select * from TARGET.result_citations orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_citations;
INSERT INTO TARGET.result_references_oc select * from TARGET.result_references_oc orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_references_oc;
INSERT INTO TARGET.result_citations_oc select * from TARGET.result_citations_oc orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_citations_oc;
INSERT INTO TARGET.result_classifications select * from TARGET.result_classifications orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_classifications;
INSERT INTO TARGET.result_apc select * from TARGET.result_apc orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_apc;
INSERT INTO TARGET.result_concepts select * from TARGET.result_concepts orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_concepts;
INSERT INTO TARGET.result_datasources select * from TARGET.result_datasources orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_datasources;
INSERT INTO TARGET.result_fundercount select * from TARGET.result_fundercount orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_fundercount;
INSERT INTO TARGET.result_gold select * from TARGET.result_gold orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_gold;
INSERT INTO TARGET.result_greenoa select * from TARGET.result_greenoa orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_greenoa;
INSERT INTO TARGET.result_languages select * from TARGET.result_languages orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_languages;
INSERT INTO TARGET.result_licenses select * from TARGET.result_licenses orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_licenses;
INSERT INTO TARGET.result_oids select * from TARGET.result_oids orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_oids;
INSERT INTO TARGET.result_organization select * from TARGET.result_organization orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_organization;
INSERT INTO TARGET.result_peerreviewed select * from TARGET.result_peerreviewed orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_peerreviewed;
INSERT INTO TARGET.result_pids select * from TARGET.result_pids orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_pids;
INSERT INTO TARGET.result_projectcount select * from TARGET.result_projectcount orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_projectcount;
INSERT INTO TARGET.result_projects select * from TARGET.result_projects orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_projects;
INSERT INTO TARGET.result_refereed select * from TARGET.result_refereed orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_refereed;
INSERT INTO TARGET.result_sources select * from TARGET.result_sources orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_sources;
INSERT INTO TARGET.result_topics select * from TARGET.result_topics orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_topics;
INSERT INTO TARGET.result_fos select * from TARGET.result_fos orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.result_fos;
create view TARGET.foo1 as select * from TARGET.result_result rr where rr.source in (select id from TARGET.result_new);
create view TARGET.foo2 as select * from TARGET.result_result rr where rr.target in (select id from TARGET.result_new);
INSERT INTO TARGET.result_result select distinct * from (select * from TARGET.foo1 union all select * from TARGET.foo2) foufou;
drop view TARGET.foo1;
drop view TARGET.foo2;
COMPUTE STATS TARGET.result_result;
-- indicators
-- Sprint 1 ----
INSERT INTO TARGET.indi_pub_green_oa select * from TARGET.indi_pub_green_oa orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_green_oa;
INSERT INTO TARGET.indi_pub_grey_lit select * from TARGET.indi_pub_grey_lit orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_grey_lit;
INSERT INTO TARGET.indi_pub_doi_from_crossref select * from TARGET.indi_pub_doi_from_crossref orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_doi_from_crossref;
-- Sprint 2 ----
INSERT INTO TARGET.indi_result_has_cc_licence select * from TARGET.indi_result_has_cc_licence orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_result_has_cc_licence;
INSERT INTO TARGET.indi_result_has_cc_licence_url select * from TARGET.indi_result_has_cc_licence_url orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_result_has_cc_licence_url;
INSERT INTO TARGET.indi_pub_has_abstract select * from TARGET.indi_pub_has_abstract orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_has_abstract;
INSERT INTO TARGET.indi_result_with_orcid select * from TARGET.indi_result_with_orcid orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_result_with_orcid;
---- Sprint 3 ----
INSERT INTO TARGET.indi_funded_result_with_fundref select * from TARGET.indi_funded_result_with_fundref orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_funded_result_with_fundref;
---- Sprint 4 ----
INSERT INTO TARGET.indi_pub_diamond select * from TARGET.indi_pub_diamond orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_diamond;
INSERT INTO TARGET.indi_pub_in_transformative select * from TARGET.indi_pub_in_transformative orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_in_transformative;
INSERT INTO TARGET.indi_pub_closed_other_open select * from TARGET.indi_pub_closed_other_open orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_closed_other_open;
---- Sprint 5 ----
INSERT INTO TARGET.indi_result_no_of_copies select * from TARGET.indi_result_no_of_copies orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_result_no_of_copies;
---- Sprint 6 ----
INSERT INTO TARGET.indi_pub_hybrid_oa_with_cc select * from TARGET.indi_pub_hybrid_oa_with_cc orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_hybrid_oa_with_cc;
INSERT INTO TARGET.indi_pub_downloads select * from TARGET.indi_pub_downloads orig where exists (select 1 from TARGET.result_new r where r.id=orig.result_id);
COMPUTE STATS TARGET.indi_pub_downloads;
INSERT INTO TARGET.indi_pub_downloads_datasource select * from TARGET.indi_pub_downloads_datasource orig where exists (select 1 from TARGET.result_new r where r.id=orig.result_id);
COMPUTE STATS TARGET.indi_pub_downloads_datasource;
INSERT INTO TARGET.indi_pub_downloads_year select * from TARGET.indi_pub_downloads_year orig where exists (select 1 from TARGET.result_new r where r.id=orig.result_id);
COMPUTE STATS TARGET.indi_pub_downloads_year;
INSERT INTO TARGET.indi_pub_downloads_datasource_year select * from TARGET.indi_pub_downloads_datasource_year orig where exists (select 1 from TARGET.result_new r where r.id=orig.result_id);
COMPUTE STATS TARGET.indi_pub_downloads_datasource_year;
---- Sprint 7 ----
INSERT INTO TARGET.indi_pub_gold_oa select * from TARGET.indi_pub_gold_oa orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_gold_oa;
INSERT INTO TARGET.indi_pub_hybrid select * from TARGET.indi_pub_hybrid orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_hybrid;
INSERT INTO TARGET.indi_pub_has_preprint select * from TARGET.indi_pub_has_preprint orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_has_preprint;
INSERT INTO TARGET.indi_pub_in_subscribed select * from TARGET.indi_pub_in_subscribed orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_pub_in_subscribed;
INSERT INTO TARGET.indi_result_with_pid select * from TARGET.indi_result_with_pid orig where exists (select 1 from TARGET.result_new r where r.id=orig.id);
COMPUTE STATS TARGET.indi_result_with_pid;
--create table TARGET.indi_datasets_gold_oa stored as parquet as select * from SOURCE.indi_datasets_gold_oa orig where exists (select 1 from TARGET.result r where r.id=orig.id);
--compute stats TARGET.indi_datasets_gold_oa;
--create table TARGET.indi_software_gold_oa stored as parquet as select * from SOURCE.indi_software_gold_oa orig where exists (select 1 from TARGET.result r where r.id=orig.id);
--compute stats TARGET.indi_software_gold_oa;
DROP TABLE TARGET.result_new;

77
dhp-workflows/dhp-monitor-update/src/main/resources/eu/dnetlib/dhp/oa/graph/monitor/oozie_app/workflow.xml Normal file
View File

@ -0,0 +1,77 @@
<workflow-app name="Monitor DB" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>stats_db_name</name>
<description>the target stats database name</description>
</property>
<property>
<name>stats_db_shadow_name</name>
<description>the name of the shadow schema</description>
</property>
<property>
<name>monitor_db_name</name>
<description>the target monitor db name</description>
</property>
<property>
<name>monitor_db_shadow_name</name>
<description>the name of the shadow monitor db</description>
</property>
<property>
<name>stats_tool_api_url</name>
<description>The url of the API of the stats tool. Is used to trigger the cache update.</description>
</property>
<property>
<name>hive_metastore_uris</name>
<description>hive server metastore URIs</description>
</property>
<property>
<name>hive_jdbc_url</name>
<description>hive server jdbc url</description>
</property>
<property>
<name>hive_timeout</name>
<description>the time period, in seconds, after which Hive fails a transaction if a Hive client has not sent a hearbeat. The default value is 300 seconds.</description>
</property>
<property>
<name>context_api_url</name>
<description>the base url of the context api (https://services.openaire.eu/openaire)</description>
</property>
</parameters>
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>hive.metastore.uris</name>
<value>${hive_metastore_uris}</value>
</property>
<property>
<name>hive.txn.timeout</name>
<value>${hive_timeout}</value>
</property>
</configuration>
</global>
<start to="Step1-createMonitorDB"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="Step1-createMonitorDB">
<shell xmlns="uri:oozie:shell-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<exec>monitor.sh</exec>
<argument>${stats_db_name}</argument>
<argument>${monitor_db_name}</argument>
<argument>${wf:appPath()}/scripts/createMonitorDB.sql</argument>
<file>monitor.sh</file>
</shell>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

7
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step15_5.sql
View File

@ -30,11 +30,16 @@ from rcount
group by rcount.pid;
create view ${stats_db_name}.rndexpenditure as select * from stats_ext.rndexpediture;
create view ${stats_db_name}.rndgdpexpenditure as select * from stats_ext.rndgdpexpenditure;
create view ${stats_db_name}.doctoratestudents as select * from stats_ext.doctoratestudents;
create view ${stats_db_name}.totalresearchers as select * from stats_ext.totalresearchers;
create view ${stats_db_name}.totalresearchersft as select * from stats_ext.totalresearchersft;
create view ${stats_db_name}.hrrst as select * from stats_ext.hrrst;
create table ${stats_db_name}.result_instance stored as parquet as
select distinct r.*
from (
select substr(r.id, 4) as id, inst.accessright.classname as accessright, substr(inst.collectedfrom.key, 4) as collectedfrom,
select substr(r.id, 4) as id, inst.accessright.classname as accessright, inst.accessright.openaccessroute as accessright_uw, substr(inst.collectedfrom.key, 4) as collectedfrom,
substr(inst.hostedby.key, 4) as hostedby, inst.dateofacceptance.value as dateofacceptance, inst.license.value as license, p.qualifier.classname as pidtype, p.value as pid
from ${openaire_db_name}.result r lateral view explode(r.instance) instances as inst lateral view explode(inst.pid) pids as p) r
join ${stats_db_name}.result res on res.id=r.id;

17
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step20-createMonitorDB.sql
View File

@ -10,6 +10,11 @@ create view if not exists TARGET.creation_date as select * from SOURCE.creation_
create view if not exists TARGET.funder as select * from SOURCE.funder;
create view if not exists TARGET.fundref as select * from SOURCE.fundref;
create view if not exists TARGET.rndexpenditure as select * from SOURCE.rndexpediture;
create view if not exists TARGET.rndgdpexpenditure as select * from SOURCE.rndgdpexpenditure;
create view if not exists TARGET.doctoratestudents as select * from SOURCE.doctoratestudents;
create view if not exists TARGET.totalresearchers as select * from SOURCE.totalresearchers;
create view if not exists TARGET.totalresearchersft as select * from SOURCE.totalresearchersft;
create view if not exists TARGET.hrrst as select * from SOURCE.hrrst;
create table TARGET.result stored as parquet as
select distinct * from (
@ -50,8 +55,16 @@ create table TARGET.result stored as parquet as
'openorgs____::1698a2eb1885ef8adb5a4a969e745ad3', -- École des Ponts ParisTech
'openorgs____::e15adb13c4dadd49de4d35c39b5da93a', -- Nanyang Technological University
'openorgs____::4b34103bde246228fcd837f5f1bf4212', -- Autonomous University of Barcelona
'openorgs____::72ec75fcfc4e0df1a76dc4c49007fceb' -- McMaster University
) )) foo;
'openorgs____::72ec75fcfc4e0df1a76dc4c49007fceb', -- McMaster University
'openorgs____::51c7fc556e46381734a25a6fbc3fd398', -- University of Modena and Reggio Emilia
'openorgs____::235d7f9ad18ecd7e6dc62ea4990cb9db', -- Bilkent University
'openorgs____::31f2fa9e05b49d4cf40a19c3fed8eb06', -- Saints Cyril and Methodius University of Skopje
'openorgs____::db7686f30f22cbe73a4fde872ce812a6', -- University of Milan
'openorgs____::b8b8ca674452579f3f593d9f5e557483', -- University College Cork
'openorgs____::38d7097854736583dde879d12dacafca', -- Brown University
'openorgs____::57784c9e047e826fefdb1ef816120d92', --Arts et Métiers ParisTech
'openorgs____::2530baca8a15936ba2e3297f2bce2e7e' -- University of Cape Town
))) foo;
compute stats TARGET.result;
create table TARGET.result_citations stored as parquet as select * from SOURCE.result_citations orig where exists (select 1 from TARGET.result r where r.id=orig.id);

35
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml
View File

@ -70,7 +70,40 @@
</configuration>
</global>
<start to="Step1"/>
<start to="resume_from"/>
<decision name="resume_from">
<switch>
<case to="Step1">${wf:conf('resumeFrom') eq 'Step1'}</case>
<case to="Step2">${wf:conf('resumeFrom') eq 'Step2'}</case>
<case to="Step3">${wf:conf('resumeFrom') eq 'Step3'}</case>
<case to="Step4">${wf:conf('resumeFrom') eq 'Step4'}</case>
<case to="Step5">${wf:conf('resumeFrom') eq 'Step5'}</case>
<case to="Step6">${wf:conf('resumeFrom') eq 'Step6'}</case>
<case to="Step7">${wf:conf('resumeFrom') eq 'Step7'}</case>
<case to="Step8">${wf:conf('resumeFrom') eq 'Step8'}</case>
<case to="Step9">${wf:conf('resumeFrom') eq 'Step9'}</case>
<case to="Step10">${wf:conf('resumeFrom') eq 'Step10'}</case>
<case to="Step11">${wf:conf('resumeFrom') eq 'Step11'}</case>
<case to="Step12">${wf:conf('resumeFrom') eq 'Step12'}</case>
<case to="Step13">${wf:conf('resumeFrom') eq 'Step13'}</case>
<case to="Step14">${wf:conf('resumeFrom') eq 'Step14'}</case>
<case to="Step15">${wf:conf('resumeFrom') eq 'Step15'}</case>
<case to="Step15_5">${wf:conf('resumeFrom') eq 'Step15_5'}</case>
<case to="Contexts">${wf:conf('resumeFrom') eq 'Contexts'}</case>
<case to="Step16-createIndicatorsTables">${wf:conf('resumeFrom') eq 'Step16-createIndicatorsTables'}</case>
<case to="Step16_1-definitions">${wf:conf('resumeFrom') eq 'Step16_1-definitions'}</case>
<case to="Step16_5">${wf:conf('resumeFrom') eq 'Step16_5'}</case>
<case to="Step19-finalize">${wf:conf('resumeFrom') eq 'Step19-finalize'}</case>
<case to="step20-createMonitorDB">${wf:conf('resumeFrom') eq 'step20-createMonitorDB'}</case>
<case to="step21-createObservatoryDB-pre">${wf:conf('resumeFrom') eq 'step21-createObservatoryDB-pre'}</case>
<case to="step21-createObservatoryDB">${wf:conf('resumeFrom') eq 'step21-createObservatoryDB'}</case>
<case to="step21-createObservatoryDB-post">${wf:conf('resumeFrom') eq 'step21-createObservatoryDB-post'}</case>
<case to="Step22">${wf:conf('resumeFrom') eq 'Step22'}</case>
<default to="Step1"/>
</switch>
</decision>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>