master #59

Closed
claudio.atzori wants to merge 3221 commits from master into stable_ids
3 changed files with 367 additions and 209 deletions
Showing only changes of commit 9a961a0092 - Show all commits

View File

@ -1,16 +1,13 @@
package eu.dnetlib.dhp.oa.graph.clean; package eu.dnetlib.dhp.oa.graph.clean;
import com.fasterxml.jackson.databind.ObjectMapper; import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport; import java.io.Serializable;
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup; import java.util.List;
import eu.dnetlib.dhp.schema.common.ModelConstants; import java.util.Optional;
import eu.dnetlib.dhp.schema.oaf.Context; import java.util.stream.Collectors;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.utils.ISLookupClientFactory;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
import org.apache.commons.io.IOUtils; import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf; import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.MapFunction; import org.apache.spark.api.java.function.MapFunction;
@ -21,12 +18,18 @@ import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger; import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;
import java.io.Serializable; import com.fasterxml.jackson.databind.ObjectMapper;
import java.util.List;
import java.util.Optional;
import java.util.stream.Collectors;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Context;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.utils.ISLookupClientFactory;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
public class CleanContextSparkJob implements Serializable { public class CleanContextSparkJob implements Serializable {
private static final Logger log = LoggerFactory.getLogger(CleanContextSparkJob.class); private static final Logger log = LoggerFactory.getLogger(CleanContextSparkJob.class);
@ -61,13 +64,11 @@ public class CleanContextSparkJob implements Serializable {
String verifyParam = parser.get("verifyParam"); String verifyParam = parser.get("verifyParam");
log.info("verifyParam: {}", verifyParam); log.info("verifyParam: {}", verifyParam);
String graphTableClassName = parser.get("graphTableClassName"); String graphTableClassName = parser.get("graphTableClassName");
log.info("graphTableClassName: {}", graphTableClassName); log.info("graphTableClassName: {}", graphTableClassName);
Class<? extends Result> entityClazz = (Class<? extends Result>) Class.forName(graphTableClassName); Class<? extends Result> entityClazz = (Class<? extends Result>) Class.forName(graphTableClassName);
SparkConf conf = new SparkConf(); SparkConf conf = new SparkConf();
runWithSparkSession( runWithSparkSession(
conf, conf,
@ -78,7 +79,8 @@ public class CleanContextSparkJob implements Serializable {
}); });
} }
private static <T extends Result> void cleanContext(SparkSession spark, String contextId, String verifyParam, String inputPath, Class<T> entityClazz, String workingPath) { private static <T extends Result> void cleanContext(SparkSession spark, String contextId, String verifyParam,
String inputPath, Class<T> entityClazz, String workingPath) {
Dataset<T> res = spark Dataset<T> res = spark
.read() .read()
.textFile(inputPath) .textFile(inputPath)
@ -87,27 +89,42 @@ public class CleanContextSparkJob implements Serializable {
Encoders.bean(entityClazz)); Encoders.bean(entityClazz));
res.map((MapFunction<T, T>) r -> { res.map((MapFunction<T, T>) r -> {
if(!r.getTitle() if (!r
.getTitle()
.stream() .stream()
.filter(t -> t.getQualifier().getClassid() .filter(
t -> t
.getQualifier()
.getClassid()
.equalsIgnoreCase(ModelConstants.MAIN_TITLE_QUALIFIER.getClassid())) .equalsIgnoreCase(ModelConstants.MAIN_TITLE_QUALIFIER.getClassid()))
.anyMatch(t -> t.getValue().toLowerCase().startsWith(verifyParam.toLowerCase()))){ .anyMatch(t -> t.getValue().toLowerCase().startsWith(verifyParam.toLowerCase()))) {
return r; return r;
} }
r.setContext(r.getContext().stream().filter(c -> !c.getId().split("::")[0] r
.equalsIgnoreCase(contextId)).collect(Collectors.toList())); .setContext(
r
.getContext()
.stream()
.filter(
c -> !c.getId().split("::")[0]
.equalsIgnoreCase(contextId))
.collect(Collectors.toList()));
return r; return r;
} ,Encoders.bean(entityClazz)) }, Encoders.bean(entityClazz))
.write() .write()
.mode(SaveMode.Overwrite) .mode(SaveMode.Overwrite)
.option("compression","gzip") .option("compression", "gzip")
.json(workingPath); .json(workingPath);
spark.read().textFile(workingPath).map((MapFunction<String, T>) value -> OBJECT_MAPPER.readValue(value, entityClazz), spark
.read()
.textFile(workingPath)
.map(
(MapFunction<String, T>) value -> OBJECT_MAPPER.readValue(value, entityClazz),
Encoders.bean(entityClazz)) Encoders.bean(entityClazz))
.write() .write()
.mode(SaveMode.Overwrite) .mode(SaveMode.Overwrite)
.option("compression","gzip") .option("compression", "gzip")
.json(inputPath); .json(inputPath);
} }
} }

View File

@ -15,7 +15,7 @@
</property> </property>
<property> <property>
<name>shouldCleanContext</name> <name>shouldCleanContext</name>
<value>false</value> <description>true if the context have to be cleaned</description>
</property> </property>
<property> <property>
@ -312,9 +312,9 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680 --conf spark.sql.shuffle.partitions=7680
</spark-opts> </spark-opts>
<arg>--inputPath</arg><arg>${inputPath}/publication</arg> <arg>--inputPath</arg><arg>${graphOutputPath}/publication</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg> <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
<arg>--workingPath</arg><arg>${workingDir}/working</arg> <arg>--workingPath</arg><arg>${workingDir}/working/publication</arg>
<arg>--contextId</arg><arg>${contextId}</arg> <arg>--contextId</arg><arg>${contextId}</arg>
<arg>--verifyParam</arg><arg>${verifyParam}</arg> <arg>--verifyParam</arg><arg>${verifyParam}</arg>
</spark> </spark>
@ -339,9 +339,9 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680 --conf spark.sql.shuffle.partitions=7680
</spark-opts> </spark-opts>
<arg>--inputPath</arg><arg>${graphInputPath}/dataset</arg> <arg>--inputPath</arg><arg>${graphOutputPath}/dataset</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg> <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
<arg>--workingPath</arg><arg>${workingDir}/working</arg> <arg>--workingPath</arg><arg>${workingDir}/working/dataset</arg>
<arg>--contextId</arg><arg>${contextId}</arg> <arg>--contextId</arg><arg>${contextId}</arg>
<arg>--verifyParam</arg><arg>${verifyParam}</arg> <arg>--verifyParam</arg><arg>${verifyParam}</arg>
</spark> </spark>
@ -366,9 +366,9 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680 --conf spark.sql.shuffle.partitions=7680
</spark-opts> </spark-opts>
<arg>--inputPath</arg><arg>${graphInputPath}/otherresearchproduct</arg> <arg>--inputPath</arg><arg>${graphOutputPath}/otherresearchproduct</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg> <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
<arg>--workingPath</arg><arg>${workingDir}/working</arg> <arg>--workingPath</arg><arg>${workingDir}/working/otherresearchproduct</arg>
<arg>--contextId</arg><arg>${contextId}</arg> <arg>--contextId</arg><arg>${contextId}</arg>
<arg>--verifyParam</arg><arg>${verifyParam}</arg> <arg>--verifyParam</arg><arg>${verifyParam}</arg>
</spark> </spark>
@ -393,9 +393,9 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680 --conf spark.sql.shuffle.partitions=7680
</spark-opts> </spark-opts>
<arg>--inputPath</arg><arg>${graphInputPath}/software</arg> <arg>--inputPath</arg><arg>${graphOutputPath}/software</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg> <arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
<arg>--workingPath</arg><arg>${workingDir}/working</arg> <arg>--workingPath</arg><arg>${workingDir}/working/software</arg>
<arg>--contextId</arg><arg>${contextId}</arg> <arg>--contextId</arg><arg>${contextId}</arg>
<arg>--verifyParam</arg><arg>${verifyParam}</arg> <arg>--verifyParam</arg><arg>${verifyParam}</arg>
</spark> </spark>

View File

@ -1,18 +1,12 @@
package eu.dnetlib.dhp.oa.graph.clean; package eu.dnetlib.dhp.oa.graph.clean;
import com.fasterxml.jackson.core.JsonProcessingException; import java.io.IOException;
import com.fasterxml.jackson.databind.ObjectMapper; import java.nio.file.Files;
import eu.dnetlib.dhp.oa.graph.dump.Constants; import java.nio.file.Path;
import eu.dnetlib.dhp.oa.graph.dump.DumpJobTest; import java.util.List;
import eu.dnetlib.dhp.oa.graph.dump.DumpProducts; import java.util.Locale;
import eu.dnetlib.dhp.oa.graph.dump.community.CommunityMap;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.dump.oaf.Instance;
import eu.dnetlib.dhp.schema.dump.oaf.OpenAccessRoute;
import eu.dnetlib.dhp.schema.dump.oaf.graph.GraphResult;
import eu.dnetlib.dhp.schema.oaf.Publication;
import eu.dnetlib.dhp.schema.oaf.Software;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
import org.apache.commons.io.FileUtils; import org.apache.commons.io.FileUtils;
import org.apache.spark.SparkConf; import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD; import org.apache.spark.api.java.JavaRDD;
@ -27,11 +21,20 @@ import org.junit.jupiter.api.Test;
import org.slf4j.Logger; import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;
import java.io.IOException; import com.fasterxml.jackson.core.JsonProcessingException;
import java.nio.file.Files; import com.fasterxml.jackson.databind.ObjectMapper;
import java.nio.file.Path;
import java.util.List; import eu.dnetlib.dhp.oa.graph.dump.Constants;
import java.util.Locale; import eu.dnetlib.dhp.oa.graph.dump.DumpJobTest;
import eu.dnetlib.dhp.oa.graph.dump.DumpProducts;
import eu.dnetlib.dhp.oa.graph.dump.community.CommunityMap;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.dump.oaf.Instance;
import eu.dnetlib.dhp.schema.dump.oaf.OpenAccessRoute;
import eu.dnetlib.dhp.schema.dump.oaf.graph.GraphResult;
import eu.dnetlib.dhp.schema.oaf.Publication;
import eu.dnetlib.dhp.schema.oaf.Software;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
public class CleanContextTest { public class CleanContextTest {
@ -78,18 +81,22 @@ public class CleanContextTest {
.getPath(); .getPath();
final String prefix = "gcube "; final String prefix = "gcube ";
spark
spark.read().textFile(sourcePath).map((MapFunction<String, Publication>) r -> OBJECT_MAPPER.readValue(r, Publication.class), Encoders.bean(Publication.class)) .read()
.write().json(workingDir.toString() + "/publication"); .textFile(sourcePath)
.map(
(MapFunction<String, Publication>) r -> OBJECT_MAPPER.readValue(r, Publication.class),
Encoders.bean(Publication.class))
.write()
.json(workingDir.toString() + "/publication");
CleanContextSparkJob.main(new String[] { CleanContextSparkJob.main(new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(), "--isSparkSessionManaged", Boolean.FALSE.toString(),
"--inputPath", workingDir.toString() + "/publication", "--inputPath", workingDir.toString() + "/publication",
"-graphTableClassName", Publication.class.getCanonicalName(), "-graphTableClassName", Publication.class.getCanonicalName(),
"-workingPath", workingDir.toString() + "/working", "-workingPath", workingDir.toString() + "/working",
"-contextId","sobigdata", "-contextId", "sobigdata",
"-verifyParam","gCube " "-verifyParam", "gCube "
}); });
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext()); final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
@ -99,61 +106,195 @@ public class CleanContextTest {
Assertions.assertEquals(7, tmp.count()); Assertions.assertEquals(7, tmp.count());
//original result with sobigdata context and gcube as starting string in the main title for the publication // original result with sobigdata context and gcube as starting string in the main title for the publication
Assertions.assertEquals(0, Assertions
tmp.filter(p->p.getId().equals("50|DansKnawCris::0224aae28af558f21768dbc6439c7a95")).collect().get(0).getContext().size()); .assertEquals(
0,
tmp
.filter(p -> p.getId().equals("50|DansKnawCris::0224aae28af558f21768dbc6439c7a95"))
.collect()
.get(0)
.getContext()
.size());
//original result with sobigdata context without gcube as starting string in the main title for the publication // original result with sobigdata context without gcube as starting string in the main title for the publication
Assertions.assertEquals(1, Assertions
tmp.filter(p->p.getId().equals("50|DansKnawCris::20c414a3b1c742d5dd3851f1b67df2d9")).collect().get(0).getContext().size()); .assertEquals(
Assertions.assertEquals("sobigdata::projects::2",tmp.filter(p->p.getId().equals("50|DansKnawCris::20c414a3b1c742d5dd3851f1b67df2d9")).collect().get(0).getContext().get(0).getId() ); 1,
tmp
.filter(p -> p.getId().equals("50|DansKnawCris::20c414a3b1c742d5dd3851f1b67df2d9"))
.collect()
.get(0)
.getContext()
.size());
Assertions
.assertEquals(
"sobigdata::projects::2",
tmp
.filter(p -> p.getId().equals("50|DansKnawCris::20c414a3b1c742d5dd3851f1b67df2d9"))
.collect()
.get(0)
.getContext()
.get(0)
.getId());
//original result with sobigdata context with gcube as starting string in the subtitle // original result with sobigdata context with gcube as starting string in the subtitle
Assertions.assertEquals(1, Assertions
tmp.filter(p->p.getId().equals("50|DansKnawCris::3c81248c335f0aa07e06817ece6fa6af")).collect().get(0).getContext().size()); .assertEquals(
Assertions.assertEquals("sobigdata::projects::2",tmp.filter(p->p.getId().equals("50|DansKnawCris::3c81248c335f0aa07e06817ece6fa6af")).collect().get(0).getContext().get(0).getId() ); 1,
List<StructuredProperty> titles = tmp.filter(p -> p.getId().equals("50|DansKnawCris::3c81248c335f0aa07e06817ece6fa6af")).collect().get(0).getTitle(); tmp
.filter(p -> p.getId().equals("50|DansKnawCris::3c81248c335f0aa07e06817ece6fa6af"))
.collect()
.get(0)
.getContext()
.size());
Assertions
.assertEquals(
"sobigdata::projects::2",
tmp
.filter(p -> p.getId().equals("50|DansKnawCris::3c81248c335f0aa07e06817ece6fa6af"))
.collect()
.get(0)
.getContext()
.get(0)
.getId());
List<StructuredProperty> titles = tmp
.filter(p -> p.getId().equals("50|DansKnawCris::3c81248c335f0aa07e06817ece6fa6af"))
.collect()
.get(0)
.getTitle();
Assertions.assertEquals(1, titles.size()); Assertions.assertEquals(1, titles.size());
Assertions.assertTrue(titles.get(0).getValue().toLowerCase().startsWith(prefix) ); Assertions.assertTrue(titles.get(0).getValue().toLowerCase().startsWith(prefix));
Assertions.assertEquals("subtitle", titles.get(0).getQualifier().getClassid()); Assertions.assertEquals("subtitle", titles.get(0).getQualifier().getClassid());
//original result with sobigdata context with gcube not as starting string in the main title // original result with sobigdata context with gcube not as starting string in the main title
Assertions.assertEquals(1, Assertions
tmp.filter(p->p.getId().equals("50|DansKnawCris::3c9f068ddc930360bec6925488a9a97f")).collect().get(0).getContext().size()); .assertEquals(
Assertions.assertEquals("sobigdata::projects::1",tmp.filter(p->p.getId().equals("50|DansKnawCris::3c9f068ddc930360bec6925488a9a97f")).collect().get(0).getContext().get(0).getId() ); 1,
titles = tmp.filter(p -> p.getId().equals("50|DansKnawCris::3c9f068ddc930360bec6925488a9a97f")).collect().get(0).getTitle(); tmp
.filter(p -> p.getId().equals("50|DansKnawCris::3c9f068ddc930360bec6925488a9a97f"))
.collect()
.get(0)
.getContext()
.size());
Assertions
.assertEquals(
"sobigdata::projects::1",
tmp
.filter(p -> p.getId().equals("50|DansKnawCris::3c9f068ddc930360bec6925488a9a97f"))
.collect()
.get(0)
.getContext()
.get(0)
.getId());
titles = tmp
.filter(p -> p.getId().equals("50|DansKnawCris::3c9f068ddc930360bec6925488a9a97f"))
.collect()
.get(0)
.getTitle();
Assertions.assertEquals(1, titles.size()); Assertions.assertEquals(1, titles.size());
Assertions.assertFalse(titles.get(0).getValue().toLowerCase().startsWith(prefix) ); Assertions.assertFalse(titles.get(0).getValue().toLowerCase().startsWith(prefix));
Assertions.assertTrue(titles.get(0).getValue().toLowerCase().contains(prefix.trim()) ); Assertions.assertTrue(titles.get(0).getValue().toLowerCase().contains(prefix.trim()));
Assertions.assertEquals("main title", titles.get(0).getQualifier().getClassid()); Assertions.assertEquals("main title", titles.get(0).getQualifier().getClassid());
//original result with sobigdata in context and also other contexts with gcube as starting string for the main title // original result with sobigdata in context and also other contexts with gcube as starting string for the main
Assertions.assertEquals(1, // title
tmp.filter(p->p.getId().equals("50|DansKnawCris::4669a378a73661417182c208e6fdab53")).collect().get(0).getContext().size()); Assertions
Assertions.assertEquals("dh-ch",tmp.filter(p->p.getId().equals("50|DansKnawCris::4669a378a73661417182c208e6fdab53")).collect().get(0).getContext().get(0).getId() ); .assertEquals(
titles = tmp.filter(p -> p.getId().equals("50|DansKnawCris::4669a378a73661417182c208e6fdab53")).collect().get(0).getTitle(); 1,
tmp
.filter(p -> p.getId().equals("50|DansKnawCris::4669a378a73661417182c208e6fdab53"))
.collect()
.get(0)
.getContext()
.size());
Assertions
.assertEquals(
"dh-ch",
tmp
.filter(p -> p.getId().equals("50|DansKnawCris::4669a378a73661417182c208e6fdab53"))
.collect()
.get(0)
.getContext()
.get(0)
.getId());
titles = tmp
.filter(p -> p.getId().equals("50|DansKnawCris::4669a378a73661417182c208e6fdab53"))
.collect()
.get(0)
.getTitle();
Assertions.assertEquals(1, titles.size()); Assertions.assertEquals(1, titles.size());
Assertions.assertTrue(titles.get(0).getValue().toLowerCase().startsWith(prefix) ); Assertions.assertTrue(titles.get(0).getValue().toLowerCase().startsWith(prefix));
Assertions.assertEquals("main title", titles.get(0).getQualifier().getClassid()); Assertions.assertEquals("main title", titles.get(0).getQualifier().getClassid());
//original result with multiple main title one of which whith gcube as starting string and with 2 contextes // original result with multiple main title one of which whith gcube as starting string and with 2 contextes
Assertions.assertEquals(1, Assertions
tmp.filter(p->p.getId().equals("50|DansKnawCris::4a9152e80f860eab99072e921d74a0ff")).collect().get(0).getContext().size()); .assertEquals(
Assertions.assertEquals("dh-ch",tmp.filter(p->p.getId().equals("50|DansKnawCris::4a9152e80f860eab99072e921d74a0ff")).collect().get(0).getContext().get(0).getId() ); 1,
titles = tmp.filter(p -> p.getId().equals("50|DansKnawCris::4a9152e80f860eab99072e921d74a0ff")).collect().get(0).getTitle(); tmp
.filter(p -> p.getId().equals("50|DansKnawCris::4a9152e80f860eab99072e921d74a0ff"))
.collect()
.get(0)
.getContext()
.size());
Assertions
.assertEquals(
"dh-ch",
tmp
.filter(p -> p.getId().equals("50|DansKnawCris::4a9152e80f860eab99072e921d74a0ff"))
.collect()
.get(0)
.getContext()
.get(0)
.getId());
titles = tmp
.filter(p -> p.getId().equals("50|DansKnawCris::4a9152e80f860eab99072e921d74a0ff"))
.collect()
.get(0)
.getTitle();
Assertions.assertEquals(2, titles.size()); Assertions.assertEquals(2, titles.size());
Assertions.assertTrue(titles.stream().anyMatch(t -> t.getQualifier().getClassid().equals("main title") && t.getValue().toLowerCase().startsWith(prefix)) ); Assertions
.assertTrue(
titles
.stream()
.anyMatch(
t -> t.getQualifier().getClassid().equals("main title")
&& t.getValue().toLowerCase().startsWith(prefix)));
// original result without sobigdata in context with gcube as starting string for the main title
//original result without sobigdata in context with gcube as starting string for the main title Assertions
Assertions.assertEquals(1, .assertEquals(
tmp.filter(p->p.getId().equals("50|dedup_wf_001::01e6a28565ca01376b7548e530c6f6e8")).collect().get(0).getContext().size()); 1,
Assertions.assertEquals("dh-ch",tmp.filter(p->p.getId().equals("50|dedup_wf_001::01e6a28565ca01376b7548e530c6f6e8")).collect().get(0).getContext().get(0).getId() ); tmp
titles = tmp.filter(p -> p.getId().equals("50|dedup_wf_001::01e6a28565ca01376b7548e530c6f6e8")).collect().get(0).getTitle(); .filter(p -> p.getId().equals("50|dedup_wf_001::01e6a28565ca01376b7548e530c6f6e8"))
.collect()
.get(0)
.getContext()
.size());
Assertions
.assertEquals(
"dh-ch",
tmp
.filter(p -> p.getId().equals("50|dedup_wf_001::01e6a28565ca01376b7548e530c6f6e8"))
.collect()
.get(0)
.getContext()
.get(0)
.getId());
titles = tmp
.filter(p -> p.getId().equals("50|dedup_wf_001::01e6a28565ca01376b7548e530c6f6e8"))
.collect()
.get(0)
.getTitle();
Assertions.assertEquals(2, titles.size()); Assertions.assertEquals(2, titles.size());
Assertions.assertTrue(titles.stream().anyMatch(t -> t.getQualifier().getClassid().equals("main title") && t.getValue().toLowerCase().startsWith(prefix))); Assertions
.assertTrue(
titles
.stream()
.anyMatch(
t -> t.getQualifier().getClassid().equals("main title")
&& t.getValue().toLowerCase().startsWith(prefix)));
} }
} }