Compare commits
308 Commits
Author | SHA1 | Date |
---|---|---|
Giambattista Bloisi | 9bf2bda1c6 | |
Giambattista Bloisi | d90cb099b8 | |
Claudio Atzori | 11fe3a4fe0 | |
Claudio Atzori | a8d68c9d29 | |
Miriam Baglioni | 8fe934810f | |
Miriam Baglioni | 9da006e98c | |
Giambattista Bloisi | 85c1eae7e0 | |
Claudio Atzori | b0eba210c0 | |
Claudio Atzori | 3776327a8c | |
Claudio Atzori | 0139f23d66 | |
Michele Artini | c726572418 | |
Claudio Atzori | ec79405cc9 | |
Miriam Baglioni | 1477406ecc | |
Claudio Atzori | 92c3abd5a4 | |
Claudio Atzori | ce2364743a | |
Claudio Atzori | f70dc76b61 | |
Claudio Atzori | 73bd1938a5 | |
Claudio Atzori | da5c1e73a4 | |
Claudio Atzori | 81090ad593 | |
Claudio Atzori | a02f3f0d2b | |
Alessia Bardi | eadfd8d71d | |
Alessia Bardi | 05ee783c07 | |
Alessia Bardi | fe9fb59c90 | |
Claudio Atzori | c272c4ad68 | |
Alessia Bardi | c5f4da16a4 | |
Alessia | 1b165a14a0 | |
Michele Artini | e996787be2 | |
Claudio Atzori | 62716141c5 | |
Miriam Baglioni | 5d85b70e1f | |
Lampros Smyrnaios | e3f28338c1 | |
Giambattista Bloisi | 73316d8c83 | |
Miriam Baglioni | 75d5ddb999 | |
Miriam Baglioni | 87c9c61b41 | |
Miriam Baglioni | b55fed09f8 | |
Claudio Atzori | 107d958b89 | |
Claudio Atzori | 3a7a6ecc32 | |
Claudio Atzori | 1af4224d3d | |
Claudio Atzori | 0d5bdb2db0 | |
Claudio Atzori | 66548e6a83 | |
Antonis Lempesis | 15b54a345a | |
Lampros Smyrnaios | b48ed6e617 | |
Lampros Smyrnaios | 68322843e2 | |
Lampros Smyrnaios | c7b32bbacc | |
Giambattista Bloisi | 1b2357e10a | |
Sandro La Bruzzo | f1fe363b19 | |
Sandro La Bruzzo | 66c1ffc866 | |
Claudio Atzori | 1ea67eba82 | |
Claudio Atzori | f9fb2fef6e | |
Claudio Atzori | 834461ba26 | |
Sandro La Bruzzo | e8a61d5dd5 | |
Sandro La Bruzzo | ca9414b737 | |
Sandro La Bruzzo | 032bcc8279 | |
Sandro La Bruzzo | 103e2652b3 | |
Sandro La Bruzzo | a87f9ea643 | |
Sandro La Bruzzo | 6efab4d88e | |
Claudio Atzori | 92f018d196 | |
Claudio Atzori | 0611c81a2f | |
Michele Artini | 2b3b5fe9a1 | |
Claudio Atzori | 1efe7f7e39 | |
Claudio Atzori | 53e7bb4336 | |
Claudio Atzori | f7d56e2ef2 | |
Claudio Atzori | c1237ab39e | |
Claudio Atzori | dc3a5858f7 | |
Claudio Atzori | 55f39f7850 | |
Claudio Atzori | 39a2afe8b5 | |
Claudio Atzori | 908ed9da7a | |
Antonis Lempesis | 0cada3cc8f | |
Antonis Lempesis | 90a4fb3547 | |
Claudio Atzori | 18aa323ee9 | |
Michele Artini | c9a327bc50 | |
Michele Artini | e234848af8 | |
Claudio Atzori | b4e3389432 | |
Giambattista Bloisi | 711048ceed | |
Michele Artini | 70bf6ac415 | |
Michele Artini | aa40e53c19 | |
Michele Artini | ed052a3476 | |
Claudio Atzori | 26363060ed | |
Claudio Atzori | 0486227185 | |
Claudio Atzori | a5d13d5d27 | |
Claudio Atzori | e1a0fb8933 | |
Giambattista Bloisi | 69c5efbd8b | |
Sandro La Bruzzo | db358ad0d2 | |
Sandro La Bruzzo | 26bf8e763a | |
Sandro La Bruzzo | a860c57bbc | |
Sandro La Bruzzo | 0646d0d064 | |
Claudio Atzori | 00ad21d814 | |
Claudio Atzori | 4355f64810 | |
Claudio Atzori | 66680b8b9a | |
Claudio Atzori | dcf23b3d06 | |
Michele Artini | f4068de298 | |
Claudio Atzori | 11bd89e132 | |
Claudio Atzori | e96c2c1606 | |
Claudio Atzori | 50c18f7a0b | |
Michele Artini | 2615136efc | |
Sandro La Bruzzo | 133ead1e3e | |
Sandro La Bruzzo | 052c6aac9d | |
Sandro La Bruzzo | 9cd3bc0f10 | |
Claudio Atzori | c08a58bba8 | |
Claudio Atzori | e2937db385 | |
Giambattista Bloisi | 1878199dae | |
Sandro La Bruzzo | 0d628cd62b | |
Lampros Smyrnaios | 49af2e5740 | |
Antonis Lempesis | d2649a1429 | |
Claudio Atzori | c3053ef34d | |
Claudio Atzori | b5bcab13ec | |
Claudio Atzori | 425c9afc36 | |
Claudio Atzori | 93dd9cc639 | |
Miriam Baglioni | 6189879643 | |
Claudio Atzori | c57cff2d6d | |
Miriam Baglioni | 7de114bda0 | |
Claudio Atzori | eb4692e4ee | |
Claudio Atzori | 24a83fc24f | |
Sandro La Bruzzo | 073f320c6a | |
Miriam Baglioni | 776c898c4b | |
Claudio Atzori | 5857fd38c1 | |
Claudio Atzori | 0656ab2838 | |
Claudio Atzori | ab7f0855af | |
Claudio Atzori | 7a7e313157 | |
Claudio Atzori | e5879b68c7 | |
Claudio Atzori | 3a027e97a7 | |
Sandro La Bruzzo | b72c3139e2 | |
Sandro La Bruzzo | b84ad0c06e | |
Antonis Lempesis | b52a5a753b | |
Sandro La Bruzzo | 8dd9cf84e2 | |
Sandro La Bruzzo | 342cb6189b | |
Antonis Lempesis | c3fe9662b2 | |
Claudio Atzori | 57c678d904 | |
Claudio Atzori | 5ab8cd1794 | |
Antonis Lempesis | 0c71c58df6 | |
Antonis Lempesis | 43d05dbebb | |
Antonis Lempesis | e728a0897c | |
Antonis Lempesis | 308ae580a9 | |
Antonis Lempesis | 27d22bd8f9 | |
Antonis Lempesis | 1f5aba12fa | |
Claudio Atzori | b554c41cc7 | |
Claudio Atzori | ac8747582c | |
Claudio Atzori | 0db7e4ae9a | |
Giambattista Bloisi | 8ac167e420 | |
Miriam Baglioni | 0625b9061f | |
Miriam Baglioni | 9eeb9f5d32 | |
Claudio Atzori | 589bce3520 | |
Sandro La Bruzzo | a5ddd8dfbb | |
Giambattista Bloisi | da333e9f4d | |
Claudio Atzori | 43fd1de681 | |
Claudio Atzori | d070db4a32 | |
Michele Artini | 78b9d84e4a | |
Giambattista Bloisi | 43b454399f | |
Sandro La Bruzzo | 41a42dde64 | |
Sandro La Bruzzo | 843dc95340 | |
Sandro La Bruzzo | 1e30454ee0 | |
Sandro La Bruzzo | 2581672c11 | |
Claudio Atzori | 3cad4a415d | |
Sandro La Bruzzo | a0642bd190 | |
Sandro La Bruzzo | 98dc042db5 | |
Sandro La Bruzzo | ef582948a7 | |
Sandro La Bruzzo | 5142f462b5 | |
Miriam Baglioni | 0794e0667b | |
Miriam Baglioni | 4b1de076ac | |
Miriam Baglioni | c8a88b2187 | |
Sandro La Bruzzo | 31e152d2bb | |
Sandro La Bruzzo | 6f3e925cae | |
Miriam Baglioni | f0f6abf892 | |
Claudio Atzori | 26b97aa5ed | |
Miriam Baglioni | 50fbebf186 | |
Michele Artini | 71d6e02886 | |
Michele Artini | 02c9a311c8 | |
Miriam Baglioni | 42846d3b91 | |
Miriam Baglioni | 4f0a044245 | |
Miriam Baglioni | 4bb504e693 | |
Serafeim Chatzopoulos | cbe13a5c61 | |
Miriam Baglioni | 9c9a9562ae | |
Miriam Baglioni | 2c4440951f | |
Miriam Baglioni | b42bdd5fb3 | |
Miriam Baglioni | 64cbd8abe9 | |
Serafeim Chatzopoulos | 0eb0701b26 | |
Claudio Atzori | 24227ab598 | |
Claudio Atzori | cff6040424 | |
Sandro La Bruzzo | 73a67c0e4a | |
Claudio Atzori | 9e700a8b0d | |
Claudio Atzori | 75551ad4ec | |
Miriam Baglioni | 94b931f7bd | |
Miriam Baglioni | 3b209261f2 | |
Claudio Atzori | 730eaffc85 | |
Claudio Atzori | ef52128c55 | |
Claudio Atzori | bfba71a95c | |
Claudio Atzori | d72e7b7487 | |
Sandro La Bruzzo | ece56f0178 | |
Claudio Atzori | 414acd4ef4 | |
Claudio Atzori | ecff0b4825 | |
Claudio Atzori | 25c2025223 | |
Claudio Atzori | 538b180fe0 | |
Claudio Atzori | eae88c0fe3 | |
Claudio Atzori | 82fc609c4f | |
Claudio Atzori | 4b978ffa2d | |
Claudio Atzori | fa4b3e6d2b | |
Claudio Atzori | 74e5d05577 | |
Claudio Atzori | 6c3b692f60 | |
Claudio Atzori | e9eb590f87 | |
Claudio Atzori | 9a5b134ddf | |
Claudio Atzori | 069803f34a | |
Claudio Atzori | 71c1f81b54 | |
Claudio Atzori | c3c9bdb59c | |
Claudio Atzori | 91b61687fa | |
Claudio Atzori | 63067d4b24 | |
Claudio Atzori | e0c315b07b | |
Claudio Atzori | 54936b7f42 | |
Claudio Atzori | 9fc70a9451 | |
Michele Artini | e1149eb5c4 | |
Michele Artini | 3f174ad90f | |
Michele Artini | 6ffb1faf09 | |
Giambattista Bloisi | 3f22c101d9 | |
Claudio Atzori | c8683eb13c | |
Claudio Atzori | aaa73f89d1 | |
Giambattista Bloisi | 0ff7faad72 | |
Michele Artini | 7faa115ba0 | |
Michele Artini | f9c74c98fa | |
Claudio Atzori | 7ae7e8aa06 | |
Sandro La Bruzzo | 58dbe71d39 | |
Giambattista Bloisi | 664a381d31 | |
Michele Artini | cb29b9773c | |
Michele Artini | 85b844d57e | |
Michele Artini | 455f2e1e07 | |
Michele Artini | 30167aa882 | |
Michele Artini | 88fef367b9 | |
Claudio Atzori | 078169b922 | |
Claudio Atzori | af154d4456 | |
Claudio Atzori | 7863c92466 | |
Claudio Atzori | eb5887cb9a | |
Sandro La Bruzzo | 5281f010a5 | |
Sandro La Bruzzo | ee1fcb672b | |
Miriam Baglioni | 5a32bb9578 | |
Sandro La Bruzzo | c532831718 | |
Miriam Baglioni | 48c052215c | |
Claudio Atzori | db66555ebb | |
Giambattista Bloisi | 9092075760 | |
Sandro La Bruzzo | cbd4e5e4bb | |
Claudio Atzori | d4871b31e8 | |
Miriam Baglioni | 5180b6ec8a | |
Miriam Baglioni | 7827a2d66b | |
Miriam Baglioni | fd34372c40 | |
Sandro La Bruzzo | d34cef3f8d | |
Sandro La Bruzzo | 3b837d38ce | |
Sandro La Bruzzo | f417515e43 | |
Sandro La Bruzzo | ad0e9aa80c | |
Sandro La Bruzzo | 9d94648f3b | |
Giambattista Bloisi | 3cd5590f3b | |
Giambattista Bloisi | 56dd05f85c | |
Claudio Atzori | 6fcf872daa | |
Claudio Atzori | 3f07390a58 | |
Sandro La Bruzzo | 7d806a434c | |
Sandro La Bruzzo | e468e99100 | |
Sandro La Bruzzo | b63994dcc4 | |
Sandro La Bruzzo | 915a76a796 | |
Giambattista Bloisi | 773e856550 | |
Sandro La Bruzzo | a712df1e1d | |
Sandro La Bruzzo | b32a9d1994 | |
Michele Artini | 3268570b2c | |
Miriam Baglioni | 72bae7af76 | |
Miriam Baglioni | 43da7e1191 | |
Serafeim Chatzopoulos | f0dc12634b | |
Claudio Atzori | 753c2a72bd | |
Claudio Atzori | a63b091bae | |
Giambattista Bloisi | 85aeff72f1 | |
Giambattista Bloisi | d65285da7f | |
Giambattista Bloisi | 29194472a7 | |
Miriam Baglioni | 8dae10b442 | |
Miriam Baglioni | 83bb97be83 | |
Miriam Baglioni | 6e1f383e4a | |
Miriam Baglioni | 3f7d262a4e | |
Miriam Baglioni | eca021f4d6 | |
Miriam Baglioni | bdb6bbb365 | |
Claudio Atzori | d85d2df6ad | |
Giambattista Bloisi | b19643f6eb | |
Claudio Atzori | e6bdee86d1 | |
Claudio Atzori | 38c9001147 | |
Claudio Atzori | fd17c1f17c | |
Claudio Atzori | 009dcf6aea | |
Claudio Atzori | bb82052c40 | |
Claudio Atzori | 42f5506306 | |
Alessia Bardi | f2a08d8cc2 | |
Miriam Baglioni | 07a373a0bd | |
Miriam Baglioni | ead08b0dd4 | |
Miriam Baglioni | a5995ab557 | |
Miriam Baglioni | a418dacb47 | |
Miriam Baglioni | e9131f4e4a | |
Sandro La Bruzzo | 9aebca77a0 | |
Sandro La Bruzzo | 0386f36385 | |
Sandro La Bruzzo | 43e0bba7ed | |
Miriam Baglioni | f7d06dc661 | |
Miriam Baglioni | 6e58d79623 | |
Miriam Baglioni | e0ec800d7e | |
Sandro La Bruzzo | e0753f19da | |
sandro.labruzzo | e328bc0ade | |
Sandro La Bruzzo | 859babf722 | |
Sandro La Bruzzo | 39ebb60b38 | |
Sandro La Bruzzo | 9d5a7c3b22 | |
Sandro La Bruzzo | 8f61063201 | |
Sandro La Bruzzo | 1a42a5c10d | |
Miriam Baglioni | 624f5f3f21 | |
Miriam Baglioni | 354e02e6a9 | |
Miriam Baglioni | b00771c7cc | |
Giambattista Bloisi | 613ec5ffce | |
Sandro La Bruzzo | 52495f2cd2 | |
Sandro La Bruzzo | 8c3e9a09d3 | |
Giambattista Bloisi | 2fa78f6071 | |
Giambattista Bloisi | 326c9dc08c | |
Miriam Baglioni | 4c9bc4c3a5 | |
Miriam Baglioni | 55ea485783 |
|
@ -27,3 +27,4 @@ spark-warehouse
|
||||||
/**/.factorypath
|
/**/.factorypath
|
||||||
/**/.scalafmt.conf
|
/**/.scalafmt.conf
|
||||||
/.java-version
|
/.java-version
|
||||||
|
/dhp-shade-package/dependency-reduced-pom.xml
|
||||||
|
|
|
@ -80,7 +80,15 @@ class WritePredefinedProjectPropertiesTest {
|
||||||
mojo.outputFile = testFolder;
|
mojo.outputFile = testFolder;
|
||||||
|
|
||||||
// execute
|
// execute
|
||||||
Assertions.assertThrows(MojoExecutionException.class, () -> mojo.execute());
|
try {
|
||||||
|
mojo.execute();
|
||||||
|
Assertions.assertTrue(false); // not reached
|
||||||
|
} catch (Exception e) {
|
||||||
|
Assertions
|
||||||
|
.assertTrue(
|
||||||
|
MojoExecutionException.class.isAssignableFrom(e.getClass()) ||
|
||||||
|
IllegalArgumentException.class.isAssignableFrom(e.getClass()));
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
@Test
|
@Test
|
||||||
|
|
|
@ -63,15 +63,14 @@
|
||||||
|
|
||||||
<dependencies>
|
<dependencies>
|
||||||
<dependency>
|
<dependency>
|
||||||
<groupId>eu.dnetlib.dhp</groupId>
|
<groupId>edu.cmu</groupId>
|
||||||
<artifactId>dhp-pace-core</artifactId>
|
<artifactId>secondstring</artifactId>
|
||||||
<version>${project.version}</version>
|
</dependency>
|
||||||
|
<dependency>
|
||||||
|
<groupId>com.ibm.icu</groupId>
|
||||||
|
<artifactId>icu4j</artifactId>
|
||||||
</dependency>
|
</dependency>
|
||||||
|
|
||||||
<dependency>
|
|
||||||
<groupId>org.apache.hadoop</groupId>
|
|
||||||
<artifactId>hadoop-common</artifactId>
|
|
||||||
</dependency>
|
|
||||||
<dependency>
|
<dependency>
|
||||||
<groupId>com.github.sisyphsu</groupId>
|
<groupId>com.github.sisyphsu</groupId>
|
||||||
<artifactId>dateparser</artifactId>
|
<artifactId>dateparser</artifactId>
|
||||||
|
@ -161,7 +160,7 @@
|
||||||
|
|
||||||
<dependency>
|
<dependency>
|
||||||
<groupId>eu.dnetlib.dhp</groupId>
|
<groupId>eu.dnetlib.dhp</groupId>
|
||||||
<artifactId>${dhp-schemas.artifact}</artifactId>
|
<artifactId>dhp-schemas</artifactId>
|
||||||
</dependency>
|
</dependency>
|
||||||
|
|
||||||
<dependency>
|
<dependency>
|
||||||
|
@ -170,4 +169,23 @@
|
||||||
</dependency>
|
</dependency>
|
||||||
</dependencies>
|
</dependencies>
|
||||||
|
|
||||||
|
<!-- dependencies required on JDK9+ because J2EE has been removed -->
|
||||||
|
<profiles>
|
||||||
|
<profile>
|
||||||
|
<id>spark-34</id>
|
||||||
|
<dependencies>
|
||||||
|
<dependency>
|
||||||
|
<groupId>javax.xml.bind</groupId>
|
||||||
|
<artifactId>jaxb-api</artifactId>
|
||||||
|
<version>2.2.11</version>
|
||||||
|
</dependency>
|
||||||
|
<dependency>
|
||||||
|
<groupId>com.sun.xml.ws</groupId>
|
||||||
|
<artifactId>jaxws-ri</artifactId>
|
||||||
|
<version>2.3.3</version>
|
||||||
|
<type>pom</type>
|
||||||
|
</dependency>
|
||||||
|
</dependencies>
|
||||||
|
</profile>
|
||||||
|
</profiles>
|
||||||
</project>
|
</project>
|
||||||
|
|
|
@ -38,7 +38,7 @@ public class PacePerson {
|
||||||
PacePerson.class
|
PacePerson.class
|
||||||
.getResourceAsStream(
|
.getResourceAsStream(
|
||||||
"/eu/dnetlib/dhp/common/name_particles.txt")));
|
"/eu/dnetlib/dhp/common/name_particles.txt")));
|
||||||
} catch (IOException e) {
|
} catch (Exception e) {
|
||||||
throw new RuntimeException(e);
|
throw new RuntimeException(e);
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
|
@ -217,8 +217,6 @@ public class ZenodoAPIClient implements Serializable {
|
||||||
* part of the url for the DOI Zenodo suggests to use to cite all versions: DOI: 10.xxx/zenodo.656930
|
* part of the url for the DOI Zenodo suggests to use to cite all versions: DOI: 10.xxx/zenodo.656930
|
||||||
* concept_rec_id = 656930
|
* concept_rec_id = 656930
|
||||||
* @return response code
|
* @return response code
|
||||||
* @throws IOException
|
|
||||||
* @throws MissingConceptDoiException
|
|
||||||
*/
|
*/
|
||||||
public int newVersion(String concept_rec_id) throws IOException, MissingConceptDoiException {
|
public int newVersion(String concept_rec_id) throws IOException, MissingConceptDoiException {
|
||||||
setDepositionId(concept_rec_id, 1);
|
setDepositionId(concept_rec_id, 1);
|
||||||
|
|
|
@ -12,9 +12,7 @@ import java.util.concurrent.TimeUnit;
|
||||||
|
|
||||||
import org.apache.commons.io.IOUtils;
|
import org.apache.commons.io.IOUtils;
|
||||||
import org.apache.commons.lang3.math.NumberUtils;
|
import org.apache.commons.lang3.math.NumberUtils;
|
||||||
import org.apache.commons.lang3.time.DateUtils;
|
|
||||||
import org.apache.http.HttpHeaders;
|
import org.apache.http.HttpHeaders;
|
||||||
import org.joda.time.Instant;
|
|
||||||
import org.slf4j.Logger;
|
import org.slf4j.Logger;
|
||||||
import org.slf4j.LoggerFactory;
|
import org.slf4j.LoggerFactory;
|
||||||
|
|
||||||
|
|
|
@ -10,6 +10,7 @@ import org.apache.commons.lang3.StringUtils;
|
||||||
import com.wcohen.ss.JaroWinkler;
|
import com.wcohen.ss.JaroWinkler;
|
||||||
|
|
||||||
import eu.dnetlib.dhp.schema.oaf.Author;
|
import eu.dnetlib.dhp.schema.oaf.Author;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.Qualifier;
|
||||||
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
|
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
|
||||||
import eu.dnetlib.pace.model.Person;
|
import eu.dnetlib.pace.model.Person;
|
||||||
import scala.Tuple2;
|
import scala.Tuple2;
|
||||||
|
@ -145,110 +146,21 @@ public class AuthorMerger {
|
||||||
return null;
|
return null;
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
|
||||||
* This method tries to figure out when two author are the same in the contest
|
|
||||||
* of ORCID enrichment
|
|
||||||
*
|
|
||||||
* @param left Author in the OAF entity
|
|
||||||
* @param right Author ORCID
|
|
||||||
* @return based on a heuristic on the names of the authors if they are the same.
|
|
||||||
*/
|
|
||||||
public static boolean checkORCIDSimilarity(final Author left, final Author right) {
|
|
||||||
final Person pl = parse(left);
|
|
||||||
final Person pr = parse(right);
|
|
||||||
|
|
||||||
// If one of them didn't have a surname we verify if they have the fullName not empty
|
|
||||||
// and verify if the normalized version is equal
|
|
||||||
if (!(pl.getSurname() != null && pl.getSurname().stream().anyMatch(StringUtils::isNotBlank) &&
|
|
||||||
pr.getSurname() != null && pr.getSurname().stream().anyMatch(StringUtils::isNotBlank))) {
|
|
||||||
|
|
||||||
if (pl.getFullname() != null && !pl.getFullname().isEmpty() && pr.getFullname() != null
|
|
||||||
&& !pr.getFullname().isEmpty()) {
|
|
||||||
return pl
|
|
||||||
.getFullname()
|
|
||||||
.stream()
|
|
||||||
.anyMatch(
|
|
||||||
fl -> pr.getFullname().stream().anyMatch(fr -> normalize(fl).equalsIgnoreCase(normalize(fr))));
|
|
||||||
} else {
|
|
||||||
return false;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
// The Authors have one surname in common
|
|
||||||
if (pl.getSurname().stream().anyMatch(sl -> pr.getSurname().stream().anyMatch(sr -> sr.equalsIgnoreCase(sl)))) {
|
|
||||||
|
|
||||||
// If one of them has only a surname and is the same we can say that they are the same author
|
|
||||||
if ((pl.getName() == null || pl.getName().stream().allMatch(StringUtils::isBlank)) ||
|
|
||||||
(pr.getName() == null || pr.getName().stream().allMatch(StringUtils::isBlank)))
|
|
||||||
return true;
|
|
||||||
// The authors have the same initials of Name in common
|
|
||||||
if (pl
|
|
||||||
.getName()
|
|
||||||
.stream()
|
|
||||||
.anyMatch(
|
|
||||||
nl -> pr
|
|
||||||
.getName()
|
|
||||||
.stream()
|
|
||||||
.anyMatch(nr -> nr.equalsIgnoreCase(nl))))
|
|
||||||
return true;
|
|
||||||
}
|
|
||||||
|
|
||||||
// Sometimes we noticed that publication have author wrote in inverse order Surname, Name
|
|
||||||
// We verify if we have an exact match between name and surname
|
|
||||||
if (pl.getSurname().stream().anyMatch(sl -> pr.getName().stream().anyMatch(nr -> nr.equalsIgnoreCase(sl))) &&
|
|
||||||
pl.getName().stream().anyMatch(nl -> pr.getSurname().stream().anyMatch(sr -> sr.equalsIgnoreCase(nl))))
|
|
||||||
return true;
|
|
||||||
else
|
|
||||||
return false;
|
|
||||||
}
|
|
||||||
//
|
|
||||||
|
|
||||||
/**
|
|
||||||
* Method to enrich ORCID information in one list of authors based on another list
|
|
||||||
*
|
|
||||||
* @param baseAuthor the Author List in the OAF Entity
|
|
||||||
* @param orcidAuthor The list of ORCID Author intersected
|
|
||||||
* @return The Author List of the OAF Entity enriched with the orcid Author
|
|
||||||
*/
|
|
||||||
public static List<Author> enrichOrcid(List<Author> baseAuthor, List<Author> orcidAuthor) {
|
|
||||||
|
|
||||||
if (baseAuthor == null || baseAuthor.isEmpty())
|
|
||||||
return orcidAuthor;
|
|
||||||
|
|
||||||
if (orcidAuthor == null || orcidAuthor.isEmpty())
|
|
||||||
return baseAuthor;
|
|
||||||
|
|
||||||
if (baseAuthor.size() == 1 && orcidAuthor.size() > 10)
|
|
||||||
return baseAuthor;
|
|
||||||
|
|
||||||
final List<Author> oAuthor = new ArrayList<>();
|
|
||||||
oAuthor.addAll(orcidAuthor);
|
|
||||||
|
|
||||||
baseAuthor.forEach(ba -> {
|
|
||||||
Optional<Author> aMatch = oAuthor.stream().filter(oa -> checkORCIDSimilarity(ba, oa)).findFirst();
|
|
||||||
if (aMatch.isPresent()) {
|
|
||||||
final Author sameAuthor = aMatch.get();
|
|
||||||
addPid(ba, sameAuthor.getPid());
|
|
||||||
oAuthor.remove(sameAuthor);
|
|
||||||
}
|
|
||||||
});
|
|
||||||
return baseAuthor;
|
|
||||||
}
|
|
||||||
|
|
||||||
private static void addPid(final Author a, final List<StructuredProperty> pids) {
|
|
||||||
|
|
||||||
if (a.getPid() == null) {
|
|
||||||
a.setPid(new ArrayList<>());
|
|
||||||
}
|
|
||||||
|
|
||||||
a.getPid().addAll(pids);
|
|
||||||
|
|
||||||
}
|
|
||||||
|
|
||||||
public static String pidToComparableString(StructuredProperty pid) {
|
public static String pidToComparableString(StructuredProperty pid) {
|
||||||
final String classid = pid.getQualifier().getClassid() != null ? pid.getQualifier().getClassid().toLowerCase()
|
final String classId = Optional
|
||||||
: "";
|
.ofNullable(pid)
|
||||||
return (pid.getQualifier() != null ? classid : "")
|
.map(
|
||||||
+ (pid.getValue() != null ? pid.getValue().toLowerCase() : "");
|
p -> Optional
|
||||||
|
.ofNullable(p.getQualifier())
|
||||||
|
.map(Qualifier::getClassid)
|
||||||
|
.map(String::toLowerCase)
|
||||||
|
.orElse(""))
|
||||||
|
.orElse("");
|
||||||
|
return Optional
|
||||||
|
.ofNullable(pid)
|
||||||
|
.map(StructuredProperty::getValue)
|
||||||
|
.map(v -> String.join("|", v, classId))
|
||||||
|
.orElse("");
|
||||||
}
|
}
|
||||||
|
|
||||||
public static int countAuthorsPids(List<Author> authors) {
|
public static int countAuthorsPids(List<Author> authors) {
|
||||||
|
|
|
@ -14,7 +14,7 @@ import java.util.stream.Collectors;
|
||||||
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;
|
||||||
import org.apache.spark.api.java.function.ReduceFunction;
|
import org.apache.spark.api.java.function.MapGroupsFunction;
|
||||||
import org.apache.spark.sql.*;
|
import org.apache.spark.sql.*;
|
||||||
import org.slf4j.Logger;
|
import org.slf4j.Logger;
|
||||||
import org.slf4j.LoggerFactory;
|
import org.slf4j.LoggerFactory;
|
||||||
|
@ -26,7 +26,7 @@ import eu.dnetlib.dhp.schema.common.EntityType;
|
||||||
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
||||||
import eu.dnetlib.dhp.schema.oaf.OafEntity;
|
import eu.dnetlib.dhp.schema.oaf.OafEntity;
|
||||||
import eu.dnetlib.dhp.schema.oaf.utils.GraphCleaningFunctions;
|
import eu.dnetlib.dhp.schema.oaf.utils.GraphCleaningFunctions;
|
||||||
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
|
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
|
||||||
import eu.dnetlib.dhp.utils.ISLookupClientFactory;
|
import eu.dnetlib.dhp.utils.ISLookupClientFactory;
|
||||||
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
|
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
|
||||||
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
|
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
|
||||||
|
@ -135,10 +135,10 @@ public class GroupEntitiesSparkJob {
|
||||||
.applyCoarVocabularies(entity, vocs),
|
.applyCoarVocabularies(entity, vocs),
|
||||||
OAFENTITY_KRYO_ENC)
|
OAFENTITY_KRYO_ENC)
|
||||||
.groupByKey((MapFunction<OafEntity, String>) OafEntity::getId, Encoders.STRING())
|
.groupByKey((MapFunction<OafEntity, String>) OafEntity::getId, Encoders.STRING())
|
||||||
.reduceGroups((ReduceFunction<OafEntity>) OafMapperUtils::mergeEntities)
|
.mapGroups((MapGroupsFunction<String, OafEntity, OafEntity>) MergeUtils::mergeById, OAFENTITY_KRYO_ENC)
|
||||||
.map(
|
.map(
|
||||||
(MapFunction<Tuple2<String, OafEntity>, Tuple2<String, OafEntity>>) t -> new Tuple2<>(
|
(MapFunction<OafEntity, Tuple2<String, OafEntity>>) t -> new Tuple2<>(
|
||||||
t._2().getClass().getName(), t._2()),
|
t.getClass().getName(), t),
|
||||||
Encoders.tuple(Encoders.STRING(), OAFENTITY_KRYO_ENC));
|
Encoders.tuple(Encoders.STRING(), OAFENTITY_KRYO_ENC));
|
||||||
|
|
||||||
// pivot on "_1" (classname of the entity)
|
// pivot on "_1" (classname of the entity)
|
||||||
|
|
|
@ -0,0 +1,76 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.schema.oaf.utils;
|
||||||
|
|
||||||
|
import java.util.HashSet;
|
||||||
|
import java.util.Objects;
|
||||||
|
import java.util.Optional;
|
||||||
|
import java.util.Set;
|
||||||
|
|
||||||
|
import org.apache.commons.lang3.StringUtils;
|
||||||
|
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
|
||||||
|
|
||||||
|
public class CleaningFunctions {
|
||||||
|
|
||||||
|
public static final String DOI_PREFIX_REGEX = "(^10\\.|\\/10\\.)";
|
||||||
|
public static final String DOI_PREFIX = "10.";
|
||||||
|
|
||||||
|
public static final Set<String> PID_BLACKLIST = new HashSet<>();
|
||||||
|
|
||||||
|
static {
|
||||||
|
PID_BLACKLIST.add("none");
|
||||||
|
PID_BLACKLIST.add("na");
|
||||||
|
}
|
||||||
|
|
||||||
|
public CleaningFunctions() {
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Utility method that filter PID values on a per-type basis.
|
||||||
|
* @param s the PID whose value will be checked.
|
||||||
|
* @return false if the pid matches the filter criteria, true otherwise.
|
||||||
|
*/
|
||||||
|
public static boolean pidFilter(StructuredProperty s) {
|
||||||
|
final String pidValue = s.getValue();
|
||||||
|
if (Objects.isNull(s.getQualifier()) ||
|
||||||
|
StringUtils.isBlank(pidValue) ||
|
||||||
|
StringUtils.isBlank(pidValue.replaceAll("(?:\\n|\\r|\\t|\\s)", ""))) {
|
||||||
|
return false;
|
||||||
|
}
|
||||||
|
if (CleaningFunctions.PID_BLACKLIST.contains(pidValue)) {
|
||||||
|
return false;
|
||||||
|
}
|
||||||
|
return !PidBlacklistProvider.getBlacklist(s.getQualifier().getClassid()).contains(pidValue);
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Utility method that normalises PID values on a per-type basis.
|
||||||
|
* @param pid the PID whose value will be normalised.
|
||||||
|
* @return the PID containing the normalised value.
|
||||||
|
*/
|
||||||
|
public static StructuredProperty normalizePidValue(StructuredProperty pid) {
|
||||||
|
pid
|
||||||
|
.setValue(
|
||||||
|
normalizePidValue(
|
||||||
|
pid.getQualifier().getClassid(),
|
||||||
|
pid.getValue()));
|
||||||
|
|
||||||
|
return pid;
|
||||||
|
}
|
||||||
|
|
||||||
|
public static String normalizePidValue(String pidType, String pidValue) {
|
||||||
|
String value = Optional
|
||||||
|
.ofNullable(pidValue)
|
||||||
|
.map(String::trim)
|
||||||
|
.orElseThrow(() -> new IllegalArgumentException("PID value cannot be empty"));
|
||||||
|
|
||||||
|
switch (pidType) {
|
||||||
|
|
||||||
|
// TODO add cleaning for more PID types as needed
|
||||||
|
case "doi":
|
||||||
|
return value.toLowerCase().replaceFirst(DOI_PREFIX_REGEX, DOI_PREFIX);
|
||||||
|
}
|
||||||
|
return value;
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -1,6 +1,8 @@
|
||||||
|
|
||||||
package eu.dnetlib.dhp.schema.oaf.utils;
|
package eu.dnetlib.dhp.schema.oaf.utils;
|
||||||
|
|
||||||
|
import org.apache.commons.lang3.StringUtils;
|
||||||
|
|
||||||
public class DoiCleaningRule {
|
public class DoiCleaningRule {
|
||||||
|
|
||||||
public static String clean(final String doi) {
|
public static String clean(final String doi) {
|
||||||
|
@ -11,4 +13,26 @@ public class DoiCleaningRule {
|
||||||
.replaceFirst(CleaningFunctions.DOI_PREFIX_REGEX, CleaningFunctions.DOI_PREFIX);
|
.replaceFirst(CleaningFunctions.DOI_PREFIX_REGEX, CleaningFunctions.DOI_PREFIX);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
public static String normalizeDoi(final String input) {
|
||||||
|
if (input == null)
|
||||||
|
return null;
|
||||||
|
final String replaced = input
|
||||||
|
.replaceAll("\\n|\\r|\\t|\\s", "")
|
||||||
|
.toLowerCase()
|
||||||
|
.replaceFirst(CleaningFunctions.DOI_PREFIX_REGEX, CleaningFunctions.DOI_PREFIX);
|
||||||
|
if (StringUtils.isEmpty(replaced))
|
||||||
|
return null;
|
||||||
|
|
||||||
|
if (!replaced.contains("10."))
|
||||||
|
return null;
|
||||||
|
|
||||||
|
final String ret = replaced.substring(replaced.indexOf("10."));
|
||||||
|
|
||||||
|
if (!ret.startsWith(CleaningFunctions.DOI_PREFIX))
|
||||||
|
return null;
|
||||||
|
|
||||||
|
return ret;
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
|
@ -92,6 +92,8 @@ public class GraphCleaningFunctions extends CleaningFunctions {
|
||||||
INVALID_AUTHOR_NAMES.add("null anonymous");
|
INVALID_AUTHOR_NAMES.add("null anonymous");
|
||||||
INVALID_AUTHOR_NAMES.add("unbekannt");
|
INVALID_AUTHOR_NAMES.add("unbekannt");
|
||||||
INVALID_AUTHOR_NAMES.add("unknown");
|
INVALID_AUTHOR_NAMES.add("unknown");
|
||||||
|
INVALID_AUTHOR_NAMES.add("autor, Sin");
|
||||||
|
INVALID_AUTHOR_NAMES.add("Desconocido / Inconnu,");
|
||||||
|
|
||||||
INVALID_URL_HOSTS.add("creativecommons.org");
|
INVALID_URL_HOSTS.add("creativecommons.org");
|
||||||
INVALID_URL_HOSTS.add("www.academia.edu");
|
INVALID_URL_HOSTS.add("www.academia.edu");
|
||||||
|
@ -312,7 +314,8 @@ public class GraphCleaningFunctions extends CleaningFunctions {
|
||||||
}
|
}
|
||||||
|
|
||||||
if (value instanceof Datasource) {
|
if (value instanceof Datasource) {
|
||||||
// nothing to evaluate here
|
final Datasource d = (Datasource) value;
|
||||||
|
return Objects.nonNull(d.getOfficialname()) && StringUtils.isNotBlank(d.getOfficialname().getValue());
|
||||||
} else if (value instanceof Project) {
|
} else if (value instanceof Project) {
|
||||||
final Project p = (Project) value;
|
final Project p = (Project) value;
|
||||||
return Objects.nonNull(p.getCode()) && StringUtils.isNotBlank(p.getCode().getValue());
|
return Objects.nonNull(p.getCode()) && StringUtils.isNotBlank(p.getCode().getValue());
|
||||||
|
@ -505,6 +508,8 @@ public class GraphCleaningFunctions extends CleaningFunctions {
|
||||||
.filter(Objects::nonNull)
|
.filter(Objects::nonNull)
|
||||||
.filter(sp -> StringUtils.isNotBlank(sp.getValue()))
|
.filter(sp -> StringUtils.isNotBlank(sp.getValue()))
|
||||||
.map(GraphCleaningFunctions::cleanValue)
|
.map(GraphCleaningFunctions::cleanValue)
|
||||||
|
.sorted((s1, s2) -> s2.getValue().length() - s1.getValue().length())
|
||||||
|
.limit(ModelHardLimits.MAX_ABSTRACTS)
|
||||||
.collect(Collectors.toList()));
|
.collect(Collectors.toList()));
|
||||||
}
|
}
|
||||||
if (Objects.isNull(r.getResourcetype()) || StringUtils.isBlank(r.getResourcetype().getClassid())) {
|
if (Objects.isNull(r.getResourcetype()) || StringUtils.isBlank(r.getResourcetype().getClassid())) {
|
||||||
|
|
|
@ -0,0 +1,294 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.schema.oaf.utils;
|
||||||
|
|
||||||
|
import static com.google.common.base.Preconditions.checkArgument;
|
||||||
|
import static eu.dnetlib.dhp.schema.common.ModelConstants.*;
|
||||||
|
|
||||||
|
import java.io.Serializable;
|
||||||
|
import java.nio.charset.StandardCharsets;
|
||||||
|
import java.security.MessageDigest;
|
||||||
|
import java.util.*;
|
||||||
|
import java.util.function.Function;
|
||||||
|
import java.util.stream.Collectors;
|
||||||
|
import java.util.stream.Stream;
|
||||||
|
|
||||||
|
import org.apache.commons.codec.binary.Hex;
|
||||||
|
import org.apache.commons.lang3.StringUtils;
|
||||||
|
|
||||||
|
import com.google.common.collect.HashBiMap;
|
||||||
|
import com.google.common.collect.Maps;
|
||||||
|
|
||||||
|
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.*;
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Factory class for OpenAIRE identifiers in the Graph
|
||||||
|
*/
|
||||||
|
public class IdentifierFactory implements Serializable {
|
||||||
|
|
||||||
|
public static final String ID_SEPARATOR = "::";
|
||||||
|
public static final String ID_PREFIX_SEPARATOR = "|";
|
||||||
|
|
||||||
|
public static final int ID_PREFIX_LEN = 12;
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Declares the associations PID_TYPE -> [DATASOURCE ID, NAME] considered authoritative for that PID_TYPE.
|
||||||
|
* The id of the record (source_::id) will be rewritten as pidType_::id)
|
||||||
|
*/
|
||||||
|
public static final Map<PidType, HashBiMap<String, String>> PID_AUTHORITY = Maps.newHashMap();
|
||||||
|
|
||||||
|
static {
|
||||||
|
PID_AUTHORITY.put(PidType.doi, HashBiMap.create());
|
||||||
|
PID_AUTHORITY.get(PidType.doi).put(CROSSREF_ID, "Crossref");
|
||||||
|
PID_AUTHORITY.get(PidType.doi).put(DATACITE_ID, "Datacite");
|
||||||
|
PID_AUTHORITY.get(PidType.doi).put(ZENODO_OD_ID, "ZENODO");
|
||||||
|
PID_AUTHORITY.get(PidType.doi).put(ZENODO_R3_ID, "Zenodo");
|
||||||
|
|
||||||
|
PID_AUTHORITY.put(PidType.pmc, HashBiMap.create());
|
||||||
|
PID_AUTHORITY.get(PidType.pmc).put(EUROPE_PUBMED_CENTRAL_ID, "Europe PubMed Central");
|
||||||
|
PID_AUTHORITY.get(PidType.pmc).put(PUBMED_CENTRAL_ID, "PubMed Central");
|
||||||
|
|
||||||
|
PID_AUTHORITY.put(PidType.pmid, HashBiMap.create());
|
||||||
|
PID_AUTHORITY.get(PidType.pmid).put(EUROPE_PUBMED_CENTRAL_ID, "Europe PubMed Central");
|
||||||
|
PID_AUTHORITY.get(PidType.pmid).put(PUBMED_CENTRAL_ID, "PubMed Central");
|
||||||
|
|
||||||
|
PID_AUTHORITY.put(PidType.arXiv, HashBiMap.create());
|
||||||
|
PID_AUTHORITY.get(PidType.arXiv).put(ARXIV_ID, "arXiv.org e-Print Archive");
|
||||||
|
|
||||||
|
PID_AUTHORITY.put(PidType.w3id, HashBiMap.create());
|
||||||
|
PID_AUTHORITY.get(PidType.w3id).put(ROHUB_ID, "ROHub");
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Declares the associations PID_TYPE -> [DATASOURCE ID, PID SUBSTRING] considered as delegated authority for that
|
||||||
|
* PID_TYPE. Example, Zenodo is delegated to forge DOIs that contain the 'zenodo' word.
|
||||||
|
*
|
||||||
|
* If a record with the same id (same pid) comes from 2 data sources, the one coming from a delegated source wins. E.g. Zenodo records win over those from Datacite.
|
||||||
|
* See also https://code-repo.d4science.org/D-Net/dnet-hadoop/pulls/187 and the class dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/OafMapperUtils.java
|
||||||
|
*/
|
||||||
|
public static final Map<PidType, Map<String, String>> DELEGATED_PID_AUTHORITY = Maps.newHashMap();
|
||||||
|
|
||||||
|
static {
|
||||||
|
DELEGATED_PID_AUTHORITY.put(PidType.doi, new HashMap<>());
|
||||||
|
DELEGATED_PID_AUTHORITY.get(PidType.doi).put(ZENODO_OD_ID, "zenodo");
|
||||||
|
DELEGATED_PID_AUTHORITY.get(PidType.doi).put(ZENODO_R3_ID, "zenodo");
|
||||||
|
DELEGATED_PID_AUTHORITY.put(PidType.w3id, new HashMap<>());
|
||||||
|
DELEGATED_PID_AUTHORITY.get(PidType.w3id).put(ROHUB_ID, "ro-id");
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Declares the associations PID_TYPE -> [DATASOURCE ID, NAME] whose records are considered enrichment for the graph.
|
||||||
|
* Their OpenAIRE ID is built from the declared PID type. Are merged with their corresponding record, identified by
|
||||||
|
* the same OpenAIRE id.
|
||||||
|
*/
|
||||||
|
public static final Map<PidType, HashBiMap<String, String>> ENRICHMENT_PROVIDER = Maps.newHashMap();
|
||||||
|
|
||||||
|
static {
|
||||||
|
ENRICHMENT_PROVIDER.put(PidType.doi, HashBiMap.create());
|
||||||
|
ENRICHMENT_PROVIDER.get(PidType.doi).put(OPEN_APC_ID, OPEN_APC_NAME);
|
||||||
|
}
|
||||||
|
|
||||||
|
public static Set<String> delegatedAuthorityDatasourceIds() {
|
||||||
|
return DELEGATED_PID_AUTHORITY
|
||||||
|
.values()
|
||||||
|
.stream()
|
||||||
|
.flatMap(m -> m.keySet().stream())
|
||||||
|
.collect(Collectors.toCollection(HashSet::new));
|
||||||
|
}
|
||||||
|
|
||||||
|
public static List<StructuredProperty> getPids(List<StructuredProperty> pid, KeyValue collectedFrom) {
|
||||||
|
return pidFromInstance(pid, collectedFrom, true).distinct().collect(Collectors.toList());
|
||||||
|
}
|
||||||
|
|
||||||
|
public static <T extends Result> String createDOIBoostIdentifier(T entity) {
|
||||||
|
if (entity == null)
|
||||||
|
return null;
|
||||||
|
|
||||||
|
StructuredProperty pid = null;
|
||||||
|
if (entity.getPid() != null) {
|
||||||
|
pid = entity
|
||||||
|
.getPid()
|
||||||
|
.stream()
|
||||||
|
.filter(Objects::nonNull)
|
||||||
|
.filter(s -> s.getQualifier() != null && "doi".equalsIgnoreCase(s.getQualifier().getClassid()))
|
||||||
|
.filter(CleaningFunctions::pidFilter)
|
||||||
|
.findAny()
|
||||||
|
.orElse(null);
|
||||||
|
} else {
|
||||||
|
if (entity.getInstance() != null) {
|
||||||
|
pid = entity
|
||||||
|
.getInstance()
|
||||||
|
.stream()
|
||||||
|
.filter(i -> i.getPid() != null)
|
||||||
|
.flatMap(i -> i.getPid().stream())
|
||||||
|
.filter(CleaningFunctions::pidFilter)
|
||||||
|
.findAny()
|
||||||
|
.orElse(null);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
if (pid != null)
|
||||||
|
return idFromPid(entity, pid, true);
|
||||||
|
return null;
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Creates an identifier from the most relevant PID (if available) provided by a known PID authority in the given
|
||||||
|
* entity T. Returns entity.id when none of the PIDs meet the selection criteria is available.
|
||||||
|
*
|
||||||
|
* @param entity the entity providing PIDs and a default ID.
|
||||||
|
* @param <T> the specific entity type. Currently Organization and Result subclasses are supported.
|
||||||
|
* @param md5 indicates whether should hash the PID value or not.
|
||||||
|
* @return an identifier from the most relevant PID, entity.id otherwise
|
||||||
|
*/
|
||||||
|
public static <T extends OafEntity> String createIdentifier(T entity, boolean md5) {
|
||||||
|
|
||||||
|
checkArgument(StringUtils.isNoneBlank(entity.getId()), "missing entity identifier");
|
||||||
|
|
||||||
|
final Map<String, Set<StructuredProperty>> pids = extractPids(entity);
|
||||||
|
|
||||||
|
return pids
|
||||||
|
.values()
|
||||||
|
.stream()
|
||||||
|
.flatMap(Set::stream)
|
||||||
|
.min(new PidComparator<>(entity))
|
||||||
|
.map(
|
||||||
|
min -> Optional
|
||||||
|
.ofNullable(pids.get(min.getQualifier().getClassid()))
|
||||||
|
.map(
|
||||||
|
p -> p
|
||||||
|
.stream()
|
||||||
|
.sorted(new PidValueComparator())
|
||||||
|
.findFirst()
|
||||||
|
.map(s -> idFromPid(entity, s, md5))
|
||||||
|
.orElseGet(entity::getId))
|
||||||
|
.orElseGet(entity::getId))
|
||||||
|
.orElseGet(entity::getId);
|
||||||
|
}
|
||||||
|
|
||||||
|
private static <T extends OafEntity> Map<String, Set<StructuredProperty>> extractPids(T entity) {
|
||||||
|
if (entity instanceof Result) {
|
||||||
|
return Optional
|
||||||
|
.ofNullable(((Result) entity).getInstance())
|
||||||
|
.map(IdentifierFactory::mapPids)
|
||||||
|
.orElse(new HashMap<>());
|
||||||
|
} else {
|
||||||
|
return entity
|
||||||
|
.getPid()
|
||||||
|
.stream()
|
||||||
|
.map(CleaningFunctions::normalizePidValue)
|
||||||
|
.filter(CleaningFunctions::pidFilter)
|
||||||
|
.collect(
|
||||||
|
Collectors
|
||||||
|
.groupingBy(
|
||||||
|
p -> p.getQualifier().getClassid(),
|
||||||
|
Collectors.mapping(p -> p, Collectors.toCollection(HashSet::new))));
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
private static Map<String, Set<StructuredProperty>> mapPids(List<Instance> instance) {
|
||||||
|
return instance
|
||||||
|
.stream()
|
||||||
|
.map(i -> pidFromInstance(i.getPid(), i.getCollectedfrom(), false))
|
||||||
|
.flatMap(Function.identity())
|
||||||
|
.collect(
|
||||||
|
Collectors
|
||||||
|
.groupingBy(
|
||||||
|
p -> p.getQualifier().getClassid(),
|
||||||
|
Collectors.mapping(p -> p, Collectors.toCollection(HashSet::new))));
|
||||||
|
}
|
||||||
|
|
||||||
|
private static Stream<StructuredProperty> pidFromInstance(List<StructuredProperty> pid, KeyValue collectedFrom,
|
||||||
|
boolean mapHandles) {
|
||||||
|
return Optional
|
||||||
|
.ofNullable(pid)
|
||||||
|
.map(
|
||||||
|
pp -> pp
|
||||||
|
.stream()
|
||||||
|
// filter away PIDs provided by a DS that is not considered an authority for the
|
||||||
|
// given PID Type
|
||||||
|
.filter(p -> shouldFilterPidByCriteria(collectedFrom, p, mapHandles))
|
||||||
|
.map(CleaningFunctions::normalizePidValue)
|
||||||
|
.filter(p -> isNotFromDelegatedAuthority(collectedFrom, p))
|
||||||
|
.filter(CleaningFunctions::pidFilter))
|
||||||
|
.orElse(Stream.empty());
|
||||||
|
}
|
||||||
|
|
||||||
|
private static boolean shouldFilterPidByCriteria(KeyValue collectedFrom, StructuredProperty p, boolean mapHandles) {
|
||||||
|
final PidType pType = PidType.tryValueOf(p.getQualifier().getClassid());
|
||||||
|
|
||||||
|
if (Objects.isNull(collectedFrom)) {
|
||||||
|
return false;
|
||||||
|
}
|
||||||
|
|
||||||
|
boolean isEnrich = Optional
|
||||||
|
.ofNullable(ENRICHMENT_PROVIDER.get(pType))
|
||||||
|
.map(
|
||||||
|
enrich -> enrich.containsKey(collectedFrom.getKey())
|
||||||
|
|| enrich.containsValue(collectedFrom.getValue()))
|
||||||
|
.orElse(false);
|
||||||
|
|
||||||
|
boolean isAuthority = Optional
|
||||||
|
.ofNullable(PID_AUTHORITY.get(pType))
|
||||||
|
.map(
|
||||||
|
authorities -> authorities.containsKey(collectedFrom.getKey())
|
||||||
|
|| authorities.containsValue(collectedFrom.getValue()))
|
||||||
|
.orElse(false);
|
||||||
|
|
||||||
|
return (mapHandles && pType.equals(PidType.handle)) || isEnrich || isAuthority;
|
||||||
|
}
|
||||||
|
|
||||||
|
private static boolean isNotFromDelegatedAuthority(KeyValue collectedFrom, StructuredProperty p) {
|
||||||
|
final PidType pType = PidType.tryValueOf(p.getQualifier().getClassid());
|
||||||
|
|
||||||
|
final Map<String, String> da = DELEGATED_PID_AUTHORITY.get(pType);
|
||||||
|
if (Objects.isNull(da)) {
|
||||||
|
return true;
|
||||||
|
}
|
||||||
|
if (!da.containsKey(collectedFrom.getKey())) {
|
||||||
|
return true;
|
||||||
|
}
|
||||||
|
return StringUtils.contains(p.getValue(), da.get(collectedFrom.getKey()));
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* @see {@link IdentifierFactory#createIdentifier(OafEntity, boolean)}
|
||||||
|
*/
|
||||||
|
public static <T extends OafEntity> String createIdentifier(T entity) {
|
||||||
|
|
||||||
|
return createIdentifier(entity, true);
|
||||||
|
}
|
||||||
|
|
||||||
|
private static <T extends OafEntity> String idFromPid(T entity, StructuredProperty s, boolean md5) {
|
||||||
|
return idFromPid(ModelSupport.getIdPrefix(entity.getClass()), s.getQualifier().getClassid(), s.getValue(), md5);
|
||||||
|
}
|
||||||
|
|
||||||
|
public static String idFromPid(String numericPrefix, String pidType, String pidValue, boolean md5) {
|
||||||
|
return new StringBuilder()
|
||||||
|
.append(numericPrefix)
|
||||||
|
.append(ID_PREFIX_SEPARATOR)
|
||||||
|
.append(createPrefix(pidType))
|
||||||
|
.append(ID_SEPARATOR)
|
||||||
|
.append(md5 ? md5(pidValue) : pidValue)
|
||||||
|
.toString();
|
||||||
|
}
|
||||||
|
|
||||||
|
// create the prefix (length = 12)
|
||||||
|
private static String createPrefix(String pidType) {
|
||||||
|
StringBuilder prefix = new StringBuilder(StringUtils.left(pidType, ID_PREFIX_LEN));
|
||||||
|
while (prefix.length() < ID_PREFIX_LEN) {
|
||||||
|
prefix.append("_");
|
||||||
|
}
|
||||||
|
return prefix.substring(0, ID_PREFIX_LEN);
|
||||||
|
}
|
||||||
|
|
||||||
|
public static String md5(final String s) {
|
||||||
|
try {
|
||||||
|
final MessageDigest md = MessageDigest.getInstance("MD5");
|
||||||
|
md.update(s.getBytes(StandardCharsets.UTF_8));
|
||||||
|
return new String(Hex.encodeHex(md.digest()));
|
||||||
|
} catch (final Exception e) {
|
||||||
|
return null;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -0,0 +1,78 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.schema.oaf.utils;
|
||||||
|
|
||||||
|
import java.util.Comparator;
|
||||||
|
import java.util.HashSet;
|
||||||
|
import java.util.Optional;
|
||||||
|
import java.util.stream.Collectors;
|
||||||
|
|
||||||
|
//
|
||||||
|
// Source code recreated from a .class file by IntelliJ IDEA
|
||||||
|
// (powered by FernFlower decompiler)
|
||||||
|
//
|
||||||
|
import eu.dnetlib.dhp.schema.common.EntityType;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.KeyValue;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.Oaf;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.OafEntity;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.Result;
|
||||||
|
|
||||||
|
public class MergeComparator implements Comparator<Oaf> {
|
||||||
|
public MergeComparator() {
|
||||||
|
}
|
||||||
|
|
||||||
|
public int compare(Oaf left, Oaf right) {
|
||||||
|
// nulls at the end
|
||||||
|
if (left == null && right == null) {
|
||||||
|
return 0;
|
||||||
|
} else if (left == null) {
|
||||||
|
return -1;
|
||||||
|
} else if (right == null) {
|
||||||
|
return 1;
|
||||||
|
}
|
||||||
|
|
||||||
|
// invisible
|
||||||
|
if (left.getDataInfo() != null && left.getDataInfo().getInvisible() == true) {
|
||||||
|
if (right.getDataInfo() != null && right.getDataInfo().getInvisible() == false) {
|
||||||
|
return -1;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// collectedfrom
|
||||||
|
HashSet<String> lCf = getCollectedFromIds(left);
|
||||||
|
HashSet<String> rCf = getCollectedFromIds(right);
|
||||||
|
if (lCf.contains("10|openaire____::081b82f96300b6a6e3d282bad31cb6e2")
|
||||||
|
&& !rCf.contains("10|openaire____::081b82f96300b6a6e3d282bad31cb6e2")) {
|
||||||
|
return -1;
|
||||||
|
} else if (!lCf.contains("10|openaire____::081b82f96300b6a6e3d282bad31cb6e2")
|
||||||
|
&& rCf.contains("10|openaire____::081b82f96300b6a6e3d282bad31cb6e2")) {
|
||||||
|
return 1;
|
||||||
|
}
|
||||||
|
|
||||||
|
SubEntityType lClass = SubEntityType.fromClass(left.getClass());
|
||||||
|
SubEntityType rClass = SubEntityType.fromClass(right.getClass());
|
||||||
|
return lClass.ordinal() - rClass.ordinal();
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
|
protected HashSet<String> getCollectedFromIds(Oaf left) {
|
||||||
|
return (HashSet) Optional.ofNullable(left.getCollectedfrom()).map((cf) -> {
|
||||||
|
return (HashSet) cf.stream().map(KeyValue::getKey).collect(Collectors.toCollection(HashSet::new));
|
||||||
|
}).orElse(new HashSet());
|
||||||
|
}
|
||||||
|
|
||||||
|
enum SubEntityType {
|
||||||
|
publication, dataset, software, otherresearchproduct, datasource, organization, project;
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Resolves the EntityType, given the relative class name
|
||||||
|
*
|
||||||
|
* @param clazz the given class name
|
||||||
|
* @param <T> actual OafEntity subclass
|
||||||
|
* @return the EntityType associated to the given class
|
||||||
|
*/
|
||||||
|
public static <T extends Oaf> SubEntityType fromClass(Class<T> clazz) {
|
||||||
|
return valueOf(clazz.getSimpleName().toLowerCase());
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -0,0 +1,106 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.schema.oaf.utils;
|
||||||
|
|
||||||
|
import java.util.*;
|
||||||
|
|
||||||
|
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.Oaf;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.OafEntity;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.Result;
|
||||||
|
|
||||||
|
public class MergeEntitiesComparator implements Comparator<Oaf> {
|
||||||
|
static final List<String> PID_AUTHORITIES = Arrays
|
||||||
|
.asList(
|
||||||
|
ModelConstants.ARXIV_ID,
|
||||||
|
ModelConstants.PUBMED_CENTRAL_ID,
|
||||||
|
ModelConstants.EUROPE_PUBMED_CENTRAL_ID,
|
||||||
|
ModelConstants.DATACITE_ID,
|
||||||
|
ModelConstants.CROSSREF_ID);
|
||||||
|
|
||||||
|
static final List<String> RESULT_TYPES = Arrays
|
||||||
|
.asList(
|
||||||
|
ModelConstants.ORP_RESULTTYPE_CLASSID,
|
||||||
|
ModelConstants.SOFTWARE_RESULTTYPE_CLASSID,
|
||||||
|
ModelConstants.DATASET_RESULTTYPE_CLASSID,
|
||||||
|
ModelConstants.PUBLICATION_RESULTTYPE_CLASSID);
|
||||||
|
|
||||||
|
public static final Comparator<Oaf> INSTANCE = new MergeEntitiesComparator();
|
||||||
|
|
||||||
|
@Override
|
||||||
|
public int compare(Oaf left, Oaf right) {
|
||||||
|
if (left == null && right == null)
|
||||||
|
return 0;
|
||||||
|
if (left == null)
|
||||||
|
return -1;
|
||||||
|
if (right == null)
|
||||||
|
return 1;
|
||||||
|
|
||||||
|
int res = 0;
|
||||||
|
|
||||||
|
// pid authority
|
||||||
|
int cfp1 = Optional
|
||||||
|
.ofNullable(left.getCollectedfrom())
|
||||||
|
.map(
|
||||||
|
cf -> cf
|
||||||
|
.stream()
|
||||||
|
.map(kv -> PID_AUTHORITIES.indexOf(kv.getKey()))
|
||||||
|
.max(Integer::compare)
|
||||||
|
.orElse(-1))
|
||||||
|
.orElse(-1);
|
||||||
|
int cfp2 = Optional
|
||||||
|
.ofNullable(right.getCollectedfrom())
|
||||||
|
.map(
|
||||||
|
cf -> cf
|
||||||
|
.stream()
|
||||||
|
.map(kv -> PID_AUTHORITIES.indexOf(kv.getKey()))
|
||||||
|
.max(Integer::compare)
|
||||||
|
.orElse(-1))
|
||||||
|
.orElse(-1);
|
||||||
|
|
||||||
|
if (cfp1 >= 0 && cfp1 > cfp2) {
|
||||||
|
return 1;
|
||||||
|
} else if (cfp2 >= 0 && cfp2 > cfp1) {
|
||||||
|
return -1;
|
||||||
|
}
|
||||||
|
|
||||||
|
// trust
|
||||||
|
if (left.getDataInfo() != null && right.getDataInfo() != null) {
|
||||||
|
res = left.getDataInfo().getTrust().compareTo(right.getDataInfo().getTrust());
|
||||||
|
}
|
||||||
|
|
||||||
|
// result type
|
||||||
|
if (res == 0) {
|
||||||
|
if (left instanceof Result && right instanceof Result) {
|
||||||
|
Result r1 = (Result) left;
|
||||||
|
Result r2 = (Result) right;
|
||||||
|
|
||||||
|
if (r1.getResulttype() == null || r1.getResulttype().getClassid() == null) {
|
||||||
|
if (r2.getResulttype() != null && r2.getResulttype().getClassid() != null) {
|
||||||
|
return -1;
|
||||||
|
}
|
||||||
|
} else if (r2.getResulttype() == null || r2.getResulttype().getClassid() == null) {
|
||||||
|
return 1;
|
||||||
|
}
|
||||||
|
|
||||||
|
int rt1 = RESULT_TYPES.indexOf(r1.getResulttype().getClassid());
|
||||||
|
int rt2 = RESULT_TYPES.indexOf(r2.getResulttype().getClassid());
|
||||||
|
|
||||||
|
if (rt1 >= 0 && rt1 > rt2) {
|
||||||
|
return 1;
|
||||||
|
} else if (rt2 >= 0 && rt2 > rt1) {
|
||||||
|
return -1;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// id
|
||||||
|
if (res == 0) {
|
||||||
|
if (left instanceof OafEntity && right instanceof OafEntity) {
|
||||||
|
res = ((OafEntity) left).getId().compareTo(((OafEntity) right).getId());
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
return res;
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
File diff suppressed because it is too large
Load Diff
|
@ -0,0 +1,27 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.schema.oaf.utils;
|
||||||
|
|
||||||
|
public class ModelHardLimits {
|
||||||
|
|
||||||
|
private ModelHardLimits() {
|
||||||
|
}
|
||||||
|
|
||||||
|
public static final String LAYOUT = "index";
|
||||||
|
public static final String INTERPRETATION = "openaire";
|
||||||
|
public static final String SEPARATOR = "-";
|
||||||
|
|
||||||
|
public static final int MAX_EXTERNAL_ENTITIES = 50;
|
||||||
|
public static final int MAX_AUTHORS = 200;
|
||||||
|
public static final int MAX_AUTHOR_FULLNAME_LENGTH = 1000;
|
||||||
|
public static final int MAX_TITLE_LENGTH = 5000;
|
||||||
|
public static final int MAX_TITLES = 10;
|
||||||
|
public static final int MAX_ABSTRACTS = 10;
|
||||||
|
public static final int MAX_ABSTRACT_LENGTH = 150000;
|
||||||
|
public static final int MAX_RELATED_ABSTRACT_LENGTH = 500;
|
||||||
|
public static final int MAX_INSTANCES = 10;
|
||||||
|
|
||||||
|
public static String getCollectionName(String format) {
|
||||||
|
return format + SEPARATOR + LAYOUT + SEPARATOR + INTERPRETATION;
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -14,7 +14,6 @@ import java.util.stream.Collectors;
|
||||||
import org.apache.commons.lang3.StringUtils;
|
import org.apache.commons.lang3.StringUtils;
|
||||||
|
|
||||||
import eu.dnetlib.dhp.schema.common.AccessRightComparator;
|
import eu.dnetlib.dhp.schema.common.AccessRightComparator;
|
||||||
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
|
||||||
import eu.dnetlib.dhp.schema.oaf.*;
|
import eu.dnetlib.dhp.schema.oaf.*;
|
||||||
|
|
||||||
public class OafMapperUtils {
|
public class OafMapperUtils {
|
||||||
|
@ -22,65 +21,6 @@ public class OafMapperUtils {
|
||||||
private OafMapperUtils() {
|
private OafMapperUtils() {
|
||||||
}
|
}
|
||||||
|
|
||||||
public static Oaf merge(final Oaf left, final Oaf right) {
|
|
||||||
if (ModelSupport.isSubClass(left, OafEntity.class)) {
|
|
||||||
return mergeEntities((OafEntity) left, (OafEntity) right);
|
|
||||||
} else if (ModelSupport.isSubClass(left, Relation.class)) {
|
|
||||||
((Relation) left).mergeFrom((Relation) right);
|
|
||||||
} else {
|
|
||||||
throw new IllegalArgumentException("invalid Oaf type:" + left.getClass().getCanonicalName());
|
|
||||||
}
|
|
||||||
return left;
|
|
||||||
}
|
|
||||||
|
|
||||||
public static OafEntity mergeEntities(OafEntity left, OafEntity right) {
|
|
||||||
if (ModelSupport.isSubClass(left, Result.class)) {
|
|
||||||
return mergeResults((Result) left, (Result) right);
|
|
||||||
} else if (ModelSupport.isSubClass(left, Datasource.class)) {
|
|
||||||
left.mergeFrom(right);
|
|
||||||
} else if (ModelSupport.isSubClass(left, Organization.class)) {
|
|
||||||
left.mergeFrom(right);
|
|
||||||
} else if (ModelSupport.isSubClass(left, Project.class)) {
|
|
||||||
left.mergeFrom(right);
|
|
||||||
} else {
|
|
||||||
throw new IllegalArgumentException("invalid OafEntity subtype:" + left.getClass().getCanonicalName());
|
|
||||||
}
|
|
||||||
return left;
|
|
||||||
}
|
|
||||||
|
|
||||||
public static Result mergeResults(Result left, Result right) {
|
|
||||||
|
|
||||||
final boolean leftFromDelegatedAuthority = isFromDelegatedAuthority(left);
|
|
||||||
final boolean rightFromDelegatedAuthority = isFromDelegatedAuthority(right);
|
|
||||||
|
|
||||||
if (leftFromDelegatedAuthority && !rightFromDelegatedAuthority) {
|
|
||||||
return left;
|
|
||||||
}
|
|
||||||
if (!leftFromDelegatedAuthority && rightFromDelegatedAuthority) {
|
|
||||||
return right;
|
|
||||||
}
|
|
||||||
|
|
||||||
if (new ResultTypeComparator().compare(left, right) < 0) {
|
|
||||||
left.mergeFrom(right);
|
|
||||||
return left;
|
|
||||||
} else {
|
|
||||||
right.mergeFrom(left);
|
|
||||||
return right;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
private static boolean isFromDelegatedAuthority(Result r) {
|
|
||||||
return Optional
|
|
||||||
.ofNullable(r.getInstance())
|
|
||||||
.map(
|
|
||||||
instance -> instance
|
|
||||||
.stream()
|
|
||||||
.filter(i -> Objects.nonNull(i.getCollectedfrom()))
|
|
||||||
.map(i -> i.getCollectedfrom().getKey())
|
|
||||||
.anyMatch(cfId -> IdentifierFactory.delegatedAuthorityDatasourceIds().contains(cfId)))
|
|
||||||
.orElse(false);
|
|
||||||
}
|
|
||||||
|
|
||||||
public static KeyValue keyValue(final String k, final String v) {
|
public static KeyValue keyValue(final String k, final String v) {
|
||||||
final KeyValue kv = new KeyValue();
|
final KeyValue kv = new KeyValue();
|
||||||
kv.setKey(k);
|
kv.setKey(k);
|
||||||
|
|
|
@ -0,0 +1,46 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.schema.oaf.utils;
|
||||||
|
|
||||||
|
import java.util.Comparator;
|
||||||
|
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
|
||||||
|
|
||||||
|
public class OrganizationPidComparator implements Comparator<StructuredProperty> {
|
||||||
|
|
||||||
|
@Override
|
||||||
|
public int compare(StructuredProperty left, StructuredProperty right) {
|
||||||
|
if (left == null) {
|
||||||
|
return right == null ? 0 : -1;
|
||||||
|
} else if (right == null) {
|
||||||
|
return 1;
|
||||||
|
}
|
||||||
|
|
||||||
|
PidType lClass = PidType.tryValueOf(left.getQualifier().getClassid());
|
||||||
|
PidType rClass = PidType.tryValueOf(right.getQualifier().getClassid());
|
||||||
|
|
||||||
|
if (lClass.equals(rClass))
|
||||||
|
return 0;
|
||||||
|
|
||||||
|
if (lClass.equals(PidType.openorgs))
|
||||||
|
return -1;
|
||||||
|
if (rClass.equals(PidType.openorgs))
|
||||||
|
return 1;
|
||||||
|
|
||||||
|
if (lClass.equals(PidType.GRID))
|
||||||
|
return -1;
|
||||||
|
if (rClass.equals(PidType.GRID))
|
||||||
|
return 1;
|
||||||
|
|
||||||
|
if (lClass.equals(PidType.mag_id))
|
||||||
|
return -1;
|
||||||
|
if (rClass.equals(PidType.mag_id))
|
||||||
|
return 1;
|
||||||
|
|
||||||
|
if (lClass.equals(PidType.urn))
|
||||||
|
return -1;
|
||||||
|
if (rClass.equals(PidType.urn))
|
||||||
|
return 1;
|
||||||
|
|
||||||
|
return 0;
|
||||||
|
}
|
||||||
|
}
|
|
@ -0,0 +1,8 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.schema.oaf.utils;
|
||||||
|
|
||||||
|
import java.util.HashMap;
|
||||||
|
import java.util.HashSet;
|
||||||
|
|
||||||
|
public class PidBlacklist extends HashMap<String, HashSet<String>> {
|
||||||
|
}
|
|
@ -0,0 +1,40 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.schema.oaf.utils;
|
||||||
|
|
||||||
|
import java.io.IOException;
|
||||||
|
import java.util.HashSet;
|
||||||
|
import java.util.Optional;
|
||||||
|
import java.util.Set;
|
||||||
|
|
||||||
|
import org.apache.commons.io.IOUtils;
|
||||||
|
|
||||||
|
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||||
|
|
||||||
|
public class PidBlacklistProvider {
|
||||||
|
|
||||||
|
private static final PidBlacklist blacklist;
|
||||||
|
|
||||||
|
static {
|
||||||
|
try {
|
||||||
|
String json = IOUtils.toString(IdentifierFactory.class.getResourceAsStream("pid_blacklist.json"));
|
||||||
|
blacklist = new ObjectMapper().readValue(json, PidBlacklist.class);
|
||||||
|
|
||||||
|
} catch (IOException e) {
|
||||||
|
throw new RuntimeException(e);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
public static PidBlacklist getBlacklist() {
|
||||||
|
return blacklist;
|
||||||
|
}
|
||||||
|
|
||||||
|
public static Set<String> getBlacklist(String pidType) {
|
||||||
|
return Optional
|
||||||
|
.ofNullable(getBlacklist().get(pidType))
|
||||||
|
.orElse(new HashSet<>());
|
||||||
|
}
|
||||||
|
|
||||||
|
private PidBlacklistProvider() {
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -0,0 +1,48 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.schema.oaf.utils;
|
||||||
|
|
||||||
|
import java.util.Comparator;
|
||||||
|
|
||||||
|
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.OafEntity;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.Organization;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.Result;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
|
||||||
|
|
||||||
|
public class PidComparator<T extends OafEntity> implements Comparator<StructuredProperty> {
|
||||||
|
|
||||||
|
private final T entity;
|
||||||
|
|
||||||
|
public PidComparator(T entity) {
|
||||||
|
this.entity = entity;
|
||||||
|
}
|
||||||
|
|
||||||
|
@Override
|
||||||
|
public int compare(StructuredProperty left, StructuredProperty right) {
|
||||||
|
|
||||||
|
if (left == null && right == null)
|
||||||
|
return 0;
|
||||||
|
if (left == null)
|
||||||
|
return 1;
|
||||||
|
if (right == null)
|
||||||
|
return -1;
|
||||||
|
|
||||||
|
if (ModelSupport.isSubClass(entity, Result.class)) {
|
||||||
|
return compareResultPids(left, right);
|
||||||
|
}
|
||||||
|
if (ModelSupport.isSubClass(entity, Organization.class)) {
|
||||||
|
return compareOrganizationtPids(left, right);
|
||||||
|
}
|
||||||
|
|
||||||
|
// Else (but unlikely), lexicographical ordering will do.
|
||||||
|
return left.getQualifier().getClassid().compareTo(right.getQualifier().getClassid());
|
||||||
|
}
|
||||||
|
|
||||||
|
private int compareResultPids(StructuredProperty left, StructuredProperty right) {
|
||||||
|
return new ResultPidComparator().compare(left, right);
|
||||||
|
}
|
||||||
|
|
||||||
|
private int compareOrganizationtPids(StructuredProperty left, StructuredProperty right) {
|
||||||
|
return new OrganizationPidComparator().compare(left, right);
|
||||||
|
}
|
||||||
|
}
|
|
@ -0,0 +1,79 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.schema.oaf.utils;
|
||||||
|
|
||||||
|
import org.apache.commons.lang3.EnumUtils;
|
||||||
|
|
||||||
|
public enum PidType {
|
||||||
|
|
||||||
|
/**
|
||||||
|
* The DOI syntax shall be made up of a DOI prefix and a DOI suffix separated by a forward slash.
|
||||||
|
*
|
||||||
|
* There is no defined limit on the length of the DOI name, or of the DOI prefix or DOI suffix.
|
||||||
|
*
|
||||||
|
* The DOI name is case-insensitive and can incorporate any printable characters from the legal graphic characters
|
||||||
|
* of Unicode. Further constraints on character use (e.g. use of language-specific alphanumeric characters) can be
|
||||||
|
* defined for an application by the ISO 26324 Registration Authority.
|
||||||
|
*
|
||||||
|
*
|
||||||
|
* DOI prefix: The DOI prefix shall be composed of a directory indicator followed by a registrant code.
|
||||||
|
* These two components shall be separated by a full stop (period). The directory indicator shall be "10" and
|
||||||
|
* distinguishes the entire set of character strings (prefix and suffix) as digital object identifiers within the
|
||||||
|
* resolution system.
|
||||||
|
*
|
||||||
|
* Registrant code: The second element of the DOI prefix shall be the registrant code. The registrant code is a
|
||||||
|
* unique string assigned to a registrant.
|
||||||
|
*
|
||||||
|
* DOI suffix: The DOI suffix shall consist of a character string of any length chosen by the registrant.
|
||||||
|
* Each suffix shall be unique to the prefix element that precedes it. The unique suffix can be a sequential number,
|
||||||
|
* or it might incorporate an identifier generated from or based on another system used by the registrant
|
||||||
|
* (e.g. ISAN, ISBN, ISRC, ISSN, ISTC, ISNI; in such cases, a preferred construction for such a suffix can be
|
||||||
|
* specified, as in Example 1).
|
||||||
|
*
|
||||||
|
* Source: https://www.doi.org/doi_handbook/2_Numbering.html#2.2
|
||||||
|
*/
|
||||||
|
doi,
|
||||||
|
|
||||||
|
/**
|
||||||
|
* PubMed Unique Identifier (PMID)
|
||||||
|
*
|
||||||
|
* This field is a 1-to-8 digit accession number with no leading zeros. It is present on all records and is the
|
||||||
|
* accession number for managing and disseminating records. PMIDs are not reused after records are deleted.
|
||||||
|
*
|
||||||
|
* Beginning in February 2012 PMIDs include extensions following a decimal point to account for article versions
|
||||||
|
* (e.g., 21804956.2). All citations are considered version 1 until replaced. The extended PMID is not displayed
|
||||||
|
* on the MEDLINE format.
|
||||||
|
*
|
||||||
|
* View the citation in abstract format in PubMed to access additional versions when available (see the article in
|
||||||
|
* the Jan-Feb 2012 NLM Technical Bulletin).
|
||||||
|
*
|
||||||
|
* Source: https://www.nlm.nih.gov/bsd/mms/medlineelements.html#pmid
|
||||||
|
*/
|
||||||
|
pmid,
|
||||||
|
|
||||||
|
/**
|
||||||
|
* This field contains the unique identifier for the cited article in PubMed Central. The identifier begins with the
|
||||||
|
* prefix PMC.
|
||||||
|
*
|
||||||
|
* Source: https://www.nlm.nih.gov/bsd/mms/medlineelements.html#pmc
|
||||||
|
*/
|
||||||
|
pmc, handle, arXiv, nct, pdb, w3id,
|
||||||
|
|
||||||
|
// Organization
|
||||||
|
openorgs, ROR, GRID, PIC, ISNI, Wikidata, FundRef, corda, corda_h2020, mag_id, urn,
|
||||||
|
|
||||||
|
// Used by dedup
|
||||||
|
undefined, original;
|
||||||
|
|
||||||
|
public static boolean isValid(String type) {
|
||||||
|
return EnumUtils.isValidEnum(PidType.class, type);
|
||||||
|
}
|
||||||
|
|
||||||
|
public static PidType tryValueOf(String s) {
|
||||||
|
try {
|
||||||
|
return PidType.valueOf(s);
|
||||||
|
} catch (Exception e) {
|
||||||
|
return PidType.original;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -0,0 +1,33 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.schema.oaf.utils;
|
||||||
|
|
||||||
|
import java.util.Comparator;
|
||||||
|
import java.util.Optional;
|
||||||
|
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
|
||||||
|
|
||||||
|
public class PidValueComparator implements Comparator<StructuredProperty> {
|
||||||
|
|
||||||
|
@Override
|
||||||
|
public int compare(StructuredProperty left, StructuredProperty right) {
|
||||||
|
|
||||||
|
if (left == null && right == null)
|
||||||
|
return 0;
|
||||||
|
if (left == null)
|
||||||
|
return 1;
|
||||||
|
if (right == null)
|
||||||
|
return -1;
|
||||||
|
|
||||||
|
StructuredProperty l = CleaningFunctions.normalizePidValue(left);
|
||||||
|
StructuredProperty r = CleaningFunctions.normalizePidValue(right);
|
||||||
|
|
||||||
|
return Optional
|
||||||
|
.ofNullable(l.getValue())
|
||||||
|
.map(
|
||||||
|
lv -> Optional
|
||||||
|
.ofNullable(r.getValue())
|
||||||
|
.map(rv -> lv.compareTo(rv))
|
||||||
|
.orElse(-1))
|
||||||
|
.orElse(1);
|
||||||
|
}
|
||||||
|
}
|
|
@ -0,0 +1,46 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.schema.oaf.utils;
|
||||||
|
|
||||||
|
import java.util.Comparator;
|
||||||
|
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.Qualifier;
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Comparator for sorting the values from the dnet:review_levels vocabulary, implements the following ordering
|
||||||
|
*
|
||||||
|
* peerReviewed (0001) > nonPeerReviewed (0002) > UNKNOWN (0000)
|
||||||
|
*/
|
||||||
|
public class RefereedComparator implements Comparator<Qualifier> {
|
||||||
|
|
||||||
|
@Override
|
||||||
|
public int compare(Qualifier left, Qualifier right) {
|
||||||
|
if (left == null || left.getClassid() == null) {
|
||||||
|
return (right == null || right.getClassid() == null) ? 0 : -1;
|
||||||
|
} else if (right == null || right.getClassid() == null) {
|
||||||
|
return 1;
|
||||||
|
}
|
||||||
|
|
||||||
|
String lClass = left.getClassid();
|
||||||
|
String rClass = right.getClassid();
|
||||||
|
|
||||||
|
if (lClass.equals(rClass))
|
||||||
|
return 0;
|
||||||
|
|
||||||
|
if ("0001".equals(lClass))
|
||||||
|
return -1;
|
||||||
|
if ("0001".equals(rClass))
|
||||||
|
return 1;
|
||||||
|
|
||||||
|
if ("0002".equals(lClass))
|
||||||
|
return -1;
|
||||||
|
if ("0002".equals(rClass))
|
||||||
|
return 1;
|
||||||
|
|
||||||
|
if ("0000".equals(lClass))
|
||||||
|
return -1;
|
||||||
|
if ("0000".equals(rClass))
|
||||||
|
return 1;
|
||||||
|
|
||||||
|
return 0;
|
||||||
|
}
|
||||||
|
}
|
|
@ -0,0 +1,56 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.schema.oaf.utils;
|
||||||
|
|
||||||
|
import java.util.Comparator;
|
||||||
|
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
|
||||||
|
|
||||||
|
public class ResultPidComparator implements Comparator<StructuredProperty> {
|
||||||
|
|
||||||
|
@Override
|
||||||
|
public int compare(StructuredProperty left, StructuredProperty right) {
|
||||||
|
|
||||||
|
PidType lClass = PidType.tryValueOf(left.getQualifier().getClassid());
|
||||||
|
PidType rClass = PidType.tryValueOf(right.getQualifier().getClassid());
|
||||||
|
|
||||||
|
if (lClass.equals(rClass))
|
||||||
|
return 0;
|
||||||
|
|
||||||
|
if (lClass.equals(PidType.doi))
|
||||||
|
return -1;
|
||||||
|
if (rClass.equals(PidType.doi))
|
||||||
|
return 1;
|
||||||
|
|
||||||
|
if (lClass.equals(PidType.pmid))
|
||||||
|
return -1;
|
||||||
|
if (rClass.equals(PidType.pmid))
|
||||||
|
return 1;
|
||||||
|
|
||||||
|
if (lClass.equals(PidType.pmc))
|
||||||
|
return -1;
|
||||||
|
if (rClass.equals(PidType.pmc))
|
||||||
|
return 1;
|
||||||
|
|
||||||
|
if (lClass.equals(PidType.handle))
|
||||||
|
return -1;
|
||||||
|
if (rClass.equals(PidType.handle))
|
||||||
|
return 1;
|
||||||
|
|
||||||
|
if (lClass.equals(PidType.arXiv))
|
||||||
|
return -1;
|
||||||
|
if (rClass.equals(PidType.arXiv))
|
||||||
|
return 1;
|
||||||
|
|
||||||
|
if (lClass.equals(PidType.nct))
|
||||||
|
return -1;
|
||||||
|
if (rClass.equals(PidType.nct))
|
||||||
|
return 1;
|
||||||
|
|
||||||
|
if (lClass.equals(PidType.pdb))
|
||||||
|
return -1;
|
||||||
|
if (rClass.equals(PidType.pdb))
|
||||||
|
return 1;
|
||||||
|
|
||||||
|
return 0;
|
||||||
|
}
|
||||||
|
}
|
|
@ -0,0 +1,101 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.pace.common;
|
||||||
|
|
||||||
|
import java.nio.charset.StandardCharsets;
|
||||||
|
import java.text.Normalizer;
|
||||||
|
import java.util.Set;
|
||||||
|
import java.util.regex.Matcher;
|
||||||
|
import java.util.regex.Pattern;
|
||||||
|
|
||||||
|
import org.apache.commons.io.IOUtils;
|
||||||
|
import org.apache.commons.lang3.StringUtils;
|
||||||
|
|
||||||
|
import com.google.common.base.Splitter;
|
||||||
|
import com.google.common.collect.Iterables;
|
||||||
|
import com.google.common.collect.Sets;
|
||||||
|
import com.ibm.icu.text.Transliterator;
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Set of common functions for the framework
|
||||||
|
*
|
||||||
|
* @author claudio
|
||||||
|
*/
|
||||||
|
public class PaceCommonUtils {
|
||||||
|
|
||||||
|
// transliterator
|
||||||
|
protected static Transliterator transliterator = Transliterator.getInstance("Any-Eng");
|
||||||
|
|
||||||
|
protected static final String aliases_from = "⁰¹²³⁴⁵⁶⁷⁸⁹⁺⁻⁼⁽⁾ⁿ₀₁₂₃₄₅₆₇₈₉₊₋₌₍₎àáâäæãåāèéêëēėęəîïíīįìôöòóœøōõûüùúūßśšłžźżçćčñń";
|
||||||
|
protected static final String aliases_to = "0123456789+-=()n0123456789+-=()aaaaaaaaeeeeeeeeiiiiiioooooooouuuuussslzzzcccnn";
|
||||||
|
|
||||||
|
protected static Pattern hexUnicodePattern = Pattern.compile("\\\\u(\\p{XDigit}{4})");
|
||||||
|
|
||||||
|
protected static String fixAliases(final String s) {
|
||||||
|
final StringBuilder sb = new StringBuilder();
|
||||||
|
|
||||||
|
s.chars().forEach(ch -> {
|
||||||
|
final int i = StringUtils.indexOf(aliases_from, ch);
|
||||||
|
sb.append(i >= 0 ? aliases_to.charAt(i) : (char) ch);
|
||||||
|
});
|
||||||
|
|
||||||
|
return sb.toString();
|
||||||
|
}
|
||||||
|
|
||||||
|
protected static String transliterate(final String s) {
|
||||||
|
try {
|
||||||
|
return transliterator.transliterate(s);
|
||||||
|
} catch (Exception e) {
|
||||||
|
return s;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
public static String normalize(final String s) {
|
||||||
|
return fixAliases(transliterate(nfd(unicodeNormalization(s))))
|
||||||
|
.toLowerCase()
|
||||||
|
// do not compact the regexes in a single expression, would cause StackOverflowError in case of large input
|
||||||
|
// strings
|
||||||
|
.replaceAll("[^ \\w]+", "")
|
||||||
|
.replaceAll("(\\p{InCombiningDiacriticalMarks})+", "")
|
||||||
|
.replaceAll("(\\p{Punct})+", " ")
|
||||||
|
.replaceAll("(\\d)+", " ")
|
||||||
|
.replaceAll("(\\n)+", " ")
|
||||||
|
.trim();
|
||||||
|
}
|
||||||
|
|
||||||
|
public static String nfd(final String s) {
|
||||||
|
return Normalizer.normalize(s, Normalizer.Form.NFD);
|
||||||
|
}
|
||||||
|
|
||||||
|
public static String unicodeNormalization(final String s) {
|
||||||
|
|
||||||
|
Matcher m = hexUnicodePattern.matcher(s);
|
||||||
|
StringBuffer buf = new StringBuffer(s.length());
|
||||||
|
while (m.find()) {
|
||||||
|
String ch = String.valueOf((char) Integer.parseInt(m.group(1), 16));
|
||||||
|
m.appendReplacement(buf, Matcher.quoteReplacement(ch));
|
||||||
|
}
|
||||||
|
m.appendTail(buf);
|
||||||
|
return buf.toString();
|
||||||
|
}
|
||||||
|
|
||||||
|
public static Set<String> loadFromClasspath(final String classpath) {
|
||||||
|
|
||||||
|
Transliterator transliterator = Transliterator.getInstance("Any-Eng");
|
||||||
|
|
||||||
|
final Set<String> h = Sets.newHashSet();
|
||||||
|
try {
|
||||||
|
for (final String s : IOUtils
|
||||||
|
.readLines(PaceCommonUtils.class.getResourceAsStream(classpath), StandardCharsets.UTF_8)) {
|
||||||
|
h.add(fixAliases(transliterator.transliterate(s))); // transliteration of the stopwords
|
||||||
|
}
|
||||||
|
} catch (final Throwable e) {
|
||||||
|
return Sets.newHashSet();
|
||||||
|
}
|
||||||
|
return h;
|
||||||
|
}
|
||||||
|
|
||||||
|
protected static Iterable<String> tokens(final String s, final int maxTokens) {
|
||||||
|
return Iterables.limit(Splitter.on(" ").omitEmptyStrings().trimResults().split(s), maxTokens);
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -12,7 +12,7 @@ import com.google.common.collect.Iterables;
|
||||||
import com.google.common.collect.Lists;
|
import com.google.common.collect.Lists;
|
||||||
import com.google.common.hash.Hashing;
|
import com.google.common.hash.Hashing;
|
||||||
|
|
||||||
import eu.dnetlib.pace.common.AbstractPaceFunctions;
|
import eu.dnetlib.pace.common.PaceCommonUtils;
|
||||||
import eu.dnetlib.pace.util.Capitalise;
|
import eu.dnetlib.pace.util.Capitalise;
|
||||||
import eu.dnetlib.pace.util.DotAbbreviations;
|
import eu.dnetlib.pace.util.DotAbbreviations;
|
||||||
|
|
||||||
|
@ -86,7 +86,7 @@ public class Person {
|
||||||
|
|
||||||
private List<String> splitTerms(final String s) {
|
private List<String> splitTerms(final String s) {
|
||||||
if (particles == null) {
|
if (particles == null) {
|
||||||
particles = AbstractPaceFunctions.loadFromClasspath("/eu/dnetlib/pace/config/name_particles.txt");
|
particles = PaceCommonUtils.loadFromClasspath("/eu/dnetlib/pace/config/name_particles.txt");
|
||||||
}
|
}
|
||||||
|
|
||||||
final List<String> list = Lists.newArrayList();
|
final List<String> list = Lists.newArrayList();
|
|
@ -15,4 +15,4 @@ public class Capitalise implements Function<String, String> {
|
||||||
public String apply(final String s) {
|
public String apply(final String s) {
|
||||||
return WordUtils.capitalize(s.toLowerCase(), DELIM);
|
return WordUtils.capitalize(s.toLowerCase(), DELIM);
|
||||||
}
|
}
|
||||||
};
|
}
|
|
@ -8,4 +8,4 @@ public class DotAbbreviations implements Function<String, String> {
|
||||||
public String apply(String s) {
|
public String apply(String s) {
|
||||||
return s.length() == 1 ? s + "." : s;
|
return s.length() == 1 ? s + "." : s;
|
||||||
}
|
}
|
||||||
};
|
}
|
|
@ -154,5 +154,13 @@
|
||||||
"unknown":{
|
"unknown":{
|
||||||
"original":"Unknown",
|
"original":"Unknown",
|
||||||
"inverse":"Unknown"
|
"inverse":"Unknown"
|
||||||
|
},
|
||||||
|
"isamongtopnsimilardocuments": {
|
||||||
|
"original": "IsAmongTopNSimilarDocuments",
|
||||||
|
"inverse": "HasAmongTopNSimilarDocuments"
|
||||||
|
},
|
||||||
|
"hasamongtopnsimilardocuments": {
|
||||||
|
"original": "HasAmongTopNSimilarDocuments",
|
||||||
|
"inverse": "IsAmongTopNSimilarDocuments"
|
||||||
}
|
}
|
||||||
}
|
}
|
|
@ -1,5 +1,8 @@
|
||||||
package eu.dnetlib.dhp.application
|
package eu.dnetlib.dhp.application
|
||||||
|
|
||||||
|
import eu.dnetlib.dhp.common.Constants
|
||||||
|
import eu.dnetlib.dhp.utils.DHPUtils.writeHdfsFile
|
||||||
|
|
||||||
import scala.io.Source
|
import scala.io.Source
|
||||||
|
|
||||||
/** This is the main Interface SparkApplication
|
/** This is the main Interface SparkApplication
|
||||||
|
@ -62,12 +65,22 @@ abstract class AbstractScalaApplication(
|
||||||
val conf: SparkConf = new SparkConf()
|
val conf: SparkConf = new SparkConf()
|
||||||
val master = parser.get("master")
|
val master = parser.get("master")
|
||||||
log.info(s"Creating Spark session: Master: $master")
|
log.info(s"Creating Spark session: Master: $master")
|
||||||
SparkSession
|
val b = SparkSession
|
||||||
.builder()
|
.builder()
|
||||||
.config(conf)
|
.config(conf)
|
||||||
.appName(getClass.getSimpleName)
|
.appName(getClass.getSimpleName)
|
||||||
.master(master)
|
if (master != null)
|
||||||
.getOrCreate()
|
b.master(master)
|
||||||
|
b.getOrCreate()
|
||||||
|
}
|
||||||
|
|
||||||
|
def reportTotalSize(targetPath: String, outputBasePath: String): Unit = {
|
||||||
|
val total_items = spark.read.text(targetPath).count()
|
||||||
|
writeHdfsFile(
|
||||||
|
spark.sparkContext.hadoopConfiguration,
|
||||||
|
s"$total_items",
|
||||||
|
outputBasePath + Constants.MDSTORE_SIZE_PATH
|
||||||
|
)
|
||||||
}
|
}
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
|
@ -65,7 +65,11 @@ object ScholixUtils extends Serializable {
|
||||||
}
|
}
|
||||||
|
|
||||||
def generateScholixResourceFromResult(r: Result): ScholixResource = {
|
def generateScholixResourceFromResult(r: Result): ScholixResource = {
|
||||||
|
val sum = ScholixUtils.resultToSummary(r)
|
||||||
|
if (sum != null)
|
||||||
generateScholixResourceFromSummary(ScholixUtils.resultToSummary(r))
|
generateScholixResourceFromSummary(ScholixUtils.resultToSummary(r))
|
||||||
|
else
|
||||||
|
null
|
||||||
}
|
}
|
||||||
|
|
||||||
val statsAggregator: Aggregator[(String, String, Long), RelatedEntities, RelatedEntities] =
|
val statsAggregator: Aggregator[(String, String, Long), RelatedEntities, RelatedEntities] =
|
||||||
|
@ -153,6 +157,14 @@ object ScholixUtils extends Serializable {
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
|
def invRel(rel: String): String = {
|
||||||
|
val semanticRelation = relations.getOrElse(rel.toLowerCase, null)
|
||||||
|
if (semanticRelation != null)
|
||||||
|
semanticRelation.inverse
|
||||||
|
else
|
||||||
|
null
|
||||||
|
}
|
||||||
|
|
||||||
def extractCollectedFrom(summary: ScholixResource): List[ScholixEntityId] = {
|
def extractCollectedFrom(summary: ScholixResource): List[ScholixEntityId] = {
|
||||||
if (summary.getCollectedFrom != null && !summary.getCollectedFrom.isEmpty) {
|
if (summary.getCollectedFrom != null && !summary.getCollectedFrom.isEmpty) {
|
||||||
val l: List[ScholixEntityId] = summary.getCollectedFrom.asScala.map { d =>
|
val l: List[ScholixEntityId] = summary.getCollectedFrom.asScala.map { d =>
|
||||||
|
@ -377,10 +389,7 @@ object ScholixUtils extends Serializable {
|
||||||
if (persistentIdentifiers.isEmpty)
|
if (persistentIdentifiers.isEmpty)
|
||||||
return null
|
return null
|
||||||
s.setLocalIdentifier(persistentIdentifiers.asJava)
|
s.setLocalIdentifier(persistentIdentifiers.asJava)
|
||||||
if (r.isInstanceOf[Publication])
|
// s.setTypology(r.getResulttype.getClassid)
|
||||||
s.setTypology(Typology.publication)
|
|
||||||
else
|
|
||||||
s.setTypology(Typology.dataset)
|
|
||||||
|
|
||||||
s.setSubType(r.getInstance().get(0).getInstancetype.getClassname)
|
s.setSubType(r.getInstance().get(0).getInstancetype.getClassname)
|
||||||
|
|
||||||
|
|
|
@ -0,0 +1,21 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.schema.oaf.utils;
|
||||||
|
|
||||||
|
import java.util.Set;
|
||||||
|
|
||||||
|
import org.junit.jupiter.api.Assertions;
|
||||||
|
import org.junit.jupiter.api.Test;
|
||||||
|
|
||||||
|
class BlackListProviderTest {
|
||||||
|
|
||||||
|
@Test
|
||||||
|
void blackListTest() {
|
||||||
|
|
||||||
|
Assertions.assertNotNull(PidBlacklistProvider.getBlacklist());
|
||||||
|
Assertions.assertNotNull(PidBlacklistProvider.getBlacklist().get("doi"));
|
||||||
|
Assertions.assertTrue(PidBlacklistProvider.getBlacklist().get("doi").size() > 0);
|
||||||
|
final Set<String> xxx = PidBlacklistProvider.getBlacklist("xxx");
|
||||||
|
Assertions.assertNotNull(xxx);
|
||||||
|
Assertions.assertEquals(0, xxx.size());
|
||||||
|
}
|
||||||
|
}
|
|
@ -0,0 +1,87 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.schema.oaf.utils;
|
||||||
|
|
||||||
|
import static org.junit.jupiter.api.Assertions.assertEquals;
|
||||||
|
import static org.junit.jupiter.api.Assertions.assertNotNull;
|
||||||
|
|
||||||
|
import java.io.IOException;
|
||||||
|
|
||||||
|
import org.apache.commons.io.IOUtils;
|
||||||
|
import org.junit.jupiter.api.Test;
|
||||||
|
|
||||||
|
import com.fasterxml.jackson.databind.DeserializationFeature;
|
||||||
|
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||||
|
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.Publication;
|
||||||
|
|
||||||
|
class IdentifierFactoryTest {
|
||||||
|
|
||||||
|
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper()
|
||||||
|
.configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false);
|
||||||
|
|
||||||
|
@Test
|
||||||
|
void testCreateIdentifierForPublication() throws IOException {
|
||||||
|
|
||||||
|
verifyIdentifier(
|
||||||
|
"publication_doi1.json", "50|doi_________::79dbc7a2a56dc1532659f9038843256e", true);
|
||||||
|
|
||||||
|
verifyIdentifier(
|
||||||
|
"publication_doi2.json", "50|doi_________::79dbc7a2a56dc1532659f9038843256e", true);
|
||||||
|
|
||||||
|
verifyIdentifier(
|
||||||
|
"publication_doi3.json", "50|pmc_________::94e4cb08c93f8733b48e2445d04002ac", true);
|
||||||
|
|
||||||
|
verifyIdentifier(
|
||||||
|
"publication_doi4.json", "50|od______2852::38861c44e6052a8d49f59a4c39ba5e66", true);
|
||||||
|
|
||||||
|
verifyIdentifier(
|
||||||
|
"publication_doi5.json", "50|doi_________::3bef95c0ca26dd55451fc8839ea69d27", true);
|
||||||
|
|
||||||
|
verifyIdentifier(
|
||||||
|
"publication_pmc1.json", "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f", true);
|
||||||
|
|
||||||
|
verifyIdentifier(
|
||||||
|
"publication_pmc2.json", "50|pmc_________::94e4cb08c93f8733b48e2445d04002ac", true);
|
||||||
|
|
||||||
|
verifyIdentifier(
|
||||||
|
"publication_openapc.json", "50|doi_________::79dbc7a2a56dc1532659f9038843256e", true);
|
||||||
|
|
||||||
|
final String defaultID = "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f";
|
||||||
|
verifyIdentifier("publication_3.json", defaultID, true);
|
||||||
|
verifyIdentifier("publication_4.json", defaultID, true);
|
||||||
|
verifyIdentifier("publication_5.json", defaultID, true);
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
|
@Test
|
||||||
|
void testCreateIdentifierForPublicationNoHash() throws IOException {
|
||||||
|
|
||||||
|
verifyIdentifier("publication_doi1.json", "50|doi_________::10.1016/j.cmet.2010.03.013", false);
|
||||||
|
verifyIdentifier("publication_doi2.json", "50|doi_________::10.1016/j.cmet.2010.03.013", false);
|
||||||
|
verifyIdentifier("publication_pmc1.json", "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f", false);
|
||||||
|
verifyIdentifier(
|
||||||
|
"publication_urn1.json", "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f", false);
|
||||||
|
|
||||||
|
final String defaultID = "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f";
|
||||||
|
verifyIdentifier("publication_3.json", defaultID, false);
|
||||||
|
verifyIdentifier("publication_4.json", defaultID, false);
|
||||||
|
verifyIdentifier("publication_5.json", defaultID, false);
|
||||||
|
}
|
||||||
|
|
||||||
|
@Test
|
||||||
|
void testCreateIdentifierForROHub() throws IOException {
|
||||||
|
verifyIdentifier(
|
||||||
|
"orp-rohub.json", "50|w3id________::afc7592914ae190a50570db90f55f9c2", true);
|
||||||
|
}
|
||||||
|
|
||||||
|
protected void verifyIdentifier(String filename, String expectedID, boolean md5) throws IOException {
|
||||||
|
final String json = IOUtils.toString(getClass().getResourceAsStream(filename));
|
||||||
|
final Publication pub = OBJECT_MAPPER.readValue(json, Publication.class);
|
||||||
|
|
||||||
|
String id = IdentifierFactory.createIdentifier(pub, md5);
|
||||||
|
System.out.println(id);
|
||||||
|
assertNotNull(id);
|
||||||
|
assertEquals(expectedID, id);
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -0,0 +1,130 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.schema.oaf.utils;
|
||||||
|
|
||||||
|
import static org.junit.jupiter.api.Assertions.*;
|
||||||
|
import static org.junit.jupiter.api.Assertions.assertEquals;
|
||||||
|
|
||||||
|
import java.io.IOException;
|
||||||
|
import java.lang.reflect.InvocationTargetException;
|
||||||
|
import java.util.HashSet;
|
||||||
|
import java.util.List;
|
||||||
|
import java.util.stream.Collectors;
|
||||||
|
|
||||||
|
import org.apache.commons.beanutils.BeanUtils;
|
||||||
|
import org.apache.commons.io.IOUtils;
|
||||||
|
import org.junit.jupiter.api.Test;
|
||||||
|
|
||||||
|
import com.fasterxml.jackson.databind.DeserializationFeature;
|
||||||
|
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||||
|
import com.google.common.collect.Lists;
|
||||||
|
|
||||||
|
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||||
|
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.*;
|
||||||
|
|
||||||
|
public class MergeUtilsTest {
|
||||||
|
|
||||||
|
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper()
|
||||||
|
.configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false);
|
||||||
|
|
||||||
|
@Test
|
||||||
|
void testMergePubs_new() throws IOException {
|
||||||
|
Publication pt = read("publication_test.json", Publication.class);
|
||||||
|
Publication p1 = read("publication_test.json", Publication.class);
|
||||||
|
|
||||||
|
assertEquals(1, pt.getCollectedfrom().size());
|
||||||
|
assertEquals(ModelConstants.CROSSREF_ID, pt.getCollectedfrom().get(0).getKey());
|
||||||
|
|
||||||
|
Instance i = new Instance();
|
||||||
|
i.setUrl(Lists.newArrayList("https://..."));
|
||||||
|
p1.getInstance().add(i);
|
||||||
|
|
||||||
|
Publication ptp1 = MergeUtils.mergePublication(pt, p1);
|
||||||
|
|
||||||
|
assertNotNull(ptp1.getInstance());
|
||||||
|
assertEquals(2, ptp1.getInstance().size());
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
|
@Test
|
||||||
|
void testMergePubs() throws IOException {
|
||||||
|
Publication p1 = read("publication_1.json", Publication.class);
|
||||||
|
Publication p2 = read("publication_2.json", Publication.class);
|
||||||
|
Dataset d1 = read("dataset_1.json", Dataset.class);
|
||||||
|
Dataset d2 = read("dataset_2.json", Dataset.class);
|
||||||
|
|
||||||
|
assertEquals(1, p1.getCollectedfrom().size());
|
||||||
|
assertEquals(ModelConstants.CROSSREF_ID, p1.getCollectedfrom().get(0).getKey());
|
||||||
|
assertEquals(1, d2.getCollectedfrom().size());
|
||||||
|
assertFalse(cfId(d2.getCollectedfrom()).contains(ModelConstants.CROSSREF_ID));
|
||||||
|
|
||||||
|
assertEquals(1, p2.getCollectedfrom().size());
|
||||||
|
assertFalse(cfId(p2.getCollectedfrom()).contains(ModelConstants.CROSSREF_ID));
|
||||||
|
assertEquals(1, d1.getCollectedfrom().size());
|
||||||
|
assertTrue(cfId(d1.getCollectedfrom()).contains(ModelConstants.CROSSREF_ID));
|
||||||
|
|
||||||
|
final Result p1d2 = MergeUtils.checkedMerge(p1, d2, true);
|
||||||
|
assertEquals(ModelConstants.PUBLICATION_RESULTTYPE_CLASSID, p1d2.getResulttype().getClassid());
|
||||||
|
assertTrue(p1d2 instanceof Publication);
|
||||||
|
assertEquals(p1.getId(), p1d2.getId());
|
||||||
|
}
|
||||||
|
|
||||||
|
@Test
|
||||||
|
void testMergePubs_1() throws IOException {
|
||||||
|
Publication p2 = read("publication_2.json", Publication.class);
|
||||||
|
Dataset d1 = read("dataset_1.json", Dataset.class);
|
||||||
|
|
||||||
|
final Result p2d1 = MergeUtils.checkedMerge(p2, d1, true);
|
||||||
|
assertEquals((ModelConstants.DATASET_RESULTTYPE_CLASSID), p2d1.getResulttype().getClassid());
|
||||||
|
assertTrue(p2d1 instanceof Dataset);
|
||||||
|
assertEquals(d1.getId(), p2d1.getId());
|
||||||
|
assertEquals(2, p2d1.getCollectedfrom().size());
|
||||||
|
}
|
||||||
|
|
||||||
|
@Test
|
||||||
|
void testMergePubs_2() throws IOException {
|
||||||
|
Publication p1 = read("publication_1.json", Publication.class);
|
||||||
|
Publication p2 = read("publication_2.json", Publication.class);
|
||||||
|
|
||||||
|
Result p1p2 = MergeUtils.checkedMerge(p1, p2, true);
|
||||||
|
assertTrue(p1p2 instanceof Publication);
|
||||||
|
assertEquals(p1.getId(), p1p2.getId());
|
||||||
|
assertEquals(2, p1p2.getCollectedfrom().size());
|
||||||
|
}
|
||||||
|
|
||||||
|
@Test
|
||||||
|
void testDelegatedAuthority_1() throws IOException {
|
||||||
|
Dataset d1 = read("dataset_2.json", Dataset.class);
|
||||||
|
Dataset d2 = read("dataset_delegated.json", Dataset.class);
|
||||||
|
|
||||||
|
assertEquals(1, d2.getCollectedfrom().size());
|
||||||
|
assertTrue(cfId(d2.getCollectedfrom()).contains(ModelConstants.ZENODO_OD_ID));
|
||||||
|
|
||||||
|
Result res = (Result) MergeUtils.merge(d1, d2, true);
|
||||||
|
|
||||||
|
assertEquals(d2, res);
|
||||||
|
}
|
||||||
|
|
||||||
|
@Test
|
||||||
|
void testDelegatedAuthority_2() throws IOException {
|
||||||
|
Dataset p1 = read("publication_1.json", Dataset.class);
|
||||||
|
Dataset d2 = read("dataset_delegated.json", Dataset.class);
|
||||||
|
|
||||||
|
assertEquals(1, d2.getCollectedfrom().size());
|
||||||
|
assertTrue(cfId(d2.getCollectedfrom()).contains(ModelConstants.ZENODO_OD_ID));
|
||||||
|
|
||||||
|
Result res = (Result) MergeUtils.merge(p1, d2, true);
|
||||||
|
|
||||||
|
assertEquals(d2, res);
|
||||||
|
}
|
||||||
|
|
||||||
|
protected HashSet<String> cfId(List<KeyValue> collectedfrom) {
|
||||||
|
return collectedfrom.stream().map(KeyValue::getKey).collect(Collectors.toCollection(HashSet::new));
|
||||||
|
}
|
||||||
|
|
||||||
|
protected <T extends Result> T read(String filename, Class<T> clazz) throws IOException {
|
||||||
|
final String json = IOUtils.toString(getClass().getResourceAsStream(filename));
|
||||||
|
return OBJECT_MAPPER.readValue(json, clazz);
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -149,7 +149,7 @@ class OafMapperUtilsTest {
|
||||||
void testDate() {
|
void testDate() {
|
||||||
final String date = GraphCleaningFunctions.cleanDate("23-FEB-1998");
|
final String date = GraphCleaningFunctions.cleanDate("23-FEB-1998");
|
||||||
assertNotNull(date);
|
assertNotNull(date);
|
||||||
System.out.println(date);
|
assertEquals("1998-02-23", date);
|
||||||
}
|
}
|
||||||
|
|
||||||
@Test
|
@Test
|
||||||
|
@ -166,8 +166,8 @@ class OafMapperUtilsTest {
|
||||||
|
|
||||||
assertEquals(
|
assertEquals(
|
||||||
ModelConstants.PUBLICATION_RESULTTYPE_CLASSID,
|
ModelConstants.PUBLICATION_RESULTTYPE_CLASSID,
|
||||||
OafMapperUtils
|
MergeUtils
|
||||||
.mergeResults(p1, d2)
|
.mergeResult(p1, d2)
|
||||||
.getResulttype()
|
.getResulttype()
|
||||||
.getClassid());
|
.getClassid());
|
||||||
|
|
||||||
|
@ -178,8 +178,8 @@ class OafMapperUtilsTest {
|
||||||
|
|
||||||
assertEquals(
|
assertEquals(
|
||||||
ModelConstants.DATASET_RESULTTYPE_CLASSID,
|
ModelConstants.DATASET_RESULTTYPE_CLASSID,
|
||||||
OafMapperUtils
|
((Result) MergeUtils
|
||||||
.mergeResults(p2, d1)
|
.merge(p2, d1))
|
||||||
.getResulttype()
|
.getResulttype()
|
||||||
.getClassid());
|
.getClassid());
|
||||||
}
|
}
|
||||||
|
@ -192,7 +192,7 @@ class OafMapperUtilsTest {
|
||||||
assertEquals(1, d2.getCollectedfrom().size());
|
assertEquals(1, d2.getCollectedfrom().size());
|
||||||
assertTrue(cfId(d2.getCollectedfrom()).contains(ModelConstants.ZENODO_OD_ID));
|
assertTrue(cfId(d2.getCollectedfrom()).contains(ModelConstants.ZENODO_OD_ID));
|
||||||
|
|
||||||
Result res = OafMapperUtils.mergeResults(d1, d2);
|
Result res = MergeUtils.mergeResult(d1, d2);
|
||||||
|
|
||||||
assertEquals(d2, res);
|
assertEquals(d2, res);
|
||||||
|
|
||||||
|
|
|
@ -0,0 +1,12 @@
|
||||||
|
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0000/ra.v2i3.114::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"4.65008652949e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0000/ra.v2i3.114"}]}]}
|
||||||
|
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0001/(aj).v3i6.458::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"4.01810569717e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0001/(aj).v3i6.458"}]}]}
|
||||||
|
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0001/1587::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.39172290649e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0001/1587"}]}]}
|
||||||
|
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0001/462::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"6.33235333753e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.36"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.00285265116e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0001/462"}]}]}
|
||||||
|
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0001/731::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"4.01810569717e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0001/731"}]}]}
|
||||||
|
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0001/ijllis.v9i4.2066.g2482::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"8.48190886761e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0001/ijllis.v9i4.2066.g2482"}]}]}
|
||||||
|
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0118/alfahim.v3i1.140::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"9.88840807598e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0118/alfahim.v3i1.140"}]}]}
|
||||||
|
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0166/fk2.stagefigshare.6442896.v3::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"7.28336930301e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0166/fk2.stagefigshare.6442896.v3"}]}]}
|
||||||
|
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0301/jttb.v2i1.64::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"7.28336930301e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0301/jttb.v2i1.64"}]}]}
|
||||||
|
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0809/seruni.v1i1.567::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"2.62959564033e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0809/seruni.v1i1.567"}]}]}
|
||||||
|
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0809/seruni.v2i1.765::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"9.40178571921e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0559872"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"3.67659957614e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0809/seruni.v2i1.765"}]}]}
|
||||||
|
{"dataInfo":{"deletedbyinference":false,"inferred":true,"invisible":false,"provenanceaction":{"classid":"sysimport:enrich","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"id":"unresolved::10.0901/jkip.v7i3.485::doi","instance":[{"measures":[{"id":"influence","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"5.91019644836e-09"}]},{"id":"popularity_alt","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"0.0"}]},{"id":"popularity","unit":[{"dataInfo":{"deletedbyinference":false,"inferenceprovenance":"update","inferred":true,"invisible":false,"provenanceaction":{"classid":"measure:bip","classname":"Inferred by OpenAIRE","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"},"trust":""},"key":"score","value":"6.26204125721e-09"}]}],"pid":[{"qualifier":{"classid":"doi","classname":"Digital Object Identifier","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"value":"10.0901/jkip.v7i3.485"}]}]}
|
File diff suppressed because one or more lines are too long
|
@ -0,0 +1 @@
|
||||||
|
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f","pid":[{"qualifier":{"classid":"scp-number"},"value":"79953761260"}]}
|
|
@ -0,0 +1 @@
|
||||||
|
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f","pid":[]}
|
|
@ -0,0 +1 @@
|
||||||
|
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f"}
|
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
|
@ -0,0 +1,33 @@
|
||||||
|
{
|
||||||
|
"id": "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f",
|
||||||
|
"instance": [
|
||||||
|
{
|
||||||
|
"collectedfrom": {
|
||||||
|
"key": "10|openaire____::081b82f96300b6a6e3d282bad31cb6e2",
|
||||||
|
"value": "Crossref"
|
||||||
|
},
|
||||||
|
"pid": [
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "doi"},
|
||||||
|
"value": "10.1016/j.cmet.2010.03.013"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"pid": [
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "urn"},
|
||||||
|
"value": "urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "scp-number"},
|
||||||
|
"value": "79953761260"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "pmc"},
|
||||||
|
"value": "21459329"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
|
@ -0,0 +1,37 @@
|
||||||
|
{
|
||||||
|
"id": "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f",
|
||||||
|
"instance": [
|
||||||
|
{
|
||||||
|
"collectedfrom": {
|
||||||
|
"key": "10|openaire____::081b82f96300b6a6e3d282bad31cb6e2",
|
||||||
|
"value": "Crossref"
|
||||||
|
},
|
||||||
|
"pid": [
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "doi"},
|
||||||
|
"value": "10.1016/j.cmet.2010.03.013"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"collectedfrom": {
|
||||||
|
"key": "10|opendoar____::8b6dd7db9af49e67306feb59a8bdc52c",
|
||||||
|
"value": "Europe PubMed Central"
|
||||||
|
},
|
||||||
|
"pid": [
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "urn"},
|
||||||
|
"value": "urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "scp-number"},
|
||||||
|
"value": "79953761260"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "pmc"},
|
||||||
|
"value": "21459329"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
|
@ -0,0 +1,37 @@
|
||||||
|
{
|
||||||
|
"id": "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f",
|
||||||
|
"instance": [
|
||||||
|
{
|
||||||
|
"collectedfrom": {
|
||||||
|
"key": "10|opendoar____::358aee4cc897452c00244351e4d91f69",
|
||||||
|
"value": "Zenodo"
|
||||||
|
},
|
||||||
|
"pid": [
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "doi"},
|
||||||
|
"value": "10.1016/j.cmet.2010.03.013"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"collectedfrom": {
|
||||||
|
"key": "10|opendoar____::8b6dd7db9af49e67306feb59a8bdc52c",
|
||||||
|
"value": "Europe PubMed Central"
|
||||||
|
},
|
||||||
|
"pid": [
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "urn"},
|
||||||
|
"value": "urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "scp-number"},
|
||||||
|
"value": "79953761260"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "pmc"},
|
||||||
|
"value": "21459329"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
|
@ -0,0 +1,37 @@
|
||||||
|
{
|
||||||
|
"id": "50|od______2852::38861c44e6052a8d49f59a4c39ba5e66",
|
||||||
|
"instance": [
|
||||||
|
{
|
||||||
|
"collectedfrom": {
|
||||||
|
"key": "10|opendoar____::358aee4cc897452c00244351e4d91f69",
|
||||||
|
"value": "Zenodo"
|
||||||
|
},
|
||||||
|
"pid": [
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "doi"},
|
||||||
|
"value": "10.1016/j.cmet.2010.03.013"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "handle"},
|
||||||
|
"value": "11012/83840"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"collectedfrom": {
|
||||||
|
"key": "10|opendoar____::2852",
|
||||||
|
"value": "Digital library of Brno University of Technology"
|
||||||
|
},
|
||||||
|
"pid": [
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "pmc"},
|
||||||
|
"value": "21459329"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "handle"},
|
||||||
|
"value": "11012/83840"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
|
@ -0,0 +1,37 @@
|
||||||
|
{
|
||||||
|
"id": "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f",
|
||||||
|
"instance": [
|
||||||
|
{
|
||||||
|
"collectedfrom": {
|
||||||
|
"key": "10|opendoar____::358aee4cc897452c00244351e4d91f69",
|
||||||
|
"value": "Zenodo"
|
||||||
|
},
|
||||||
|
"pid": [
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "doi"},
|
||||||
|
"value": "10.5281/zenodo.5121485"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"collectedfrom": {
|
||||||
|
"key": "10|opendoar____::8b6dd7db9af49e67306feb59a8bdc52c",
|
||||||
|
"value": "Europe PubMed Central"
|
||||||
|
},
|
||||||
|
"pid": [
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "urn"},
|
||||||
|
"value": "urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "scp-number"},
|
||||||
|
"value": "79953761260"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "pmc"},
|
||||||
|
"value": "21459329"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
|
@ -0,0 +1,3 @@
|
||||||
|
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f", "resulttype" : { "classid" : "publication" }, "pid":[{"qualifier":{"classid":"doi"},"value":"10.1016/j.cmet.2011.03.013"},{"qualifier":{"classid":"urn"},"value":"urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"},{"qualifier":{"classid":"scp-number"},"value":"79953761260"},{"qualifier":{"classid":"pmc"},"value":"21459329"}], "collectedfrom" : [ { "key" : "10|openaire____::081b82f96300b6a6e3d282bad31cb6e2", "value" : "Crossref"} ], "isGreen": null, "openAccessColor": "gold", "isInDiamondJournal": null, "publiclyFunded": null}
|
||||||
|
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1g", "resulttype" : { "classid" : "publication" }, "isGreen": true, "openAccessColor": "gold", "isInDiamondJournal": true, "publiclyFunded": false }
|
||||||
|
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1h", "resulttype" : { "classid" : "publication" }, "isGreen": false, "openAccessColor": null, "isInDiamondJournal": true, "publiclyFunded": false }
|
|
@ -0,0 +1,3 @@
|
||||||
|
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f", "resulttype" : { "classid" : "publication" }, "pid":[{"qualifier":{"classid":"doi"},"value":"10.1016/j.cmet.2011.03.013"},{"qualifier":{"classid":"urn"},"value":"urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"},{"qualifier":{"classid":"scp-number"},"value":"79953761260"},{"qualifier":{"classid":"pmc"},"value":"21459329"}], "collectedfrom" : [ { "key" : "10|openaire____::081b82f96300b6a6e3d282bad31cb6e2", "value" : "Crossref"} ], "isGreen": null, "openAccessColor": "gold", "isInDiamondJournal": null, "publiclyFunded": null}
|
||||||
|
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1g", "resulttype" : { "classid" : "publication" }, "isGreen": true, "openAccessColor": "bronze", "isInDiamondJournal": true, "publiclyFunded": false }
|
||||||
|
{"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1h", "resulttype" : { "classid" : "publication" }, "isGreen": false, "openAccessColor": null, "isInDiamondJournal": true, "publiclyFunded": false }
|
|
@ -0,0 +1,31 @@
|
||||||
|
{
|
||||||
|
"id": "50|openapc_____::000023f9cb6e3a247c764daec4273cbc",
|
||||||
|
"resuttype": {
|
||||||
|
"classid": "publication"
|
||||||
|
},
|
||||||
|
"instance": [
|
||||||
|
{
|
||||||
|
"collectedfrom": {
|
||||||
|
"key": "10|apc_________::e2b1600b229fc30663c8a1f662debddf",
|
||||||
|
"value": "OpenAPC Global Initiative"
|
||||||
|
},
|
||||||
|
"pid": [
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "doi"},
|
||||||
|
"value": "10.1016/j.cmet.2010.03.013"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "pmc"},
|
||||||
|
"value": "21459329"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "pmid"},
|
||||||
|
"value": "25811027"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"url":["https://doi.org/10.1155/2015/439379"]
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
|
||||||
|
|
|
@ -0,0 +1,17 @@
|
||||||
|
{
|
||||||
|
"id": "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f",
|
||||||
|
"pid": [
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "urn"},
|
||||||
|
"value": "urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "scp-number"},
|
||||||
|
"value": "79953761260"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "pmc"},
|
||||||
|
"value": "21459329"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
|
@ -0,0 +1,21 @@
|
||||||
|
{
|
||||||
|
"id":"50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f",
|
||||||
|
"instance": [
|
||||||
|
{
|
||||||
|
"collectedfrom": {
|
||||||
|
"key": "10|opendoar____::8b6dd7db9af49e67306feb59a8bdc52c",
|
||||||
|
"value": "Europe PubMed Central"
|
||||||
|
},
|
||||||
|
"pid": [
|
||||||
|
{
|
||||||
|
"qualifier": {"classid": "doi"},
|
||||||
|
"value": "10.1016/j.cmet.2010.03.013"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"qualifier":{"classid":"pmc"},
|
||||||
|
"value":"21459329"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
|
@ -0,0 +1,428 @@
|
||||||
|
{
|
||||||
|
"author": [
|
||||||
|
{
|
||||||
|
"affiliation": null,
|
||||||
|
"fullname": "Deymier, Ghislaine",
|
||||||
|
"name": "Ghislaine",
|
||||||
|
"pid": [],
|
||||||
|
"rank": 1,
|
||||||
|
"surname": "Deymier"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"affiliation": null,
|
||||||
|
"fullname": "Gaschet, Frédéric",
|
||||||
|
"name": "Frédéric",
|
||||||
|
"pid": [],
|
||||||
|
"rank": 2,
|
||||||
|
"surname": "Gaschet"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"affiliation": null,
|
||||||
|
"fullname": "Pouyanne, Guillaume",
|
||||||
|
"name": "Guillaume",
|
||||||
|
"pid": [],
|
||||||
|
"rank": 3,
|
||||||
|
"surname": "Pouyanne"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"bestaccessright": {
|
||||||
|
"classid": "OPEN",
|
||||||
|
"classname": "Open Access",
|
||||||
|
"schemeid": "dnet:access_modes",
|
||||||
|
"schemename": "dnet:access_modes"
|
||||||
|
},
|
||||||
|
"collectedfrom": [
|
||||||
|
{
|
||||||
|
"key" : "10|openaire____::081b82f96300b6a6e3d282bad31cb6e2",
|
||||||
|
"value" : "Crossref"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"context": [],
|
||||||
|
"contributor": [],
|
||||||
|
"country": [],
|
||||||
|
"coverage": [],
|
||||||
|
"dataInfo": {
|
||||||
|
"deletedbyinference": false,
|
||||||
|
"inferred": false,
|
||||||
|
"invisible": false,
|
||||||
|
"provenanceaction": {
|
||||||
|
"classid": "sysimport:crosswalk:repository",
|
||||||
|
"classname": "Harvested",
|
||||||
|
"schemeid": "dnet:provenanceActions",
|
||||||
|
"schemename": "dnet:provenanceActions"
|
||||||
|
},
|
||||||
|
"trust": "0.9"
|
||||||
|
},
|
||||||
|
"dateofacceptance": {
|
||||||
|
"dataInfo": {
|
||||||
|
"deletedbyinference": false,
|
||||||
|
"inferred": false,
|
||||||
|
"invisible": false,
|
||||||
|
"provenanceaction": {
|
||||||
|
"classid": "sysimport:crosswalk:repository",
|
||||||
|
"classname": "Harvested",
|
||||||
|
"schemeid": "dnet:provenanceActions",
|
||||||
|
"schemename": "dnet:provenanceActions"
|
||||||
|
},
|
||||||
|
"trust": "0.9"
|
||||||
|
},
|
||||||
|
"value": "2013-11-30"
|
||||||
|
},
|
||||||
|
"dateofcollection": "2024-02-28T00:22:13+0000",
|
||||||
|
"dateoftransformation": "2024-03-06T08:43:13.253Z",
|
||||||
|
"description": [
|
||||||
|
{
|
||||||
|
"dataInfo": {
|
||||||
|
"deletedbyinference": false,
|
||||||
|
"inferred": false,
|
||||||
|
"invisible": false,
|
||||||
|
"provenanceaction": {
|
||||||
|
"classid": "sysimport:crosswalk:repository",
|
||||||
|
"classname": "Harvested",
|
||||||
|
"schemeid": "dnet:provenanceActions",
|
||||||
|
"schemename": "dnet:provenanceActions"
|
||||||
|
},
|
||||||
|
"trust": "0.9"
|
||||||
|
},
|
||||||
|
"value": "For analyzing the reciprocal interaction between urban sprawl and car use, research has first focused on the link between urban density and mobility. By looking for a reduction in energy consumption, cities have favoured a compact planning development. Then reflection has broadened from the simple density to the wider, multi-dimensional concept of urban form. This controversy has led to a renewal of analysis in term of the costs of urban growth, notably by comparing the costs of \"compact\" and \"sprawled\" development. The idea is to compare the mobility costs of different urban forms. However, most often because of a lack of data, such studies are scarce. This paper suggests an innovative method to compute mobility costs at an infra-urban scale : The Spatialized Travel Account (STA). It is based on the CERTU's travel account methodology at a metropolitan scale. It puts forward an accurate estimate of the mobility costs for each transport mode (individual and public) and for each type of payer (households, firms, local authorities...). In order to test the relationships between mobility costs and urban form, we link the computed costs to morphological characteristics of infra-urban zones, taking in account sociodemographic characteristics of households."
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"dataInfo": {
|
||||||
|
"deletedbyinference": false,
|
||||||
|
"inferred": false,
|
||||||
|
"invisible": false,
|
||||||
|
"provenanceaction": {
|
||||||
|
"classid": "sysimport:crosswalk:repository",
|
||||||
|
"classname": "Harvested",
|
||||||
|
"schemeid": "dnet:provenanceActions",
|
||||||
|
"schemename": "dnet:provenanceActions"
|
||||||
|
},
|
||||||
|
"trust": "0.9"
|
||||||
|
},
|
||||||
|
"value": "L'interaction réciproque entre étalement urbain et usage de l'automobile a conduit la recherche à se focaliser sur le lien entre les densités urbaines et la mobilité. En cherchant à réduire leur consommation d'énergie pour les transports, et donc leurs émissions de Gaz à Effet de Serre, les villes ont alors cherché à planifier la \" ville compacte \", privilégiant notamment la reconstruction de la ville sur elle-même et la densification. Par la suite, la réflexion s'est élargie de la simple densité à la notion de forme urbaine et à toutes ses dimensions. Cette controverse devait conduire à un renouveau des analyses en termes de coûts de la croissance urbaine : le débat reste vif, encore aujourd'hui, sur les coûts comparés de la ville étalée et de la ville compacte. Plus largement, il s'agit d'explorer les coûts des différentes formes urbaines en termes de mobilité. Malgré cela, généralement pour des raisons de disponibilité de données, les études sur le sujet restent extrêmement rares. Cet article propose un outil novateur pour mesurer les coûts de la mobilité à l'échelle intraurbaine : le Compte Déplacements Territorialisé (CDT). Il s'inspire de la méthode développée par le CERTU pour l'établissement des Comptes Déplacements Voyageurs à l'échelle métropolitaine. Le CDT propose, pour chacune des zones de l'agglomération, une estimation précise de l'ensemble des coûts liés aux déplacements de personnes, ventilés par mode de transport (individuels et collectifs) et par type de financeurs (ménages, entreprises, collectivités territoriales, etc.). Nous proposons une application de cette méthode à la controverse sur le lien entre forme urbaine et coûts de la mobilité. Les coûts sont reliés aux caractéristiques morphologiques des zones (en termes de densité et de diversité, notamment), en prenant soin de contrôler les facteurs socio-économiques qui influent traditionnellement sur les comportements de mobilité (taille du ménage, revenu, etc.)."
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"eoscifguidelines": [],
|
||||||
|
"externalReference": [],
|
||||||
|
"extraInfo": [],
|
||||||
|
"format": [
|
||||||
|
{
|
||||||
|
"dataInfo": {
|
||||||
|
"deletedbyinference": false,
|
||||||
|
"inferred": false,
|
||||||
|
"invisible": false,
|
||||||
|
"provenanceaction": {
|
||||||
|
"classid": "sysimport:crosswalk:repository",
|
||||||
|
"classname": "Harvested",
|
||||||
|
"schemeid": "dnet:provenanceActions",
|
||||||
|
"schemename": "dnet:provenanceActions"
|
||||||
|
},
|
||||||
|
"trust": "0.9"
|
||||||
|
},
|
||||||
|
"value": "application/pdf"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"fulltext": [],
|
||||||
|
"id": "50|06cdd3ff4700::4826ac62a11a957fe332e2c291dcfcca",
|
||||||
|
"instance": [
|
||||||
|
{
|
||||||
|
"accessright": {
|
||||||
|
"classid": "OPEN",
|
||||||
|
"classname": "Open Access",
|
||||||
|
"schemeid": "dnet:access_modes",
|
||||||
|
"schemename": "dnet:access_modes"
|
||||||
|
},
|
||||||
|
"alternateIdentifier": [
|
||||||
|
{
|
||||||
|
"dataInfo": {
|
||||||
|
"deletedbyinference": false,
|
||||||
|
"inferred": false,
|
||||||
|
"invisible": false,
|
||||||
|
"provenanceaction": {
|
||||||
|
"classid": "sysimport:crosswalk:repository",
|
||||||
|
"classname": "Harvested",
|
||||||
|
"schemeid": "dnet:provenanceActions",
|
||||||
|
"schemename": "dnet:provenanceActions"
|
||||||
|
},
|
||||||
|
"trust": "0.9"
|
||||||
|
},
|
||||||
|
"qualifier": {
|
||||||
|
"classid": "doi",
|
||||||
|
"classname": "Digital Object Identifier",
|
||||||
|
"schemeid": "dnet:pid_types",
|
||||||
|
"schemename": "dnet:pid_types"
|
||||||
|
},
|
||||||
|
"value": "10.46298/cst.12132"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"collectedfrom": {
|
||||||
|
"key": "10|openaire____::6824b298c96ba906a3e6a70593affbf5",
|
||||||
|
"value": "Episciences"
|
||||||
|
},
|
||||||
|
"dateofacceptance": {
|
||||||
|
"dataInfo": {
|
||||||
|
"deletedbyinference": false,
|
||||||
|
"inferred": false,
|
||||||
|
"invisible": false,
|
||||||
|
"provenanceaction": {
|
||||||
|
"classid": "sysimport:crosswalk:repository",
|
||||||
|
"classname": "Harvested",
|
||||||
|
"schemeid": "dnet:provenanceActions",
|
||||||
|
"schemename": "dnet:provenanceActions"
|
||||||
|
},
|
||||||
|
"trust": "0.9"
|
||||||
|
},
|
||||||
|
"value": "2013-11-30"
|
||||||
|
},
|
||||||
|
"hostedby": {
|
||||||
|
"key": "10|openaire____::6824b298c96ba906a3e6a70593affbf5",
|
||||||
|
"value": "Episciences"
|
||||||
|
},
|
||||||
|
"instanceTypeMapping": [
|
||||||
|
{
|
||||||
|
"originalType": "http://purl.org/coar/resource_type/c_6501",
|
||||||
|
"typeCode": "http://purl.org/coar/resource_type/c_6501",
|
||||||
|
"typeLabel": "journal article",
|
||||||
|
"vocabularyName": "openaire::coar_resource_types_3_1"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"originalType": "http://purl.org/coar/resource_type/c_6501",
|
||||||
|
"typeCode": "Article",
|
||||||
|
"typeLabel": "Article",
|
||||||
|
"vocabularyName": "openaire::user_resource_types"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"instancetype": {
|
||||||
|
"classid": "0001",
|
||||||
|
"classname": "Article",
|
||||||
|
"schemeid": "dnet:publication_resource",
|
||||||
|
"schemename": "dnet:publication_resource"
|
||||||
|
},
|
||||||
|
"license": {
|
||||||
|
"dataInfo": {
|
||||||
|
"deletedbyinference": false,
|
||||||
|
"inferred": false,
|
||||||
|
"invisible": false,
|
||||||
|
"provenanceaction": {
|
||||||
|
"classid": "sysimport:crosswalk:repository",
|
||||||
|
"classname": "Harvested",
|
||||||
|
"schemeid": "dnet:provenanceActions",
|
||||||
|
"schemename": "dnet:provenanceActions"
|
||||||
|
},
|
||||||
|
"trust": "0.9"
|
||||||
|
},
|
||||||
|
"value": "CC BY NC SA"
|
||||||
|
},
|
||||||
|
"pid": [],
|
||||||
|
"refereed": {
|
||||||
|
"classid": "0002",
|
||||||
|
"classname": "nonPeerReviewed",
|
||||||
|
"schemeid": "dnet:review_levels",
|
||||||
|
"schemename": "dnet:review_levels"
|
||||||
|
},
|
||||||
|
"url": [
|
||||||
|
"https://doi.org/10.46298/cst.12132",
|
||||||
|
"https://cst.episciences.org/12132"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"language": {
|
||||||
|
"classid": "fra/fre",
|
||||||
|
"classname": "French",
|
||||||
|
"schemeid": "dnet:languages",
|
||||||
|
"schemename": "dnet:languages"
|
||||||
|
},
|
||||||
|
"lastupdatetimestamp": 1710636106633,
|
||||||
|
"metaResourceType": {
|
||||||
|
"classid": "Research Literature",
|
||||||
|
"classname": "Research Literature",
|
||||||
|
"schemeid": "openaire::meta_resource_types",
|
||||||
|
"schemename": "openaire::meta_resource_types"
|
||||||
|
},
|
||||||
|
"originalId": [
|
||||||
|
"oai:episciences.org:cst:12132",
|
||||||
|
"50|06cdd3ff4700::4826ac62a11a957fe332e2c291dcfcca"
|
||||||
|
],
|
||||||
|
"pid": [],
|
||||||
|
"publisher": {
|
||||||
|
"dataInfo": {
|
||||||
|
"deletedbyinference": false,
|
||||||
|
"inferred": false,
|
||||||
|
"invisible": false,
|
||||||
|
"provenanceaction": {
|
||||||
|
"classid": "sysimport:crosswalk:repository",
|
||||||
|
"classname": "Harvested",
|
||||||
|
"schemeid": "dnet:provenanceActions",
|
||||||
|
"schemename": "dnet:provenanceActions"
|
||||||
|
},
|
||||||
|
"trust": "0.9"
|
||||||
|
},
|
||||||
|
"value": "episciences.org"
|
||||||
|
},
|
||||||
|
"relevantdate": [
|
||||||
|
{
|
||||||
|
"dataInfo": {
|
||||||
|
"deletedbyinference": false,
|
||||||
|
"inferred": false,
|
||||||
|
"invisible": false,
|
||||||
|
"provenanceaction": {
|
||||||
|
"classid": "sysimport:crosswalk:repository",
|
||||||
|
"classname": "Harvested",
|
||||||
|
"schemeid": "dnet:provenanceActions",
|
||||||
|
"schemename": "dnet:provenanceActions"
|
||||||
|
},
|
||||||
|
"trust": "0.9"
|
||||||
|
},
|
||||||
|
"qualifier": {
|
||||||
|
"classid": "Accepted",
|
||||||
|
"classname": "Accepted",
|
||||||
|
"schemeid": "dnet:dataCite_date",
|
||||||
|
"schemename": "dnet:dataCite_date"
|
||||||
|
},
|
||||||
|
"value": "2024-02-11"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"dataInfo": {
|
||||||
|
"deletedbyinference": false,
|
||||||
|
"inferred": false,
|
||||||
|
"invisible": false,
|
||||||
|
"provenanceaction": {
|
||||||
|
"classid": "sysimport:crosswalk:repository",
|
||||||
|
"classname": "Harvested",
|
||||||
|
"schemeid": "dnet:provenanceActions",
|
||||||
|
"schemename": "dnet:provenanceActions"
|
||||||
|
},
|
||||||
|
"trust": "0.9"
|
||||||
|
},
|
||||||
|
"qualifier": {
|
||||||
|
"classid": "issued",
|
||||||
|
"classname": "issued",
|
||||||
|
"schemeid": "dnet:dataCite_date",
|
||||||
|
"schemename": "dnet:dataCite_date"
|
||||||
|
},
|
||||||
|
"value": "2013-11-30"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"dataInfo": {
|
||||||
|
"deletedbyinference": false,
|
||||||
|
"inferred": false,
|
||||||
|
"invisible": false,
|
||||||
|
"provenanceaction": {
|
||||||
|
"classid": "sysimport:crosswalk:repository",
|
||||||
|
"classname": "Harvested",
|
||||||
|
"schemeid": "dnet:provenanceActions",
|
||||||
|
"schemename": "dnet:provenanceActions"
|
||||||
|
},
|
||||||
|
"trust": "0.9"
|
||||||
|
},
|
||||||
|
"qualifier": {
|
||||||
|
"classid": "available",
|
||||||
|
"classname": "available",
|
||||||
|
"schemeid": "dnet:dataCite_date",
|
||||||
|
"schemename": "dnet:dataCite_date"
|
||||||
|
},
|
||||||
|
"value": "2013-11-30"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"resourcetype": {
|
||||||
|
"classid": "journal article",
|
||||||
|
"classname": "journal article",
|
||||||
|
"schemeid": "dnet:dataCite_resource",
|
||||||
|
"schemename": "dnet:dataCite_resource"
|
||||||
|
},
|
||||||
|
"resulttype": {
|
||||||
|
"classid": "publication",
|
||||||
|
"classname": "publication",
|
||||||
|
"schemeid": "dnet:result_typologies",
|
||||||
|
"schemename": "dnet:result_typologies"
|
||||||
|
},
|
||||||
|
"source": [],
|
||||||
|
"subject": [
|
||||||
|
{
|
||||||
|
"dataInfo": {
|
||||||
|
"deletedbyinference": false,
|
||||||
|
"inferred": false,
|
||||||
|
"invisible": false,
|
||||||
|
"provenanceaction": {
|
||||||
|
"classid": "sysimport:crosswalk:repository",
|
||||||
|
"classname": "Harvested",
|
||||||
|
"schemeid": "dnet:provenanceActions",
|
||||||
|
"schemename": "dnet:provenanceActions"
|
||||||
|
},
|
||||||
|
"trust": "0.9"
|
||||||
|
},
|
||||||
|
"qualifier": {
|
||||||
|
"classid": "keyword",
|
||||||
|
"classname": "keyword",
|
||||||
|
"schemeid": "dnet:subject_classification_typologies",
|
||||||
|
"schemename": "dnet:subject_classification_typologies"
|
||||||
|
},
|
||||||
|
"value": "JEL: H - Public Economics/H.H7 - State and Local Government • Intergovernmental Relations/H.H7.H72 - State and Local Budget and Expenditures"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"dataInfo": {
|
||||||
|
"deletedbyinference": false,
|
||||||
|
"inferred": false,
|
||||||
|
"invisible": false,
|
||||||
|
"provenanceaction": {
|
||||||
|
"classid": "sysimport:crosswalk:repository",
|
||||||
|
"classname": "Harvested",
|
||||||
|
"schemeid": "dnet:provenanceActions",
|
||||||
|
"schemename": "dnet:provenanceActions"
|
||||||
|
},
|
||||||
|
"trust": "0.9"
|
||||||
|
},
|
||||||
|
"qualifier": {
|
||||||
|
"classid": "keyword",
|
||||||
|
"classname": "keyword",
|
||||||
|
"schemeid": "dnet:subject_classification_typologies",
|
||||||
|
"schemename": "dnet:subject_classification_typologies"
|
||||||
|
},
|
||||||
|
"value": "Local public finance"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"dataInfo": {
|
||||||
|
"deletedbyinference": false,
|
||||||
|
"inferred": false,
|
||||||
|
"invisible": false,
|
||||||
|
"provenanceaction": {
|
||||||
|
"classid": "sysimport:crosswalk:repository",
|
||||||
|
"classname": "Harvested",
|
||||||
|
"schemeid": "dnet:provenanceActions",
|
||||||
|
"schemename": "dnet:provenanceActions"
|
||||||
|
},
|
||||||
|
"trust": "0.9"
|
||||||
|
},
|
||||||
|
"qualifier": {
|
||||||
|
"classid": "keyword",
|
||||||
|
"classname": "keyword",
|
||||||
|
"schemeid": "dnet:subject_classification_typologies",
|
||||||
|
"schemename": "dnet:subject_classification_typologies"
|
||||||
|
},
|
||||||
|
"value": "JEL: R - Urban, Rural, Regional, Real Estate, and Transportation Economics/R.R5 - Regional Government Analysis/R.R5.R51 - Finance in Urban and Rural Economies"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"title": [
|
||||||
|
{
|
||||||
|
"dataInfo": {
|
||||||
|
"deletedbyinference": false,
|
||||||
|
"inferred": false,
|
||||||
|
"invisible": false,
|
||||||
|
"provenanceaction": {
|
||||||
|
"classid": "sysimport:crosswalk:repository",
|
||||||
|
"classname": "Harvested",
|
||||||
|
"schemeid": "dnet:provenanceActions",
|
||||||
|
"schemename": "dnet:provenanceActions"
|
||||||
|
},
|
||||||
|
"trust": "0.9"
|
||||||
|
},
|
||||||
|
"qualifier": {
|
||||||
|
"classid": "main title",
|
||||||
|
"classname": "main title",
|
||||||
|
"schemeid": "dnet:dataCite_title",
|
||||||
|
"schemename": "dnet:dataCite_title"
|
||||||
|
},
|
||||||
|
"value": "Urban form and the costs of daily mobility. The spatialized travel account tool and its application to the Bordeaux metropolitan area"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
|
@ -0,0 +1,23 @@
|
||||||
|
{
|
||||||
|
"id": "50|DansKnawCris::0829b5191605bdbea36d6502b8c1ce1f",
|
||||||
|
"pid": [
|
||||||
|
{
|
||||||
|
"qualifier": {
|
||||||
|
"classid": "urn"
|
||||||
|
},
|
||||||
|
"value": "urn:nbn:nl:ui:29-f3ed5f9e-edf6-457e-8848-61b58a4075e2"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"qualifier": {
|
||||||
|
"classid": "scp-number"
|
||||||
|
},
|
||||||
|
"value": "79953761260"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"qualifier": {
|
||||||
|
"classid": "pmcid"
|
||||||
|
},
|
||||||
|
"value": "21459329"
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
File diff suppressed because one or more lines are too long
|
@ -24,7 +24,7 @@
|
||||||
<executions>
|
<executions>
|
||||||
<execution>
|
<execution>
|
||||||
<id>scala-compile-first</id>
|
<id>scala-compile-first</id>
|
||||||
<phase>initialize</phase>
|
<phase>process-resources</phase>
|
||||||
<goals>
|
<goals>
|
||||||
<goal>add-source</goal>
|
<goal>add-source</goal>
|
||||||
<goal>compile</goal>
|
<goal>compile</goal>
|
||||||
|
@ -49,18 +49,16 @@
|
||||||
</build>
|
</build>
|
||||||
|
|
||||||
<dependencies>
|
<dependencies>
|
||||||
|
<dependency>
|
||||||
|
<groupId>eu.dnetlib.dhp</groupId>
|
||||||
|
<artifactId>dhp-common</artifactId>
|
||||||
|
<version>${project.version}</version>
|
||||||
|
</dependency>
|
||||||
|
|
||||||
<dependency>
|
<dependency>
|
||||||
<groupId>edu.cmu</groupId>
|
<groupId>edu.cmu</groupId>
|
||||||
<artifactId>secondstring</artifactId>
|
<artifactId>secondstring</artifactId>
|
||||||
</dependency>
|
</dependency>
|
||||||
<dependency>
|
|
||||||
<groupId>com.google.guava</groupId>
|
|
||||||
<artifactId>guava</artifactId>
|
|
||||||
</dependency>
|
|
||||||
<dependency>
|
|
||||||
<groupId>com.google.code.gson</groupId>
|
|
||||||
<artifactId>gson</artifactId>
|
|
||||||
</dependency>
|
|
||||||
<dependency>
|
<dependency>
|
||||||
<groupId>org.apache.commons</groupId>
|
<groupId>org.apache.commons</groupId>
|
||||||
<artifactId>commons-lang3</artifactId>
|
<artifactId>commons-lang3</artifactId>
|
||||||
|
@ -85,10 +83,6 @@
|
||||||
<groupId>com.fasterxml.jackson.core</groupId>
|
<groupId>com.fasterxml.jackson.core</groupId>
|
||||||
<artifactId>jackson-databind</artifactId>
|
<artifactId>jackson-databind</artifactId>
|
||||||
</dependency>
|
</dependency>
|
||||||
<dependency>
|
|
||||||
<groupId>org.apache.commons</groupId>
|
|
||||||
<artifactId>commons-math3</artifactId>
|
|
||||||
</dependency>
|
|
||||||
<dependency>
|
<dependency>
|
||||||
<groupId>com.jayway.jsonpath</groupId>
|
<groupId>com.jayway.jsonpath</groupId>
|
||||||
<artifactId>json-path</artifactId>
|
<artifactId>json-path</artifactId>
|
||||||
|
@ -107,4 +101,90 @@
|
||||||
</dependency>
|
</dependency>
|
||||||
</dependencies>
|
</dependencies>
|
||||||
|
|
||||||
|
<profiles>
|
||||||
|
<profile>
|
||||||
|
<id>spark-24</id>
|
||||||
|
<activation>
|
||||||
|
<activeByDefault>true</activeByDefault>
|
||||||
|
</activation>
|
||||||
|
|
||||||
|
<build>
|
||||||
|
<plugins>
|
||||||
|
<plugin>
|
||||||
|
<groupId>org.codehaus.mojo</groupId>
|
||||||
|
<artifactId>build-helper-maven-plugin</artifactId>
|
||||||
|
<version>3.4.0</version>
|
||||||
|
<executions>
|
||||||
|
<execution>
|
||||||
|
<phase>generate-sources</phase>
|
||||||
|
<goals>
|
||||||
|
<goal>add-source</goal>
|
||||||
|
</goals>
|
||||||
|
<configuration>
|
||||||
|
<sources>
|
||||||
|
<source>src/main/spark-2</source>
|
||||||
|
</sources>
|
||||||
|
</configuration>
|
||||||
|
</execution>
|
||||||
|
</executions>
|
||||||
|
</plugin>
|
||||||
|
</plugins>
|
||||||
|
</build>
|
||||||
|
</profile>
|
||||||
|
|
||||||
|
<profile>
|
||||||
|
<id>spark-34</id>
|
||||||
|
|
||||||
|
<build>
|
||||||
|
<plugins>
|
||||||
|
<plugin>
|
||||||
|
<groupId>org.codehaus.mojo</groupId>
|
||||||
|
<artifactId>build-helper-maven-plugin</artifactId>
|
||||||
|
<version>3.4.0</version>
|
||||||
|
<executions>
|
||||||
|
<execution>
|
||||||
|
<phase>generate-sources</phase>
|
||||||
|
<goals>
|
||||||
|
<goal>add-source</goal>
|
||||||
|
</goals>
|
||||||
|
<configuration>
|
||||||
|
<sources>
|
||||||
|
<source>src/main/spark-2</source>
|
||||||
|
</sources>
|
||||||
|
</configuration>
|
||||||
|
</execution>
|
||||||
|
</executions>
|
||||||
|
</plugin>
|
||||||
|
</plugins>
|
||||||
|
</build>
|
||||||
|
</profile>
|
||||||
|
|
||||||
|
<profile>
|
||||||
|
<id>spark-35</id>
|
||||||
|
|
||||||
|
<build>
|
||||||
|
<plugins>
|
||||||
|
<plugin>
|
||||||
|
<groupId>org.codehaus.mojo</groupId>
|
||||||
|
<artifactId>build-helper-maven-plugin</artifactId>
|
||||||
|
<version>3.4.0</version>
|
||||||
|
<executions>
|
||||||
|
<execution>
|
||||||
|
<phase>generate-sources</phase>
|
||||||
|
<goals>
|
||||||
|
<goal>add-source</goal>
|
||||||
|
</goals>
|
||||||
|
<configuration>
|
||||||
|
<sources>
|
||||||
|
<source>src/main/spark-35</source>
|
||||||
|
</sources>
|
||||||
|
</configuration>
|
||||||
|
</execution>
|
||||||
|
</executions>
|
||||||
|
</plugin>
|
||||||
|
</plugins>
|
||||||
|
</build>
|
||||||
|
</profile>
|
||||||
|
</profiles>
|
||||||
|
|
||||||
</project>
|
</project>
|
||||||
|
|
|
@ -20,7 +20,7 @@ public class WordsStatsSuffixPrefixChain extends AbstractClusteringFunction {
|
||||||
return suffixPrefixChain(s, param("mod"));
|
return suffixPrefixChain(s, param("mod"));
|
||||||
}
|
}
|
||||||
|
|
||||||
private Collection<String> suffixPrefixChain(String s, int mod) {
|
static Collection<String> suffixPrefixChain(String s, int mod) {
|
||||||
|
|
||||||
// create the list of words from the string (remove short words)
|
// create the list of words from the string (remove short words)
|
||||||
List<String> wordsList = Arrays
|
List<String> wordsList = Arrays
|
||||||
|
@ -38,7 +38,7 @@ public class WordsStatsSuffixPrefixChain extends AbstractClusteringFunction {
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
private Collection<String> doSuffixPrefixChain(List<String> wordsList, String prefix) {
|
static private Collection<String> doSuffixPrefixChain(List<String> wordsList, String prefix) {
|
||||||
|
|
||||||
Set<String> set = Sets.newLinkedHashSet();
|
Set<String> set = Sets.newLinkedHashSet();
|
||||||
switch (wordsList.size()) {
|
switch (wordsList.size()) {
|
||||||
|
@ -80,12 +80,16 @@ public class WordsStatsSuffixPrefixChain extends AbstractClusteringFunction {
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
private String suffix(String s, int len) {
|
private static String suffix(String s, int len) {
|
||||||
return s.substring(s.length() - len);
|
return s.substring(s.length() - len);
|
||||||
}
|
}
|
||||||
|
|
||||||
private String prefix(String s, int len) {
|
private static String prefix(String s, int len) {
|
||||||
return s.substring(0, len);
|
return s.substring(0, len);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
static public void main(String[] args) {
|
||||||
|
String title = "MY LIFE AS A BOSON: THE STORY OF \"THE HIGGS\"".toLowerCase();
|
||||||
|
System.out.println(suffixPrefixChain(title, 10));
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|
|
@ -4,7 +4,6 @@ package eu.dnetlib.pace.common;
|
||||||
import java.io.IOException;
|
import java.io.IOException;
|
||||||
import java.io.StringWriter;
|
import java.io.StringWriter;
|
||||||
import java.nio.charset.StandardCharsets;
|
import java.nio.charset.StandardCharsets;
|
||||||
import java.text.Normalizer;
|
|
||||||
import java.util.*;
|
import java.util.*;
|
||||||
import java.util.regex.Matcher;
|
import java.util.regex.Matcher;
|
||||||
import java.util.regex.Pattern;
|
import java.util.regex.Pattern;
|
||||||
|
@ -14,19 +13,15 @@ import org.apache.commons.io.IOUtils;
|
||||||
import org.apache.commons.lang3.StringUtils;
|
import org.apache.commons.lang3.StringUtils;
|
||||||
|
|
||||||
import com.google.common.base.Joiner;
|
import com.google.common.base.Joiner;
|
||||||
import com.google.common.base.Splitter;
|
|
||||||
import com.google.common.collect.Iterables;
|
|
||||||
import com.google.common.collect.Sets;
|
import com.google.common.collect.Sets;
|
||||||
import com.ibm.icu.text.Transliterator;
|
import com.ibm.icu.text.Transliterator;
|
||||||
|
|
||||||
import eu.dnetlib.pace.clustering.NGramUtils;
|
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* Set of common functions for the framework
|
* Set of common functions for the framework
|
||||||
*
|
*
|
||||||
* @author claudio
|
* @author claudio
|
||||||
*/
|
*/
|
||||||
public class AbstractPaceFunctions {
|
public class AbstractPaceFunctions extends PaceCommonUtils {
|
||||||
|
|
||||||
// city map to be used when translating the city names into codes
|
// city map to be used when translating the city names into codes
|
||||||
private static Map<String, String> cityMap = AbstractPaceFunctions
|
private static Map<String, String> cityMap = AbstractPaceFunctions
|
||||||
|
@ -41,9 +36,6 @@ public class AbstractPaceFunctions {
|
||||||
protected static Set<String> stopwords_it = loadFromClasspath("/eu/dnetlib/pace/config/stopwords_it.txt");
|
protected static Set<String> stopwords_it = loadFromClasspath("/eu/dnetlib/pace/config/stopwords_it.txt");
|
||||||
protected static Set<String> stopwords_pt = loadFromClasspath("/eu/dnetlib/pace/config/stopwords_pt.txt");
|
protected static Set<String> stopwords_pt = loadFromClasspath("/eu/dnetlib/pace/config/stopwords_pt.txt");
|
||||||
|
|
||||||
// transliterator
|
|
||||||
protected static Transliterator transliterator = Transliterator.getInstance("Any-Eng");
|
|
||||||
|
|
||||||
// blacklist of ngrams: to avoid generic keys
|
// blacklist of ngrams: to avoid generic keys
|
||||||
protected static Set<String> ngramBlacklist = loadFromClasspath("/eu/dnetlib/pace/config/ngram_blacklist.txt");
|
protected static Set<String> ngramBlacklist = loadFromClasspath("/eu/dnetlib/pace/config/ngram_blacklist.txt");
|
||||||
|
|
||||||
|
@ -51,8 +43,6 @@ public class AbstractPaceFunctions {
|
||||||
public static final Pattern HTML_REGEX = Pattern.compile("<[^>]*>");
|
public static final Pattern HTML_REGEX = Pattern.compile("<[^>]*>");
|
||||||
|
|
||||||
private static final String alpha = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789 ";
|
private static final String alpha = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789 ";
|
||||||
private static final String aliases_from = "⁰¹²³⁴⁵⁶⁷⁸⁹⁺⁻⁼⁽⁾ⁿ₀₁₂₃₄₅₆₇₈₉₊₋₌₍₎àáâäæãåāèéêëēėęəîïíīįìôöòóœøōõûüùúūßśšłžźżçćčñń";
|
|
||||||
private static final String aliases_to = "0123456789+-=()n0123456789+-=()aaaaaaaaeeeeeeeeiiiiiioooooooouuuuussslzzzcccnn";
|
|
||||||
|
|
||||||
// doi prefix for normalization
|
// doi prefix for normalization
|
||||||
public static final Pattern DOI_PREFIX = Pattern.compile("(https?:\\/\\/dx\\.doi\\.org\\/)|(doi:)");
|
public static final Pattern DOI_PREFIX = Pattern.compile("(https?:\\/\\/dx\\.doi\\.org\\/)|(doi:)");
|
||||||
|
@ -129,25 +119,6 @@ public class AbstractPaceFunctions {
|
||||||
return numberPattern.matcher(strNum).matches();
|
return numberPattern.matcher(strNum).matches();
|
||||||
}
|
}
|
||||||
|
|
||||||
protected static String fixAliases(final String s) {
|
|
||||||
final StringBuilder sb = new StringBuilder();
|
|
||||||
|
|
||||||
s.chars().forEach(ch -> {
|
|
||||||
final int i = StringUtils.indexOf(aliases_from, ch);
|
|
||||||
sb.append(i >= 0 ? aliases_to.charAt(i) : (char) ch);
|
|
||||||
});
|
|
||||||
|
|
||||||
return sb.toString();
|
|
||||||
}
|
|
||||||
|
|
||||||
protected static String transliterate(final String s) {
|
|
||||||
try {
|
|
||||||
return transliterator.transliterate(s);
|
|
||||||
} catch (Exception e) {
|
|
||||||
return s;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
protected static String removeSymbols(final String s) {
|
protected static String removeSymbols(final String s) {
|
||||||
final StringBuilder sb = new StringBuilder();
|
final StringBuilder sb = new StringBuilder();
|
||||||
|
|
||||||
|
@ -162,23 +133,6 @@ public class AbstractPaceFunctions {
|
||||||
return s != null;
|
return s != null;
|
||||||
}
|
}
|
||||||
|
|
||||||
public static String normalize(final String s) {
|
|
||||||
return fixAliases(transliterate(nfd(unicodeNormalization(s))))
|
|
||||||
.toLowerCase()
|
|
||||||
// do not compact the regexes in a single expression, would cause StackOverflowError in case of large input
|
|
||||||
// strings
|
|
||||||
.replaceAll("[^ \\w]+", "")
|
|
||||||
.replaceAll("(\\p{InCombiningDiacriticalMarks})+", "")
|
|
||||||
.replaceAll("(\\p{Punct})+", " ")
|
|
||||||
.replaceAll("(\\d)+", " ")
|
|
||||||
.replaceAll("(\\n)+", " ")
|
|
||||||
.trim();
|
|
||||||
}
|
|
||||||
|
|
||||||
public static String nfd(final String s) {
|
|
||||||
return Normalizer.normalize(s, Normalizer.Form.NFD);
|
|
||||||
}
|
|
||||||
|
|
||||||
public static String utf8(final String s) {
|
public static String utf8(final String s) {
|
||||||
byte[] bytes = s.getBytes(StandardCharsets.UTF_8);
|
byte[] bytes = s.getBytes(StandardCharsets.UTF_8);
|
||||||
return new String(bytes, StandardCharsets.UTF_8);
|
return new String(bytes, StandardCharsets.UTF_8);
|
||||||
|
@ -233,22 +187,6 @@ public class AbstractPaceFunctions {
|
||||||
return newset;
|
return newset;
|
||||||
}
|
}
|
||||||
|
|
||||||
public static Set<String> loadFromClasspath(final String classpath) {
|
|
||||||
|
|
||||||
Transliterator transliterator = Transliterator.getInstance("Any-Eng");
|
|
||||||
|
|
||||||
final Set<String> h = Sets.newHashSet();
|
|
||||||
try {
|
|
||||||
for (final String s : IOUtils
|
|
||||||
.readLines(NGramUtils.class.getResourceAsStream(classpath), StandardCharsets.UTF_8)) {
|
|
||||||
h.add(fixAliases(transliterator.transliterate(s))); // transliteration of the stopwords
|
|
||||||
}
|
|
||||||
} catch (final Throwable e) {
|
|
||||||
return Sets.newHashSet();
|
|
||||||
}
|
|
||||||
return h;
|
|
||||||
}
|
|
||||||
|
|
||||||
public static Map<String, String> loadMapFromClasspath(final String classpath) {
|
public static Map<String, String> loadMapFromClasspath(final String classpath) {
|
||||||
|
|
||||||
Transliterator transliterator = Transliterator.getInstance("Any-Eng");
|
Transliterator transliterator = Transliterator.getInstance("Any-Eng");
|
||||||
|
@ -303,10 +241,6 @@ public class AbstractPaceFunctions {
|
||||||
return StringUtils.substring(s, 0, 1).toLowerCase();
|
return StringUtils.substring(s, 0, 1).toLowerCase();
|
||||||
}
|
}
|
||||||
|
|
||||||
protected static Iterable<String> tokens(final String s, final int maxTokens) {
|
|
||||||
return Iterables.limit(Splitter.on(" ").omitEmptyStrings().trimResults().split(s), maxTokens);
|
|
||||||
}
|
|
||||||
|
|
||||||
public static String normalizePid(String pid) {
|
public static String normalizePid(String pid) {
|
||||||
return DOI_PREFIX.matcher(pid.toLowerCase()).replaceAll("");
|
return DOI_PREFIX.matcher(pid.toLowerCase()).replaceAll("");
|
||||||
}
|
}
|
||||||
|
|
|
@ -3,7 +3,7 @@ package eu.dnetlib.pace.model
|
||||||
import com.jayway.jsonpath.{Configuration, JsonPath}
|
import com.jayway.jsonpath.{Configuration, JsonPath}
|
||||||
import eu.dnetlib.pace.common.AbstractPaceFunctions
|
import eu.dnetlib.pace.common.AbstractPaceFunctions
|
||||||
import eu.dnetlib.pace.config.{DedupConfig, Type}
|
import eu.dnetlib.pace.config.{DedupConfig, Type}
|
||||||
import eu.dnetlib.pace.util.MapDocumentUtil
|
import eu.dnetlib.pace.util.{MapDocumentUtil, SparkCompatUtils}
|
||||||
import org.apache.commons.lang3.StringUtils
|
import org.apache.commons.lang3.StringUtils
|
||||||
import org.apache.spark.sql.catalyst.encoders.RowEncoder
|
import org.apache.spark.sql.catalyst.encoders.RowEncoder
|
||||||
import org.apache.spark.sql.catalyst.expressions.GenericRowWithSchema
|
import org.apache.spark.sql.catalyst.expressions.GenericRowWithSchema
|
||||||
|
@ -52,7 +52,7 @@ case class SparkModel(conf: DedupConfig) {
|
||||||
val orderingFieldPosition: Int = schema.fieldIndex(orderingFieldName)
|
val orderingFieldPosition: Int = schema.fieldIndex(orderingFieldName)
|
||||||
|
|
||||||
val parseJsonDataset: (Dataset[String] => Dataset[Row]) = df => {
|
val parseJsonDataset: (Dataset[String] => Dataset[Row]) = df => {
|
||||||
df.map(r => rowFromJson(r))(RowEncoder(schema))
|
df.map(r => rowFromJson(r))(SparkCompatUtils.encoderFor(schema))
|
||||||
}
|
}
|
||||||
|
|
||||||
def rowFromJson(json: String): Row = {
|
def rowFromJson(json: String): Row = {
|
||||||
|
|
|
@ -1,8 +1,10 @@
|
||||||
|
|
||||||
package eu.dnetlib.pace.tree;
|
package eu.dnetlib.pace.tree;
|
||||||
|
|
||||||
|
import java.util.ArrayList;
|
||||||
import java.util.List;
|
import java.util.List;
|
||||||
import java.util.Map;
|
import java.util.Map;
|
||||||
|
import java.util.function.BiFunction;
|
||||||
import java.util.stream.Collectors;
|
import java.util.stream.Collectors;
|
||||||
|
|
||||||
import com.wcohen.ss.AbstractStringDistance;
|
import com.wcohen.ss.AbstractStringDistance;
|
||||||
|
@ -11,6 +13,7 @@ import eu.dnetlib.pace.config.Config;
|
||||||
import eu.dnetlib.pace.model.Person;
|
import eu.dnetlib.pace.model.Person;
|
||||||
import eu.dnetlib.pace.tree.support.AbstractListComparator;
|
import eu.dnetlib.pace.tree.support.AbstractListComparator;
|
||||||
import eu.dnetlib.pace.tree.support.ComparatorClass;
|
import eu.dnetlib.pace.tree.support.ComparatorClass;
|
||||||
|
import eu.dnetlib.pace.util.AuthorMatchers;
|
||||||
|
|
||||||
@ComparatorClass("authorsMatch")
|
@ComparatorClass("authorsMatch")
|
||||||
public class AuthorsMatch extends AbstractListComparator {
|
public class AuthorsMatch extends AbstractListComparator {
|
||||||
|
@ -41,24 +44,36 @@ public class AuthorsMatch extends AbstractListComparator {
|
||||||
}
|
}
|
||||||
|
|
||||||
@Override
|
@Override
|
||||||
public double compare(final List<String> a, final List<String> b, final Config conf) {
|
public double compare(final List<String> left, final List<String> right, final Config conf) {
|
||||||
if (a.isEmpty() || b.isEmpty())
|
if (left.isEmpty() || right.isEmpty())
|
||||||
return -1;
|
return -1;
|
||||||
|
|
||||||
if (a.size() > SIZE_THRESHOLD || b.size() > SIZE_THRESHOLD)
|
if (left.size() > SIZE_THRESHOLD || right.size() > SIZE_THRESHOLD)
|
||||||
return 1.0;
|
return 1.0;
|
||||||
|
|
||||||
int maxMiss = Integer.MAX_VALUE;
|
|
||||||
List<Person> bList = b.stream().map(author -> new Person(author, false)).collect(Collectors.toList());
|
|
||||||
|
|
||||||
Double threshold = getDoubleParam("threshold");
|
Double threshold = getDoubleParam("threshold");
|
||||||
|
int maxMiss = Integer.MAX_VALUE;
|
||||||
|
|
||||||
if (threshold != null && threshold >= 0.0 && threshold <= 1.0 && a.size() == b.size()) {
|
if (threshold != null && threshold >= 0.0 && threshold <= 1.0 && left.size() == right.size()) {
|
||||||
maxMiss = (int) Math.floor((1 - threshold) * Math.max(a.size(), b.size()));
|
maxMiss = (int) Math.floor((1 - threshold) * Math.max(left.size(), right.size()));
|
||||||
}
|
}
|
||||||
|
|
||||||
int common = 0;
|
int common = 0;
|
||||||
|
|
||||||
|
List<String> a = new ArrayList<>(left);
|
||||||
|
List<String> b = new ArrayList<>(right);
|
||||||
|
|
||||||
|
common += AuthorMatchers
|
||||||
|
.removeMatches(a, b, (BiFunction<String, String, Object>) AuthorMatchers::matchEqualsIgnoreCase)
|
||||||
|
.size() / 2;
|
||||||
|
common += AuthorMatchers
|
||||||
|
.removeMatches(a, b, (BiFunction<String, String, Object>) AuthorMatchers::matchOrderedTokenAndAbbreviations)
|
||||||
|
.size() / 2;
|
||||||
|
|
||||||
|
List<Person> bList = b.stream().map(author -> new Person(author, false)).collect(Collectors.toList());
|
||||||
|
|
||||||
// compare each element of List1 with each element of List2
|
// compare each element of List1 with each element of List2
|
||||||
|
int alreadyMatched = common;
|
||||||
for (int i = 0; i < a.size(); i++) {
|
for (int i = 0; i < a.size(); i++) {
|
||||||
Person p1 = new Person(a.get(i), false);
|
Person p1 = new Person(a.get(i), false);
|
||||||
|
|
||||||
|
@ -123,13 +138,13 @@ public class AuthorsMatch extends AbstractListComparator {
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
if (i - common > maxMiss) {
|
if (i - common - alreadyMatched > maxMiss) {
|
||||||
return 0.0;
|
return 0.0;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
// normalization factor to compute the score
|
// normalization factor to compute the score
|
||||||
int normFactor = a.size() == b.size() ? a.size() : (a.size() + b.size() - common);
|
int normFactor = left.size() == right.size() ? left.size() : (left.size() + right.size() - common);
|
||||||
|
|
||||||
if (TYPE.equals("percentage")) {
|
if (TYPE.equals("percentage")) {
|
||||||
return (double) common / normFactor;
|
return (double) common / normFactor;
|
||||||
|
@ -160,5 +175,4 @@ public class AuthorsMatch extends AbstractListComparator {
|
||||||
public String normalization(String s) {
|
public String normalization(String s) {
|
||||||
return normalize(utf8(cleanup(s)));
|
return normalize(utf8(cleanup(s)));
|
||||||
}
|
}
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
|
@ -23,15 +23,18 @@ public class InstanceTypeMatch extends AbstractListComparator {
|
||||||
|
|
||||||
// jolly types
|
// jolly types
|
||||||
translationMap.put("Conference object", "*");
|
translationMap.put("Conference object", "*");
|
||||||
|
translationMap.put("Research", "*");
|
||||||
translationMap.put("Other literature type", "*");
|
translationMap.put("Other literature type", "*");
|
||||||
translationMap.put("Unknown", "*");
|
translationMap.put("Unknown", "*");
|
||||||
translationMap.put("UNKNOWN", "*");
|
translationMap.put("UNKNOWN", "*");
|
||||||
|
|
||||||
// article types
|
// article types
|
||||||
translationMap.put("Article", "Article");
|
translationMap.put("Article", "Article");
|
||||||
|
translationMap.put("Journal", "Article");
|
||||||
translationMap.put("Data Paper", "Article");
|
translationMap.put("Data Paper", "Article");
|
||||||
translationMap.put("Software Paper", "Article");
|
translationMap.put("Software Paper", "Article");
|
||||||
translationMap.put("Preprint", "Article");
|
translationMap.put("Preprint", "Article");
|
||||||
|
translationMap.put("Part of book or chapter of book", "Article");
|
||||||
|
|
||||||
// thesis types
|
// thesis types
|
||||||
translationMap.put("Thesis", "Thesis");
|
translationMap.put("Thesis", "Thesis");
|
||||||
|
|
|
@ -0,0 +1,112 @@
|
||||||
|
package eu.dnetlib.pace.util
|
||||||
|
|
||||||
|
import java.util.Locale
|
||||||
|
import java.util.regex.Pattern
|
||||||
|
import scala.util.control.Breaks.{break, breakable}
|
||||||
|
|
||||||
|
object AuthorMatchers {
|
||||||
|
val SPLIT_REGEX = Pattern.compile("[\\s,\\.]+")
|
||||||
|
|
||||||
|
val WORD_DIFF = 2
|
||||||
|
|
||||||
|
def matchEqualsIgnoreCase(a1: String, a2: String): Boolean = {
|
||||||
|
if (a1 == null || a2 == null)
|
||||||
|
false
|
||||||
|
else
|
||||||
|
a1 == a2 || a1.toLowerCase(Locale.ROOT).equals(a2.toLowerCase(Locale.ROOT))
|
||||||
|
}
|
||||||
|
|
||||||
|
def matchOtherNames(fullName: String, otherNames: Seq[String]): Boolean = {
|
||||||
|
if (otherNames != null) {
|
||||||
|
otherNames.exists(matchEqualsIgnoreCase(fullName, _))
|
||||||
|
} else {
|
||||||
|
false
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
def matchOrderedTokenAndAbbreviations(a1: String, a2: String): Boolean = {
|
||||||
|
val p1: Array[String] = SPLIT_REGEX.split(a1.trim.toLowerCase(Locale.ROOT)).filter(_.nonEmpty).sorted
|
||||||
|
val p2: Array[String] = SPLIT_REGEX.split(a2.trim.toLowerCase(Locale.ROOT)).filter(_.nonEmpty).sorted
|
||||||
|
|
||||||
|
if (p1.length < 2 || p2.length < 2) return false
|
||||||
|
if (Math.abs(p1.length - p2.length) > WORD_DIFF) return false // use alternative comparison algo
|
||||||
|
|
||||||
|
var p1Idx: Int = 0
|
||||||
|
var p2Idx: Int = 0
|
||||||
|
var shortMatches: Int = 0
|
||||||
|
var longMatches: Int = 0
|
||||||
|
while (p1Idx < p1.length && p2Idx < p2.length) {
|
||||||
|
val e1: String = p1(p1Idx)
|
||||||
|
val c1: Char = e1.charAt(0)
|
||||||
|
val e2: String = p2(p2Idx)
|
||||||
|
val c2: Char = e2.charAt(0)
|
||||||
|
if (c1 < c2) p1Idx += 1
|
||||||
|
else if (c1 > c2) p2Idx += 1
|
||||||
|
else {
|
||||||
|
var res: Boolean = false
|
||||||
|
if (e1.length != 1 && e2.length != 1) {
|
||||||
|
res = e1 == e2
|
||||||
|
if (res)
|
||||||
|
longMatches += 1
|
||||||
|
} else {
|
||||||
|
res = true
|
||||||
|
shortMatches += 1
|
||||||
|
}
|
||||||
|
if (res) {
|
||||||
|
p1Idx += 1
|
||||||
|
p2Idx += 1
|
||||||
|
} else {
|
||||||
|
val diff: Int = e1.compareTo(e2)
|
||||||
|
if (diff < 0) p1Idx += 1
|
||||||
|
else if (diff > 0) p2Idx += 1
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
longMatches > 0 && (shortMatches + longMatches) == Math.min(p1.length, p2.length)
|
||||||
|
}
|
||||||
|
|
||||||
|
def removeMatches(
|
||||||
|
graph_authors: java.util.List[String],
|
||||||
|
orcid_authors: java.util.List[String],
|
||||||
|
matchingFunc: java.util.function.BiFunction[String,String,Boolean]
|
||||||
|
) : java.util.List[String] = {
|
||||||
|
removeMatches(graph_authors, orcid_authors, (a, b) => matchingFunc(a,b))
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
|
def removeMatches(
|
||||||
|
graph_authors: java.util.List[String],
|
||||||
|
orcid_authors: java.util.List[String],
|
||||||
|
matchingFunc: (String, String) => Boolean
|
||||||
|
) : java.util.List[String] = {
|
||||||
|
val matched = new java.util.ArrayList[String]()
|
||||||
|
|
||||||
|
if (graph_authors != null && !graph_authors.isEmpty) {
|
||||||
|
val ait = graph_authors.iterator
|
||||||
|
|
||||||
|
while (ait.hasNext) {
|
||||||
|
val author = ait.next()
|
||||||
|
val oit = orcid_authors.iterator
|
||||||
|
|
||||||
|
breakable {
|
||||||
|
while (oit.hasNext) {
|
||||||
|
val orcid = oit.next()
|
||||||
|
|
||||||
|
if (matchingFunc(author, orcid)) {
|
||||||
|
ait.remove()
|
||||||
|
oit.remove()
|
||||||
|
|
||||||
|
matched.add(author)
|
||||||
|
matched.add(orcid)
|
||||||
|
|
||||||
|
break()
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
matched
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
File diff suppressed because it is too large
Load Diff
|
@ -0,0 +1,12 @@
|
||||||
|
package eu.dnetlib.pace.util
|
||||||
|
|
||||||
|
import org.apache.spark.sql.Row
|
||||||
|
import org.apache.spark.sql.catalyst.encoders.{ExpressionEncoder, RowEncoder}
|
||||||
|
import org.apache.spark.sql.types.StructType
|
||||||
|
|
||||||
|
object SparkCompatUtils {
|
||||||
|
|
||||||
|
def encoderFor(schema: StructType): ExpressionEncoder[Row] = {
|
||||||
|
RowEncoder(schema)
|
||||||
|
}
|
||||||
|
}
|
|
@ -0,0 +1,12 @@
|
||||||
|
package eu.dnetlib.pace.util
|
||||||
|
|
||||||
|
import org.apache.spark.sql.Row
|
||||||
|
import org.apache.spark.sql.catalyst.encoders.ExpressionEncoder
|
||||||
|
import org.apache.spark.sql.types.StructType
|
||||||
|
|
||||||
|
object SparkCompatUtils {
|
||||||
|
|
||||||
|
def encoderFor(schema: StructType): ExpressionEncoder[Row] = {
|
||||||
|
ExpressionEncoder(schema)
|
||||||
|
}
|
||||||
|
}
|
|
@ -7,6 +7,7 @@ import java.util.HashMap;
|
||||||
import java.util.Map;
|
import java.util.Map;
|
||||||
|
|
||||||
import org.junit.jupiter.api.BeforeAll;
|
import org.junit.jupiter.api.BeforeAll;
|
||||||
|
import org.junit.jupiter.api.Disabled;
|
||||||
import org.junit.jupiter.api.Test;
|
import org.junit.jupiter.api.Test;
|
||||||
|
|
||||||
import eu.dnetlib.pace.model.Person;
|
import eu.dnetlib.pace.model.Person;
|
||||||
|
@ -22,7 +23,7 @@ public class UtilTest {
|
||||||
}
|
}
|
||||||
|
|
||||||
@Test
|
@Test
|
||||||
@Ignore
|
@Disabled
|
||||||
public void paceResolverTest() {
|
public void paceResolverTest() {
|
||||||
PaceResolver paceResolver = new PaceResolver();
|
PaceResolver paceResolver = new PaceResolver();
|
||||||
paceResolver.getComparator("keywordMatch", params);
|
paceResolver.getComparator("keywordMatch", params);
|
||||||
|
|
|
@ -0,0 +1,113 @@
|
||||||
|
<?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/maven-v4_0_0.xsd">
|
||||||
|
<parent>
|
||||||
|
<artifactId>dhp</artifactId>
|
||||||
|
<groupId>eu.dnetlib.dhp</groupId>
|
||||||
|
<version>1.2.5-SNAPSHOT</version>
|
||||||
|
</parent>
|
||||||
|
<modelVersion>4.0.0</modelVersion>
|
||||||
|
<artifactId>dhp-shade-package</artifactId>
|
||||||
|
<description>This module create a jar of all module dependencies</description>
|
||||||
|
<build>
|
||||||
|
<plugins>
|
||||||
|
<plugin>
|
||||||
|
<artifactId>maven-shade-plugin</artifactId>
|
||||||
|
<executions>
|
||||||
|
<execution>
|
||||||
|
<phase>package</phase>
|
||||||
|
<goals>
|
||||||
|
<goal>shade</goal>
|
||||||
|
</goals>
|
||||||
|
<configuration>
|
||||||
|
<transformers>
|
||||||
|
<transformer>
|
||||||
|
<mainClass>eu.dnetlib.dhp.oa.dedup.SparkCreateSimRels</mainClass>
|
||||||
|
</transformer>
|
||||||
|
<transformer />
|
||||||
|
<transformer>
|
||||||
|
<resource>META-INF/cxf/bus-extensions.txt</resource>
|
||||||
|
</transformer>
|
||||||
|
</transformers>
|
||||||
|
<filters>
|
||||||
|
<filter>
|
||||||
|
<artifact>*:*</artifact>
|
||||||
|
<excludes>
|
||||||
|
<exclude>META-INF/maven/**</exclude>
|
||||||
|
<exclude>META-INF/*.SF</exclude>
|
||||||
|
<exclude>META-INF/*.DSA</exclude>
|
||||||
|
<exclude>META-INF/*.RSA</exclude>
|
||||||
|
</excludes>
|
||||||
|
</filter>
|
||||||
|
</filters>
|
||||||
|
<relocations>
|
||||||
|
<relocation>
|
||||||
|
<pattern>com</pattern>
|
||||||
|
<shadedPattern>repackaged.com.google.common</shadedPattern>
|
||||||
|
<includes>
|
||||||
|
<include>com.google.common.**</include>
|
||||||
|
</includes>
|
||||||
|
</relocation>
|
||||||
|
</relocations>
|
||||||
|
</configuration>
|
||||||
|
</execution>
|
||||||
|
</executions>
|
||||||
|
</plugin>
|
||||||
|
</plugins>
|
||||||
|
</build>
|
||||||
|
<dependencies>
|
||||||
|
<dependency>
|
||||||
|
<groupId>org.projectlombok</groupId>
|
||||||
|
<artifactId>lombok</artifactId>
|
||||||
|
<version>1.18.28</version>
|
||||||
|
<scope>provided</scope>
|
||||||
|
</dependency>
|
||||||
|
<dependency>
|
||||||
|
<groupId>org.junit.jupiter</groupId>
|
||||||
|
<artifactId>junit-jupiter</artifactId>
|
||||||
|
<version>5.6.1</version>
|
||||||
|
<scope>test</scope>
|
||||||
|
<exclusions>
|
||||||
|
<exclusion>
|
||||||
|
<artifactId>junit-jupiter-api</artifactId>
|
||||||
|
<groupId>org.junit.jupiter</groupId>
|
||||||
|
</exclusion>
|
||||||
|
<exclusion>
|
||||||
|
<artifactId>junit-jupiter-params</artifactId>
|
||||||
|
<groupId>org.junit.jupiter</groupId>
|
||||||
|
</exclusion>
|
||||||
|
<exclusion>
|
||||||
|
<artifactId>junit-jupiter-engine</artifactId>
|
||||||
|
<groupId>org.junit.jupiter</groupId>
|
||||||
|
</exclusion>
|
||||||
|
</exclusions>
|
||||||
|
</dependency>
|
||||||
|
<dependency>
|
||||||
|
<groupId>org.mockito</groupId>
|
||||||
|
<artifactId>mockito-core</artifactId>
|
||||||
|
<version>3.3.3</version>
|
||||||
|
<scope>test</scope>
|
||||||
|
<exclusions>
|
||||||
|
<exclusion>
|
||||||
|
<artifactId>byte-buddy</artifactId>
|
||||||
|
<groupId>net.bytebuddy</groupId>
|
||||||
|
</exclusion>
|
||||||
|
<exclusion>
|
||||||
|
<artifactId>byte-buddy-agent</artifactId>
|
||||||
|
<groupId>net.bytebuddy</groupId>
|
||||||
|
</exclusion>
|
||||||
|
</exclusions>
|
||||||
|
</dependency>
|
||||||
|
<dependency>
|
||||||
|
<groupId>org.mockito</groupId>
|
||||||
|
<artifactId>mockito-junit-jupiter</artifactId>
|
||||||
|
<version>3.3.3</version>
|
||||||
|
<scope>test</scope>
|
||||||
|
</dependency>
|
||||||
|
</dependencies>
|
||||||
|
<distributionManagement>
|
||||||
|
<site>
|
||||||
|
<id>DHPSite</id>
|
||||||
|
<url>${dhp.site.stage.path}/dhp-common</url>
|
||||||
|
</site>
|
||||||
|
</distributionManagement>
|
||||||
|
</project>
|
|
@ -0,0 +1,169 @@
|
||||||
|
<?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">
|
||||||
|
<modelVersion>4.0.0</modelVersion>
|
||||||
|
<parent>
|
||||||
|
<groupId>eu.dnetlib.dhp</groupId>
|
||||||
|
<artifactId>dhp</artifactId>
|
||||||
|
<version>1.2.5-SNAPSHOT</version>
|
||||||
|
<relativePath>../pom.xml</relativePath>
|
||||||
|
|
||||||
|
</parent>
|
||||||
|
|
||||||
|
<artifactId>dhp-shade-package</artifactId>
|
||||||
|
<packaging>jar</packaging>
|
||||||
|
|
||||||
|
<distributionManagement>
|
||||||
|
<site>
|
||||||
|
<id>DHPSite</id>
|
||||||
|
<url>${dhp.site.stage.path}/dhp-common</url>
|
||||||
|
</site>
|
||||||
|
</distributionManagement>
|
||||||
|
|
||||||
|
<description>This module create a jar of all module dependencies</description>
|
||||||
|
|
||||||
|
|
||||||
|
<dependencies>
|
||||||
|
|
||||||
|
<dependency>
|
||||||
|
<groupId>eu.dnetlib.dhp</groupId>
|
||||||
|
<artifactId>dhp-actionmanager</artifactId>
|
||||||
|
<version>${project.version}</version>
|
||||||
|
</dependency>
|
||||||
|
<!-- <dependency>-->
|
||||||
|
<!-- <groupId>eu.dnetlib.dhp</groupId>-->
|
||||||
|
<!-- <artifactId>dhp-aggregation</artifactId>-->
|
||||||
|
<!-- <version>${project.version}</version>-->
|
||||||
|
<!-- </dependency>-->
|
||||||
|
<!-- <dependency>-->
|
||||||
|
<!-- <groupId>eu.dnetlib.dhp</groupId>-->
|
||||||
|
<!-- <artifactId>dhp-blacklist</artifactId>-->
|
||||||
|
<!-- <version>${project.version}</version>-->
|
||||||
|
<!-- </dependency>-->
|
||||||
|
<!-- <dependency>-->
|
||||||
|
<!-- <groupId>eu.dnetlib.dhp</groupId>-->
|
||||||
|
<!-- <artifactId>dhp-broker-events</artifactId>-->
|
||||||
|
<!-- <version>${project.version}</version>-->
|
||||||
|
<!-- </dependency>-->
|
||||||
|
<!-- <dependency>-->
|
||||||
|
<!-- <groupId>eu.dnetlib.dhp</groupId>-->
|
||||||
|
<!-- <artifactId>dhp-dedup-openaire</artifactId>-->
|
||||||
|
<!-- <version>${project.version}</version>-->
|
||||||
|
<!-- </dependency>-->
|
||||||
|
<!-- <dependency>-->
|
||||||
|
<!-- <groupId>eu.dnetlib.dhp</groupId>-->
|
||||||
|
<!-- <artifactId>dhp-enrichment</artifactId>-->
|
||||||
|
<!-- <version>${project.version}</version>-->
|
||||||
|
<!-- </dependency>-->
|
||||||
|
<dependency>
|
||||||
|
<groupId>eu.dnetlib.dhp</groupId>
|
||||||
|
<artifactId>dhp-graph-mapper</artifactId>
|
||||||
|
<version>${project.version}</version>
|
||||||
|
</dependency>
|
||||||
|
<dependency>
|
||||||
|
<groupId>eu.dnetlib.dhp</groupId>
|
||||||
|
<artifactId>dhp-graph-provision</artifactId>
|
||||||
|
<version>${project.version}</version>
|
||||||
|
</dependency>
|
||||||
|
<dependency>
|
||||||
|
<groupId>eu.dnetlib.dhp</groupId>
|
||||||
|
<artifactId>dhp-impact-indicators</artifactId>
|
||||||
|
<version>${project.version}</version>
|
||||||
|
</dependency>
|
||||||
|
<dependency>
|
||||||
|
<groupId>eu.dnetlib.dhp</groupId>
|
||||||
|
<artifactId>dhp-stats-actionsets</artifactId>
|
||||||
|
<version>${project.version}</version>
|
||||||
|
</dependency>
|
||||||
|
<dependency>
|
||||||
|
<groupId>eu.dnetlib.dhp</groupId>
|
||||||
|
<artifactId>dhp-stats-hist-snaps</artifactId>
|
||||||
|
<version>${project.version}</version>
|
||||||
|
</dependency>
|
||||||
|
<dependency>
|
||||||
|
<groupId>eu.dnetlib.dhp</groupId>
|
||||||
|
<artifactId>dhp-stats-monitor-irish</artifactId>
|
||||||
|
<version>${project.version}</version>
|
||||||
|
</dependency>
|
||||||
|
<dependency>
|
||||||
|
<groupId>eu.dnetlib.dhp</groupId>
|
||||||
|
<artifactId>dhp-stats-promote</artifactId>
|
||||||
|
<version>${project.version}</version>
|
||||||
|
</dependency>
|
||||||
|
<dependency>
|
||||||
|
<groupId>eu.dnetlib.dhp</groupId>
|
||||||
|
<artifactId>dhp-stats-update</artifactId>
|
||||||
|
<version>${project.version}</version>
|
||||||
|
</dependency>
|
||||||
|
<dependency>
|
||||||
|
<groupId>eu.dnetlib.dhp</groupId>
|
||||||
|
<artifactId>dhp-swh</artifactId>
|
||||||
|
<version>${project.version}</version>
|
||||||
|
</dependency>
|
||||||
|
<dependency>
|
||||||
|
<groupId>eu.dnetlib.dhp</groupId>
|
||||||
|
<artifactId>dhp-usage-raw-data-update</artifactId>
|
||||||
|
<version>${project.version}</version>
|
||||||
|
</dependency>
|
||||||
|
<dependency>
|
||||||
|
<groupId>eu.dnetlib.dhp</groupId>
|
||||||
|
<artifactId>dhp-usage-stats-build</artifactId>
|
||||||
|
<version>${project.version}</version>
|
||||||
|
</dependency>
|
||||||
|
</dependencies>
|
||||||
|
|
||||||
|
|
||||||
|
<build>
|
||||||
|
<plugins>
|
||||||
|
<plugin>
|
||||||
|
<groupId>org.apache.maven.plugins</groupId>
|
||||||
|
<artifactId>maven-shade-plugin</artifactId>
|
||||||
|
<executions>
|
||||||
|
<execution>
|
||||||
|
<phase>package</phase>
|
||||||
|
<goals>
|
||||||
|
<goal>shade</goal>
|
||||||
|
</goals>
|
||||||
|
<configuration>
|
||||||
|
<transformers>
|
||||||
|
<transformer
|
||||||
|
implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
|
||||||
|
<mainClass>eu.dnetlib.dhp.oa.dedup.SparkCreateSimRels</mainClass>
|
||||||
|
</transformer>
|
||||||
|
<!-- This is needed if you have dependencies that use Service Loader. Most Google Cloud client libraries do. -->
|
||||||
|
<transformer
|
||||||
|
implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer"/>
|
||||||
|
<transformer
|
||||||
|
implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer">
|
||||||
|
<resource>META-INF/cxf/bus-extensions.txt</resource>
|
||||||
|
</transformer>
|
||||||
|
</transformers>
|
||||||
|
<filters>
|
||||||
|
<filter>
|
||||||
|
<artifact>*:*</artifact>
|
||||||
|
<excludes>
|
||||||
|
<exclude>META-INF/maven/**</exclude>
|
||||||
|
<exclude>META-INF/*.SF</exclude>
|
||||||
|
<exclude>META-INF/*.DSA</exclude>
|
||||||
|
<exclude>META-INF/*.RSA</exclude>
|
||||||
|
</excludes>
|
||||||
|
</filter>
|
||||||
|
</filters>
|
||||||
|
<relocations>
|
||||||
|
<relocation>
|
||||||
|
<pattern>com</pattern>
|
||||||
|
<shadedPattern>repackaged.com.google.common</shadedPattern>
|
||||||
|
<includes>
|
||||||
|
<include>com.google.common.**</include>
|
||||||
|
</includes>
|
||||||
|
</relocation>
|
||||||
|
</relocations>
|
||||||
|
</configuration>
|
||||||
|
</execution>
|
||||||
|
</executions>
|
||||||
|
</plugin>
|
||||||
|
</plugins>
|
||||||
|
</build>
|
||||||
|
|
||||||
|
</project>
|
|
@ -7,8 +7,7 @@ import java.util.function.BiFunction;
|
||||||
|
|
||||||
import eu.dnetlib.dhp.common.FunctionalInterfaceSupport.SerializableSupplier;
|
import eu.dnetlib.dhp.common.FunctionalInterfaceSupport.SerializableSupplier;
|
||||||
import eu.dnetlib.dhp.schema.oaf.Oaf;
|
import eu.dnetlib.dhp.schema.oaf.Oaf;
|
||||||
import eu.dnetlib.dhp.schema.oaf.OafEntity;
|
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
|
||||||
import eu.dnetlib.dhp.schema.oaf.Relation;
|
|
||||||
|
|
||||||
/** OAF model merging support. */
|
/** OAF model merging support. */
|
||||||
public class MergeAndGet {
|
public class MergeAndGet {
|
||||||
|
@ -46,20 +45,7 @@ public class MergeAndGet {
|
||||||
}
|
}
|
||||||
|
|
||||||
private static <G extends Oaf, A extends Oaf> G mergeFromAndGet(G x, A y) {
|
private static <G extends Oaf, A extends Oaf> G mergeFromAndGet(G x, A y) {
|
||||||
if (isSubClass(x, Relation.class) && isSubClass(y, Relation.class)) {
|
return (G) MergeUtils.merge(x, y);
|
||||||
((Relation) x).mergeFrom((Relation) y);
|
|
||||||
return x;
|
|
||||||
} else if (isSubClass(x, OafEntity.class)
|
|
||||||
&& isSubClass(y, OafEntity.class)
|
|
||||||
&& isSubClass(x, y)) {
|
|
||||||
((OafEntity) x).mergeFrom((OafEntity) y);
|
|
||||||
return x;
|
|
||||||
}
|
|
||||||
throw new RuntimeException(
|
|
||||||
String
|
|
||||||
.format(
|
|
||||||
"MERGE_FROM_AND_GET incompatible types: %s, %s",
|
|
||||||
x.getClass().getCanonicalName(), y.getClass().getCanonicalName()));
|
|
||||||
}
|
}
|
||||||
|
|
||||||
@SuppressWarnings("unchecked")
|
@SuppressWarnings("unchecked")
|
||||||
|
|
|
@ -0,0 +1,39 @@
|
||||||
|
/*
|
||||||
|
* Copyright (c) 2024.
|
||||||
|
* SPDX-FileCopyrightText: © 2023 Consiglio Nazionale delle Ricerche
|
||||||
|
* SPDX-License-Identifier: AGPL-3.0-or-later
|
||||||
|
*/
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.actionmanager.promote;
|
||||||
|
|
||||||
|
/** Encodes the Actionset promotion strategies */
|
||||||
|
public class PromoteAction {
|
||||||
|
|
||||||
|
/** The supported actionset promotion strategies
|
||||||
|
*
|
||||||
|
* ENRICH: promotes only records in the actionset matching another record in the
|
||||||
|
* graph and enriches them applying the given MergeAndGet strategy
|
||||||
|
* UPSERT: promotes all the records in an actionset, matching records are updated
|
||||||
|
* using the given MergeAndGet strategy, the non-matching record as inserted as they are.
|
||||||
|
*/
|
||||||
|
public enum Strategy {
|
||||||
|
ENRICH, UPSERT
|
||||||
|
}
|
||||||
|
|
||||||
|
/**
|
||||||
|
* Returns the string representation of the join type implementing the given PromoteAction.
|
||||||
|
*
|
||||||
|
* @param strategy the strategy to be used to promote the Actionset contents
|
||||||
|
* @return the join type used to implement the promotion strategy
|
||||||
|
*/
|
||||||
|
public static String joinTypeForStrategy(PromoteAction.Strategy strategy) {
|
||||||
|
switch (strategy) {
|
||||||
|
case ENRICH:
|
||||||
|
return "left_outer";
|
||||||
|
case UPSERT:
|
||||||
|
return "full_outer";
|
||||||
|
default:
|
||||||
|
throw new IllegalStateException("unsupported PromoteAction: " + strategy.toString());
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
|
@ -67,8 +67,9 @@ public class PromoteActionPayloadForGraphTableJob {
|
||||||
String outputGraphTablePath = parser.get("outputGraphTablePath");
|
String outputGraphTablePath = parser.get("outputGraphTablePath");
|
||||||
logger.info("outputGraphTablePath: {}", outputGraphTablePath);
|
logger.info("outputGraphTablePath: {}", outputGraphTablePath);
|
||||||
|
|
||||||
MergeAndGet.Strategy strategy = MergeAndGet.Strategy.valueOf(parser.get("mergeAndGetStrategy").toUpperCase());
|
MergeAndGet.Strategy mergeAndGetStrategy = MergeAndGet.Strategy
|
||||||
logger.info("strategy: {}", strategy);
|
.valueOf(parser.get("mergeAndGetStrategy").toUpperCase());
|
||||||
|
logger.info("mergeAndGetStrategy: {}", mergeAndGetStrategy);
|
||||||
|
|
||||||
Boolean shouldGroupById = Optional
|
Boolean shouldGroupById = Optional
|
||||||
.ofNullable(parser.get("shouldGroupById"))
|
.ofNullable(parser.get("shouldGroupById"))
|
||||||
|
@ -76,6 +77,12 @@ public class PromoteActionPayloadForGraphTableJob {
|
||||||
.orElse(true);
|
.orElse(true);
|
||||||
logger.info("shouldGroupById: {}", shouldGroupById);
|
logger.info("shouldGroupById: {}", shouldGroupById);
|
||||||
|
|
||||||
|
PromoteAction.Strategy promoteActionStrategy = Optional
|
||||||
|
.ofNullable(parser.get("promoteActionStrategy"))
|
||||||
|
.map(PromoteAction.Strategy::valueOf)
|
||||||
|
.orElse(PromoteAction.Strategy.UPSERT);
|
||||||
|
logger.info("promoteActionStrategy: {}", promoteActionStrategy);
|
||||||
|
|
||||||
@SuppressWarnings("unchecked")
|
@SuppressWarnings("unchecked")
|
||||||
Class<? extends Oaf> rowClazz = (Class<? extends Oaf>) Class.forName(graphTableClassName);
|
Class<? extends Oaf> rowClazz = (Class<? extends Oaf>) Class.forName(graphTableClassName);
|
||||||
@SuppressWarnings("unchecked")
|
@SuppressWarnings("unchecked")
|
||||||
|
@ -97,7 +104,8 @@ public class PromoteActionPayloadForGraphTableJob {
|
||||||
inputGraphTablePath,
|
inputGraphTablePath,
|
||||||
inputActionPayloadPath,
|
inputActionPayloadPath,
|
||||||
outputGraphTablePath,
|
outputGraphTablePath,
|
||||||
strategy,
|
mergeAndGetStrategy,
|
||||||
|
promoteActionStrategy,
|
||||||
rowClazz,
|
rowClazz,
|
||||||
actionPayloadClazz,
|
actionPayloadClazz,
|
||||||
shouldGroupById);
|
shouldGroupById);
|
||||||
|
@ -124,14 +132,16 @@ public class PromoteActionPayloadForGraphTableJob {
|
||||||
String inputGraphTablePath,
|
String inputGraphTablePath,
|
||||||
String inputActionPayloadPath,
|
String inputActionPayloadPath,
|
||||||
String outputGraphTablePath,
|
String outputGraphTablePath,
|
||||||
MergeAndGet.Strategy strategy,
|
MergeAndGet.Strategy mergeAndGetStrategy,
|
||||||
|
PromoteAction.Strategy promoteActionStrategy,
|
||||||
Class<G> rowClazz,
|
Class<G> rowClazz,
|
||||||
Class<A> actionPayloadClazz, Boolean shouldGroupById) {
|
Class<A> actionPayloadClazz, Boolean shouldGroupById) {
|
||||||
Dataset<G> rowDS = readGraphTable(spark, inputGraphTablePath, rowClazz);
|
Dataset<G> rowDS = readGraphTable(spark, inputGraphTablePath, rowClazz);
|
||||||
Dataset<A> actionPayloadDS = readActionPayload(spark, inputActionPayloadPath, actionPayloadClazz);
|
Dataset<A> actionPayloadDS = readActionPayload(spark, inputActionPayloadPath, actionPayloadClazz);
|
||||||
|
|
||||||
Dataset<G> result = promoteActionPayloadForGraphTable(
|
Dataset<G> result = promoteActionPayloadForGraphTable(
|
||||||
rowDS, actionPayloadDS, strategy, rowClazz, actionPayloadClazz, shouldGroupById)
|
rowDS, actionPayloadDS, mergeAndGetStrategy, promoteActionStrategy, rowClazz, actionPayloadClazz,
|
||||||
|
shouldGroupById)
|
||||||
.map((MapFunction<G, G>) value -> value, Encoders.bean(rowClazz));
|
.map((MapFunction<G, G>) value -> value, Encoders.bean(rowClazz));
|
||||||
|
|
||||||
saveGraphTable(result, outputGraphTablePath);
|
saveGraphTable(result, outputGraphTablePath);
|
||||||
|
@ -183,7 +193,8 @@ public class PromoteActionPayloadForGraphTableJob {
|
||||||
private static <G extends Oaf, A extends Oaf> Dataset<G> promoteActionPayloadForGraphTable(
|
private static <G extends Oaf, A extends Oaf> Dataset<G> promoteActionPayloadForGraphTable(
|
||||||
Dataset<G> rowDS,
|
Dataset<G> rowDS,
|
||||||
Dataset<A> actionPayloadDS,
|
Dataset<A> actionPayloadDS,
|
||||||
MergeAndGet.Strategy strategy,
|
MergeAndGet.Strategy mergeAndGetStrategy,
|
||||||
|
PromoteAction.Strategy promoteActionStrategy,
|
||||||
Class<G> rowClazz,
|
Class<G> rowClazz,
|
||||||
Class<A> actionPayloadClazz,
|
Class<A> actionPayloadClazz,
|
||||||
Boolean shouldGroupById) {
|
Boolean shouldGroupById) {
|
||||||
|
@ -195,8 +206,9 @@ public class PromoteActionPayloadForGraphTableJob {
|
||||||
|
|
||||||
SerializableSupplier<Function<G, String>> rowIdFn = ModelSupport::idFn;
|
SerializableSupplier<Function<G, String>> rowIdFn = ModelSupport::idFn;
|
||||||
SerializableSupplier<Function<A, String>> actionPayloadIdFn = ModelSupport::idFn;
|
SerializableSupplier<Function<A, String>> actionPayloadIdFn = ModelSupport::idFn;
|
||||||
SerializableSupplier<BiFunction<G, A, G>> mergeRowWithActionPayloadAndGetFn = MergeAndGet.functionFor(strategy);
|
SerializableSupplier<BiFunction<G, A, G>> mergeRowWithActionPayloadAndGetFn = MergeAndGet
|
||||||
SerializableSupplier<BiFunction<G, G, G>> mergeRowsAndGetFn = MergeAndGet.functionFor(strategy);
|
.functionFor(mergeAndGetStrategy);
|
||||||
|
SerializableSupplier<BiFunction<G, G, G>> mergeRowsAndGetFn = MergeAndGet.functionFor(mergeAndGetStrategy);
|
||||||
SerializableSupplier<G> zeroFn = zeroFn(rowClazz);
|
SerializableSupplier<G> zeroFn = zeroFn(rowClazz);
|
||||||
SerializableSupplier<Function<G, Boolean>> isNotZeroFn = PromoteActionPayloadForGraphTableJob::isNotZeroFnUsingIdOrSourceAndTarget;
|
SerializableSupplier<Function<G, Boolean>> isNotZeroFn = PromoteActionPayloadForGraphTableJob::isNotZeroFnUsingIdOrSourceAndTarget;
|
||||||
|
|
||||||
|
@ -207,6 +219,7 @@ public class PromoteActionPayloadForGraphTableJob {
|
||||||
rowIdFn,
|
rowIdFn,
|
||||||
actionPayloadIdFn,
|
actionPayloadIdFn,
|
||||||
mergeRowWithActionPayloadAndGetFn,
|
mergeRowWithActionPayloadAndGetFn,
|
||||||
|
promoteActionStrategy,
|
||||||
rowClazz,
|
rowClazz,
|
||||||
actionPayloadClazz);
|
actionPayloadClazz);
|
||||||
|
|
||||||
|
|
|
@ -34,6 +34,7 @@ public class PromoteActionPayloadFunctions {
|
||||||
* @param rowIdFn Function used to get the id of graph table row
|
* @param rowIdFn Function used to get the id of graph table row
|
||||||
* @param actionPayloadIdFn Function used to get id of action payload instance
|
* @param actionPayloadIdFn Function used to get id of action payload instance
|
||||||
* @param mergeAndGetFn Function used to merge graph table row and action payload instance
|
* @param mergeAndGetFn Function used to merge graph table row and action payload instance
|
||||||
|
* @param promoteActionStrategy the Actionset promotion strategy
|
||||||
* @param rowClazz Class of graph table
|
* @param rowClazz Class of graph table
|
||||||
* @param actionPayloadClazz Class of action payload
|
* @param actionPayloadClazz Class of action payload
|
||||||
* @param <G> Type of graph table row
|
* @param <G> Type of graph table row
|
||||||
|
@ -46,6 +47,7 @@ public class PromoteActionPayloadFunctions {
|
||||||
SerializableSupplier<Function<G, String>> rowIdFn,
|
SerializableSupplier<Function<G, String>> rowIdFn,
|
||||||
SerializableSupplier<Function<A, String>> actionPayloadIdFn,
|
SerializableSupplier<Function<A, String>> actionPayloadIdFn,
|
||||||
SerializableSupplier<BiFunction<G, A, G>> mergeAndGetFn,
|
SerializableSupplier<BiFunction<G, A, G>> mergeAndGetFn,
|
||||||
|
PromoteAction.Strategy promoteActionStrategy,
|
||||||
Class<G> rowClazz,
|
Class<G> rowClazz,
|
||||||
Class<A> actionPayloadClazz) {
|
Class<A> actionPayloadClazz) {
|
||||||
if (!isSubClass(rowClazz, actionPayloadClazz)) {
|
if (!isSubClass(rowClazz, actionPayloadClazz)) {
|
||||||
|
@ -61,7 +63,7 @@ public class PromoteActionPayloadFunctions {
|
||||||
.joinWith(
|
.joinWith(
|
||||||
actionPayloadWithIdDS,
|
actionPayloadWithIdDS,
|
||||||
rowWithIdDS.col("_1").equalTo(actionPayloadWithIdDS.col("_1")),
|
rowWithIdDS.col("_1").equalTo(actionPayloadWithIdDS.col("_1")),
|
||||||
"full_outer")
|
PromoteAction.joinTypeForStrategy(promoteActionStrategy))
|
||||||
.map(
|
.map(
|
||||||
(MapFunction<Tuple2<Tuple2<String, G>, Tuple2<String, A>>, G>) value -> {
|
(MapFunction<Tuple2<Tuple2<String, G>, Tuple2<String, A>>, G>) value -> {
|
||||||
Optional<G> rowOpt = Optional.ofNullable(value._1()).map(Tuple2::_2);
|
Optional<G> rowOpt = Optional.ofNullable(value._1()).map(Tuple2::_2);
|
||||||
|
|
|
@ -41,6 +41,12 @@
|
||||||
"paramDescription": "strategy for merging graph table objects with action payload instances, MERGE_FROM_AND_GET or SELECT_NEWER_AND_GET",
|
"paramDescription": "strategy for merging graph table objects with action payload instances, MERGE_FROM_AND_GET or SELECT_NEWER_AND_GET",
|
||||||
"paramRequired": true
|
"paramRequired": true
|
||||||
},
|
},
|
||||||
|
{
|
||||||
|
"paramName": "pas",
|
||||||
|
"paramLongName": "promoteActionStrategy",
|
||||||
|
"paramDescription": "strategy for promoting the actionset contents into the graph tables, ENRICH or UPSERT (default)",
|
||||||
|
"paramRequired": false
|
||||||
|
},
|
||||||
{
|
{
|
||||||
"paramName": "sgid",
|
"paramName": "sgid",
|
||||||
"paramLongName": "shouldGroupById",
|
"paramLongName": "shouldGroupById",
|
||||||
|
|
|
@ -103,6 +103,7 @@
|
||||||
--executor-memory=${sparkExecutorMemory}
|
--executor-memory=${sparkExecutorMemory}
|
||||||
--executor-cores=${sparkExecutorCores}
|
--executor-cores=${sparkExecutorCores}
|
||||||
--driver-memory=${sparkDriverMemory}
|
--driver-memory=${sparkDriverMemory}
|
||||||
|
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
|
||||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||||
|
@ -115,6 +116,7 @@
|
||||||
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
|
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
|
||||||
<arg>--outputGraphTablePath</arg><arg>${workingDir}/dataset</arg>
|
<arg>--outputGraphTablePath</arg><arg>${workingDir}/dataset</arg>
|
||||||
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
||||||
|
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
|
||||||
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
|
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
|
||||||
</spark>
|
</spark>
|
||||||
<ok to="DecisionPromoteResultActionPayloadForDatasetTable"/>
|
<ok to="DecisionPromoteResultActionPayloadForDatasetTable"/>
|
||||||
|
@ -155,6 +157,7 @@
|
||||||
--executor-memory=${sparkExecutorMemory}
|
--executor-memory=${sparkExecutorMemory}
|
||||||
--executor-cores=${sparkExecutorCores}
|
--executor-cores=${sparkExecutorCores}
|
||||||
--driver-memory=${sparkDriverMemory}
|
--driver-memory=${sparkDriverMemory}
|
||||||
|
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
|
||||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||||
|
@ -167,6 +170,7 @@
|
||||||
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Result</arg>
|
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Result</arg>
|
||||||
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/dataset</arg>
|
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/dataset</arg>
|
||||||
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
||||||
|
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
|
||||||
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
|
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
|
||||||
</spark>
|
</spark>
|
||||||
<ok to="End"/>
|
<ok to="End"/>
|
||||||
|
|
|
@ -95,6 +95,7 @@
|
||||||
--executor-memory=${sparkExecutorMemory}
|
--executor-memory=${sparkExecutorMemory}
|
||||||
--executor-cores=${sparkExecutorCores}
|
--executor-cores=${sparkExecutorCores}
|
||||||
--driver-memory=${sparkDriverMemory}
|
--driver-memory=${sparkDriverMemory}
|
||||||
|
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
|
||||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||||
|
@ -106,6 +107,7 @@
|
||||||
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Datasource</arg>
|
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Datasource</arg>
|
||||||
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/datasource</arg>
|
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/datasource</arg>
|
||||||
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
||||||
|
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
|
||||||
</spark>
|
</spark>
|
||||||
<ok to="End"/>
|
<ok to="End"/>
|
||||||
<error to="Kill"/>
|
<error to="Kill"/>
|
||||||
|
|
|
@ -125,6 +125,7 @@
|
||||||
--executor-memory=${sparkExecutorMemory}
|
--executor-memory=${sparkExecutorMemory}
|
||||||
--executor-cores=${sparkExecutorCores}
|
--executor-cores=${sparkExecutorCores}
|
||||||
--driver-memory=${sparkDriverMemory}
|
--driver-memory=${sparkDriverMemory}
|
||||||
|
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
|
||||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||||
|
|
|
@ -95,6 +95,7 @@
|
||||||
--executor-memory=${sparkExecutorMemory}
|
--executor-memory=${sparkExecutorMemory}
|
||||||
--executor-cores=${sparkExecutorCores}
|
--executor-cores=${sparkExecutorCores}
|
||||||
--driver-memory=${sparkDriverMemory}
|
--driver-memory=${sparkDriverMemory}
|
||||||
|
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
|
||||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||||
|
@ -106,6 +107,7 @@
|
||||||
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Organization</arg>
|
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Organization</arg>
|
||||||
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/organization</arg>
|
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/organization</arg>
|
||||||
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
||||||
|
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
|
||||||
</spark>
|
</spark>
|
||||||
<ok to="End"/>
|
<ok to="End"/>
|
||||||
<error to="Kill"/>
|
<error to="Kill"/>
|
||||||
|
|
|
@ -103,6 +103,7 @@
|
||||||
--executor-memory=${sparkExecutorMemory}
|
--executor-memory=${sparkExecutorMemory}
|
||||||
--executor-cores=${sparkExecutorCores}
|
--executor-cores=${sparkExecutorCores}
|
||||||
--driver-memory=${sparkDriverMemory}
|
--driver-memory=${sparkDriverMemory}
|
||||||
|
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
|
||||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||||
|
@ -114,6 +115,7 @@
|
||||||
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
|
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
|
||||||
<arg>--outputGraphTablePath</arg><arg>${workingDir}/otherresearchproduct</arg>
|
<arg>--outputGraphTablePath</arg><arg>${workingDir}/otherresearchproduct</arg>
|
||||||
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
||||||
|
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
|
||||||
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
|
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
|
||||||
</spark>
|
</spark>
|
||||||
<ok to="DecisionPromoteResultActionPayloadForOtherResearchProductTable"/>
|
<ok to="DecisionPromoteResultActionPayloadForOtherResearchProductTable"/>
|
||||||
|
@ -154,11 +156,12 @@
|
||||||
--executor-memory=${sparkExecutorMemory}
|
--executor-memory=${sparkExecutorMemory}
|
||||||
--executor-cores=${sparkExecutorCores}
|
--executor-cores=${sparkExecutorCores}
|
||||||
--driver-memory=${sparkDriverMemory}
|
--driver-memory=${sparkDriverMemory}
|
||||||
|
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
|
||||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||||
--conf spark.sql.shuffle.partitions=2560
|
--conf spark.sql.shuffle.partitions=8000
|
||||||
</spark-opts>
|
</spark-opts>
|
||||||
<arg>--inputGraphTablePath</arg><arg>${workingDir}/otherresearchproduct</arg>
|
<arg>--inputGraphTablePath</arg><arg>${workingDir}/otherresearchproduct</arg>
|
||||||
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
|
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
|
||||||
|
@ -166,6 +169,7 @@
|
||||||
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Result</arg>
|
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Result</arg>
|
||||||
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/otherresearchproduct</arg>
|
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/otherresearchproduct</arg>
|
||||||
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
||||||
|
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
|
||||||
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
|
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
|
||||||
</spark>
|
</spark>
|
||||||
<ok to="End"/>
|
<ok to="End"/>
|
||||||
|
|
|
@ -95,6 +95,7 @@
|
||||||
--executor-memory=${sparkExecutorMemory}
|
--executor-memory=${sparkExecutorMemory}
|
||||||
--executor-cores=${sparkExecutorCores}
|
--executor-cores=${sparkExecutorCores}
|
||||||
--driver-memory=${sparkDriverMemory}
|
--driver-memory=${sparkDriverMemory}
|
||||||
|
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
|
||||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||||
|
@ -106,6 +107,7 @@
|
||||||
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Project</arg>
|
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Project</arg>
|
||||||
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/project</arg>
|
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/project</arg>
|
||||||
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
||||||
|
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
|
||||||
</spark>
|
</spark>
|
||||||
<ok to="End"/>
|
<ok to="End"/>
|
||||||
<error to="Kill"/>
|
<error to="Kill"/>
|
||||||
|
|
|
@ -103,11 +103,12 @@
|
||||||
--executor-memory=${sparkExecutorMemory}
|
--executor-memory=${sparkExecutorMemory}
|
||||||
--executor-cores=${sparkExecutorCores}
|
--executor-cores=${sparkExecutorCores}
|
||||||
--driver-memory=${sparkDriverMemory}
|
--driver-memory=${sparkDriverMemory}
|
||||||
|
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
|
||||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||||
--conf spark.sql.shuffle.partitions=7000
|
--conf spark.sql.shuffle.partitions=15000
|
||||||
</spark-opts>
|
</spark-opts>
|
||||||
<arg>--inputGraphTablePath</arg><arg>${inputGraphRootPath}/publication</arg>
|
<arg>--inputGraphTablePath</arg><arg>${inputGraphRootPath}/publication</arg>
|
||||||
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
|
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
|
||||||
|
@ -115,6 +116,7 @@
|
||||||
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
|
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
|
||||||
<arg>--outputGraphTablePath</arg><arg>${workingDir}/publication</arg>
|
<arg>--outputGraphTablePath</arg><arg>${workingDir}/publication</arg>
|
||||||
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
||||||
|
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
|
||||||
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
|
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
|
||||||
</spark>
|
</spark>
|
||||||
<ok to="DecisionPromoteResultActionPayloadForPublicationTable"/>
|
<ok to="DecisionPromoteResultActionPayloadForPublicationTable"/>
|
||||||
|
@ -155,11 +157,12 @@
|
||||||
--executor-memory=${sparkExecutorMemory}
|
--executor-memory=${sparkExecutorMemory}
|
||||||
--executor-cores=${sparkExecutorCores}
|
--executor-cores=${sparkExecutorCores}
|
||||||
--driver-memory=${sparkDriverMemory}
|
--driver-memory=${sparkDriverMemory}
|
||||||
|
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
|
||||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||||
--conf spark.sql.shuffle.partitions=7000
|
--conf spark.sql.shuffle.partitions=15000
|
||||||
</spark-opts>
|
</spark-opts>
|
||||||
<arg>--inputGraphTablePath</arg><arg>${workingDir}/publication</arg>
|
<arg>--inputGraphTablePath</arg><arg>${workingDir}/publication</arg>
|
||||||
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
|
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
|
||||||
|
@ -167,6 +170,7 @@
|
||||||
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Result</arg>
|
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Result</arg>
|
||||||
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/publication</arg>
|
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/publication</arg>
|
||||||
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
||||||
|
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
|
||||||
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
|
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
|
||||||
</spark>
|
</spark>
|
||||||
<ok to="End"/>
|
<ok to="End"/>
|
||||||
|
|
|
@ -95,11 +95,12 @@
|
||||||
--executor-memory=${sparkExecutorMemory}
|
--executor-memory=${sparkExecutorMemory}
|
||||||
--executor-cores=${sparkExecutorCores}
|
--executor-cores=${sparkExecutorCores}
|
||||||
--driver-memory=${sparkDriverMemory}
|
--driver-memory=${sparkDriverMemory}
|
||||||
|
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
|
||||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||||
--conf spark.sql.shuffle.partitions=10000
|
--conf spark.sql.shuffle.partitions=15000
|
||||||
</spark-opts>
|
</spark-opts>
|
||||||
<arg>--inputGraphTablePath</arg><arg>${inputGraphRootPath}/relation</arg>
|
<arg>--inputGraphTablePath</arg><arg>${inputGraphRootPath}/relation</arg>
|
||||||
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Relation</arg>
|
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Relation</arg>
|
||||||
|
@ -107,6 +108,7 @@
|
||||||
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Relation</arg>
|
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Relation</arg>
|
||||||
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/relation</arg>
|
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/relation</arg>
|
||||||
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
||||||
|
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
|
||||||
</spark>
|
</spark>
|
||||||
<ok to="End"/>
|
<ok to="End"/>
|
||||||
<error to="Kill"/>
|
<error to="Kill"/>
|
||||||
|
|
|
@ -103,6 +103,7 @@
|
||||||
--executor-memory=${sparkExecutorMemory}
|
--executor-memory=${sparkExecutorMemory}
|
||||||
--executor-cores=${sparkExecutorCores}
|
--executor-cores=${sparkExecutorCores}
|
||||||
--driver-memory=${sparkDriverMemory}
|
--driver-memory=${sparkDriverMemory}
|
||||||
|
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
|
||||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||||
|
@ -114,6 +115,7 @@
|
||||||
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
|
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
|
||||||
<arg>--outputGraphTablePath</arg><arg>${workingDir}/software</arg>
|
<arg>--outputGraphTablePath</arg><arg>${workingDir}/software</arg>
|
||||||
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
||||||
|
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
|
||||||
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
|
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
|
||||||
</spark>
|
</spark>
|
||||||
<ok to="DecisionPromoteResultActionPayloadForSoftwareTable"/>
|
<ok to="DecisionPromoteResultActionPayloadForSoftwareTable"/>
|
||||||
|
@ -154,11 +156,12 @@
|
||||||
--executor-memory=${sparkExecutorMemory}
|
--executor-memory=${sparkExecutorMemory}
|
||||||
--executor-cores=${sparkExecutorCores}
|
--executor-cores=${sparkExecutorCores}
|
||||||
--driver-memory=${sparkDriverMemory}
|
--driver-memory=${sparkDriverMemory}
|
||||||
|
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
|
||||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||||
--conf spark.sql.shuffle.partitions=2560
|
--conf spark.sql.shuffle.partitions=4000
|
||||||
</spark-opts>
|
</spark-opts>
|
||||||
<arg>--inputGraphTablePath</arg><arg>${workingDir}/software</arg>
|
<arg>--inputGraphTablePath</arg><arg>${workingDir}/software</arg>
|
||||||
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
|
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
|
||||||
|
@ -166,6 +169,7 @@
|
||||||
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Result</arg>
|
<arg>--actionPayloadClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Result</arg>
|
||||||
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/software</arg>
|
<arg>--outputGraphTablePath</arg><arg>${outputGraphRootPath}/software</arg>
|
||||||
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
<arg>--mergeAndGetStrategy</arg><arg>${mergeAndGetStrategy}</arg>
|
||||||
|
<arg>--promoteActionStrategy</arg><arg>${promoteActionStrategy}</arg>
|
||||||
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
|
<arg>--shouldGroupById</arg><arg>${shouldGroupById}</arg>
|
||||||
</spark>
|
</spark>
|
||||||
<ok to="End"/>
|
<ok to="End"/>
|
||||||
|
|
|
@ -8,6 +8,7 @@ import static org.mockito.Mockito.*;
|
||||||
|
|
||||||
import java.util.function.BiFunction;
|
import java.util.function.BiFunction;
|
||||||
|
|
||||||
|
import org.junit.jupiter.api.Disabled;
|
||||||
import org.junit.jupiter.api.Nested;
|
import org.junit.jupiter.api.Nested;
|
||||||
import org.junit.jupiter.api.Test;
|
import org.junit.jupiter.api.Test;
|
||||||
|
|
||||||
|
@ -85,6 +86,7 @@ public class MergeAndGetTest {
|
||||||
}
|
}
|
||||||
|
|
||||||
@Test
|
@Test
|
||||||
|
@Disabled
|
||||||
void shouldBehaveProperlyForRelationAndRelation() {
|
void shouldBehaveProperlyForRelationAndRelation() {
|
||||||
// given
|
// given
|
||||||
Relation a = mock(Relation.class);
|
Relation a = mock(Relation.class);
|
||||||
|
@ -96,7 +98,9 @@ public class MergeAndGetTest {
|
||||||
// then
|
// then
|
||||||
Oaf x = fn.get().apply(a, b);
|
Oaf x = fn.get().apply(a, b);
|
||||||
assertTrue(Relation.class.isAssignableFrom(x.getClass()));
|
assertTrue(Relation.class.isAssignableFrom(x.getClass()));
|
||||||
verify(a).mergeFrom(b);
|
|
||||||
|
// TODO should be reimplemented
|
||||||
|
// verify(a).mergeFrom(b);
|
||||||
assertEquals(a, x);
|
assertEquals(a, x);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@ -145,6 +149,7 @@ public class MergeAndGetTest {
|
||||||
}
|
}
|
||||||
|
|
||||||
@Test
|
@Test
|
||||||
|
@Disabled
|
||||||
void shouldBehaveProperlyForOafEntityAndOafEntity() {
|
void shouldBehaveProperlyForOafEntityAndOafEntity() {
|
||||||
// given
|
// given
|
||||||
OafEntity a = mock(OafEntity.class);
|
OafEntity a = mock(OafEntity.class);
|
||||||
|
@ -156,7 +161,9 @@ public class MergeAndGetTest {
|
||||||
// then
|
// then
|
||||||
Oaf x = fn.get().apply(a, b);
|
Oaf x = fn.get().apply(a, b);
|
||||||
assertTrue(OafEntity.class.isAssignableFrom(x.getClass()));
|
assertTrue(OafEntity.class.isAssignableFrom(x.getClass()));
|
||||||
verify(a).mergeFrom(b);
|
|
||||||
|
// TODO should be reimplemented
|
||||||
|
// verify(a).mergeFrom(b);
|
||||||
assertEquals(a, x);
|
assertEquals(a, x);
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
|
@ -54,7 +54,7 @@ public class PromoteActionPayloadFunctionsTest {
|
||||||
RuntimeException.class,
|
RuntimeException.class,
|
||||||
() -> PromoteActionPayloadFunctions
|
() -> PromoteActionPayloadFunctions
|
||||||
.joinGraphTableWithActionPayloadAndMerge(
|
.joinGraphTableWithActionPayloadAndMerge(
|
||||||
null, null, null, null, null, OafImplSubSub.class, OafImpl.class));
|
null, null, null, null, null, null, OafImplSubSub.class, OafImpl.class));
|
||||||
}
|
}
|
||||||
|
|
||||||
@Test
|
@Test
|
||||||
|
@ -104,6 +104,7 @@ public class PromoteActionPayloadFunctionsTest {
|
||||||
rowIdFn,
|
rowIdFn,
|
||||||
actionPayloadIdFn,
|
actionPayloadIdFn,
|
||||||
mergeAndGetFn,
|
mergeAndGetFn,
|
||||||
|
PromoteAction.Strategy.UPSERT,
|
||||||
OafImplSubSub.class,
|
OafImplSubSub.class,
|
||||||
OafImplSubSub.class)
|
OafImplSubSub.class)
|
||||||
.collectAsList();
|
.collectAsList();
|
||||||
|
@ -183,6 +184,7 @@ public class PromoteActionPayloadFunctionsTest {
|
||||||
rowIdFn,
|
rowIdFn,
|
||||||
actionPayloadIdFn,
|
actionPayloadIdFn,
|
||||||
mergeAndGetFn,
|
mergeAndGetFn,
|
||||||
|
PromoteAction.Strategy.UPSERT,
|
||||||
OafImplSubSub.class,
|
OafImplSubSub.class,
|
||||||
OafImplSub.class)
|
OafImplSub.class)
|
||||||
.collectAsList();
|
.collectAsList();
|
||||||
|
|
|
@ -9,6 +9,7 @@ import java.util.List;
|
||||||
|
|
||||||
import org.apache.commons.io.IOUtils;
|
import org.apache.commons.io.IOUtils;
|
||||||
import org.apache.hadoop.io.Text;
|
import org.apache.hadoop.io.Text;
|
||||||
|
import org.apache.hadoop.io.compress.BZip2Codec;
|
||||||
import org.apache.hadoop.io.compress.GzipCodec;
|
import org.apache.hadoop.io.compress.GzipCodec;
|
||||||
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
|
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
|
||||||
import org.apache.spark.SparkConf;
|
import org.apache.spark.SparkConf;
|
||||||
|
@ -64,6 +65,12 @@ public class PrepareAffiliationRelations implements Serializable {
|
||||||
final String pubmedInputPath = parser.get("pubmedInputPath");
|
final String pubmedInputPath = parser.get("pubmedInputPath");
|
||||||
log.info("pubmedInputPath: {}", pubmedInputPath);
|
log.info("pubmedInputPath: {}", pubmedInputPath);
|
||||||
|
|
||||||
|
final String openapcInputPath = parser.get("openapcInputPath");
|
||||||
|
log.info("openapcInputPath: {}", openapcInputPath);
|
||||||
|
|
||||||
|
final String dataciteInputPath = parser.get("dataciteInputPath");
|
||||||
|
log.info("dataciteInputPath: {}", dataciteInputPath);
|
||||||
|
|
||||||
final String outputPath = parser.get("outputPath");
|
final String outputPath = parser.get("outputPath");
|
||||||
log.info("outputPath: {}", outputPath);
|
log.info("outputPath: {}", outputPath);
|
||||||
|
|
||||||
|
@ -85,10 +92,22 @@ public class PrepareAffiliationRelations implements Serializable {
|
||||||
JavaPairRDD<Text, Text> pubmedRelations = prepareAffiliationRelations(
|
JavaPairRDD<Text, Text> pubmedRelations = prepareAffiliationRelations(
|
||||||
spark, pubmedInputPath, collectedFromPubmed);
|
spark, pubmedInputPath, collectedFromPubmed);
|
||||||
|
|
||||||
|
List<KeyValue> collectedFromOpenAPC = OafMapperUtils
|
||||||
|
.listKeyValues(ModelConstants.OPEN_APC_ID, "OpenAPC");
|
||||||
|
JavaPairRDD<Text, Text> openAPCRelations = prepareAffiliationRelations(
|
||||||
|
spark, openapcInputPath, collectedFromOpenAPC);
|
||||||
|
|
||||||
|
List<KeyValue> collectedFromDatacite = OafMapperUtils
|
||||||
|
.listKeyValues(ModelConstants.DATACITE_ID, "Datacite");
|
||||||
|
JavaPairRDD<Text, Text> dataciteRelations = prepareAffiliationRelations(
|
||||||
|
spark, dataciteInputPath, collectedFromDatacite);
|
||||||
|
|
||||||
crossrefRelations
|
crossrefRelations
|
||||||
.union(pubmedRelations)
|
.union(pubmedRelations)
|
||||||
|
.union(openAPCRelations)
|
||||||
|
.union(dataciteRelations)
|
||||||
.saveAsHadoopFile(
|
.saveAsHadoopFile(
|
||||||
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
|
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, BZip2Codec.class);
|
||||||
|
|
||||||
});
|
});
|
||||||
}
|
}
|
||||||
|
|
|
@ -10,6 +10,7 @@ import java.util.stream.Collectors;
|
||||||
|
|
||||||
import org.apache.commons.io.IOUtils;
|
import org.apache.commons.io.IOUtils;
|
||||||
import org.apache.hadoop.io.Text;
|
import org.apache.hadoop.io.Text;
|
||||||
|
import org.apache.hadoop.io.compress.BZip2Codec;
|
||||||
import org.apache.hadoop.io.compress.GzipCodec;
|
import org.apache.hadoop.io.compress.GzipCodec;
|
||||||
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
|
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
|
||||||
import org.apache.spark.SparkConf;
|
import org.apache.spark.SparkConf;
|
||||||
|
@ -83,7 +84,7 @@ public class SparkAtomicActionScoreJob implements Serializable {
|
||||||
resultsRDD
|
resultsRDD
|
||||||
.union(projectsRDD)
|
.union(projectsRDD)
|
||||||
.saveAsHadoopFile(
|
.saveAsHadoopFile(
|
||||||
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
|
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, BZip2Codec.class);
|
||||||
});
|
});
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
|
@ -34,6 +34,10 @@ public class BipProjectModel {
|
||||||
|
|
||||||
String totalCitationCount;
|
String totalCitationCount;
|
||||||
|
|
||||||
|
public String getProjectId() {
|
||||||
|
return projectId;
|
||||||
|
}
|
||||||
|
|
||||||
// each project bip measure has exactly one value, hence one key-value pair
|
// each project bip measure has exactly one value, hence one key-value pair
|
||||||
private Measure createMeasure(String measureId, String measureValue) {
|
private Measure createMeasure(String measureId, String measureValue) {
|
||||||
|
|
||||||
|
|
|
@ -75,6 +75,7 @@ public class GetFOSSparkJob implements Serializable {
|
||||||
fosData.map((MapFunction<Row, FOSDataModel>) r -> {
|
fosData.map((MapFunction<Row, FOSDataModel>) r -> {
|
||||||
FOSDataModel fosDataModel = new FOSDataModel();
|
FOSDataModel fosDataModel = new FOSDataModel();
|
||||||
fosDataModel.setDoi(r.getString(0).toLowerCase());
|
fosDataModel.setDoi(r.getString(0).toLowerCase());
|
||||||
|
fosDataModel.setOaid(r.getString(1).toLowerCase());
|
||||||
fosDataModel.setLevel1(r.getString(2));
|
fosDataModel.setLevel1(r.getString(2));
|
||||||
fosDataModel.setLevel2(r.getString(3));
|
fosDataModel.setLevel2(r.getString(3));
|
||||||
fosDataModel.setLevel3(r.getString(4));
|
fosDataModel.setLevel3(r.getString(4));
|
||||||
|
|
|
@ -16,12 +16,14 @@ import org.apache.spark.sql.Dataset;
|
||||||
import org.apache.spark.sql.Encoders;
|
import org.apache.spark.sql.Encoders;
|
||||||
import org.apache.spark.sql.SaveMode;
|
import org.apache.spark.sql.SaveMode;
|
||||||
import org.apache.spark.sql.SparkSession;
|
import org.apache.spark.sql.SparkSession;
|
||||||
|
import org.jetbrains.annotations.NotNull;
|
||||||
import org.slf4j.Logger;
|
import org.slf4j.Logger;
|
||||||
import org.slf4j.LoggerFactory;
|
import org.slf4j.LoggerFactory;
|
||||||
|
|
||||||
import eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.FOSDataModel;
|
import eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.FOSDataModel;
|
||||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||||
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||||
|
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
||||||
import eu.dnetlib.dhp.schema.oaf.Result;
|
import eu.dnetlib.dhp.schema.oaf.Result;
|
||||||
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
|
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
|
||||||
import eu.dnetlib.dhp.schema.oaf.Subject;
|
import eu.dnetlib.dhp.schema.oaf.Subject;
|
||||||
|
@ -52,28 +54,48 @@ public class PrepareFOSSparkJob implements Serializable {
|
||||||
final String outputPath = parser.get("outputPath");
|
final String outputPath = parser.get("outputPath");
|
||||||
log.info("outputPath: {}", outputPath);
|
log.info("outputPath: {}", outputPath);
|
||||||
|
|
||||||
|
final Boolean distributeDOI = Optional
|
||||||
|
.ofNullable(parser.get("distributeDoi"))
|
||||||
|
.map(Boolean::valueOf)
|
||||||
|
.orElse(Boolean.TRUE);
|
||||||
|
|
||||||
SparkConf conf = new SparkConf();
|
SparkConf conf = new SparkConf();
|
||||||
runWithSparkSession(
|
runWithSparkSession(
|
||||||
conf,
|
conf,
|
||||||
isSparkSessionManaged,
|
isSparkSessionManaged,
|
||||||
spark -> {
|
spark -> {
|
||||||
|
if (distributeDOI)
|
||||||
distributeFOSdois(
|
distributeFOSdois(
|
||||||
spark,
|
spark,
|
||||||
sourcePath,
|
sourcePath,
|
||||||
|
|
||||||
outputPath);
|
outputPath);
|
||||||
|
else
|
||||||
|
distributeFOSoaid(spark, sourcePath, outputPath);
|
||||||
});
|
});
|
||||||
}
|
}
|
||||||
|
|
||||||
private static void distributeFOSdois(SparkSession spark, String sourcePath, String outputPath) {
|
private static void distributeFOSoaid(SparkSession spark, String sourcePath, String outputPath) {
|
||||||
Dataset<FOSDataModel> fosDataset = readPath(spark, sourcePath, FOSDataModel.class);
|
Dataset<FOSDataModel> fosDataset = readPath(spark, sourcePath, FOSDataModel.class);
|
||||||
|
|
||||||
fosDataset
|
fosDataset
|
||||||
.groupByKey((MapFunction<FOSDataModel, String>) v -> v.getDoi().toLowerCase(), Encoders.STRING())
|
.groupByKey((MapFunction<FOSDataModel, String>) v -> v.getOaid().toLowerCase(), Encoders.STRING())
|
||||||
.mapGroups((MapGroupsFunction<String, FOSDataModel, Result>) (k, it) -> {
|
.mapGroups(
|
||||||
|
(MapGroupsFunction<String, FOSDataModel, Result>) (k,
|
||||||
|
it) -> getResult(
|
||||||
|
ModelSupport.entityIdPrefix.get(Result.class.getSimpleName().toLowerCase()) + "|" + k, it),
|
||||||
|
Encoders.bean(Result.class))
|
||||||
|
.write()
|
||||||
|
.mode(SaveMode.Overwrite)
|
||||||
|
.option("compression", "gzip")
|
||||||
|
.json(outputPath + "/fos");
|
||||||
|
}
|
||||||
|
|
||||||
|
@NotNull
|
||||||
|
private static Result getResult(String k, Iterator<FOSDataModel> it) {
|
||||||
Result r = new Result();
|
Result r = new Result();
|
||||||
FOSDataModel first = it.next();
|
FOSDataModel first = it.next();
|
||||||
r.setId(DHPUtils.generateUnresolvedIdentifier(k, DOI));
|
r.setId(k);
|
||||||
|
|
||||||
HashSet<String> level1 = new HashSet<>();
|
HashSet<String> level1 = new HashSet<>();
|
||||||
HashSet<String> level2 = new HashSet<>();
|
HashSet<String> level2 = new HashSet<>();
|
||||||
|
@ -93,21 +115,19 @@ public class PrepareFOSSparkJob implements Serializable {
|
||||||
.forEach(
|
.forEach(
|
||||||
l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID, true)));
|
l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID, true)));
|
||||||
r.setSubject(sbjs);
|
r.setSubject(sbjs);
|
||||||
r
|
|
||||||
.setDataInfo(
|
|
||||||
OafMapperUtils
|
|
||||||
.dataInfo(
|
|
||||||
false, null, true,
|
|
||||||
false,
|
|
||||||
OafMapperUtils
|
|
||||||
.qualifier(
|
|
||||||
ModelConstants.PROVENANCE_ENRICH,
|
|
||||||
null,
|
|
||||||
ModelConstants.DNET_PROVENANCE_ACTIONS,
|
|
||||||
ModelConstants.DNET_PROVENANCE_ACTIONS),
|
|
||||||
null));
|
|
||||||
return r;
|
return r;
|
||||||
}, Encoders.bean(Result.class))
|
}
|
||||||
|
|
||||||
|
private static void distributeFOSdois(SparkSession spark, String sourcePath, String outputPath) {
|
||||||
|
Dataset<FOSDataModel> fosDataset = readPath(spark, sourcePath, FOSDataModel.class);
|
||||||
|
|
||||||
|
fosDataset
|
||||||
|
.groupByKey((MapFunction<FOSDataModel, String>) v -> v.getDoi().toLowerCase(), Encoders.STRING())
|
||||||
|
.mapGroups(
|
||||||
|
(MapGroupsFunction<String, FOSDataModel, Result>) (k,
|
||||||
|
it) -> getResult(DHPUtils.generateUnresolvedIdentifier(k, DOI), it),
|
||||||
|
Encoders.bean(Result.class))
|
||||||
.write()
|
.write()
|
||||||
.mode(SaveMode.Overwrite)
|
.mode(SaveMode.Overwrite)
|
||||||
.option("compression", "gzip")
|
.option("compression", "gzip")
|
||||||
|
|
|
@ -81,19 +81,7 @@ public class PrepareSDGSparkJob implements Serializable {
|
||||||
s -> sbjs
|
s -> sbjs
|
||||||
.add(getSubject(s.getSbj(), SDG_CLASS_ID, SDG_CLASS_NAME, UPDATE_SUBJECT_SDG_CLASS_ID)));
|
.add(getSubject(s.getSbj(), SDG_CLASS_ID, SDG_CLASS_NAME, UPDATE_SUBJECT_SDG_CLASS_ID)));
|
||||||
r.setSubject(sbjs);
|
r.setSubject(sbjs);
|
||||||
r
|
|
||||||
.setDataInfo(
|
|
||||||
OafMapperUtils
|
|
||||||
.dataInfo(
|
|
||||||
false, null, true,
|
|
||||||
false,
|
|
||||||
OafMapperUtils
|
|
||||||
.qualifier(
|
|
||||||
ModelConstants.PROVENANCE_ENRICH,
|
|
||||||
null,
|
|
||||||
ModelConstants.DNET_PROVENANCE_ACTIONS,
|
|
||||||
ModelConstants.DNET_PROVENANCE_ACTIONS),
|
|
||||||
null));
|
|
||||||
return r;
|
return r;
|
||||||
}, Encoders.bean(Result.class))
|
}, Encoders.bean(Result.class))
|
||||||
.write()
|
.write()
|
||||||
|
|
|
@ -0,0 +1,92 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.actionmanager.fosnodoi;
|
||||||
|
|
||||||
|
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||||
|
|
||||||
|
import java.io.IOException;
|
||||||
|
import java.io.Serializable;
|
||||||
|
import java.util.*;
|
||||||
|
|
||||||
|
import org.apache.commons.cli.ParseException;
|
||||||
|
import org.apache.commons.io.IOUtils;
|
||||||
|
import org.apache.hadoop.io.Text;
|
||||||
|
import org.apache.hadoop.io.compress.GzipCodec;
|
||||||
|
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
|
||||||
|
import org.apache.spark.SparkConf;
|
||||||
|
import org.apache.spark.api.java.JavaPairRDD;
|
||||||
|
import org.apache.spark.api.java.function.FilterFunction;
|
||||||
|
import org.apache.spark.api.java.function.FlatMapFunction;
|
||||||
|
import org.apache.spark.api.java.function.MapFunction;
|
||||||
|
import org.apache.spark.sql.Encoders;
|
||||||
|
import org.apache.spark.sql.SparkSession;
|
||||||
|
import org.slf4j.Logger;
|
||||||
|
import org.slf4j.LoggerFactory;
|
||||||
|
|
||||||
|
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||||
|
|
||||||
|
import eu.dnetlib.dhp.actionmanager.opencitations.model.COCI;
|
||||||
|
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||||
|
import eu.dnetlib.dhp.schema.action.AtomicAction;
|
||||||
|
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.Relation;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.Result;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.utils.*;
|
||||||
|
import scala.Tuple2;
|
||||||
|
|
||||||
|
public class CreateActionSetSparkJob implements Serializable {
|
||||||
|
|
||||||
|
private static final Logger log = LoggerFactory.getLogger(CreateActionSetSparkJob.class);
|
||||||
|
|
||||||
|
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||||
|
|
||||||
|
public static void main(final String[] args) throws IOException, ParseException {
|
||||||
|
|
||||||
|
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
|
||||||
|
IOUtils
|
||||||
|
.toString(
|
||||||
|
Objects
|
||||||
|
.requireNonNull(
|
||||||
|
CreateActionSetSparkJob.class
|
||||||
|
.getResourceAsStream(
|
||||||
|
"/eu/dnetlib/dhp/actionmanager/fosnodoi/as_parameters.json"))));
|
||||||
|
|
||||||
|
parser.parseArgument(args);
|
||||||
|
|
||||||
|
Boolean isSparkSessionManaged = Optional
|
||||||
|
.ofNullable(parser.get("isSparkSessionManaged"))
|
||||||
|
.map(Boolean::valueOf)
|
||||||
|
.orElse(Boolean.TRUE);
|
||||||
|
|
||||||
|
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
|
||||||
|
|
||||||
|
final String inputPath = parser.get("sourcePath");
|
||||||
|
log.info("inputPath {}", inputPath);
|
||||||
|
|
||||||
|
final String outputPath = parser.get("outputPath");
|
||||||
|
log.info("outputPath {}", outputPath);
|
||||||
|
|
||||||
|
SparkConf conf = new SparkConf();
|
||||||
|
runWithSparkSession(
|
||||||
|
conf,
|
||||||
|
isSparkSessionManaged,
|
||||||
|
spark -> createActionSet(spark, inputPath, outputPath));
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
|
private static void createActionSet(SparkSession spark, String inputPath, String outputPath) {
|
||||||
|
spark
|
||||||
|
.read()
|
||||||
|
.textFile(inputPath)
|
||||||
|
.map(
|
||||||
|
(MapFunction<String, Result>) value -> OBJECT_MAPPER.readValue(value, Result.class),
|
||||||
|
Encoders.bean(Result.class))
|
||||||
|
.toJavaRDD()
|
||||||
|
.map(p -> new AtomicAction(p.getClass(), p))
|
||||||
|
.mapToPair(
|
||||||
|
aa -> new Tuple2<>(new Text(aa.getClazz().getCanonicalName()),
|
||||||
|
new Text(OBJECT_MAPPER.writeValueAsString(aa))))
|
||||||
|
.saveAsHadoopFile(
|
||||||
|
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -22,12 +22,14 @@ import org.apache.spark.sql.SparkSession;
|
||||||
import org.slf4j.Logger;
|
import org.slf4j.Logger;
|
||||||
import org.slf4j.LoggerFactory;
|
import org.slf4j.LoggerFactory;
|
||||||
|
|
||||||
|
import com.fasterxml.jackson.core.JsonProcessingException;
|
||||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||||
|
|
||||||
import eu.dnetlib.dhp.actionmanager.opencitations.model.COCI;
|
import eu.dnetlib.dhp.actionmanager.opencitations.model.COCI;
|
||||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||||
import eu.dnetlib.dhp.schema.action.AtomicAction;
|
import eu.dnetlib.dhp.schema.action.AtomicAction;
|
||||||
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||||
|
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
||||||
import eu.dnetlib.dhp.schema.oaf.*;
|
import eu.dnetlib.dhp.schema.oaf.*;
|
||||||
import eu.dnetlib.dhp.schema.oaf.utils.*;
|
import eu.dnetlib.dhp.schema.oaf.utils.*;
|
||||||
import eu.dnetlib.dhp.utils.DHPUtils;
|
import eu.dnetlib.dhp.utils.DHPUtils;
|
||||||
|
@ -37,16 +39,12 @@ public class CreateActionSetSparkJob implements Serializable {
|
||||||
public static final String OPENCITATIONS_CLASSID = "sysimport:crosswalk:opencitations";
|
public static final String OPENCITATIONS_CLASSID = "sysimport:crosswalk:opencitations";
|
||||||
public static final String OPENCITATIONS_CLASSNAME = "Imported from OpenCitations";
|
public static final String OPENCITATIONS_CLASSNAME = "Imported from OpenCitations";
|
||||||
|
|
||||||
// DOI-to-DOI citations
|
|
||||||
public static final String COCI = "COCI";
|
|
||||||
|
|
||||||
// PMID-to-PMID citations
|
|
||||||
public static final String POCI = "POCI";
|
|
||||||
|
|
||||||
private static final String DOI_PREFIX = "50|doi_________::";
|
private static final String DOI_PREFIX = "50|doi_________::";
|
||||||
|
|
||||||
private static final String PMID_PREFIX = "50|pmid________::";
|
private static final String PMID_PREFIX = "50|pmid________::";
|
||||||
|
private static final String ARXIV_PREFIX = "50|arXiv_______::";
|
||||||
|
|
||||||
|
private static final String PMCID_PREFIX = "50|pmcid_______::";
|
||||||
private static final String TRUST = "0.91";
|
private static final String TRUST = "0.91";
|
||||||
|
|
||||||
private static final Logger log = LoggerFactory.getLogger(CreateActionSetSparkJob.class);
|
private static final Logger log = LoggerFactory.getLogger(CreateActionSetSparkJob.class);
|
||||||
|
@ -79,38 +77,30 @@ public class CreateActionSetSparkJob implements Serializable {
|
||||||
final String outputPath = parser.get("outputPath");
|
final String outputPath = parser.get("outputPath");
|
||||||
log.info("outputPath {}", outputPath);
|
log.info("outputPath {}", outputPath);
|
||||||
|
|
||||||
final boolean shouldDuplicateRels = Optional
|
|
||||||
.ofNullable(parser.get("shouldDuplicateRels"))
|
|
||||||
.map(Boolean::valueOf)
|
|
||||||
.orElse(Boolean.FALSE);
|
|
||||||
|
|
||||||
SparkConf conf = new SparkConf();
|
SparkConf conf = new SparkConf();
|
||||||
runWithSparkSession(
|
runWithSparkSession(
|
||||||
conf,
|
conf,
|
||||||
isSparkSessionManaged,
|
isSparkSessionManaged,
|
||||||
spark -> extractContent(spark, inputPath, outputPath, shouldDuplicateRels));
|
spark -> extractContent(spark, inputPath, outputPath));
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
private static void extractContent(SparkSession spark, String inputPath, String outputPath,
|
private static void extractContent(SparkSession spark, String inputPath, String outputPath) {
|
||||||
boolean shouldDuplicateRels) {
|
|
||||||
|
|
||||||
getTextTextJavaPairRDD(spark, inputPath, shouldDuplicateRels, COCI)
|
getTextTextJavaPairRDD(spark, inputPath)
|
||||||
.union(getTextTextJavaPairRDD(spark, inputPath, shouldDuplicateRels, POCI))
|
|
||||||
.saveAsHadoopFile(outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
|
.saveAsHadoopFile(outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
|
||||||
}
|
}
|
||||||
|
|
||||||
private static JavaPairRDD<Text, Text> getTextTextJavaPairRDD(SparkSession spark, String inputPath,
|
private static JavaPairRDD<Text, Text> getTextTextJavaPairRDD(SparkSession spark, String inputPath) {
|
||||||
boolean shouldDuplicateRels, String prefix) {
|
|
||||||
return spark
|
return spark
|
||||||
.read()
|
.read()
|
||||||
.textFile(inputPath + "/" + prefix + "/" + prefix + "_JSON/*")
|
.textFile(inputPath)
|
||||||
.map(
|
.map(
|
||||||
(MapFunction<String, COCI>) value -> OBJECT_MAPPER.readValue(value, COCI.class),
|
(MapFunction<String, COCI>) value -> OBJECT_MAPPER.readValue(value, COCI.class),
|
||||||
Encoders.bean(COCI.class))
|
Encoders.bean(COCI.class))
|
||||||
.flatMap(
|
.flatMap(
|
||||||
(FlatMapFunction<COCI, Relation>) value -> createRelation(
|
(FlatMapFunction<COCI, Relation>) value -> createRelation(
|
||||||
value, shouldDuplicateRels, prefix)
|
value)
|
||||||
.iterator(),
|
.iterator(),
|
||||||
Encoders.bean(Relation.class))
|
Encoders.bean(Relation.class))
|
||||||
.filter((FilterFunction<Relation>) Objects::nonNull)
|
.filter((FilterFunction<Relation>) Objects::nonNull)
|
||||||
|
@ -121,34 +111,68 @@ public class CreateActionSetSparkJob implements Serializable {
|
||||||
new Text(OBJECT_MAPPER.writeValueAsString(aa))));
|
new Text(OBJECT_MAPPER.writeValueAsString(aa))));
|
||||||
}
|
}
|
||||||
|
|
||||||
private static List<Relation> createRelation(COCI value, boolean duplicate, String p) {
|
private static List<Relation> createRelation(COCI value) throws JsonProcessingException {
|
||||||
|
|
||||||
List<Relation> relationList = new ArrayList<>();
|
List<Relation> relationList = new ArrayList<>();
|
||||||
String prefix;
|
|
||||||
String citing;
|
String citing;
|
||||||
String cited;
|
String cited;
|
||||||
|
|
||||||
switch (p) {
|
switch (value.getCiting_pid()) {
|
||||||
case COCI:
|
case "doi":
|
||||||
prefix = DOI_PREFIX;
|
citing = DOI_PREFIX
|
||||||
citing = prefix
|
|
||||||
+ IdentifierFactory
|
+ IdentifierFactory
|
||||||
.md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getCiting()));
|
.md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getCiting()));
|
||||||
cited = prefix
|
break;
|
||||||
|
case "pmid":
|
||||||
|
citing = PMID_PREFIX
|
||||||
|
+ IdentifierFactory
|
||||||
|
.md5(PidCleaner.normalizePidValue(PidType.pmid.toString(), value.getCiting()));
|
||||||
|
break;
|
||||||
|
case "arxiv":
|
||||||
|
citing = ARXIV_PREFIX
|
||||||
|
+ IdentifierFactory
|
||||||
|
.md5(PidCleaner.normalizePidValue(PidType.arXiv.toString(), value.getCiting()));
|
||||||
|
break;
|
||||||
|
case "pmcid":
|
||||||
|
citing = PMCID_PREFIX
|
||||||
|
+ IdentifierFactory
|
||||||
|
.md5(PidCleaner.normalizePidValue(PidType.pmc.toString(), value.getCiting()));
|
||||||
|
break;
|
||||||
|
case "isbn":
|
||||||
|
case "issn":
|
||||||
|
return relationList;
|
||||||
|
|
||||||
|
default:
|
||||||
|
throw new IllegalStateException("Invalid prefix: " + new ObjectMapper().writeValueAsString(value));
|
||||||
|
}
|
||||||
|
|
||||||
|
switch (value.getCited_pid()) {
|
||||||
|
case "doi":
|
||||||
|
cited = DOI_PREFIX
|
||||||
+ IdentifierFactory
|
+ IdentifierFactory
|
||||||
.md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getCited()));
|
.md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getCited()));
|
||||||
break;
|
break;
|
||||||
case POCI:
|
case "pmid":
|
||||||
prefix = PMID_PREFIX;
|
cited = PMID_PREFIX
|
||||||
citing = prefix
|
|
||||||
+ IdentifierFactory
|
|
||||||
.md5(PidCleaner.normalizePidValue(PidType.pmid.toString(), value.getCiting()));
|
|
||||||
cited = prefix
|
|
||||||
+ IdentifierFactory
|
+ IdentifierFactory
|
||||||
.md5(PidCleaner.normalizePidValue(PidType.pmid.toString(), value.getCited()));
|
.md5(PidCleaner.normalizePidValue(PidType.pmid.toString(), value.getCited()));
|
||||||
break;
|
break;
|
||||||
|
case "arxiv":
|
||||||
|
cited = ARXIV_PREFIX
|
||||||
|
+ IdentifierFactory
|
||||||
|
.md5(PidCleaner.normalizePidValue(PidType.arXiv.toString(), value.getCited()));
|
||||||
|
break;
|
||||||
|
case "pmcid":
|
||||||
|
cited = PMCID_PREFIX
|
||||||
|
+ IdentifierFactory
|
||||||
|
.md5(PidCleaner.normalizePidValue(PidType.pmc.toString(), value.getCited()));
|
||||||
|
break;
|
||||||
|
case "isbn":
|
||||||
|
case "issn":
|
||||||
|
return relationList;
|
||||||
default:
|
default:
|
||||||
throw new IllegalStateException("Invalid prefix: " + p);
|
throw new IllegalStateException("Invalid prefix: " + new ObjectMapper().writeValueAsString(value));
|
||||||
}
|
}
|
||||||
|
|
||||||
if (!citing.equals(cited)) {
|
if (!citing.equals(cited)) {
|
||||||
|
@ -157,15 +181,6 @@ public class CreateActionSetSparkJob implements Serializable {
|
||||||
getRelation(
|
getRelation(
|
||||||
citing,
|
citing,
|
||||||
cited, ModelConstants.CITES));
|
cited, ModelConstants.CITES));
|
||||||
|
|
||||||
if (duplicate && value.getCiting().endsWith(".refs")) {
|
|
||||||
citing = prefix + IdentifierFactory
|
|
||||||
.md5(
|
|
||||||
CleaningFunctions
|
|
||||||
.normalizePidValue(
|
|
||||||
"doi", value.getCiting().substring(0, value.getCiting().indexOf(".refs"))));
|
|
||||||
relationList.add(getRelation(citing, cited, ModelConstants.CITES));
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
|
|
||||||
return relationList;
|
return relationList;
|
||||||
|
|
|
@ -12,10 +12,7 @@ import java.util.zip.ZipInputStream;
|
||||||
import org.apache.commons.cli.ParseException;
|
import org.apache.commons.cli.ParseException;
|
||||||
import org.apache.commons.io.IOUtils;
|
import org.apache.commons.io.IOUtils;
|
||||||
import org.apache.hadoop.conf.Configuration;
|
import org.apache.hadoop.conf.Configuration;
|
||||||
import org.apache.hadoop.fs.FSDataInputStream;
|
import org.apache.hadoop.fs.*;
|
||||||
import org.apache.hadoop.fs.FSDataOutputStream;
|
|
||||||
import org.apache.hadoop.fs.FileSystem;
|
|
||||||
import org.apache.hadoop.fs.Path;
|
|
||||||
import org.slf4j.Logger;
|
import org.slf4j.Logger;
|
||||||
import org.slf4j.LoggerFactory;
|
import org.slf4j.LoggerFactory;
|
||||||
|
|
||||||
|
@ -37,17 +34,17 @@ public class GetOpenCitationsRefs implements Serializable {
|
||||||
|
|
||||||
parser.parseArgument(args);
|
parser.parseArgument(args);
|
||||||
|
|
||||||
final String[] inputFile = parser.get("inputFile").split(";");
|
// final String[] inputFile = parser.get("inputFile").split(";");
|
||||||
log.info("inputFile {}", Arrays.asList(inputFile));
|
// log.info("inputFile {}", Arrays.asList(inputFile));
|
||||||
|
|
||||||
final String workingPath = parser.get("workingPath");
|
final String inputPath = parser.get("inputPath");
|
||||||
log.info("workingPath {}", workingPath);
|
log.info("inputPath {}", inputPath);
|
||||||
|
|
||||||
final String hdfsNameNode = parser.get("hdfsNameNode");
|
final String hdfsNameNode = parser.get("hdfsNameNode");
|
||||||
log.info("hdfsNameNode {}", hdfsNameNode);
|
log.info("hdfsNameNode {}", hdfsNameNode);
|
||||||
|
|
||||||
final String prefix = parser.get("prefix");
|
final String outputPath = parser.get("outputPath");
|
||||||
log.info("prefix {}", prefix);
|
log.info("outputPath {}", outputPath);
|
||||||
|
|
||||||
Configuration conf = new Configuration();
|
Configuration conf = new Configuration();
|
||||||
conf.set("fs.defaultFS", hdfsNameNode);
|
conf.set("fs.defaultFS", hdfsNameNode);
|
||||||
|
@ -56,20 +53,20 @@ public class GetOpenCitationsRefs implements Serializable {
|
||||||
|
|
||||||
GetOpenCitationsRefs ocr = new GetOpenCitationsRefs();
|
GetOpenCitationsRefs ocr = new GetOpenCitationsRefs();
|
||||||
|
|
||||||
for (String file : inputFile) {
|
ocr.doExtract(inputPath, outputPath, fileSystem);
|
||||||
ocr.doExtract(workingPath + "/Original/" + file, workingPath, fileSystem, prefix);
|
|
||||||
}
|
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
private void doExtract(String inputFile, String workingPath, FileSystem fileSystem, String prefix)
|
private void doExtract(String inputPath, String outputPath, FileSystem fileSystem)
|
||||||
throws IOException {
|
throws IOException {
|
||||||
|
|
||||||
final Path path = new Path(inputFile);
|
RemoteIterator<LocatedFileStatus> fileStatusListIterator = fileSystem
|
||||||
|
.listFiles(
|
||||||
FSDataInputStream oc_zip = fileSystem.open(path);
|
new Path(inputPath), true);
|
||||||
|
while (fileStatusListIterator.hasNext()) {
|
||||||
// int count = 1;
|
LocatedFileStatus fileStatus = fileStatusListIterator.next();
|
||||||
|
// do stuff with the file like ...
|
||||||
|
FSDataInputStream oc_zip = fileSystem.open(fileStatus.getPath());
|
||||||
try (ZipInputStream zis = new ZipInputStream(oc_zip)) {
|
try (ZipInputStream zis = new ZipInputStream(oc_zip)) {
|
||||||
ZipEntry entry = null;
|
ZipEntry entry = null;
|
||||||
while ((entry = zis.getNextEntry()) != null) {
|
while ((entry = zis.getNextEntry()) != null) {
|
||||||
|
@ -81,7 +78,7 @@ public class GetOpenCitationsRefs implements Serializable {
|
||||||
// count++;
|
// count++;
|
||||||
try (
|
try (
|
||||||
FSDataOutputStream out = fileSystem
|
FSDataOutputStream out = fileSystem
|
||||||
.create(new Path(workingPath + "/" + prefix + "/" + fileName + ".gz"));
|
.create(new Path(outputPath + "/" + fileName + ".gz"));
|
||||||
GZIPOutputStream gzipOs = new GZIPOutputStream(new BufferedOutputStream(out))) {
|
GZIPOutputStream gzipOs = new GZIPOutputStream(new BufferedOutputStream(out))) {
|
||||||
|
|
||||||
IOUtils.copy(zis, gzipOs);
|
IOUtils.copy(zis, gzipOs);
|
||||||
|
@ -92,6 +89,7 @@ public class GetOpenCitationsRefs implements Serializable {
|
||||||
}
|
}
|
||||||
|
|
||||||
}
|
}
|
||||||
|
}
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
|
@ -0,0 +1,171 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.actionmanager.opencitations;
|
||||||
|
|
||||||
|
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||||
|
|
||||||
|
import java.io.IOException;
|
||||||
|
import java.io.Serializable;
|
||||||
|
import java.util.Arrays;
|
||||||
|
import java.util.Objects;
|
||||||
|
import java.util.Optional;
|
||||||
|
import java.util.stream.Collectors;
|
||||||
|
import java.util.zip.ZipEntry;
|
||||||
|
import java.util.zip.ZipInputStream;
|
||||||
|
|
||||||
|
import org.apache.commons.cli.ParseException;
|
||||||
|
import org.apache.commons.io.IOUtils;
|
||||||
|
import org.apache.hadoop.conf.Configuration;
|
||||||
|
import org.apache.hadoop.fs.FSDataInputStream;
|
||||||
|
import org.apache.hadoop.fs.FSDataOutputStream;
|
||||||
|
import org.apache.hadoop.fs.FileSystem;
|
||||||
|
import org.apache.hadoop.fs.Path;
|
||||||
|
import org.apache.spark.SparkConf;
|
||||||
|
import org.apache.spark.api.java.function.FlatMapFunction;
|
||||||
|
import org.apache.spark.api.java.function.ForeachFunction;
|
||||||
|
import org.apache.spark.api.java.function.MapFunction;
|
||||||
|
import org.apache.spark.sql.*;
|
||||||
|
import org.slf4j.Logger;
|
||||||
|
import org.slf4j.LoggerFactory;
|
||||||
|
|
||||||
|
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||||
|
|
||||||
|
import eu.dnetlib.dhp.actionmanager.opencitations.model.COCI;
|
||||||
|
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||||
|
import scala.Tuple2;
|
||||||
|
|
||||||
|
/**
|
||||||
|
* @author miriam.baglioni
|
||||||
|
* @Date 29/02/24
|
||||||
|
*/
|
||||||
|
public class MapOCIdsInPids implements Serializable {
|
||||||
|
|
||||||
|
private static final Logger log = LoggerFactory.getLogger(CreateActionSetSparkJob.class);
|
||||||
|
private static final String DELIMITER = ",";
|
||||||
|
|
||||||
|
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||||
|
|
||||||
|
public static void main(final String[] args) throws IOException, ParseException {
|
||||||
|
|
||||||
|
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
|
||||||
|
IOUtils
|
||||||
|
.toString(
|
||||||
|
Objects
|
||||||
|
.requireNonNull(
|
||||||
|
MapOCIdsInPids.class
|
||||||
|
.getResourceAsStream(
|
||||||
|
"/eu/dnetlib/dhp/actionmanager/opencitations/remap_parameters.json"))));
|
||||||
|
|
||||||
|
parser.parseArgument(args);
|
||||||
|
|
||||||
|
Boolean isSparkSessionManaged = Optional
|
||||||
|
.ofNullable(parser.get("isSparkSessionManaged"))
|
||||||
|
.map(Boolean::valueOf)
|
||||||
|
.orElse(Boolean.TRUE);
|
||||||
|
|
||||||
|
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
|
||||||
|
|
||||||
|
final String inputPath = parser.get("inputPath");
|
||||||
|
log.info("inputPath {}", inputPath);
|
||||||
|
|
||||||
|
final String outputPath = parser.get("outputPath");
|
||||||
|
log.info("outputPath {}", outputPath);
|
||||||
|
|
||||||
|
final String nameNode = parser.get("nameNode");
|
||||||
|
log.info("nameNode {}", nameNode);
|
||||||
|
|
||||||
|
unzipCorrespondenceFile(inputPath, nameNode);
|
||||||
|
SparkConf conf = new SparkConf();
|
||||||
|
runWithSparkSession(
|
||||||
|
conf,
|
||||||
|
isSparkSessionManaged,
|
||||||
|
spark -> mapIdentifiers(spark, inputPath, outputPath));
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
|
private static void unzipCorrespondenceFile(String inputPath, String hdfsNameNode) throws IOException {
|
||||||
|
Configuration conf = new Configuration();
|
||||||
|
conf.set("fs.defaultFS", hdfsNameNode);
|
||||||
|
|
||||||
|
final Path path = new Path(inputPath + "/correspondence/omid.zip");
|
||||||
|
FileSystem fileSystem = FileSystem.get(conf);
|
||||||
|
|
||||||
|
FSDataInputStream project_zip = fileSystem.open(path);
|
||||||
|
|
||||||
|
try (ZipInputStream zis = new ZipInputStream(project_zip)) {
|
||||||
|
ZipEntry entry = null;
|
||||||
|
while ((entry = zis.getNextEntry()) != null) {
|
||||||
|
|
||||||
|
if (!entry.isDirectory()) {
|
||||||
|
String fileName = entry.getName();
|
||||||
|
byte buffer[] = new byte[1024];
|
||||||
|
int count;
|
||||||
|
|
||||||
|
try (
|
||||||
|
FSDataOutputStream out = fileSystem
|
||||||
|
.create(new Path(inputPath + "/correspondence/omid.csv"))) {
|
||||||
|
|
||||||
|
while ((count = zis.read(buffer, 0, buffer.length)) != -1)
|
||||||
|
out.write(buffer, 0, count);
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
|
private static void mapIdentifiers(SparkSession spark, String inputPath, String outputPath) {
|
||||||
|
Dataset<COCI> coci = spark
|
||||||
|
.read()
|
||||||
|
.textFile(inputPath + "/JSON")
|
||||||
|
.map(
|
||||||
|
(MapFunction<String, COCI>) value -> OBJECT_MAPPER.readValue(value, COCI.class),
|
||||||
|
Encoders.bean(COCI.class));
|
||||||
|
|
||||||
|
Dataset<Tuple2<String, String>> correspondenceData = spark
|
||||||
|
.read()
|
||||||
|
.format("csv")
|
||||||
|
.option("sep", DELIMITER)
|
||||||
|
.option("inferSchema", "true")
|
||||||
|
.option("header", "true")
|
||||||
|
.option("quotes", "\"")
|
||||||
|
.load(inputPath + "/correspondence/omid.csv")
|
||||||
|
.repartition(5000)
|
||||||
|
.flatMap((FlatMapFunction<Row, Tuple2<String, String>>) r -> {
|
||||||
|
String ocIdentifier = r.getAs("omid");
|
||||||
|
String[] correspondentIdentifiers = ((String) r.getAs("id")).split(" ");
|
||||||
|
return Arrays
|
||||||
|
.stream(correspondentIdentifiers)
|
||||||
|
.map(ci -> new Tuple2<String, String>(ocIdentifier, ci))
|
||||||
|
.collect(Collectors.toList())
|
||||||
|
.iterator();
|
||||||
|
}, Encoders.tuple(Encoders.STRING(), Encoders.STRING()));
|
||||||
|
|
||||||
|
Dataset<COCI> mappedCitingDataset = coci
|
||||||
|
.joinWith(correspondenceData, coci.col("citing").equalTo(correspondenceData.col("_1")))
|
||||||
|
.map((MapFunction<Tuple2<COCI, Tuple2<String, String>>, COCI>) t2 -> {
|
||||||
|
String correspondent = t2._2()._2();
|
||||||
|
t2._1().setCiting_pid(correspondent.substring(0, correspondent.indexOf(":")));
|
||||||
|
t2._1().setCiting(correspondent.substring(correspondent.indexOf(":") + 1));
|
||||||
|
return t2._1();
|
||||||
|
}, Encoders.bean(COCI.class));
|
||||||
|
|
||||||
|
mappedCitingDataset
|
||||||
|
.joinWith(correspondenceData, mappedCitingDataset.col("cited").equalTo(correspondenceData.col("_1")))
|
||||||
|
.map((MapFunction<Tuple2<COCI, Tuple2<String, String>>, COCI>) t2 -> {
|
||||||
|
String correspondent = t2._2()._2();
|
||||||
|
t2._1().setCited_pid(correspondent.substring(0, correspondent.indexOf(":")));
|
||||||
|
t2._1().setCited(correspondent.substring(correspondent.indexOf(":") + 1));
|
||||||
|
return t2._1();
|
||||||
|
}, Encoders.bean(COCI.class))
|
||||||
|
.write()
|
||||||
|
.mode(SaveMode.Append)
|
||||||
|
.option("compression", "gzip")
|
||||||
|
.json(outputPath);
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
|
@ -12,11 +12,9 @@ import java.util.Optional;
|
||||||
|
|
||||||
import org.apache.commons.io.IOUtils;
|
import org.apache.commons.io.IOUtils;
|
||||||
import org.apache.hadoop.conf.Configuration;
|
import org.apache.hadoop.conf.Configuration;
|
||||||
import org.apache.hadoop.fs.FileSystem;
|
import org.apache.hadoop.fs.*;
|
||||||
import org.apache.hadoop.fs.LocatedFileStatus;
|
|
||||||
import org.apache.hadoop.fs.Path;
|
|
||||||
import org.apache.hadoop.fs.RemoteIterator;
|
|
||||||
import org.apache.spark.SparkConf;
|
import org.apache.spark.SparkConf;
|
||||||
|
import org.apache.spark.api.java.function.FilterFunction;
|
||||||
import org.apache.spark.api.java.function.MapFunction;
|
import org.apache.spark.api.java.function.MapFunction;
|
||||||
import org.apache.spark.sql.*;
|
import org.apache.spark.sql.*;
|
||||||
import org.slf4j.Logger;
|
import org.slf4j.Logger;
|
||||||
|
@ -42,19 +40,21 @@ public class ReadCOCI implements Serializable {
|
||||||
final String outputPath = parser.get("outputPath");
|
final String outputPath = parser.get("outputPath");
|
||||||
log.info("outputPath: {}", outputPath);
|
log.info("outputPath: {}", outputPath);
|
||||||
|
|
||||||
final String[] inputFile = parser.get("inputFile").split(";");
|
final String hdfsNameNode = parser.get("hdfsNameNode");
|
||||||
log.info("inputFile {}", Arrays.asList(inputFile));
|
log.info("hdfsNameNode {}", hdfsNameNode);
|
||||||
|
|
||||||
Boolean isSparkSessionManaged = isSparkSessionManaged(parser);
|
Boolean isSparkSessionManaged = isSparkSessionManaged(parser);
|
||||||
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
|
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
|
||||||
|
|
||||||
final String workingPath = parser.get("workingPath");
|
final String workingPath = parser.get("inputPath");
|
||||||
log.info("workingPath {}", workingPath);
|
log.info("workingPath {}", workingPath);
|
||||||
|
|
||||||
final String format = parser.get("format");
|
|
||||||
log.info("format {}", format);
|
|
||||||
|
|
||||||
SparkConf sconf = new SparkConf();
|
SparkConf sconf = new SparkConf();
|
||||||
|
|
||||||
|
Configuration conf = new Configuration();
|
||||||
|
conf.set("fs.defaultFS", hdfsNameNode);
|
||||||
|
|
||||||
|
FileSystem fileSystem = FileSystem.get(conf);
|
||||||
final String delimiter = Optional
|
final String delimiter = Optional
|
||||||
.ofNullable(parser.get("delimiter"))
|
.ofNullable(parser.get("delimiter"))
|
||||||
.orElse(DEFAULT_DELIMITER);
|
.orElse(DEFAULT_DELIMITER);
|
||||||
|
@ -66,20 +66,21 @@ public class ReadCOCI implements Serializable {
|
||||||
doRead(
|
doRead(
|
||||||
spark,
|
spark,
|
||||||
workingPath,
|
workingPath,
|
||||||
inputFile,
|
fileSystem,
|
||||||
outputPath,
|
outputPath,
|
||||||
delimiter,
|
delimiter);
|
||||||
format);
|
|
||||||
});
|
});
|
||||||
}
|
}
|
||||||
|
|
||||||
private static void doRead(SparkSession spark, String workingPath, String[] inputFiles,
|
private static void doRead(SparkSession spark, String workingPath, FileSystem fileSystem,
|
||||||
String outputPath,
|
String outputPath,
|
||||||
String delimiter, String format) {
|
String delimiter) throws IOException {
|
||||||
|
RemoteIterator<LocatedFileStatus> fileStatusListIterator = fileSystem
|
||||||
for (String inputFile : inputFiles) {
|
.listFiles(
|
||||||
String pString = workingPath + "/" + inputFile + ".gz";
|
new Path(workingPath), true);
|
||||||
|
while (fileStatusListIterator.hasNext()) {
|
||||||
|
LocatedFileStatus fileStatus = fileStatusListIterator.next();
|
||||||
|
log.info("extracting file {}", fileStatus.getPath().toString());
|
||||||
Dataset<Row> cociData = spark
|
Dataset<Row> cociData = spark
|
||||||
.read()
|
.read()
|
||||||
.format("csv")
|
.format("csv")
|
||||||
|
@ -87,26 +88,26 @@ public class ReadCOCI implements Serializable {
|
||||||
.option("inferSchema", "true")
|
.option("inferSchema", "true")
|
||||||
.option("header", "true")
|
.option("header", "true")
|
||||||
.option("quotes", "\"")
|
.option("quotes", "\"")
|
||||||
.load(pString)
|
.load(fileStatus.getPath().toString())
|
||||||
.repartition(100);
|
.repartition(100);
|
||||||
|
|
||||||
cociData.map((MapFunction<Row, COCI>) row -> {
|
cociData.map((MapFunction<Row, COCI>) row -> {
|
||||||
|
|
||||||
COCI coci = new COCI();
|
COCI coci = new COCI();
|
||||||
if (format.equals("COCI")) {
|
|
||||||
coci.setCiting(row.getString(1));
|
coci.setCiting(row.getString(1));
|
||||||
coci.setCited(row.getString(2));
|
coci.setCited(row.getString(2));
|
||||||
} else {
|
|
||||||
coci.setCiting(String.valueOf(row.getInt(1)));
|
|
||||||
coci.setCited(String.valueOf(row.getInt(2)));
|
|
||||||
}
|
|
||||||
coci.setOci(row.getString(0));
|
coci.setOci(row.getString(0));
|
||||||
|
|
||||||
return coci;
|
return coci;
|
||||||
}, Encoders.bean(COCI.class))
|
}, Encoders.bean(COCI.class))
|
||||||
|
.filter((FilterFunction<COCI>) c -> c != null)
|
||||||
.write()
|
.write()
|
||||||
.mode(SaveMode.Overwrite)
|
.mode(SaveMode.Append)
|
||||||
.option("compression", "gzip")
|
.option("compression", "gzip")
|
||||||
.json(outputPath + inputFile);
|
.json(outputPath);
|
||||||
|
fileSystem.rename(fileStatus.getPath(), new Path("/tmp/miriam/OC/DONE"));
|
||||||
}
|
}
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
|
@ -9,8 +9,10 @@ public class COCI implements Serializable {
|
||||||
private String oci;
|
private String oci;
|
||||||
|
|
||||||
private String citing;
|
private String citing;
|
||||||
|
private String citing_pid;
|
||||||
|
|
||||||
private String cited;
|
private String cited;
|
||||||
|
private String cited_pid;
|
||||||
|
|
||||||
public String getOci() {
|
public String getOci() {
|
||||||
return oci;
|
return oci;
|
||||||
|
@ -25,6 +27,8 @@ public class COCI implements Serializable {
|
||||||
}
|
}
|
||||||
|
|
||||||
public void setCiting(String citing) {
|
public void setCiting(String citing) {
|
||||||
|
if (citing != null && citing.startsWith("omid:"))
|
||||||
|
citing = citing.substring(5);
|
||||||
this.citing = citing;
|
this.citing = citing;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@ -33,7 +37,24 @@ public class COCI implements Serializable {
|
||||||
}
|
}
|
||||||
|
|
||||||
public void setCited(String cited) {
|
public void setCited(String cited) {
|
||||||
|
if (cited != null && cited.startsWith("omid:"))
|
||||||
|
cited = cited.substring(5);
|
||||||
this.cited = cited;
|
this.cited = cited;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
public String getCiting_pid() {
|
||||||
|
return citing_pid;
|
||||||
|
}
|
||||||
|
|
||||||
|
public void setCiting_pid(String citing_pid) {
|
||||||
|
this.citing_pid = citing_pid;
|
||||||
|
}
|
||||||
|
|
||||||
|
public String getCited_pid() {
|
||||||
|
return cited_pid;
|
||||||
|
}
|
||||||
|
|
||||||
|
public void setCited_pid(String cited_pid) {
|
||||||
|
this.cited_pid = cited_pid;
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|
|
@ -23,7 +23,6 @@ import com.fasterxml.jackson.databind.ObjectMapper;
|
||||||
|
|
||||||
import eu.dnetlib.dhp.actionmanager.project.utils.model.CSVProgramme;
|
import eu.dnetlib.dhp.actionmanager.project.utils.model.CSVProgramme;
|
||||||
import eu.dnetlib.dhp.actionmanager.project.utils.model.CSVProject;
|
import eu.dnetlib.dhp.actionmanager.project.utils.model.CSVProject;
|
||||||
import eu.dnetlib.dhp.actionmanager.project.utils.model.EXCELTopic;
|
|
||||||
import eu.dnetlib.dhp.actionmanager.project.utils.model.JsonTopic;
|
import eu.dnetlib.dhp.actionmanager.project.utils.model.JsonTopic;
|
||||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||||
import eu.dnetlib.dhp.common.HdfsSupport;
|
import eu.dnetlib.dhp.common.HdfsSupport;
|
||||||
|
@ -33,6 +32,7 @@ import eu.dnetlib.dhp.schema.oaf.H2020Classification;
|
||||||
import eu.dnetlib.dhp.schema.oaf.H2020Programme;
|
import eu.dnetlib.dhp.schema.oaf.H2020Programme;
|
||||||
import eu.dnetlib.dhp.schema.oaf.OafEntity;
|
import eu.dnetlib.dhp.schema.oaf.OafEntity;
|
||||||
import eu.dnetlib.dhp.schema.oaf.Project;
|
import eu.dnetlib.dhp.schema.oaf.Project;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
|
||||||
import eu.dnetlib.dhp.utils.DHPUtils;
|
import eu.dnetlib.dhp.utils.DHPUtils;
|
||||||
import scala.Tuple2;
|
import scala.Tuple2;
|
||||||
|
|
||||||
|
@ -160,9 +160,11 @@ public class SparkAtomicActionJob {
|
||||||
(MapFunction<Project, String>) OafEntity::getId,
|
(MapFunction<Project, String>) OafEntity::getId,
|
||||||
Encoders.STRING())
|
Encoders.STRING())
|
||||||
.mapGroups((MapGroupsFunction<String, Project, Project>) (s, it) -> {
|
.mapGroups((MapGroupsFunction<String, Project, Project>) (s, it) -> {
|
||||||
Project first = it.next();
|
Project merge = it.next();
|
||||||
it.forEachRemaining(first::mergeFrom);
|
while (it.hasNext()) {
|
||||||
return first;
|
merge = MergeUtils.mergeProject(merge, it.next());
|
||||||
|
}
|
||||||
|
return merge;
|
||||||
}, Encoders.bean(Project.class))
|
}, Encoders.bean(Project.class))
|
||||||
.toJavaRDD()
|
.toJavaRDD()
|
||||||
.map(p -> new AtomicAction(Project.class, p))
|
.map(p -> new AtomicAction(Project.class, p))
|
||||||
|
|
|
@ -0,0 +1,196 @@
|
||||||
|
|
||||||
|
package eu.dnetlib.dhp.actionmanager.transformativeagreement;
|
||||||
|
|
||||||
|
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||||
|
|
||||||
|
import java.io.IOException;
|
||||||
|
import java.io.Serializable;
|
||||||
|
import java.util.*;
|
||||||
|
|
||||||
|
import org.apache.commons.cli.ParseException;
|
||||||
|
import org.apache.commons.io.IOUtils;
|
||||||
|
import org.apache.hadoop.io.Text;
|
||||||
|
import org.apache.hadoop.io.compress.GzipCodec;
|
||||||
|
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
|
||||||
|
import org.apache.spark.SparkConf;
|
||||||
|
import org.apache.spark.api.java.JavaRDD;
|
||||||
|
import org.apache.spark.api.java.function.FilterFunction;
|
||||||
|
import org.apache.spark.api.java.function.FlatMapFunction;
|
||||||
|
import org.apache.spark.api.java.function.MapFunction;
|
||||||
|
import org.apache.spark.sql.Encoders;
|
||||||
|
import org.apache.spark.sql.SparkSession;
|
||||||
|
import org.slf4j.Logger;
|
||||||
|
import org.slf4j.LoggerFactory;
|
||||||
|
|
||||||
|
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||||
|
|
||||||
|
import eu.dnetlib.dhp.actionmanager.transformativeagreement.model.TransformativeAgreementModel;
|
||||||
|
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||||
|
import eu.dnetlib.dhp.schema.action.AtomicAction;
|
||||||
|
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.Country;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.Relation;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.Result;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.utils.*;
|
||||||
|
import scala.Tuple2;
|
||||||
|
|
||||||
|
public class CreateActionSetSparkJob implements Serializable {
|
||||||
|
|
||||||
|
private static final Logger log = LoggerFactory.getLogger(CreateActionSetSparkJob.class);
|
||||||
|
|
||||||
|
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||||
|
|
||||||
|
private static final String IREL_PROJECT = "40|100018998___::1e5e62235d094afd01cd56e65112fc63";
|
||||||
|
private static final String TRANSFORMATIVE_AGREEMENT = "openapc::transformativeagreement";
|
||||||
|
|
||||||
|
public static void main(final String[] args) throws IOException, ParseException {
|
||||||
|
|
||||||
|
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
|
||||||
|
IOUtils
|
||||||
|
.toString(
|
||||||
|
Objects
|
||||||
|
.requireNonNull(
|
||||||
|
CreateActionSetSparkJob.class
|
||||||
|
.getResourceAsStream(
|
||||||
|
"/eu/dnetlib/dhp/actionmanager/transformativeagreement/as_parameters.json"))));
|
||||||
|
|
||||||
|
parser.parseArgument(args);
|
||||||
|
|
||||||
|
Boolean isSparkSessionManaged = Optional
|
||||||
|
.ofNullable(parser.get("isSparkSessionManaged"))
|
||||||
|
.map(Boolean::valueOf)
|
||||||
|
.orElse(Boolean.TRUE);
|
||||||
|
|
||||||
|
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
|
||||||
|
|
||||||
|
final String inputPath = parser.get("inputPath");
|
||||||
|
log.info("inputPath {}", inputPath);
|
||||||
|
|
||||||
|
final String outputPath = parser.get("outputPath");
|
||||||
|
log.info("outputPath {}", outputPath);
|
||||||
|
|
||||||
|
SparkConf conf = new SparkConf();
|
||||||
|
runWithSparkSession(
|
||||||
|
conf,
|
||||||
|
isSparkSessionManaged,
|
||||||
|
spark -> createActionSet(spark, inputPath, outputPath));
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
|
private static void createActionSet(SparkSession spark, String inputPath, String outputPath) {
|
||||||
|
JavaRDD<AtomicAction> relations = spark
|
||||||
|
.read()
|
||||||
|
.textFile(inputPath)
|
||||||
|
.map(
|
||||||
|
(MapFunction<String, TransformativeAgreementModel>) value -> OBJECT_MAPPER
|
||||||
|
.readValue(value, TransformativeAgreementModel.class),
|
||||||
|
Encoders.bean(TransformativeAgreementModel.class))
|
||||||
|
.flatMap(
|
||||||
|
(FlatMapFunction<TransformativeAgreementModel, Relation>) value -> createRelation(
|
||||||
|
value)
|
||||||
|
.iterator(),
|
||||||
|
Encoders.bean(Relation.class))
|
||||||
|
.filter((FilterFunction<Relation>) Objects::nonNull)
|
||||||
|
.toJavaRDD()
|
||||||
|
.map(p -> new AtomicAction(p.getClass(), p));
|
||||||
|
|
||||||
|
spark
|
||||||
|
.read()
|
||||||
|
.textFile(inputPath)
|
||||||
|
.map(
|
||||||
|
(MapFunction<String, TransformativeAgreementModel>) value -> OBJECT_MAPPER
|
||||||
|
.readValue(value, TransformativeAgreementModel.class),
|
||||||
|
Encoders.bean(TransformativeAgreementModel.class))
|
||||||
|
.map(
|
||||||
|
(MapFunction<TransformativeAgreementModel, Result>) value -> createResult(
|
||||||
|
value),
|
||||||
|
Encoders.bean(Result.class))
|
||||||
|
.filter((FilterFunction<Result>) r -> r != null)
|
||||||
|
.toJavaRDD()
|
||||||
|
.map(p -> new AtomicAction(p.getClass(), p))
|
||||||
|
.union(relations)
|
||||||
|
.mapToPair(
|
||||||
|
aa -> new Tuple2<>(new Text(aa.getClazz().getCanonicalName()),
|
||||||
|
new Text(OBJECT_MAPPER.writeValueAsString(aa))))
|
||||||
|
.saveAsHadoopFile(
|
||||||
|
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
|
||||||
|
|
||||||
|
}
|
||||||
|
|
||||||
|
private static Result createResult(TransformativeAgreementModel value) {
|
||||||
|
Result r = new Result();
|
||||||
|
r
|
||||||
|
.setId(
|
||||||
|
"50|doi_________::"
|
||||||
|
+ IdentifierFactory
|
||||||
|
.md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getDoi())));
|
||||||
|
r.setTransformativeAgreement(value.getAgreement());
|
||||||
|
Country country = new Country();
|
||||||
|
country.setClassid(value.getCountry());
|
||||||
|
country.setClassname(value.getCountry());
|
||||||
|
country
|
||||||
|
.setDataInfo(
|
||||||
|
OafMapperUtils
|
||||||
|
.dataInfo(
|
||||||
|
false, ModelConstants.SYSIMPORT_ACTIONSET, false, false,
|
||||||
|
OafMapperUtils
|
||||||
|
.qualifier(
|
||||||
|
"openapc::transformativeagreement",
|
||||||
|
"Harvested from Trnasformative Agreement file from OpenAPC",
|
||||||
|
ModelConstants.DNET_PROVENANCE_ACTIONS, ModelConstants.DNET_PROVENANCE_ACTIONS),
|
||||||
|
"0.9"));
|
||||||
|
country.setSchemeid(ModelConstants.DNET_COUNTRY_TYPE);
|
||||||
|
country.setSchemename(ModelConstants.DNET_COUNTRY_TYPE);
|
||||||
|
r.setCountry(Arrays.asList(country));
|
||||||
|
return r;
|
||||||
|
}
|
||||||
|
|
||||||
|
private static List<Relation> createRelation(TransformativeAgreementModel value) {
|
||||||
|
|
||||||
|
List<Relation> relationList = new ArrayList<>();
|
||||||
|
|
||||||
|
if (value.getAgreement().startsWith("IReL")) {
|
||||||
|
String paper;
|
||||||
|
|
||||||
|
paper = "50|doi_________::"
|
||||||
|
+ IdentifierFactory
|
||||||
|
.md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getDoi()));
|
||||||
|
|
||||||
|
relationList
|
||||||
|
.add(
|
||||||
|
getRelation(
|
||||||
|
paper,
|
||||||
|
IREL_PROJECT, ModelConstants.IS_PRODUCED_BY));
|
||||||
|
|
||||||
|
relationList.add(getRelation(IREL_PROJECT, paper, ModelConstants.PRODUCES));
|
||||||
|
}
|
||||||
|
return relationList;
|
||||||
|
}
|
||||||
|
|
||||||
|
public static Relation getRelation(
|
||||||
|
String source,
|
||||||
|
String target,
|
||||||
|
String relClass) {
|
||||||
|
|
||||||
|
return OafMapperUtils
|
||||||
|
.getRelation(
|
||||||
|
source,
|
||||||
|
target,
|
||||||
|
ModelConstants.RESULT_PROJECT,
|
||||||
|
ModelConstants.OUTCOME,
|
||||||
|
relClass,
|
||||||
|
Arrays
|
||||||
|
.asList(
|
||||||
|
OafMapperUtils.keyValue(ModelConstants.OPEN_APC_ID, ModelConstants.OPEN_APC_NAME)),
|
||||||
|
OafMapperUtils
|
||||||
|
.dataInfo(
|
||||||
|
false, null, false, false,
|
||||||
|
OafMapperUtils
|
||||||
|
.qualifier(
|
||||||
|
TRANSFORMATIVE_AGREEMENT, "Transformative Agreement",
|
||||||
|
ModelConstants.DNET_PROVENANCE_ACTIONS, ModelConstants.DNET_PROVENANCE_ACTIONS),
|
||||||
|
"0.9"),
|
||||||
|
null);
|
||||||
|
}
|
||||||
|
|
||||||
|
}
|
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue