D-Net
/
dnet-hadoop
13
4
Fork 10
Code Issues 14 Pull Requests 9 Projects 2 Releases 1 Wiki Activity

Merge branch 'beta' into dependency-revision

This commit is contained in:
Claudio Atzori 2024-05-02 11:54:59 +02:00
parent 0173bf02f3 00ad21d814
commit 591b76047f
14 changed files with 178 additions and 2721 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
dhp-common/pom.xml
View File

@ -63,11 +63,13 @@
<dependencies>
<dependency>
<groupId>eu.dnetlib.dhp</groupId>
<artifactId>dhp-pace-core</artifactId>
<version>${project.version}</version>
<groupId>edu.cmu</groupId>
<artifactId>secondstring</artifactId>
</dependency>
<dependency>
<groupId>com.ibm.icu</groupId>
<artifactId>icu4j</artifactId>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>

100
dhp-common/src/main/java/eu/dnetlib/pace/common/PaceCommonUtils.java Normal file
View File

@ -0,0 +1,100 @@
package eu.dnetlib.pace.common;
import com.google.common.base.Splitter;
import com.google.common.collect.Iterables;
import com.google.common.collect.Sets;
import com.ibm.icu.text.Transliterator;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import java.nio.charset.StandardCharsets;
import java.text.Normalizer;
import java.util.Set;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
/**
* 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);
}
}

15
dhp-pace-core/src/main/java/eu/dnetlib/pace/model/Person.java → dhp-common/src/main/java/eu/dnetlib/pace/model/Person.java
View File

@ -1,21 +1,20 @@
package eu.dnetlib.pace.model;
import java.nio.charset.Charset;
import java.text.Normalizer;
import java.util.List;
import java.util.Set;
import com.google.common.base.Joiner;
import com.google.common.base.Splitter;
import com.google.common.collect.Iterables;
import com.google.common.collect.Lists;
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.DotAbbreviations;
import java.nio.charset.Charset;
import java.text.Normalizer;
import java.util.List;
import java.util.Set;
public class Person {
private static final String UTF8 = "UTF-8";
@ -86,7 +85,7 @@ public class Person {
private List<String> splitTerms(final String s) {
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();

5
dhp-pace-core/src/main/java/eu/dnetlib/pace/util/Capitalise.java → dhp-common/src/main/java/eu/dnetlib/pace/util/Capitalise.java
View File

@ -1,9 +1,8 @@
package eu.dnetlib.pace.util;
import org.apache.commons.lang3.text.WordUtils;
import com.google.common.base.Function;
import org.apache.commons.lang3.text.WordUtils;
public class Capitalise implements Function<String, String> {
@ -15,4 +14,4 @@ public class Capitalise implements Function<String, String> {
public String apply(final String s) {
return WordUtils.capitalize(s.toLowerCase(), DELIM);
}
};
}

2
dhp-pace-core/src/main/java/eu/dnetlib/pace/util/DotAbbreviations.java → dhp-common/src/main/java/eu/dnetlib/pace/util/DotAbbreviations.java
View File

@ -8,4 +8,4 @@ public class DotAbbreviations implements Function<String, String> {
public String apply(String s) {
return s.length() == 1 ? s + "." : s;
}
};
}

0
dhp-pace-core/src/main/resources/eu/dnetlib/pace/config/name_particles.txt → dhp-common/src/main/resources/eu/dnetlib/pace/config/name_particles.txt
View File

6
dhp-pace-core/pom.xml
View File

@ -49,6 +49,12 @@
</build>
<dependencies>
<dependency>
<groupId>eu.dnetlib.dhp</groupId>
<artifactId>dhp-common</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>edu.cmu</groupId>
<artifactId>secondstring</artifactId>

81
dhp-pace-core/src/main/java/eu/dnetlib/pace/common/AbstractPaceFunctions.java
View File

@ -1,32 +1,26 @@
package eu.dnetlib.pace.common;
import com.google.common.base.Joiner;
import com.google.common.collect.Sets;
import com.ibm.icu.text.Transliterator;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import java.io.IOException;
import java.io.StringWriter;
import java.nio.charset.StandardCharsets;
import java.text.Normalizer;
import java.util.*;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import java.util.stream.Collectors;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
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.ibm.icu.text.Transliterator;
import eu.dnetlib.pace.clustering.NGramUtils;
/**
* Set of common functions for the framework
*
* @author claudio
*/
public class AbstractPaceFunctions {
public class AbstractPaceFunctions extends PaceCommonUtils {
// city map to be used when translating the city names into codes
private static Map<String, String> cityMap = AbstractPaceFunctions
@ -41,9 +35,6 @@ public class AbstractPaceFunctions {
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");
// transliterator
protected static Transliterator transliterator = Transliterator.getInstance("Any-Eng");
// blacklist of ngrams: to avoid generic keys
protected static Set<String> ngramBlacklist = loadFromClasspath("/eu/dnetlib/pace/config/ngram_blacklist.txt");
@ -51,8 +42,6 @@ public class AbstractPaceFunctions {
public static final Pattern HTML_REGEX = Pattern.compile("<[^>]*>");
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
public static final Pattern DOI_PREFIX = Pattern.compile("(https?:\\/\\/dx\\.doi\\.org\\/)|(doi:)");
@ -129,25 +118,6 @@ public class AbstractPaceFunctions {
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) {
final StringBuilder sb = new StringBuilder();
@ -162,23 +132,6 @@ public class AbstractPaceFunctions {
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) {
byte[] bytes = s.getBytes(StandardCharsets.UTF_8);
return new String(bytes, StandardCharsets.UTF_8);
@ -233,22 +186,6 @@ public class AbstractPaceFunctions {
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) {
Transliterator transliterator = Transliterator.getInstance("Any-Eng");
@ -303,10 +240,6 @@ public class AbstractPaceFunctions {
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) {
return DOI_PREFIX.matcher(pid.toLowerCase()).replaceAll("");
}

2553
dhp-pace-core/src/main/java/eu/dnetlib/pace/util/DiffPatchMatch.java
View File

File diff suppressed because it is too large Load Diff

2
dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/consistency/oozie_app/workflow.xml
View File

@ -102,6 +102,8 @@
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=15000
--conf spark.network.timeout=300s
--conf spark.shuffle.registration.timeout=50000
</spark-opts>
<arg>--graphBasePath</arg><arg>${graphBasePath}</arg>
<arg>--graphOutputPath</arg><arg>${graphOutputPath}</arg>

46
dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/scan/oozie_app/workflow.xml
View File

@ -33,16 +33,14 @@
<description>max number of elements in a connected component</description>
</property>
<property>
<name>sparkDriverMemory</name>
<description>memory for driver process</description>
<name>sparkResourceOpts</name>
<value>--executor-memory=6G --conf spark.executor.memoryOverhead=4G --executor-cores=6 --driver-memory=8G --driver-cores=4</value>
<description>spark resource options</description>
</property>
<property>
<name>sparkExecutorMemory</name>
<description>memory for individual executor</description>
</property>
<property>
<name>sparkExecutorCores</name>
<description>number of cores used by single executor</description>
<name>sparkResourceOptsCreateMergeRel</name>
<value>--executor-memory=6G --conf spark.executor.memoryOverhead=4G --executor-cores=6 --driver-memory=8G --driver-cores=4</value>
<description>spark resource options</description>
</property>
<property>
<name>oozieActionShareLibForSpark2</name>
@ -119,9 +117,7 @@
<class>eu.dnetlib.dhp.oa.dedup.SparkCreateSimRels</class>
<jar>dhp-dedup-openaire-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
${sparkResourceOpts}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@ -146,9 +142,7 @@
<class>eu.dnetlib.dhp.oa.dedup.SparkWhitelistSimRels</class>
<jar>dhp-dedup-openaire-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
${sparkResourceOpts}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@ -174,9 +168,7 @@
<class>eu.dnetlib.dhp.oa.dedup.SparkCreateMergeRels</class>
<jar>dhp-dedup-openaire-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
${sparkResourceOptsCreateMergeRel}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@ -203,9 +195,7 @@
<class>eu.dnetlib.dhp.oa.dedup.SparkCreateDedupRecord</class>
<jar>dhp-dedup-openaire-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
${sparkResourceOpts}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@ -230,9 +220,7 @@
<class>eu.dnetlib.dhp.oa.dedup.SparkCopyOpenorgsMergeRels</class>
<jar>dhp-dedup-openaire-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
${sparkResourceOpts}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@ -257,9 +245,7 @@
<class>eu.dnetlib.dhp.oa.dedup.SparkCreateOrgsDedupRecord</class>
<jar>dhp-dedup-openaire-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
${sparkResourceOpts}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@ -283,9 +269,7 @@
<class>eu.dnetlib.dhp.oa.dedup.SparkUpdateEntity</class>
<jar>dhp-dedup-openaire-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
${sparkResourceOpts}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
@ -309,9 +293,7 @@
<class>eu.dnetlib.dhp.oa.dedup.SparkCopyRelationsNoOpenorgs</class>
<jar>dhp-dedup-openaire-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
${sparkResourceOpts}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}

61
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/workflow.xml
View File

@ -100,16 +100,12 @@
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
--conf spark.sql.shuffle.partitions=3840
--conf spark.speculation=false
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
--conf spark.sql.shuffle.partitions=8000
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
@ -132,12 +128,11 @@
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
@ -160,12 +155,11 @@
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
@ -188,12 +182,11 @@
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
@ -218,12 +211,11 @@
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/orcid/targetOrcidAssoc</arg>
<arg>--outputPath</arg><arg>${workingDir}/orcid/mergedOrcidAssoc</arg>
@ -247,19 +239,14 @@
<class>eu.dnetlib.dhp.orcidtoresultfromsemrel.SparkOrcidToResultFromSemRelJob</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=4
--executor-memory=4G
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=5G
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
--conf spark.speculation=false
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
--conf spark.sql.shuffle.partitions=15000
</spark-opts>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/mergedOrcidAssoc</arg>
@ -282,15 +269,12 @@
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
--conf spark.speculation=false
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
--conf spark.sql.shuffle.partitions=8000
</spark-opts>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/mergedOrcidAssoc</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
@ -312,15 +296,12 @@
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
--conf spark.speculation=false
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
--conf spark.sql.shuffle.partitions=8000
</spark-opts>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/mergedOrcidAssoc</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
@ -342,15 +323,12 @@
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${sparkExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
--conf spark.speculation=false
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
--conf spark.sql.shuffle.partitions=4000
</spark-opts>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/mergedOrcidAssoc</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
@ -362,15 +340,6 @@
</action>
<join name="wait2" to="End"/>
<!-- <action name="reset_workingDir">-->
<!-- <fs>-->
<!-- <delete path="${workingDir}"/>-->
<!-- <mkdir path="${workingDir}"/>-->
<!-- </fs>-->
<!-- <ok to="End"/>-->
<!-- <error to="Kill"/>-->
<!-- </action>-->
<end name="End"/>

6
dhp-workflows/dhp-graph-mapper/pom.xml
View File

@ -90,6 +90,12 @@
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>eu.dnetlib.dhp</groupId>
<artifactId>dhp-pace-core</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>com.jayway.jsonpath</groupId>
<artifactId>json-path</artifactId>

12
dhp-workflows/dhp-impact-indicators/src/main/resources/eu/dnetlib/dhp/oa/graph/impact_indicators/oozie_app/workflow.xml
View File

@ -71,6 +71,7 @@
--executor-memory=${sparkHighExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkHighDriverMemory}
--conf spark.executor.memoryOverhead=${sparkHighExecutorMemory}
--conf spark.sql.shuffle.partitions=${sparkShufflePartitions}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@ -108,6 +109,7 @@
--executor-memory=${sparkHighExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkNormalDriverMemory}
--conf spark.executor.memoryOverhead=${sparkHighExecutorMemory}
--conf spark.sql.shuffle.partitions=${sparkShufflePartitions}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@ -141,6 +143,7 @@
--executor-memory=${sparkHighExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkNormalDriverMemory}
--conf spark.executor.memoryOverhead=${sparkHighExecutorMemory}
--conf spark.sql.shuffle.partitions=${sparkShufflePartitions}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@ -176,6 +179,7 @@
--executor-memory=${sparkHighExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkNormalDriverMemory}
--conf spark.executor.memoryOverhead=${sparkHighExecutorMemory}
--conf spark.sql.shuffle.partitions=${sparkShufflePartitions}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@ -209,6 +213,7 @@
--executor-memory=${sparkHighExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkNormalDriverMemory}
--conf spark.executor.memoryOverhead=${sparkHighExecutorMemory}
--conf spark.sql.shuffle.partitions=${sparkShufflePartitions}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@ -245,6 +250,7 @@
--executor-memory=${sparkHighExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkNormalDriverMemory}
--conf spark.executor.memoryOverhead=${sparkHighExecutorMemory}
--conf spark.sql.shuffle.partitions=${sparkShufflePartitions}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@ -315,6 +321,7 @@
--executor-memory=${sparkNormalExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkNormalDriverMemory}
--conf spark.executor.memoryOverhead=${sparkNormalExecutorMemory}
--conf spark.sql.shuffle.partitions=${sparkShufflePartitions}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@ -361,6 +368,7 @@
--executor-memory=${sparkNormalExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkNormalDriverMemory}
--conf spark.executor.memoryOverhead=${sparkNormalExecutorMemory}
--conf spark.sql.shuffle.partitions=${sparkShufflePartitions}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@ -409,6 +417,7 @@
--executor-memory=${sparkHighExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkHighDriverMemory}
--conf spark.executor.memoryOverhead=${sparkHighExecutorMemory}
--conf spark.sql.shuffle.partitions=${sparkShufflePartitions}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@ -444,6 +453,7 @@
--executor-memory=${sparkHighExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkHighDriverMemory}
--conf spark.executor.memoryOverhead=${sparkHighExecutorMemory}
--conf spark.sql.shuffle.partitions=${sparkShufflePartitions}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@ -482,6 +492,7 @@
--executor-memory=${sparkHighExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkNormalDriverMemory}
--conf spark.executor.memoryOverhead=${sparkHighExecutorMemory}
--conf spark.sql.shuffle.partitions=${sparkShufflePartitions}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@ -533,6 +544,7 @@
--executor-memory=${sparkNormalExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkNormalDriverMemory}
--conf spark.executor.memoryOverhead=${sparkNormalExecutorMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}