Added module containing all the dependencies, useful for spark deploy on k8.

This commit is contained in:
Sandro La Bruzzo 2024-04-22 11:32:31 +02:00
parent b84ad0c06e
commit 073f320c6a
5 changed files with 174 additions and 5 deletions

View File

@ -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 = {

169
dhp-shade-package/pom.xml Normal file
View File

@ -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>

View File

@ -42,6 +42,7 @@ 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;
import eu.dnetlib.pace.config.DedupConfig; import eu.dnetlib.pace.config.DedupConfig;
import eu.dnetlib.pace.util.SparkCompatUtils;
import scala.Tuple3; import scala.Tuple3;
import scala.collection.JavaConversions; import scala.collection.JavaConversions;
@ -148,8 +149,7 @@ public class SparkCreateMergeRels extends AbstractSparkAction {
Dataset<Row> pivotHistory = spark Dataset<Row> pivotHistory = spark
.createDataset( .createDataset(
Collections.emptyList(), Collections.emptyList(),
RowEncoder SparkCompatUtils.encoderFor(StructType.fromDDL("id STRING, lastUsage STRING")));
.apply(StructType.fromDDL("id STRING, lastUsage STRING")));
if (StringUtils.isNotBlank(pivotHistoryDatabase)) { if (StringUtils.isNotBlank(pivotHistoryDatabase)) {
pivotHistory = spark pivotHistory = spark

View File

@ -8,7 +8,6 @@ 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.ReduceFunction;
import org.apache.spark.sql.*; import org.apache.spark.sql.*;
import org.apache.spark.sql.catalyst.encoders.RowEncoder;
import org.apache.spark.sql.types.StructType; import org.apache.spark.sql.types.StructType;
import org.slf4j.Logger; import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;

View File

@ -23,6 +23,7 @@
<module>dhp-pace-core</module> <module>dhp-pace-core</module>
<module>dhp-common</module> <module>dhp-common</module>
<module>dhp-workflows</module> <module>dhp-workflows</module>
<module>dhp-shade-package</module>
</modules> </modules>
<issueManagement> <issueManagement>