Description

<dependency>
    <groupId>org.dbpedia.extraction</groupId>
    <artifactId>dump</artifactId>
    <version>4.1</version>
</dependency>

<?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">

	<modelVersion>4.0.0</modelVersion>

	<parent>
		<groupId>org.dbpedia</groupId>
		<artifactId>extraction</artifactId>
		<version>4.1</version>
	</parent>

	<groupId>org.dbpedia.extraction</groupId>
	<artifactId>dump</artifactId>
	<name>DBpedia Dump Extraction</name>

	<build>
		<plugins>
			<plugin>

				<groupId>net.alchim31.maven</groupId>
				<artifactId>scala-maven-plugin</artifactId>
				<executions>
					<execution>
						<id>attach-docs-sources</id>
						<goals>
							<goal>add-source</goal>
							<goal>doc-jar</goal>
						</goals>
					</execution>
				</executions>

				<configuration>
					<launchers>

						<launcher>
							<id>import</id>
							<mainClass>org.dbpedia.extraction.dump.sql.Import</mainClass>
							<jvmArgs>
								<jvmArg>-server</jvmArg>
							</jvmArgs>
							<args>
								<!-- base folder of downloaded dumps -->
								<arg>/data/dbpedia-release/data</arg>
								<!-- location of SQL file containing MediaWiki table definitions -->
								<arg>/home/dbpedia-release/bin/mediawiki/core/maintenance/tables.sql</arg>
								<!-- JDBC URL of MySQL server. Import creates a new database for 
									each wiki. -->
								<arg>jdbc:mysql://localhost/?characterEncoding=UTF-8</arg>
								<!-- require-download-complete -->
								<arg>true</arg>
								<!-- file name: pages-articles.xml{,.bz2,.gz} -->
								<arg>pages-articles.xml.bz2</arg>
								<!-- languages and article count ranges, comma-separated, e.g. "de,en" 
									or "@mappings" etc. -->
								<arg>10000-</arg>
							</args>
						</launcher>

						<launcher>
							<id>extraction</id>
							<mainClass>org.dbpedia.extraction.dump.extract.Extraction</mainClass>

							<jvmArgs>
								<jvmArg>-server</jvmArg>
								<!-- <jvmArg>-Xmx4096m</jvmArg> <jvmArg>-XX:+HeapDumpOnOutOfMemoryError</jvmArg> 
									<jvmArg>-XX:+UseConcMarkSweepGC</jvmArg> <jvmArg>-XX:+PrintGC</jvmArg> <jvmArg>-XX:+PrintGCTimeStamps</jvmArg> 
									<jvmArg>-Dhttp.proxyHost=proxy.server.com</jvmArg> <jvmArg>-Dhttp.proxyPort=80</jvmArg> 
									<jvmArg>-Dhttp.proxyUser=user</jvmArg> <jvmArg>-Dhttp.proxyPassword=password</jvmArg> 
									<jvmArg>-Dhttp.nonProxyHosts="localhost|127.0.0.1"</jvmArg> -->
							</jvmArgs>
						</launcher>

						<launcher>
							<id>stats-extraction</id>
							<mainClass>org.dbpedia.extraction.dump.extract.Extraction</mainClass>

							<jvmArgs>
								<jvmArg>-server</jvmArg>
								<!-- Request statistics -->
								<jvmArg>-Dextract.template.stats=true</jvmArg>
								<!-- <jvmArg>-Xmx4096m</jvmArg> <jvmArg>-XX:+HeapDumpOnOutOfMemoryError</jvmArg> 
									<jvmArg>-XX:+UseConcMarkSweepGC</jvmArg> <jvmArg>-XX:+PrintGC</jvmArg> <jvmArg>-XX:+PrintGCTimeStamps</jvmArg> 
									<jvmArg>-Dhttp.proxyHost=proxy.server.com</jvmArg> <jvmArg>-Dhttp.proxyPort=80</jvmArg> 
									<jvmArg>-Dhttp.proxyUser=user</jvmArg> <jvmArg>-Dhttp.proxyPassword=password</jvmArg> 
									<jvmArg>-Dhttp.nonProxyHosts="localhost|127.0.0.1"</jvmArg> -->
							</jvmArgs>
						</launcher>

						<launcher>
							<id>compress</id>
							<mainClass>org.dbpedia.extraction.dump.compress.Compress</mainClass>
							<jvmArgs>
								<jvmArg>-Xmx1024m</jvmArg>
							</jvmArgs>
							<!-- mvn scala:run -Dlauncher=Compress "-DaddArgs=/data|/data-compressed" -->
						</launcher>

						<launcher>
							<id>download</id>
							<mainClass>org.dbpedia.extraction.dump.download.Download</mainClass>
							<!-- <jvmArgs> <jvmArg>-Dhttp.proxyHost=proxy.server.com</jvmArg> 
								<jvmArg>-Dhttp.proxyPort=port</jvmArg> <jvmArg>-Dhttp.proxyUser=user</jvmArg> 
								<jvmArg>-Dhttp.proxyPassword=password</jvmArg> <jvmArg>-Dhttp.nonProxyHosts="localhost|127.0.0.1"</jvmArg> 
								</jvmArgs> -->
							<!-- ../run download config=download.properties -->
						</launcher>

						<launcher>
							<id>purge-download</id>
							<mainClass>org.dbpedia.extraction.dump.clean.Clean</mainClass>
							<args>
								<arg>/home/release/wikipedia</arg>
								<arg>download-complete</arg>
								<arg>1</arg><!-- keep only one latest download -->
								<arg>*.sql.gz,*.xml.bz2,*.sql,*-pages-articles.xml,index.html</arg><!-- 
									delete these files -->
							</args>
						</launcher>

						<launcher>
							<id>purge-extraction</id>
							<mainClass>org.dbpedia.extraction.dump.clean.Clean</mainClass>
							<args>
								<arg>/home/release/wikipedia</arg>
								<arg>extraction-complete</arg>
								<arg>2</arg><!-- keep two extractions -->
								<arg>*.nt,*.nq,*.tql,*.ttl,*.trix,*-redirects.obj</arg><!-- delete 
									these files -->
							</args>
						</launcher>

					</launchers>
				</configuration>

			</plugin>
		</plugins>
	</build>

	<dependencies>

		<dependency>
			<groupId>org.dbpedia.extraction</groupId>
			<artifactId>core</artifactId>
		</dependency>

		<dependency>
			<groupId>org.scala-lang</groupId>
			<artifactId>scala-xml</artifactId>
		</dependency>

		<dependency>
			<groupId>mysql</groupId>
			<artifactId>mysql-connector-java</artifactId>
			<version>5.1.20</version>
		</dependency>

	</dependencies>

</project>