4.0.0 com.github.helgeho archivespark_2.11 jar archivespark https://github.com/helgeho/ArchiveSpark 2.5 MIT http://www.opensource.org/licenses/mit-license.php repo archivespark com.github.helgeho https://github.com/helgeho/ArchiveSpark https://github.com/helgeho/ArchiveSpark scm:git@github.com:helgeho/ArchiveSpark.git helgeho Helge Holzmann holzmann@L3S.de http://www.HelgeHolzmann.de org.scala-lang scala-library 2.11.7 org.apache.spark spark-core_2.11 2.2.0 provided org.scala-lang scala-library org.apache.hadoop hadoop-core com.google.guava guava org.apache.hadoop hadoop-client 2.5.0 provided org.netpreserve.commons webarchive-commons 1.1.5 org.apache.hadoop hadoop-core com.google.guava guava commons-io commons-io 2.4 org.json4s json4s-native_2.11 3.2.11 org.scala-lang scala-library org.jsoup jsoup 1.10.1 com.google.protobuf protobuf-java 2.6.1 org.apache.httpcomponents httpclient 4.5.1 org.apache.httpcomponents httpcore 4.4.4 edu.stanford.nlp stanford-corenlp 3.5.1 provided org.elasticsearch elasticsearch-spark_2.11 2.2.0 provided org.scalatest scalatest_2.11 2.2.6 test