4.0.0 org.warcbase warcbase jar 0.1.0-SNAPSHOT warcbase WARC + HBase http://warcbase.org/ The Apache Software License, Version 2.0 http://www.apache.org/licenses/LICENSE-2.0.txt repo scm:git:git@github.com:lintool/warcbase.git scm:git:git@github.com:lintool/warcbase.git git@github.com:lintool/warcbase.git lintool Jimmy Lin jimmylin@umd.edu milad621 Milad Gholami mgholami@cs.umd.edu jeffyRao Jinfeng Rao jinfeng@cs.umd.edu org.sonatype.oss oss-parent 7 UTF-8 UTF-8 8.1.12.v20130726 2.0.0-cdh4.4.0 0.94.6-cdh4.4.0 3.4.5-cdh4.4.0 1.0.0 org.apache.maven.plugins maven-shade-plugin 2.1 package shade *:* META-INF/*.SF META-INF/*.DSA META-INF/*.RSA true fatjar org.apache.hadoop:* org.codehaus.mojo appassembler-maven-plugin 1.3.1 -Xms512M -Xmx24576M org.warcbase.WarcbaseAdmin WarcbaseAdmin org.warcbase.data.UrlMappingBuilder UrlMappingBuilder org.warcbase.data.UrlMapping UrlMapping org.warcbase.data.ExtractLinks ExtractLinks org.warcbase.data.ExtractSiteLinks ExtractSiteLinks org.warcbase.ingest.IngestFiles IngestFiles org.warcbase.ingest.SearchForUri SearchForUri org.warcbase.browser.WarcBrowser WarcBrowser org.warcbase.analysis.CountRowTypes CountRowTypes org.warcbase.analysis.DetectDuplicates DetectDuplicates org.warcbase.analysis.PrintAllUris PrintAllUris org.warcbase.analysis.ExtractText ExtractText internetarchive Internet Archive Maven Repository http://builds.archive.org:8080/maven2 cloudera https://repository.cloudera.com/artifactory/cloudera-repos/ maven http://repo.maven.apache.org/maven2/ junit junit 4.11 test commons-codec commons-codec 1.8 org.jsoup jsoup 1.7.3 org.apache.lucene lucene-core 4.5.1 com.google.guava guava 14.0.1 tl.lin lintools-datatypes 0.9.2 org.apache.hbase hbase ${hbase.version} slf4j-api slf4j-api org.slf4j slf4j-api org.slf4j slf4j-api-1.4.3 jsp-api jsp-api org.mortbay.jetty jsp-api org.mortbay.jetty jsp-api-2.1 org.mortbay.jetty servlet-api-2.5 org.mortbay.jetty servlet-api servlet-api servlet-api org.mortbay.jetty jetty org.mortbay.jetty jetty-util org.mortbay.jetty jsp-2.1 org.apache.hadoop hadoop-common ${hadoop.version2} javax.servlet servlet-api org.mortbay.jetty jetty org.mortbay.jetty jetty-util org.mortbay.jetty jsp-2.1 org.apache.hadoop hadoop-client ${hadoop.version2} javax.servlet servlet-api org.mortbay.jetty jetty org.mortbay.jetty jetty-util org.mortbay.jetty jsp-2.1 org.apache.zookeeper zookeeper ${zookeeper.version} org.netpreserve.openwayback openwayback-core 2.0.0.BETA.2 org.apache.hadoop hadoop-core ch.qos.logback logback-classic org.eclipse.jetty jetty-server ${jettyVersion} org.eclipse.jetty jetty-webapp ${jettyVersion} true org.slf4j slf4j-log4j12 1.6.4 org.jwat jwat-common ${jwat.version} org.jwat jwat-gzip ${jwat.version} org.jwat jwat-arc ${jwat.version} org.jwat jwat-warc ${jwat.version} org.apache.commons commons-lang3 3.0 net.sf.opencsv opencsv 2.3 org.netpreserve.commons webarchive-commons 1.1.3