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
2.3.0-cdh5.1.2
0.98.1-cdh5.1.2
3.4.5-cdh5.1.2
0.12.0-cdh5.1.2
1.0.0
org.apache.maven.plugins
maven-compiler-plugin
2.3.2
1.7
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.SearchForUrl
SearchForUrl
org.warcbase.browser.WarcBrowser
WarcBrowser
org.warcbase.analysis.DetectDuplicates
DetectDuplicates
org.warcbase.browser.SeleniumBrowser
SeleniumBrowser
maven
http://repo.maven.apache.org/maven2/
cloudera
https://repository.cloudera.com/artifactory/cloudera-repos/
internetarchive
Internet Archive Maven Repository
http://builds.archive.org:8080/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-client
${hbase.version}
org.apache.hadoophadoop-core
org.apache.hbase
hbase-server
${hbase.version}
org.apache.hadoophadoop-core
org.mortbay.jettyservlet-api-2.5
javax.servletservlet-api
org.apache.hadoop
hadoop-client
${hadoop.version}
javax.servletservlet-api
org.apache.zookeeper
zookeeper
${zookeeper.version}
org.apache.pig
pig
${pig.version}
org.mortbay.jettyservlet-api-2.5
javax.servletservlet-api
org.apache.pig
pigunit
${pig.version}
commons-langcommons-lang
commons-loggingcommons-logging
org.netpreserve.openwayback
openwayback-core
2.0.0.BETA.2
org.apache.hadoophadoop-core
ch.qos.logbacklogback-classic
org.netpreserve.openwaybackopenwayback-cdx-server
org.netpreserve.openwaybackopenwayback-access-control-core
it.unimi.dsidsiutils
fastutilfastutil
org.netpreserve.commons
webarchive-commons
1.1.3
org.apache.hadoophadoop-core
commons-langcommons-lang
fastutilfastutil
it.unimi.dsi
dsiutils
2.2.0
ch.qos.logbacklogback-classic
commons-langcommons-lang
it.unimi.dsi
fastutil
6.5.15
commons-langcommons-lang
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
commons-cli
commons-cli
1.2
net.sf.opencsv
opencsv
2.3
org.apache.tika
tika-core
1.5
org.antlr
antlr
3.5.2
org.seleniumhq.selenium
selenium-java
2.42.2
org.seleniumhq.seleniumselenium-htmlunit-driver
org.seleniumhq.seleniumselenium-ie-driver
org.webbitserverwebbit