Name: parquet Version: 1.5.0 Release: 4%{?dist} Summary: Java readers/writers for columnar file formats to use with Map-Reduce License: ASL 2.0 # http://parquet.incubator.apache.org/ URL: http://parquet.io/ # wget https://github.com/Parquet/parquet-mr/archive/parquet-1.5.0.tar.gz # rm -r parquet-mr-parquet-1.5.0/doc/dremel_paper/*.png # tar czf parquet-mr-parquet-1.5.0-clean.tar.gz parquet-mr-parquet-1.5.0 Source0: %{name}-mr-%{name}-%{version}-clean.tar.gz BuildRequires: mvn(com.google.guava:guava) BuildRequires: mvn(com.twitter:parquet-format) BuildRequires: mvn(commons-cli:commons-cli) BuildRequires: mvn(commons-codec:commons-codec) BuildRequires: mvn(it.unimi.dsi:fastutil) %if %{?fedora} > 20 BuildRequires: mvn(log4j:log4j:1.2.17) %else BuildRequires: mvn(log4j:log4j) %endif # avro 1.7.6 BuildRequires: mvn(org.apache.avro:avro) BuildRequires: mvn(org.apache.avro:avro-maven-plugin) BuildRequires: mvn(org.apache.hadoop:hadoop-common) BuildRequires: mvn(org.apache.hadoop:hadoop-mapreduce-client-core) BuildRequires: mvn(org.codehaus.jackson:jackson-core-asl) BuildRequires: mvn(org.codehaus.jackson:jackson-mapper-asl) BuildRequires: mvn(org.xerial.snappy:snappy-java) %if 0 # Test deps BuildRequires: mvn(com.carrotsearch:junit-benchmarks) BuildRequires: mvn(com.h2database:h2) BuildRequires: mvn(commons-httpclient:commons-httpclient) BuildRequires: mvn(junit:junit) %endif BuildRequires: maven-local BuildRequires: buildnumber-maven-plugin BuildRequires: exec-maven-plugin # Hadoop is not available on ARM ExcludeArch: %{arm} BuildArch: noarch %description Parquet is a columnar storage format that supports nested data. This provides the java implementation. %package tools Summary: Command line that aid in the inspection of columnar file formats Requires: %{name} = %{version}-%{release} Requires: apache-commons-configuration Requires: apache-commons-lang Requires: apache-commons-logging Requires: avalon-framework Requires: avalon-logkit Requires: geronimo-jms Requires: hadoop-common Requires: httpcomponents-client Requires: httpcomponents-core Requires: javamail Requires: libthrift-java %if %{?fedora} > 20 Requires: log4j12 %else Requires: log4j %endif Requires: slf4j Requires: jboss-servlet-3.0-api %description tools Parquet-Tools contain java based command line tool that aid in the inspection of Parquet files. %package javadoc Summary: Javadoc for %{name} %description javadoc This package contains javadoc for %{name}. %prep %setup -q -n %{name}-mr-%{name}-%{version} find . -name "*.jar" -print -delete find . -name "*.class" -print -delete # Disable copy of: fastutil jackson %pom_remove_plugin :maven-shade-plugin %pom_remove_plugin :maven-shade-plugin parquet-column %pom_remove_plugin org.codehaus.mojo:buildnumber-maven-plugin %pom_disable_module parquet-jackson %pom_remove_dep :parquet-jackson parquet-hadoop %pom_remove_dep :hadoop-client parquet-avro %pom_remove_dep :hadoop-client parquet-hadoop %pom_remove_dep :hadoop-client parquet-tools %pom_add_dep org.apache.hadoop:hadoop-common:'${hadoop.version}':provided parquet-avro %pom_add_dep org.apache.hadoop:hadoop-mapreduce-client-core:'${hadoop.version}':provided parquet-avro %pom_add_dep org.apache.hadoop:hadoop-common:'${hadoop.version}':provided parquet-hadoop %pom_add_dep org.apache.hadoop:hadoop-mapreduce-client-core:'${hadoop.version}':provided parquet-hadoop %pom_add_dep org.apache.hadoop:hadoop-common:'${hadoop.version}':provided parquet-tools %pom_add_dep org.apache.hadoop:hadoop-mapreduce-client-core:'${hadoop.version}':provided parquet-tools # Unavailable deps, disabled for now # # cascading:cascading-hadoop:2.5.1 %pom_disable_module parquet-cascading %pom_disable_module parquet-pig %pom_disable_module parquet-pig-bundle # com.twitter:scrooge-core_2.9.2:3.8.0 %pom_disable_module parquet-scrooge # com.twitter.elephantbird:elephant-bird-core,elephant-bird-pig:4.4 %pom_disable_module parquet-protobuf %pom_disable_module parquet-thrift %pom_disable_module parquet-test-hadoop2 %pom_disable_module parquet-hadoop-bundle %pom_disable_module parquet-hive %pom_disable_module parquet-hive-bundle # Use org.semver:enforcer-rule:0.9.17 %pom_remove_plugin :maven-enforcer-plugin parquet-avro %pom_remove_plugin :maven-enforcer-plugin parquet-cascading %pom_remove_plugin :maven-enforcer-plugin parquet-column %pom_remove_plugin :maven-enforcer-plugin parquet-common %pom_remove_plugin :maven-enforcer-plugin parquet-encoding %pom_remove_plugin :maven-enforcer-plugin parquet-generator %pom_remove_plugin :maven-enforcer-plugin parquet-hadoop %pom_remove_plugin :maven-enforcer-plugin parquet-tools %build # No test deps %mvn_build -f %install %mvn_install %if %{?fedora} > 20 %jpackage_script parquet.tools.Main "" "" %{name}:%{name}-format:avalon-framework-api:avalon-logkit:commons-cli:commons-codec:commons-configuration:commons-lang:commons-logging:fastutil:geronimo-jms:guava:httpcomponents/httpclient:httpcomponents/httpcore:jackson/jackson-core-asl:jackson/jackson-mapper-asl:libthrift:log4j12-1.2.17:javamail/mail:jboss-servlet-3.0-api:snappy-java:slf4j/slf4j-api:hadoop/hadoop-common:hadoop/hadoop-auth %{name}-tools true %else %jpackage_script parquet.tools.Main "" "" %{name}:%{name}-format:avalon-framework-api:avalon-logkit:commons-cli:commons-codec:commons-configuration:commons-lang:commons-logging:fastutil:geronimo-jms:guava:httpcomponents/httpclient:httpcomponents/httpcore:jackson/jackson-core-asl:jackson/jackson-mapper-asl:libthrift:log4j:javamail/mail:jboss-servlet-3.0-api:snappy-java:slf4j/slf4j-api:hadoop/hadoop-common:hadoop/hadoop-auth %{name}-tools true %endif %files -f .mfiles %dir %{_javadir}/%{name} %doc CHANGES.md README.md %license LICENSE NOTICE %files tools %{_bindir}/%{name}-tools %doc %{name}-tools/README.md %license LICENSE %{name}-tools/NOTICE %files javadoc -f .mfiles-javadoc %license LICENSE NOTICE %changelog * Wed Jul 09 2014 gil cattaneo 1.5.0-4 - add parquet-tools sub package * Wed Jul 09 2014 gil cattaneo 1.5.0-3 - fix summary - remove images with unknow copyright * Wed Jul 09 2014 gil cattaneo 1.5.0-2 - avoid missing dep (Hadoop) on arm * Wed Jul 09 2014 gil cattaneo 1.5.0-1 - update to 1.5.0 * Wed Mar 05 2014 gil cattaneo 1.4.3-1 - update to 1.4.3 * Wed Mar 05 2014 gil cattaneo 1.3.2-1 - initial rpm