From 2a255e331724f31501a77ddd3e0108af05c5271e Mon Sep 17 00:00:00 2001 From: Suraj B M Date: Mon, 29 Jan 2024 23:25:05 +0530 Subject: [PATCH] Add pig installation --- .gitignore | 1 + Dockerfile | 13 +++++++++++-- 2 files changed, 12 insertions(+), 2 deletions(-) create mode 100644 .gitignore diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..99d6725 --- /dev/null +++ b/.gitignore @@ -0,0 +1 @@ +getport \ No newline at end of file diff --git a/Dockerfile b/Dockerfile index f153a4b..d79d561 100644 --- a/Dockerfile +++ b/Dockerfile @@ -37,6 +37,7 @@ COPY hdfs-site.xml $HADOOP_HOME/etc/hadoop/hdfs-site.xml COPY mapred-site.xml $HADOOP_HOME/etc/hadoop/mapred-site.xml COPY yarn-site.xml $HADOOP_HOME/etc/hadoop/yarn-site.xml +RUN echo "export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64/bin" >> ~/.bashrc RUN echo "export HADOOP_HOME=/usr/local/hadoop" >> ~/.bashrc RUN echo "export HADOOP_INSTALL=\$HADOOP_HOME" >> ~/.bashrc RUN echo "export HADOOP_MAPRED_HOME=\$HADOOP_HOME" >> ~/.bashrc @@ -55,11 +56,19 @@ RUN echo "YARN_RESOURCEMANAGER_USER=root" >> /usr/local/hadoop/etc/hadoop/hadoop RUN echo "export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64" >> /usr/local/hadoop/etc/hadoop/hadoop-env.sh RUN echo "export HADOOP_CLASSPATH+=\" \$HADOOP_HOME/lib/*.jar\"" >> /usr/local/hadoop/etc/hadoop/hadoop-env.sh +# Copy init and restart scripts COPY restart $HADOOP_HOME/bin/restart -RUN chmod +x $HADOOP_HOME/bin/restart - COPY init $HADOOP_HOME/bin/init +RUN chmod +x $HADOOP_HOME/bin/restart RUN chmod +x $HADOOP_HOME/bin/init +# Install pig +RUN wget -O pig.tar.gz https://downloads.apache.org/pig/pig-0.17.0/pig-0.17.0.tar.gz +RUN tar -xzvf pig.tar.gz +RUN mv pig-0.17.0 /pig +RUN echo "export PIG_HOME=/pig" >> ~/.bashrc +RUN echo "export PATH=\$PATH:/pig/bin" >> ~/.bashrc +RUN echo "export PIG_CLASSPATH=\$HADOOP_HOME/etc/hadoop" >> ~/.bashrc + # Expose necessary ports EXPOSE 9870 8088 9000