Merge pull request #14 from doanxem99/amd

Fix download URL and install script errors in Dockerfile

Dockerfile

@@ -36,7 +36,7 @@ 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-arm64" >> ~/.bashrc && \
+RUN echo "export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64" >> ~/.bashrc && \
     echo "export HADOOP_HOME=/usr/local/hadoop" >> ~/.bashrc && \
     echo "export HADOOP_INSTALL=\$HADOOP_HOME" >> ~/.bashrc && \
     echo "export HADOOP_MAPRED_HOME=\$HADOOP_HOME" >> ~/.bashrc && \
@@ -52,7 +52,7 @@ RUN echo "HDFS_NAMENODE_USER=root" >> /usr/local/hadoop/etc/hadoop/hadoop-env.sh
     echo "HDFS_SECONDARYNAMENODE_USER=root" >> /usr/local/hadoop/etc/hadoop/hadoop-env.sh && \
     echo "YARN_NODEMANAGER_USER=root" >> /usr/local/hadoop/etc/hadoop/hadoop-env.sh && \
     echo "YARN_RESOURCEMANAGER_USER=root" >> /usr/local/hadoop/etc/hadoop/hadoop-env.sh && \
-    echo "export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-arm64" >> /usr/local/hadoop/etc/hadoop/hadoop-env.sh && \
+    echo "export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64" >> /usr/local/hadoop/etc/hadoop/hadoop-env.sh && \
     echo "export HADOOP_CLASSPATH+=\" \$HADOOP_HOME/lib/*.jar\"" >> /usr/local/hadoop/etc/hadoop/hadoop-env.sh
 
 # Install pig
@@ -64,20 +64,20 @@ RUN wget -O pig.tar.gz https://downloads.apache.org/pig/pig-0.17.0/pig-0.17.0.ta
     echo "export PIG_CLASSPATH=\$HADOOP_HOME/etc/hadoop" >> ~/.bashrc
 
 # Install hbase
-RUN wget http://apache.mirror.gtcomm.net/hbase/2.5.8/hbase-2.5.8-bin.tar.gz && \
-    tar -xzvf hbase-2.5.8-bin.tar.gz && \
-    mv hbase-2.5.8 /usr/local/hbase && \
+RUN wget https://archive.apache.org/dist/hbase/3.0.0-beta-1/hbase-3.0.0-beta-1-bin.tar.gz && \
+    tar -xzvf hbase-3.0.0-beta-1-bin.tar.gz && \
+    mv hbase-3.0.0-beta-1 /usr/local/hbase && \
     echo "export HBASE_HOME=/usr/local/hbase" >> ~/.bashrc && \
     echo "export PATH=\$PATH:\$HBASE_HOME/bin" >> ~/.bashrc && \
     echo "export HBASE_DISABLE_HADOOP_CLASSPATH_LOOKUP=\"true\"" >> /usr/local/hbase/conf/hbase-env.sh && \
-    echo "JAVA_HOME=/usr/lib/jvm/java-8-openjdk-arm64/" >> /usr/local/hbase/conf/hbase-env.sh
+    echo "JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64/" >> /usr/local/hbase/conf/hbase-env.sh
 COPY hbase-site.xml ~/hbase-site.xml
 
 RUN mkdir -p /hadoop/zookeeper && \
     chown -R $USER:$USER /hadoop/
 
 # Install Hive
-RUN wget https://dlcdn.apache.org/hive/hive-3.1.3/apache-hive-3.1.3-bin.tar.gz && \
+RUN wget http://archive.apache.org/dist/hive/hive-3.1.3/apache-hive-3.1.3-bin.tar.gz && \
     tar -xzvf apache-hive-3.1.3-bin.tar.gz && \
     mv apache-hive-3.1.3-bin /usr/local/hive && \
     echo "export HIVE_HOME=/usr/local/hive" >> ~/.bashrc && \
@@ -103,7 +103,7 @@ RUN wget https://archive.apache.org/dist/sqoop/1.4.7/sqoop-1.4.7.bin__hadoop-2.6
     echo "export HADOOP_MAPRED_HOME=/usr/local/hadoop" >> /usr/local/sqoop/conf/sqoop-env.sh
 
 # Install Zookeeper
-RUN wget https://downloads.apache.org/zookeeper/zookeeper-3.9.1/apache-zookeeper-3.9.1-bin.tar.gz && \
+RUN wget https://archive.apache.org/dist/zookeeper/zookeeper-3.9.1/apache-zookeeper-3.9.1-bin.tar.gz && \
     tar -xvf apache-zookeeper-3.9.1-bin.tar.gz && \
     mv apache-zookeeper-3.9.1-bin /usr/local/zookeeper && \
     mv /usr/local/zookeeper/conf/zoo_sample.cfg /usr/local/zookeeper/conf/zoo.cfg && \
@@ -121,10 +121,10 @@ RUN apt-get update && \
     echo "export PATH=\$PATH:\$SPARK_HOME/bin:\$SPARK_HOME/sbin" >> ~/.bashrc
 
 # Install Pyspark
-RUN pip install pyspark
+RUN pip install pyspark --break-system-packages
 
 # Install Kafka
-RUN wget https://downloads.apache.org/kafka/3.6.1/kafka_2.13-3.6.1.tgz && \
+RUN wget https://archive.apache.org/dist/kafka/3.6.1/kafka_2.13-3.6.1.tgz && \
     tar -xzvf kafka_2.13-3.6.1.tgz && \
     mv kafka_2.13-3.6.1 /usr/local/kafka && \
     echo "export KAFKA_HOME=/usr/local/kafka" >> ~/.bashrc && \

README.md

@@ -1,2 +1,35 @@
 # Hadoop on Docker
+## Linux/WSL
+### Installation
+```bash
+curl -fsSL https://bit.ly/hadock-install -o ~/hadoock && chmod +x ~/hadoock && sudo mv ~/hadoock /usr/bin/hadoock
+```
+if you're using WSL make sure to update it
+```powershell
+wsl.exe --update
+```
+### Usage
+```bash
+hadock
+```
+### Update
+```bash
+hadock --uninstall
+curl -fsSL https://bit.ly/hadock-install | bash
+```
+#### Copying from host
+```bash
+dockcp /path/to/file
+```
+This command copies ```path/to/file``` from host to ```/home``` on your docker container
+#### Running multiple instances
+```bash
+hadock_again
+```
+Use this command to open another shell in the same docker instance
+### Uninstallation
+```bash
+hadock --uninstall
+```
+
 Check the [wiki](https://github.com/silicoflare/docker-hadoop/wiki) for a full guide to use this docker image.

kafka

@@ -1,20 +1,41 @@
 #!/bin/bash
 
-verb=$1
-arg=$2
+verb="$1"
+arg="$2"
 
-if [ $verb == "start" ]; then
-    if [ $arg == "zookeeper" ]; then
-        $KAFKA_HOME/bin/zookeeper-server-start.sh $KAFKA_HOME/config/zookeeper.properties
-    elif [ $arg == "kafka" ]; then
-        $KAFKA_HOME/bin/kafka-server-start.sh $KAFKA_HOME/config/server.properties
+# Check if KAFKA_HOME is set
+if [ -z "$KAFKA_HOME" ]; then
+  echo "Error: KAFKA_HOME is not set"
+  exit 1
 fi
-elif [ $verb == "create-topic" ]; then
-    $KAFKA_HOME/bin/kafka-topics.sh --create --topic $arg --bootstrap-server localhost:9092
-elif [ $verb == "produce" ]; then
-    $KAFKA_HOME/bin/kafka-console-producer.sh --topic $arg --bootstrap-server localhost:9092
-elif [ $verb == "consume" ]; then
-    $KAFKA_HOME/bin/kafka-console-consumer.sh --topic $arg --from-beginning --bootstrap-server localhost:9092
-elif [ $verb == "submit" ]; then
-    spark-submit --packages org.apache.spark:spark-sql-kafka-0-10_2.12:3.0.1 $arg
+
+case "$verb" in
+"start")
+  if [ "$arg" == "zookeeper" ]; then
+    "$KAFKA_HOME/bin/zookeeper-server-start.sh" "$KAFKA_HOME/config/zookeeper.properties" &
+  elif [ "$arg" == "kafka" ]; then
+    "$KAFKA_HOME/bin/kafka-server-start.sh" "$KAFKA_HOME/config/server.properties" &
+  else
+    echo "Error: Invalid argument for 'start'. Use 'zookeeper' or 'kafka'."
   fi
+  ;;
+"create-topic")
+  "$KAFKA_HOME/bin/kafka-topics.sh" --create --topic "$arg" --bootstrap-server localhost:9092 &
+  ;;
+"produce")
+  "$KAFKA_HOME/bin/kafka-console-producer.sh" --topic "$arg" --bootstrap-server localhost:9092 &
+  ;;
+"consume")
+  "$KAFKA_HOME/bin/kafka-console-consumer.sh" --topic "$arg" --from-beginning --bootstrap-server localhost:9092 &
+  ;;
+"submit")
+  if [ -z "$arg" ]; then
+    echo "Error: Please provide a Spark script."
+  else
+    spark-submit --packages org.apache.spark:spark-sql-kafka-0-10_2.12:3.0.1 "$arg" &
+  fi
+  ;;
+*)
+  echo "Error: Unknown verb. Use 'start', 'create-topic', 'produce', 'consume', or 'submit'."
+  ;;
+esac