Install Hadoop 1.0.3 using Homebrew

install_hadoop.sh

#!/bin/bash
HADOOP_VERSION=1.0.3
HADOOP_URL=http://archive.apache.org/dist/hadoop/core/hadoop-$HADOOP_VERSION/hadoop-$HADOOP_VERSION.tar.gz

pushd `brew --prefix`

CHECKOUT_CMD=`brew versions hadoop 2> /dev/null | grep $HADOOP_VERSION | awk -F "    " '{ print $2 }'`
echo $CHECKOUT_CMD...
$CHECKOUT_CMD

sed -i -e "s#  url '.*'#  url '$HADOOP_URL'#" Library/Formula/hadoop.rb

echo brew install hadoop...
brew install hadoop

pushd Cellar/hadoop/$HADOOP_VERSION/libexec

echo Installing configuration files...

echo "export HADOOP_OPTS=\"-Djava.security.krb5.realm=OX.AC.UK -Djava.security.krb5.kdc=kdc0.ox.ac.uk:kdc1.ox.ac.uk\"" >> conf/hadoop-env.sh

echo """<?xml version=\"1.0\"?>
<?xml-stylesheet type=\"text/xsl\" href=\"configuration.xsl\"?>
<configuration>
    <property>
        <name>hadoop.tmp.dir</name>
        <value>${HOME}/.hadoop</value>
    </property>
    <property>
        <name>fs.default.name</name>
        <value>hdfs://localhost:8020</value>
    </property>
</configuration>""" > conf/core-site.xml


echo """<?xml version=\"1.0\"?>
<?xml-stylesheet type=\"text/xsl\" href=\"configuration.xsl\"?>
<configuration>
    <property>
      <name>mapred.job.tracker</name>
      <value>localhost:9001</value>
    </property> 
    <property>
        <name>mapred.tasktracker.map.tasks.maximum</name>
        <value>2</value>
    </property>
    <property>
        <name>mapred.tasktracker.reduce.tasks.maximum</name>
        <value>2</value>
    </property>
</configuration>
""" > conf/mapred-site.xml

echo """<?xml version=\"1.0\"?>
<?xml-stylesheet type=\"text/xsl\" href=\"configuration.xsl\"?>
<configuration>
    <property>
      <name>dfs.replication</name>
      <value>1</value>
    </property>
</configuration>""" > conf/hdfs-site.xml

echo Replacing commons-codec...
rm lib/commons-codec-1.4.jar
curl http://central.maven.org/maven2/commons-codec/commons-codec/1.6/commons-codec-1.6.jar > lib/commons-codec-1.6.jar

popd
popd

brew pin hadoop

mkdir -p ${HOME}/.hadoop/

hadoop namenode -format

echo
echo
echo "use start-all.sh and stop-all.sh to manage Hadoop"