A Dockerfile for DataStage (https://github.com/dataflow/DataStage). Now supports DataStage 0.4.0.

Dockerfile

# DataStage
# for Docker 0.7 or newer
#
# This Dockerfile builds an image that runs DataStage.
#
# This performs a manual installation of DataStage from GitHub using a
# modified version of the install script found here:
# https://oxfile.ox.ac.uk/oxfile/work/extBoxNoJs?execution=e2s1
# 
# How to use (assuming Docker is installed):
# 
#   # This builds the Docker image. Wait for the command to finish.
#   sudo docker build -t datastage .
#
#   # This creates a container based on the image and runs it in daemon mode,
#   # binding http and ssh to ports 8888 and 2222 on the host machine.
#   # The container name will be 'ds'. Change as desired.
#   sudo docker run -d -p 8888:80 -p 2222:22 -v /srv/datastage:/srv/datastage:rw -v /tmp:/tmp:rw -name ds datastage
#
#   # You should be able to SSH into the container now (pass: badpassword):
#   ssh -p 2222 root@localhost
#
#   # Once you're in, you should change the root password:
#   passwd
#
#   # And then use datastage-config to set up users, etc:
#   datastage-config
#
#   # You may need to stop/start the container for all changes to take effect.
#
# If at any point the container becomes stopped, you can start it again using:
# 
#   sudo docker start ds
#
# To stop the container, use:
#
#   sudo docker stop ds
#
#  Note that any changes you made to the database will not persist the next
#  time you use "docker run" with this image. (See docker.io for docs).
#
# VERSION               0.2

FROM ubuntu:12.04

# Install prerequisites
RUN echo "debconf debconf/frontend select Teletype" | debconf-set-selections
RUN echo "deb http://archive.ubuntu.com/ubuntu precise main universe" > /etc/apt/sources.list
RUN apt-get update
RUN apt-get install -y postgresql-8.4 openssh-server sudo git net-tools supervisor python-setuptools python-all build-essential debhelper
RUN mkdir -p /var/run/sshd
RUN mkdir -p /var/log/supervisor

# Run installation scripts
ADD install-deps.sh /tmp/
RUN bash /tmp/install-deps.sh
ADD install-datastage.sh /tmp/
RUN bash /tmp/install-datastage.sh

# Configure datastage since it would have failed the first time
RUN /etc/init.d/postgresql start && dpkg-reconfigure dataflow-datastage

# Installation cleanup
RUN apt-get clean

# Set root password
RUN echo "root:badpassword" | chpasswd

# Remove default apache site so the user doesn't have to
RUN rm /etc/apache2/sites-enabled/000-default

# Inject the supervisor config
ADD supervisord.conf /etc/supervisor/conf.d/supervisord.conf

# Specify what to do when starting this image
CMD /etc/init.d/postgresql start && /usr/bin/supervisord

# Expose the ports for SSH and HTTP to outside the container
EXPOSE 22 80

# Define external mount points
VOLUME ["/srv/datastage", "/tmp"]

# A little documentation for the end user
RUN echo -e "\nRun datastage-config to set up DataStage." >> /etc/motd

install-datastage.sh

#!/bin/bash
set -e

TMP_DIR=/tmp/datastage_install

mkdir -p $TMP_DIR
cd $TMP_DIR

git clone https://github.com/dataflow/DataStage.git
cd DataStage

# Remove bad dependencies
echo "***** Removing bad dependencies from control file *****"
for NAME in django-conneg django-longliving django-pam sword-client python-libmount; do
	sed -i "/${NAME}/d" debian/control
done

make debian-package
dpkg --force-all -i debian-package/*.deb

cd
rm -rf $TMP_DIR

apt-get -y -f install

install-deps.sh

#!/bin/bash
set -e

TMP_DIR=/tmp/datastage_install

mkdir -p $TMP_DIR
cd $TMP_DIR

git clone https://github.com/ox-it/python-libmount.git
cd python-libmount
python setup.py install
cd ..

git clone https://github.com/ox-it/django-conneg.git
cd django-conneg
python setup.py install
cd ..


git clone  https://github.com/ox-it/django-longliving.git
cd django-longliving
python setup.py install
cd ..

git clone https://github.com/dataflow/python-client-sword2.git
cd python-client-sword2
python setup.py install
cd ..

git clone https://github.com/tehmaze/django-pam.git
cd django-pam
python setup.py install
cd ..

cd
rm -rf $TMP_DIR

supervisord.conf

[supervisord]
nodaemon=true

[program:sshd]
command=/usr/sbin/sshd -D

[program:apache2]
command=/bin/bash -c "source /etc/apache2/envvars && exec /usr/sbin/apache2 -DFOREGROUND"

[program:datastage]
command=/bin/bash -c "rm -f /var/run/datastage.pid && datastage-server start --no-daemonize"

Apologies, just realised this Dockerfile was tested only on EC2.