recreated the repository and collapsed commits down

Dockerfile

@@ -0,0 +1,61 @@
+FROM ubuntu:cosmic-20190515
+ENV PYTHONDONTWRITEBYTECODE 1
+
+MAINTAINER Victor Ng <victor@crankycoder.com>
+EXPOSE 8080
+
+# add a non-privileged user for installing and running
+# the application
+
+RUN apt-get update && \
+    apt-get install -y sudo
+
+RUN groupadd --gid 10001 app && \
+    useradd --uid 10001 --gid 10001 --home /app --create-home app && \
+    echo "app:docker" | chpasswd && adduser app sudo
+
+# Set 'badpass' as the app password
+RUN echo 'app:badpass' | chpasswd
+
+RUN apt-get update && \
+    apt-get install -y bash build-essential curl gettext gfortran git libatlas3-base \
+    libbz2-dev libopenblas-dev libreadline-dev libsnappy-dev \
+    libsqlite3-dev libssl-dev locales make software-properties-common unzip \
+    vim wget zlib1g-dev
+
+RUN curl -sL https://deb.nodesource.com/setup_12.x | bash && apt-get install -y nodejs && apt-get clean
+
+RUN rm -rf /var/lib/apt/lists/*
+
+RUN update-locale LANG=C.UTF-8
+
+
+# Install Java8
+RUN wget --quiet https://github.com/frekele/oracle-java/releases/download/8u212-b10/jdk-8u212-linux-x64.tar.gz -O /tmp/jdk-8u212-linux-x64.tar.gz
+RUN wget --quiet https://raw.githubusercontent.com/crankycoder/install-java/master/install-java.sh -O /tmp/install-java.sh
+RUN chmod +x /tmp/install-java.sh && /tmp/install-java.sh -f /tmp/jdk-8u212-linux-x64.tar.gz
+
+# Set default user
+USER app
+
+# Install pyenv
+WORKDIR /app
+RUN git clone git://github.com/yyuu/pyenv.git .pyenv
+
+ENV HOME  /app
+ENV PYENV_ROOT $HOME/.pyenv
+ENV PATH $PYENV_ROOT/shims:$PYENV_ROOT/bin:$PATH
+
+RUN pyenv install 3.5.7
+RUN pyenv rehash
+
+# Install pyenv virtualenv
+RUN git clone https://github.com/pyenv/pyenv-virtualenv.git $PYENV_ROOT/plugins/pyenv-virtualenv
+
+RUN echo 'export PYENV_ROOT="$HOME/.pyenv"' >> /app/.bashrc
+RUN echo 'export PATH="$PYENV_ROOT/bin:$PATH"' >> /app/.bashrc
+RUN echo 'eval "$(pyenv init -)"' >> /app/.bashrc
+
+# Setup locale for Python/Java bridge
+RUN echo 'export LC_ALL=C.UTF-8' >> /app/.bashrc
+RUN echo 'export LANG=C.UTF-8' >> /app/.bashrc

Makefile

@@ -0,0 +1,8 @@
+bash:
+	docker-compose run --service-ports  devshell
+
+build:
+	docker-compose build devshell
+
+root_shell:
+	docker-compose run --user root --service-ports devshell

README.md

@@ -0,0 +1,21 @@
+# srg-python_mozetl
+
+Stop futzing with setting up your python_mozetl dependencies.  
+
+You'll go mad.
+
+This sets up a stock Ubuntu image with a working PySpark toolchain
+that will pass all the mozilla/python_mozetl testsuite.
+
+Run `make build` to build the image
+
+Run `make bash` to run bash with ~/dev/ mounted into /app/src
+
+The container has an enviroment variable set for HOST_IP which is your
+host machine's IP address for en0
+
+The default user is 'app' with a password set to 'badpass' with sudo
+rights
+
+TODO: add instructions on how to use pyenv-virtualenv to setup the
+python 3.5 enviroment to run the python_mozetl testsuite

docker-compose.yml

@@ -0,0 +1,18 @@
+version: "3.7"
+services:
+  devshell:
+    environment:
+        # This expects that your host machine has something like :
+        #    export HOST_IP=`ifconfig en0 | awk '/ *inet /{print $2}'`
+        # setup.
+      - HOST_IP=${HOST_IP}
+    build: .
+    expose:
+      - "8080"
+    ports:
+        - "8080:8080"
+    volumes:
+      - /Users/vng/dev:/app/src
+      - .:/app/dev
+    stdin_open: true
+    tty: true

etl-requirements.txt

@@ -0,0 +1,60 @@
+arrow==0.10.0
+atomicwrites==1.3.0
+attrs==19.1.0
+backcall==0.1.0
+boto==2.49.0
+boto3==1.9.87
+botocore==1.10.84
+certifi==2019.3.9
+chardet==3.0.4
+click==6.7
+click-datetime==0.2
+coverage==4.5.3
+decorator==4.4.0
+docutils==0.14
+expiringdict==1.1.4
+filelock==3.0.12
+funcsigs==1.0.2
+idna==2.7
+ipython==7.5.0
+ipython-genutils==0.2.0
+jedi==0.13.3
+jmespath==0.9.4
+more-itertools==5.0.0
+numpy==1.13.3
+pandas==0.23.4
+parso==0.4.0
+pathlib2==2.3.3
+pexpect==4.7.0
+pickleshare==0.7.5
+pluggy==0.9.0
+prompt-toolkit==2.0.9
+protobuf==3.8.0rc1
+ptyprocess==0.6.0
+py==1.8.0
+py4j==0.10.7
+Pygments==2.4.2
+pyspark==2.4.3
+pyspark-hyperloglog==2.1.1
+pytest==4.4.1
+pytest-cov==2.7.1
+pytest-timeout==1.3.3
+python-dateutil==2.8.0
+python-moztelemetry==0.10.2
+python-snappy==0.5.4
+pytz==2019.1
+PyYAML==5.1
+requests==2.20.1
+requests-toolbelt==0.8.0
+s3transfer==0.1.13
+scandir==1.10.0
+scipy==1.0.0rc1
+six==1.11.0
+toml==0.10.0
+tox==3.12.1
+traitlets==4.3.2
+typing==3.6.4
+ujson==1.35
+urllib3==1.24.3
+virtualenv==16.6.0
+wcwidth==0.1.7