One liner gemini

Dockerfile

FROM ubuntu:16.04

# install java 8 and other tools
RUN apt-get update && apt-get install -y --no-install-recommends default-jdk curl git && \
    rm -rf /var/lib/apt/lists/* && \
# needed to install cassandra
    apt-get install -y --no-install-recommends curl && \
    echo "deb http://www.apache.org/dist/cassandra/debian 311x main" >> /etc/apt/sources.list.d/cassandra.sources.list && \
    curl https://www.apache.org/dist/cassandra/KEYS | apt-key add - && \
    apt-key adv --keyserver pool.sks-keyservers.net --recv-key A278B781FE4B2BDA && \
    apt-get update && apt-get install -y --no-install-recommends cassandra && \
# install gemini
    apt-get install -y --no-install-recommends git && \
    git clone https://github.com/src-d/gemini.git && \
    cd /gemini && ./sbt assembly && ./sbt package && \
# install spark (needs to be 2.2.0)
    apt-get install -y --no-install-recommends curl && \
    curl http://www.trieuvan.com/apache/spark/spark-2.2.0/spark-2.2.0-bin-hadoop2.7.tgz > /spark.tgz && \
    mkdir -p /spark && tar -xvzf /spark.tgz -C /spark --strip-components=1 && rm -f /spark.tgz && \
    apt-get remove git curl && rm -rf /var/lib/apt/lists/*

ENV SPARK_HOME=/spark
ADD startup.sh /
RUN chmod +x /startup.sh
CMD ["/startup.sh"]

startup.sh

#! /bin/bash

# start cassandra as root (not recommended, but YOLO)
# logs available in /var/log/cassandra
cassandra -R &> /dev/null

# sleeping until cassandra is up

until cqlsh -e "describe tables;" &> /dev/null
do
  echo "waiting for cassandra, sleeping for 5 seconds"
  sleep 5
done

# start hashing
cd gemini && /gemini/hash -h localhost /repositories

# finish reporting all duplicates across all repositories
/gemini/report