Dockerfiles for automated build

2.6rc1/Dockerfile

@@ -0,0 +1,20 @@
+FROM java:8-jre-alpine
+MAINTAINER felixlohmeier <felixlohmeier@opencultureconsulting.de>
+# OpenRefine 2.6 Release Candidate 1
+# derived from docker image vimagick/openrefine for personal use
+
+ENV OR_URL https://github.com/OpenRefine/OpenRefine/releases/download/v2.6-rc1/openrefine-linux-2.6-rc1.tar.gz
+
+WORKDIR /app
+
+RUN set -xe \
+    && apk add --no-cache bash curl jq tar \
+    && curl -sSL ${OR_URL} | tar xz --strip 1
+
+VOLUME /data
+WORKDIR /data
+
+EXPOSE 3333
+
+ENTRYPOINT ["/app/refine"]
+CMD ["-i", "0.0.0.0", "-d", "/data"]

2.6rc2/Dockerfile

@@ -0,0 +1,20 @@
+FROM java:8-jre-alpine
+MAINTAINER felixlohmeier <felixlohmeier@opencultureconsulting.de>
+# OpenRefine 2.6 Release Candidate 2
+# derived from docker image vimagick/openrefine for personal use
+
+ENV OR_URL https://github.com/OpenRefine/OpenRefine/releases/download/2.6-rc.2/openrefine-linux-2.6-rc.2.tar.gz
+
+WORKDIR /app
+
+RUN set -xe \
+    && apk add --no-cache bash curl jq tar \
+    && curl -sSL ${OR_URL} | tar xz --strip 1
+
+VOLUME /data
+WORKDIR /data
+
+EXPOSE 3333
+
+ENTRYPOINT ["/app/refine"]
+CMD ["-i", "0.0.0.0", "-d", "/data"]

Dockerfile

@@ -0,0 +1,26 @@
+FROM ubuntu:trusty
+MAINTAINER felixlohmeier <felixlohmeier@opencultureconsulting.de>
+# OpenRefine 2.6 Development Version
+# derived from docker image psychemedia/openrefine for personal use
+
+# Install JDK after updating installed packages.
+RUN apt-get update && apt-get install -y wget ant unzip openjdk-7-jdk && apt-get clean
+
+WORKDIR /app
+
+#Build OpenRefine
+RUN wget --no-check-certificate https://github.com/OpenRefine/OpenRefine/archive/master.zip
+RUN unzip master.zip  && rm master.zip
+RUN OpenRefine-master/refine build
+
+#Tidy up
+RUN apt-get remove -y openjdk-7-jdk
+RUN apt-get install openjdk-7-jre-headless
+
+VOLUME /data
+WORKDIR /data
+
+EXPOSE 3333
+
+ENTRYPOINT ["/app/OpenRefine-master/refine"]
+CMD ["-i", "0.0.0.0", "-d", "/data"]

README.md

@@ -1,2 +1,39 @@
-# openrefine-docker
+# OpenRefine-docker
- OpenRefine is a free, open source power tool for working with messy data and improving it. This repository contains Dockerbuild files.
+[OpenRefine](http://openrefine.org/) is a free, open source power tool for working with messy data and improving it. These docker images are automatically build from released versions (2.6rc1, 2.6rc2) or from the official GitHub Repository (latest).
+
+GitHub Repository with Docker 
+
+These docker images are inspired by docker image [vimagick/openrefine](https://hub.docker.com/r/vimagick/openrefine/) and [psychemedia/openrefine](https://hub.docker.com/r/psychemedia/openrefine/).
+
+### versions
+cf. [OpenRefine Releases](https://github.com/OpenRefine/OpenRefine/releases)
+
+OpenRefine 2.6 Release Candidate 2 (2015-10-14) from java:8-jre-alpine **[2.6rc2]**
+> docker pull felixlohmeier/openrefine:2.6rc2
+
+OpenRefine 2.6 Release Candidate 1 (2015-04-30) from java:8-jre-alpine **[2.6rc1]**
+> docker pull felixlohmeier/openrefine:2.6rc1
+
+OpenRefine Development Version (automated build) from ubuntu:trusty + jdk **[latest]**
+> docker pull felixlohmeier/openrefine
+
+### usage
+> docker run -p 80:3333 felixlohmeier/openrefine:2.6rc2
+
+point your browser on host machine to http://localhost or point browser on any machine within your network to http://<ip address of host machine>
+
+### example for customized run command
+
+```docker run --rm -p 80:3333 -v /home/felix/refine:/data:z felixlohmeier/openrefine -i 0.0.0.0 -m 4G -d /data```
+
+* automatically remove docker container when it exits
+* publish internal port 3333 to host port 80
+* mount host directory /home/felix/refine as working directory
+* make openrefine available in the network
+* increase java heap size to 4 GB
+* set refine workspace to /data
+* set refine workspace to /data
+
+### batch processing with python client
+
+see https://hub.docker.com/r/felixlohmeier/openrefine-client/

client-py/Dockerfile

@@ -0,0 +1,31 @@
+FROM alpine:latest
+MAINTAINER felixlohmeier <felixlohmeier@opencultureconsulting.de>
+# Client for batch processing with OpenRefine: https://github.com/PaulMakepeace/refine-client-py/
+# expects an OpenRefine container running with --name=refine-server
+
+# Install python, pip, wget, unzip and bash
+RUN apk add --no-cache \
+	bash \
+	python \
+	py-pip \
+	wget \
+	unzip
+
+# Install dependency urllib2_file
+RUN pip install urllib2_file==0.2.1
+
+# Download and build refine-client-py
+WORKDIR /app
+RUN wget --no-check-certificate https://github.com/PaulMakepeace/refine-client-py/archive/master.zip
+RUN unzip master.zip && rm master.zip
+RUN python refine-client-py-master/setup.py build
+RUN python refine-client-py-master/setup.py install
+
+# Change docker WORKDIR (shall be mounted)
+WORKDIR /data
+
+# Execute refine.py with option host = refine-server
+ENTRYPOINT ["/app/refine-client-py-master/refine.py", "-H", "refine-server"]
+
+# Default command: list projects
+CMD ["-l"]