Last active
August 31, 2021 09:19
-
-
Save neuged/8fad98c6833bcb3e982c94db5054fef9 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| ## | |
| # Dockerfile that downloads Heideltime and a TreeTagger dependendency | |
| # | |
| # - https://github.com/HeidelTime/heideltime | |
| # - https://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger | |
| # | |
| # on a Ubuntu 18.04, and builds/configures them together. | |
| # | |
| # Before using this, be sure to review the TreeTagger and Heideltime Licenses, | |
| # as they are not the most permissive ones. | |
| # | |
| # - https://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/Tagger-Licence | |
| # - https://github.com/HeidelTime/heideltime/blob/master/COPYING | |
| ## | |
| FROM ubuntu:18.04 | |
| # install dependencies | |
| RUN apt-get update && apt-get -y install \ | |
| openjdk-8-jdk \ | |
| git \ | |
| maven \ | |
| wget | |
| # Download and install the tree tagger | |
| # NOTE: Downloads english and german parameter files for the tree tagger, more language options at: | |
| # https://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/#parfiles | |
| WORKDIR /srv/app/treetagger | |
| RUN wget https://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/data/tree-tagger-linux-3.2.2.tar.gz | |
| RUN wget https://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/data/tagger-scripts.tar.gz | |
| RUN wget https://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/data/install-tagger.sh | |
| RUN wget https://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/data/english.par.gz | |
| RUN wget https://www.cis.uni-muenchen.de/~schmid/tools/TreeTagger/data/german.par.gz | |
| RUN sh install-tagger.sh | |
| # Clone heideltime itself and set up the location of the tagger in a new config file | |
| WORKDIR /srv/app | |
| RUN git clone https://github.com/HeidelTime/heideltime.git | |
| RUN cp heideltime/conf/config.props . | |
| RUN sed -i 's|^treeTaggerHome =.*$|treeTaggerHome = /srv/app/treetagger|g' config.props | |
| # Build heideltime | |
| # NOTE: This modifies the pom.xml to include dependencies in the standalone jar. | |
| WORKDIR /srv/app/heideltime | |
| ENV JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64/ | |
| RUN sed -i 's|<scope>provided</scope>||g' pom.xml | |
| RUN mvn clean package | |
| # Expose the "java -jar ..." with our config as a simpler "heideltime" command | |
| RUN echo '#!/bin/bash \n\ | |
| java -jar /srv/app/heideltime/target/de.unihd.dbs.heideltime.standalone.jar -c /srv/app/config.props "$@" \n\ | |
| ' > /bin/heideltime && chmod a+x /bin/heideltime | |
| # Do a test annotation | |
| RUN echo "Did we install heideltime today?" > /tmp/test.txt | |
| RUN heideltime -l english -t scientific -dct 1970-01-01 /tmp/test.txt | |
| # keep the container running when started | |
| CMD /bin/sleep infinity |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment