Catch up versions, add CI

Author: chilland

.github/workflows/docker.yml

@@ -0,0 +1,18 @@
+name: Publish Docker image
+on:
+  release:
+    types: [published]
+jobs:
+  push_to_registry:
+    name: Push Docker image to Docker Hub
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out the repo
+        uses: actions/checkout@v2
+      - name: Push to Docker Hub
+        uses: docker/build-push-action@v1
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+          repository: chilland/corenlp
+          tag_with_ref: true

Dockerfile

@@ -3,11 +3,13 @@ FROM maven:alpine
 RUN apk add --update --no-cache \
         unzip wget
 
-RUN wget http://nlp.stanford.edu/software/stanford-corenlp-full-2018-02-27.zip
-RUN unzip stanford-corenlp-full-2018-02-27.zip && \
-        rm stanford-corenlp-full-2018-02-27.zip 
+ARG CORENLP_VERSION="4.2.0"
 
-WORKDIR stanford-corenlp-full-2018-02-27
+RUN wget http://nlp.stanford.edu/software/stanford-corenlp-${CORENLP_VERSION}.zip
+RUN unzip stanford-corenlp-${CORENLP_VERSION}.zip && \
+        rm stanford-corenlp-${CORENLP_VERSION}.zip 
+
+WORKDIR stanford-corenlp-${CORENLP_VERSION}
 
 RUN wget https://nlp.stanford.edu/software/stanford-srparser-2014-10-23-models.jar
 RUN mvn install:install-file -Dfile=stanford-srparser-2014-10-23-models.jar \
@@ -16,9 +18,6 @@ RUN mvn install:install-file -Dfile=stanford-srparser-2014-10-23-models.jar \
 
 RUN export CLASSPATH="`find . -name '*.jar'`"
 
-ENV PORT 9000
-
-EXPOSE $PORT
+EXPOSE 9000
 
-CMD java -cp "*" -mx4g edu.stanford.nlp.pipeline.StanfordCoreNLPServer -port \
-        $PORT -parse.model edu/stanford/nlp/models/srparser/englishSR.ser.gz
+CMD java -cp "*" -mx4g edu.stanford.nlp.pipeline.StanfordCoreNLPServer -parse.model edu/stanford/nlp/models/srparser/englishSR.ser.gz

README.md

@@ -5,10 +5,20 @@ Dockerfile for Stanford CoreNLP Server
 This Dockerfile builds the [Stanford CoreNLP
 Server](http://stanfordnlp.github.io/CoreNLP/corenlp-server.html) and
 shift-reduce parser. It exposes the endpoint on port 9000. Requests 
-are made as covered in the documentation.
+are made as covered in the documentation. Including the shift-reduce parser
+makes the image rather large (2.5gb+). You can specify the version you want to
+build via `--build-arg`.
 
 ## Build
 
 ```shell
-docker build -t corenlp:3.9.1 .
+docker build --build-arg CORENLP_VERSION=${CORENLP_VERSION} -t corenlp:${CORENLP_VERSION} .
+```
+
+## Run
+The container runs the server with some simple defaults and runs the jar with
+4gb of memory. The command can be overriden when you start the container. For
+example:
+```shell
+docker run -p 9000:9000 -d corenlp java -cp "*" -mx15g edu.stanford.nlp.pipeline.StanfordCoreNLPServer -parse.model edu/stanford/nlp/models/srparser/englishSR.ser.gz -preload tokenize,ssplit,pos,lemma,depparse,ner,kbp,relation,coref,quote,sentiment -quiet
 ```