Full refactor

12 files changed, 255 insertions, 165 deletions

diff --git a/.dockerignore b/.dockerignore
deleted file mode 100644
index 40a87fe..0000000
--- a/.dockerignore
+++ /dev/null
@@ -1,9 +0,0 @@
-*.swp
-*.zip
-.dockerignore
-.git
-.gitignore
-.travis.yml
-Makefile
-ngrams
-readme.md
diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
index 3fddc7e..a8a47ef 100644
--- a/.github/workflows/main.yml
+++ b/.github/workflows/main.yml
@@ -1,51 +1,40 @@
 
-name: Release for silvio/docker-languagetool
-
+name: Build
 on:
   push:
-    tags:
-      - '[0-9]+.[0-9]+'
-      - '[0-9]+.[0-9]+.[0-9]+'
-      - '[0-9]+.[0-9]+-update[0-9]+'
-      - '[0-9]+.[0-9]+.[0-9]+-update[0-9]+'
+    branches: [ master ]
+  schedule:
+    - cron: '5 4 * * *'
+  workflow_dispatch:
 
 jobs:
-  docker:
+  build:
     runs-on: ubuntu-latest
     steps:
-      - name: Checkout
-        uses: actions/checkout@v2
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v1
-
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v1
-
-      - name: Set environment variables
-        run: |
-          make envout >> ${GITHUB_ENV}
-
-      - name: Prepare system
-        run: |
-          make prepare
-
-      - name: Build Docker image
-        run: |
-          make build
+      - uses: actions/checkout@v2
+      - run: |
+          make docker-test
 
-      - name: Run tests
-        run: |
-          make test
-
-      - name: Login Docker
-        uses: docker/login-action@v1
+  push:
+    runs-on: ubuntu-latest
+    needs: [ build ]
+    permissions:
+      packages: write
+      contents: read
+    steps:
+      - uses: actions/checkout@v2
         with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_PASSWORD }}
+          fetch-depth: 0
 
-      - name: Push tag
-        run: |
-          make tag
+      - uses: docker/login-action@v1
+        env:
+          GITHUB_USER: ${{ github.actor }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          registry: ghcr.io
+          username: $GITHUB_USER
+          password: ${{ secrets.GITHUB_TOKEN }}
 
+      - run: |
+          make docker-push \
+            DOCKER_EXTRA_ARGS="-v ${HOME}/.docker:/root/.docker"
diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
index de95a7f..63c8c1b 100644
--- a/.github/workflows/test.yml
+++ b/.github/workflows/test.yml
@@ -1,36 +1,18 @@
 
-name: Test for silviof/docker-languagetool
+name: Test
 
 on:
+  push:
+    branches: [ master ]
   pull_request:
+    branches: [ master ]
   workflow_dispatch:
 
 jobs:
   build:
     runs-on: ubuntu-latest
     steps:
-      - name: Checkout
-        uses: actions/checkout@v2
+      - uses: actions/checkout@v2
 
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v1
-
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v1
-
-      - name: Set environment variables
-        run: |
-          make envout >> ${GITHUB_ENV}
-
-      - name: Prepare system
-        run: |
-          make prepare
-
-      - name: Build Docker image
-        run: |
-          make build
-
-      - name: Run tests
-        run: |
-          make test
+      - run: |
+          make docker-test
diff --git a/.github/workflows/trivy.yml b/.github/workflows/trivy.yml
new file mode 100644
index 0000000..ce25513
--- /dev/null
+++ b/.github/workflows/trivy.yml
@@ -0,0 +1,38 @@
+name: Trivy
+
+on:
+  workflow_dispatch:
+  push:
+    branches: [ master ]
+  pull_request:
+    branches: [ master ]
+  schedule:
+    - cron: '28 15 * * 3'
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+    permissions:
+      contents: read
+      security-events: write
+    runs-on: "ubuntu-18.04"
+    steps:
+      - uses: actions/checkout@v2
+
+      - run: |
+          docker build -t docker.io/my-organization/my-app:${{ github.sha }} .
+
+      - uses: aquasecurity/trivy-action@2a2157eb22c08c9a1fac99263430307b8d1bc7a2
+        with:
+          image-ref: 'docker.io/my-organization/my-app:${{ github.sha }}'
+          format: 'template'
+          template: '@/contrib/sarif.tpl'
+          output: 'trivy-results.sarif'
+          severity: 'CRITICAL,HIGH'
+          ignore-unfixed: true
+
+      - uses: github/codeql-action/upload-sarif@v1
+        with:
+          sarif_file: 'trivy-results.sarif'
diff --git a/.gitignore b/.gitignore
deleted file mode 100644
index 32b1038..0000000
--- a/.gitignore
+++ /dev/null
@@ -1 +0,0 @@
-ngrams
diff --git a/Dockerfile b/Dockerfile
index 98473cf..58f5b7a 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -1,19 +1,20 @@
-FROM openjdk:16-slim-buster
+FROM openjdk:slim
 
-# see Makefile.version
-ARG VERSION
+ARG VERSION=5.6
 
-MAINTAINER Silvio Fricke <silvio.fricke@gmail.com>
+RUN apt-get update && \
+    apt-get install -y \
+        curl \
+        libarchive-tools && \
+    rm -rf /var/lib/apt/lists/*
 
-RUN apt-get update && apt-get install -y wget unzip && rm -rf /var/lib/apt/lists/*
+RUN curl --progress-bar "https://languagetool.org/download/LanguageTool-$VERSION.zip" |\
+    bsdtar -x -f -
 
-RUN wget https://www.languagetool.org/download/LanguageTool-$VERSION.zip && \
-    unzip LanguageTool-$VERSION.zip && \
-    rm LanguageTool-$VERSION.zip
+ADD misc/init.sh /init.sh
+ADD misc/ngram.sh /ngram.sh
 
 WORKDIR /LanguageTool-$VERSION
-
-ADD misc/start.sh /start.sh
-CMD [ "sh", "/start.sh" ]
+CMD [ "sh", "/init.sh" ]
 USER nobody
 EXPOSE 8010
diff --git a/Makefile b/Makefile
index e8c9d31..51613f4 100644
--- a/Makefile
+++ b/Makefile
@@ -1,65 +1,91 @@
 
-include Makefile.version
+LANGUAGETOOL_VERSION := 5.6
+TRIVY_VERSION := 0.24.2
 
-envout:
-	@echo "VERSION=$(VERSION)"
-	@echo "BUILDARG_VERSION=$(BUILDARG_VERSION)"
-	@echo "IMAGENAME=$(IMAGENAME)"
-	@echo "BUILDARG_PLATFORM=$(BUILDARG_PLATFORM)"
+BUILDARG_VERSION := --build-arg VERSION=$(LANGUAGETOOL_VERSION)
+IMAGENAME := ghcr.io/someone-stole-my-name/docker-languagetool
+BUILDARG_PLATFORM := --platform linux/amd64,linux/arm64/v8
+DOCKER_EXTRA_ARGS := 
 
-prepare:
-	sudo apt-get -qq -y install curl
+ci-deps:
+	apt-get -qq -y install \
+		binfmt-support \
+		ca-certificates \
+		curl \
+		git \
+		gnupg \
+		lsb-release \
+		qemu-user-static \
+		wget \
+		jq
 
-build:
+ci-deps-docker:
+	curl -fsSL https://download.docker.com/linux/debian/gpg | gpg --dearmor -o /usr/share/keyrings/docker-archive-keyring.gpg && \
+	echo "deb [arch=$(shell dpkg --print-architecture) signed-by=/usr/share/keyrings/docker-archive-keyring.gpg] https://download.docker.com/linux/debian $(shell lsb_release -cs) stable" |\
+	tee /etc/apt/sources.list.d/docker.list > /dev/null && \
+	cat /etc/apt/sources.list.d/docker.list && \
+	apt-get update && \
+	apt-get -qq -y install \
+		docker-ce \
+		docker-ce-cli \
+		containerd.io
+
+ci-deps-trivy:
+	wget https://github.com/aquasecurity/trivy/releases/download/v$(TRIVY_VERSION)/trivy_$(TRIVY_VERSION)_Linux-64bit.deb && \
+	dpkg -i trivy_$(TRIVY_VERSION)_Linux-64bit.deb
+
+ci-setup-buildx:
+	docker run --privileged --rm tonistiigi/binfmt --install all
+	docker buildx create --name mybuilder
+	docker buildx use mybuilder
+
+ci-prepare: ci-deps ci-deps-docker ci-deps-trivy ci-setup-buildx
+
+build: ci-prepare
 	docker buildx build $(BUILDARG_VERSION) $(BUILDARG_PLATFORM) -t $(IMAGENAME):latest .
 	docker buildx build $(BUILDARG_VERSION) --load -t $(IMAGENAME):latest .
 
-test: test-cleanup.1
-test: TESTIPADDRESS=$(subst ",,$(shell docker inspect languagetool | jq '.[0].NetworkSettings.IPAddress'))
-test: test-print-ip-address
-test: test-start
-test: test-run-test-lang
-test: test-run-test-en
-test: test-run-test-fr
-test: test-cleanup.2
+push: ci-prepare
+	docker buildx build $(BUILDARG_VERSION) $(BUILDARG_PLATFORM) -t $(IMAGENAME):latest . --push
+	docker buildx build $(BUILDARG_VERSION) $(BUILDARG_PLATFORM) -t $(IMAGENAME):$(shell git describe --tags --abbrev=0) . --push
+
+trivy:
+	trivy i \
+		--ignore-unfixed \
+		--exit-code 1 \
+		$(IMAGENAME):latest
 
-test-start:
-	docker run -d --name languagetool -p 8010:8010 $(IMAGENAME):latest
-	sleep 3
+test: build trivy test-int
 
-test-print-ip-address:
-	@echo "IP address of languagetools docker container: $(TESTIPADDRESS)"
+test-int-start:
+	docker kill languagetool || true
+	docker rm languagetool || true
+	docker run --rm -d --name languagetool -p 8010:8010 $(IMAGENAME):latest
 
-test-run-test-lang:
+test-int-run: IP=$(subst ",,$(shell docker inspect languagetool | jq '.[0].NetworkSettings.IPAddress'))
+test-int-run:
+	timeout 60 sh -c 'until (curl -i $(IP):8010/v2/info | grep "200 OK") do sleep 1; done'
 	curl \
 		-X GET \
 		--header 'Accept: application/json' \
-		'http://$(TESTIPADDRESS):8010/v2/languages'
-
-test-run-test-en:
+		--fail \
+		'http://$(IP):8010/v2/languages'
 	curl \
 		-X POST \
 		--header 'Content-Type: application/x-www-form-urlencoded' \
 		--header 'Accept: application/json' \
+		--fail \
 		-d 'text=hello%20woorld&language=en-US&motherTongue=de-DE&enabledOnly=false' \
-		'http://$(TESTIPADDRESS):8010/v2/check'
+		'http://$(IP):8010/v2/check'
 
-test-run-test-fr:
-	curl -X POST \
-		--header 'Content-Type: application/x-www-form-urlencoded' \
-		--header 'Accept: application/json' \
-		-d 'text=hello%20woorld&language=fr&motherTongue=de-DE&enabledOnly=false' \
-		'http://$(TESTIPADDRESS):8010/v2/check'
 
-.PHONY: test-cleanup
-test-cleanup.%:
-	-docker stop languagetool
-	-docker rm languagetool
+test-int: test-int-start test-int-run
 
-.PHONY: tag
-tag: tag-push
-
-.PHONY: tag-push
-tag-push:
-	docker buildx build $(BUILDARG_VERSION) $(BUILDARG_PLATFORM) -t $(IMAGENAME):latest . --push
-	docker buildx build $(BUILDARG_VERSION) $(BUILDARG_PLATFORM) -t $(IMAGENAME):$(VERSION) . --push
+docker-%:
+	docker run \
+		--rm \
+		--privileged \
+		-v /var/run/docker.sock:/var/run/docker.sock \
+		-v $(shell pwd):/data \
+		-w /data $(DOCKER_EXTRA_ARGS) \
+		debian:stable sh -c "apt-get update && apt-get install make && make $*"
diff --git a/Makefile.version b/Makefile.version
deleted file mode 100644
index 2d4cbb0..0000000
--- a/Makefile.version
+++ /dev/null
@@ -1,4 +0,0 @@
-VERSION := 5.6
-BUILDARG_VERSION := --build-arg VERSION=$(VERSION)
-IMAGENAME := docker.io/silviof/docker-languagetool
-BUILDARG_PLATFORM := --platform linux/amd64,linux/arm64/v8
diff --git a/misc/init.sh b/misc/init.sh
new file mode 100644
index 0000000..5681037
--- /dev/null
+++ b/misc/init.sh
@@ -0,0 +1,13 @@
+#!/usr/bin/env bash
+
+EXTRAOPTIONS=${EXTRAOPTIONS:-}
+JAVAOPTIONS=${JAVAOPTIONS:-}
+
+if [ -d "/ngrams" ]; then
+    EXTRAOPTIONS="${EXTRAOPTIONS} --languageModel /ngrams"
+    if [ ! -z ${NGRAM_LANGUAGES+x} ]; then
+        bash /ngram.sh "${NGRAM_LANGUAGES}" "/ngrams"
+    fi
+fi
+
+java ${JAVAOPTIONS} -cp languagetool-server.jar org.languagetool.server.HTTPServer --port 8010 --public --allow-origin '*' ${EXTRAOPTIONS}
diff --git a/misc/ngram.sh b/misc/ngram.sh
new file mode 100755
index 0000000..ce25a49
--- /dev/null
+++ b/misc/ngram.sh
@@ -0,0 +1,59 @@
+#!/usr/bin/env bash
+
+set -euo pipefail
+
+NGRAM_DATA_URL="https://languagetool.org/download/ngram-data/"
+NGRAM_ARCHIVES=$(curl -sS "${NGRAM_DATA_URL}" | grep "\.zip" | grep -oP 'ngrams-\w\w-\d+\.zip' | sort | uniq)
+
+TARGET_LANGS="${1}"
+TARGET_DIR="${2}"
+
+download_ngram() {
+  local lang=$1
+  local version=$2
+  local directory=$3
+
+  echo "Downloading: ${lang} - ${version}"
+  rm -rf "${directory}/${lang}"
+  curl --progress-bar "${NGRAM_DATA_URL}ngrams-${lang}-${version}.zip" |\
+    bsdtar -x -f - -C "${directory}"
+}
+
+
+VERSION_FILE_CONTENT=
+
+if test -f "${TARGET_DIR}/version"; then
+  VERSION_FILE_CONTENT=$(cat "${TARGET_DIR}/version")
+  >"${TARGET_DIR}/version"
+fi
+
+while read -r ngram_archive; do
+  for lang in ${TARGET_LANGS/,/ }; do
+    if echo "$(echo ${ngram_archive} | cut -d'-' -f2)" | grep -q $lang; then
+      version=$(echo ${ngram_archive} | cut -d'-' -f3 | cut -d'.' -f1)
+      if echo "${VERSION_FILE_CONTENT}" | grep -q "$lang"; then
+        existing_version=$(echo "${VERSION_FILE_CONTENT}" | grep "${lang}" | cut -d':' -f2)
+        current_version=$(echo "${ngram_archive}" | cut -d'-' -f3 | cut -d'.' -f1)
+        if [[ "${existing_version}" -lt "${current_version}" ]]; then
+          download_ngram "${lang}" "${version}" "${TARGET_DIR}"
+        fi
+      else
+        download_ngram "${lang}" "${version}" "${TARGET_DIR}"
+      fi
+      echo "${lang}:${version}" >> "${TARGET_DIR}/version"
+    fi
+  done
+done <<< "${NGRAM_ARCHIVES}"
+
+for i in $(ls -d "${TARGET_DIR}"/*/); do
+  realdir="$(basename ${i})"
+  delete=yes
+  for lang in ${TARGET_LANGS/,/ }; do
+    if echo "${realdir}" | grep -q "${lang}"; then
+      delete=no
+    fi
+  done
+  if [ "${delete}" == "yes" ]; then
+    rm -rf "${TARGET_DIR}/${realdir}"
+  fi
+done
diff --git a/misc/start.sh b/misc/start.sh
deleted file mode 100644
index f550f08..0000000
--- a/misc/start.sh
+++ /dev/null
@@ -1,6 +0,0 @@
-#!/bin/bash
-
-EXTRAOPTIONS=""
-[ -d "/ngrams" ] && EXTRAOPTIONS=" --languageModel /ngrams "
-
-java -cp languagetool-server.jar  org.languagetool.server.HTTPServer --port 8010 --public --allow-origin '*' ${EXTRAOPTIONS}
diff --git a/readme.md b/readme.md
index 843159f..60885f0 100644
--- a/readme.md
+++ b/readme.md
@@ -1,59 +1,61 @@
+[![Publish](https://github.com/someone-stole-my-name/docker-languagetool/actions/workflows/main.yml/badge.svg?branch=master)](https://github.com/someone-stole-my-name/docker-languagetool/actions/workflows/main.yml) [![Test](https://github.com/someone-stole-my-name/docker-languagetool/actions/workflows/test.yml/badge.svg)](https://github.com/someone-stole-my-name/docker-languagetool/actions/workflows/test.yml) [![trivy](https://github.com/someone-stole-my-name/docker-languagetool/actions/workflows/trivy.yml/badge.svg?branch=master)](https://github.com/someone-stole-my-name/docker-languagetool/actions/workflows/trivy.yml)
 
 # Introduction
 
 [LanguageTool] is an Open Source proof­reading software for English, French,
 German, Polish, and more than 20 other languages.
 
-You can use the LanguageTools with a [firefox-plugin].
+You can use LanguageTool with a [Firefox extension].
 
-This is a Dockerfile to get the languagetools running on a system without java.
+This is a container to get the LanguageTool running on a system without java.
 
 [LanguageTool]: https://www.languagetool.org/
-[firefox-plugin]: https://addons.mozilla.org/firefox/addon/languagetool
+[Firefox extension]: https://addons.mozilla.org/firefox/addon/languagetool
 
 # Usage
 
 The Server is running on port 8010, this port should exposed.
 
-    $ docker pull silviof/docker-languagetool
+    docker pull ghcr.io/someone-stole-my-name/docker-languagetool
     [...]
-    $ docker run --rm -p 8010:8010 silviof/docker-languagetool
+    docker run --rm -p 8010:8010 ghcr.io/someone-stole-my-name/docker-languagetool
 
-Or you run it in background via `-d`-option.
+Or you run it in background via `-d` option.
 
 Run with no minimum rights and RAM
-```
-docker run --name languagetool \
-                        --cap-drop=ALL \
-                        --user=65534:65534 \
-                        --read-only \
-                        --mount type=bind,src=/tmp/languagetool/tmp,dst=/tmp \
-                        -p 127.0.0.1:8010:8010 \
-                        --memory 412m --memory-swap 500m \
-                        -e EXTRAOPTIONS="-Xmx382M" \
-                        silviof/docker-languagetool:latest
-```
+
+    docker run --name languagetool \
+        --cap-drop=ALL \
+        --user=65534:65534 \
+        --read-only \
+        --mount type=bind,src=/tmp/languagetool/tmp,dst=/tmp \
+        -p 127.0.0.1:8010:8010 \
+        --memory 412m --memory-swap 500m \
+        -e JAVAOPTIONS="-Xmx382M" \
+        ghcr.io/someone-stole-my-name/docker-languagetool:latest
+
 
 Route information can be found at https://languagetool.org/http-api/swagger-ui/#/default, an easy route to test that it's running is `/v2/languages`.
 
 ## ngram support
 
 To support [ngrams] you need an additional volume or directory mounted to the
-`/ngrams` directory. For that add a `-v` to the `docker run`-command.
+`/ngrams` directory. For that add a `-v` to the `docker run` command.
 
-    docker run ... -v /path/to/ngrams:/ngrams ...
+    docker run ... -v /foo:/ngrams ...
 
 [ngrams]: http://wiki.languagetool.org/finding-errors-using-n-gram-data
-
+### Manual
 
 Download English ngrams with the commands:
 
     mkdir ngrams
-    wget https://languagetool.org/download/ngram-data/ngrams-en-20150817.zip
-    (cd ngrams && unzip ../ngrams-en-20150817.zip)
-    rm -f ngrams-en-20150817.zip
+    wget https://languagetool.org/download/ngram-data/ngrams-en-YYYYMMDD.zip
+    (cd ngrams && unzip ../ngrams-en-YYYYMMDD.zip)
+    rm -f ngrams-en-YYYYMMDD.zip
 
+### Automatically
 
-One can use them using web browser plugin "Local server (localhost)" setting by running:
+Mount a directory or volume to `/ngrams` and use the `NGRAM_LANGUAGES` variable to pass a comma separated string with languages:
 
-    docker run -d --name languagetool -p 127.0.0.1:8081:8010 -v `pwd`/ngrams:/ngrams:ro --restart=unless-stopped silviof/docker-languagetool
+    docker run ... -v /path/to/ngrams:/ngrams -e NGRAM_LANGUAGES="en,es" ...