User based docker image (#7)

* Push image with user

* Update Dockerfile logic

* Extract checkpoint retrieval

.github/workflows/docker-test.yml

@@ -0,0 +1,92 @@
+name: DockerTest
+
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+on:
+    push:
+      branches: [ "*" ]
+
+env:
+  # Use docker.io for Docker Hub if empty
+  REGISTRY: ghcr.io
+  # github.repository as <account>/<repo>
+  IMAGE_NAME: ${{ github.repository }}
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+      # This is used to complete the identity challenge
+      # with sigstore/fulcio when running outside of PRs.
+      id-token: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+      # Install the cosign tool except on PR
+      # https://github.com/sigstore/cosign-installer
+      - name: Install cosign
+        if: github.event_name != 'pull_request'
+        uses: sigstore/cosign-installer@6e04d228eb30da1757ee4e1dd75a0ec73a653e06 #v3.1.1
+        with:
+          cosign-release: 'v2.1.1'
+
+      # Set up BuildKit Docker container builder to be able to build
+      # multi-platform images and export cache
+      # https://github.com/docker/setup-buildx-action
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@f95db51fddba0c2d1ec667646a06c2ce06100226 # v3.0.0
+
+      # Login against a Docker registry except on PR
+      # https://github.com/docker/login-action
+      - name: Log into registry ${{ env.REGISTRY }}
+        if: github.event_name != 'pull_request'
+        uses: docker/login-action@343f7c4344506bcbf9b4de18042ae17996df046d # v3.0.0
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      # Extract metadata (tags, labels) for Docker
+      # https://github.com/docker/metadata-action
+      - name: Extract Docker metadata
+        id: meta
+        uses: docker/metadata-action@96383f45573cb7f253c731d3b3ab81c87ef81934 # v5.0.0
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+
+      # Build and push Docker image with Buildx (don't push on PR)
+      # https://github.com/docker/build-push-action
+      - name: Build and push Docker image
+        id: build-and-push
+        uses: docker/build-push-action@0565240e2d4ab88bba5387d719585280857ece09 # v5.0.0
+        with:
+          context: .
+          #push: ${{ github.event_name != 'pull_request' }}
+          push: false
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+      # Sign the resulting Docker image digest except on PRs.
+      # This will only write to the public Rekor transparency log when the Docker
+      # repository is public to avoid leaking data.  If you would like to publish
+      # transparency data even for private images, pass --force to cosign below.
+      # https://github.com/sigstore/cosign
+      #- name: Sign the published Docker image
+      #  if: ${{ github.event_name != 'pull_request' }}
+      #  env:
+      #    # https://docs.github.com/en/actions/security-guides/security-hardening-for-github-actions#using-an-intermediate-environment-variable
+      #    TAGS: ${{ steps.meta.outputs.tags }}
+      #    DIGEST: ${{ steps.build-and-push.outputs.digest }}
+      #  # This step uses the identity token to provision an ephemeral certificate
+      #  # against the sigstore community Fulcio instance.
+      #  run: echo "${TAGS}" | xargs -I {} cosign sign --yes {}@${DIGEST}
+

Dockerfile

@@ -1,16 +1,27 @@
 # Use the slim base image
 FROM python:3.10-slim
 
+WORKDIR /home/appuser
+
 # Add relevant files
-ADD *.py /
-ADD *.sh /
-ADD requirements.txt /
-ADD Data /Data
-ADD MetadataExtractor /MetadataExtractor
+ADD *.py ./
+ADD *.sh ./
+ADD requirements.txt ./
+ADD Data ./Data
+ADD MetadataExtractor ./MetadataExtractor
 
 # Install dependencies and clean up in a single layer
 RUN chmod +x installDependencies.sh && chmod +x installDependenciesCleanup.sh \
     && ./installDependencies.sh && ./installDependenciesCleanup.sh
 
+# Create a new user 'appuser' and switch to it
+RUN useradd --create-home appuser
+RUN chown -R appuser:appuser /home/appuser
+
+# Switch to non-root user
+USER appuser
+
+RUN chmod +x getCheckpoints.sh && ./getCheckpoints.sh
+
 # Set the entry point
 CMD ["/bin/sh", "-c", "./run.sh"]

getCheckpoints.sh

@@ -0,0 +1,3 @@
+mkdir -p ~/.cache/torch/hub/checkpoints
+wget -O ~/.cache/torch/hub/checkpoints/yolo_nas_l_coco.pth https://sghub.deci.ai/models/yolo_nas_l_coco.pth
+wget -O ~/.cache/torch/hub/checkpoints/mobilenet_v3_small-047dcff4.pth https://download.pytorch.org/models/mobilenet_v3_small-047dcff4.pth

installDependencies.sh

@@ -1,9 +1,6 @@
-apt-get update \
-    && apt-get install -y --no-install-recommends git python3-opencv default-jre tesseract-ocr build-essential default-libmysqlclient-dev pkg-config wget libmagic1 libcairo2-dev \
-    && pip install --no-cache-dir --ignore-installed -r requirements.txt \
-    && python -c "import nltk; nltk.download('punkt')" \
-    && wget -O ./tika-server.jar https://archive.apache.org/dist/tika/2.7.0/tika-server-standard-2.7.0.jar \
-    && mkdir -p ~/.cache/torch/hub/checkpoints \
-    && wget -O ~/.cache/torch/hub/checkpoints/yolo_nas_l_coco.pth https://sghub.deci.ai/models/yolo_nas_l_coco.pth \
-    && wget -O ~/.cache/torch/hub/checkpoints/mobilenet_v3_small-047dcff4.pth https://download.pytorch.org/models/mobilenet_v3_small-047dcff4.pth \
-    && chmod +x run.sh
+apt-get update
+apt-get install -y --no-install-recommends git python3-opencv default-jre tesseract-ocr build-essential default-libmysqlclient-dev pkg-config wget libmagic1 libcairo2-dev
+pip install --no-cache-dir --ignore-installed -r requirements.txt
+python -c "import nltk; nltk.download('punkt')"
+wget -O ./tika-server.jar https://archive.apache.org/dist/tika/2.7.0/tika-server-standard-2.7.0.jar
+chmod +x run.sh

installDependenciesCleanup.sh

@@ -1,2 +1,2 @@
-apt-get remove -y --auto-remove git build-essential \
-    && rm -rf /var/lib/apt/lists/*
+apt-get remove -y --auto-remove git build-essential
+rm -rf /var/lib/apt/lists/*