Merge pull request #209 from freelawproject/uv

Move dependency management to uv, improve Docker setup

Author: albertisfu

.dockerignore

@@ -0,0 +1,2 @@
+.git
+.venv

.github/workflows/deploy.yml

@@ -16,9 +16,9 @@ jobs:
     if: (github.event_name == 'pull_request' && github.event.pull_request.merged == true)
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - name: Login to Docker Hub
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}
@@ -30,12 +30,12 @@ jobs:
     needs: build
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
     - name: Set shortcode
       id: vars
       run: echo "::set-output name=sha_short::$(git rev-parse --short HEAD)"
     - name: Configure AWS credentials
-      uses: aws-actions/configure-aws-credentials@v1
+      uses: aws-actions/configure-aws-credentials@v4
       with:
         aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
         aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}

.github/workflows/lint.yml

@@ -10,8 +10,8 @@ jobs:
   pre-commit:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2-beta
-      - uses: actions/setup-python@v2
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
         with:
           python-version: "3.10"
-      - uses: pre-commit/[email protected].0
+      - uses: pre-commit/[email protected].1

.github/workflows/tests.yml

@@ -9,15 +9,8 @@ on:
 jobs:
   build:
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version: ["3.10", "3.11", "3.12"]
     steps:
-    - uses: actions/checkout@v2
-    - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v1
-      with:
-        python-version: ${{ matrix.python-version }}
+    - uses: actions/checkout@v4
 
     - name: Create the .env settings file
       run: cp .env.example .env.dev
@@ -27,7 +20,7 @@ jobs:
         echo 'DEBUG=on' >> .env.dev
 
     - name: Build Image
-      run: docker compose -f docker-compose.dev.yml up --build -d
+      run: docker compose up --build -d
 
     - name: Run tests
-      run: docker exec mock_web_app python3 -m unittest doctor.tests
+      run: docker compose exec doctor python -m unittest

.gitignore

@@ -81,9 +81,6 @@ target/
 profile_default/
 ipython_config.py
 
-# pyenv
-.python-version
-
 # pipenv
 #   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
 #   However, in case of collaboration, if having platform-specific dependencies or dependencies

DEVELOPING.md

@@ -5,11 +5,11 @@ application that calls to this service.
 
 To build the microservice and start it up, run:
 
-    docker compose -f docker-compose.dev.yml up --build -d
+    docker compose up --build -d
 
 To see logs:
 
-    docker compose -f docker-compose.dev.yml logs -f
+    docker compose logs -f
 
 If you want to see debug logs, set `DEBUG` to `True` in `settings.py`.
 

README.md

@@ -333,7 +333,7 @@ This returns the audio file as a file response.
 
 ## Testing
 
-Testing is designed to be run with the `docker-compose.dev.yml` file.  To see more about testing
+Testing is designed to be run with the `compose.yaml` file.  To see more about testing
 checkout the DEVELOPING.md file.
 
 ## Sentry Logging

docker-compose.dev.yml renamed to compose.yaml

@@ -7,16 +7,8 @@ services:
       args:
         options: --reload
     image: freelawproject/doctor:latest
-
-
-
-  mock_web_app:
-    container_name: mock_web_app
-    image: freelawproject/doctor:latest
-    depends_on:
-      - doctor
     ports:
-      - "5050:5050"
+      - 5050:5050
     volumes:
       - .:/opt/app
     env_file:

docker/Dockerfile

@@ -1,24 +1,46 @@
 # Note: Force M1 to emulate amd64
-FROM --platform=linux/amd64 python:3.10-slim
+FROM --platform=linux/amd64 python:3.10
 
-RUN apt-get update --option "Acquire::Retries=3" --quiet=2 && \
+# Install uv
+# https://docs.astral.sh/uv/guides/integration/docker/#installing-uv
+COPY --from=ghcr.io/astral-sh/uv:0.7 /uv /uvx /bin/
+
+# Install apt dependencies
+# caching: https://docs.docker.com/build/cache/optimize/#use-cache-mounts
+RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
+    --mount=type=cache,target=/var/lib/apt,sharing=locked \
+    apt-get update --option "Acquire::Retries=3" --quiet=2 && \
     apt-get install -y --no-install-recommends apt-utils && \
-    apt-get install -y python3-pip poppler-utils curl \
-    libleptonica-dev tesseract-ocr libtesseract-dev \
-    g++ libz-dev libjpeg-dev build-essential qpdf && \
+    apt-get install -y \
+        build-essential \
+        curl \
+        libjpeg-dev \
+        libleptonica-dev \
+        libtesseract-dev \
+        libz-dev \
+        poppler-utils \
+        qpdf \
+        tesseract-ocr \
+        && \
     apt-get install \
         --option "Acquire::Retries=3" \
         --no-install-recommends \
         --assume-yes \
         --quiet=2 \
         `# Document extraction and OCR tools` \
-        antiword docx2txt ghostscript libwpd-tools \
+        antiword \
+        docx2txt \
+        ghostscript \
+        libwpd-tools \
         `# Audio extraction/manipulation tools` \
-         ffmpeg libmagic1 \
+        ffmpeg \
+        libmagic1 \
         `# Image & OCR tools` \
         imagemagick \
         `# Other dependencies` \
-        libffi-dev libxml2-dev libxslt-dev
+        libffi-dev \
+        libxml2-dev \
+        libxslt-dev
 
 # set environment variables
 ENV PYTHONDONTWRITEBYTECODE=1 \
@@ -27,12 +49,19 @@ ENV PYTHONDONTWRITEBYTECODE=1 \
     # faster overall performance
     OMP_THREAD_LIMIT=1
 
-COPY requirements.txt .
-RUN pip install -r requirements.txt
+WORKDIR /code
+
+# Install Python dependencies
+COPY pyproject.toml uv.lock .
+# https://docs.astral.sh/uv/guides/integration/docker/#caching
+ENV UV_COMPILE_BYTECODE=1 \
+    UV_LINK_MODE=copy \
+    UV_PROJECT_ENVIRONMENT=/venv \
+    PATH="/venv/bin:$PATH"
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync
 
-COPY doctor /opt/app/doctor
-COPY manage.py /opt/app/
-WORKDIR /opt/app
+COPY . .
 
 EXPOSE 5050
 

pyproject.toml

@@ -3,6 +3,40 @@ name = "doctor"
 version = "1"
 description = "CourtListener doctor"
 requires-python = ">=3.10"
+dependencies = [
+  "certifi",
+  "chardet>=3.0.4",
+  "django>=3.2,<4",
+  "django-environ>=0.8.1",
+  "eyed3",
+  "gunicorn==20.1",
+  "idna==2.10",
+  "img2pdf",
+  "lxml>=4.5.2",
+  "lxml-html-clean",
+  "numpy>=1.19.1",
+  "opencv-python>=4.2.0.32",
+  "pandas>=1.1.1",
+  "pdf2image>=1.7.1",
+  "pdfplumber",
+  "pillow>=8.0.1",
+  "pkginfo==1.5.0.1",
+  "pypdf2[crypto]",
+  "pytesseract>=0.3.5",
+  "python-magic",
+  "reportlab",
+  "requests>=2.25",
+  "seal-rookery>=2.2.1",
+  "sentry-sdk",
+  "six>=1.15",
+  "urllib3>=1.25.10",
+  "x-ray==0.3.3",
+]
+
+[dependency-groups]
+dev = [
+  "ipython",
+]
 
 [tool.ruff]
 line-length = 79