Merge pull request #21 from bcye/feature/docker

Dockerize

.dockerignore

@@ -1,8 +1,8 @@
 .env
-
-# NODE
-node_modules
-
-# PYTHON
 __pycache__
 .venv
+.pytest_cache
+docs
+node_modules
+output
+sketching

.github/workflows/build-image.yaml

@@ -0,0 +1,33 @@
+name: Build Docker Image
+
+on:
+  push:
+    tags:
+      - "docker/*"
+
+jobs:
+  docker:
+    runs-on: ubuntu-latest
+    permissions:
+      packages: write
+      contents: read
+      id-token: write
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Build and push
+        uses: docker/build-push-action@v6
+        with:
+          push: true
+          tags: ghcr.io/bcye/structured-wikivoyage-exports:latest

Dockerfile

@@ -1,12 +1,10 @@
-FROM node:22
+FROM ghcr.io/astral-sh/uv:0.6-python3.12-bookworm
 
 WORKDIR /app
 
-COPY package.json .
-COPY package-lock.json .
+COPY pyproject.toml uv.lock ./
+RUN uv sync --frozen
 
-RUN npm install
+COPY . .
 
-COPY index.ts .
-
-CMD [ "node", "--max-old-space-size=4096", "--experimental-strip-types", "index.ts" ]
+CMD ["uv", "run", "main.py"]

README.md

@@ -2,7 +2,15 @@
 
 Small utility to convert the wikitext data from the Wikivoyage dumps into a structured format. The goal is to make it easier to work with the data and extract useful information programmatically.
 
-## Installation
+## Usage
+
+### Docker
+
+This script is intended to be run with docker. A docker image is [available from the GitHub registry](https://github.com/bcye/structured-wikivoyage-exports/pkgs/container/structured-wikivoyage-exports). For example, you may run it using the filesystem handler with `docker run -e HANDLER=filesystem -e HANDLER_FILESYSTEM_OUTPUT_DIR=/output -v ./output:/output --ulimit nofile=65536:65536 ghcr.io/bcye/structured-wikivoyage-exports`. For all the different options, refer to [the docs](docs).
+
+### Types
+
+TypeScript types for consuming the json output are available, you may install them from the [@bcye/structured-wikivoyage-types](https://www.npmjs.com/package/@bcye/structured-wikivoyage-types) npm package. Refer to the included docstrings in [types/index.d.ts](types/index.d.ts) for reference.
 
 ## Documentation
 
@@ -22,4 +30,4 @@ All code and documentation unless otherwise stated is licensed under the AGPLv3
 
 ### Examples
 
-Files in the `docs/example` and `tests/fixtures` are copies (.txt) or derivatives (.json) of the Boston Article on Wikivoyage and licensed under CC BY-SA 4.0. A [list of contributors is available on the original article](https://en.wikivoyage.org/w/index.php?title=Boston&action=history).
+Files in the `docs/example` and `tests/fixtures` are copies (.txt) or derivatives (.json) of the Boston Article on Wikivoyage and licensed under CC BY-SA 4.0. A [list of contributors is available on the original article](https://en.wikivoyage.org/w/index.php?title=Boston&action=history).