Implement RDS snapshot sanitizer

.github/workflows/workflow.yml

@@ -0,0 +1,51 @@
+name: Create and publish a Docker image
+
+on:
+  release:
+    types: [published]
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+jobs:
+  build-and-push-image:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+      attestations: write
+      id-token: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Log in to the Container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+
+      - name: Build and push Docker image
+        id: push
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+
+      - name: Generate artifact attestation
+        uses: actions/attest-build-provenance@v2
+        with:
+          subject-name: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME}}
+          subject-digest: ${{ steps.push.outputs.digest }}
+          push-to-registry: true
+

.gitignore

@@ -0,0 +1,5 @@
+.venv
+.envrc
+
+__pycache__/
+hardcode.py

.pre-commit-config.yaml

@@ -0,0 +1,7 @@
+repos:
+  - repo: https://github.com/charliermarsh/ruff-pre-commit
+    rev: v0.11.0
+    hooks:
+      - id: ruff
+        args: [--fix]
+      - id: ruff-format

Dockerfile

@@ -0,0 +1,22 @@
+FROM python:3.13.2-alpine
+
+WORKDIR /app
+
+COPY poetry.lock pyproject.toml /app/
+COPY src/ /app/src
+
+RUN apk update \
+    && apk upgrade --no-cache \
+    && apk add --no-cache --virtual build-dependencies build-base curl \
+    && pip install --no-cache-dir --upgrade pip setuptools wheel \
+    && curl -sSL https://install.python-poetry.org | POETRY_HOME=/etc/poetry python - \
+    && ln -s /etc/poetry/bin/poetry /usr/local/bin/poetry \
+    && poetry run pip install --upgrade pip setuptools wheel \
+    && MAKEFLAGS="-j" poetry install \
+    && poetry run python -m compileall -j 0 src \
+    && rm -rf /root/.cache/pip \
+    && rm -rf /root/.cache/pypoetry/artifacts /root/.cache/pypoetry/cache \
+    && rm -rf /etc/poetry/lib/poetry/_vendor/py3.13 \
+    && apk del --no-cache build-dependencies
+
+ENTRYPOINT ["poetry", "run", "sanitizer"]

README.md

@@ -1 +1,33 @@
 # rds-snapshot-sanitizer
+
+Create sanitized copy of RDS snapshots and share them with selected accounts.
+
+It works by restoring an unsanitized snapshot to a temporary cluster and executing sanitizing SQL queries against it, after which sanitized snapshot will be created and optionally shared with other accounts.
+
+# Environment variable
+- `SANITIZER_RDS_CLUSTER_ID`: RDS cluster identifier whose snapshots will be sanitized.
+- `SANITIZER_CONFIG`: rds-snapshot-sanitizer configuration in JSON. See [Configuration](#configuration).
+- `SANTITIZER_RDS_INSTANCE_ACU`: (Optional) ACU to be allocatted for the temporary RDS instance. Defaults to 2 ACU.
+- `SANITIZER_SQL_MAX_CONNECTIONS`: (Optional) Number of maximum connections to be created for executing the SQL queries. Defaults to 20.
+- `SANITIZER_SHARE_KMS_KEY_ID`: (Optional) KMS key identifier to be used for the sanitized snapshot.
+- `SANITIZER_SHARE_ACCOUNT_IDS`: (Optional) List of AWS account ids to share the sanitized snapshot with.
+- `SANITIZER_AWS_REGION`: (Optional) AWS region where the RDS cluster is hosted. Defaults to `AWS_REGION` or `AWS_DEFAULT_REGION` environment variable.
+- `SANITIZER_DELETE_OLD_SNAPSHOTS`: (Optional) Whether to delete old snapshots. Defaults to False.
+- `SANITIZER_OLD_SNAPSHOT_DAYS`: (Optional) Number of days for a snapshot to be considered old. Defaults to 30.
+
+# Configuration
+The configuration is a JSON file with the following schema:
+- `"tables"`: list of table configuration
+  - `"name"`: name of the table
+  - `"columns"`: list of column configuration
+    - `"name"`: name of the column
+    - `"sanitizer"`: type of sanitizer to be used. There are two types provided, static and random.
+      - `"type"`: `"static"`
+      - `"value"`: a static string value to be used for replacement.
+
+      OR
+
+      - `"type"`: `"random"`
+      - `"kind"`: `"name"`, `"first_name"`, `"last_name"`, `"user_name"`, `"email"`, `"phone_number"`, etc. See the full list of [randomizer](https://faker.readthedocs.io/en/master/providers.html).
+  - `"drop_constraints"`: list of table constraints to be dropped
+- `"drop_indexes"`: list of index to be dropped