From c69a5fa1c978c24369432377d8428816c3820fab Mon Sep 17 00:00:00 2001
From: erinhmclark <erinhannahmary.clark@gmail.com>
Date: Sun, 12 Jan 2025 12:38:12 +0000
Subject: [PATCH] Refactor Dockerfile for multi-stage builds.

Combining environment and runtime stages due to Poetry's dependency on source code.
---
 Dockerfile | 42 ++++++++++++++++++++++++++++++++----------
 1 file changed, 32 insertions(+), 10 deletions(-)

diff --git a/Dockerfile b/Dockerfile
index d7ca54a..b1c4bd0 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -1,10 +1,13 @@
-FROM webrecorder/browsertrix-crawler:1.0.4
+FROM webrecorder/browsertrix-crawler:1.0.4 AS base
 
-ENV RUNNING_IN_DOCKER=1
-ENV PATH="/usr/local/bin:/root/.local/bin:$PATH"
-
-WORKDIR /app
+ENV RUNNING_IN_DOCKER=1 \
+    LANG=C.UTF-8 \
+    LC_ALL=C.UTF-8 \
+    PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONFAULTHANDLER=1 \
+    PATH="/root/.local/bin:$PATH"
 
+# Installing system dependencies
 RUN add-apt-repository ppa:mozillateam/ppa && \
 	apt-get update && \
     apt-get install -y --no-install-recommends gcc ffmpeg fonts-noto exiftool && \
@@ -17,20 +20,39 @@ RUN add-apt-repository ppa:mozillateam/ppa && \
     apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 
+
+# Poetry and runtime
+FROM base AS runtime
+
+ENV POETRY_NO_INTERACTION=1 \
+    POETRY_VIRTUALENVS_IN_PROJECT=1 \
+    POETRY_VIRTUALENVS_CREATE=1
+
+
 RUN pip install --upgrade pip && \
     pip install "poetry>=2.0.0"
 
+WORKDIR /app
+
+
 COPY pyproject.toml poetry.lock README.md ./
+# Copy dependency files and install dependencies (excluding the package itself)
+RUN poetry install --only main --no-root --no-cache
 
-# doing this at the end helps during development, builds are quick
+
+# Copy code: This is needed for poetry to install the package itself,
+# but the environment should be cached from the previous step if toml and lock files haven't changed
 COPY ./src/ .
-
-# Verify Poetry installation and install dependencies
-RUN poetry install
+RUN poetry install --only main --no-cache
 
 
-ENTRYPOINT ["poetry", "run", "python3", "-m", "auto_archiver"]
+# Update PATH to include virtual environment binaries
+# Allowing entry point to run the application directly with Python
+ENV VIRTUAL_ENV=/app/.venv \
+    PATH="/app/.venv/bin:$PATH"
 
+ENTRYPOINT ["python3", "-m", "auto_archiver"]
 
 # should be executed with 2 volumes (3 if local_storage is used)
 # docker run --rm -v $PWD/secrets:/app/secrets -v $PWD/local_archive:/app/local_archive aa pipenv run python3 -m auto_archiver --config secrets/orchestration.yaml
+