1
Fork 0
mirror of https://github.com/thegeneralist01/archivr synced 2026-07-22 03:05:32 +02:00

fix: address code review issues with Docker setup

- .gitignore: whitelist Dockerfile, docker-compose.yml, docker/ so they
  are actually tracked (the * catch-all was silently dropping them)
- Dockerfile: build and ship the archivr CLI alongside archivr-server so
  users can run `archivr init` inside the container on first setup
- docker/config.example.toml: fix archive_path to point at the .archivr
  subdirectory that archivr init creates (not the parent directory), which
  is what read_archive_paths expects
- docs/README.md: replace the bare mkdir quickstart step with
  `archivr init`, explain why mkdir is insufficient; add a callout that
  auth_db_path must be set explicitly to a writable path when the config
  mount is read-only
This commit is contained in:
TheGeneralist 2026-06-30 11:20:55 +02:00
parent 2ba832ad59
commit 38d3066ee4
Signed by: thegeneralist01
SSH key fingerprint: SHA256:pp9qddbCNmVNoSjevdvQvM5z0DHN7LTa8qBMbcMq/R4
5 changed files with 170 additions and 3 deletions

97
Dockerfile Normal file
View file

@ -0,0 +1,97 @@
# syntax=docker/dockerfile:1
###############################################################################
# Stage 1 Build the Rust server and CLI binaries
###############################################################################
FROM rust:1.87-slim-bookworm AS builder
RUN apt-get update && apt-get install -y --no-install-recommends \
pkg-config \
libssl-dev \
&& rm -rf /var/lib/apt/lists/*
WORKDIR /build
# Layer the dependency build separately for better cache reuse.
# Stub out every crate so Cargo can resolve and compile all dependencies
# before we copy the real source.
COPY Cargo.toml Cargo.lock ./
COPY crates/archivr-core/Cargo.toml crates/archivr-core/Cargo.toml
COPY crates/archivr-server/Cargo.toml crates/archivr-server/Cargo.toml
COPY crates/archivr-cli/Cargo.toml crates/archivr-cli/Cargo.toml
RUN mkdir -p \
crates/archivr-core/src \
crates/archivr-server/src \
crates/archivr-cli/src \
&& touch crates/archivr-core/src/lib.rs \
&& echo 'fn main() {}' > crates/archivr-server/src/main.rs \
&& echo 'fn main() {}' > crates/archivr-cli/src/main.rs \
&& cargo build --release -p archivr-server -p archivr-cli || true
# Build the real binaries; touch source files to force Cargo to relink.
COPY crates/ crates/
RUN touch \
crates/archivr-core/src/lib.rs \
crates/archivr-server/src/main.rs \
crates/archivr-cli/src/main.rs \
&& cargo build --release -p archivr-server -p archivr-cli
###############################################################################
# Stage 2 Runtime image
###############################################################################
FROM debian:bookworm-slim
# Runtime dependencies:
# chromium used by single-file-cli for full-page archiving
# nodejs + npm runtime for single-file-cli
# python3 + pip + venv twitter scraper
# ca-certificates outbound HTTPS from the server
# libssl3 OpenSSL linked by the Rust binary
RUN apt-get update && apt-get install -y --no-install-recommends \
chromium \
nodejs \
npm \
python3 \
python3-pip \
python3-venv \
ca-certificates \
libssl3 \
&& rm -rf /var/lib/apt/lists/*
# Install single-file-cli globally so `single-file` is on PATH.
RUN npm install -g single-file-cli
# Install yt-dlp and twitter-api-client into an isolated venv to avoid
# conflicts with Debian's system Python packages.
RUN python3 -m venv /opt/archivr-venv \
&& /opt/archivr-venv/bin/pip install --no-cache-dir \
yt-dlp \
twitter-api-client
# Server and CLI binaries (CLI is needed to run `archivr init` on first setup)
COPY --from=builder /build/target/release/archivr-server /usr/local/bin/archivr-server
COPY --from=builder /build/target/release/archivr /usr/local/bin/archivr
# Pre-built frontend assets (already compiled; no Vite build step needed)
COPY crates/archivr-server/static/ /usr/share/archivr-server/static/
# Twitter scraper script
COPY vendor/twitter/scrape_user_tweet_contents.py \
/usr/local/lib/archivr/scrape_user_tweet_contents.py
# Wire up env vars that the server (and archivr-core) read at runtime.
# ARCHIVR_BIND and ARCHIVR_TWITTER_CREDENTIALS_FILE are intentionally left
# unset here — set them in docker-compose.yml or at `docker run` time.
ENV ARCHIVR_STATIC_DIR=/usr/share/archivr-server/static \
ARCHIVR_CHROME=/usr/bin/chromium \
ARCHIVR_SINGLE_FILE=/usr/local/bin/single-file \
ARCHIVR_TWEET_PYTHON=/opt/archivr-venv/bin/python3 \
ARCHIVR_TWEET_SCRAPER=/usr/local/lib/archivr/scrape_user_tweet_contents.py \
ARCHIVR_YT_DLP=/opt/archivr-venv/bin/yt-dlp
EXPOSE 8080
# Expects the TOML config at /config/archivr-server.toml (mount a volume).
# Copy docker/config.example.toml as a starting point.
ENTRYPOINT ["archivr-server", "/config/archivr-server.toml"]