fix: address second round of Docker review issues

Chromium sandbox (P2):
- singlefile.rs: add ARCHIVR_CHROME_ARGS env var (space-separated flags
  appended to Chromium's --browser-args JSON array); Dockerfile sets it
  to --no-sandbox because Chromium refuses to start as root without it

Store-path outside volume (P1):
- README: pass explicit absolute store-path as the second positional arg
  to `archivr init` so the blob store lands on /data instead of the
  container layer (CLI default is ./.archivr/store, resolved from cwd,
  which is / with no WORKDIR set)

ENTRYPOINT vs CMD (P2):
- Dockerfile: switch from ENTRYPOINT to CMD so `docker compose run
  archivr archivr init …` overrides the full command instead of being
  appended to the server invocation

ffmpeg missing (P2):
- Dockerfile: add ffmpeg to the apt-get install block (required by
  yt-dlp --merge-output-format mp4 for bestvideo+bestaudio streams)

Node version (P2):
- Dockerfile: replace Debian bookworm's nodejs (18.x) with Node 20 via
  the NodeSource setup script (single-file-cli declares engines.node >=20)

Build context secrets (P2):
- Add .dockerignore excluding config/ and docker/ from the build context
  so runtime secrets (e.g. twitter-cookies.txt) are never sent to the builder
- Whitelist .dockerignore in .gitignore

docs:
- README: document ARCHIVR_CHROME_ARGS in the Environment Variables section

.dockerignore

@@ -0,0 +1,9 @@
+# Exclude runtime config and data directories from the Docker build context.
+# The config/ directory may contain secrets (e.g. twitter-cookies.txt) that are
+# only needed at runtime via a volume mount — they must never reach the builder.
+config/
+docker/
+
+# Development and VCS noise
+.git/
+.gitignore

.gitignore

@@ -20,6 +20,7 @@
 !NEXT.md
 
 !Dockerfile
+!.dockerignore
 !docker-compose.yml
 !docker/
 !docker/**

Dockerfile

@@ -44,18 +44,24 @@ FROM debian:bookworm-slim
 
 # Runtime dependencies:
 #   chromium              used by single-file-cli for full-page archiving
-#   nodejs + npm          runtime for single-file-cli
+#   nodejs (20+)          runtime for single-file-cli (requires Node >=20; Debian
+#                         bookworm ships 18, so we install from the NodeSource repo)
+#   ffmpeg                required by yt-dlp to merge separate audio/video streams
+#                         (e.g. YouTube bestvideo+bestaudio format selection)
 #   python3 + pip + venv  twitter scraper
-#   ca-certificates       outbound HTTPS from the server
+#   ca-certificates       outbound HTTPS from the server and NodeSource HTTPS
 #   libssl3               OpenSSL linked by the Rust binary
 RUN apt-get update && apt-get install -y --no-install-recommends \
+    curl \
+    ca-certificates \
+    && curl -fsSL https://deb.nodesource.com/setup_20.x | bash - \
+    && apt-get install -y --no-install-recommends \
     chromium \
     nodejs \
-    npm \
+    ffmpeg \
     python3 \
     python3-pip \
     python3-venv \
-    ca-certificates \
     libssl3 \
     && rm -rf /var/lib/apt/lists/*
 
@@ -88,10 +94,13 @@ ENV ARCHIVR_STATIC_DIR=/usr/share/archivr-server/static \
     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
+    ARCHIVR_YT_DLP=/opt/archivr-venv/bin/yt-dlp \
+    ARCHIVR_CHROME_ARGS=--no-sandbox
 
 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"]
+# Using CMD (not ENTRYPOINT) so `docker compose run archivr archivr init …`
+# can override the whole command for first-time archive initialisation.
+CMD ["archivr-server", "/config/archivr-server.toml"]

crates/archivr-core/src/downloader/singlefile.rs

@@ -68,10 +68,22 @@ fn save_with(
     // without a writable user-data-dir. Using a subdirectory of temp_dir
     // keeps it isolated and it gets cleaned up with the rest of the temp dir.
     let chrome_data_dir = temp_dir.join("chrome-data");
-    let browser_args = format!(
-        "[\"--disable-web-security\",\"--user-data-dir={}\"]",
-        chrome_data_dir.display()
-    );
+    // Build the browser-args JSON array. Start with the flags always required,
+    // then append any extra flags from ARCHIVR_CHROME_ARGS (space-separated).
+    // Docker containers running as root need "--no-sandbox" here because
+    // Chromium refuses to start as root without it.
+    let mut chrome_flags = vec![
+        "--disable-web-security".to_string(),
+        format!("--user-data-dir={}", chrome_data_dir.display()),
+    ];
+    if let Ok(extra) = std::env::var("ARCHIVR_CHROME_ARGS") {
+        chrome_flags.extend(extra.split_whitespace().filter(|s| !s.is_empty()).map(str::to_string));
+    }
+    let quoted: Vec<String> = chrome_flags
+        .iter()
+        .map(|f| format!("\"{}\"", f.replace('\\', "\\\\").replace('"', "\\\"")))
+        .collect();
+    let browser_args = format!("[{}]", quoted.join(","));
 
     let out = Command::new(single_file)
         .arg(url)

docs/README.md

@@ -209,7 +209,7 @@ A `Dockerfile` and `docker-compose.yml` are provided for self-hosting without Ni
    The image includes the `archivr` CLI for this purpose:
 
    ```sh
-   docker compose run --rm archivr archivr init /data/archives/main --name "Main Archive"
+   docker compose run --rm archivr archivr init /data/archives/main /data/archives/main/.archivr/store --name "Main Archive"
    ```
 
    This creates `/data/archives/main/.archivr/` with the metadata the server requires.
@@ -300,6 +300,11 @@ dependencies (Chromium, Node.js, Python) land in the final layer.
 - `ARCHIVR_CHROME`
   - Optional.
   - Overrides the Chromium/Chrome executable passed to `single-file` via `--browser-executable-path`. Set automatically by the Nix wrapper and the Docker image. Default: `chromium`.
+- `ARCHIVR_CHROME_ARGS`
+  - Optional.
+  - Space-separated extra flags appended to Chromium's `--browser-args`. The Docker
+    image sets this to `--no-sandbox` because Chromium refuses to run as root without
+    it. Leave unset when running natively (Nix, Linux desktop).
 - `ARCHIVR_TWITTER_CREDENTIALS_FILE`
   - Required for tweet/thread scraping inputs such as `tweet:ID` and `x:thread:ID`.
   - Must point to a cookies file for the vendored scraper.