EventSnap/backend/src/main.rs

use anyhow::Result;
use axum::extract::DefaultBodyLimit;
use axum::routing::{delete, get, patch, post};
use axum::Router;
use tower_http::services::ServeDir;
use tower_http::trace::TraceLayer;
use tracing_subscriber::{layer::SubscriberExt, util::SubscriberInitExt};

mod auth;
mod config;
mod db;
mod error;
mod handlers;
mod models;
mod services;
mod state;

use config::AppConfig;
use state::AppState;

/// Hard HTTP body cap for the upload endpoint (576 MiB). Backstop against
/// memory-exhaustion; precise per-class size limits are enforced in the handler.
const MAX_UPLOAD_BYTES: usize = 576 * 1024 * 1024;

#[tokio::main]
async fn main() -> Result<()> {
    dotenvy::dotenv().ok();

    tracing_subscriber::registry()
        .with(tracing_subscriber::EnvFilter::try_from_default_env().unwrap_or_else(|_| {
            "eventsnap_backend=debug,tower_http=debug".into()
        }))
        .with(tracing_subscriber::fmt::layer())
        .init();

    let config = AppConfig::from_env()?;
    let pool = db::create_pool(&config.database_url).await?;

    // Reset any rows left mid-flight by a previous (possibly crashed) instance —
    // stuck `compression_status='processing'` uploads and `status='running'` export
    // jobs. Must run before the server starts taking requests so clients never see
    // the half-state.
    services::maintenance::startup_recovery(&pool).await;

    let state = AppState::new(pool.clone(), config.clone());

    // Re-spawn exports for events that were released but whose keepsake never finished
    // (crash mid-export). Needs the media/export paths + SSE sender, so it runs here
    // rather than inside `startup_recovery`. Fire-and-forget: the workers run in the
    // background; the HTTP server can start accepting requests meanwhile.
    services::export::recover_exports(
        pool.clone(),
        config.media_path.clone(),
        config.export_path.clone(),
        state.sse_tx.clone(),
    )
    .await;

    // Hourly background hygiene: prune expired sessions, evict cold rate-limiter
    // keys. Keeps the DB and process from growing unboundedly over multi-day events.
    services::maintenance::spawn_periodic_tasks(
        pool,
        state.rate_limiter.clone(),
        state.sse_tickets.clone(),
    );

    // Ensure media directories exist
    tokio::fs::create_dir_all(&config.media_path).await.ok();

    let api = Router::new()
        // Auth
        .route("/api/v1/event", get(handlers::public::get_public_event))
        .route("/api/v1/join", post(auth::handlers::join))
        .route("/api/v1/recover", post(auth::handlers::recover))
        // Forgotten-PIN escape hatch: ask a host to reset it (unauthenticated, throttled).
        .route("/api/v1/recover/request", post(auth::handlers::request_pin_reset))
        .route("/api/v1/admin/login", post(auth::handlers::admin_login))
        .route("/api/v1/session", delete(auth::handlers::logout))
        // "Sign out everywhere" — revoke all of the caller's sessions.
        .route("/api/v1/sessions", delete(auth::handlers::logout_all))
        // Upload — HTTP-level body cap as an OOM backstop. The handler still enforces
        // the precise per-class limits from DB config (max_image/video_size_mb); this
        // layer just stops a multi-GB body from being buffered into memory before that
        // check runs. Sized generously above the default 500 MB video limit + multipart
        // overhead — if an admin raises max_video_size_mb above this, bump MAX_UPLOAD_BYTES.
        .route("/api/v1/upload", post(handlers::upload::upload)
            .route_layer(DefaultBodyLimit::max(MAX_UPLOAD_BYTES)))
        .route(
            "/api/v1/upload/{id}",
            patch(handlers::upload::edit_upload).delete(handlers::upload::delete_upload),
        )
        .route(
            "/api/v1/upload/{id}/original",
            get(handlers::upload::get_original),
        )
        // Preview/thumbnail variants are gated the same way as originals (visibility
        // check + direct /media block below) so moderation actually revokes access to
        // the displayed images, not just the full-res download.
        .route(
            "/api/v1/upload/{id}/preview",
            get(handlers::upload::get_preview),
        )
        .route(
            "/api/v1/upload/{id}/thumbnail",
            get(handlers::upload::get_thumbnail),
        )
        // Current-user endpoints (live quota estimate, profile + privacy note bundle)
        .route("/api/v1/me/context", get(handlers::me::get_context))
        .route("/api/v1/me/quota", get(handlers::me::get_quota))
        // Feed
        .route("/api/v1/feed", get(handlers::feed::feed))
        .route("/api/v1/feed/delta", get(handlers::feed::feed_delta))
        .route("/api/v1/hashtags", get(handlers::feed::hashtags))
        // Social
        .route("/api/v1/upload/{id}/like", post(handlers::social::toggle_like))
        .route(
            "/api/v1/upload/{id}/comments",
            get(handlers::social::list_comments).post(handlers::social::add_comment),
        )
        .route("/api/v1/comment/{id}", delete(handlers::social::delete_comment))
        // SSE
        .route("/api/v1/stream", get(handlers::sse::stream))
        .route("/api/v1/stream/ticket", post(handlers::sse::issue_ticket))
        // Host Dashboard
        .route("/api/v1/host/event", get(handlers::host::get_event_status))
        .route("/api/v1/host/event/close", post(handlers::host::close_event))
        .route("/api/v1/host/event/open", post(handlers::host::open_event))
        .route("/api/v1/host/gallery/release", post(handlers::host::release_gallery))
        // Escape hatch: force a keepsake rebuild. Without it a failed export is terminal at runtime
        // (release_gallery refuses an already-released event; recovery only runs at boot).
        .route("/api/v1/host/export/rebuild", post(handlers::host::rebuild_export))
        .route("/api/v1/host/users", get(handlers::host::list_users))
        .route("/api/v1/host/users/{id}/ban", post(handlers::host::ban_user))
        .route("/api/v1/host/users/{id}/unban", post(handlers::host::unban_user))
        .route("/api/v1/host/users/{id}/role", patch(handlers::host::set_role))
        .route(
            "/api/v1/host/users/{id}/pin-reset",
            post(handlers::host::reset_user_pin),
        )
        .route(
            "/api/v1/host/pin-reset-requests",
            get(handlers::host::list_pin_reset_requests),
        )
        .route(
            "/api/v1/host/pin-reset-requests/{id}",
            delete(handlers::host::dismiss_pin_reset_request),
        )
        .route("/api/v1/host/upload/{id}", delete(handlers::host::host_delete_upload))
        .route("/api/v1/host/comment/{id}", delete(handlers::host::host_delete_comment))
        // Export (all authenticated users)
        .route("/api/v1/export/status", get(handlers::admin::export_status))
        .route("/api/v1/export/ticket", post(handlers::admin::export_ticket))
        .route("/api/v1/export/zip", get(handlers::admin::download_zip))
        .route("/api/v1/export/html", get(handlers::admin::download_html))
        // Admin Dashboard
        .route("/api/v1/admin/stats", get(handlers::admin::get_stats))
        .route(
            "/api/v1/admin/config",
            get(handlers::admin::get_config).patch(handlers::admin::patch_config),
        )
        .route("/api/v1/admin/export/jobs", get(handlers::admin::get_export_jobs));

    // Test-only route: a hard reset for the Playwright E2E harness. The handler
    // is compiled in always, but the route is only attached when
    // `EVENTSNAP_TEST_MODE=1`. In production the call returns 404 — the route
    // simply isn't there.
    let api = if handlers::test_admin::is_test_mode() {
        tracing::warn!(
            "EVENTSNAP_TEST_MODE=1 — registering /api/v1/admin/__truncate. \
             DO NOT enable this in production."
        );
        api.route(
            "/api/v1/admin/__truncate",
            post(handlers::test_admin::truncate_all),
        )
    } else {
        api
    };

    // Serve media files from disk
    let media_service = ServeDir::new(&config.media_path);

    let router = Router::new()
        .route("/health", get(|| async { "ok" }))
        .merge(api)
        // Block direct HTTP access to ALL media subtrees. The files live under
        // `media_path` (so the compression worker and export can read them off disk) but
        // must NOT be pullable straight from `/media/**` — that bypasses the visibility
        // checks (soft-delete + ban-hide) in the gated handlers. Every legitimate fetch
        // goes through `/api/v1/upload/{id}/{original,preview,thumbnail}`, which filter
        // via `find_visible_media`. The more specific nests take precedence over the
        // `/media` ServeDir below (which, with all three subtrees blocked, now serves
        // nothing — kept as a backstop).
        .nest_service(
            "/media/originals",
            get(|| async { axum::http::StatusCode::NOT_FOUND }),
        )
        .nest_service(
            "/media/previews",
            get(|| async { axum::http::StatusCode::NOT_FOUND }),
        )
        .nest_service(
            "/media/thumbnails",
            get(|| async { axum::http::StatusCode::NOT_FOUND }),
        )
        .nest_service("/media", media_service)
        .layer(TraceLayer::new_for_http())
        .with_state(state);

    let listener = tokio::net::TcpListener::bind(("0.0.0.0", config.app_port)).await?;
    tracing::info!("listening on {}", listener.local_addr()?);
    axum::serve(listener, router)
        .with_graceful_shutdown(shutdown_signal())
        .await?;

    Ok(())
}

/// Hard cap on how long we wait for in-flight connections to drain after a shutdown
/// signal. Uploads (streamed to disk) finish in well under this; the cap exists because
/// long-lived SSE streams never end on their own and would otherwise keep the graceful
/// drain — and thus the process — pending until the orchestrator force-kills it.
const SHUTDOWN_GRACE: std::time::Duration = std::time::Duration::from_secs(10);

/// Resolves on SIGINT (Ctrl-C) or SIGTERM (container stop / deploy). Letting
/// `axum::serve` drain in-flight requests on this signal means a redeploy no longer
/// truncates uploads mid-flight; any background compression/export half-states that a
/// hard kill would leave are already reconciled by `startup_recovery` on the next boot.
///
/// Once the signal fires we also arm a detached backstop that force-exits after
/// [`SHUTDOWN_GRACE`]. Without it, open SSE streams (which have no natural end) would
/// hold the graceful drain open indefinitely; the backstop bounds shutdown regardless
/// of the orchestrator's own kill timeout. If the drain completes first, `main` returns
/// and the process exits before the timer ever fires.
async fn shutdown_signal() {
    let ctrl_c = async {
        let _ = tokio::signal::ctrl_c().await;
    };

    #[cfg(unix)]
    let terminate = async {
        match tokio::signal::unix::signal(tokio::signal::unix::SignalKind::terminate()) {
            Ok(mut sig) => {
                sig.recv().await;
            }
            Err(e) => {
                tracing::warn!(error = ?e, "failed to install SIGTERM handler");
                // Never resolve — fall back to ctrl_c only.
                std::future::pending::<()>().await;
            }
        }
    };

    #[cfg(not(unix))]
    let terminate = std::future::pending::<()>();

    tokio::select! {
        _ = ctrl_c => {}
        _ = terminate => {}
    }

    tracing::info!(
        "shutdown signal received, draining in-flight requests (max {}s)",
        SHUTDOWN_GRACE.as_secs()
    );

    // Backstop: if the graceful drain is still blocked after the grace window (almost
    // always because SSE streams are still open), exit anyway so deploys aren't stalled.
    tokio::spawn(async {
        tokio::time::sleep(SHUTDOWN_GRACE).await;
        tracing::warn!(
            "graceful drain exceeded {}s (likely open SSE streams); forcing exit",
            SHUTDOWN_GRACE.as_secs()
        );
        std::process::exit(0);
    });
}