//! Backups (docs/backups.md, oxygenhub#169), end to end: a real `oxy` push, //! a backup to a directory, a second run that sends nothing new, and a //! restore into a fresh hub that gives back the same repository, byte for //! byte; and an owner's backup never holding another's repositories. use oxy_core::repo::Repo; use oxygenhub::backups::{self, Destination, Directory, Setting}; use oxygenhub::config::Config; use oxygenhub::repos::RepoName; use oxygenhub::{db, Shared}; use std::path::Path; use std::sync::Arc; fn hermetic() { static ONCE: std::sync::Once = std::sync::Once::new(); static DIR: std::sync::OnceLock = std::sync::OnceLock::new(); ONCE.call_once(|| { let d = tempfile::tempdir().unwrap(); std::env::set_var("OXY_HOME", d.path()); DIR.set(d).ok(); }); } struct Hub { app: Shared, base: String, _dir: tempfile::TempDir, } async fn hub(backups: &Path) -> Hub { hub_with(backups, None).await } async fn hub_with(backups: &Path, google: Option<&str>) -> Hub { hermetic(); let dir = tempfile::tempdir().unwrap(); let mut config = Config::load(dir.path()).unwrap(); config.auth.push_tokens = vec!["site".into()]; config.backups.directories = vec![backups.to_path_buf()]; if let Some(g) = google { config.backups.sts_url = g.to_string(); config.backups.storage_url = g.to_string(); } let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap(); let port = listener.local_addr().unwrap().port(); config.server.base_url = format!("http://127.0.0.1:{port}"); let app = oxygenhub::build(config).await.unwrap(); let router = oxygenhub::router(app.clone()); tokio::spawn(async move { axum::serve(listener, router).await.unwrap() }); Hub { app, base: format!("http://127.0.0.1:{port}"), _dir: dir } } fn write(root: &Path, rel: &str, content: &str) { let p = root.join(rel); std::fs::create_dir_all(p.parent().unwrap()).unwrap(); std::fs::write(p, content).unwrap(); } async fn create(app: &Shared, owner: &str, name: &str, visibility: hub_api::Visibility) { app.repos.create(&RepoName::parse(&format!("{owner}/{name}")).unwrap(), None).unwrap(); db::repos::create(&app.db, owner, name, "a demo", visibility).await.unwrap(); } fn push(url: &str, work: &Path, files: &[(&str, &str)]) { let mut c = Repo::init(work).unwrap(); c.config.set("remote.origin.url", url).unwrap(); c.config.set("remote.origin.token", "site").unwrap(); c.save_config().unwrap(); for (f, t) in files { write(work, f, t); } c.snapshot("t").unwrap(); c.commit("Some work", &[]).unwrap(); assert!(c.push("origin", false).unwrap().iter().all(|r| r.ok)); } /// Every file under `dir`, with its bytes. fn files(dir: &Path) -> Vec<(String, Vec)> { let mut out = Vec::new(); let mut stack = vec![dir.to_path_buf()]; while let Some(d) = stack.pop() { for e in std::fs::read_dir(&d).unwrap().flatten() { let p = e.path(); if p.is_dir() { stack.push(p); } else { out.push((p.strip_prefix(dir).unwrap().to_string_lossy().into_owned(), std::fs::read(&p).unwrap())); } } } out.sort(); out } #[tokio::test(flavor = "multi_thread")] async fn a_backup_restores_the_same_repository_and_sends_only_what_changed() { let store = tempfile::tempdir().unwrap(); let h = hub(store.path()).await; db::accounts::create_account(&h.app.db, "andy", "a@example.com", "x", "salt", false).await.unwrap(); db::accounts::create_account(&h.app.db, "bob", "b@example.com", "x", "salt", false).await.unwrap(); create(&h.app, "andy", "demo", hub_api::Visibility::Private).await; create(&h.app, "bob", "other", hub_api::Visibility::Public).await; let work = tempfile::tempdir().unwrap(); push(&format!("{}/andy/demo", h.base), work.path(), &[("README.md", "hello\n"), ("src/main.rs", "fn main() {}\n")]); let other = tempfile::tempdir().unwrap(); push(&format!("{}/bob/other", h.base), other.path(), &[("x.txt", "bob's\n")]); // Andy backs up to the directory the hub allows. let target = store.path().display().to_string(); let mut s = Setting::off("andy", "user"); s.every = "hourly".into(); s.target = target.clone(); backups::save(&h.app.db, &s).await.unwrap(); let first = backups::run(&h.app, "andy", "now").await.unwrap(); assert_eq!((first.status.as_str(), first.repos), ("ok", 1), "{}", first.detail); assert!(first.sent > 0 && first.bytes > 0); let dest = Directory { root: store.path().join("andy") }; assert!(dest.exists(&format!("runs/{}/DONE", first.at)).unwrap()); let records: serde_json::Value = serde_json::from_slice(&dest.get(&format!("runs/{}/records/demo.json", first.at)).unwrap()).unwrap(); assert_eq!(records["repositories"][0]["visibility"], "private"); let text = String::from_utf8_lossy(&dest.get(&format!("runs/{}/records/demo.json", first.at)).unwrap()).into_owned(); assert!(!text.contains("bob/other") && !text.contains("\"other\""), "nothing of another owner"); assert!(!store.path().join("bob").exists(), "bob set up no backup"); // Nothing changed: the next run sends nothing new. tokio::time::sleep(std::time::Duration::from_millis(1100)).await; let second = backups::run(&h.app, "andy", "now").await.unwrap(); assert_eq!((second.status.as_str(), second.sent), ("ok", 0), "{}", second.detail); // A fresh hub, restored from the backup, has the same repository. let empty = tempfile::tempdir().unwrap(); let fresh = hub(empty.path()).await; let dest: Arc = Arc::new(Directory { root: store.path().join("andy") }); let done = backups::restore_into_hub(&fresh.app, dest, None).await.unwrap(); assert_eq!(done, vec!["andy/demo (repos)"]); let name = RepoName::parse("andy/demo").unwrap(); assert_eq!(files(&fresh.app.repos.dir(&name)), files(&h.app.repos.dir(&name)), "byte for byte"); let row = db::repos::get(&fresh.app.db, "andy", "demo").await.unwrap().expect("listed on the hub"); assert_eq!((row.visibility.as_str(), row.description.as_str()), ("private", "a demo")); let (a, b) = (h.app.repos.open(&name).unwrap(), fresh.app.repos.open(&name).unwrap()); assert_eq!( a.bookmarks().unwrap().iter().map(|b| b.heads.clone()).collect::>(), b.bookmarks().unwrap().iter().map(|b| b.heads.clone()).collect::>() ); // A directory the hub does not allow is refused. let mut bad = Setting::off("andy", "user"); bad.every = "hourly".into(); bad.target = "/tmp/somewhere-else".into(); backups::save(&h.app.db, &bad).await.unwrap(); let refused = backups::run(&h.app, "andy", "now").await.unwrap(); assert_eq!(refused.status, "failed"); assert!(refused.detail.contains("not a backup directory this hub allows"), "{}", refused.detail); } #[tokio::test(flavor = "multi_thread")] async fn backups_fall_due_on_their_schedule() { let store = tempfile::tempdir().unwrap(); let h = hub(store.path()).await; let mut s = Setting::off("andy", "user"); s.target = store.path().display().to_string(); backups::save(&h.app.db, &s).await.unwrap(); assert!(backups::due(&h.app.db).await.unwrap().is_empty(), "off is never due"); s.every = "hourly".into(); backups::save(&h.app.db, &s).await.unwrap(); assert_eq!(backups::due(&h.app.db).await.unwrap().len(), 1, "never run: due"); sqlx::query("INSERT INTO backup_runs (owner, started_ms, status) VALUES ('andy', ?, 'ok')") .bind(db::now_ms()) .execute(&h.app.db) .await .unwrap(); assert!(backups::due(&h.app.db).await.unwrap().is_empty(), "ran just now"); } // ------------------------------------------------------------ a fake Google /// What the fake has seen and holds. #[derive(Default)] struct Google { /// Objects by bucket and name. objects: std::collections::BTreeMap<(String, String), Vec>, /// The subjects and audiences of the tokens exchanged. exchanged: Vec<(String, String)>, } type Shared2 = Arc>; fn decode(s: &str) -> String { let b = s.as_bytes(); let mut out = Vec::new(); let mut i = 0; while i < b.len() { if b[i] == b'%' && i + 2 < b.len() { out.push(u8::from_str_radix(&s[i + 1..i + 3], 16).unwrap()); i += 3; } else { out.push(b[i]); i += 1; } } String::from_utf8(out).unwrap() } fn query(uri: &axum::http::Uri, key: &str) -> Option { uri.query()?.split('&').find_map(|kv| kv.split_once('=').filter(|(k, _)| *k == key).map(|(_, v)| decode(v))) } /// Google's STS and Cloud Storage, as much as backups use: a token /// exchange that admits `backup:` subjects for the provider's audience, /// and buckets that admit only their owner's token (bucket `OWNER-backup`). async fn fake_google() -> (String, Shared2) { use axum::extract::{Request, State}; use axum::http::StatusCode; use axum::response::IntoResponse; let state: Shared2 = Default::default(); async fn handle(State(g): State, req: Request) -> axum::response::Response { let (parts, body) = req.into_parts(); let bytes = http_body_util::BodyExt::collect(body).await.unwrap().to_bytes(); let path = parts.uri.path().to_string(); if path == "/v1/token" { let v: serde_json::Value = serde_json::from_slice(&bytes).unwrap(); let jwt = v["subjectToken"].as_str().unwrap(); let payload = jwt.split('.').nth(1).unwrap(); let claims: serde_json::Value = serde_json::from_slice(&base64url(payload)).unwrap(); let (sub, aud) = (claims["sub"].as_str().unwrap().to_string(), claims["aud"].as_str().unwrap().to_string()); let provider = v["audience"].as_str().unwrap(); g.lock().unwrap().exchanged.push((sub.clone(), aud.clone())); if !sub.starts_with("backup:") || aud != format!("https:{provider}") { return ( StatusCode::BAD_REQUEST, axum::Json(serde_json::json!({"error": "invalid_grant", "error_description": "not admitted"})), ) .into_response(); } return axum::Json(serde_json::json!({ "access_token": format!("tok-{sub}"), "expires_in": 3600 })).into_response(); } let auth = parts.headers.get("authorization").and_then(|v| v.to_str().ok()).unwrap_or("").to_string(); let segs: Vec<&str> = path.split('/').collect(); // /storage/v1/b/{bucket}/o[/{name}] or /upload/storage/v1/b/{bucket}/o let upload = segs.get(1) == Some(&"upload"); let at = if upload { 5 } else { 4 }; let bucket = segs.get(at).unwrap_or(&"").to_string(); let owner = bucket.trim_end_matches("-backup"); if auth != format!("Bearer tok-backup:{owner}") { return (StatusCode::FORBIDDEN, "caller does not have storage.objects access").into_response(); } let mut g = g.lock().unwrap(); if upload { let name = query(&parts.uri, "name").unwrap(); g.objects.insert((bucket, name), bytes.to_vec()); return axum::Json(serde_json::json!({})).into_response(); } let name = segs.get(at + 2).map(|n| decode(n)); match (parts.method.as_str(), name) { ("GET", Some(n)) => match g.objects.get(&(bucket, n.clone())) { Some(b) if query(&parts.uri, "alt").as_deref() == Some("media") => b.clone().into_response(), Some(_) => axum::Json(serde_json::json!({ "name": n })).into_response(), None => StatusCode::NOT_FOUND.into_response(), }, ("DELETE", Some(n)) => { g.objects.remove(&(bucket, n)); StatusCode::NO_CONTENT.into_response() } ("GET", None) => { let prefix = query(&parts.uri, "prefix").unwrap_or_default(); let delimited = query(&parts.uri, "delimiter").is_some(); let (mut items, mut prefixes) = (Vec::new(), std::collections::BTreeSet::new()); for (b, n) in g.objects.keys() { if *b != bucket || !n.starts_with(&prefix) { continue; } let rest = &n[prefix.len()..]; match rest.find('/') { Some(i) if delimited => { prefixes.insert(format!("{prefix}{}", &rest[..=i])); } _ => items.push(serde_json::json!({ "name": n })), } } axum::Json(serde_json::json!({ "items": items, "prefixes": prefixes })).into_response() } _ => StatusCode::METHOD_NOT_ALLOWED.into_response(), } } let app = axum::Router::new().fallback(handle).with_state(state.clone()); let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap(); let port = listener.local_addr().unwrap().port(); tokio::spawn(async move { axum::serve(listener, app).await.unwrap() }); (format!("http://127.0.0.1:{port}"), state) } fn base64url(s: &str) -> Vec { let table = b"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_"; let mut bits = 0u32; let mut n = 0; let mut out = Vec::new(); for c in s.bytes() { let v = table.iter().position(|t| *t == c).unwrap() as u32; bits = (bits << 6) | v; n += 6; if n >= 8 { n -= 8; out.push((bits >> n) as u8); bits &= (1 << n) - 1; } } out } const PROVIDER: &str = "//iam.googleapis.com/projects/1/locations/global/workloadIdentityPools/oxygenhub/providers/oxygenhub-io"; fn gcs(owner: &str, bucket: &str) -> Setting { let mut s = Setting::off(owner, "user"); s.every = "hourly".into(); s.destination = "gcs".into(); s.target = bucket.into(); s.provider = PROVIDER.into(); s } #[tokio::test(flavor = "multi_thread")] async fn a_gcs_backup_needs_no_key_and_restores_the_same_repository() { let (google, seen) = fake_google().await; let store = tempfile::tempdir().unwrap(); let h = hub_with(store.path(), Some(&google)).await; db::accounts::create_account(&h.app.db, "andy", "a@example.com", "x", "salt", false).await.unwrap(); db::accounts::create_account(&h.app.db, "bob", "b@example.com", "x", "salt", false).await.unwrap(); create(&h.app, "andy", "demo", hub_api::Visibility::Public).await; let work = tempfile::tempdir().unwrap(); push(&format!("{}/andy/demo", h.base), work.path(), &[("README.md", "hello\n")]); backups::save(&h.app.db, &gcs("andy", "andy-backup")).await.unwrap(); let first = backups::run(&h.app, "andy", "now").await.unwrap(); assert_eq!((first.status.as_str(), first.repos), ("ok", 1), "{}", first.detail); { let g = seen.lock().unwrap(); assert!(g.objects.keys().any(|(b, n)| b == "andy-backup" && n == &format!("runs/{}/DONE", first.at))); assert!(g.objects.keys().all(|(b, _)| b == "andy-backup")); let (sub, aud) = g.exchanged.first().unwrap(); assert_eq!( (sub.as_str(), aud.as_str()), ("backup:andy", format!("https:{PROVIDER}").as_str()), "the hub signs in as the owner, for the provider" ); } tokio::time::sleep(std::time::Duration::from_millis(1100)).await; let second = backups::run(&h.app, "andy", "now").await.unwrap(); assert_eq!((second.status.as_str(), second.sent), ("ok", 0), "{}", second.detail); // The probe writes, reads and removes; the bucket is as it was. let before = seen.lock().unwrap().objects.len(); let dest = backups::destination(&h.app, &gcs("andy", "andy-backup")).unwrap(); tokio::task::spawn_blocking(move || backups::probe(dest.as_ref())).await.unwrap().unwrap(); assert_eq!(seen.lock().unwrap().objects.len(), before); // Restored from the bucket into a fresh hub: the same repository. let empty = tempfile::tempdir().unwrap(); let fresh = hub_with(empty.path(), Some(&google)).await; let dest: Arc = backups::destination(&fresh.app, &gcs("andy", "andy-backup")).unwrap().into(); assert_eq!(backups::restore_into_hub(&fresh.app, dest, None).await.unwrap(), vec!["andy/demo (repos)"]); let name = RepoName::parse("andy/demo").unwrap(); assert_eq!(files(&fresh.app.repos.dir(&name)), files(&h.app.repos.dir(&name)), "byte for byte"); // Bob cannot write Andy's bucket: Google refuses his token, and the // run says what to grant. backups::save(&h.app.db, &gcs("bob", "andy-backup")).await.unwrap(); let refused = backups::run(&h.app, "bob", "now").await.unwrap(); assert_eq!(refused.status, "failed"); assert!(refused.detail.contains("roles/storage.objectAdmin") && refused.detail.contains("backup:bob"), "{}", refused.detail); }